Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9973474801061006,
+    "total_flos": 1.0915292825780224e+17,
+    "train_loss": 0.34044326600333263,
+    "train_runtime": 16671.2674,
+    "train_samples_per_second": 2.713,
+    "train_steps_per_second": 0.17
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.51.3"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed47a2a1bdd745859e240ca86f36ada514fff5e2902de178e8e2a8a437ef9e85
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:952b5689d0a622c734d55a3fbee12ac66b73bbc04ff7cf93d5e0772940685d96
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b28cb6a34499ca0da1666388fc0f112b1f3fa5709a95149d8e8d07330e584142
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aecf5dac29337a29a07085a83ebffc4ca81f8f57357400b35ae84672dfe60e83
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 10000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9973474801061006,
+    "total_flos": 1.0915292825780224e+17,
+    "train_loss": 0.34044326600333263,
+    "train_runtime": 16671.2674,
+    "train_samples_per_second": 2.713,
+    "train_steps_per_second": 0.17
+}

trainer_log.jsonl

@@ -0,0 +1,283 @@
+{"current_steps": 10, "total_steps": 2826, "loss": 0.741, "lr": 1.5901060070671379e-07, "epoch": 0.010610079575596816, "percentage": 0.35, "elapsed_time": "0:01:24", "remaining_time": "6:38:39"}
+{"current_steps": 20, "total_steps": 2826, "loss": 0.5551, "lr": 3.356890459363958e-07, "epoch": 0.021220159151193633, "percentage": 0.71, "elapsed_time": "0:02:35", "remaining_time": "6:04:09"}
+{"current_steps": 30, "total_steps": 2826, "loss": 0.6185, "lr": 5.123674911660778e-07, "epoch": 0.03183023872679045, "percentage": 1.06, "elapsed_time": "0:03:35", "remaining_time": "5:34:34"}
+{"current_steps": 40, "total_steps": 2826, "loss": 0.6358, "lr": 6.890459363957598e-07, "epoch": 0.042440318302387266, "percentage": 1.42, "elapsed_time": "0:04:37", "remaining_time": "5:21:39"}
+{"current_steps": 50, "total_steps": 2826, "loss": 0.5922, "lr": 8.657243816254418e-07, "epoch": 0.05305039787798409, "percentage": 1.77, "elapsed_time": "0:05:42", "remaining_time": "5:16:32"}
+{"current_steps": 60, "total_steps": 2826, "loss": 0.6282, "lr": 1.0424028268551239e-06, "epoch": 0.0636604774535809, "percentage": 2.12, "elapsed_time": "0:06:37", "remaining_time": "5:05:32"}
+{"current_steps": 70, "total_steps": 2826, "loss": 0.5836, "lr": 1.2190812720848057e-06, "epoch": 0.07427055702917772, "percentage": 2.48, "elapsed_time": "0:07:33", "remaining_time": "4:57:51"}
+{"current_steps": 80, "total_steps": 2826, "loss": 0.5836, "lr": 1.3957597173144876e-06, "epoch": 0.08488063660477453, "percentage": 2.83, "elapsed_time": "0:08:31", "remaining_time": "4:52:48"}
+{"current_steps": 90, "total_steps": 2826, "loss": 0.4983, "lr": 1.5724381625441699e-06, "epoch": 0.09549071618037135, "percentage": 3.18, "elapsed_time": "0:09:31", "remaining_time": "4:49:33"}
+{"current_steps": 100, "total_steps": 2826, "loss": 0.6057, "lr": 1.7491166077738517e-06, "epoch": 0.10610079575596817, "percentage": 3.54, "elapsed_time": "0:10:27", "remaining_time": "4:44:57"}
+{"current_steps": 110, "total_steps": 2826, "loss": 0.5135, "lr": 1.925795053003534e-06, "epoch": 0.11671087533156499, "percentage": 3.89, "elapsed_time": "0:11:26", "remaining_time": "4:42:35"}
+{"current_steps": 120, "total_steps": 2826, "loss": 0.4844, "lr": 2.1024734982332157e-06, "epoch": 0.1273209549071618, "percentage": 4.25, "elapsed_time": "0:12:26", "remaining_time": "4:40:33"}
+{"current_steps": 130, "total_steps": 2826, "loss": 0.5386, "lr": 2.279151943462898e-06, "epoch": 0.13793103448275862, "percentage": 4.6, "elapsed_time": "0:13:25", "remaining_time": "4:38:25"}
+{"current_steps": 140, "total_steps": 2826, "loss": 0.4774, "lr": 2.45583038869258e-06, "epoch": 0.14854111405835543, "percentage": 4.95, "elapsed_time": "0:14:23", "remaining_time": "4:36:04"}
+{"current_steps": 150, "total_steps": 2826, "loss": 0.5035, "lr": 2.6325088339222617e-06, "epoch": 0.15915119363395225, "percentage": 5.31, "elapsed_time": "0:15:26", "remaining_time": "4:35:28"}
+{"current_steps": 160, "total_steps": 2826, "loss": 0.4897, "lr": 2.8091872791519436e-06, "epoch": 0.16976127320954906, "percentage": 5.66, "elapsed_time": "0:16:22", "remaining_time": "4:32:54"}
+{"current_steps": 170, "total_steps": 2826, "loss": 0.5196, "lr": 2.985865724381626e-06, "epoch": 0.18037135278514588, "percentage": 6.02, "elapsed_time": "0:17:19", "remaining_time": "4:30:33"}
+{"current_steps": 180, "total_steps": 2826, "loss": 0.4791, "lr": 3.162544169611308e-06, "epoch": 0.1909814323607427, "percentage": 6.37, "elapsed_time": "0:18:18", "remaining_time": "4:29:01"}
+{"current_steps": 190, "total_steps": 2826, "loss": 0.5024, "lr": 3.3392226148409896e-06, "epoch": 0.20159151193633953, "percentage": 6.72, "elapsed_time": "0:19:13", "remaining_time": "4:26:38"}
+{"current_steps": 200, "total_steps": 2826, "loss": 0.5781, "lr": 3.5159010600706715e-06, "epoch": 0.21220159151193635, "percentage": 7.08, "elapsed_time": "0:20:10", "remaining_time": "4:25:00"}
+{"current_steps": 210, "total_steps": 2826, "loss": 0.4186, "lr": 3.6925795053003538e-06, "epoch": 0.22281167108753316, "percentage": 7.43, "elapsed_time": "0:21:09", "remaining_time": "4:23:34"}
+{"current_steps": 220, "total_steps": 2826, "loss": 0.4819, "lr": 3.869257950530036e-06, "epoch": 0.23342175066312998, "percentage": 7.78, "elapsed_time": "0:22:04", "remaining_time": "4:21:34"}
+{"current_steps": 230, "total_steps": 2826, "loss": 0.547, "lr": 4.045936395759718e-06, "epoch": 0.2440318302387268, "percentage": 8.14, "elapsed_time": "0:23:02", "remaining_time": "4:20:09"}
+{"current_steps": 240, "total_steps": 2826, "loss": 0.5603, "lr": 4.222614840989399e-06, "epoch": 0.2546419098143236, "percentage": 8.49, "elapsed_time": "0:24:02", "remaining_time": "4:19:07"}
+{"current_steps": 250, "total_steps": 2826, "loss": 0.4483, "lr": 4.399293286219082e-06, "epoch": 0.26525198938992045, "percentage": 8.85, "elapsed_time": "0:25:00", "remaining_time": "4:17:40"}
+{"current_steps": 260, "total_steps": 2826, "loss": 0.5178, "lr": 4.575971731448763e-06, "epoch": 0.27586206896551724, "percentage": 9.2, "elapsed_time": "0:25:55", "remaining_time": "4:15:48"}
+{"current_steps": 270, "total_steps": 2826, "loss": 0.5264, "lr": 4.752650176678445e-06, "epoch": 0.2864721485411141, "percentage": 9.55, "elapsed_time": "0:26:51", "remaining_time": "4:14:15"}
+{"current_steps": 280, "total_steps": 2826, "loss": 0.5124, "lr": 4.929328621908128e-06, "epoch": 0.29708222811671087, "percentage": 9.91, "elapsed_time": "0:27:50", "remaining_time": "4:13:07"}
+{"current_steps": 290, "total_steps": 2826, "loss": 0.4977, "lr": 4.99993132201408e-06, "epoch": 0.3076923076923077, "percentage": 10.26, "elapsed_time": "0:28:47", "remaining_time": "4:11:48"}
+{"current_steps": 300, "total_steps": 2826, "loss": 0.5005, "lr": 4.9995116368759e-06, "epoch": 0.3183023872679045, "percentage": 10.62, "elapsed_time": "0:29:45", "remaining_time": "4:10:29"}
+{"current_steps": 310, "total_steps": 2826, "loss": 0.4857, "lr": 4.998710485009401e-06, "epoch": 0.32891246684350134, "percentage": 10.97, "elapsed_time": "0:30:47", "remaining_time": "4:09:58"}
+{"current_steps": 320, "total_steps": 2826, "loss": 0.4637, "lr": 4.99752798868358e-06, "epoch": 0.3395225464190981, "percentage": 11.32, "elapsed_time": "0:31:44", "remaining_time": "4:08:36"}
+{"current_steps": 330, "total_steps": 2826, "loss": 0.4775, "lr": 4.99596432836689e-06, "epoch": 0.35013262599469497, "percentage": 11.68, "elapsed_time": "0:32:43", "remaining_time": "4:07:30"}
+{"current_steps": 340, "total_steps": 2826, "loss": 0.5779, "lr": 4.994019742699705e-06, "epoch": 0.36074270557029176, "percentage": 12.03, "elapsed_time": "0:33:39", "remaining_time": "4:06:08"}
+{"current_steps": 350, "total_steps": 2826, "loss": 0.5057, "lr": 4.991694528457891e-06, "epoch": 0.3713527851458886, "percentage": 12.38, "elapsed_time": "0:34:37", "remaining_time": "4:05:00"}
+{"current_steps": 360, "total_steps": 2826, "loss": 0.5313, "lr": 4.988989040507518e-06, "epoch": 0.3819628647214854, "percentage": 12.74, "elapsed_time": "0:35:37", "remaining_time": "4:03:59"}
+{"current_steps": 370, "total_steps": 2826, "loss": 0.4441, "lr": 4.985903691750697e-06, "epoch": 0.3925729442970822, "percentage": 13.09, "elapsed_time": "0:36:35", "remaining_time": "4:02:52"}
+{"current_steps": 380, "total_steps": 2826, "loss": 0.4778, "lr": 4.982438953062572e-06, "epoch": 0.40318302387267907, "percentage": 13.45, "elapsed_time": "0:37:33", "remaining_time": "4:01:46"}
+{"current_steps": 390, "total_steps": 2826, "loss": 0.4848, "lr": 4.978595353219449e-06, "epoch": 0.41379310344827586, "percentage": 13.8, "elapsed_time": "0:38:35", "remaining_time": "4:01:01"}
+{"current_steps": 400, "total_steps": 2826, "loss": 0.4891, "lr": 4.974373478818098e-06, "epoch": 0.4244031830238727, "percentage": 14.15, "elapsed_time": "0:39:33", "remaining_time": "3:59:57"}
+{"current_steps": 410, "total_steps": 2826, "loss": 0.4954, "lr": 4.969773974186235e-06, "epoch": 0.4350132625994695, "percentage": 14.51, "elapsed_time": "0:40:32", "remaining_time": "3:58:56"}
+{"current_steps": 420, "total_steps": 2826, "loss": 0.5353, "lr": 4.964797541284175e-06, "epoch": 0.44562334217506633, "percentage": 14.86, "elapsed_time": "0:41:28", "remaining_time": "3:57:35"}
+{"current_steps": 430, "total_steps": 2826, "loss": 0.5726, "lr": 4.959444939597712e-06, "epoch": 0.4562334217506631, "percentage": 15.22, "elapsed_time": "0:42:25", "remaining_time": "3:56:23"}
+{"current_steps": 440, "total_steps": 2826, "loss": 0.5642, "lr": 4.953716986022204e-06, "epoch": 0.46684350132625996, "percentage": 15.57, "elapsed_time": "0:43:24", "remaining_time": "3:55:22"}
+{"current_steps": 450, "total_steps": 2826, "loss": 0.4429, "lr": 4.947614554737904e-06, "epoch": 0.47745358090185674, "percentage": 15.92, "elapsed_time": "0:44:23", "remaining_time": "3:54:23"}
+{"current_steps": 460, "total_steps": 2826, "loss": 0.4683, "lr": 4.941138577076538e-06, "epoch": 0.4880636604774536, "percentage": 16.28, "elapsed_time": "0:45:22", "remaining_time": "3:53:21"}
+{"current_steps": 470, "total_steps": 2826, "loss": 0.4385, "lr": 4.934290041379182e-06, "epoch": 0.4986737400530504, "percentage": 16.63, "elapsed_time": "0:46:24", "remaining_time": "3:52:37"}
+{"current_steps": 480, "total_steps": 2826, "loss": 0.4935, "lr": 4.92706999284541e-06, "epoch": 0.5092838196286472, "percentage": 16.99, "elapsed_time": "0:47:22", "remaining_time": "3:51:32"}
+{"current_steps": 490, "total_steps": 2826, "loss": 0.4548, "lr": 4.9194795333737925e-06, "epoch": 0.519893899204244, "percentage": 17.34, "elapsed_time": "0:48:21", "remaining_time": "3:50:32"}
+{"current_steps": 500, "total_steps": 2826, "loss": 0.5486, "lr": 4.911519821393718e-06, "epoch": 0.5305039787798409, "percentage": 17.69, "elapsed_time": "0:49:21", "remaining_time": "3:49:36"}
+{"current_steps": 510, "total_steps": 2826, "loss": 0.5121, "lr": 4.9031920716886035e-06, "epoch": 0.5411140583554377, "percentage": 18.05, "elapsed_time": "0:50:17", "remaining_time": "3:48:23"}
+{"current_steps": 520, "total_steps": 2826, "loss": 0.4495, "lr": 4.894497555210499e-06, "epoch": 0.5517241379310345, "percentage": 18.4, "elapsed_time": "0:51:16", "remaining_time": "3:47:24"}
+{"current_steps": 530, "total_steps": 2826, "loss": 0.5028, "lr": 4.8854375988861134e-06, "epoch": 0.5623342175066313, "percentage": 18.75, "elapsed_time": "0:52:13", "remaining_time": "3:46:13"}
+{"current_steps": 540, "total_steps": 2826, "loss": 0.5193, "lr": 4.87601358541431e-06, "epoch": 0.5729442970822282, "percentage": 19.11, "elapsed_time": "0:53:09", "remaining_time": "3:45:01"}
+{"current_steps": 550, "total_steps": 2826, "loss": 0.545, "lr": 4.8662269530550825e-06, "epoch": 0.583554376657825, "percentage": 19.46, "elapsed_time": "0:54:07", "remaining_time": "3:43:57"}
+{"current_steps": 560, "total_steps": 2826, "loss": 0.5219, "lr": 4.856079195410046e-06, "epoch": 0.5941644562334217, "percentage": 19.82, "elapsed_time": "0:55:03", "remaining_time": "3:42:48"}
+{"current_steps": 570, "total_steps": 2826, "loss": 0.4725, "lr": 4.845571861194501e-06, "epoch": 0.6047745358090185, "percentage": 20.17, "elapsed_time": "0:56:04", "remaining_time": "3:41:57"}
+{"current_steps": 580, "total_steps": 2826, "loss": 0.4232, "lr": 4.834706554001065e-06, "epoch": 0.6153846153846154, "percentage": 20.52, "elapsed_time": "0:57:04", "remaining_time": "3:41:01"}
+{"current_steps": 590, "total_steps": 2826, "loss": 0.4834, "lr": 4.823484932054937e-06, "epoch": 0.6259946949602122, "percentage": 20.88, "elapsed_time": "0:58:02", "remaining_time": "3:39:58"}
+{"current_steps": 600, "total_steps": 2826, "loss": 0.5302, "lr": 4.811908707960832e-06, "epoch": 0.636604774535809, "percentage": 21.23, "elapsed_time": "0:58:58", "remaining_time": "3:38:46"}
+{"current_steps": 610, "total_steps": 2826, "loss": 0.494, "lr": 4.799979648441602e-06, "epoch": 0.6472148541114059, "percentage": 21.59, "elapsed_time": "0:59:55", "remaining_time": "3:37:40"}
+{"current_steps": 620, "total_steps": 2826, "loss": 0.487, "lr": 4.787699574068611e-06, "epoch": 0.6578249336870027, "percentage": 21.94, "elapsed_time": "1:00:52", "remaining_time": "3:36:36"}
+{"current_steps": 630, "total_steps": 2826, "loss": 0.4911, "lr": 4.775070358983881e-06, "epoch": 0.6684350132625995, "percentage": 22.29, "elapsed_time": "1:01:52", "remaining_time": "3:35:42"}
+{"current_steps": 640, "total_steps": 2826, "loss": 0.4744, "lr": 4.7620939306140696e-06, "epoch": 0.6790450928381963, "percentage": 22.65, "elapsed_time": "1:02:49", "remaining_time": "3:34:36"}
+{"current_steps": 650, "total_steps": 2826, "loss": 0.4789, "lr": 4.748772269376312e-06, "epoch": 0.6896551724137931, "percentage": 23.0, "elapsed_time": "1:03:47", "remaining_time": "3:33:34"}
+{"current_steps": 660, "total_steps": 2826, "loss": 0.488, "lr": 4.735107408375977e-06, "epoch": 0.7002652519893899, "percentage": 23.35, "elapsed_time": "1:04:46", "remaining_time": "3:32:34"}
+{"current_steps": 670, "total_steps": 2826, "loss": 0.4462, "lr": 4.721101433096381e-06, "epoch": 0.7108753315649867, "percentage": 23.71, "elapsed_time": "1:05:40", "remaining_time": "3:31:21"}
+{"current_steps": 680, "total_steps": 2826, "loss": 0.5087, "lr": 4.706756481080511e-06, "epoch": 0.7214854111405835, "percentage": 24.06, "elapsed_time": "1:06:41", "remaining_time": "3:30:27"}
+{"current_steps": 690, "total_steps": 2826, "loss": 0.5304, "lr": 4.692074741604795e-06, "epoch": 0.7320954907161804, "percentage": 24.42, "elapsed_time": "1:07:36", "remaining_time": "3:29:18"}
+{"current_steps": 700, "total_steps": 2826, "loss": 0.5177, "lr": 4.677058455344989e-06, "epoch": 0.7427055702917772, "percentage": 24.77, "elapsed_time": "1:08:33", "remaining_time": "3:28:13"}
+{"current_steps": 710, "total_steps": 2826, "loss": 0.4841, "lr": 4.661709914034209e-06, "epoch": 0.753315649867374, "percentage": 25.12, "elapsed_time": "1:09:37", "remaining_time": "3:27:29"}
+{"current_steps": 720, "total_steps": 2826, "loss": 0.4544, "lr": 4.646031460113175e-06, "epoch": 0.7639257294429708, "percentage": 25.48, "elapsed_time": "1:10:38", "remaining_time": "3:26:36"}
+{"current_steps": 730, "total_steps": 2826, "loss": 0.4715, "lr": 4.630025486372715e-06, "epoch": 0.7745358090185677, "percentage": 25.83, "elapsed_time": "1:11:32", "remaining_time": "3:25:25"}
+{"current_steps": 740, "total_steps": 2826, "loss": 0.4824, "lr": 4.613694435588589e-06, "epoch": 0.7851458885941645, "percentage": 26.19, "elapsed_time": "1:12:28", "remaining_time": "3:24:17"}
+{"current_steps": 750, "total_steps": 2826, "loss": 0.4852, "lr": 4.597040800148679e-06, "epoch": 0.7957559681697612, "percentage": 26.54, "elapsed_time": "1:13:25", "remaining_time": "3:23:14"}
+{"current_steps": 760, "total_steps": 2826, "loss": 0.4134, "lr": 4.580067121672607e-06, "epoch": 0.8063660477453581, "percentage": 26.89, "elapsed_time": "1:14:21", "remaining_time": "3:22:09"}
+{"current_steps": 770, "total_steps": 2826, "loss": 0.4493, "lr": 4.562775990623847e-06, "epoch": 0.8169761273209549, "percentage": 27.25, "elapsed_time": "1:15:20", "remaining_time": "3:21:11"}
+{"current_steps": 780, "total_steps": 2826, "loss": 0.5255, "lr": 4.5451700459143735e-06, "epoch": 0.8275862068965517, "percentage": 27.6, "elapsed_time": "1:16:18", "remaining_time": "3:20:10"}
+{"current_steps": 790, "total_steps": 2826, "loss": 0.4503, "lr": 4.527251974501923e-06, "epoch": 0.8381962864721485, "percentage": 27.95, "elapsed_time": "1:17:17", "remaining_time": "3:19:12"}
+{"current_steps": 800, "total_steps": 2826, "loss": 0.4636, "lr": 4.509024510979917e-06, "epoch": 0.8488063660477454, "percentage": 28.31, "elapsed_time": "1:18:17", "remaining_time": "3:18:17"}
+{"current_steps": 810, "total_steps": 2826, "loss": 0.4685, "lr": 4.4904904371601176e-06, "epoch": 0.8594164456233422, "percentage": 28.66, "elapsed_time": "1:19:18", "remaining_time": "3:17:23"}
+{"current_steps": 820, "total_steps": 2826, "loss": 0.5248, "lr": 4.4716525816480816e-06, "epoch": 0.870026525198939, "percentage": 29.02, "elapsed_time": "1:20:20", "remaining_time": "3:16:33"}
+{"current_steps": 830, "total_steps": 2826, "loss": 0.4747, "lr": 4.4525138194114644e-06, "epoch": 0.8806366047745358, "percentage": 29.37, "elapsed_time": "1:21:20", "remaining_time": "3:15:37"}
+{"current_steps": 840, "total_steps": 2826, "loss": 0.4198, "lr": 4.4330770713412555e-06, "epoch": 0.8912466843501327, "percentage": 29.72, "elapsed_time": "1:22:27", "remaining_time": "3:14:56"}
+{"current_steps": 850, "total_steps": 2826, "loss": 0.4545, "lr": 4.413345303805996e-06, "epoch": 0.9018567639257294, "percentage": 30.08, "elapsed_time": "1:23:27", "remaining_time": "3:14:02"}
+{"current_steps": 860, "total_steps": 2826, "loss": 0.5003, "lr": 4.393321528199072e-06, "epoch": 0.9124668435013262, "percentage": 30.43, "elapsed_time": "1:24:24", "remaining_time": "3:12:56"}
+{"current_steps": 870, "total_steps": 2826, "loss": 0.472, "lr": 4.373008800479118e-06, "epoch": 0.9230769230769231, "percentage": 30.79, "elapsed_time": "1:25:20", "remaining_time": "3:11:51"}
+{"current_steps": 880, "total_steps": 2826, "loss": 0.4661, "lr": 4.352410220703629e-06, "epoch": 0.9336870026525199, "percentage": 31.14, "elapsed_time": "1:26:17", "remaining_time": "3:10:50"}
+{"current_steps": 890, "total_steps": 2826, "loss": 0.4614, "lr": 4.331528932555844e-06, "epoch": 0.9442970822281167, "percentage": 31.49, "elapsed_time": "1:27:17", "remaining_time": "3:09:53"}
+{"current_steps": 900, "total_steps": 2826, "loss": 0.4623, "lr": 4.3103681228649626e-06, "epoch": 0.9549071618037135, "percentage": 31.85, "elapsed_time": "1:28:15", "remaining_time": "3:08:52"}
+{"current_steps": 910, "total_steps": 2826, "loss": 0.4902, "lr": 4.288931021119788e-06, "epoch": 0.9655172413793104, "percentage": 32.2, "elapsed_time": "1:29:13", "remaining_time": "3:07:52"}
+{"current_steps": 920, "total_steps": 2826, "loss": 0.5047, "lr": 4.267220898975848e-06, "epoch": 0.9761273209549072, "percentage": 32.55, "elapsed_time": "1:30:10", "remaining_time": "3:06:48"}
+{"current_steps": 930, "total_steps": 2826, "loss": 0.5358, "lr": 4.245241069756092e-06, "epoch": 0.986737400530504, "percentage": 32.91, "elapsed_time": "1:31:10", "remaining_time": "3:05:53"}
+{"current_steps": 940, "total_steps": 2826, "loss": 0.4928, "lr": 4.222994887945219e-06, "epoch": 0.9973474801061007, "percentage": 33.26, "elapsed_time": "1:32:11", "remaining_time": "3:04:58"}
+{"current_steps": 950, "total_steps": 2826, "loss": 0.3963, "lr": 4.20048574867773e-06, "epoch": 1.0074270557029177, "percentage": 33.62, "elapsed_time": "1:33:45", "remaining_time": "3:05:08"}
+{"current_steps": 960, "total_steps": 2826, "loss": 0.3125, "lr": 4.1777170872197725e-06, "epoch": 1.0180371352785147, "percentage": 33.97, "elapsed_time": "1:34:43", "remaining_time": "3:04:07"}
+{"current_steps": 970, "total_steps": 2826, "loss": 0.3457, "lr": 4.1546923784448646e-06, "epoch": 1.0286472148541115, "percentage": 34.32, "elapsed_time": "1:35:40", "remaining_time": "3:03:04"}
+{"current_steps": 980, "total_steps": 2826, "loss": 0.3029, "lr": 4.1314151363035705e-06, "epoch": 1.0392572944297083, "percentage": 34.68, "elapsed_time": "1:36:38", "remaining_time": "3:02:02"}
+{"current_steps": 990, "total_steps": 2826, "loss": 0.3289, "lr": 4.1078889132872145e-06, "epoch": 1.049867374005305, "percentage": 35.03, "elapsed_time": "1:37:36", "remaining_time": "3:01:01"}
+{"current_steps": 1000, "total_steps": 2826, "loss": 0.3234, "lr": 4.084117299885712e-06, "epoch": 1.0604774535809018, "percentage": 35.39, "elapsed_time": "1:38:36", "remaining_time": "3:00:04"}
+{"current_steps": 1010, "total_steps": 2826, "loss": 0.3139, "lr": 4.060103924039599e-06, "epoch": 1.0710875331564986, "percentage": 35.74, "elapsed_time": "1:39:35", "remaining_time": "2:59:04"}
+{"current_steps": 1020, "total_steps": 2826, "loss": 0.3144, "lr": 4.035852450586352e-06, "epoch": 1.0816976127320954, "percentage": 36.09, "elapsed_time": "1:40:32", "remaining_time": "2:58:00"}
+{"current_steps": 1030, "total_steps": 2826, "loss": 0.323, "lr": 4.011366580701073e-06, "epoch": 1.0923076923076924, "percentage": 36.45, "elapsed_time": "1:41:29", "remaining_time": "2:56:58"}
+{"current_steps": 1040, "total_steps": 2826, "loss": 0.3694, "lr": 3.9866500513316274e-06, "epoch": 1.1029177718832892, "percentage": 36.8, "elapsed_time": "1:42:28", "remaining_time": "2:55:59"}
+{"current_steps": 1050, "total_steps": 2826, "loss": 0.3351, "lr": 3.961706634628323e-06, "epoch": 1.113527851458886, "percentage": 37.15, "elapsed_time": "1:43:26", "remaining_time": "2:54:57"}
+{"current_steps": 1060, "total_steps": 2826, "loss": 0.3459, "lr": 3.936540137368222e-06, "epoch": 1.1241379310344828, "percentage": 37.51, "elapsed_time": "1:44:26", "remaining_time": "2:54:00"}
+{"current_steps": 1070, "total_steps": 2826, "loss": 0.3186, "lr": 3.911154400374159e-06, "epoch": 1.1347480106100796, "percentage": 37.86, "elapsed_time": "1:45:24", "remaining_time": "2:52:58"}
+{"current_steps": 1080, "total_steps": 2826, "loss": 0.3333, "lr": 3.885553297928573e-06, "epoch": 1.1453580901856764, "percentage": 38.22, "elapsed_time": "1:46:21", "remaining_time": "2:51:56"}
+{"current_steps": 1090, "total_steps": 2826, "loss": 0.3137, "lr": 3.859740737182222e-06, "epoch": 1.1559681697612731, "percentage": 38.57, "elapsed_time": "1:47:19", "remaining_time": "2:50:55"}
+{"current_steps": 1100, "total_steps": 2826, "loss": 0.3426, "lr": 3.833720657557894e-06, "epoch": 1.16657824933687, "percentage": 38.92, "elapsed_time": "1:48:18", "remaining_time": "2:49:56"}
+{"current_steps": 1110, "total_steps": 2826, "loss": 0.3709, "lr": 3.807497030149181e-06, "epoch": 1.1771883289124667, "percentage": 39.28, "elapsed_time": "1:49:13", "remaining_time": "2:48:51"}
+{"current_steps": 1120, "total_steps": 2826, "loss": 0.329, "lr": 3.7810738571144257e-06, "epoch": 1.1877984084880637, "percentage": 39.63, "elapsed_time": "1:50:12", "remaining_time": "2:47:52"}
+{"current_steps": 1130, "total_steps": 2826, "loss": 0.305, "lr": 3.7544551710659296e-06, "epoch": 1.1984084880636605, "percentage": 39.99, "elapsed_time": "1:51:11", "remaining_time": "2:46:53"}
+{"current_steps": 1140, "total_steps": 2826, "loss": 0.3449, "lr": 3.7276450344545024e-06, "epoch": 1.2090185676392573, "percentage": 40.34, "elapsed_time": "1:52:08", "remaining_time": "2:45:50"}
+{"current_steps": 1150, "total_steps": 2826, "loss": 0.3403, "lr": 3.7006475389494723e-06, "epoch": 1.219628647214854, "percentage": 40.69, "elapsed_time": "1:53:07", "remaining_time": "2:44:51"}
+{"current_steps": 1160, "total_steps": 2826, "loss": 0.3342, "lr": 3.6734668048142273e-06, "epoch": 1.2302387267904509, "percentage": 41.05, "elapsed_time": "1:54:06", "remaining_time": "2:43:52"}
+{"current_steps": 1170, "total_steps": 2826, "loss": 0.3589, "lr": 3.646106980277394e-06, "epoch": 1.2408488063660477, "percentage": 41.4, "elapsed_time": "1:55:04", "remaining_time": "2:42:53"}
+{"current_steps": 1180, "total_steps": 2826, "loss": 0.3447, "lr": 3.618572240899748e-06, "epoch": 1.2514588859416444, "percentage": 41.76, "elapsed_time": "1:56:02", "remaining_time": "2:41:52"}
+{"current_steps": 1190, "total_steps": 2826, "loss": 0.3787, "lr": 3.5908667889369603e-06, "epoch": 1.2620689655172415, "percentage": 42.11, "elapsed_time": "1:56:58", "remaining_time": "2:40:48"}
+{"current_steps": 1200, "total_steps": 2826, "loss": 0.3376, "lr": 3.5629948526982563e-06, "epoch": 1.2726790450928382, "percentage": 42.46, "elapsed_time": "1:57:58", "remaining_time": "2:39:50"}
+{"current_steps": 1210, "total_steps": 2826, "loss": 0.3461, "lr": 3.534960685901111e-06, "epoch": 1.283289124668435, "percentage": 42.82, "elapsed_time": "1:58:55", "remaining_time": "2:38:49"}
+{"current_steps": 1220, "total_steps": 2826, "loss": 0.3396, "lr": 3.506768567022062e-06, "epoch": 1.2938992042440318, "percentage": 43.17, "elapsed_time": "1:59:49", "remaining_time": "2:37:44"}
+{"current_steps": 1230, "total_steps": 2826, "loss": 0.3364, "lr": 3.478422798643737e-06, "epoch": 1.3045092838196286, "percentage": 43.52, "elapsed_time": "2:00:49", "remaining_time": "2:36:47"}
+{"current_steps": 1240, "total_steps": 2826, "loss": 0.3126, "lr": 3.4499277067982177e-06, "epoch": 1.3151193633952254, "percentage": 43.88, "elapsed_time": "2:01:46", "remaining_time": "2:35:45"}
+{"current_steps": 1250, "total_steps": 2826, "loss": 0.3092, "lr": 3.421287640306809e-06, "epoch": 1.3257294429708222, "percentage": 44.23, "elapsed_time": "2:02:44", "remaining_time": "2:34:45"}
+{"current_steps": 1260, "total_steps": 2826, "loss": 0.3374, "lr": 3.3925069701163406e-06, "epoch": 1.3363395225464192, "percentage": 44.59, "elapsed_time": "2:03:48", "remaining_time": "2:33:51"}
+{"current_steps": 1270, "total_steps": 2826, "loss": 0.3436, "lr": 3.363590088632085e-06, "epoch": 1.346949602122016, "percentage": 44.94, "elapsed_time": "2:04:49", "remaining_time": "2:32:55"}
+{"current_steps": 1280, "total_steps": 2826, "loss": 0.3283, "lr": 3.334541409047408e-06, "epoch": 1.3575596816976128, "percentage": 45.29, "elapsed_time": "2:05:49", "remaining_time": "2:31:58"}
+{"current_steps": 1290, "total_steps": 2826, "loss": 0.358, "lr": 3.3053653646702422e-06, "epoch": 1.3681697612732096, "percentage": 45.65, "elapsed_time": "2:06:47", "remaining_time": "2:30:58"}
+{"current_steps": 1300, "total_steps": 2826, "loss": 0.3084, "lr": 3.276066408246487e-06, "epoch": 1.3787798408488063, "percentage": 46.0, "elapsed_time": "2:07:45", "remaining_time": "2:29:57"}
+{"current_steps": 1310, "total_steps": 2826, "loss": 0.3508, "lr": 3.2466490112804484e-06, "epoch": 1.3893899204244031, "percentage": 46.36, "elapsed_time": "2:08:45", "remaining_time": "2:29:00"}
+{"current_steps": 1320, "total_steps": 2826, "loss": 0.3215, "lr": 3.217117663352417e-06, "epoch": 1.4, "percentage": 46.71, "elapsed_time": "2:09:41", "remaining_time": "2:27:57"}
+{"current_steps": 1330, "total_steps": 2826, "loss": 0.3193, "lr": 3.187476871433478e-06, "epoch": 1.410610079575597, "percentage": 47.06, "elapsed_time": "2:10:40", "remaining_time": "2:26:58"}
+{"current_steps": 1340, "total_steps": 2826, "loss": 0.3019, "lr": 3.1577311591976766e-06, "epoch": 1.4212201591511937, "percentage": 47.42, "elapsed_time": "2:11:37", "remaining_time": "2:25:57"}
+{"current_steps": 1350, "total_steps": 2826, "loss": 0.3099, "lr": 3.1278850663316307e-06, "epoch": 1.4318302387267905, "percentage": 47.77, "elapsed_time": "2:12:36", "remaining_time": "2:24:59"}
+{"current_steps": 1360, "total_steps": 2826, "loss": 0.3085, "lr": 3.0979431478416987e-06, "epoch": 1.4424403183023873, "percentage": 48.12, "elapsed_time": "2:13:35", "remaining_time": "2:24:00"}
+{"current_steps": 1370, "total_steps": 2826, "loss": 0.3211, "lr": 3.067909973358811e-06, "epoch": 1.453050397877984, "percentage": 48.48, "elapsed_time": "2:14:32", "remaining_time": "2:22:58"}
+{"current_steps": 1380, "total_steps": 2826, "loss": 0.3329, "lr": 3.0377901264410673e-06, "epoch": 1.4636604774535809, "percentage": 48.83, "elapsed_time": "2:15:37", "remaining_time": "2:22:06"}
+{"current_steps": 1390, "total_steps": 2826, "loss": 0.3376, "lr": 3.0075882038742133e-06, "epoch": 1.4742705570291776, "percentage": 49.19, "elapsed_time": "2:16:35", "remaining_time": "2:21:06"}
+{"current_steps": 1400, "total_steps": 2826, "loss": 0.2896, "lr": 2.9773088149700923e-06, "epoch": 1.4848806366047747, "percentage": 49.54, "elapsed_time": "2:17:35", "remaining_time": "2:20:08"}
+{"current_steps": 1410, "total_steps": 2826, "loss": 0.299, "lr": 2.9469565808631888e-06, "epoch": 1.4954907161803712, "percentage": 49.89, "elapsed_time": "2:18:32", "remaining_time": "2:19:07"}
+{"current_steps": 1420, "total_steps": 2826, "loss": 0.3484, "lr": 2.9165361338053683e-06, "epoch": 1.5061007957559682, "percentage": 50.25, "elapsed_time": "2:19:29", "remaining_time": "2:18:06"}
+{"current_steps": 1430, "total_steps": 2826, "loss": 0.3316, "lr": 2.886052116458918e-06, "epoch": 1.516710875331565, "percentage": 50.6, "elapsed_time": "2:20:28", "remaining_time": "2:17:08"}
+{"current_steps": 1440, "total_steps": 2826, "loss": 0.328, "lr": 2.8555091811880004e-06, "epoch": 1.5273209549071618, "percentage": 50.96, "elapsed_time": "2:21:25", "remaining_time": "2:16:07"}
+{"current_steps": 1450, "total_steps": 2826, "loss": 0.3215, "lr": 2.8249119893486252e-06, "epoch": 1.5379310344827586, "percentage": 51.31, "elapsed_time": "2:22:28", "remaining_time": "2:15:12"}
+{"current_steps": 1460, "total_steps": 2826, "loss": 0.3118, "lr": 2.7942652105772516e-06, "epoch": 1.5485411140583554, "percentage": 51.66, "elapsed_time": "2:23:28", "remaining_time": "2:14:14"}
+{"current_steps": 1470, "total_steps": 2826, "loss": 0.2973, "lr": 2.7635735220781214e-06, "epoch": 1.5591511936339524, "percentage": 52.02, "elapsed_time": "2:24:31", "remaining_time": "2:13:19"}
+{"current_steps": 1480, "total_steps": 2826, "loss": 0.3423, "lr": 2.7328416079094412e-06, "epoch": 1.569761273209549, "percentage": 52.37, "elapsed_time": "2:25:31", "remaining_time": "2:12:20"}
+{"current_steps": 1490, "total_steps": 2826, "loss": 0.3211, "lr": 2.7020741582685217e-06, "epoch": 1.580371352785146, "percentage": 52.72, "elapsed_time": "2:26:27", "remaining_time": "2:11:19"}
+{"current_steps": 1500, "total_steps": 2826, "loss": 0.2733, "lr": 2.6712758687759706e-06, "epoch": 1.5909814323607427, "percentage": 53.08, "elapsed_time": "2:27:26", "remaining_time": "2:10:20"}
+{"current_steps": 1510, "total_steps": 2826, "loss": 0.338, "lr": 2.6404514397590657e-06, "epoch": 1.6015915119363395, "percentage": 53.43, "elapsed_time": "2:28:24", "remaining_time": "2:09:20"}
+{"current_steps": 1520, "total_steps": 2826, "loss": 0.3124, "lr": 2.6096055755344113e-06, "epoch": 1.6122015915119363, "percentage": 53.79, "elapsed_time": "2:29:24", "remaining_time": "2:08:22"}
+{"current_steps": 1530, "total_steps": 2826, "loss": 0.3538, "lr": 2.578742983689973e-06, "epoch": 1.622811671087533, "percentage": 54.14, "elapsed_time": "2:30:18", "remaining_time": "2:07:19"}
+{"current_steps": 1540, "total_steps": 2826, "loss": 0.3353, "lr": 2.547868374366631e-06, "epoch": 1.6334217506631301, "percentage": 54.49, "elapsed_time": "2:31:20", "remaining_time": "2:06:22"}
+{"current_steps": 1550, "total_steps": 2826, "loss": 0.302, "lr": 2.5169864595393295e-06, "epoch": 1.6440318302387267, "percentage": 54.85, "elapsed_time": "2:32:18", "remaining_time": "2:05:22"}
+{"current_steps": 1560, "total_steps": 2826, "loss": 0.3124, "lr": 2.4861019522979537e-06, "epoch": 1.6546419098143237, "percentage": 55.2, "elapsed_time": "2:33:16", "remaining_time": "2:04:22"}
+{"current_steps": 1570, "total_steps": 2826, "loss": 0.3497, "lr": 2.455219566128034e-06, "epoch": 1.6652519893899205, "percentage": 55.56, "elapsed_time": "2:34:13", "remaining_time": "2:03:22"}
+{"current_steps": 1580, "total_steps": 2826, "loss": 0.3233, "lr": 2.4243440141913905e-06, "epoch": 1.6758620689655173, "percentage": 55.91, "elapsed_time": "2:35:12", "remaining_time": "2:02:23"}
+{"current_steps": 1590, "total_steps": 2826, "loss": 0.3067, "lr": 2.393480008606825e-06, "epoch": 1.686472148541114, "percentage": 56.26, "elapsed_time": "2:36:10", "remaining_time": "2:01:24"}
+{"current_steps": 1600, "total_steps": 2826, "loss": 0.2893, "lr": 2.3626322597309774e-06, "epoch": 1.6970822281167108, "percentage": 56.62, "elapsed_time": "2:37:09", "remaining_time": "2:00:25"}
+{"current_steps": 1610, "total_steps": 2826, "loss": 0.2825, "lr": 2.331805475439445e-06, "epoch": 1.7076923076923078, "percentage": 56.97, "elapsed_time": "2:38:07", "remaining_time": "1:59:26"}
+{"current_steps": 1620, "total_steps": 2826, "loss": 0.3379, "lr": 2.3010043604082824e-06, "epoch": 1.7183023872679044, "percentage": 57.32, "elapsed_time": "2:39:01", "remaining_time": "1:58:22"}
+{"current_steps": 1630, "total_steps": 2826, "loss": 0.301, "lr": 2.2702336153959925e-06, "epoch": 1.7289124668435014, "percentage": 57.68, "elapsed_time": "2:40:01", "remaining_time": "1:57:25"}
+{"current_steps": 1640, "total_steps": 2826, "loss": 0.404, "lr": 2.2394979365261134e-06, "epoch": 1.739522546419098, "percentage": 58.03, "elapsed_time": "2:40:58", "remaining_time": "1:56:24"}
+{"current_steps": 1650, "total_steps": 2826, "loss": 0.3242, "lr": 2.208802014570507e-06, "epoch": 1.750132625994695, "percentage": 58.39, "elapsed_time": "2:41:56", "remaining_time": "1:55:25"}
+{"current_steps": 1660, "total_steps": 2826, "loss": 0.3152, "lr": 2.1781505342334775e-06, "epoch": 1.7607427055702918, "percentage": 58.74, "elapsed_time": "2:42:55", "remaining_time": "1:54:26"}
+{"current_steps": 1670, "total_steps": 2826, "loss": 0.3302, "lr": 2.147548173436805e-06, "epoch": 1.7713527851458886, "percentage": 59.09, "elapsed_time": "2:43:56", "remaining_time": "1:53:29"}
+{"current_steps": 1680, "total_steps": 2826, "loss": 0.293, "lr": 2.116999602605814e-06, "epoch": 1.7819628647214856, "percentage": 59.45, "elapsed_time": "2:44:55", "remaining_time": "1:52:29"}
+{"current_steps": 1690, "total_steps": 2826, "loss": 0.2683, "lr": 2.086509483956594e-06, "epoch": 1.7925729442970821, "percentage": 59.8, "elapsed_time": "2:45:54", "remaining_time": "1:51:31"}
+{"current_steps": 1700, "total_steps": 2826, "loss": 0.313, "lr": 2.056082470784469e-06, "epoch": 1.8031830238726791, "percentage": 60.16, "elapsed_time": "2:46:50", "remaining_time": "1:50:30"}
+{"current_steps": 1710, "total_steps": 2826, "loss": 0.262, "lr": 2.0257232067538213e-06, "epoch": 1.8137931034482757, "percentage": 60.51, "elapsed_time": "2:47:47", "remaining_time": "1:49:30"}
+{"current_steps": 1720, "total_steps": 2826, "loss": 0.3457, "lr": 1.9954363251894007e-06, "epoch": 1.8244031830238727, "percentage": 60.86, "elapsed_time": "2:48:43", "remaining_time": "1:48:29"}
+{"current_steps": 1730, "total_steps": 2826, "loss": 0.2739, "lr": 1.9652264483691933e-06, "epoch": 1.8350132625994695, "percentage": 61.22, "elapsed_time": "2:49:43", "remaining_time": "1:47:31"}
+{"current_steps": 1740, "total_steps": 2826, "loss": 0.3109, "lr": 1.9350981868189944e-06, "epoch": 1.8456233421750663, "percentage": 61.57, "elapsed_time": "2:50:40", "remaining_time": "1:46:31"}
+{"current_steps": 1750, "total_steps": 2826, "loss": 0.3269, "lr": 1.9050561386087618e-06, "epoch": 1.856233421750663, "percentage": 61.92, "elapsed_time": "2:51:36", "remaining_time": "1:45:31"}
+{"current_steps": 1760, "total_steps": 2826, "loss": 0.3617, "lr": 1.8751048886508711e-06, "epoch": 1.8668435013262599, "percentage": 62.28, "elapsed_time": "2:52:34", "remaining_time": "1:44:31"}
+{"current_steps": 1770, "total_steps": 2826, "loss": 0.3228, "lr": 1.8452490080003888e-06, "epoch": 1.8774535809018569, "percentage": 62.63, "elapsed_time": "2:53:33", "remaining_time": "1:43:32"}
+{"current_steps": 1780, "total_steps": 2826, "loss": 0.2857, "lr": 1.8154930531574521e-06, "epoch": 1.8880636604774534, "percentage": 62.99, "elapsed_time": "2:54:32", "remaining_time": "1:42:33"}
+{"current_steps": 1790, "total_steps": 2826, "loss": 0.3622, "lr": 1.785841565371868e-06, "epoch": 1.8986737400530505, "percentage": 63.34, "elapsed_time": "2:55:29", "remaining_time": "1:41:34"}
+{"current_steps": 1800, "total_steps": 2826, "loss": 0.3031, "lr": 1.7562990699500482e-06, "epoch": 1.9092838196286472, "percentage": 63.69, "elapsed_time": "2:56:27", "remaining_time": "1:40:34"}
+{"current_steps": 1810, "total_steps": 2826, "loss": 0.3019, "lr": 1.7268700755643708e-06, "epoch": 1.919893899204244, "percentage": 64.05, "elapsed_time": "2:57:25", "remaining_time": "1:39:35"}
+{"current_steps": 1820, "total_steps": 2826, "loss": 0.3047, "lr": 1.6975590735650812e-06, "epoch": 1.9305039787798408, "percentage": 64.4, "elapsed_time": "2:58:25", "remaining_time": "1:38:37"}
+{"current_steps": 1830, "total_steps": 2826, "loss": 0.3048, "lr": 1.668370537294841e-06, "epoch": 1.9411140583554376, "percentage": 64.76, "elapsed_time": "2:59:22", "remaining_time": "1:37:37"}
+{"current_steps": 1840, "total_steps": 2826, "loss": 0.3205, "lr": 1.6393089214060204e-06, "epoch": 1.9517241379310346, "percentage": 65.11, "elapsed_time": "3:00:20", "remaining_time": "1:36:38"}
+{"current_steps": 1850, "total_steps": 2826, "loss": 0.321, "lr": 1.6103786611808414e-06, "epoch": 1.9623342175066312, "percentage": 65.46, "elapsed_time": "3:01:23", "remaining_time": "1:35:41"}
+{"current_steps": 1860, "total_steps": 2826, "loss": 0.2954, "lr": 1.5815841718544884e-06, "epoch": 1.9729442970822282, "percentage": 65.82, "elapsed_time": "3:02:19", "remaining_time": "1:34:41"}
+{"current_steps": 1870, "total_steps": 2826, "loss": 0.2945, "lr": 1.5529298479412636e-06, "epoch": 1.983554376657825, "percentage": 66.17, "elapsed_time": "3:03:16", "remaining_time": "1:33:41"}
+{"current_steps": 1880, "total_steps": 2826, "loss": 0.3291, "lr": 1.524420062563912e-06, "epoch": 1.9941644562334218, "percentage": 66.53, "elapsed_time": "3:04:13", "remaining_time": "1:32:41"}
+{"current_steps": 1890, "total_steps": 2826, "loss": 0.234, "lr": 1.4960591667862163e-06, "epoch": 2.004244031830239, "percentage": 66.88, "elapsed_time": "3:05:53", "remaining_time": "1:32:03"}
+{"current_steps": 1900, "total_steps": 2826, "loss": 0.1943, "lr": 1.4678514889489464e-06, "epoch": 2.0148541114058354, "percentage": 67.23, "elapsed_time": "3:06:54", "remaining_time": "1:31:05"}
+{"current_steps": 1910, "total_steps": 2826, "loss": 0.1911, "lr": 1.4398013340092864e-06, "epoch": 2.0254641909814324, "percentage": 67.59, "elapsed_time": "3:07:56", "remaining_time": "1:30:08"}
+{"current_steps": 1920, "total_steps": 2826, "loss": 0.1895, "lr": 1.4119129828838275e-06, "epoch": 2.0360742705570294, "percentage": 67.94, "elapsed_time": "3:08:56", "remaining_time": "1:29:09"}
+{"current_steps": 1930, "total_steps": 2826, "loss": 0.2177, "lr": 1.384190691795226e-06, "epoch": 2.046684350132626, "percentage": 68.29, "elapsed_time": "3:09:56", "remaining_time": "1:28:10"}
+{"current_steps": 1940, "total_steps": 2826, "loss": 0.2252, "lr": 1.3566386916226373e-06, "epoch": 2.057294429708223, "percentage": 68.65, "elapsed_time": "3:10:53", "remaining_time": "1:27:10"}
+{"current_steps": 1950, "total_steps": 2826, "loss": 0.1982, "lr": 1.3292611872560134e-06, "epoch": 2.0679045092838195, "percentage": 69.0, "elapsed_time": "3:11:57", "remaining_time": "1:26:13"}
+{"current_steps": 1960, "total_steps": 2826, "loss": 0.1696, "lr": 1.302062356954365e-06, "epoch": 2.0785145888594165, "percentage": 69.36, "elapsed_time": "3:12:58", "remaining_time": "1:25:15"}
+{"current_steps": 1970, "total_steps": 2826, "loss": 0.1936, "lr": 1.2750463517080922e-06, "epoch": 2.089124668435013, "percentage": 69.71, "elapsed_time": "3:14:00", "remaining_time": "1:24:17"}
+{"current_steps": 1980, "total_steps": 2826, "loss": 0.1604, "lr": 1.2482172946054753e-06, "epoch": 2.09973474801061, "percentage": 70.06, "elapsed_time": "3:14:56", "remaining_time": "1:23:17"}
+{"current_steps": 1990, "total_steps": 2826, "loss": 0.2069, "lr": 1.2215792802034187e-06, "epoch": 2.110344827586207, "percentage": 70.42, "elapsed_time": "3:15:54", "remaining_time": "1:22:18"}
+{"current_steps": 2000, "total_steps": 2826, "loss": 0.1964, "lr": 1.1951363739025618e-06, "epoch": 2.1209549071618037, "percentage": 70.77, "elapsed_time": "3:16:54", "remaining_time": "1:21:19"}
+{"current_steps": 2010, "total_steps": 2826, "loss": 0.1871, "lr": 1.168892611326827e-06, "epoch": 2.1315649867374007, "percentage": 71.13, "elapsed_time": "3:17:53", "remaining_time": "1:20:20"}
+{"current_steps": 2020, "total_steps": 2826, "loss": 0.2595, "lr": 1.1428519977075136e-06, "epoch": 2.1421750663129973, "percentage": 71.48, "elapsed_time": "3:18:51", "remaining_time": "1:19:20"}
+{"current_steps": 2030, "total_steps": 2826, "loss": 0.185, "lr": 1.1170185072720434e-06, "epoch": 2.1527851458885943, "percentage": 71.83, "elapsed_time": "3:19:49", "remaining_time": "1:18:21"}
+{"current_steps": 2040, "total_steps": 2826, "loss": 0.228, "lr": 1.091396082637419e-06, "epoch": 2.163395225464191, "percentage": 72.19, "elapsed_time": "3:20:47", "remaining_time": "1:17:21"}
+{"current_steps": 2050, "total_steps": 2826, "loss": 0.2098, "lr": 1.065988634208516e-06, "epoch": 2.174005305039788, "percentage": 72.54, "elapsed_time": "3:21:48", "remaining_time": "1:16:23"}
+{"current_steps": 2060, "total_steps": 2826, "loss": 0.1982, "lr": 1.0408000395812961e-06, "epoch": 2.184615384615385, "percentage": 72.89, "elapsed_time": "3:22:48", "remaining_time": "1:15:24"}
+{"current_steps": 2070, "total_steps": 2826, "loss": 0.1844, "lr": 1.0158341429510194e-06, "epoch": 2.1952254641909814, "percentage": 73.25, "elapsed_time": "3:23:45", "remaining_time": "1:14:24"}
+{"current_steps": 2080, "total_steps": 2826, "loss": 0.1654, "lr": 9.910947545255523e-07, "epoch": 2.2058355437665784, "percentage": 73.6, "elapsed_time": "3:24:45", "remaining_time": "1:13:26"}
+{"current_steps": 2090, "total_steps": 2826, "loss": 0.2037, "lr": 9.665856499438744e-07, "epoch": 2.216445623342175, "percentage": 73.96, "elapsed_time": "3:25:43", "remaining_time": "1:12:26"}
+{"current_steps": 2100, "total_steps": 2826, "loss": 0.2087, "lr": 9.423105696998491e-07, "epoch": 2.227055702917772, "percentage": 74.31, "elapsed_time": "3:26:40", "remaining_time": "1:11:26"}
+{"current_steps": 2110, "total_steps": 2826, "loss": 0.2105, "lr": 9.182732185713633e-07, "epoch": 2.2376657824933686, "percentage": 74.66, "elapsed_time": "3:27:38", "remaining_time": "1:10:27"}
+{"current_steps": 2120, "total_steps": 2826, "loss": 0.2186, "lr": 8.94477265054918e-07, "epoch": 2.2482758620689656, "percentage": 75.02, "elapsed_time": "3:28:36", "remaining_time": "1:09:28"}
+{"current_steps": 2130, "total_steps": 2826, "loss": 0.1879, "lr": 8.709263408057522e-07, "epoch": 2.2588859416445626, "percentage": 75.37, "elapsed_time": "3:29:34", "remaining_time": "1:08:28"}
+{"current_steps": 2140, "total_steps": 2826, "loss": 0.2177, "lr": 8.476240400835972e-07, "epoch": 2.269496021220159, "percentage": 75.73, "elapsed_time": "3:30:30", "remaining_time": "1:07:28"}
+{"current_steps": 2150, "total_steps": 2826, "loss": 0.165, "lr": 8.245739192041311e-07, "epoch": 2.280106100795756, "percentage": 76.08, "elapsed_time": "3:31:30", "remaining_time": "1:06:30"}
+{"current_steps": 2160, "total_steps": 2826, "loss": 0.2018, "lr": 8.017794959962225e-07, "epoch": 2.2907161803713527, "percentage": 76.43, "elapsed_time": "3:32:27", "remaining_time": "1:05:30"}
+{"current_steps": 2170, "total_steps": 2826, "loss": 0.1955, "lr": 7.792442492650587e-07, "epoch": 2.3013262599469497, "percentage": 76.79, "elapsed_time": "3:33:28", "remaining_time": "1:04:32"}
+{"current_steps": 2180, "total_steps": 2826, "loss": 0.1976, "lr": 7.569716182612177e-07, "epoch": 2.3119363395225463, "percentage": 77.14, "elapsed_time": "3:34:25", "remaining_time": "1:03:32"}
+{"current_steps": 2190, "total_steps": 2826, "loss": 0.1685, "lr": 7.349650021557839e-07, "epoch": 2.3225464190981433, "percentage": 77.49, "elapsed_time": "3:35:25", "remaining_time": "1:02:33"}
+{"current_steps": 2200, "total_steps": 2826, "loss": 0.1519, "lr": 7.132277595215773e-07, "epoch": 2.33315649867374, "percentage": 77.85, "elapsed_time": "3:36:19", "remaining_time": "1:01:33"}
+{"current_steps": 2210, "total_steps": 2826, "loss": 0.1573, "lr": 6.917632078205805e-07, "epoch": 2.343766578249337, "percentage": 78.2, "elapsed_time": "3:37:18", "remaining_time": "1:00:34"}
+{"current_steps": 2220, "total_steps": 2826, "loss": 0.184, "lr": 6.705746228976387e-07, "epoch": 2.3543766578249334, "percentage": 78.56, "elapsed_time": "3:38:14", "remaining_time": "0:59:34"}
+{"current_steps": 2230, "total_steps": 2826, "loss": 0.1968, "lr": 6.496652384805125e-07, "epoch": 2.3649867374005304, "percentage": 78.91, "elapsed_time": "3:39:11", "remaining_time": "0:58:34"}
+{"current_steps": 2240, "total_steps": 2826, "loss": 0.1846, "lr": 6.290382456863584e-07, "epoch": 2.3755968169761275, "percentage": 79.26, "elapsed_time": "3:40:12", "remaining_time": "0:57:36"}
+{"current_steps": 2250, "total_steps": 2826, "loss": 0.1858, "lr": 6.086967925347075e-07, "epoch": 2.386206896551724, "percentage": 79.62, "elapsed_time": "3:41:13", "remaining_time": "0:56:38"}
+{"current_steps": 2260, "total_steps": 2826, "loss": 0.1837, "lr": 5.88643983467033e-07, "epoch": 2.396816976127321, "percentage": 79.97, "elapsed_time": "3:42:12", "remaining_time": "0:55:39"}
+{"current_steps": 2270, "total_steps": 2826, "loss": 0.1659, "lr": 5.688828788729547e-07, "epoch": 2.4074270557029176, "percentage": 80.33, "elapsed_time": "3:43:09", "remaining_time": "0:54:39"}
+{"current_steps": 2280, "total_steps": 2826, "loss": 0.2095, "lr": 5.494164946231747e-07, "epoch": 2.4180371352785146, "percentage": 80.68, "elapsed_time": "3:44:04", "remaining_time": "0:53:39"}
+{"current_steps": 2290, "total_steps": 2826, "loss": 0.1862, "lr": 5.302478016092075e-07, "epoch": 2.428647214854111, "percentage": 81.03, "elapsed_time": "3:45:03", "remaining_time": "0:52:40"}
+{"current_steps": 2300, "total_steps": 2826, "loss": 0.2085, "lr": 5.113797252899728e-07, "epoch": 2.439257294429708, "percentage": 81.39, "elapsed_time": "3:46:01", "remaining_time": "0:51:41"}
+{"current_steps": 2310, "total_steps": 2826, "loss": 0.1914, "lr": 4.928151452453184e-07, "epoch": 2.449867374005305, "percentage": 81.74, "elapsed_time": "3:46:58", "remaining_time": "0:50:42"}
+{"current_steps": 2320, "total_steps": 2826, "loss": 0.1718, "lr": 4.745568947365542e-07, "epoch": 2.4604774535809018, "percentage": 82.09, "elapsed_time": "3:47:59", "remaining_time": "0:49:43"}
+{"current_steps": 2330, "total_steps": 2826, "loss": 0.1669, "lr": 4.5660776027404654e-07, "epoch": 2.4710875331564988, "percentage": 82.45, "elapsed_time": "3:48:58", "remaining_time": "0:48:44"}
+{"current_steps": 2340, "total_steps": 2826, "loss": 0.1731, "lr": 4.389704811919507e-07, "epoch": 2.4816976127320953, "percentage": 82.8, "elapsed_time": "3:50:00", "remaining_time": "0:47:46"}
+{"current_steps": 2350, "total_steps": 2826, "loss": 0.1802, "lr": 4.216477492301455e-07, "epoch": 2.4923076923076923, "percentage": 83.16, "elapsed_time": "3:50:57", "remaining_time": "0:46:46"}
+{"current_steps": 2360, "total_steps": 2826, "loss": 0.2232, "lr": 4.0464220812342526e-07, "epoch": 2.502917771883289, "percentage": 83.51, "elapsed_time": "3:51:53", "remaining_time": "0:45:47"}
+{"current_steps": 2370, "total_steps": 2826, "loss": 0.1432, "lr": 3.87956453198027e-07, "epoch": 2.513527851458886, "percentage": 83.86, "elapsed_time": "3:52:52", "remaining_time": "0:44:48"}
+{"current_steps": 2380, "total_steps": 2826, "loss": 0.1834, "lr": 3.715930309755389e-07, "epoch": 2.524137931034483, "percentage": 84.22, "elapsed_time": "3:53:51", "remaining_time": "0:43:49"}
+{"current_steps": 2390, "total_steps": 2826, "loss": 0.2123, "lr": 3.5555443878425635e-07, "epoch": 2.5347480106100795, "percentage": 84.57, "elapsed_time": "3:54:47", "remaining_time": "0:42:49"}
+{"current_steps": 2400, "total_steps": 2826, "loss": 0.2034, "lr": 3.398431243780531e-07, "epoch": 2.5453580901856765, "percentage": 84.93, "elapsed_time": "3:55:41", "remaining_time": "0:41:50"}
+{"current_steps": 2410, "total_steps": 2826, "loss": 0.1778, "lr": 3.2446148556281117e-07, "epoch": 2.555968169761273, "percentage": 85.28, "elapsed_time": "3:56:40", "remaining_time": "0:40:51"}
+{"current_steps": 2420, "total_steps": 2826, "loss": 0.1892, "lr": 3.0941186983047543e-07, "epoch": 2.56657824933687, "percentage": 85.63, "elapsed_time": "3:57:36", "remaining_time": "0:39:51"}
+{"current_steps": 2430, "total_steps": 2826, "loss": 0.1935, "lr": 2.9469657400078925e-07, "epoch": 2.5771883289124666, "percentage": 85.99, "elapsed_time": "3:58:33", "remaining_time": "0:38:52"}
+{"current_steps": 2440, "total_steps": 2826, "loss": 0.1858, "lr": 2.8031784387076186e-07, "epoch": 2.5877984084880636, "percentage": 86.34, "elapsed_time": "3:59:29", "remaining_time": "0:37:53"}
+{"current_steps": 2450, "total_steps": 2826, "loss": 0.2118, "lr": 2.6627787387191934e-07, "epoch": 2.5984084880636606, "percentage": 86.69, "elapsed_time": "4:00:25", "remaining_time": "0:36:53"}
+{"current_steps": 2460, "total_steps": 2826, "loss": 0.1929, "lr": 2.5257880673540376e-07, "epoch": 2.609018567639257, "percentage": 87.05, "elapsed_time": "4:01:21", "remaining_time": "0:35:54"}
+{"current_steps": 2470, "total_steps": 2826, "loss": 0.1745, "lr": 2.392227331649527e-07, "epoch": 2.6196286472148542, "percentage": 87.4, "elapsed_time": "4:02:18", "remaining_time": "0:34:55"}
+{"current_steps": 2480, "total_steps": 2826, "loss": 0.1823, "lr": 2.2621169151782417e-07, "epoch": 2.630238726790451, "percentage": 87.76, "elapsed_time": "4:03:15", "remaining_time": "0:33:56"}
+{"current_steps": 2490, "total_steps": 2826, "loss": 0.2037, "lr": 2.1354766749371093e-07, "epoch": 2.640848806366048, "percentage": 88.11, "elapsed_time": "4:04:11", "remaining_time": "0:32:57"}
+{"current_steps": 2500, "total_steps": 2826, "loss": 0.2196, "lr": 2.0123259383169031e-07, "epoch": 2.6514588859416444, "percentage": 88.46, "elapsed_time": "4:05:10", "remaining_time": "0:31:58"}
+{"current_steps": 2510, "total_steps": 2826, "loss": 0.1848, "lr": 1.8926835001525257e-07, "epoch": 2.6620689655172414, "percentage": 88.82, "elapsed_time": "4:06:05", "remaining_time": "0:30:58"}
+{"current_steps": 2520, "total_steps": 2826, "loss": 0.1823, "lr": 1.776567619854655e-07, "epoch": 2.6726790450928384, "percentage": 89.17, "elapsed_time": "4:07:00", "remaining_time": "0:29:59"}
+{"current_steps": 2530, "total_steps": 2826, "loss": 0.2039, "lr": 1.6639960186230293e-07, "epoch": 2.683289124668435, "percentage": 89.53, "elapsed_time": "4:08:00", "remaining_time": "0:29:00"}
+{"current_steps": 2540, "total_steps": 2826, "loss": 0.1796, "lr": 1.5549858767419018e-07, "epoch": 2.693899204244032, "percentage": 89.88, "elapsed_time": "4:08:57", "remaining_time": "0:28:01"}
+{"current_steps": 2550, "total_steps": 2826, "loss": 0.1893, "lr": 1.449553830958053e-07, "epoch": 2.7045092838196285, "percentage": 90.23, "elapsed_time": "4:09:57", "remaining_time": "0:27:03"}
+{"current_steps": 2560, "total_steps": 2826, "loss": 0.1947, "lr": 1.347715971941746e-07, "epoch": 2.7151193633952255, "percentage": 90.59, "elapsed_time": "4:10:56", "remaining_time": "0:26:04"}
+{"current_steps": 2570, "total_steps": 2826, "loss": 0.1744, "lr": 1.2494878418310234e-07, "epoch": 2.725729442970822, "percentage": 90.94, "elapsed_time": "4:11:56", "remaining_time": "0:25:05"}
+{"current_steps": 2580, "total_steps": 2826, "loss": 0.2351, "lr": 1.1548844318597208e-07, "epoch": 2.736339522546419, "percentage": 91.3, "elapsed_time": "4:12:55", "remaining_time": "0:24:06"}
+{"current_steps": 2590, "total_steps": 2826, "loss": 0.2245, "lr": 1.0639201800695553e-07, "epoch": 2.746949602122016, "percentage": 91.65, "elapsed_time": "4:13:51", "remaining_time": "0:23:07"}
+{"current_steps": 2600, "total_steps": 2826, "loss": 0.2014, "lr": 9.76608969106646e-08, "epoch": 2.7575596816976127, "percentage": 92.0, "elapsed_time": "4:14:49", "remaining_time": "0:22:09"}
+{"current_steps": 2610, "total_steps": 2826, "loss": 0.1824, "lr": 8.929641241027937e-08, "epoch": 2.7681697612732097, "percentage": 92.36, "elapsed_time": "4:15:47", "remaining_time": "0:21:10"}
+{"current_steps": 2620, "total_steps": 2826, "loss": 0.1706, "lr": 8.129984106418354e-08, "epoch": 2.7787798408488062, "percentage": 92.71, "elapsed_time": "4:16:45", "remaining_time": "0:20:11"}
+{"current_steps": 2630, "total_steps": 2826, "loss": 0.2195, "lr": 7.3672403281142e-08, "epoch": 2.7893899204244033, "percentage": 93.06, "elapsed_time": "4:17:44", "remaining_time": "0:19:12"}
+{"current_steps": 2640, "total_steps": 2826, "loss": 0.1748, "lr": 6.641526313404534e-08, "epoch": 2.8, "percentage": 93.42, "elapsed_time": "4:18:42", "remaining_time": "0:18:13"}
+{"current_steps": 2650, "total_steps": 2826, "loss": 0.2061, "lr": 5.952952818225416e-08, "epoch": 2.810610079575597, "percentage": 93.77, "elapsed_time": "4:19:40", "remaining_time": "0:17:14"}
+{"current_steps": 2660, "total_steps": 2826, "loss": 0.1742, "lr": 5.3016249302565436e-08, "epoch": 2.821220159151194, "percentage": 94.13, "elapsed_time": "4:20:36", "remaining_time": "0:16:15"}
+{"current_steps": 2670, "total_steps": 2826, "loss": 0.2082, "lr": 4.6876420528833014e-08, "epoch": 2.8318302387267904, "percentage": 94.48, "elapsed_time": "4:21:35", "remaining_time": "0:15:17"}
+{"current_steps": 2680, "total_steps": 2826, "loss": 0.1805, "lr": 4.111097890026089e-08, "epoch": 2.8424403183023874, "percentage": 94.83, "elapsed_time": "4:22:35", "remaining_time": "0:14:18"}
+{"current_steps": 2690, "total_steps": 2826, "loss": 0.2058, "lr": 3.5720804318395976e-08, "epoch": 2.853050397877984, "percentage": 95.19, "elapsed_time": "4:23:34", "remaining_time": "0:13:19"}
+{"current_steps": 2700, "total_steps": 2826, "loss": 0.2027, "lr": 3.0706719412839926e-08, "epoch": 2.863660477453581, "percentage": 95.54, "elapsed_time": "4:24:32", "remaining_time": "0:12:20"}
+{"current_steps": 2710, "total_steps": 2826, "loss": 0.1941, "lr": 2.6069489415703197e-08, "epoch": 2.8742705570291776, "percentage": 95.9, "elapsed_time": "4:25:32", "remaining_time": "0:11:21"}
+{"current_steps": 2720, "total_steps": 2826, "loss": 0.2029, "lr": 2.18098220448168e-08, "epoch": 2.8848806366047746, "percentage": 96.25, "elapsed_time": "4:26:30", "remaining_time": "0:10:23"}
+{"current_steps": 2730, "total_steps": 2826, "loss": 0.2062, "lr": 1.7928367395725066e-08, "epoch": 2.8954907161803716, "percentage": 96.6, "elapsed_time": "4:27:27", "remaining_time": "0:09:24"}
+{"current_steps": 2740, "total_steps": 2826, "loss": 0.1873, "lr": 1.442571784246699e-08, "epoch": 2.906100795755968, "percentage": 96.96, "elapsed_time": "4:28:27", "remaining_time": "0:08:25"}
+{"current_steps": 2750, "total_steps": 2826, "loss": 0.1653, "lr": 1.1302407947173522e-08, "epoch": 2.916710875331565, "percentage": 97.31, "elapsed_time": "4:29:27", "remaining_time": "0:07:26"}
+{"current_steps": 2760, "total_steps": 2826, "loss": 0.1743, "lr": 8.558914378481996e-09, "epoch": 2.9273209549071617, "percentage": 97.66, "elapsed_time": "4:30:28", "remaining_time": "0:06:28"}
+{"current_steps": 2770, "total_steps": 2826, "loss": 0.1821, "lr": 6.195655838790726e-09, "epoch": 2.9379310344827587, "percentage": 98.02, "elapsed_time": "4:31:26", "remaining_time": "0:05:29"}
+{"current_steps": 2780, "total_steps": 2826, "loss": 0.1954, "lr": 4.212993000356491e-09, "epoch": 2.9485411140583553, "percentage": 98.37, "elapsed_time": "4:32:26", "remaining_time": "0:04:30"}
+{"current_steps": 2790, "total_steps": 2826, "loss": 0.1925, "lr": 2.611228450250802e-09, "epoch": 2.9591511936339523, "percentage": 98.73, "elapsed_time": "4:33:21", "remaining_time": "0:03:31"}
+{"current_steps": 2800, "total_steps": 2826, "loss": 0.1805, "lr": 1.3906066441798927e-09, "epoch": 2.9697612732095493, "percentage": 99.08, "elapsed_time": "4:34:23", "remaining_time": "0:02:32"}
+{"current_steps": 2810, "total_steps": 2826, "loss": 0.2084, "lr": 5.513138691767839e-10, "epoch": 2.980371352785146, "percentage": 99.43, "elapsed_time": "4:35:21", "remaining_time": "0:01:34"}
+{"current_steps": 2820, "total_steps": 2826, "loss": 0.2115, "lr": 9.347821517069477e-11, "epoch": 2.9909814323607424, "percentage": 99.79, "elapsed_time": "4:36:24", "remaining_time": "0:00:35"}
+{"current_steps": 2826, "total_steps": 2826, "epoch": 2.9973474801061006, "percentage": 100.0, "elapsed_time": "4:37:51", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2017 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9973474801061006,
+  "eval_steps": 500,
+  "global_step": 2826,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010610079575596816,
+      "grad_norm": 4.634474754333496,
+      "learning_rate": 1.5901060070671379e-07,
+      "loss": 0.741,
+      "step": 10
+    },
+    {
+      "epoch": 0.021220159151193633,
+      "grad_norm": 2.9002726078033447,
+      "learning_rate": 3.356890459363958e-07,
+      "loss": 0.5551,
+      "step": 20
+    },
+    {
+      "epoch": 0.03183023872679045,
+      "grad_norm": 4.242003917694092,
+      "learning_rate": 5.123674911660778e-07,
+      "loss": 0.6185,
+      "step": 30
+    },
+    {
+      "epoch": 0.042440318302387266,
+      "grad_norm": 3.8156638145446777,
+      "learning_rate": 6.890459363957598e-07,
+      "loss": 0.6358,
+      "step": 40
+    },
+    {
+      "epoch": 0.05305039787798409,
+      "grad_norm": 3.047624349594116,
+      "learning_rate": 8.657243816254418e-07,
+      "loss": 0.5922,
+      "step": 50
+    },
+    {
+      "epoch": 0.0636604774535809,
+      "grad_norm": 2.2943954467773438,
+      "learning_rate": 1.0424028268551239e-06,
+      "loss": 0.6282,
+      "step": 60
+    },
+    {
+      "epoch": 0.07427055702917772,
+      "grad_norm": 2.831937551498413,
+      "learning_rate": 1.2190812720848057e-06,
+      "loss": 0.5836,
+      "step": 70
+    },
+    {
+      "epoch": 0.08488063660477453,
+      "grad_norm": 3.941297769546509,
+      "learning_rate": 1.3957597173144876e-06,
+      "loss": 0.5836,
+      "step": 80
+    },
+    {
+      "epoch": 0.09549071618037135,
+      "grad_norm": 2.4598379135131836,
+      "learning_rate": 1.5724381625441699e-06,
+      "loss": 0.4983,
+      "step": 90
+    },
+    {
+      "epoch": 0.10610079575596817,
+      "grad_norm": 2.533829927444458,
+      "learning_rate": 1.7491166077738517e-06,
+      "loss": 0.6057,
+      "step": 100
+    },
+    {
+      "epoch": 0.11671087533156499,
+      "grad_norm": 2.412334442138672,
+      "learning_rate": 1.925795053003534e-06,
+      "loss": 0.5135,
+      "step": 110
+    },
+    {
+      "epoch": 0.1273209549071618,
+      "grad_norm": 2.7505877017974854,
+      "learning_rate": 2.1024734982332157e-06,
+      "loss": 0.4844,
+      "step": 120
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 2.701307535171509,
+      "learning_rate": 2.279151943462898e-06,
+      "loss": 0.5386,
+      "step": 130
+    },
+    {
+      "epoch": 0.14854111405835543,
+      "grad_norm": 2.8261961936950684,
+      "learning_rate": 2.45583038869258e-06,
+      "loss": 0.4774,
+      "step": 140
+    },
+    {
+      "epoch": 0.15915119363395225,
+      "grad_norm": 2.4490256309509277,
+      "learning_rate": 2.6325088339222617e-06,
+      "loss": 0.5035,
+      "step": 150
+    },
+    {
+      "epoch": 0.16976127320954906,
+      "grad_norm": 2.418158769607544,
+      "learning_rate": 2.8091872791519436e-06,
+      "loss": 0.4897,
+      "step": 160
+    },
+    {
+      "epoch": 0.18037135278514588,
+      "grad_norm": 3.5972161293029785,
+      "learning_rate": 2.985865724381626e-06,
+      "loss": 0.5196,
+      "step": 170
+    },
+    {
+      "epoch": 0.1909814323607427,
+      "grad_norm": 2.814927577972412,
+      "learning_rate": 3.162544169611308e-06,
+      "loss": 0.4791,
+      "step": 180
+    },
+    {
+      "epoch": 0.20159151193633953,
+      "grad_norm": 2.6151270866394043,
+      "learning_rate": 3.3392226148409896e-06,
+      "loss": 0.5024,
+      "step": 190
+    },
+    {
+      "epoch": 0.21220159151193635,
+      "grad_norm": 2.8331387042999268,
+      "learning_rate": 3.5159010600706715e-06,
+      "loss": 0.5781,
+      "step": 200
+    },
+    {
+      "epoch": 0.22281167108753316,
+      "grad_norm": 2.433027744293213,
+      "learning_rate": 3.6925795053003538e-06,
+      "loss": 0.4186,
+      "step": 210
+    },
+    {
+      "epoch": 0.23342175066312998,
+      "grad_norm": 2.671696186065674,
+      "learning_rate": 3.869257950530036e-06,
+      "loss": 0.4819,
+      "step": 220
+    },
+    {
+      "epoch": 0.2440318302387268,
+      "grad_norm": 2.5337982177734375,
+      "learning_rate": 4.045936395759718e-06,
+      "loss": 0.547,
+      "step": 230
+    },
+    {
+      "epoch": 0.2546419098143236,
+      "grad_norm": 2.2034990787506104,
+      "learning_rate": 4.222614840989399e-06,
+      "loss": 0.5603,
+      "step": 240
+    },
+    {
+      "epoch": 0.26525198938992045,
+      "grad_norm": 2.2893121242523193,
+      "learning_rate": 4.399293286219082e-06,
+      "loss": 0.4483,
+      "step": 250
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 1.8757219314575195,
+      "learning_rate": 4.575971731448763e-06,
+      "loss": 0.5178,
+      "step": 260
+    },
+    {
+      "epoch": 0.2864721485411141,
+      "grad_norm": 2.3748602867126465,
+      "learning_rate": 4.752650176678445e-06,
+      "loss": 0.5264,
+      "step": 270
+    },
+    {
+      "epoch": 0.29708222811671087,
+      "grad_norm": 3.0481033325195312,
+      "learning_rate": 4.929328621908128e-06,
+      "loss": 0.5124,
+      "step": 280
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 2.682847023010254,
+      "learning_rate": 4.99993132201408e-06,
+      "loss": 0.4977,
+      "step": 290
+    },
+    {
+      "epoch": 0.3183023872679045,
+      "grad_norm": 2.472842216491699,
+      "learning_rate": 4.9995116368759e-06,
+      "loss": 0.5005,
+      "step": 300
+    },
+    {
+      "epoch": 0.32891246684350134,
+      "grad_norm": 2.582815647125244,
+      "learning_rate": 4.998710485009401e-06,
+      "loss": 0.4857,
+      "step": 310
+    },
+    {
+      "epoch": 0.3395225464190981,
+      "grad_norm": 2.3572824001312256,
+      "learning_rate": 4.99752798868358e-06,
+      "loss": 0.4637,
+      "step": 320
+    },
+    {
+      "epoch": 0.35013262599469497,
+      "grad_norm": 2.3432295322418213,
+      "learning_rate": 4.99596432836689e-06,
+      "loss": 0.4775,
+      "step": 330
+    },
+    {
+      "epoch": 0.36074270557029176,
+      "grad_norm": 2.7486777305603027,
+      "learning_rate": 4.994019742699705e-06,
+      "loss": 0.5779,
+      "step": 340
+    },
+    {
+      "epoch": 0.3713527851458886,
+      "grad_norm": 2.3831562995910645,
+      "learning_rate": 4.991694528457891e-06,
+      "loss": 0.5057,
+      "step": 350
+    },
+    {
+      "epoch": 0.3819628647214854,
+      "grad_norm": 2.5414721965789795,
+      "learning_rate": 4.988989040507518e-06,
+      "loss": 0.5313,
+      "step": 360
+    },
+    {
+      "epoch": 0.3925729442970822,
+      "grad_norm": 2.4140472412109375,
+      "learning_rate": 4.985903691750697e-06,
+      "loss": 0.4441,
+      "step": 370
+    },
+    {
+      "epoch": 0.40318302387267907,
+      "grad_norm": 2.4907593727111816,
+      "learning_rate": 4.982438953062572e-06,
+      "loss": 0.4778,
+      "step": 380
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 2.579932928085327,
+      "learning_rate": 4.978595353219449e-06,
+      "loss": 0.4848,
+      "step": 390
+    },
+    {
+      "epoch": 0.4244031830238727,
+      "grad_norm": 2.5512266159057617,
+      "learning_rate": 4.974373478818098e-06,
+      "loss": 0.4891,
+      "step": 400
+    },
+    {
+      "epoch": 0.4350132625994695,
+      "grad_norm": 2.3293063640594482,
+      "learning_rate": 4.969773974186235e-06,
+      "loss": 0.4954,
+      "step": 410
+    },
+    {
+      "epoch": 0.44562334217506633,
+      "grad_norm": 2.6347479820251465,
+      "learning_rate": 4.964797541284175e-06,
+      "loss": 0.5353,
+      "step": 420
+    },
+    {
+      "epoch": 0.4562334217506631,
+      "grad_norm": 2.7719151973724365,
+      "learning_rate": 4.959444939597712e-06,
+      "loss": 0.5726,
+      "step": 430
+    },
+    {
+      "epoch": 0.46684350132625996,
+      "grad_norm": 2.1757211685180664,
+      "learning_rate": 4.953716986022204e-06,
+      "loss": 0.5642,
+      "step": 440
+    },
+    {
+      "epoch": 0.47745358090185674,
+      "grad_norm": 2.432244300842285,
+      "learning_rate": 4.947614554737904e-06,
+      "loss": 0.4429,
+      "step": 450
+    },
+    {
+      "epoch": 0.4880636604774536,
+      "grad_norm": 1.972844123840332,
+      "learning_rate": 4.941138577076538e-06,
+      "loss": 0.4683,
+      "step": 460
+    },
+    {
+      "epoch": 0.4986737400530504,
+      "grad_norm": 2.484992742538452,
+      "learning_rate": 4.934290041379182e-06,
+      "loss": 0.4385,
+      "step": 470
+    },
+    {
+      "epoch": 0.5092838196286472,
+      "grad_norm": 2.0424418449401855,
+      "learning_rate": 4.92706999284541e-06,
+      "loss": 0.4935,
+      "step": 480
+    },
+    {
+      "epoch": 0.519893899204244,
+      "grad_norm": 2.3754308223724365,
+      "learning_rate": 4.9194795333737925e-06,
+      "loss": 0.4548,
+      "step": 490
+    },
+    {
+      "epoch": 0.5305039787798409,
+      "grad_norm": 3.0801432132720947,
+      "learning_rate": 4.911519821393718e-06,
+      "loss": 0.5486,
+      "step": 500
+    },
+    {
+      "epoch": 0.5411140583554377,
+      "grad_norm": 2.2712507247924805,
+      "learning_rate": 4.9031920716886035e-06,
+      "loss": 0.5121,
+      "step": 510
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 2.0000548362731934,
+      "learning_rate": 4.894497555210499e-06,
+      "loss": 0.4495,
+      "step": 520
+    },
+    {
+      "epoch": 0.5623342175066313,
+      "grad_norm": 2.590303897857666,
+      "learning_rate": 4.8854375988861134e-06,
+      "loss": 0.5028,
+      "step": 530
+    },
+    {
+      "epoch": 0.5729442970822282,
+      "grad_norm": 2.377298355102539,
+      "learning_rate": 4.87601358541431e-06,
+      "loss": 0.5193,
+      "step": 540
+    },
+    {
+      "epoch": 0.583554376657825,
+      "grad_norm": 2.966008186340332,
+      "learning_rate": 4.8662269530550825e-06,
+      "loss": 0.545,
+      "step": 550
+    },
+    {
+      "epoch": 0.5941644562334217,
+      "grad_norm": 2.250293254852295,
+      "learning_rate": 4.856079195410046e-06,
+      "loss": 0.5219,
+      "step": 560
+    },
+    {
+      "epoch": 0.6047745358090185,
+      "grad_norm": 2.437361240386963,
+      "learning_rate": 4.845571861194501e-06,
+      "loss": 0.4725,
+      "step": 570
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 2.435994863510132,
+      "learning_rate": 4.834706554001065e-06,
+      "loss": 0.4232,
+      "step": 580
+    },
+    {
+      "epoch": 0.6259946949602122,
+      "grad_norm": 2.705902099609375,
+      "learning_rate": 4.823484932054937e-06,
+      "loss": 0.4834,
+      "step": 590
+    },
+    {
+      "epoch": 0.636604774535809,
+      "grad_norm": 2.1471517086029053,
+      "learning_rate": 4.811908707960832e-06,
+      "loss": 0.5302,
+      "step": 600
+    },
+    {
+      "epoch": 0.6472148541114059,
+      "grad_norm": 2.0760443210601807,
+      "learning_rate": 4.799979648441602e-06,
+      "loss": 0.494,
+      "step": 610
+    },
+    {
+      "epoch": 0.6578249336870027,
+      "grad_norm": 2.334944009780884,
+      "learning_rate": 4.787699574068611e-06,
+      "loss": 0.487,
+      "step": 620
+    },
+    {
+      "epoch": 0.6684350132625995,
+      "grad_norm": 2.3444855213165283,
+      "learning_rate": 4.775070358983881e-06,
+      "loss": 0.4911,
+      "step": 630
+    },
+    {
+      "epoch": 0.6790450928381963,
+      "grad_norm": 2.127737045288086,
+      "learning_rate": 4.7620939306140696e-06,
+      "loss": 0.4744,
+      "step": 640
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 2.2132568359375,
+      "learning_rate": 4.748772269376312e-06,
+      "loss": 0.4789,
+      "step": 650
+    },
+    {
+      "epoch": 0.7002652519893899,
+      "grad_norm": 1.9452372789382935,
+      "learning_rate": 4.735107408375977e-06,
+      "loss": 0.488,
+      "step": 660
+    },
+    {
+      "epoch": 0.7108753315649867,
+      "grad_norm": 2.7268893718719482,
+      "learning_rate": 4.721101433096381e-06,
+      "loss": 0.4462,
+      "step": 670
+    },
+    {
+      "epoch": 0.7214854111405835,
+      "grad_norm": 2.1095452308654785,
+      "learning_rate": 4.706756481080511e-06,
+      "loss": 0.5087,
+      "step": 680
+    },
+    {
+      "epoch": 0.7320954907161804,
+      "grad_norm": 2.278555154800415,
+      "learning_rate": 4.692074741604795e-06,
+      "loss": 0.5304,
+      "step": 690
+    },
+    {
+      "epoch": 0.7427055702917772,
+      "grad_norm": 2.455960512161255,
+      "learning_rate": 4.677058455344989e-06,
+      "loss": 0.5177,
+      "step": 700
+    },
+    {
+      "epoch": 0.753315649867374,
+      "grad_norm": 2.1136856079101562,
+      "learning_rate": 4.661709914034209e-06,
+      "loss": 0.4841,
+      "step": 710
+    },
+    {
+      "epoch": 0.7639257294429708,
+      "grad_norm": 2.296614646911621,
+      "learning_rate": 4.646031460113175e-06,
+      "loss": 0.4544,
+      "step": 720
+    },
+    {
+      "epoch": 0.7745358090185677,
+      "grad_norm": 1.8733782768249512,
+      "learning_rate": 4.630025486372715e-06,
+      "loss": 0.4715,
+      "step": 730
+    },
+    {
+      "epoch": 0.7851458885941645,
+      "grad_norm": 2.526837110519409,
+      "learning_rate": 4.613694435588589e-06,
+      "loss": 0.4824,
+      "step": 740
+    },
+    {
+      "epoch": 0.7957559681697612,
+      "grad_norm": 2.2026150226593018,
+      "learning_rate": 4.597040800148679e-06,
+      "loss": 0.4852,
+      "step": 750
+    },
+    {
+      "epoch": 0.8063660477453581,
+      "grad_norm": 2.214277744293213,
+      "learning_rate": 4.580067121672607e-06,
+      "loss": 0.4134,
+      "step": 760
+    },
+    {
+      "epoch": 0.8169761273209549,
+      "grad_norm": 2.623305559158325,
+      "learning_rate": 4.562775990623847e-06,
+      "loss": 0.4493,
+      "step": 770
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 2.9433794021606445,
+      "learning_rate": 4.5451700459143735e-06,
+      "loss": 0.5255,
+      "step": 780
+    },
+    {
+      "epoch": 0.8381962864721485,
+      "grad_norm": 2.143739938735962,
+      "learning_rate": 4.527251974501923e-06,
+      "loss": 0.4503,
+      "step": 790
+    },
+    {
+      "epoch": 0.8488063660477454,
+      "grad_norm": 2.1592986583709717,
+      "learning_rate": 4.509024510979917e-06,
+      "loss": 0.4636,
+      "step": 800
+    },
+    {
+      "epoch": 0.8594164456233422,
+      "grad_norm": 2.2622759342193604,
+      "learning_rate": 4.4904904371601176e-06,
+      "loss": 0.4685,
+      "step": 810
+    },
+    {
+      "epoch": 0.870026525198939,
+      "grad_norm": 2.3408522605895996,
+      "learning_rate": 4.4716525816480816e-06,
+      "loss": 0.5248,
+      "step": 820
+    },
+    {
+      "epoch": 0.8806366047745358,
+      "grad_norm": 2.5351459980010986,
+      "learning_rate": 4.4525138194114644e-06,
+      "loss": 0.4747,
+      "step": 830
+    },
+    {
+      "epoch": 0.8912466843501327,
+      "grad_norm": 2.4038591384887695,
+      "learning_rate": 4.4330770713412555e-06,
+      "loss": 0.4198,
+      "step": 840
+    },
+    {
+      "epoch": 0.9018567639257294,
+      "grad_norm": 2.2719292640686035,
+      "learning_rate": 4.413345303805996e-06,
+      "loss": 0.4545,
+      "step": 850
+    },
+    {
+      "epoch": 0.9124668435013262,
+      "grad_norm": 3.1209301948547363,
+      "learning_rate": 4.393321528199072e-06,
+      "loss": 0.5003,
+      "step": 860
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 2.414945125579834,
+      "learning_rate": 4.373008800479118e-06,
+      "loss": 0.472,
+      "step": 870
+    },
+    {
+      "epoch": 0.9336870026525199,
+      "grad_norm": 2.21144437789917,
+      "learning_rate": 4.352410220703629e-06,
+      "loss": 0.4661,
+      "step": 880
+    },
+    {
+      "epoch": 0.9442970822281167,
+      "grad_norm": 2.210827589035034,
+      "learning_rate": 4.331528932555844e-06,
+      "loss": 0.4614,
+      "step": 890
+    },
+    {
+      "epoch": 0.9549071618037135,
+      "grad_norm": 2.403038740158081,
+      "learning_rate": 4.3103681228649626e-06,
+      "loss": 0.4623,
+      "step": 900
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 2.588114023208618,
+      "learning_rate": 4.288931021119788e-06,
+      "loss": 0.4902,
+      "step": 910
+    },
+    {
+      "epoch": 0.9761273209549072,
+      "grad_norm": 2.288691997528076,
+      "learning_rate": 4.267220898975848e-06,
+      "loss": 0.5047,
+      "step": 920
+    },
+    {
+      "epoch": 0.986737400530504,
+      "grad_norm": 2.2487804889678955,
+      "learning_rate": 4.245241069756092e-06,
+      "loss": 0.5358,
+      "step": 930
+    },
+    {
+      "epoch": 0.9973474801061007,
+      "grad_norm": 2.5266008377075195,
+      "learning_rate": 4.222994887945219e-06,
+      "loss": 0.4928,
+      "step": 940
+    },
+    {
+      "epoch": 1.0074270557029177,
+      "grad_norm": 2.5962352752685547,
+      "learning_rate": 4.20048574867773e-06,
+      "loss": 0.3963,
+      "step": 950
+    },
+    {
+      "epoch": 1.0180371352785147,
+      "grad_norm": 2.707613229751587,
+      "learning_rate": 4.1777170872197725e-06,
+      "loss": 0.3125,
+      "step": 960
+    },
+    {
+      "epoch": 1.0286472148541115,
+      "grad_norm": 2.4237964153289795,
+      "learning_rate": 4.1546923784448646e-06,
+      "loss": 0.3457,
+      "step": 970
+    },
+    {
+      "epoch": 1.0392572944297083,
+      "grad_norm": 1.6531928777694702,
+      "learning_rate": 4.1314151363035705e-06,
+      "loss": 0.3029,
+      "step": 980
+    },
+    {
+      "epoch": 1.049867374005305,
+      "grad_norm": 2.1669981479644775,
+      "learning_rate": 4.1078889132872145e-06,
+      "loss": 0.3289,
+      "step": 990
+    },
+    {
+      "epoch": 1.0604774535809018,
+      "grad_norm": 2.445012092590332,
+      "learning_rate": 4.084117299885712e-06,
+      "loss": 0.3234,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0710875331564986,
+      "grad_norm": 2.0615527629852295,
+      "learning_rate": 4.060103924039599e-06,
+      "loss": 0.3139,
+      "step": 1010
+    },
+    {
+      "epoch": 1.0816976127320954,
+      "grad_norm": 1.990400791168213,
+      "learning_rate": 4.035852450586352e-06,
+      "loss": 0.3144,
+      "step": 1020
+    },
+    {
+      "epoch": 1.0923076923076924,
+      "grad_norm": 2.5510122776031494,
+      "learning_rate": 4.011366580701073e-06,
+      "loss": 0.323,
+      "step": 1030
+    },
+    {
+      "epoch": 1.1029177718832892,
+      "grad_norm": 2.462083101272583,
+      "learning_rate": 3.9866500513316274e-06,
+      "loss": 0.3694,
+      "step": 1040
+    },
+    {
+      "epoch": 1.113527851458886,
+      "grad_norm": 2.4385085105895996,
+      "learning_rate": 3.961706634628323e-06,
+      "loss": 0.3351,
+      "step": 1050
+    },
+    {
+      "epoch": 1.1241379310344828,
+      "grad_norm": 1.7553578615188599,
+      "learning_rate": 3.936540137368222e-06,
+      "loss": 0.3459,
+      "step": 1060
+    },
+    {
+      "epoch": 1.1347480106100796,
+      "grad_norm": 2.513950824737549,
+      "learning_rate": 3.911154400374159e-06,
+      "loss": 0.3186,
+      "step": 1070
+    },
+    {
+      "epoch": 1.1453580901856764,
+      "grad_norm": 2.6273515224456787,
+      "learning_rate": 3.885553297928573e-06,
+      "loss": 0.3333,
+      "step": 1080
+    },
+    {
+      "epoch": 1.1559681697612731,
+      "grad_norm": 2.4155592918395996,
+      "learning_rate": 3.859740737182222e-06,
+      "loss": 0.3137,
+      "step": 1090
+    },
+    {
+      "epoch": 1.16657824933687,
+      "grad_norm": 2.719611644744873,
+      "learning_rate": 3.833720657557894e-06,
+      "loss": 0.3426,
+      "step": 1100
+    },
+    {
+      "epoch": 1.1771883289124667,
+      "grad_norm": 2.5729358196258545,
+      "learning_rate": 3.807497030149181e-06,
+      "loss": 0.3709,
+      "step": 1110
+    },
+    {
+      "epoch": 1.1877984084880637,
+      "grad_norm": 1.9626141786575317,
+      "learning_rate": 3.7810738571144257e-06,
+      "loss": 0.329,
+      "step": 1120
+    },
+    {
+      "epoch": 1.1984084880636605,
+      "grad_norm": 2.601951837539673,
+      "learning_rate": 3.7544551710659296e-06,
+      "loss": 0.305,
+      "step": 1130
+    },
+    {
+      "epoch": 1.2090185676392573,
+      "grad_norm": 2.4118540287017822,
+      "learning_rate": 3.7276450344545024e-06,
+      "loss": 0.3449,
+      "step": 1140
+    },
+    {
+      "epoch": 1.219628647214854,
+      "grad_norm": 2.5080604553222656,
+      "learning_rate": 3.7006475389494723e-06,
+      "loss": 0.3403,
+      "step": 1150
+    },
+    {
+      "epoch": 1.2302387267904509,
+      "grad_norm": 2.6882951259613037,
+      "learning_rate": 3.6734668048142273e-06,
+      "loss": 0.3342,
+      "step": 1160
+    },
+    {
+      "epoch": 1.2408488063660477,
+      "grad_norm": 2.3755247592926025,
+      "learning_rate": 3.646106980277394e-06,
+      "loss": 0.3589,
+      "step": 1170
+    },
+    {
+      "epoch": 1.2514588859416444,
+      "grad_norm": 2.4138166904449463,
+      "learning_rate": 3.618572240899748e-06,
+      "loss": 0.3447,
+      "step": 1180
+    },
+    {
+      "epoch": 1.2620689655172415,
+      "grad_norm": 2.6930105686187744,
+      "learning_rate": 3.5908667889369603e-06,
+      "loss": 0.3787,
+      "step": 1190
+    },
+    {
+      "epoch": 1.2726790450928382,
+      "grad_norm": 2.732795476913452,
+      "learning_rate": 3.5629948526982563e-06,
+      "loss": 0.3376,
+      "step": 1200
+    },
+    {
+      "epoch": 1.283289124668435,
+      "grad_norm": 1.8468087911605835,
+      "learning_rate": 3.534960685901111e-06,
+      "loss": 0.3461,
+      "step": 1210
+    },
+    {
+      "epoch": 1.2938992042440318,
+      "grad_norm": 2.3408284187316895,
+      "learning_rate": 3.506768567022062e-06,
+      "loss": 0.3396,
+      "step": 1220
+    },
+    {
+      "epoch": 1.3045092838196286,
+      "grad_norm": 2.7420434951782227,
+      "learning_rate": 3.478422798643737e-06,
+      "loss": 0.3364,
+      "step": 1230
+    },
+    {
+      "epoch": 1.3151193633952254,
+      "grad_norm": 2.634403705596924,
+      "learning_rate": 3.4499277067982177e-06,
+      "loss": 0.3126,
+      "step": 1240
+    },
+    {
+      "epoch": 1.3257294429708222,
+      "grad_norm": 2.4217336177825928,
+      "learning_rate": 3.421287640306809e-06,
+      "loss": 0.3092,
+      "step": 1250
+    },
+    {
+      "epoch": 1.3363395225464192,
+      "grad_norm": 1.7107937335968018,
+      "learning_rate": 3.3925069701163406e-06,
+      "loss": 0.3374,
+      "step": 1260
+    },
+    {
+      "epoch": 1.346949602122016,
+      "grad_norm": 2.1515822410583496,
+      "learning_rate": 3.363590088632085e-06,
+      "loss": 0.3436,
+      "step": 1270
+    },
+    {
+      "epoch": 1.3575596816976128,
+      "grad_norm": 2.0105717182159424,
+      "learning_rate": 3.334541409047408e-06,
+      "loss": 0.3283,
+      "step": 1280
+    },
+    {
+      "epoch": 1.3681697612732096,
+      "grad_norm": 1.8952791690826416,
+      "learning_rate": 3.3053653646702422e-06,
+      "loss": 0.358,
+      "step": 1290
+    },
+    {
+      "epoch": 1.3787798408488063,
+      "grad_norm": 1.8639928102493286,
+      "learning_rate": 3.276066408246487e-06,
+      "loss": 0.3084,
+      "step": 1300
+    },
+    {
+      "epoch": 1.3893899204244031,
+      "grad_norm": 2.563251256942749,
+      "learning_rate": 3.2466490112804484e-06,
+      "loss": 0.3508,
+      "step": 1310
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 2.214616060256958,
+      "learning_rate": 3.217117663352417e-06,
+      "loss": 0.3215,
+      "step": 1320
+    },
+    {
+      "epoch": 1.410610079575597,
+      "grad_norm": 1.793468952178955,
+      "learning_rate": 3.187476871433478e-06,
+      "loss": 0.3193,
+      "step": 1330
+    },
+    {
+      "epoch": 1.4212201591511937,
+      "grad_norm": 2.204789638519287,
+      "learning_rate": 3.1577311591976766e-06,
+      "loss": 0.3019,
+      "step": 1340
+    },
+    {
+      "epoch": 1.4318302387267905,
+      "grad_norm": 2.307568311691284,
+      "learning_rate": 3.1278850663316307e-06,
+      "loss": 0.3099,
+      "step": 1350
+    },
+    {
+      "epoch": 1.4424403183023873,
+      "grad_norm": 2.485848903656006,
+      "learning_rate": 3.0979431478416987e-06,
+      "loss": 0.3085,
+      "step": 1360
+    },
+    {
+      "epoch": 1.453050397877984,
+      "grad_norm": 1.953053593635559,
+      "learning_rate": 3.067909973358811e-06,
+      "loss": 0.3211,
+      "step": 1370
+    },
+    {
+      "epoch": 1.4636604774535809,
+      "grad_norm": 2.2350101470947266,
+      "learning_rate": 3.0377901264410673e-06,
+      "loss": 0.3329,
+      "step": 1380
+    },
+    {
+      "epoch": 1.4742705570291776,
+      "grad_norm": 2.542452335357666,
+      "learning_rate": 3.0075882038742133e-06,
+      "loss": 0.3376,
+      "step": 1390
+    },
+    {
+      "epoch": 1.4848806366047747,
+      "grad_norm": 2.3203530311584473,
+      "learning_rate": 2.9773088149700923e-06,
+      "loss": 0.2896,
+      "step": 1400
+    },
+    {
+      "epoch": 1.4954907161803712,
+      "grad_norm": 1.9708584547042847,
+      "learning_rate": 2.9469565808631888e-06,
+      "loss": 0.299,
+      "step": 1410
+    },
+    {
+      "epoch": 1.5061007957559682,
+      "grad_norm": 2.63698148727417,
+      "learning_rate": 2.9165361338053683e-06,
+      "loss": 0.3484,
+      "step": 1420
+    },
+    {
+      "epoch": 1.516710875331565,
+      "grad_norm": 2.091648578643799,
+      "learning_rate": 2.886052116458918e-06,
+      "loss": 0.3316,
+      "step": 1430
+    },
+    {
+      "epoch": 1.5273209549071618,
+      "grad_norm": 1.955355167388916,
+      "learning_rate": 2.8555091811880004e-06,
+      "loss": 0.328,
+      "step": 1440
+    },
+    {
+      "epoch": 1.5379310344827586,
+      "grad_norm": 1.6724951267242432,
+      "learning_rate": 2.8249119893486252e-06,
+      "loss": 0.3215,
+      "step": 1450
+    },
+    {
+      "epoch": 1.5485411140583554,
+      "grad_norm": 2.1872570514678955,
+      "learning_rate": 2.7942652105772516e-06,
+      "loss": 0.3118,
+      "step": 1460
+    },
+    {
+      "epoch": 1.5591511936339524,
+      "grad_norm": 3.0710208415985107,
+      "learning_rate": 2.7635735220781214e-06,
+      "loss": 0.2973,
+      "step": 1470
+    },
+    {
+      "epoch": 1.569761273209549,
+      "grad_norm": 2.357663631439209,
+      "learning_rate": 2.7328416079094412e-06,
+      "loss": 0.3423,
+      "step": 1480
+    },
+    {
+      "epoch": 1.580371352785146,
+      "grad_norm": 2.2559144496917725,
+      "learning_rate": 2.7020741582685217e-06,
+      "loss": 0.3211,
+      "step": 1490
+    },
+    {
+      "epoch": 1.5909814323607427,
+      "grad_norm": 2.0730817317962646,
+      "learning_rate": 2.6712758687759706e-06,
+      "loss": 0.2733,
+      "step": 1500
+    },
+    {
+      "epoch": 1.6015915119363395,
+      "grad_norm": 2.6119141578674316,
+      "learning_rate": 2.6404514397590657e-06,
+      "loss": 0.338,
+      "step": 1510
+    },
+    {
+      "epoch": 1.6122015915119363,
+      "grad_norm": 2.315875768661499,
+      "learning_rate": 2.6096055755344113e-06,
+      "loss": 0.3124,
+      "step": 1520
+    },
+    {
+      "epoch": 1.622811671087533,
+      "grad_norm": 2.2880892753601074,
+      "learning_rate": 2.578742983689973e-06,
+      "loss": 0.3538,
+      "step": 1530
+    },
+    {
+      "epoch": 1.6334217506631301,
+      "grad_norm": 2.2615041732788086,
+      "learning_rate": 2.547868374366631e-06,
+      "loss": 0.3353,
+      "step": 1540
+    },
+    {
+      "epoch": 1.6440318302387267,
+      "grad_norm": 1.9062315225601196,
+      "learning_rate": 2.5169864595393295e-06,
+      "loss": 0.302,
+      "step": 1550
+    },
+    {
+      "epoch": 1.6546419098143237,
+      "grad_norm": 2.7016942501068115,
+      "learning_rate": 2.4861019522979537e-06,
+      "loss": 0.3124,
+      "step": 1560
+    },
+    {
+      "epoch": 1.6652519893899205,
+      "grad_norm": 2.4618184566497803,
+      "learning_rate": 2.455219566128034e-06,
+      "loss": 0.3497,
+      "step": 1570
+    },
+    {
+      "epoch": 1.6758620689655173,
+      "grad_norm": 2.8924951553344727,
+      "learning_rate": 2.4243440141913905e-06,
+      "loss": 0.3233,
+      "step": 1580
+    },
+    {
+      "epoch": 1.686472148541114,
+      "grad_norm": 2.32255482673645,
+      "learning_rate": 2.393480008606825e-06,
+      "loss": 0.3067,
+      "step": 1590
+    },
+    {
+      "epoch": 1.6970822281167108,
+      "grad_norm": 1.8984359502792358,
+      "learning_rate": 2.3626322597309774e-06,
+      "loss": 0.2893,
+      "step": 1600
+    },
+    {
+      "epoch": 1.7076923076923078,
+      "grad_norm": 1.8360289335250854,
+      "learning_rate": 2.331805475439445e-06,
+      "loss": 0.2825,
+      "step": 1610
+    },
+    {
+      "epoch": 1.7183023872679044,
+      "grad_norm": 2.331998109817505,
+      "learning_rate": 2.3010043604082824e-06,
+      "loss": 0.3379,
+      "step": 1620
+    },
+    {
+      "epoch": 1.7289124668435014,
+      "grad_norm": 2.3304574489593506,
+      "learning_rate": 2.2702336153959925e-06,
+      "loss": 0.301,
+      "step": 1630
+    },
+    {
+      "epoch": 1.739522546419098,
+      "grad_norm": 2.534090518951416,
+      "learning_rate": 2.2394979365261134e-06,
+      "loss": 0.404,
+      "step": 1640
+    },
+    {
+      "epoch": 1.750132625994695,
+      "grad_norm": 2.273122549057007,
+      "learning_rate": 2.208802014570507e-06,
+      "loss": 0.3242,
+      "step": 1650
+    },
+    {
+      "epoch": 1.7607427055702918,
+      "grad_norm": 1.8859643936157227,
+      "learning_rate": 2.1781505342334775e-06,
+      "loss": 0.3152,
+      "step": 1660
+    },
+    {
+      "epoch": 1.7713527851458886,
+      "grad_norm": 2.567715644836426,
+      "learning_rate": 2.147548173436805e-06,
+      "loss": 0.3302,
+      "step": 1670
+    },
+    {
+      "epoch": 1.7819628647214856,
+      "grad_norm": 2.7930519580841064,
+      "learning_rate": 2.116999602605814e-06,
+      "loss": 0.293,
+      "step": 1680
+    },
+    {
+      "epoch": 1.7925729442970821,
+      "grad_norm": 2.646296262741089,
+      "learning_rate": 2.086509483956594e-06,
+      "loss": 0.2683,
+      "step": 1690
+    },
+    {
+      "epoch": 1.8031830238726791,
+      "grad_norm": 2.3010053634643555,
+      "learning_rate": 2.056082470784469e-06,
+      "loss": 0.313,
+      "step": 1700
+    },
+    {
+      "epoch": 1.8137931034482757,
+      "grad_norm": 2.3864669799804688,
+      "learning_rate": 2.0257232067538213e-06,
+      "loss": 0.262,
+      "step": 1710
+    },
+    {
+      "epoch": 1.8244031830238727,
+      "grad_norm": 2.63028883934021,
+      "learning_rate": 1.9954363251894007e-06,
+      "loss": 0.3457,
+      "step": 1720
+    },
+    {
+      "epoch": 1.8350132625994695,
+      "grad_norm": 2.0011484622955322,
+      "learning_rate": 1.9652264483691933e-06,
+      "loss": 0.2739,
+      "step": 1730
+    },
+    {
+      "epoch": 1.8456233421750663,
+      "grad_norm": 2.6818690299987793,
+      "learning_rate": 1.9350981868189944e-06,
+      "loss": 0.3109,
+      "step": 1740
+    },
+    {
+      "epoch": 1.856233421750663,
+      "grad_norm": 2.6978225708007812,
+      "learning_rate": 1.9050561386087618e-06,
+      "loss": 0.3269,
+      "step": 1750
+    },
+    {
+      "epoch": 1.8668435013262599,
+      "grad_norm": 2.578031301498413,
+      "learning_rate": 1.8751048886508711e-06,
+      "loss": 0.3617,
+      "step": 1760
+    },
+    {
+      "epoch": 1.8774535809018569,
+      "grad_norm": 2.5525052547454834,
+      "learning_rate": 1.8452490080003888e-06,
+      "loss": 0.3228,
+      "step": 1770
+    },
+    {
+      "epoch": 1.8880636604774534,
+      "grad_norm": 2.1095635890960693,
+      "learning_rate": 1.8154930531574521e-06,
+      "loss": 0.2857,
+      "step": 1780
+    },
+    {
+      "epoch": 1.8986737400530505,
+      "grad_norm": 2.3965845108032227,
+      "learning_rate": 1.785841565371868e-06,
+      "loss": 0.3622,
+      "step": 1790
+    },
+    {
+      "epoch": 1.9092838196286472,
+      "grad_norm": 2.293715238571167,
+      "learning_rate": 1.7562990699500482e-06,
+      "loss": 0.3031,
+      "step": 1800
+    },
+    {
+      "epoch": 1.919893899204244,
+      "grad_norm": 2.026015281677246,
+      "learning_rate": 1.7268700755643708e-06,
+      "loss": 0.3019,
+      "step": 1810
+    },
+    {
+      "epoch": 1.9305039787798408,
+      "grad_norm": 1.7175791263580322,
+      "learning_rate": 1.6975590735650812e-06,
+      "loss": 0.3047,
+      "step": 1820
+    },
+    {
+      "epoch": 1.9411140583554376,
+      "grad_norm": 2.0024490356445312,
+      "learning_rate": 1.668370537294841e-06,
+      "loss": 0.3048,
+      "step": 1830
+    },
+    {
+      "epoch": 1.9517241379310346,
+      "grad_norm": 2.8226239681243896,
+      "learning_rate": 1.6393089214060204e-06,
+      "loss": 0.3205,
+      "step": 1840
+    },
+    {
+      "epoch": 1.9623342175066312,
+      "grad_norm": 1.9452221393585205,
+      "learning_rate": 1.6103786611808414e-06,
+      "loss": 0.321,
+      "step": 1850
+    },
+    {
+      "epoch": 1.9729442970822282,
+      "grad_norm": 2.304274320602417,
+      "learning_rate": 1.5815841718544884e-06,
+      "loss": 0.2954,
+      "step": 1860
+    },
+    {
+      "epoch": 1.983554376657825,
+      "grad_norm": 2.502206802368164,
+      "learning_rate": 1.5529298479412636e-06,
+      "loss": 0.2945,
+      "step": 1870
+    },
+    {
+      "epoch": 1.9941644562334218,
+      "grad_norm": 2.5796189308166504,
+      "learning_rate": 1.524420062563912e-06,
+      "loss": 0.3291,
+      "step": 1880
+    },
+    {
+      "epoch": 2.004244031830239,
+      "grad_norm": 1.9198871850967407,
+      "learning_rate": 1.4960591667862163e-06,
+      "loss": 0.234,
+      "step": 1890
+    },
+    {
+      "epoch": 2.0148541114058354,
+      "grad_norm": 1.7082706689834595,
+      "learning_rate": 1.4678514889489464e-06,
+      "loss": 0.1943,
+      "step": 1900
+    },
+    {
+      "epoch": 2.0254641909814324,
+      "grad_norm": 1.8571817874908447,
+      "learning_rate": 1.4398013340092864e-06,
+      "loss": 0.1911,
+      "step": 1910
+    },
+    {
+      "epoch": 2.0360742705570294,
+      "grad_norm": 2.454561233520508,
+      "learning_rate": 1.4119129828838275e-06,
+      "loss": 0.1895,
+      "step": 1920
+    },
+    {
+      "epoch": 2.046684350132626,
+      "grad_norm": 2.3714683055877686,
+      "learning_rate": 1.384190691795226e-06,
+      "loss": 0.2177,
+      "step": 1930
+    },
+    {
+      "epoch": 2.057294429708223,
+      "grad_norm": 2.1356313228607178,
+      "learning_rate": 1.3566386916226373e-06,
+      "loss": 0.2252,
+      "step": 1940
+    },
+    {
+      "epoch": 2.0679045092838195,
+      "grad_norm": 2.446906089782715,
+      "learning_rate": 1.3292611872560134e-06,
+      "loss": 0.1982,
+      "step": 1950
+    },
+    {
+      "epoch": 2.0785145888594165,
+      "grad_norm": 2.1040875911712646,
+      "learning_rate": 1.302062356954365e-06,
+      "loss": 0.1696,
+      "step": 1960
+    },
+    {
+      "epoch": 2.089124668435013,
+      "grad_norm": 2.220742702484131,
+      "learning_rate": 1.2750463517080922e-06,
+      "loss": 0.1936,
+      "step": 1970
+    },
+    {
+      "epoch": 2.09973474801061,
+      "grad_norm": 2.7784054279327393,
+      "learning_rate": 1.2482172946054753e-06,
+      "loss": 0.1604,
+      "step": 1980
+    },
+    {
+      "epoch": 2.110344827586207,
+      "grad_norm": 2.0539498329162598,
+      "learning_rate": 1.2215792802034187e-06,
+      "loss": 0.2069,
+      "step": 1990
+    },
+    {
+      "epoch": 2.1209549071618037,
+      "grad_norm": 1.8337138891220093,
+      "learning_rate": 1.1951363739025618e-06,
+      "loss": 0.1964,
+      "step": 2000
+    },
+    {
+      "epoch": 2.1315649867374007,
+      "grad_norm": 1.7631642818450928,
+      "learning_rate": 1.168892611326827e-06,
+      "loss": 0.1871,
+      "step": 2010
+    },
+    {
+      "epoch": 2.1421750663129973,
+      "grad_norm": 2.386589527130127,
+      "learning_rate": 1.1428519977075136e-06,
+      "loss": 0.2595,
+      "step": 2020
+    },
+    {
+      "epoch": 2.1527851458885943,
+      "grad_norm": 2.553382635116577,
+      "learning_rate": 1.1170185072720434e-06,
+      "loss": 0.185,
+      "step": 2030
+    },
+    {
+      "epoch": 2.163395225464191,
+      "grad_norm": 2.870973825454712,
+      "learning_rate": 1.091396082637419e-06,
+      "loss": 0.228,
+      "step": 2040
+    },
+    {
+      "epoch": 2.174005305039788,
+      "grad_norm": 2.643745183944702,
+      "learning_rate": 1.065988634208516e-06,
+      "loss": 0.2098,
+      "step": 2050
+    },
+    {
+      "epoch": 2.184615384615385,
+      "grad_norm": 2.369596481323242,
+      "learning_rate": 1.0408000395812961e-06,
+      "loss": 0.1982,
+      "step": 2060
+    },
+    {
+      "epoch": 2.1952254641909814,
+      "grad_norm": 2.1093883514404297,
+      "learning_rate": 1.0158341429510194e-06,
+      "loss": 0.1844,
+      "step": 2070
+    },
+    {
+      "epoch": 2.2058355437665784,
+      "grad_norm": 1.951935052871704,
+      "learning_rate": 9.910947545255523e-07,
+      "loss": 0.1654,
+      "step": 2080
+    },
+    {
+      "epoch": 2.216445623342175,
+      "grad_norm": 2.230781078338623,
+      "learning_rate": 9.665856499438744e-07,
+      "loss": 0.2037,
+      "step": 2090
+    },
+    {
+      "epoch": 2.227055702917772,
+      "grad_norm": 2.6240904331207275,
+      "learning_rate": 9.423105696998491e-07,
+      "loss": 0.2087,
+      "step": 2100
+    },
+    {
+      "epoch": 2.2376657824933686,
+      "grad_norm": 1.712857723236084,
+      "learning_rate": 9.182732185713633e-07,
+      "loss": 0.2105,
+      "step": 2110
+    },
+    {
+      "epoch": 2.2482758620689656,
+      "grad_norm": 2.036086082458496,
+      "learning_rate": 8.94477265054918e-07,
+      "loss": 0.2186,
+      "step": 2120
+    },
+    {
+      "epoch": 2.2588859416445626,
+      "grad_norm": 2.3545398712158203,
+      "learning_rate": 8.709263408057522e-07,
+      "loss": 0.1879,
+      "step": 2130
+    },
+    {
+      "epoch": 2.269496021220159,
+      "grad_norm": 1.9098992347717285,
+      "learning_rate": 8.476240400835972e-07,
+      "loss": 0.2177,
+      "step": 2140
+    },
+    {
+      "epoch": 2.280106100795756,
+      "grad_norm": 2.107959270477295,
+      "learning_rate": 8.245739192041311e-07,
+      "loss": 0.165,
+      "step": 2150
+    },
+    {
+      "epoch": 2.2907161803713527,
+      "grad_norm": 2.550719976425171,
+      "learning_rate": 8.017794959962225e-07,
+      "loss": 0.2018,
+      "step": 2160
+    },
+    {
+      "epoch": 2.3013262599469497,
+      "grad_norm": 2.354701280593872,
+      "learning_rate": 7.792442492650587e-07,
+      "loss": 0.1955,
+      "step": 2170
+    },
+    {
+      "epoch": 2.3119363395225463,
+      "grad_norm": 2.3547091484069824,
+      "learning_rate": 7.569716182612177e-07,
+      "loss": 0.1976,
+      "step": 2180
+    },
+    {
+      "epoch": 2.3225464190981433,
+      "grad_norm": 1.4048022031784058,
+      "learning_rate": 7.349650021557839e-07,
+      "loss": 0.1685,
+      "step": 2190
+    },
+    {
+      "epoch": 2.33315649867374,
+      "grad_norm": 2.568500280380249,
+      "learning_rate": 7.132277595215773e-07,
+      "loss": 0.1519,
+      "step": 2200
+    },
+    {
+      "epoch": 2.343766578249337,
+      "grad_norm": 2.205993413925171,
+      "learning_rate": 6.917632078205805e-07,
+      "loss": 0.1573,
+      "step": 2210
+    },
+    {
+      "epoch": 2.3543766578249334,
+      "grad_norm": 2.067505121231079,
+      "learning_rate": 6.705746228976387e-07,
+      "loss": 0.184,
+      "step": 2220
+    },
+    {
+      "epoch": 2.3649867374005304,
+      "grad_norm": 2.4360201358795166,
+      "learning_rate": 6.496652384805125e-07,
+      "loss": 0.1968,
+      "step": 2230
+    },
+    {
+      "epoch": 2.3755968169761275,
+      "grad_norm": 2.042179584503174,
+      "learning_rate": 6.290382456863584e-07,
+      "loss": 0.1846,
+      "step": 2240
+    },
+    {
+      "epoch": 2.386206896551724,
+      "grad_norm": 2.849271535873413,
+      "learning_rate": 6.086967925347075e-07,
+      "loss": 0.1858,
+      "step": 2250
+    },
+    {
+      "epoch": 2.396816976127321,
+      "grad_norm": 2.0765082836151123,
+      "learning_rate": 5.88643983467033e-07,
+      "loss": 0.1837,
+      "step": 2260
+    },
+    {
+      "epoch": 2.4074270557029176,
+      "grad_norm": 1.9958840608596802,
+      "learning_rate": 5.688828788729547e-07,
+      "loss": 0.1659,
+      "step": 2270
+    },
+    {
+      "epoch": 2.4180371352785146,
+      "grad_norm": 2.253602981567383,
+      "learning_rate": 5.494164946231747e-07,
+      "loss": 0.2095,
+      "step": 2280
+    },
+    {
+      "epoch": 2.428647214854111,
+      "grad_norm": 1.5552992820739746,
+      "learning_rate": 5.302478016092075e-07,
+      "loss": 0.1862,
+      "step": 2290
+    },
+    {
+      "epoch": 2.439257294429708,
+      "grad_norm": 2.721445322036743,
+      "learning_rate": 5.113797252899728e-07,
+      "loss": 0.2085,
+      "step": 2300
+    },
+    {
+      "epoch": 2.449867374005305,
+      "grad_norm": 2.3488707542419434,
+      "learning_rate": 4.928151452453184e-07,
+      "loss": 0.1914,
+      "step": 2310
+    },
+    {
+      "epoch": 2.4604774535809018,
+      "grad_norm": 2.49068021774292,
+      "learning_rate": 4.745568947365542e-07,
+      "loss": 0.1718,
+      "step": 2320
+    },
+    {
+      "epoch": 2.4710875331564988,
+      "grad_norm": 1.4638549089431763,
+      "learning_rate": 4.5660776027404654e-07,
+      "loss": 0.1669,
+      "step": 2330
+    },
+    {
+      "epoch": 2.4816976127320953,
+      "grad_norm": 2.288776159286499,
+      "learning_rate": 4.389704811919507e-07,
+      "loss": 0.1731,
+      "step": 2340
+    },
+    {
+      "epoch": 2.4923076923076923,
+      "grad_norm": 2.385162115097046,
+      "learning_rate": 4.216477492301455e-07,
+      "loss": 0.1802,
+      "step": 2350
+    },
+    {
+      "epoch": 2.502917771883289,
+      "grad_norm": 2.0100815296173096,
+      "learning_rate": 4.0464220812342526e-07,
+      "loss": 0.2232,
+      "step": 2360
+    },
+    {
+      "epoch": 2.513527851458886,
+      "grad_norm": 1.8439091444015503,
+      "learning_rate": 3.87956453198027e-07,
+      "loss": 0.1432,
+      "step": 2370
+    },
+    {
+      "epoch": 2.524137931034483,
+      "grad_norm": 2.3093338012695312,
+      "learning_rate": 3.715930309755389e-07,
+      "loss": 0.1834,
+      "step": 2380
+    },
+    {
+      "epoch": 2.5347480106100795,
+      "grad_norm": 2.3250088691711426,
+      "learning_rate": 3.5555443878425635e-07,
+      "loss": 0.2123,
+      "step": 2390
+    },
+    {
+      "epoch": 2.5453580901856765,
+      "grad_norm": 1.8003133535385132,
+      "learning_rate": 3.398431243780531e-07,
+      "loss": 0.2034,
+      "step": 2400
+    },
+    {
+      "epoch": 2.555968169761273,
+      "grad_norm": 2.8948135375976562,
+      "learning_rate": 3.2446148556281117e-07,
+      "loss": 0.1778,
+      "step": 2410
+    },
+    {
+      "epoch": 2.56657824933687,
+      "grad_norm": 1.8556360006332397,
+      "learning_rate": 3.0941186983047543e-07,
+      "loss": 0.1892,
+      "step": 2420
+    },
+    {
+      "epoch": 2.5771883289124666,
+      "grad_norm": 2.771932363510132,
+      "learning_rate": 2.9469657400078925e-07,
+      "loss": 0.1935,
+      "step": 2430
+    },
+    {
+      "epoch": 2.5877984084880636,
+      "grad_norm": 2.5325114727020264,
+      "learning_rate": 2.8031784387076186e-07,
+      "loss": 0.1858,
+      "step": 2440
+    },
+    {
+      "epoch": 2.5984084880636606,
+      "grad_norm": 2.4069302082061768,
+      "learning_rate": 2.6627787387191934e-07,
+      "loss": 0.2118,
+      "step": 2450
+    },
+    {
+      "epoch": 2.609018567639257,
+      "grad_norm": 2.053656816482544,
+      "learning_rate": 2.5257880673540376e-07,
+      "loss": 0.1929,
+      "step": 2460
+    },
+    {
+      "epoch": 2.6196286472148542,
+      "grad_norm": 1.8820626735687256,
+      "learning_rate": 2.392227331649527e-07,
+      "loss": 0.1745,
+      "step": 2470
+    },
+    {
+      "epoch": 2.630238726790451,
+      "grad_norm": 1.9418586492538452,
+      "learning_rate": 2.2621169151782417e-07,
+      "loss": 0.1823,
+      "step": 2480
+    },
+    {
+      "epoch": 2.640848806366048,
+      "grad_norm": 2.519037961959839,
+      "learning_rate": 2.1354766749371093e-07,
+      "loss": 0.2037,
+      "step": 2490
+    },
+    {
+      "epoch": 2.6514588859416444,
+      "grad_norm": 2.010211944580078,
+      "learning_rate": 2.0123259383169031e-07,
+      "loss": 0.2196,
+      "step": 2500
+    },
+    {
+      "epoch": 2.6620689655172414,
+      "grad_norm": 1.9838532209396362,
+      "learning_rate": 1.8926835001525257e-07,
+      "loss": 0.1848,
+      "step": 2510
+    },
+    {
+      "epoch": 2.6726790450928384,
+      "grad_norm": 2.3488149642944336,
+      "learning_rate": 1.776567619854655e-07,
+      "loss": 0.1823,
+      "step": 2520
+    },
+    {
+      "epoch": 2.683289124668435,
+      "grad_norm": 2.839651584625244,
+      "learning_rate": 1.6639960186230293e-07,
+      "loss": 0.2039,
+      "step": 2530
+    },
+    {
+      "epoch": 2.693899204244032,
+      "grad_norm": 2.050480842590332,
+      "learning_rate": 1.5549858767419018e-07,
+      "loss": 0.1796,
+      "step": 2540
+    },
+    {
+      "epoch": 2.7045092838196285,
+      "grad_norm": 1.2738044261932373,
+      "learning_rate": 1.449553830958053e-07,
+      "loss": 0.1893,
+      "step": 2550
+    },
+    {
+      "epoch": 2.7151193633952255,
+      "grad_norm": 1.8912787437438965,
+      "learning_rate": 1.347715971941746e-07,
+      "loss": 0.1947,
+      "step": 2560
+    },
+    {
+      "epoch": 2.725729442970822,
+      "grad_norm": 1.8385730981826782,
+      "learning_rate": 1.2494878418310234e-07,
+      "loss": 0.1744,
+      "step": 2570
+    },
+    {
+      "epoch": 2.736339522546419,
+      "grad_norm": 2.1071712970733643,
+      "learning_rate": 1.1548844318597208e-07,
+      "loss": 0.2351,
+      "step": 2580
+    },
+    {
+      "epoch": 2.746949602122016,
+      "grad_norm": 2.054392099380493,
+      "learning_rate": 1.0639201800695553e-07,
+      "loss": 0.2245,
+      "step": 2590
+    },
+    {
+      "epoch": 2.7575596816976127,
+      "grad_norm": 1.656562328338623,
+      "learning_rate": 9.76608969106646e-08,
+      "loss": 0.2014,
+      "step": 2600
+    },
+    {
+      "epoch": 2.7681697612732097,
+      "grad_norm": 2.6887638568878174,
+      "learning_rate": 8.929641241027937e-08,
+      "loss": 0.1824,
+      "step": 2610
+    },
+    {
+      "epoch": 2.7787798408488062,
+      "grad_norm": 2.4606659412384033,
+      "learning_rate": 8.129984106418354e-08,
+      "loss": 0.1706,
+      "step": 2620
+    },
+    {
+      "epoch": 2.7893899204244033,
+      "grad_norm": 2.5548455715179443,
+      "learning_rate": 7.3672403281142e-08,
+      "loss": 0.2195,
+      "step": 2630
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 1.7952167987823486,
+      "learning_rate": 6.641526313404534e-08,
+      "loss": 0.1748,
+      "step": 2640
+    },
+    {
+      "epoch": 2.810610079575597,
+      "grad_norm": 2.376830816268921,
+      "learning_rate": 5.952952818225416e-08,
+      "loss": 0.2061,
+      "step": 2650
+    },
+    {
+      "epoch": 2.821220159151194,
+      "grad_norm": 1.7183632850646973,
+      "learning_rate": 5.3016249302565436e-08,
+      "loss": 0.1742,
+      "step": 2660
+    },
+    {
+      "epoch": 2.8318302387267904,
+      "grad_norm": 2.11011004447937,
+      "learning_rate": 4.6876420528833014e-08,
+      "loss": 0.2082,
+      "step": 2670
+    },
+    {
+      "epoch": 2.8424403183023874,
+      "grad_norm": 1.8799868822097778,
+      "learning_rate": 4.111097890026089e-08,
+      "loss": 0.1805,
+      "step": 2680
+    },
+    {
+      "epoch": 2.853050397877984,
+      "grad_norm": 2.5171291828155518,
+      "learning_rate": 3.5720804318395976e-08,
+      "loss": 0.2058,
+      "step": 2690
+    },
+    {
+      "epoch": 2.863660477453581,
+      "grad_norm": 2.142263650894165,
+      "learning_rate": 3.0706719412839926e-08,
+      "loss": 0.2027,
+      "step": 2700
+    },
+    {
+      "epoch": 2.8742705570291776,
+      "grad_norm": 2.2124040126800537,
+      "learning_rate": 2.6069489415703197e-08,
+      "loss": 0.1941,
+      "step": 2710
+    },
+    {
+      "epoch": 2.8848806366047746,
+      "grad_norm": 2.033259153366089,
+      "learning_rate": 2.18098220448168e-08,
+      "loss": 0.2029,
+      "step": 2720
+    },
+    {
+      "epoch": 2.8954907161803716,
+      "grad_norm": 2.416912794113159,
+      "learning_rate": 1.7928367395725066e-08,
+      "loss": 0.2062,
+      "step": 2730
+    },
+    {
+      "epoch": 2.906100795755968,
+      "grad_norm": 2.193751096725464,
+      "learning_rate": 1.442571784246699e-08,
+      "loss": 0.1873,
+      "step": 2740
+    },
+    {
+      "epoch": 2.916710875331565,
+      "grad_norm": 1.5729731321334839,
+      "learning_rate": 1.1302407947173522e-08,
+      "loss": 0.1653,
+      "step": 2750
+    },
+    {
+      "epoch": 2.9273209549071617,
+      "grad_norm": 1.7562044858932495,
+      "learning_rate": 8.558914378481996e-09,
+      "loss": 0.1743,
+      "step": 2760
+    },
+    {
+      "epoch": 2.9379310344827587,
+      "grad_norm": 2.183967351913452,
+      "learning_rate": 6.195655838790726e-09,
+      "loss": 0.1821,
+      "step": 2770
+    },
+    {
+      "epoch": 2.9485411140583553,
+      "grad_norm": 1.9312433004379272,
+      "learning_rate": 4.212993000356491e-09,
+      "loss": 0.1954,
+      "step": 2780
+    },
+    {
+      "epoch": 2.9591511936339523,
+      "grad_norm": 2.2055087089538574,
+      "learning_rate": 2.611228450250802e-09,
+      "loss": 0.1925,
+      "step": 2790
+    },
+    {
+      "epoch": 2.9697612732095493,
+      "grad_norm": 1.6606404781341553,
+      "learning_rate": 1.3906066441798927e-09,
+      "loss": 0.1805,
+      "step": 2800
+    },
+    {
+      "epoch": 2.980371352785146,
+      "grad_norm": 2.594404458999634,
+      "learning_rate": 5.513138691767839e-10,
+      "loss": 0.2084,
+      "step": 2810
+    },
+    {
+      "epoch": 2.9909814323607424,
+      "grad_norm": 2.007861375808716,
+      "learning_rate": 9.347821517069477e-11,
+      "loss": 0.2115,
+      "step": 2820
+    },
+    {
+      "epoch": 2.9973474801061006,
+      "step": 2826,
+      "total_flos": 1.0915292825780224e+17,
+      "train_loss": 0.34044326600333263,
+      "train_runtime": 16671.2674,
+      "train_samples_per_second": 2.713,
+      "train_steps_per_second": 0.17
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2826,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 943,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0915292825780224e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27d6ca1d781c71f5e68ee48cf8a625fd3eefbff277275730d357f7f6a9116727
+size 7928