diff --git a/.gitattributes b/.gitattributes
index 9602ec5f2bf8b5653db7bce2477f3c15537815d9..1a264862f13ef5ffe6e921b1676b75fae5082304 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -1214,3 +1214,55 @@ dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_92000/sample.
 dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_94000/sample.png filter=lfs diff=lfs merge=lfs -text
 dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_96000/sample.png filter=lfs diff=lfs merge=lfs -text
 dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_98000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_10000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_100000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_102000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_104000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_12000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_14000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_16000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_18000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_2000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_20000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_22000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_24000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_26000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_28000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_30000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_32000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_34000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_36000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_38000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_4000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_40000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_42000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_44000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_46000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_48000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_50000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_52000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_54000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_56000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_58000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_6000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_60000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_62000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_64000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_66000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_68000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_70000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_72000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_74000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_76000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_78000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_8000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_80000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_82000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_84000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_86000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_88000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_90000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_92000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_94000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_96000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_98000/sample.png filter=lfs diff=lfs merge=lfs -text
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/stdout.txt b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/stdout.txt
new file mode 100644
index 0000000000000000000000000000000000000000..f755521d68b72df92ff9d1c98e95f784de1b5421
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/stdout.txt
@@ -0,0 +1,1874 @@
+INFO - utils.py - 2024-10-24 03:39:30,972 - {'setup': {'method': 'dpsgd-diffusion', 'run_type': 'torchmp', 'n_gpus_per_node': 3, 'n_nodes': 1, 'node_rank': 0, 'master_address': '127.0.0.1', 'master_port': 6025, 'omp_n_threads': 8, 'workdir': 'exp/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27', 'local_rank': 0, 'global_rank': 0, 'global_size': 3, 'root_folder': '.'}, 'public_data': {'name': None, 'num_channels': 3, 'resolution': 32, 'n_classes': 1000, 'train_path': 'dataset/imagenet/imagenet_32', 'selective': {'ratio': 1.0}}, 'sensitive_data': {'name': 'cifar100', 'num_channels': 3, 'resolution': 32, 'n_classes': 100, 'train_path': 'dataset/cifar100/train_32.zip', 'test_path': 'dataset/cifar100/test_32.zip', 'fid_stats': 'dataset/cifar100/fid_stats_32.npz', 'train_num': 'val'}, 'model': {'ckpt': None, 'denoiser_name': 'edm', 'denoiser_network': 'song', 'ema_rate': 0.999, 'network': {'image_size': 32, 'num_in_channels': 3, 'num_out_channels': 3, 'label_dim': 100, 'attn_resolutions': [16], 'ch_mult': [2, 4]}, 'sampler': {'type': 'ddim', 'stochastic': False, 'num_steps': 50, 'tmin': 0.002, 'tmax': 80.0, 'rho': 7.0, 'guid_scale': 0.0, 'snapshot_batch_size': 80, 'fid_batch_size': 256}, 'sampler_fid': {'type': 'ddim', 'stochastic': False, 'num_steps': 250, 'tmin': 0.002, 'tmax': 80.0, 'rho': 7.0, 'guid_scale': 0.0}, 'sampler_acc': {'type': 'ddim', 'stochastic': False, 'num_steps': 250, 'tmin': 0.002, 'tmax': 80.0, 'rho': 7.0, 'guid_scale': 0.0}, 'local_rank': 0, 'global_rank': 0, 'global_size': 3, 'fid_stats': 'dataset/cifar100/fid_stats_32.npz'}, 'pretrain': {'log_dir': 'exp/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/pretrain', 'seed': 0, 'batch_size': 64, 'n_epochs': 1, 'log_freq': 100, 'snapshot_freq': 2000, 'snapshot_threshold': 1, 'save_freq': 100000, 'save_threshold': 1, 'fid_freq': 2000, 'fid_samples': 5000, 'fid_threshold': 1, 'label_random': True, 'optim': {'optimizer': 'Adam', 'params': {'lr': 0.0003, 'weight_decay': 0.0}}, 'loss': {'version': 'edm', 'p_mean': -1.2, 'p_std': 1.2, 'n_noise_samples': 1, 'n_classes': 100}}, 'train': {'log_dir': 'exp/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train', 'seed': 0, 'batch_size': 4096, 'n_epochs': 150, 'partly_finetune': False, 'log_freq': 100, 'snapshot_freq': 2000, 'snapshot_threshold': 1, 'save_freq': 100000, 'save_threshold': 1, 'fid_freq': 2000, 'fid_samples': 5000, 'final_fid_samples': 60000, 'fid_threshold': 1, 'gen': False, 'gen_batch_size': 8192, 'optim': {'optimizer': 'Adam', 'params': {'lr': 0.0003, 'weight_decay': 0.0}}, 'loss': {'version': 'edm', 'p_mean': -1.2, 'p_std': 1.2, 'n_noise_samples': 32, 'n_classes': 100}, 'dp': {'sdq': None, 'max_grad_norm': 1.0, 'delta': 1e-05, 'epsilon': 1.0, 'max_physical_batch_size': 8192, 'n_splits': 64}}, 'gen': {'data_num': 60000, 'batch_size': 1000, 'log_dir': 'exp/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/gen'}, 'eval': {'batch_size': 1000}}
+INFO - dataset_loader.py - 2024-10-24 03:39:32,381 - delta is reset as 2.07404851125286e-06
+INFO - dpsgd_diffusion.py - 2024-10-24 03:39:33,431 - Number of trainable parameters in model: 0
+INFO - dpsgd_diffusion.py - 2024-10-24 03:39:33,431 - Number of total epochs: 150
+INFO - dpsgd_diffusion.py - 2024-10-24 03:39:33,431 - Starting training at step 0
+INFO - dpsgd_diffusion.py - 2024-10-24 03:44:13,383 - Loss: 0.9660, step: 100
+INFO - dpsgd_diffusion.py - 2024-10-24 03:48:10,265 - Loss: 0.8957, step: 200
+INFO - dpsgd_diffusion.py - 2024-10-24 03:51:54,389 - Loss: 0.8921, step: 300
+INFO - dpsgd_diffusion.py - 2024-10-24 03:53:58,663 - Loss: 0.8366, step: 400
+INFO - dpsgd_diffusion.py - 2024-10-24 03:55:41,716 - Loss: 0.8261, step: 500
+INFO - dpsgd_diffusion.py - 2024-10-24 03:57:25,091 - Loss: 0.8379, step: 600
+INFO - dpsgd_diffusion.py - 2024-10-24 03:59:08,774 - Loss: 0.8501, step: 700
+INFO - dpsgd_diffusion.py - 2024-10-24 03:59:12,941 - Eps-value after 1 epochs: 0.1393
+INFO - dpsgd_diffusion.py - 2024-10-24 04:00:50,702 - Loss: 0.7873, step: 800
+INFO - dpsgd_diffusion.py - 2024-10-24 04:02:31,262 - Loss: 0.7650, step: 900
+INFO - dpsgd_diffusion.py - 2024-10-24 04:04:15,148 - Loss: 0.7832, step: 1000
+INFO - dpsgd_diffusion.py - 2024-10-24 04:05:58,039 - Loss: 0.7656, step: 1100
+INFO - dpsgd_diffusion.py - 2024-10-24 04:07:41,878 - Loss: 0.7361, step: 1200
+INFO - dpsgd_diffusion.py - 2024-10-24 04:09:25,905 - Loss: 0.6981, step: 1300
+INFO - dpsgd_diffusion.py - 2024-10-24 04:11:05,136 - Loss: 0.7255, step: 1400
+INFO - dpsgd_diffusion.py - 2024-10-24 04:11:13,090 - Eps-value after 2 epochs: 0.1504
+INFO - dpsgd_diffusion.py - 2024-10-24 04:12:45,329 - Loss: 0.6518, step: 1500
+INFO - dpsgd_diffusion.py - 2024-10-24 04:14:27,803 - Loss: 0.7370, step: 1600
+INFO - dpsgd_diffusion.py - 2024-10-24 04:16:11,965 - Loss: 0.6964, step: 1700
+INFO - dpsgd_diffusion.py - 2024-10-24 04:17:54,011 - Loss: 0.7414, step: 1800
+INFO - dpsgd_diffusion.py - 2024-10-24 04:19:37,731 - Loss: 0.6440, step: 1900
+INFO - dpsgd_diffusion.py - 2024-10-24 04:21:20,666 - Loss: 0.6685, step: 2000
+INFO - dpsgd_diffusion.py - 2024-10-24 04:21:20,762 - Saving snapshot checkpoint and sampling single batch at iteration 2000.
+WARNING - image.py - 2024-10-24 04:21:22,125 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 04:21:53,629 - FID at iteration 2000: 366.724740
+INFO - dpsgd_diffusion.py - 2024-10-24 04:23:38,950 - Loss: 0.6748, step: 2100
+INFO - dpsgd_diffusion.py - 2024-10-24 04:23:51,440 - Eps-value after 3 epochs: 0.1615
+INFO - dpsgd_diffusion.py - 2024-10-24 04:25:25,362 - Loss: 0.6625, step: 2200
+INFO - dpsgd_diffusion.py - 2024-10-24 04:27:06,651 - Loss: 0.6106, step: 2300
+INFO - dpsgd_diffusion.py - 2024-10-24 04:28:48,387 - Loss: 0.5935, step: 2400
+INFO - dpsgd_diffusion.py - 2024-10-24 04:30:30,036 - Loss: 0.6180, step: 2500
+INFO - dpsgd_diffusion.py - 2024-10-24 04:32:10,583 - Loss: 0.6078, step: 2600
+INFO - dpsgd_diffusion.py - 2024-10-24 04:33:51,448 - Loss: 0.5784, step: 2700
+INFO - dpsgd_diffusion.py - 2024-10-24 04:35:32,699 - Loss: 0.5459, step: 2800
+INFO - dpsgd_diffusion.py - 2024-10-24 04:35:49,189 - Eps-value after 4 epochs: 0.1726
+INFO - dpsgd_diffusion.py - 2024-10-24 04:37:16,324 - Loss: 0.5685, step: 2900
+INFO - dpsgd_diffusion.py - 2024-10-24 04:38:58,067 - Loss: 0.5691, step: 3000
+INFO - dpsgd_diffusion.py - 2024-10-24 04:40:39,835 - Loss: 0.4870, step: 3100
+INFO - dpsgd_diffusion.py - 2024-10-24 04:42:21,963 - Loss: 0.5666, step: 3200
+INFO - dpsgd_diffusion.py - 2024-10-24 04:44:00,329 - Loss: 0.4965, step: 3300
+INFO - dpsgd_diffusion.py - 2024-10-24 04:45:42,309 - Loss: 0.5066, step: 3400
+INFO - dpsgd_diffusion.py - 2024-10-24 04:47:26,111 - Loss: 0.4977, step: 3500
+INFO - dpsgd_diffusion.py - 2024-10-24 04:47:45,982 - Eps-value after 5 epochs: 0.1836
+INFO - dpsgd_diffusion.py - 2024-10-24 04:49:07,592 - Loss: 0.4756, step: 3600
+INFO - dpsgd_diffusion.py - 2024-10-24 04:50:52,566 - Loss: 0.4481, step: 3700
+INFO - dpsgd_diffusion.py - 2024-10-24 04:52:36,349 - Loss: 0.4911, step: 3800
+INFO - dpsgd_diffusion.py - 2024-10-24 04:54:19,960 - Loss: 0.4718, step: 3900
+INFO - dpsgd_diffusion.py - 2024-10-24 04:56:04,339 - Loss: 0.4831, step: 4000
+INFO - dpsgd_diffusion.py - 2024-10-24 04:56:04,390 - Saving snapshot checkpoint and sampling single batch at iteration 4000.
+WARNING - image.py - 2024-10-24 04:56:05,466 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 04:56:35,165 - FID at iteration 4000: 400.735772
+INFO - dpsgd_diffusion.py - 2024-10-24 04:58:16,636 - Loss: 0.4650, step: 4100
+INFO - dpsgd_diffusion.py - 2024-10-24 05:00:00,556 - Loss: 0.4501, step: 4200
+INFO - dpsgd_diffusion.py - 2024-10-24 05:00:24,878 - Eps-value after 6 epochs: 0.1947
+INFO - dpsgd_diffusion.py - 2024-10-24 05:01:43,751 - Loss: 0.4719, step: 4300
+INFO - dpsgd_diffusion.py - 2024-10-24 05:03:27,963 - Loss: 0.4560, step: 4400
+INFO - dpsgd_diffusion.py - 2024-10-24 05:05:10,177 - Loss: 0.4672, step: 4500
+INFO - dpsgd_diffusion.py - 2024-10-24 05:06:52,598 - Loss: 0.4496, step: 4600
+INFO - dpsgd_diffusion.py - 2024-10-24 05:08:34,832 - Loss: 0.4606, step: 4700
+INFO - dpsgd_diffusion.py - 2024-10-24 05:10:17,383 - Loss: 0.4289, step: 4800
+INFO - dpsgd_diffusion.py - 2024-10-24 05:12:00,338 - Loss: 0.4702, step: 4900
+INFO - dpsgd_diffusion.py - 2024-10-24 05:12:28,665 - Eps-value after 7 epochs: 0.2058
+INFO - dpsgd_diffusion.py - 2024-10-24 05:13:42,508 - Loss: 0.4464, step: 5000
+INFO - dpsgd_diffusion.py - 2024-10-24 05:15:23,614 - Loss: 0.4297, step: 5100
+INFO - dpsgd_diffusion.py - 2024-10-24 05:17:08,028 - Loss: 0.4159, step: 5200
+INFO - dpsgd_diffusion.py - 2024-10-24 05:18:50,053 - Loss: 0.4111, step: 5300
+INFO - dpsgd_diffusion.py - 2024-10-24 05:20:33,878 - Loss: 0.4556, step: 5400
+INFO - dpsgd_diffusion.py - 2024-10-24 05:22:17,407 - Loss: 0.4128, step: 5500
+INFO - dpsgd_diffusion.py - 2024-10-24 05:23:57,717 - Loss: 0.4281, step: 5600
+INFO - dpsgd_diffusion.py - 2024-10-24 05:24:29,372 - Eps-value after 8 epochs: 0.2169
+INFO - dpsgd_diffusion.py - 2024-10-24 05:25:39,152 - Loss: 0.4175, step: 5700
+INFO - dpsgd_diffusion.py - 2024-10-24 05:27:23,773 - Loss: 0.4236, step: 5800
+INFO - dpsgd_diffusion.py - 2024-10-24 05:29:09,069 - Loss: 0.4353, step: 5900
+INFO - dpsgd_diffusion.py - 2024-10-24 05:30:54,196 - Loss: 0.3968, step: 6000
+INFO - dpsgd_diffusion.py - 2024-10-24 05:30:54,288 - Saving snapshot checkpoint and sampling single batch at iteration 6000.
+WARNING - image.py - 2024-10-24 05:30:55,366 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 05:31:25,124 - FID at iteration 6000: 375.168629
+INFO - dpsgd_diffusion.py - 2024-10-24 05:33:08,185 - Loss: 0.4105, step: 6100
+INFO - dpsgd_diffusion.py - 2024-10-24 05:34:48,437 - Loss: 0.4335, step: 6200
+INFO - dpsgd_diffusion.py - 2024-10-24 05:36:31,310 - Loss: 0.4292, step: 6300
+INFO - dpsgd_diffusion.py - 2024-10-24 05:37:07,921 - Eps-value after 9 epochs: 0.2279
+INFO - dpsgd_diffusion.py - 2024-10-24 05:38:15,228 - Loss: 0.4188, step: 6400
+INFO - dpsgd_diffusion.py - 2024-10-24 05:39:57,545 - Loss: 0.4269, step: 6500
+INFO - dpsgd_diffusion.py - 2024-10-24 05:41:38,964 - Loss: 0.4240, step: 6600
+INFO - dpsgd_diffusion.py - 2024-10-24 05:43:24,549 - Loss: 0.4359, step: 6700
+INFO - dpsgd_diffusion.py - 2024-10-24 05:45:09,062 - Loss: 0.4077, step: 6800
+INFO - dpsgd_diffusion.py - 2024-10-24 05:46:53,098 - Loss: 0.4432, step: 6900
+INFO - dpsgd_diffusion.py - 2024-10-24 05:48:37,078 - Loss: 0.4126, step: 7000
+INFO - dpsgd_diffusion.py - 2024-10-24 05:49:17,494 - Eps-value after 10 epochs: 0.2390
+INFO - dpsgd_diffusion.py - 2024-10-24 05:50:16,722 - Loss: 0.3961, step: 7100
+INFO - dpsgd_diffusion.py - 2024-10-24 05:51:59,149 - Loss: 0.4136, step: 7200
+INFO - dpsgd_diffusion.py - 2024-10-24 05:53:42,415 - Loss: 0.3691, step: 7300
+INFO - dpsgd_diffusion.py - 2024-10-24 05:55:24,259 - Loss: 0.4045, step: 7400
+INFO - dpsgd_diffusion.py - 2024-10-24 05:57:05,602 - Loss: 0.4048, step: 7500
+INFO - dpsgd_diffusion.py - 2024-10-24 05:58:46,718 - Loss: 0.4321, step: 7600
+INFO - dpsgd_diffusion.py - 2024-10-24 06:00:29,657 - Loss: 0.4019, step: 7700
+INFO - dpsgd_diffusion.py - 2024-10-24 06:01:14,998 - Eps-value after 11 epochs: 0.2501
+INFO - dpsgd_diffusion.py - 2024-10-24 06:02:12,936 - Loss: 0.3913, step: 7800
+INFO - dpsgd_diffusion.py - 2024-10-24 06:03:52,353 - Loss: 0.3807, step: 7900
+INFO - dpsgd_diffusion.py - 2024-10-24 06:05:32,537 - Loss: 0.4140, step: 8000
+INFO - dpsgd_diffusion.py - 2024-10-24 06:05:32,546 - Saving snapshot checkpoint and sampling single batch at iteration 8000.
+WARNING - image.py - 2024-10-24 06:05:33,633 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 06:06:03,373 - FID at iteration 8000: 328.047084
+INFO - dpsgd_diffusion.py - 2024-10-24 06:07:46,633 - Loss: 0.4349, step: 8100
+INFO - dpsgd_diffusion.py - 2024-10-24 06:09:28,298 - Loss: 0.3931, step: 8200
+INFO - dpsgd_diffusion.py - 2024-10-24 06:11:10,154 - Loss: 0.4348, step: 8300
+INFO - dpsgd_diffusion.py - 2024-10-24 06:12:53,206 - Loss: 0.4225, step: 8400
+INFO - dpsgd_diffusion.py - 2024-10-24 06:13:42,054 - Eps-value after 12 epochs: 0.2612
+INFO - dpsgd_diffusion.py - 2024-10-24 06:14:35,289 - Loss: 0.3914, step: 8500
+INFO - dpsgd_diffusion.py - 2024-10-24 06:16:17,170 - Loss: 0.3949, step: 8600
+INFO - dpsgd_diffusion.py - 2024-10-24 06:18:00,294 - Loss: 0.4169, step: 8700
+INFO - dpsgd_diffusion.py - 2024-10-24 06:19:43,015 - Loss: 0.3854, step: 8800
+INFO - dpsgd_diffusion.py - 2024-10-24 06:21:22,351 - Loss: 0.4056, step: 8900
+INFO - dpsgd_diffusion.py - 2024-10-24 06:23:05,462 - Loss: 0.4021, step: 9000
+INFO - dpsgd_diffusion.py - 2024-10-24 06:24:45,087 - Loss: 0.3719, step: 9100
+INFO - dpsgd_diffusion.py - 2024-10-24 06:25:36,993 - Eps-value after 13 epochs: 0.2723
+INFO - dpsgd_diffusion.py - 2024-10-24 06:26:26,697 - Loss: 0.3873, step: 9200
+INFO - dpsgd_diffusion.py - 2024-10-24 06:28:08,332 - Loss: 0.4023, step: 9300
+INFO - dpsgd_diffusion.py - 2024-10-24 06:29:50,107 - Loss: 0.3848, step: 9400
+INFO - dpsgd_diffusion.py - 2024-10-24 06:31:32,549 - Loss: 0.4015, step: 9500
+INFO - dpsgd_diffusion.py - 2024-10-24 06:33:16,776 - Loss: 0.3890, step: 9600
+INFO - dpsgd_diffusion.py - 2024-10-24 06:34:59,811 - Loss: 0.3953, step: 9700
+INFO - dpsgd_diffusion.py - 2024-10-24 06:36:42,003 - Loss: 0.4138, step: 9800
+INFO - dpsgd_diffusion.py - 2024-10-24 06:37:38,469 - Eps-value after 14 epochs: 0.2831
+INFO - dpsgd_diffusion.py - 2024-10-24 06:38:24,038 - Loss: 0.3946, step: 9900
+INFO - dpsgd_diffusion.py - 2024-10-24 06:40:06,964 - Loss: 0.3814, step: 10000
+INFO - dpsgd_diffusion.py - 2024-10-24 06:40:07,014 - Saving snapshot checkpoint and sampling single batch at iteration 10000.
+WARNING - image.py - 2024-10-24 06:40:08,094 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 06:40:37,884 - FID at iteration 10000: 306.663645
+INFO - dpsgd_diffusion.py - 2024-10-24 06:42:20,509 - Loss: 0.3825, step: 10100
+INFO - dpsgd_diffusion.py - 2024-10-24 06:44:03,892 - Loss: 0.3629, step: 10200
+INFO - dpsgd_diffusion.py - 2024-10-24 06:45:45,238 - Loss: 0.4429, step: 10300
+INFO - dpsgd_diffusion.py - 2024-10-24 06:47:26,958 - Loss: 0.3998, step: 10400
+INFO - dpsgd_diffusion.py - 2024-10-24 06:49:09,033 - Loss: 0.3879, step: 10500
+INFO - dpsgd_diffusion.py - 2024-10-24 06:50:09,231 - Eps-value after 15 epochs: 0.2936
+INFO - dpsgd_diffusion.py - 2024-10-24 06:50:50,649 - Loss: 0.3819, step: 10600
+INFO - dpsgd_diffusion.py - 2024-10-24 06:52:34,674 - Loss: 0.3859, step: 10700
+INFO - dpsgd_diffusion.py - 2024-10-24 06:54:17,297 - Loss: 0.4160, step: 10800
+INFO - dpsgd_diffusion.py - 2024-10-24 06:56:00,538 - Loss: 0.3862, step: 10900
+INFO - dpsgd_diffusion.py - 2024-10-24 06:57:44,821 - Loss: 0.3761, step: 11000
+INFO - dpsgd_diffusion.py - 2024-10-24 06:59:27,106 - Loss: 0.3867, step: 11100
+INFO - dpsgd_diffusion.py - 2024-10-24 07:01:06,009 - Loss: 0.3942, step: 11200
+INFO - dpsgd_diffusion.py - 2024-10-24 07:02:15,040 - Eps-value after 16 epochs: 0.3038
+INFO - dpsgd_diffusion.py - 2024-10-24 07:02:50,214 - Loss: 0.3984, step: 11300
+INFO - dpsgd_diffusion.py - 2024-10-24 07:04:29,976 - Loss: 0.3759, step: 11400
+INFO - dpsgd_diffusion.py - 2024-10-24 07:06:10,144 - Loss: 0.3904, step: 11500
+INFO - dpsgd_diffusion.py - 2024-10-24 07:07:51,969 - Loss: 0.4037, step: 11600
+INFO - dpsgd_diffusion.py - 2024-10-24 07:09:33,486 - Loss: 0.4111, step: 11700
+INFO - dpsgd_diffusion.py - 2024-10-24 07:11:13,800 - Loss: 0.3993, step: 11800
+INFO - dpsgd_diffusion.py - 2024-10-24 07:12:55,080 - Loss: 0.3900, step: 11900
+INFO - dpsgd_diffusion.py - 2024-10-24 07:14:03,863 - Eps-value after 17 epochs: 0.3137
+INFO - dpsgd_diffusion.py - 2024-10-24 07:14:36,920 - Loss: 0.3888, step: 12000
+INFO - dpsgd_diffusion.py - 2024-10-24 07:14:36,971 - Saving snapshot checkpoint and sampling single batch at iteration 12000.
+WARNING - image.py - 2024-10-24 07:14:38,064 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 07:15:07,838 - FID at iteration 12000: 294.664449
+INFO - dpsgd_diffusion.py - 2024-10-24 07:16:49,757 - Loss: 0.4012, step: 12100
+INFO - dpsgd_diffusion.py - 2024-10-24 07:18:33,449 - Loss: 0.3894, step: 12200
+INFO - dpsgd_diffusion.py - 2024-10-24 07:20:16,058 - Loss: 0.3970, step: 12300
+INFO - dpsgd_diffusion.py - 2024-10-24 07:21:58,759 - Loss: 0.3592, step: 12400
+INFO - dpsgd_diffusion.py - 2024-10-24 07:23:41,496 - Loss: 0.3686, step: 12500
+INFO - dpsgd_diffusion.py - 2024-10-24 07:25:22,550 - Loss: 0.3726, step: 12600
+INFO - dpsgd_diffusion.py - 2024-10-24 07:26:34,929 - Eps-value after 18 epochs: 0.3234
+INFO - dpsgd_diffusion.py - 2024-10-24 07:27:03,717 - Loss: 0.3554, step: 12700
+INFO - dpsgd_diffusion.py - 2024-10-24 07:28:44,737 - Loss: 0.3854, step: 12800
+INFO - dpsgd_diffusion.py - 2024-10-24 07:30:26,638 - Loss: 0.4042, step: 12900
+INFO - dpsgd_diffusion.py - 2024-10-24 07:32:09,126 - Loss: 0.3953, step: 13000
+INFO - dpsgd_diffusion.py - 2024-10-24 07:33:51,187 - Loss: 0.3920, step: 13100
+INFO - dpsgd_diffusion.py - 2024-10-24 07:35:33,049 - Loss: 0.3763, step: 13200
+INFO - dpsgd_diffusion.py - 2024-10-24 07:37:16,293 - Loss: 0.3990, step: 13300
+INFO - dpsgd_diffusion.py - 2024-10-24 07:38:34,828 - Eps-value after 19 epochs: 0.3328
+INFO - dpsgd_diffusion.py - 2024-10-24 07:38:59,562 - Loss: 0.3609, step: 13400
+INFO - dpsgd_diffusion.py - 2024-10-24 07:40:42,014 - Loss: 0.3729, step: 13500
+INFO - dpsgd_diffusion.py - 2024-10-24 07:42:23,429 - Loss: 0.3572, step: 13600
+INFO - dpsgd_diffusion.py - 2024-10-24 07:44:05,247 - Loss: 0.3560, step: 13700
+INFO - dpsgd_diffusion.py - 2024-10-24 07:45:50,273 - Loss: 0.4020, step: 13800
+INFO - dpsgd_diffusion.py - 2024-10-24 07:47:34,174 - Loss: 0.3546, step: 13900
+INFO - dpsgd_diffusion.py - 2024-10-24 07:49:17,120 - Loss: 0.3923, step: 14000
+INFO - dpsgd_diffusion.py - 2024-10-24 07:49:17,216 - Saving snapshot checkpoint and sampling single batch at iteration 14000.
+WARNING - image.py - 2024-10-24 07:49:18,306 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 07:49:48,082 - FID at iteration 14000: 290.085445
+INFO - dpsgd_diffusion.py - 2024-10-24 07:51:10,183 - Eps-value after 20 epochs: 0.3419
+INFO - dpsgd_diffusion.py - 2024-10-24 07:51:30,682 - Loss: 0.3770, step: 14100
+INFO - dpsgd_diffusion.py - 2024-10-24 07:53:11,513 - Loss: 0.3689, step: 14200
+INFO - dpsgd_diffusion.py - 2024-10-24 07:54:53,715 - Loss: 0.3504, step: 14300
+INFO - dpsgd_diffusion.py - 2024-10-24 07:56:36,086 - Loss: 0.4001, step: 14400
+INFO - dpsgd_diffusion.py - 2024-10-24 07:58:18,119 - Loss: 0.3739, step: 14500
+INFO - dpsgd_diffusion.py - 2024-10-24 08:00:02,123 - Loss: 0.3665, step: 14600
+INFO - dpsgd_diffusion.py - 2024-10-24 08:01:44,499 - Loss: 0.3783, step: 14700
+INFO - dpsgd_diffusion.py - 2024-10-24 08:03:10,815 - Eps-value after 21 epochs: 0.3509
+INFO - dpsgd_diffusion.py - 2024-10-24 08:03:27,520 - Loss: 0.3688, step: 14800
+INFO - dpsgd_diffusion.py - 2024-10-24 08:05:08,502 - Loss: 0.3577, step: 14900
+INFO - dpsgd_diffusion.py - 2024-10-24 08:06:51,102 - Loss: 0.3693, step: 15000
+INFO - dpsgd_diffusion.py - 2024-10-24 08:08:35,277 - Loss: 0.3867, step: 15100
+INFO - dpsgd_diffusion.py - 2024-10-24 08:10:17,753 - Loss: 0.3618, step: 15200
+INFO - dpsgd_diffusion.py - 2024-10-24 08:11:57,565 - Loss: 0.3547, step: 15300
+INFO - dpsgd_diffusion.py - 2024-10-24 08:13:40,035 - Loss: 0.3717, step: 15400
+INFO - dpsgd_diffusion.py - 2024-10-24 08:15:08,376 - Eps-value after 22 epochs: 0.3596
+INFO - dpsgd_diffusion.py - 2024-10-24 08:15:20,795 - Loss: 0.3607, step: 15500
+INFO - dpsgd_diffusion.py - 2024-10-24 08:17:01,871 - Loss: 0.3580, step: 15600
+INFO - dpsgd_diffusion.py - 2024-10-24 08:18:44,974 - Loss: 0.3286, step: 15700
+INFO - dpsgd_diffusion.py - 2024-10-24 08:20:27,081 - Loss: 0.3503, step: 15800
+INFO - dpsgd_diffusion.py - 2024-10-24 08:22:10,344 - Loss: 0.3628, step: 15900
+INFO - dpsgd_diffusion.py - 2024-10-24 08:23:51,301 - Loss: 0.3488, step: 16000
+INFO - dpsgd_diffusion.py - 2024-10-24 08:23:51,311 - Saving snapshot checkpoint and sampling single batch at iteration 16000.
+WARNING - image.py - 2024-10-24 08:23:52,434 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 08:24:22,343 - FID at iteration 16000: 290.612528
+INFO - dpsgd_diffusion.py - 2024-10-24 08:26:06,163 - Loss: 0.3866, step: 16100
+INFO - dpsgd_diffusion.py - 2024-10-24 08:27:40,692 - Eps-value after 23 epochs: 0.3682
+INFO - dpsgd_diffusion.py - 2024-10-24 08:27:48,904 - Loss: 0.3394, step: 16200
+INFO - dpsgd_diffusion.py - 2024-10-24 08:29:31,158 - Loss: 0.3389, step: 16300
+INFO - dpsgd_diffusion.py - 2024-10-24 08:31:11,852 - Loss: 0.3664, step: 16400
+INFO - dpsgd_diffusion.py - 2024-10-24 08:32:52,913 - Loss: 0.3646, step: 16500
+INFO - dpsgd_diffusion.py - 2024-10-24 08:34:37,145 - Loss: 0.3413, step: 16600
+INFO - dpsgd_diffusion.py - 2024-10-24 08:36:19,184 - Loss: 0.3652, step: 16700
+INFO - dpsgd_diffusion.py - 2024-10-24 08:38:00,800 - Loss: 0.3324, step: 16800
+INFO - dpsgd_diffusion.py - 2024-10-24 08:39:38,354 - Eps-value after 24 epochs: 0.3766
+INFO - dpsgd_diffusion.py - 2024-10-24 08:39:42,493 - Loss: 0.3593, step: 16900
+INFO - dpsgd_diffusion.py - 2024-10-24 08:41:26,260 - Loss: 0.3527, step: 17000
+INFO - dpsgd_diffusion.py - 2024-10-24 08:43:08,711 - Loss: 0.3287, step: 17100
+INFO - dpsgd_diffusion.py - 2024-10-24 08:44:51,455 - Loss: 0.3317, step: 17200
+INFO - dpsgd_diffusion.py - 2024-10-24 08:46:33,886 - Loss: 0.3535, step: 17300
+INFO - dpsgd_diffusion.py - 2024-10-24 08:48:15,622 - Loss: 0.3663, step: 17400
+INFO - dpsgd_diffusion.py - 2024-10-24 08:49:56,897 - Loss: 0.3349, step: 17500
+INFO - dpsgd_diffusion.py - 2024-10-24 08:51:37,675 - Loss: 0.3395, step: 17600
+INFO - dpsgd_diffusion.py - 2024-10-24 08:51:37,688 - Eps-value after 25 epochs: 0.3848
+INFO - dpsgd_diffusion.py - 2024-10-24 08:53:22,008 - Loss: 0.3342, step: 17700
+INFO - dpsgd_diffusion.py - 2024-10-24 08:55:02,172 - Loss: 0.3728, step: 17800
+INFO - dpsgd_diffusion.py - 2024-10-24 08:56:45,726 - Loss: 0.3556, step: 17900
+INFO - dpsgd_diffusion.py - 2024-10-24 08:58:29,241 - Loss: 0.3439, step: 18000
+INFO - dpsgd_diffusion.py - 2024-10-24 08:58:29,246 - Saving snapshot checkpoint and sampling single batch at iteration 18000.
+WARNING - image.py - 2024-10-24 08:58:30,335 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 08:59:00,040 - FID at iteration 18000: 300.710388
+INFO - dpsgd_diffusion.py - 2024-10-24 09:00:41,171 - Loss: 0.3334, step: 18100
+INFO - dpsgd_diffusion.py - 2024-10-24 09:02:26,049 - Loss: 0.3235, step: 18200
+INFO - dpsgd_diffusion.py - 2024-10-24 09:04:08,563 - Loss: 0.3410, step: 18300
+INFO - dpsgd_diffusion.py - 2024-10-24 09:04:12,529 - Eps-value after 26 epochs: 0.3929
+INFO - dpsgd_diffusion.py - 2024-10-24 09:05:50,141 - Loss: 0.3318, step: 18400
+INFO - dpsgd_diffusion.py - 2024-10-24 09:07:31,637 - Loss: 0.3474, step: 18500
+INFO - dpsgd_diffusion.py - 2024-10-24 09:09:13,807 - Loss: 0.3418, step: 18600
+INFO - dpsgd_diffusion.py - 2024-10-24 09:10:53,640 - Loss: 0.3411, step: 18700
+INFO - dpsgd_diffusion.py - 2024-10-24 09:12:35,104 - Loss: 0.3469, step: 18800
+INFO - dpsgd_diffusion.py - 2024-10-24 09:14:17,847 - Loss: 0.3307, step: 18900
+INFO - dpsgd_diffusion.py - 2024-10-24 09:16:00,660 - Loss: 0.3542, step: 19000
+INFO - dpsgd_diffusion.py - 2024-10-24 09:16:08,608 - Eps-value after 27 epochs: 0.4008
+INFO - dpsgd_diffusion.py - 2024-10-24 09:17:42,722 - Loss: 0.3296, step: 19100
+INFO - dpsgd_diffusion.py - 2024-10-24 09:19:24,279 - Loss: 0.3416, step: 19200
+INFO - dpsgd_diffusion.py - 2024-10-24 09:21:06,654 - Loss: 0.3770, step: 19300
+INFO - dpsgd_diffusion.py - 2024-10-24 09:22:47,549 - Loss: 0.3391, step: 19400
+INFO - dpsgd_diffusion.py - 2024-10-24 09:24:30,974 - Loss: 0.3361, step: 19500
+INFO - dpsgd_diffusion.py - 2024-10-24 09:26:14,080 - Loss: 0.3238, step: 19600
+INFO - dpsgd_diffusion.py - 2024-10-24 09:27:56,848 - Loss: 0.3836, step: 19700
+INFO - dpsgd_diffusion.py - 2024-10-24 09:28:09,336 - Eps-value after 28 epochs: 0.4087
+INFO - dpsgd_diffusion.py - 2024-10-24 09:29:39,643 - Loss: 0.3319, step: 19800
+INFO - dpsgd_diffusion.py - 2024-10-24 09:31:21,204 - Loss: 0.3547, step: 19900
+INFO - dpsgd_diffusion.py - 2024-10-24 09:33:03,721 - Loss: 0.3666, step: 20000
+INFO - dpsgd_diffusion.py - 2024-10-24 09:33:03,819 - Saving snapshot checkpoint and sampling single batch at iteration 20000.
+WARNING - image.py - 2024-10-24 09:33:04,902 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 09:33:34,706 - FID at iteration 20000: 306.537933
+INFO - dpsgd_diffusion.py - 2024-10-24 09:35:16,413 - Loss: 0.3592, step: 20100
+INFO - dpsgd_diffusion.py - 2024-10-24 09:36:58,632 - Loss: 0.3598, step: 20200
+INFO - dpsgd_diffusion.py - 2024-10-24 09:38:41,197 - Loss: 0.3531, step: 20300
+INFO - dpsgd_diffusion.py - 2024-10-24 09:40:24,748 - Loss: 0.3518, step: 20400
+INFO - dpsgd_diffusion.py - 2024-10-24 09:40:40,560 - Eps-value after 29 epochs: 0.4163
+INFO - dpsgd_diffusion.py - 2024-10-24 09:42:04,949 - Loss: 0.3273, step: 20500
+INFO - dpsgd_diffusion.py - 2024-10-24 09:43:47,987 - Loss: 0.3553, step: 20600
+INFO - dpsgd_diffusion.py - 2024-10-24 09:45:29,452 - Loss: 0.3139, step: 20700
+INFO - dpsgd_diffusion.py - 2024-10-24 09:47:13,621 - Loss: 0.3185, step: 20800
+INFO - dpsgd_diffusion.py - 2024-10-24 09:48:55,607 - Loss: 0.3273, step: 20900
+INFO - dpsgd_diffusion.py - 2024-10-24 09:50:36,324 - Loss: 0.3367, step: 21000
+INFO - dpsgd_diffusion.py - 2024-10-24 09:52:21,475 - Loss: 0.3333, step: 21100
+INFO - dpsgd_diffusion.py - 2024-10-24 09:52:42,169 - Eps-value after 30 epochs: 0.4239
+INFO - dpsgd_diffusion.py - 2024-10-24 09:54:01,949 - Loss: 0.3313, step: 21200
+INFO - dpsgd_diffusion.py - 2024-10-24 09:55:43,907 - Loss: 0.3751, step: 21300
+INFO - dpsgd_diffusion.py - 2024-10-24 09:57:26,969 - Loss: 0.3117, step: 21400
+INFO - dpsgd_diffusion.py - 2024-10-24 09:59:09,317 - Loss: 0.3473, step: 21500
+INFO - dpsgd_diffusion.py - 2024-10-24 10:00:50,557 - Loss: 0.3463, step: 21600
+INFO - dpsgd_diffusion.py - 2024-10-24 10:02:35,749 - Loss: 0.3464, step: 21700
+INFO - dpsgd_diffusion.py - 2024-10-24 10:04:21,626 - Loss: 0.3114, step: 21800
+INFO - dpsgd_diffusion.py - 2024-10-24 10:04:46,500 - Eps-value after 31 epochs: 0.4313
+INFO - dpsgd_diffusion.py - 2024-10-24 10:06:05,680 - Loss: 0.3013, step: 21900
+INFO - dpsgd_diffusion.py - 2024-10-24 10:07:44,842 - Loss: 0.3143, step: 22000
+INFO - dpsgd_diffusion.py - 2024-10-24 10:07:44,848 - Saving snapshot checkpoint and sampling single batch at iteration 22000.
+WARNING - image.py - 2024-10-24 10:07:45,938 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 10:08:15,795 - FID at iteration 22000: 306.259188
+INFO - dpsgd_diffusion.py - 2024-10-24 10:09:57,953 - Loss: 0.3043, step: 22100
+INFO - dpsgd_diffusion.py - 2024-10-24 10:11:39,608 - Loss: 0.3371, step: 22200
+INFO - dpsgd_diffusion.py - 2024-10-24 10:13:20,476 - Loss: 0.3214, step: 22300
+INFO - dpsgd_diffusion.py - 2024-10-24 10:15:02,145 - Loss: 0.3425, step: 22400
+INFO - dpsgd_diffusion.py - 2024-10-24 10:16:46,174 - Loss: 0.3654, step: 22500
+INFO - dpsgd_diffusion.py - 2024-10-24 10:17:14,335 - Eps-value after 32 epochs: 0.4387
+INFO - dpsgd_diffusion.py - 2024-10-24 10:18:29,579 - Loss: 0.3396, step: 22600
+INFO - dpsgd_diffusion.py - 2024-10-24 10:20:10,172 - Loss: 0.3273, step: 22700
+INFO - dpsgd_diffusion.py - 2024-10-24 10:21:50,752 - Loss: 0.3010, step: 22800
+INFO - dpsgd_diffusion.py - 2024-10-24 10:23:30,192 - Loss: 0.3018, step: 22900
+INFO - dpsgd_diffusion.py - 2024-10-24 10:25:11,489 - Loss: 0.3051, step: 23000
+INFO - dpsgd_diffusion.py - 2024-10-24 10:26:52,405 - Loss: 0.3128, step: 23100
+INFO - dpsgd_diffusion.py - 2024-10-24 10:28:33,121 - Loss: 0.3046, step: 23200
+INFO - dpsgd_diffusion.py - 2024-10-24 10:29:05,655 - Eps-value after 33 epochs: 0.4459
+INFO - dpsgd_diffusion.py - 2024-10-24 10:30:16,114 - Loss: 0.3509, step: 23300
+INFO - dpsgd_diffusion.py - 2024-10-24 10:31:59,529 - Loss: 0.3061, step: 23400
+INFO - dpsgd_diffusion.py - 2024-10-24 10:33:41,378 - Loss: 0.3119, step: 23500
+INFO - dpsgd_diffusion.py - 2024-10-24 10:35:22,997 - Loss: 0.3182, step: 23600
+INFO - dpsgd_diffusion.py - 2024-10-24 10:37:03,417 - Loss: 0.3091, step: 23700
+INFO - dpsgd_diffusion.py - 2024-10-24 10:38:46,294 - Loss: 0.3386, step: 23800
+INFO - dpsgd_diffusion.py - 2024-10-24 10:40:30,154 - Loss: 0.3003, step: 23900
+INFO - dpsgd_diffusion.py - 2024-10-24 10:41:06,251 - Eps-value after 34 epochs: 0.4530
+INFO - dpsgd_diffusion.py - 2024-10-24 10:42:10,567 - Loss: 0.3245, step: 24000
+INFO - dpsgd_diffusion.py - 2024-10-24 10:42:10,577 - Saving snapshot checkpoint and sampling single batch at iteration 24000.
+WARNING - image.py - 2024-10-24 10:42:11,665 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 10:42:41,426 - FID at iteration 24000: 305.363227
+INFO - dpsgd_diffusion.py - 2024-10-24 10:44:25,688 - Loss: 0.3320, step: 24100
+INFO - dpsgd_diffusion.py - 2024-10-24 10:46:05,916 - Loss: 0.3366, step: 24200
+INFO - dpsgd_diffusion.py - 2024-10-24 10:47:49,184 - Loss: 0.3170, step: 24300
+INFO - dpsgd_diffusion.py - 2024-10-24 10:49:31,988 - Loss: 0.3198, step: 24400
+INFO - dpsgd_diffusion.py - 2024-10-24 10:51:13,697 - Loss: 0.3170, step: 24500
+INFO - dpsgd_diffusion.py - 2024-10-24 10:52:52,796 - Loss: 0.3115, step: 24600
+INFO - dpsgd_diffusion.py - 2024-10-24 10:53:33,245 - Eps-value after 35 epochs: 0.4600
+INFO - dpsgd_diffusion.py - 2024-10-24 10:54:33,200 - Loss: 0.3713, step: 24700
+INFO - dpsgd_diffusion.py - 2024-10-24 10:56:24,581 - Loss: 0.3346, step: 24800
+INFO - dpsgd_diffusion.py - 2024-10-24 10:58:08,682 - Loss: 0.3341, step: 24900
+INFO - dpsgd_diffusion.py - 2024-10-24 10:59:51,053 - Loss: 0.3343, step: 25000
+INFO - dpsgd_diffusion.py - 2024-10-24 11:01:33,015 - Loss: 0.2845, step: 25100
+INFO - dpsgd_diffusion.py - 2024-10-24 11:03:16,814 - Loss: 0.3252, step: 25200
+INFO - dpsgd_diffusion.py - 2024-10-24 11:04:58,220 - Loss: 0.3330, step: 25300
+INFO - dpsgd_diffusion.py - 2024-10-24 11:05:43,702 - Eps-value after 36 epochs: 0.4670
+INFO - dpsgd_diffusion.py - 2024-10-24 11:06:41,202 - Loss: 0.3171, step: 25400
+INFO - dpsgd_diffusion.py - 2024-10-24 11:08:24,581 - Loss: 0.3169, step: 25500
+INFO - dpsgd_diffusion.py - 2024-10-24 11:10:04,647 - Loss: 0.3013, step: 25600
+INFO - dpsgd_diffusion.py - 2024-10-24 11:11:45,217 - Loss: 0.3268, step: 25700
+INFO - dpsgd_diffusion.py - 2024-10-24 11:13:26,594 - Loss: 0.3814, step: 25800
+INFO - dpsgd_diffusion.py - 2024-10-24 11:15:11,234 - Loss: 0.3115, step: 25900
+INFO - dpsgd_diffusion.py - 2024-10-24 11:16:54,441 - Loss: 0.3041, step: 26000
+INFO - dpsgd_diffusion.py - 2024-10-24 11:16:54,492 - Saving snapshot checkpoint and sampling single batch at iteration 26000.
+WARNING - image.py - 2024-10-24 11:16:55,574 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 11:17:25,362 - FID at iteration 26000: 302.591739
+INFO - dpsgd_diffusion.py - 2024-10-24 11:18:14,219 - Eps-value after 37 epochs: 0.4738
+INFO - dpsgd_diffusion.py - 2024-10-24 11:19:09,487 - Loss: 0.3311, step: 26100
+INFO - dpsgd_diffusion.py - 2024-10-24 11:20:52,921 - Loss: 0.3018, step: 26200
+INFO - dpsgd_diffusion.py - 2024-10-24 11:22:35,818 - Loss: 0.3518, step: 26300
+INFO - dpsgd_diffusion.py - 2024-10-24 11:24:19,416 - Loss: 0.3331, step: 26400
+INFO - dpsgd_diffusion.py - 2024-10-24 11:26:03,376 - Loss: 0.3165, step: 26500
+INFO - dpsgd_diffusion.py - 2024-10-24 11:27:46,405 - Loss: 0.3265, step: 26600
+INFO - dpsgd_diffusion.py - 2024-10-24 11:29:33,089 - Loss: 0.3148, step: 26700
+INFO - dpsgd_diffusion.py - 2024-10-24 11:30:29,555 - Eps-value after 38 epochs: 0.4806
+INFO - dpsgd_diffusion.py - 2024-10-24 11:31:19,085 - Loss: 0.3175, step: 26800
+INFO - dpsgd_diffusion.py - 2024-10-24 11:32:59,939 - Loss: 0.3385, step: 26900
+INFO - dpsgd_diffusion.py - 2024-10-24 11:34:41,851 - Loss: 0.3418, step: 27000
+INFO - dpsgd_diffusion.py - 2024-10-24 11:36:24,695 - Loss: 0.3333, step: 27100
+INFO - dpsgd_diffusion.py - 2024-10-24 11:38:06,252 - Loss: 0.3174, step: 27200
+INFO - dpsgd_diffusion.py - 2024-10-24 11:39:47,213 - Loss: 0.3389, step: 27300
+INFO - dpsgd_diffusion.py - 2024-10-24 11:41:26,834 - Loss: 0.3624, step: 27400
+INFO - dpsgd_diffusion.py - 2024-10-24 11:42:24,329 - Eps-value after 39 epochs: 0.4872
+INFO - dpsgd_diffusion.py - 2024-10-24 11:43:08,965 - Loss: 0.3182, step: 27500
+INFO - dpsgd_diffusion.py - 2024-10-24 11:44:50,919 - Loss: 0.3318, step: 27600
+INFO - dpsgd_diffusion.py - 2024-10-24 11:46:34,670 - Loss: 0.3107, step: 27700
+INFO - dpsgd_diffusion.py - 2024-10-24 11:48:16,051 - Loss: 0.3246, step: 27800
+INFO - dpsgd_diffusion.py - 2024-10-24 11:49:56,692 - Loss: 0.3223, step: 27900
+INFO - dpsgd_diffusion.py - 2024-10-24 11:51:38,808 - Loss: 0.2806, step: 28000
+INFO - dpsgd_diffusion.py - 2024-10-24 11:51:38,853 - Saving snapshot checkpoint and sampling single batch at iteration 28000.
+WARNING - image.py - 2024-10-24 11:51:39,932 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 11:52:09,592 - FID at iteration 28000: 299.697611
+INFO - dpsgd_diffusion.py - 2024-10-24 11:53:51,167 - Loss: 0.3170, step: 28100
+INFO - dpsgd_diffusion.py - 2024-10-24 11:54:51,708 - Eps-value after 40 epochs: 0.4938
+INFO - dpsgd_diffusion.py - 2024-10-24 11:55:34,370 - Loss: 0.3135, step: 28200
+INFO - dpsgd_diffusion.py - 2024-10-24 11:57:14,927 - Loss: 0.3161, step: 28300
+INFO - dpsgd_diffusion.py - 2024-10-24 11:58:57,217 - Loss: 0.3162, step: 28400
+INFO - dpsgd_diffusion.py - 2024-10-24 12:00:39,923 - Loss: 0.3478, step: 28500
+INFO - dpsgd_diffusion.py - 2024-10-24 12:02:22,214 - Loss: 0.2880, step: 28600
+INFO - dpsgd_diffusion.py - 2024-10-24 12:04:03,242 - Loss: 0.3730, step: 28700
+INFO - dpsgd_diffusion.py - 2024-10-24 12:05:41,684 - Loss: 0.3132, step: 28800
+INFO - dpsgd_diffusion.py - 2024-10-24 12:06:48,460 - Eps-value after 41 epochs: 0.5003
+INFO - dpsgd_diffusion.py - 2024-10-24 12:07:26,893 - Loss: 0.3269, step: 28900
+INFO - dpsgd_diffusion.py - 2024-10-24 12:09:11,392 - Loss: 0.3021, step: 29000
+INFO - dpsgd_diffusion.py - 2024-10-24 12:10:54,928 - Loss: 0.3242, step: 29100
+INFO - dpsgd_diffusion.py - 2024-10-24 12:12:36,340 - Loss: 0.3249, step: 29200
+INFO - dpsgd_diffusion.py - 2024-10-24 12:14:19,344 - Loss: 0.3212, step: 29300
+INFO - dpsgd_diffusion.py - 2024-10-24 12:16:04,185 - Loss: 0.2977, step: 29400
+INFO - dpsgd_diffusion.py - 2024-10-24 12:17:48,685 - Loss: 0.3214, step: 29500
+INFO - dpsgd_diffusion.py - 2024-10-24 12:19:00,257 - Eps-value after 42 epochs: 0.5068
+INFO - dpsgd_diffusion.py - 2024-10-24 12:19:32,429 - Loss: 0.2999, step: 29600
+INFO - dpsgd_diffusion.py - 2024-10-24 12:21:12,488 - Loss: 0.3203, step: 29700
+INFO - dpsgd_diffusion.py - 2024-10-24 12:22:54,609 - Loss: 0.3326, step: 29800
+INFO - dpsgd_diffusion.py - 2024-10-24 12:24:38,803 - Loss: 0.3241, step: 29900
+INFO - dpsgd_diffusion.py - 2024-10-24 12:26:20,407 - Loss: 0.2770, step: 30000
+INFO - dpsgd_diffusion.py - 2024-10-24 12:26:20,462 - Saving snapshot checkpoint and sampling single batch at iteration 30000.
+WARNING - image.py - 2024-10-24 12:26:21,533 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 12:26:51,211 - FID at iteration 30000: 295.854513
+INFO - dpsgd_diffusion.py - 2024-10-24 12:28:33,583 - Loss: 0.3514, step: 30100
+INFO - dpsgd_diffusion.py - 2024-10-24 12:30:13,590 - Loss: 0.2961, step: 30200
+INFO - dpsgd_diffusion.py - 2024-10-24 12:31:26,942 - Eps-value after 43 epochs: 0.5132
+INFO - dpsgd_diffusion.py - 2024-10-24 12:31:56,865 - Loss: 0.3159, step: 30300
+INFO - dpsgd_diffusion.py - 2024-10-24 12:33:39,990 - Loss: 0.2965, step: 30400
+INFO - dpsgd_diffusion.py - 2024-10-24 12:35:20,176 - Loss: 0.3062, step: 30500
+INFO - dpsgd_diffusion.py - 2024-10-24 12:37:03,122 - Loss: 0.3518, step: 30600
+INFO - dpsgd_diffusion.py - 2024-10-24 12:38:45,240 - Loss: 0.3132, step: 30700
+INFO - dpsgd_diffusion.py - 2024-10-24 12:40:28,164 - Loss: 0.2989, step: 30800
+INFO - dpsgd_diffusion.py - 2024-10-24 12:42:11,281 - Loss: 0.3196, step: 30900
+INFO - dpsgd_diffusion.py - 2024-10-24 12:43:30,573 - Eps-value after 44 epochs: 0.5195
+INFO - dpsgd_diffusion.py - 2024-10-24 12:43:56,092 - Loss: 0.2869, step: 31000
+INFO - dpsgd_diffusion.py - 2024-10-24 12:45:37,166 - Loss: 0.3378, step: 31100
+INFO - dpsgd_diffusion.py - 2024-10-24 12:47:23,192 - Loss: 0.2963, step: 31200
+INFO - dpsgd_diffusion.py - 2024-10-24 12:49:04,089 - Loss: 0.3158, step: 31300
+INFO - dpsgd_diffusion.py - 2024-10-24 12:50:45,416 - Loss: 0.3078, step: 31400
+INFO - dpsgd_diffusion.py - 2024-10-24 12:52:30,097 - Loss: 0.3044, step: 31500
+INFO - dpsgd_diffusion.py - 2024-10-24 12:54:14,950 - Loss: 0.2925, step: 31600
+INFO - dpsgd_diffusion.py - 2024-10-24 12:55:39,117 - Eps-value after 45 epochs: 0.5257
+INFO - dpsgd_diffusion.py - 2024-10-24 12:55:59,830 - Loss: 0.3044, step: 31700
+INFO - dpsgd_diffusion.py - 2024-10-24 12:57:42,761 - Loss: 0.3109, step: 31800
+INFO - dpsgd_diffusion.py - 2024-10-24 12:59:24,376 - Loss: 0.3103, step: 31900
+INFO - dpsgd_diffusion.py - 2024-10-24 13:01:05,947 - Loss: 0.3151, step: 32000
+INFO - dpsgd_diffusion.py - 2024-10-24 13:01:05,957 - Saving snapshot checkpoint and sampling single batch at iteration 32000.
+WARNING - image.py - 2024-10-24 13:01:07,049 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 13:01:36,782 - FID at iteration 32000: 291.746208
+INFO - dpsgd_diffusion.py - 2024-10-24 13:03:18,856 - Loss: 0.2975, step: 32100
+INFO - dpsgd_diffusion.py - 2024-10-24 13:05:00,860 - Loss: 0.3524, step: 32200
+INFO - dpsgd_diffusion.py - 2024-10-24 13:06:43,701 - Loss: 0.3089, step: 32300
+INFO - dpsgd_diffusion.py - 2024-10-24 13:08:09,935 - Eps-value after 46 epochs: 0.5319
+INFO - dpsgd_diffusion.py - 2024-10-24 13:08:26,527 - Loss: 0.3157, step: 32400
+INFO - dpsgd_diffusion.py - 2024-10-24 13:10:08,791 - Loss: 0.3391, step: 32500
+INFO - dpsgd_diffusion.py - 2024-10-24 13:11:52,262 - Loss: 0.3032, step: 32600
+INFO - dpsgd_diffusion.py - 2024-10-24 13:13:35,080 - Loss: 0.2929, step: 32700
+INFO - dpsgd_diffusion.py - 2024-10-24 13:15:15,633 - Loss: 0.3126, step: 32800
+INFO - dpsgd_diffusion.py - 2024-10-24 13:16:55,596 - Loss: 0.3083, step: 32900
+INFO - dpsgd_diffusion.py - 2024-10-24 13:18:38,495 - Loss: 0.3052, step: 33000
+INFO - dpsgd_diffusion.py - 2024-10-24 13:20:06,923 - Eps-value after 47 epochs: 0.5380
+INFO - dpsgd_diffusion.py - 2024-10-24 13:20:19,266 - Loss: 0.2813, step: 33100
+INFO - dpsgd_diffusion.py - 2024-10-24 13:22:01,461 - Loss: 0.3392, step: 33200
+INFO - dpsgd_diffusion.py - 2024-10-24 13:23:45,854 - Loss: 0.3138, step: 33300
+INFO - dpsgd_diffusion.py - 2024-10-24 13:25:31,394 - Loss: 0.3010, step: 33400
+INFO - dpsgd_diffusion.py - 2024-10-24 13:27:16,703 - Loss: 0.3047, step: 33500
+INFO - dpsgd_diffusion.py - 2024-10-24 13:28:58,333 - Loss: 0.3390, step: 33600
+INFO - dpsgd_diffusion.py - 2024-10-24 13:30:42,227 - Loss: 0.3092, step: 33700
+INFO - dpsgd_diffusion.py - 2024-10-24 13:32:15,136 - Eps-value after 48 epochs: 0.5441
+INFO - dpsgd_diffusion.py - 2024-10-24 13:32:23,411 - Loss: 0.3250, step: 33800
+INFO - dpsgd_diffusion.py - 2024-10-24 13:34:04,800 - Loss: 0.3137, step: 33900
+INFO - dpsgd_diffusion.py - 2024-10-24 13:35:47,280 - Loss: 0.3213, step: 34000
+INFO - dpsgd_diffusion.py - 2024-10-24 13:35:47,331 - Saving snapshot checkpoint and sampling single batch at iteration 34000.
+WARNING - image.py - 2024-10-24 13:35:48,417 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 13:36:18,175 - FID at iteration 34000: 289.870240
+INFO - dpsgd_diffusion.py - 2024-10-24 13:38:00,145 - Loss: 0.3177, step: 34100
+INFO - dpsgd_diffusion.py - 2024-10-24 13:39:43,454 - Loss: 0.3253, step: 34200
+INFO - dpsgd_diffusion.py - 2024-10-24 13:41:29,382 - Loss: 0.3233, step: 34300
+INFO - dpsgd_diffusion.py - 2024-10-24 13:43:10,961 - Loss: 0.2943, step: 34400
+INFO - dpsgd_diffusion.py - 2024-10-24 13:44:47,889 - Eps-value after 49 epochs: 0.5501
+INFO - dpsgd_diffusion.py - 2024-10-24 13:44:52,028 - Loss: 0.3006, step: 34500
+INFO - dpsgd_diffusion.py - 2024-10-24 13:46:35,068 - Loss: 0.3016, step: 34600
+INFO - dpsgd_diffusion.py - 2024-10-24 13:48:14,608 - Loss: 0.3301, step: 34700
+INFO - dpsgd_diffusion.py - 2024-10-24 13:49:58,396 - Loss: 0.3081, step: 34800
+INFO - dpsgd_diffusion.py - 2024-10-24 13:51:39,722 - Loss: 0.3198, step: 34900
+INFO - dpsgd_diffusion.py - 2024-10-24 13:53:20,365 - Loss: 0.2794, step: 35000
+INFO - dpsgd_diffusion.py - 2024-10-24 13:55:03,507 - Loss: 0.3130, step: 35100
+INFO - dpsgd_diffusion.py - 2024-10-24 13:56:44,109 - Loss: 0.3094, step: 35200
+INFO - dpsgd_diffusion.py - 2024-10-24 13:56:44,122 - Eps-value after 50 epochs: 0.5560
+INFO - dpsgd_diffusion.py - 2024-10-24 13:58:27,720 - Loss: 0.3370, step: 35300
+INFO - dpsgd_diffusion.py - 2024-10-24 14:00:10,255 - Loss: 0.3172, step: 35400
+INFO - dpsgd_diffusion.py - 2024-10-24 14:01:52,886 - Loss: 0.3199, step: 35500
+INFO - dpsgd_diffusion.py - 2024-10-24 14:03:32,802 - Loss: 0.2807, step: 35600
+INFO - dpsgd_diffusion.py - 2024-10-24 14:05:13,673 - Loss: 0.2957, step: 35700
+INFO - dpsgd_diffusion.py - 2024-10-24 14:06:55,994 - Loss: 0.3217, step: 35800
+INFO - dpsgd_diffusion.py - 2024-10-24 14:08:38,559 - Loss: 0.3142, step: 35900
+INFO - dpsgd_diffusion.py - 2024-10-24 14:08:42,572 - Eps-value after 51 epochs: 0.5619
+INFO - dpsgd_diffusion.py - 2024-10-24 14:10:22,002 - Loss: 0.2855, step: 36000
+INFO - dpsgd_diffusion.py - 2024-10-24 14:10:22,045 - Saving snapshot checkpoint and sampling single batch at iteration 36000.
+WARNING - image.py - 2024-10-24 14:10:23,151 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 14:10:52,910 - FID at iteration 36000: 284.464543
+INFO - dpsgd_diffusion.py - 2024-10-24 14:12:35,389 - Loss: 0.3080, step: 36100
+INFO - dpsgd_diffusion.py - 2024-10-24 14:14:17,463 - Loss: 0.3090, step: 36200
+INFO - dpsgd_diffusion.py - 2024-10-24 14:16:00,648 - Loss: 0.3059, step: 36300
+INFO - dpsgd_diffusion.py - 2024-10-24 14:17:44,422 - Loss: 0.3070, step: 36400
+INFO - dpsgd_diffusion.py - 2024-10-24 14:19:25,760 - Loss: 0.2970, step: 36500
+INFO - dpsgd_diffusion.py - 2024-10-24 14:21:08,365 - Loss: 0.3386, step: 36600
+INFO - dpsgd_diffusion.py - 2024-10-24 14:21:16,688 - Eps-value after 52 epochs: 0.5678
+INFO - dpsgd_diffusion.py - 2024-10-24 14:22:51,409 - Loss: 0.2970, step: 36700
+INFO - dpsgd_diffusion.py - 2024-10-24 14:24:34,751 - Loss: 0.3313, step: 36800
+INFO - dpsgd_diffusion.py - 2024-10-24 14:26:18,577 - Loss: 0.3053, step: 36900
+INFO - dpsgd_diffusion.py - 2024-10-24 14:28:00,652 - Loss: 0.3363, step: 37000
+INFO - dpsgd_diffusion.py - 2024-10-24 14:29:41,719 - Loss: 0.2836, step: 37100
+INFO - dpsgd_diffusion.py - 2024-10-24 14:31:24,691 - Loss: 0.2779, step: 37200
+INFO - dpsgd_diffusion.py - 2024-10-24 14:33:03,293 - Loss: 0.3304, step: 37300
+INFO - dpsgd_diffusion.py - 2024-10-24 14:33:14,698 - Eps-value after 53 epochs: 0.5735
+INFO - dpsgd_diffusion.py - 2024-10-24 14:34:43,185 - Loss: 0.2960, step: 37400
+INFO - dpsgd_diffusion.py - 2024-10-24 14:36:24,457 - Loss: 0.3259, step: 37500
+INFO - dpsgd_diffusion.py - 2024-10-24 14:38:05,188 - Loss: 0.3338, step: 37600
+INFO - dpsgd_diffusion.py - 2024-10-24 14:39:46,457 - Loss: 0.3149, step: 37700
+INFO - dpsgd_diffusion.py - 2024-10-24 14:41:28,119 - Loss: 0.3090, step: 37800
+INFO - dpsgd_diffusion.py - 2024-10-24 14:43:10,485 - Loss: 0.2885, step: 37900
+INFO - dpsgd_diffusion.py - 2024-10-24 14:44:53,549 - Loss: 0.3043, step: 38000
+INFO - dpsgd_diffusion.py - 2024-10-24 14:44:53,555 - Saving snapshot checkpoint and sampling single batch at iteration 38000.
+WARNING - image.py - 2024-10-24 14:44:54,678 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 14:45:24,382 - FID at iteration 38000: 282.717085
+INFO - dpsgd_diffusion.py - 2024-10-24 14:45:40,827 - Eps-value after 54 epochs: 0.5793
+INFO - dpsgd_diffusion.py - 2024-10-24 14:47:05,680 - Loss: 0.2931, step: 38100
+INFO - dpsgd_diffusion.py - 2024-10-24 14:48:46,735 - Loss: 0.3442, step: 38200
+INFO - dpsgd_diffusion.py - 2024-10-24 14:50:28,193 - Loss: 0.3063, step: 38300
+INFO - dpsgd_diffusion.py - 2024-10-24 14:52:09,031 - Loss: 0.3055, step: 38400
+INFO - dpsgd_diffusion.py - 2024-10-24 14:53:53,119 - Loss: 0.3197, step: 38500
+INFO - dpsgd_diffusion.py - 2024-10-24 14:55:36,072 - Loss: 0.3615, step: 38600
+INFO - dpsgd_diffusion.py - 2024-10-24 14:57:21,240 - Loss: 0.3179, step: 38700
+INFO - dpsgd_diffusion.py - 2024-10-24 14:57:41,025 - Eps-value after 55 epochs: 0.5850
+INFO - dpsgd_diffusion.py - 2024-10-24 14:59:01,489 - Loss: 0.3311, step: 38800
+INFO - dpsgd_diffusion.py - 2024-10-24 15:00:44,176 - Loss: 0.2961, step: 38900
+INFO - dpsgd_diffusion.py - 2024-10-24 15:02:26,708 - Loss: 0.3222, step: 39000
+INFO - dpsgd_diffusion.py - 2024-10-24 15:04:06,545 - Loss: 0.3060, step: 39100
+INFO - dpsgd_diffusion.py - 2024-10-24 15:05:47,369 - Loss: 0.2841, step: 39200
+INFO - dpsgd_diffusion.py - 2024-10-24 15:07:28,073 - Loss: 0.3057, step: 39300
+INFO - dpsgd_diffusion.py - 2024-10-24 15:09:09,126 - Loss: 0.2958, step: 39400
+INFO - dpsgd_diffusion.py - 2024-10-24 15:09:33,590 - Eps-value after 56 epochs: 0.5906
+INFO - dpsgd_diffusion.py - 2024-10-24 15:10:51,785 - Loss: 0.2942, step: 39500
+INFO - dpsgd_diffusion.py - 2024-10-24 15:12:33,382 - Loss: 0.3197, step: 39600
+INFO - dpsgd_diffusion.py - 2024-10-24 15:14:15,798 - Loss: 0.3140, step: 39700
+INFO - dpsgd_diffusion.py - 2024-10-24 15:15:57,024 - Loss: 0.3516, step: 39800
+INFO - dpsgd_diffusion.py - 2024-10-24 15:17:37,702 - Loss: 0.3143, step: 39900
+INFO - dpsgd_diffusion.py - 2024-10-24 15:19:21,480 - Loss: 0.3222, step: 40000
+INFO - dpsgd_diffusion.py - 2024-10-24 15:19:21,490 - Saving snapshot checkpoint and sampling single batch at iteration 40000.
+WARNING - image.py - 2024-10-24 15:19:22,618 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 15:19:52,387 - FID at iteration 40000: 280.809123
+INFO - dpsgd_diffusion.py - 2024-10-24 15:21:35,816 - Loss: 0.3218, step: 40100
+INFO - dpsgd_diffusion.py - 2024-10-24 15:22:04,658 - Eps-value after 57 epochs: 0.5961
+INFO - dpsgd_diffusion.py - 2024-10-24 15:23:17,834 - Loss: 0.3282, step: 40200
+INFO - dpsgd_diffusion.py - 2024-10-24 15:24:59,828 - Loss: 0.3011, step: 40300
+INFO - dpsgd_diffusion.py - 2024-10-24 15:26:43,551 - Loss: 0.3113, step: 40400
+INFO - dpsgd_diffusion.py - 2024-10-24 15:28:26,342 - Loss: 0.2934, step: 40500
+INFO - dpsgd_diffusion.py - 2024-10-24 15:30:10,724 - Loss: 0.3145, step: 40600
+INFO - dpsgd_diffusion.py - 2024-10-24 15:31:55,982 - Loss: 0.2972, step: 40700
+INFO - dpsgd_diffusion.py - 2024-10-24 15:33:39,092 - Loss: 0.3086, step: 40800
+INFO - dpsgd_diffusion.py - 2024-10-24 15:34:12,069 - Eps-value after 58 epochs: 0.6017
+INFO - dpsgd_diffusion.py - 2024-10-24 15:35:22,610 - Loss: 0.3048, step: 40900
+INFO - dpsgd_diffusion.py - 2024-10-24 15:37:06,295 - Loss: 0.2886, step: 41000
+INFO - dpsgd_diffusion.py - 2024-10-24 15:38:48,650 - Loss: 0.2849, step: 41100
+INFO - dpsgd_diffusion.py - 2024-10-24 15:40:31,460 - Loss: 0.3016, step: 41200
+INFO - dpsgd_diffusion.py - 2024-10-24 15:42:13,609 - Loss: 0.3127, step: 41300
+INFO - dpsgd_diffusion.py - 2024-10-24 15:43:55,079 - Loss: 0.3146, step: 41400
+INFO - dpsgd_diffusion.py - 2024-10-24 15:45:39,321 - Loss: 0.3012, step: 41500
+INFO - dpsgd_diffusion.py - 2024-10-24 15:46:16,617 - Eps-value after 59 epochs: 0.6073
+INFO - dpsgd_diffusion.py - 2024-10-24 15:47:24,383 - Loss: 0.3113, step: 41600
+INFO - dpsgd_diffusion.py - 2024-10-24 15:49:07,634 - Loss: 0.3127, step: 41700
+INFO - dpsgd_diffusion.py - 2024-10-24 15:50:49,417 - Loss: 0.2916, step: 41800
+INFO - dpsgd_diffusion.py - 2024-10-24 15:52:30,672 - Loss: 0.3340, step: 41900
+INFO - dpsgd_diffusion.py - 2024-10-24 15:54:14,003 - Loss: 0.2897, step: 42000
+INFO - dpsgd_diffusion.py - 2024-10-24 15:54:14,009 - Saving snapshot checkpoint and sampling single batch at iteration 42000.
+WARNING - image.py - 2024-10-24 15:54:15,131 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 15:54:44,904 - FID at iteration 42000: 279.479380
+INFO - dpsgd_diffusion.py - 2024-10-24 15:56:28,355 - Loss: 0.3148, step: 42100
+INFO - dpsgd_diffusion.py - 2024-10-24 15:58:09,447 - Loss: 0.2910, step: 42200
+INFO - dpsgd_diffusion.py - 2024-10-24 15:58:49,415 - Eps-value after 60 epochs: 0.6127
+INFO - dpsgd_diffusion.py - 2024-10-24 15:59:50,759 - Loss: 0.3082, step: 42300
+INFO - dpsgd_diffusion.py - 2024-10-24 16:01:33,208 - Loss: 0.2943, step: 42400
+INFO - dpsgd_diffusion.py - 2024-10-24 16:03:15,431 - Loss: 0.3115, step: 42500
+INFO - dpsgd_diffusion.py - 2024-10-24 16:04:56,860 - Loss: 0.2997, step: 42600
+INFO - dpsgd_diffusion.py - 2024-10-24 16:06:37,595 - Loss: 0.3061, step: 42700
+INFO - dpsgd_diffusion.py - 2024-10-24 16:08:16,046 - Loss: 0.2972, step: 42800
+INFO - dpsgd_diffusion.py - 2024-10-24 16:09:59,157 - Loss: 0.2927, step: 42900
+INFO - dpsgd_diffusion.py - 2024-10-24 16:10:44,604 - Eps-value after 61 epochs: 0.6181
+INFO - dpsgd_diffusion.py - 2024-10-24 16:11:42,775 - Loss: 0.3281, step: 43000
+INFO - dpsgd_diffusion.py - 2024-10-24 16:13:26,909 - Loss: 0.3133, step: 43100
+INFO - dpsgd_diffusion.py - 2024-10-24 16:15:11,478 - Loss: 0.3234, step: 43200
+INFO - dpsgd_diffusion.py - 2024-10-24 16:16:54,457 - Loss: 0.3247, step: 43300
+INFO - dpsgd_diffusion.py - 2024-10-24 16:18:35,174 - Loss: 0.3045, step: 43400
+INFO - dpsgd_diffusion.py - 2024-10-24 16:20:15,897 - Loss: 0.3315, step: 43500
+INFO - dpsgd_diffusion.py - 2024-10-24 16:21:56,571 - Loss: 0.3348, step: 43600
+INFO - dpsgd_diffusion.py - 2024-10-24 16:22:46,725 - Eps-value after 62 epochs: 0.6235
+INFO - dpsgd_diffusion.py - 2024-10-24 16:23:39,347 - Loss: 0.3242, step: 43700
+INFO - dpsgd_diffusion.py - 2024-10-24 16:25:22,376 - Loss: 0.3242, step: 43800
+INFO - dpsgd_diffusion.py - 2024-10-24 16:27:07,243 - Loss: 0.3195, step: 43900
+INFO - dpsgd_diffusion.py - 2024-10-24 16:28:51,032 - Loss: 0.3006, step: 44000
+INFO - dpsgd_diffusion.py - 2024-10-24 16:28:51,038 - Saving snapshot checkpoint and sampling single batch at iteration 44000.
+WARNING - image.py - 2024-10-24 16:28:52,149 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 16:29:21,941 - FID at iteration 44000: 276.517083
+INFO - dpsgd_diffusion.py - 2024-10-24 16:31:04,800 - Loss: 0.3476, step: 44100
+INFO - dpsgd_diffusion.py - 2024-10-24 16:32:47,714 - Loss: 0.2986, step: 44200
+INFO - dpsgd_diffusion.py - 2024-10-24 16:34:32,257 - Loss: 0.3022, step: 44300
+INFO - dpsgd_diffusion.py - 2024-10-24 16:35:26,003 - Eps-value after 63 epochs: 0.6289
+INFO - dpsgd_diffusion.py - 2024-10-24 16:36:15,229 - Loss: 0.2930, step: 44400
+INFO - dpsgd_diffusion.py - 2024-10-24 16:37:59,356 - Loss: 0.3118, step: 44500
+INFO - dpsgd_diffusion.py - 2024-10-24 16:39:41,528 - Loss: 0.2729, step: 44600
+INFO - dpsgd_diffusion.py - 2024-10-24 16:41:26,792 - Loss: 0.3081, step: 44700
+INFO - dpsgd_diffusion.py - 2024-10-24 16:43:09,013 - Loss: 0.3049, step: 44800
+INFO - dpsgd_diffusion.py - 2024-10-24 16:44:53,840 - Loss: 0.3646, step: 44900
+INFO - dpsgd_diffusion.py - 2024-10-24 16:46:36,417 - Loss: 0.3219, step: 45000
+INFO - dpsgd_diffusion.py - 2024-10-24 16:47:33,948 - Eps-value after 64 epochs: 0.6341
+INFO - dpsgd_diffusion.py - 2024-10-24 16:48:19,213 - Loss: 0.3252, step: 45100
+INFO - dpsgd_diffusion.py - 2024-10-24 16:50:00,430 - Loss: 0.3085, step: 45200
+INFO - dpsgd_diffusion.py - 2024-10-24 16:51:41,747 - Loss: 0.2953, step: 45300
+INFO - dpsgd_diffusion.py - 2024-10-24 16:53:25,932 - Loss: 0.2847, step: 45400
+INFO - dpsgd_diffusion.py - 2024-10-24 16:55:06,695 - Loss: 0.2911, step: 45500
+INFO - dpsgd_diffusion.py - 2024-10-24 16:56:53,046 - Loss: 0.3029, step: 45600
+INFO - dpsgd_diffusion.py - 2024-10-24 16:58:33,630 - Loss: 0.3108, step: 45700
+INFO - dpsgd_diffusion.py - 2024-10-24 16:59:34,900 - Eps-value after 65 epochs: 0.6393
+INFO - dpsgd_diffusion.py - 2024-10-24 17:00:16,117 - Loss: 0.2722, step: 45800
+INFO - dpsgd_diffusion.py - 2024-10-24 17:01:56,572 - Loss: 0.2912, step: 45900
+INFO - dpsgd_diffusion.py - 2024-10-24 17:03:39,392 - Loss: 0.3045, step: 46000
+INFO - dpsgd_diffusion.py - 2024-10-24 17:03:39,398 - Saving snapshot checkpoint and sampling single batch at iteration 46000.
+WARNING - image.py - 2024-10-24 17:03:40,525 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 17:04:10,309 - FID at iteration 46000: 274.640017
+INFO - dpsgd_diffusion.py - 2024-10-24 17:05:51,737 - Loss: 0.2847, step: 46100
+INFO - dpsgd_diffusion.py - 2024-10-24 17:07:32,828 - Loss: 0.2850, step: 46200
+INFO - dpsgd_diffusion.py - 2024-10-24 17:09:15,227 - Loss: 0.2663, step: 46300
+INFO - dpsgd_diffusion.py - 2024-10-24 17:10:56,700 - Loss: 0.3344, step: 46400
+INFO - dpsgd_diffusion.py - 2024-10-24 17:12:02,996 - Eps-value after 66 epochs: 0.6446
+INFO - dpsgd_diffusion.py - 2024-10-24 17:12:40,269 - Loss: 0.3154, step: 46500
+INFO - dpsgd_diffusion.py - 2024-10-24 17:14:22,269 - Loss: 0.3220, step: 46600
+INFO - dpsgd_diffusion.py - 2024-10-24 17:16:06,691 - Loss: 0.2900, step: 46700
+INFO - dpsgd_diffusion.py - 2024-10-24 17:17:47,993 - Loss: 0.2918, step: 46800
+INFO - dpsgd_diffusion.py - 2024-10-24 17:19:30,487 - Loss: 0.2890, step: 46900
+INFO - dpsgd_diffusion.py - 2024-10-24 17:21:14,354 - Loss: 0.3114, step: 47000
+INFO - dpsgd_diffusion.py - 2024-10-24 17:22:55,018 - Loss: 0.2842, step: 47100
+INFO - dpsgd_diffusion.py - 2024-10-24 17:24:04,393 - Eps-value after 67 epochs: 0.6498
+INFO - dpsgd_diffusion.py - 2024-10-24 17:24:38,572 - Loss: 0.3345, step: 47200
+INFO - dpsgd_diffusion.py - 2024-10-24 17:26:21,825 - Loss: 0.2851, step: 47300
+INFO - dpsgd_diffusion.py - 2024-10-24 17:28:06,790 - Loss: 0.2982, step: 47400
+INFO - dpsgd_diffusion.py - 2024-10-24 17:29:49,293 - Loss: 0.2838, step: 47500
+INFO - dpsgd_diffusion.py - 2024-10-24 17:31:30,487 - Loss: 0.3122, step: 47600
+INFO - dpsgd_diffusion.py - 2024-10-24 17:33:11,683 - Loss: 0.2828, step: 47700
+INFO - dpsgd_diffusion.py - 2024-10-24 17:34:53,633 - Loss: 0.2848, step: 47800
+INFO - dpsgd_diffusion.py - 2024-10-24 17:36:06,708 - Eps-value after 68 epochs: 0.6550
+INFO - dpsgd_diffusion.py - 2024-10-24 17:36:35,560 - Loss: 0.2860, step: 47900
+INFO - dpsgd_diffusion.py - 2024-10-24 17:38:19,686 - Loss: 0.2975, step: 48000
+INFO - dpsgd_diffusion.py - 2024-10-24 17:38:19,696 - Saving snapshot checkpoint and sampling single batch at iteration 48000.
+WARNING - image.py - 2024-10-24 17:38:20,808 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 17:38:50,517 - FID at iteration 48000: 273.331804
+INFO - dpsgd_diffusion.py - 2024-10-24 17:40:33,072 - Loss: 0.3132, step: 48100
+INFO - dpsgd_diffusion.py - 2024-10-24 17:42:15,207 - Loss: 0.2920, step: 48200
+INFO - dpsgd_diffusion.py - 2024-10-24 17:43:57,443 - Loss: 0.2784, step: 48300
+INFO - dpsgd_diffusion.py - 2024-10-24 17:45:39,618 - Loss: 0.3105, step: 48400
+INFO - dpsgd_diffusion.py - 2024-10-24 17:47:22,916 - Loss: 0.2974, step: 48500
+INFO - dpsgd_diffusion.py - 2024-10-24 17:48:41,376 - Eps-value after 69 epochs: 0.6601
+INFO - dpsgd_diffusion.py - 2024-10-24 17:49:06,730 - Loss: 0.2847, step: 48600
+INFO - dpsgd_diffusion.py - 2024-10-24 17:50:50,049 - Loss: 0.3161, step: 48700
+INFO - dpsgd_diffusion.py - 2024-10-24 17:52:35,116 - Loss: 0.2908, step: 48800
+INFO - dpsgd_diffusion.py - 2024-10-24 17:54:16,501 - Loss: 0.2778, step: 48900
+INFO - dpsgd_diffusion.py - 2024-10-24 17:55:57,360 - Loss: 0.3074, step: 49000
+INFO - dpsgd_diffusion.py - 2024-10-24 17:57:39,009 - Loss: 0.2914, step: 49100
+INFO - dpsgd_diffusion.py - 2024-10-24 17:59:22,345 - Loss: 0.2914, step: 49200
+INFO - dpsgd_diffusion.py - 2024-10-24 18:00:42,803 - Eps-value after 70 epochs: 0.6651
+INFO - dpsgd_diffusion.py - 2024-10-24 18:01:03,503 - Loss: 0.3081, step: 49300
+INFO - dpsgd_diffusion.py - 2024-10-24 18:02:43,830 - Loss: 0.3017, step: 49400
+INFO - dpsgd_diffusion.py - 2024-10-24 18:04:25,951 - Loss: 0.3132, step: 49500
+INFO - dpsgd_diffusion.py - 2024-10-24 18:06:08,918 - Loss: 0.3180, step: 49600
+INFO - dpsgd_diffusion.py - 2024-10-24 18:07:53,749 - Loss: 0.2938, step: 49700
+INFO - dpsgd_diffusion.py - 2024-10-24 18:09:35,452 - Loss: 0.3395, step: 49800
+INFO - dpsgd_diffusion.py - 2024-10-24 18:11:18,806 - Loss: 0.2952, step: 49900
+INFO - dpsgd_diffusion.py - 2024-10-24 18:12:46,241 - Eps-value after 71 epochs: 0.6701
+INFO - dpsgd_diffusion.py - 2024-10-24 18:13:02,808 - Loss: 0.3018, step: 50000
+INFO - dpsgd_diffusion.py - 2024-10-24 18:13:02,813 - Saving snapshot checkpoint and sampling single batch at iteration 50000.
+WARNING - image.py - 2024-10-24 18:13:04,055 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 18:13:33,832 - FID at iteration 50000: 271.640277
+INFO - dpsgd_diffusion.py - 2024-10-24 18:15:15,144 - Loss: 0.3306, step: 50100
+INFO - dpsgd_diffusion.py - 2024-10-24 18:16:57,066 - Loss: 0.3101, step: 50200
+INFO - dpsgd_diffusion.py - 2024-10-24 18:18:38,891 - Loss: 0.2943, step: 50300
+INFO - dpsgd_diffusion.py - 2024-10-24 18:20:21,391 - Loss: 0.3240, step: 50400
+INFO - dpsgd_diffusion.py - 2024-10-24 18:22:01,389 - Loss: 0.3059, step: 50500
+INFO - dpsgd_diffusion.py - 2024-10-24 18:23:45,116 - Loss: 0.2791, step: 50600
+INFO - dpsgd_diffusion.py - 2024-10-24 18:25:15,610 - Eps-value after 72 epochs: 0.6752
+INFO - dpsgd_diffusion.py - 2024-10-24 18:25:28,019 - Loss: 0.3067, step: 50700
+INFO - dpsgd_diffusion.py - 2024-10-24 18:27:11,434 - Loss: 0.3090, step: 50800
+INFO - dpsgd_diffusion.py - 2024-10-24 18:28:53,436 - Loss: 0.2834, step: 50900
+INFO - dpsgd_diffusion.py - 2024-10-24 18:30:35,364 - Loss: 0.2936, step: 51000
+INFO - dpsgd_diffusion.py - 2024-10-24 18:32:19,429 - Loss: 0.2983, step: 51100
+INFO - dpsgd_diffusion.py - 2024-10-24 18:34:01,081 - Loss: 0.2837, step: 51200
+INFO - dpsgd_diffusion.py - 2024-10-24 18:35:43,551 - Loss: 0.2830, step: 51300
+INFO - dpsgd_diffusion.py - 2024-10-24 18:37:18,927 - Eps-value after 73 epochs: 0.6802
+INFO - dpsgd_diffusion.py - 2024-10-24 18:37:27,552 - Loss: 0.2777, step: 51400
+INFO - dpsgd_diffusion.py - 2024-10-24 18:39:12,874 - Loss: 0.2848, step: 51500
+INFO - dpsgd_diffusion.py - 2024-10-24 18:40:53,203 - Loss: 0.3146, step: 51600
+INFO - dpsgd_diffusion.py - 2024-10-24 18:42:33,476 - Loss: 0.2735, step: 51700
+INFO - dpsgd_diffusion.py - 2024-10-24 18:44:17,039 - Loss: 0.3342, step: 51800
+INFO - dpsgd_diffusion.py - 2024-10-24 18:46:02,517 - Loss: 0.3234, step: 51900
+INFO - dpsgd_diffusion.py - 2024-10-24 18:47:44,093 - Loss: 0.2819, step: 52000
+INFO - dpsgd_diffusion.py - 2024-10-24 18:47:44,143 - Saving snapshot checkpoint and sampling single batch at iteration 52000.
+WARNING - image.py - 2024-10-24 18:47:45,242 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 18:48:15,024 - FID at iteration 52000: 268.890785
+INFO - dpsgd_diffusion.py - 2024-10-24 18:49:49,912 - Eps-value after 74 epochs: 0.6852
+INFO - dpsgd_diffusion.py - 2024-10-24 18:49:54,053 - Loss: 0.2915, step: 52100
+INFO - dpsgd_diffusion.py - 2024-10-24 18:51:37,337 - Loss: 0.2840, step: 52200
+INFO - dpsgd_diffusion.py - 2024-10-24 18:53:19,506 - Loss: 0.2827, step: 52300
+INFO - dpsgd_diffusion.py - 2024-10-24 18:55:03,793 - Loss: 0.3074, step: 52400
+INFO - dpsgd_diffusion.py - 2024-10-24 18:56:46,090 - Loss: 0.2749, step: 52500
+INFO - dpsgd_diffusion.py - 2024-10-24 18:58:28,400 - Loss: 0.2843, step: 52600
+INFO - dpsgd_diffusion.py - 2024-10-24 19:00:09,798 - Loss: 0.2948, step: 52700
+INFO - dpsgd_diffusion.py - 2024-10-24 19:01:53,044 - Loss: 0.3226, step: 52800
+INFO - dpsgd_diffusion.py - 2024-10-24 19:01:53,056 - Eps-value after 75 epochs: 0.6900
+INFO - dpsgd_diffusion.py - 2024-10-24 19:03:35,832 - Loss: 0.3110, step: 52900
+INFO - dpsgd_diffusion.py - 2024-10-24 19:05:21,436 - Loss: 0.3009, step: 53000
+INFO - dpsgd_diffusion.py - 2024-10-24 19:07:06,912 - Loss: 0.2953, step: 53100
+INFO - dpsgd_diffusion.py - 2024-10-24 19:08:51,759 - Loss: 0.2864, step: 53200
+INFO - dpsgd_diffusion.py - 2024-10-24 19:10:33,830 - Loss: 0.3299, step: 53300
+INFO - dpsgd_diffusion.py - 2024-10-24 19:12:17,750 - Loss: 0.3084, step: 53400
+INFO - dpsgd_diffusion.py - 2024-10-24 19:14:00,822 - Loss: 0.2801, step: 53500
+INFO - dpsgd_diffusion.py - 2024-10-24 19:14:04,795 - Eps-value after 76 epochs: 0.6949
+INFO - dpsgd_diffusion.py - 2024-10-24 19:15:40,306 - Loss: 0.3098, step: 53600
+INFO - dpsgd_diffusion.py - 2024-10-24 19:17:23,075 - Loss: 0.2878, step: 53700
+INFO - dpsgd_diffusion.py - 2024-10-24 19:19:05,937 - Loss: 0.3074, step: 53800
+INFO - dpsgd_diffusion.py - 2024-10-24 19:20:47,020 - Loss: 0.2883, step: 53900
+INFO - dpsgd_diffusion.py - 2024-10-24 19:22:27,665 - Loss: 0.3020, step: 54000
+INFO - dpsgd_diffusion.py - 2024-10-24 19:22:27,672 - Saving snapshot checkpoint and sampling single batch at iteration 54000.
+WARNING - image.py - 2024-10-24 19:22:28,741 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 19:22:58,393 - FID at iteration 54000: 270.272872
+INFO - dpsgd_diffusion.py - 2024-10-24 19:24:39,849 - Loss: 0.2782, step: 54100
+INFO - dpsgd_diffusion.py - 2024-10-24 19:26:21,366 - Loss: 0.3060, step: 54200
+INFO - dpsgd_diffusion.py - 2024-10-24 19:26:29,291 - Eps-value after 77 epochs: 0.6998
+INFO - dpsgd_diffusion.py - 2024-10-24 19:28:03,262 - Loss: 0.3290, step: 54300
+INFO - dpsgd_diffusion.py - 2024-10-24 19:29:47,807 - Loss: 0.3035, step: 54400
+INFO - dpsgd_diffusion.py - 2024-10-24 19:31:28,222 - Loss: 0.2910, step: 54500
+INFO - dpsgd_diffusion.py - 2024-10-24 19:33:09,851 - Loss: 0.2974, step: 54600
+INFO - dpsgd_diffusion.py - 2024-10-24 19:34:52,972 - Loss: 0.3144, step: 54700
+INFO - dpsgd_diffusion.py - 2024-10-24 19:36:36,762 - Loss: 0.3037, step: 54800
+INFO - dpsgd_diffusion.py - 2024-10-24 19:38:16,902 - Loss: 0.3053, step: 54900
+INFO - dpsgd_diffusion.py - 2024-10-24 19:38:28,760 - Eps-value after 78 epochs: 0.7046
+INFO - dpsgd_diffusion.py - 2024-10-24 19:39:57,767 - Loss: 0.2878, step: 55000
+INFO - dpsgd_diffusion.py - 2024-10-24 19:41:41,801 - Loss: 0.3163, step: 55100
+INFO - dpsgd_diffusion.py - 2024-10-24 19:43:24,968 - Loss: 0.2811, step: 55200
+INFO - dpsgd_diffusion.py - 2024-10-24 19:45:09,496 - Loss: 0.2907, step: 55300
+INFO - dpsgd_diffusion.py - 2024-10-24 19:46:52,458 - Loss: 0.3146, step: 55400
+INFO - dpsgd_diffusion.py - 2024-10-24 19:48:34,871 - Loss: 0.2880, step: 55500
+INFO - dpsgd_diffusion.py - 2024-10-24 19:50:17,712 - Loss: 0.3282, step: 55600
+INFO - dpsgd_diffusion.py - 2024-10-24 19:50:33,517 - Eps-value after 79 epochs: 0.7095
+INFO - dpsgd_diffusion.py - 2024-10-24 19:52:00,053 - Loss: 0.2957, step: 55700
+INFO - dpsgd_diffusion.py - 2024-10-24 19:53:42,332 - Loss: 0.2979, step: 55800
+INFO - dpsgd_diffusion.py - 2024-10-24 19:55:26,502 - Loss: 0.2861, step: 55900
+INFO - dpsgd_diffusion.py - 2024-10-24 19:57:08,853 - Loss: 0.2832, step: 56000
+INFO - dpsgd_diffusion.py - 2024-10-24 19:57:08,862 - Saving snapshot checkpoint and sampling single batch at iteration 56000.
+WARNING - image.py - 2024-10-24 19:57:09,937 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 19:57:39,688 - FID at iteration 56000: 267.487245
+INFO - dpsgd_diffusion.py - 2024-10-24 19:59:23,506 - Loss: 0.2766, step: 56100
+INFO - dpsgd_diffusion.py - 2024-10-24 20:01:07,995 - Loss: 0.2786, step: 56200
+INFO - dpsgd_diffusion.py - 2024-10-24 20:02:51,254 - Loss: 0.2913, step: 56300
+INFO - dpsgd_diffusion.py - 2024-10-24 20:03:12,138 - Eps-value after 80 epochs: 0.7143
+INFO - dpsgd_diffusion.py - 2024-10-24 20:04:35,269 - Loss: 0.2746, step: 56400
+INFO - dpsgd_diffusion.py - 2024-10-24 20:06:18,472 - Loss: 0.2973, step: 56500
+INFO - dpsgd_diffusion.py - 2024-10-24 20:08:03,727 - Loss: 0.3093, step: 56600
+INFO - dpsgd_diffusion.py - 2024-10-24 20:09:44,686 - Loss: 0.3102, step: 56700
+INFO - dpsgd_diffusion.py - 2024-10-24 20:11:28,629 - Loss: 0.2782, step: 56800
+INFO - dpsgd_diffusion.py - 2024-10-24 20:13:12,317 - Loss: 0.2863, step: 56900
+INFO - dpsgd_diffusion.py - 2024-10-24 20:14:54,883 - Loss: 0.2716, step: 57000
+INFO - dpsgd_diffusion.py - 2024-10-24 20:15:19,559 - Eps-value after 81 epochs: 0.7190
+INFO - dpsgd_diffusion.py - 2024-10-24 20:16:37,358 - Loss: 0.2762, step: 57100
+INFO - dpsgd_diffusion.py - 2024-10-24 20:18:19,627 - Loss: 0.3194, step: 57200
+INFO - dpsgd_diffusion.py - 2024-10-24 20:20:02,690 - Loss: 0.2963, step: 57300
+INFO - dpsgd_diffusion.py - 2024-10-24 20:21:43,742 - Loss: 0.2919, step: 57400
+INFO - dpsgd_diffusion.py - 2024-10-24 20:23:21,233 - Loss: 0.3081, step: 57500
+INFO - dpsgd_diffusion.py - 2024-10-24 20:25:00,995 - Loss: 0.2878, step: 57600
+INFO - dpsgd_diffusion.py - 2024-10-24 20:26:44,278 - Loss: 0.2837, step: 57700
+INFO - dpsgd_diffusion.py - 2024-10-24 20:27:13,079 - Eps-value after 82 epochs: 0.7237
+INFO - dpsgd_diffusion.py - 2024-10-24 20:28:27,277 - Loss: 0.2818, step: 57800
+INFO - dpsgd_diffusion.py - 2024-10-24 20:30:10,294 - Loss: 0.2774, step: 57900
+INFO - dpsgd_diffusion.py - 2024-10-24 20:31:52,686 - Loss: 0.2882, step: 58000
+INFO - dpsgd_diffusion.py - 2024-10-24 20:31:52,692 - Saving snapshot checkpoint and sampling single batch at iteration 58000.
+WARNING - image.py - 2024-10-24 20:31:53,822 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 20:32:23,581 - FID at iteration 58000: 267.104295
+INFO - dpsgd_diffusion.py - 2024-10-24 20:34:05,063 - Loss: 0.2806, step: 58100
+INFO - dpsgd_diffusion.py - 2024-10-24 20:35:49,044 - Loss: 0.3072, step: 58200
+INFO - dpsgd_diffusion.py - 2024-10-24 20:37:31,120 - Loss: 0.3231, step: 58300
+INFO - dpsgd_diffusion.py - 2024-10-24 20:39:15,551 - Loss: 0.2771, step: 58400
+INFO - dpsgd_diffusion.py - 2024-10-24 20:39:48,022 - Eps-value after 83 epochs: 0.7283
+INFO - dpsgd_diffusion.py - 2024-10-24 20:40:58,791 - Loss: 0.2864, step: 58500
+INFO - dpsgd_diffusion.py - 2024-10-24 20:42:39,980 - Loss: 0.3073, step: 58600
+INFO - dpsgd_diffusion.py - 2024-10-24 20:44:22,787 - Loss: 0.2800, step: 58700
+INFO - dpsgd_diffusion.py - 2024-10-24 20:46:05,967 - Loss: 0.3132, step: 58800
+INFO - dpsgd_diffusion.py - 2024-10-24 20:47:49,008 - Loss: 0.3145, step: 58900
+INFO - dpsgd_diffusion.py - 2024-10-24 20:49:34,913 - Loss: 0.2853, step: 59000
+INFO - dpsgd_diffusion.py - 2024-10-24 20:51:17,397 - Loss: 0.3331, step: 59100
+INFO - dpsgd_diffusion.py - 2024-10-24 20:51:54,704 - Eps-value after 84 epochs: 0.7330
+INFO - dpsgd_diffusion.py - 2024-10-24 20:53:02,270 - Loss: 0.2887, step: 59200
+INFO - dpsgd_diffusion.py - 2024-10-24 20:54:45,589 - Loss: 0.2862, step: 59300
+INFO - dpsgd_diffusion.py - 2024-10-24 20:56:27,951 - Loss: 0.3042, step: 59400
+INFO - dpsgd_diffusion.py - 2024-10-24 20:58:08,658 - Loss: 0.2999, step: 59500
+INFO - dpsgd_diffusion.py - 2024-10-24 20:59:50,353 - Loss: 0.2935, step: 59600
+INFO - dpsgd_diffusion.py - 2024-10-24 21:01:32,601 - Loss: 0.2956, step: 59700
+INFO - dpsgd_diffusion.py - 2024-10-24 21:03:15,080 - Loss: 0.3046, step: 59800
+INFO - dpsgd_diffusion.py - 2024-10-24 21:03:54,544 - Eps-value after 85 epochs: 0.7377
+INFO - dpsgd_diffusion.py - 2024-10-24 21:04:55,757 - Loss: 0.2871, step: 59900
+INFO - dpsgd_diffusion.py - 2024-10-24 21:06:37,364 - Loss: 0.3118, step: 60000
+INFO - dpsgd_diffusion.py - 2024-10-24 21:06:37,369 - Saving snapshot checkpoint and sampling single batch at iteration 60000.
+WARNING - image.py - 2024-10-24 21:06:38,477 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 21:07:08,149 - FID at iteration 60000: 264.711648
+INFO - dpsgd_diffusion.py - 2024-10-24 21:08:49,926 - Loss: 0.2977, step: 60100
+INFO - dpsgd_diffusion.py - 2024-10-24 21:10:33,869 - Loss: 0.2872, step: 60200
+INFO - dpsgd_diffusion.py - 2024-10-24 21:12:14,410 - Loss: 0.2765, step: 60300
+INFO - dpsgd_diffusion.py - 2024-10-24 21:13:56,478 - Loss: 0.3041, step: 60400
+INFO - dpsgd_diffusion.py - 2024-10-24 21:15:38,396 - Loss: 0.2666, step: 60500
+INFO - dpsgd_diffusion.py - 2024-10-24 21:16:21,819 - Eps-value after 86 epochs: 0.7424
+INFO - dpsgd_diffusion.py - 2024-10-24 21:17:18,035 - Loss: 0.2880, step: 60600
+INFO - dpsgd_diffusion.py - 2024-10-24 21:19:01,266 - Loss: 0.2927, step: 60700
+INFO - dpsgd_diffusion.py - 2024-10-24 21:20:44,377 - Loss: 0.2981, step: 60800
+INFO - dpsgd_diffusion.py - 2024-10-24 21:22:28,610 - Loss: 0.2882, step: 60900
+INFO - dpsgd_diffusion.py - 2024-10-24 21:24:11,649 - Loss: 0.2916, step: 61000
+INFO - dpsgd_diffusion.py - 2024-10-24 21:25:54,138 - Loss: 0.3119, step: 61100
+INFO - dpsgd_diffusion.py - 2024-10-24 21:27:34,980 - Loss: 0.2956, step: 61200
+INFO - dpsgd_diffusion.py - 2024-10-24 21:28:24,166 - Eps-value after 87 epochs: 0.7470
+INFO - dpsgd_diffusion.py - 2024-10-24 21:29:17,785 - Loss: 0.2798, step: 61300
+INFO - dpsgd_diffusion.py - 2024-10-24 21:31:00,860 - Loss: 0.3195, step: 61400
+INFO - dpsgd_diffusion.py - 2024-10-24 21:32:43,254 - Loss: 0.3001, step: 61500
+INFO - dpsgd_diffusion.py - 2024-10-24 21:34:23,038 - Loss: 0.3260, step: 61600
+INFO - dpsgd_diffusion.py - 2024-10-24 21:36:05,883 - Loss: 0.3022, step: 61700
+INFO - dpsgd_diffusion.py - 2024-10-24 21:37:46,678 - Loss: 0.2912, step: 61800
+INFO - dpsgd_diffusion.py - 2024-10-24 21:39:29,007 - Loss: 0.2895, step: 61900
+INFO - dpsgd_diffusion.py - 2024-10-24 21:40:22,829 - Eps-value after 88 epochs: 0.7515
+INFO - dpsgd_diffusion.py - 2024-10-24 21:41:12,321 - Loss: 0.2818, step: 62000
+INFO - dpsgd_diffusion.py - 2024-10-24 21:41:12,328 - Saving snapshot checkpoint and sampling single batch at iteration 62000.
+WARNING - image.py - 2024-10-24 21:41:13,474 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 21:41:43,180 - FID at iteration 62000: 264.211440
+INFO - dpsgd_diffusion.py - 2024-10-24 21:43:25,191 - Loss: 0.3053, step: 62100
+INFO - dpsgd_diffusion.py - 2024-10-24 21:45:07,230 - Loss: 0.2904, step: 62200
+INFO - dpsgd_diffusion.py - 2024-10-24 21:46:48,122 - Loss: 0.2803, step: 62300
+INFO - dpsgd_diffusion.py - 2024-10-24 21:48:29,003 - Loss: 0.3082, step: 62400
+INFO - dpsgd_diffusion.py - 2024-10-24 21:50:11,729 - Loss: 0.2871, step: 62500
+INFO - dpsgd_diffusion.py - 2024-10-24 21:51:53,756 - Loss: 0.2853, step: 62600
+INFO - dpsgd_diffusion.py - 2024-10-24 21:52:50,962 - Eps-value after 89 epochs: 0.7560
+INFO - dpsgd_diffusion.py - 2024-10-24 21:53:36,003 - Loss: 0.2967, step: 62700
+INFO - dpsgd_diffusion.py - 2024-10-24 21:55:16,340 - Loss: 0.2965, step: 62800
+INFO - dpsgd_diffusion.py - 2024-10-24 21:56:57,914 - Loss: 0.3046, step: 62900
+INFO - dpsgd_diffusion.py - 2024-10-24 21:58:40,862 - Loss: 0.2860, step: 63000
+INFO - dpsgd_diffusion.py - 2024-10-24 22:00:22,492 - Loss: 0.2916, step: 63100
+INFO - dpsgd_diffusion.py - 2024-10-24 22:02:04,667 - Loss: 0.2777, step: 63200
+INFO - dpsgd_diffusion.py - 2024-10-24 22:03:47,194 - Loss: 0.2982, step: 63300
+INFO - dpsgd_diffusion.py - 2024-10-24 22:04:49,249 - Eps-value after 90 epochs: 0.7605
+INFO - dpsgd_diffusion.py - 2024-10-24 22:05:30,185 - Loss: 0.3125, step: 63400
+INFO - dpsgd_diffusion.py - 2024-10-24 22:07:12,308 - Loss: 0.2767, step: 63500
+INFO - dpsgd_diffusion.py - 2024-10-24 22:08:55,159 - Loss: 0.3270, step: 63600
+INFO - dpsgd_diffusion.py - 2024-10-24 22:10:38,659 - Loss: 0.2847, step: 63700
+INFO - dpsgd_diffusion.py - 2024-10-24 22:12:21,401 - Loss: 0.2873, step: 63800
+INFO - dpsgd_diffusion.py - 2024-10-24 22:14:04,095 - Loss: 0.2975, step: 63900
+INFO - dpsgd_diffusion.py - 2024-10-24 22:15:47,736 - Loss: 0.2958, step: 64000
+INFO - dpsgd_diffusion.py - 2024-10-24 22:15:47,745 - Saving snapshot checkpoint and sampling single batch at iteration 64000.
+WARNING - image.py - 2024-10-24 22:15:48,864 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 22:16:18,559 - FID at iteration 64000: 260.778401
+INFO - dpsgd_diffusion.py - 2024-10-24 22:17:25,664 - Eps-value after 91 epochs: 0.7650
+INFO - dpsgd_diffusion.py - 2024-10-24 22:18:03,472 - Loss: 0.3259, step: 64100
+INFO - dpsgd_diffusion.py - 2024-10-24 22:19:46,001 - Loss: 0.2753, step: 64200
+INFO - dpsgd_diffusion.py - 2024-10-24 22:21:26,084 - Loss: 0.3109, step: 64300
+INFO - dpsgd_diffusion.py - 2024-10-24 22:23:07,392 - Loss: 0.2921, step: 64400
+INFO - dpsgd_diffusion.py - 2024-10-24 22:24:50,213 - Loss: 0.2940, step: 64500
+INFO - dpsgd_diffusion.py - 2024-10-24 22:26:30,509 - Loss: 0.3330, step: 64600
+INFO - dpsgd_diffusion.py - 2024-10-24 22:28:12,447 - Loss: 0.3000, step: 64700
+INFO - dpsgd_diffusion.py - 2024-10-24 22:29:20,347 - Eps-value after 92 epochs: 0.7696
+INFO - dpsgd_diffusion.py - 2024-10-24 22:29:53,328 - Loss: 0.3003, step: 64800
+INFO - dpsgd_diffusion.py - 2024-10-24 22:31:36,532 - Loss: 0.3011, step: 64900
+INFO - dpsgd_diffusion.py - 2024-10-24 22:33:19,029 - Loss: 0.3267, step: 65000
+INFO - dpsgd_diffusion.py - 2024-10-24 22:34:59,634 - Loss: 0.2953, step: 65100
+INFO - dpsgd_diffusion.py - 2024-10-24 22:36:39,124 - Loss: 0.2692, step: 65200
+INFO - dpsgd_diffusion.py - 2024-10-24 22:38:20,977 - Loss: 0.3081, step: 65300
+INFO - dpsgd_diffusion.py - 2024-10-24 22:40:01,834 - Loss: 0.3288, step: 65400
+INFO - dpsgd_diffusion.py - 2024-10-24 22:41:15,120 - Eps-value after 93 epochs: 0.7741
+INFO - dpsgd_diffusion.py - 2024-10-24 22:41:43,978 - Loss: 0.2784, step: 65500
+INFO - dpsgd_diffusion.py - 2024-10-24 22:43:23,786 - Loss: 0.3228, step: 65600
+INFO - dpsgd_diffusion.py - 2024-10-24 22:45:07,035 - Loss: 0.2825, step: 65700
+INFO - dpsgd_diffusion.py - 2024-10-24 22:46:51,129 - Loss: 0.3115, step: 65800
+INFO - dpsgd_diffusion.py - 2024-10-24 22:48:32,043 - Loss: 0.2874, step: 65900
+INFO - dpsgd_diffusion.py - 2024-10-24 22:50:13,627 - Loss: 0.2859, step: 66000
+INFO - dpsgd_diffusion.py - 2024-10-24 22:50:13,632 - Saving snapshot checkpoint and sampling single batch at iteration 66000.
+WARNING - image.py - 2024-10-24 22:50:14,727 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 22:50:44,497 - FID at iteration 66000: 260.114363
+INFO - dpsgd_diffusion.py - 2024-10-24 22:52:25,759 - Loss: 0.2782, step: 66100
+INFO - dpsgd_diffusion.py - 2024-10-24 22:53:42,246 - Eps-value after 94 epochs: 0.7785
+INFO - dpsgd_diffusion.py - 2024-10-24 22:54:07,081 - Loss: 0.3028, step: 66200
+INFO - dpsgd_diffusion.py - 2024-10-24 22:55:49,100 - Loss: 0.2860, step: 66300
+INFO - dpsgd_diffusion.py - 2024-10-24 22:57:31,523 - Loss: 0.2853, step: 66400
+INFO - dpsgd_diffusion.py - 2024-10-24 22:59:13,337 - Loss: 0.2973, step: 66500
+INFO - dpsgd_diffusion.py - 2024-10-24 23:00:55,551 - Loss: 0.2833, step: 66600
+INFO - dpsgd_diffusion.py - 2024-10-24 23:02:37,663 - Loss: 0.2672, step: 66700
+INFO - dpsgd_diffusion.py - 2024-10-24 23:04:19,030 - Loss: 0.2879, step: 66800
+INFO - dpsgd_diffusion.py - 2024-10-24 23:05:41,773 - Eps-value after 95 epochs: 0.7829
+INFO - dpsgd_diffusion.py - 2024-10-24 23:06:02,470 - Loss: 0.2691, step: 66900
+INFO - dpsgd_diffusion.py - 2024-10-24 23:07:44,393 - Loss: 0.2968, step: 67000
+INFO - dpsgd_diffusion.py - 2024-10-24 23:09:25,251 - Loss: 0.2835, step: 67100
+INFO - dpsgd_diffusion.py - 2024-10-24 23:11:06,576 - Loss: 0.2876, step: 67200
+INFO - dpsgd_diffusion.py - 2024-10-24 23:12:49,359 - Loss: 0.2893, step: 67300
+INFO - dpsgd_diffusion.py - 2024-10-24 23:14:32,640 - Loss: 0.3303, step: 67400
+INFO - dpsgd_diffusion.py - 2024-10-24 23:16:15,657 - Loss: 0.2944, step: 67500
+INFO - dpsgd_diffusion.py - 2024-10-24 23:17:42,366 - Eps-value after 96 epochs: 0.7872
+INFO - dpsgd_diffusion.py - 2024-10-24 23:17:59,623 - Loss: 0.2979, step: 67600
+INFO - dpsgd_diffusion.py - 2024-10-24 23:19:43,082 - Loss: 0.2906, step: 67700
+INFO - dpsgd_diffusion.py - 2024-10-24 23:21:25,642 - Loss: 0.2873, step: 67800
+INFO - dpsgd_diffusion.py - 2024-10-24 23:23:06,884 - Loss: 0.2890, step: 67900
+INFO - dpsgd_diffusion.py - 2024-10-24 23:24:47,804 - Loss: 0.2750, step: 68000
+INFO - dpsgd_diffusion.py - 2024-10-24 23:24:47,857 - Saving snapshot checkpoint and sampling single batch at iteration 68000.
+WARNING - image.py - 2024-10-24 23:24:48,926 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 23:25:18,542 - FID at iteration 68000: 258.797306
+INFO - dpsgd_diffusion.py - 2024-10-24 23:27:01,231 - Loss: 0.3162, step: 68100
+INFO - dpsgd_diffusion.py - 2024-10-24 23:28:44,080 - Loss: 0.2787, step: 68200
+INFO - dpsgd_diffusion.py - 2024-10-24 23:30:15,566 - Eps-value after 97 epochs: 0.7916
+INFO - dpsgd_diffusion.py - 2024-10-24 23:30:27,971 - Loss: 0.2802, step: 68300
+INFO - dpsgd_diffusion.py - 2024-10-24 23:32:08,974 - Loss: 0.2752, step: 68400
+INFO - dpsgd_diffusion.py - 2024-10-24 23:33:50,280 - Loss: 0.2929, step: 68500
+INFO - dpsgd_diffusion.py - 2024-10-24 23:35:30,648 - Loss: 0.2970, step: 68600
+INFO - dpsgd_diffusion.py - 2024-10-24 23:37:09,913 - Loss: 0.2907, step: 68700
+INFO - dpsgd_diffusion.py - 2024-10-24 23:38:50,293 - Loss: 0.2944, step: 68800
+INFO - dpsgd_diffusion.py - 2024-10-24 23:40:31,504 - Loss: 0.2972, step: 68900
+INFO - dpsgd_diffusion.py - 2024-10-24 23:42:03,722 - Eps-value after 98 epochs: 0.7959
+INFO - dpsgd_diffusion.py - 2024-10-24 23:42:11,941 - Loss: 0.3158, step: 69000
+INFO - dpsgd_diffusion.py - 2024-10-24 23:43:54,215 - Loss: 0.2809, step: 69100
+INFO - dpsgd_diffusion.py - 2024-10-24 23:45:35,665 - Loss: 0.2897, step: 69200
+INFO - dpsgd_diffusion.py - 2024-10-24 23:47:15,360 - Loss: 0.2967, step: 69300
+INFO - dpsgd_diffusion.py - 2024-10-24 23:48:55,739 - Loss: 0.2996, step: 69400
+INFO - dpsgd_diffusion.py - 2024-10-24 23:50:35,694 - Loss: 0.2994, step: 69500
+INFO - dpsgd_diffusion.py - 2024-10-24 23:52:19,546 - Loss: 0.2944, step: 69600
+INFO - dpsgd_diffusion.py - 2024-10-24 23:53:59,693 - Eps-value after 99 epochs: 0.8003
+INFO - dpsgd_diffusion.py - 2024-10-24 23:54:03,845 - Loss: 0.2814, step: 69700
+INFO - dpsgd_diffusion.py - 2024-10-24 23:55:46,716 - Loss: 0.2661, step: 69800
+INFO - dpsgd_diffusion.py - 2024-10-24 23:57:28,982 - Loss: 0.2832, step: 69900
+INFO - dpsgd_diffusion.py - 2024-10-24 23:59:11,244 - Loss: 0.2840, step: 70000
+INFO - dpsgd_diffusion.py - 2024-10-24 23:59:11,297 - Saving snapshot checkpoint and sampling single batch at iteration 70000.
+WARNING - image.py - 2024-10-24 23:59:12,359 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 23:59:42,062 - FID at iteration 70000: 257.262931
+INFO - dpsgd_diffusion.py - 2024-10-25 00:01:25,480 - Loss: 0.3280, step: 70100
+INFO - dpsgd_diffusion.py - 2024-10-25 00:03:07,719 - Loss: 0.2886, step: 70200
+INFO - dpsgd_diffusion.py - 2024-10-25 00:04:53,100 - Loss: 0.2790, step: 70300
+INFO - dpsgd_diffusion.py - 2024-10-25 00:06:33,072 - Loss: 0.2878, step: 70400
+INFO - dpsgd_diffusion.py - 2024-10-25 00:06:33,084 - Eps-value after 100 epochs: 0.8046
+INFO - dpsgd_diffusion.py - 2024-10-25 00:08:17,454 - Loss: 0.3118, step: 70500
+INFO - dpsgd_diffusion.py - 2024-10-25 00:09:59,420 - Loss: 0.3007, step: 70600
+INFO - dpsgd_diffusion.py - 2024-10-25 00:11:42,286 - Loss: 0.2736, step: 70700
+INFO - dpsgd_diffusion.py - 2024-10-25 00:13:24,654 - Loss: 0.2947, step: 70800
+INFO - dpsgd_diffusion.py - 2024-10-25 00:15:09,071 - Loss: 0.2942, step: 70900
+INFO - dpsgd_diffusion.py - 2024-10-25 00:16:52,605 - Loss: 0.2623, step: 71000
+INFO - dpsgd_diffusion.py - 2024-10-25 00:18:33,868 - Loss: 0.3002, step: 71100
+INFO - dpsgd_diffusion.py - 2024-10-25 00:18:37,835 - Eps-value after 101 epochs: 0.8089
+INFO - dpsgd_diffusion.py - 2024-10-25 00:20:15,853 - Loss: 0.2786, step: 71200
+INFO - dpsgd_diffusion.py - 2024-10-25 00:21:57,994 - Loss: 0.2701, step: 71300
+INFO - dpsgd_diffusion.py - 2024-10-25 00:23:40,255 - Loss: 0.3079, step: 71400
+INFO - dpsgd_diffusion.py - 2024-10-25 00:25:21,337 - Loss: 0.2632, step: 71500
+INFO - dpsgd_diffusion.py - 2024-10-25 00:27:03,466 - Loss: 0.2745, step: 71600
+INFO - dpsgd_diffusion.py - 2024-10-25 00:28:46,643 - Loss: 0.3006, step: 71700
+INFO - dpsgd_diffusion.py - 2024-10-25 00:30:25,778 - Loss: 0.3115, step: 71800
+INFO - dpsgd_diffusion.py - 2024-10-25 00:30:33,688 - Eps-value after 102 epochs: 0.8133
+INFO - dpsgd_diffusion.py - 2024-10-25 00:32:08,930 - Loss: 0.2957, step: 71900
+INFO - dpsgd_diffusion.py - 2024-10-25 00:33:51,195 - Loss: 0.2839, step: 72000
+INFO - dpsgd_diffusion.py - 2024-10-25 00:33:51,205 - Saving snapshot checkpoint and sampling single batch at iteration 72000.
+WARNING - image.py - 2024-10-25 00:33:52,269 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-25 00:34:21,627 - FID at iteration 72000: 254.083396
+INFO - dpsgd_diffusion.py - 2024-10-25 00:36:04,770 - Loss: 0.2786, step: 72100
+INFO - dpsgd_diffusion.py - 2024-10-25 00:37:46,712 - Loss: 0.2720, step: 72200
+INFO - dpsgd_diffusion.py - 2024-10-25 00:39:29,294 - Loss: 0.2841, step: 72300
+INFO - dpsgd_diffusion.py - 2024-10-25 00:41:09,889 - Loss: 0.2712, step: 72400
+INFO - dpsgd_diffusion.py - 2024-10-25 00:42:52,914 - Loss: 0.3000, step: 72500
+INFO - dpsgd_diffusion.py - 2024-10-25 00:43:04,817 - Eps-value after 103 epochs: 0.8175
+INFO - dpsgd_diffusion.py - 2024-10-25 00:44:34,078 - Loss: 0.3085, step: 72600
+INFO - dpsgd_diffusion.py - 2024-10-25 00:46:15,492 - Loss: 0.2823, step: 72700
+INFO - dpsgd_diffusion.py - 2024-10-25 00:47:57,625 - Loss: 0.2888, step: 72800
+INFO - dpsgd_diffusion.py - 2024-10-25 00:49:39,649 - Loss: 0.3173, step: 72900
+INFO - dpsgd_diffusion.py - 2024-10-25 00:51:20,850 - Loss: 0.2896, step: 73000
+INFO - dpsgd_diffusion.py - 2024-10-25 00:53:02,070 - Loss: 0.2672, step: 73100
+INFO - dpsgd_diffusion.py - 2024-10-25 00:54:40,699 - Loss: 0.2721, step: 73200
+INFO - dpsgd_diffusion.py - 2024-10-25 00:54:56,263 - Eps-value after 104 epochs: 0.8217
+INFO - dpsgd_diffusion.py - 2024-10-25 00:56:24,890 - Loss: 0.2791, step: 73300
+INFO - dpsgd_diffusion.py - 2024-10-25 00:58:06,770 - Loss: 0.2705, step: 73400
+INFO - dpsgd_diffusion.py - 2024-10-25 00:59:52,844 - Loss: 0.2700, step: 73500
+INFO - dpsgd_diffusion.py - 2024-10-25 01:01:36,423 - Loss: 0.2870, step: 73600
+INFO - dpsgd_diffusion.py - 2024-10-25 01:03:19,934 - Loss: 0.3211, step: 73700
+INFO - dpsgd_diffusion.py - 2024-10-25 01:05:02,407 - Loss: 0.2816, step: 73800
+INFO - dpsgd_diffusion.py - 2024-10-25 01:06:44,051 - Loss: 0.3072, step: 73900
+INFO - dpsgd_diffusion.py - 2024-10-25 01:07:03,810 - Eps-value after 105 epochs: 0.8258
+INFO - dpsgd_diffusion.py - 2024-10-25 01:08:24,523 - Loss: 0.2847, step: 74000
+INFO - dpsgd_diffusion.py - 2024-10-25 01:08:24,529 - Saving snapshot checkpoint and sampling single batch at iteration 74000.
+WARNING - image.py - 2024-10-25 01:08:25,612 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-25 01:08:55,338 - FID at iteration 74000: 253.658583
+INFO - dpsgd_diffusion.py - 2024-10-25 01:10:38,645 - Loss: 0.2856, step: 74100
+INFO - dpsgd_diffusion.py - 2024-10-25 01:12:21,262 - Loss: 0.2773, step: 74200
+INFO - dpsgd_diffusion.py - 2024-10-25 01:14:03,421 - Loss: 0.3030, step: 74300
+INFO - dpsgd_diffusion.py - 2024-10-25 01:15:43,891 - Loss: 0.2818, step: 74400
+INFO - dpsgd_diffusion.py - 2024-10-25 01:17:25,317 - Loss: 0.3092, step: 74500
+INFO - dpsgd_diffusion.py - 2024-10-25 01:19:08,281 - Loss: 0.2679, step: 74600
+INFO - dpsgd_diffusion.py - 2024-10-25 01:19:31,997 - Eps-value after 106 epochs: 0.8300
+INFO - dpsgd_diffusion.py - 2024-10-25 01:20:49,266 - Loss: 0.2874, step: 74700
+INFO - dpsgd_diffusion.py - 2024-10-25 01:22:31,355 - Loss: 0.2703, step: 74800
+INFO - dpsgd_diffusion.py - 2024-10-25 01:24:11,815 - Loss: 0.2806, step: 74900
+INFO - dpsgd_diffusion.py - 2024-10-25 01:25:53,683 - Loss: 0.2937, step: 75000
+INFO - dpsgd_diffusion.py - 2024-10-25 01:27:36,309 - Loss: 0.2641, step: 75100
+INFO - dpsgd_diffusion.py - 2024-10-25 01:29:17,316 - Loss: 0.3136, step: 75200
+INFO - dpsgd_diffusion.py - 2024-10-25 01:31:00,682 - Loss: 0.3227, step: 75300
+INFO - dpsgd_diffusion.py - 2024-10-25 01:31:29,497 - Eps-value after 107 epochs: 0.8342
+INFO - dpsgd_diffusion.py - 2024-10-25 01:32:42,976 - Loss: 0.3155, step: 75400
+INFO - dpsgd_diffusion.py - 2024-10-25 01:34:26,600 - Loss: 0.2760, step: 75500
+INFO - dpsgd_diffusion.py - 2024-10-25 01:36:08,433 - Loss: 0.2894, step: 75600
+INFO - dpsgd_diffusion.py - 2024-10-25 01:37:49,279 - Loss: 0.2824, step: 75700
+INFO - dpsgd_diffusion.py - 2024-10-25 01:39:30,803 - Loss: 0.2852, step: 75800
+INFO - dpsgd_diffusion.py - 2024-10-25 01:41:14,423 - Loss: 0.2854, step: 75900
+INFO - dpsgd_diffusion.py - 2024-10-25 01:42:58,452 - Loss: 0.2900, step: 76000
+INFO - dpsgd_diffusion.py - 2024-10-25 01:42:58,458 - Saving snapshot checkpoint and sampling single batch at iteration 76000.
+WARNING - image.py - 2024-10-25 01:42:59,522 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-25 01:43:29,298 - FID at iteration 76000: 250.796973
+INFO - dpsgd_diffusion.py - 2024-10-25 01:44:01,512 - Eps-value after 108 epochs: 0.8383
+INFO - dpsgd_diffusion.py - 2024-10-25 01:45:12,014 - Loss: 0.2735, step: 76100
+INFO - dpsgd_diffusion.py - 2024-10-25 01:46:54,032 - Loss: 0.3006, step: 76200
+INFO - dpsgd_diffusion.py - 2024-10-25 01:48:35,311 - Loss: 0.2899, step: 76300
+INFO - dpsgd_diffusion.py - 2024-10-25 01:50:15,540 - Loss: 0.2912, step: 76400
+INFO - dpsgd_diffusion.py - 2024-10-25 01:51:57,131 - Loss: 0.2596, step: 76500
+INFO - dpsgd_diffusion.py - 2024-10-25 01:53:40,135 - Loss: 0.2653, step: 76600
+INFO - dpsgd_diffusion.py - 2024-10-25 01:55:20,311 - Loss: 0.2966, step: 76700
+INFO - dpsgd_diffusion.py - 2024-10-25 01:55:57,117 - Eps-value after 109 epochs: 0.8425
+INFO - dpsgd_diffusion.py - 2024-10-25 01:57:01,659 - Loss: 0.2912, step: 76800
+INFO - dpsgd_diffusion.py - 2024-10-25 01:58:42,592 - Loss: 0.2759, step: 76900
+INFO - dpsgd_diffusion.py - 2024-10-25 02:00:25,460 - Loss: 0.3000, step: 77000
+INFO - dpsgd_diffusion.py - 2024-10-25 02:02:04,948 - Loss: 0.2811, step: 77100
+INFO - dpsgd_diffusion.py - 2024-10-25 02:03:46,101 - Loss: 0.2674, step: 77200
+INFO - dpsgd_diffusion.py - 2024-10-25 02:05:30,321 - Loss: 0.3048, step: 77300
+INFO - dpsgd_diffusion.py - 2024-10-25 02:07:10,949 - Loss: 0.2779, step: 77400
+INFO - dpsgd_diffusion.py - 2024-10-25 02:07:51,703 - Eps-value after 110 epochs: 0.8467
+INFO - dpsgd_diffusion.py - 2024-10-25 02:08:51,918 - Loss: 0.3038, step: 77500
+INFO - dpsgd_diffusion.py - 2024-10-25 02:10:35,249 - Loss: 0.2867, step: 77600
+INFO - dpsgd_diffusion.py - 2024-10-25 02:12:18,401 - Loss: 0.2934, step: 77700
+INFO - dpsgd_diffusion.py - 2024-10-25 02:14:01,730 - Loss: 0.2673, step: 77800
+INFO - dpsgd_diffusion.py - 2024-10-25 02:15:43,287 - Loss: 0.2743, step: 77900
+INFO - dpsgd_diffusion.py - 2024-10-25 02:17:24,769 - Loss: 0.2885, step: 78000
+INFO - dpsgd_diffusion.py - 2024-10-25 02:17:24,776 - Saving snapshot checkpoint and sampling single batch at iteration 78000.
+WARNING - image.py - 2024-10-25 02:17:25,842 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-25 02:17:55,586 - FID at iteration 78000: 248.719648
+INFO - dpsgd_diffusion.py - 2024-10-25 02:19:36,005 - Loss: 0.2692, step: 78100
+INFO - dpsgd_diffusion.py - 2024-10-25 02:20:21,601 - Eps-value after 111 epochs: 0.8509
+INFO - dpsgd_diffusion.py - 2024-10-25 02:21:17,859 - Loss: 0.3149, step: 78200
+INFO - dpsgd_diffusion.py - 2024-10-25 02:22:59,376 - Loss: 0.3163, step: 78300
+INFO - dpsgd_diffusion.py - 2024-10-25 02:24:39,526 - Loss: 0.2814, step: 78400
+INFO - dpsgd_diffusion.py - 2024-10-25 02:26:22,588 - Loss: 0.3109, step: 78500
+INFO - dpsgd_diffusion.py - 2024-10-25 02:28:05,044 - Loss: 0.2783, step: 78600
+INFO - dpsgd_diffusion.py - 2024-10-25 02:29:45,902 - Loss: 0.2747, step: 78700
+INFO - dpsgd_diffusion.py - 2024-10-25 02:31:26,322 - Loss: 0.3245, step: 78800
+INFO - dpsgd_diffusion.py - 2024-10-25 02:32:14,917 - Eps-value after 112 epochs: 0.8550
+INFO - dpsgd_diffusion.py - 2024-10-25 02:33:08,365 - Loss: 0.2960, step: 78900
+INFO - dpsgd_diffusion.py - 2024-10-25 02:34:53,059 - Loss: 0.3030, step: 79000
+INFO - dpsgd_diffusion.py - 2024-10-25 02:36:36,349 - Loss: 0.3105, step: 79100
+INFO - dpsgd_diffusion.py - 2024-10-25 02:38:17,142 - Loss: 0.2807, step: 79200
+INFO - dpsgd_diffusion.py - 2024-10-25 02:39:59,947 - Loss: 0.3112, step: 79300
+INFO - dpsgd_diffusion.py - 2024-10-25 02:41:40,711 - Loss: 0.2929, step: 79400
+INFO - dpsgd_diffusion.py - 2024-10-25 02:43:22,419 - Loss: 0.2746, step: 79500
+INFO - dpsgd_diffusion.py - 2024-10-25 02:44:14,735 - Eps-value after 113 epochs: 0.8590
+INFO - dpsgd_diffusion.py - 2024-10-25 02:45:04,047 - Loss: 0.2767, step: 79600
+INFO - dpsgd_diffusion.py - 2024-10-25 02:46:46,323 - Loss: 0.2726, step: 79700
+INFO - dpsgd_diffusion.py - 2024-10-25 02:48:30,167 - Loss: 0.2724, step: 79800
+INFO - dpsgd_diffusion.py - 2024-10-25 02:50:10,885 - Loss: 0.2993, step: 79900
+INFO - dpsgd_diffusion.py - 2024-10-25 02:51:51,607 - Loss: 0.2691, step: 80000
+INFO - dpsgd_diffusion.py - 2024-10-25 02:51:51,616 - Saving snapshot checkpoint and sampling single batch at iteration 80000.
+WARNING - image.py - 2024-10-25 02:51:52,692 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-25 02:52:22,488 - FID at iteration 80000: 245.670349
+INFO - dpsgd_diffusion.py - 2024-10-25 02:54:06,727 - Loss: 0.2866, step: 80100
+INFO - dpsgd_diffusion.py - 2024-10-25 02:55:50,532 - Loss: 0.3163, step: 80200
+INFO - dpsgd_diffusion.py - 2024-10-25 02:56:45,944 - Eps-value after 114 epochs: 0.8630
+INFO - dpsgd_diffusion.py - 2024-10-25 02:57:31,212 - Loss: 0.3163, step: 80300
+INFO - dpsgd_diffusion.py - 2024-10-25 02:59:14,568 - Loss: 0.2797, step: 80400
+INFO - dpsgd_diffusion.py - 2024-10-25 03:00:55,559 - Loss: 0.2858, step: 80500
+INFO - dpsgd_diffusion.py - 2024-10-25 03:02:38,287 - Loss: 0.3018, step: 80600
+INFO - dpsgd_diffusion.py - 2024-10-25 03:04:21,630 - Loss: 0.2973, step: 80700
+INFO - dpsgd_diffusion.py - 2024-10-25 03:06:04,548 - Loss: 0.2696, step: 80800
+INFO - dpsgd_diffusion.py - 2024-10-25 03:07:45,408 - Loss: 0.3036, step: 80900
+INFO - dpsgd_diffusion.py - 2024-10-25 03:08:45,942 - Eps-value after 115 epochs: 0.8670
+INFO - dpsgd_diffusion.py - 2024-10-25 03:09:26,132 - Loss: 0.3048, step: 81000
+INFO - dpsgd_diffusion.py - 2024-10-25 03:11:08,315 - Loss: 0.2936, step: 81100
+INFO - dpsgd_diffusion.py - 2024-10-25 03:12:48,918 - Loss: 0.2803, step: 81200
+INFO - dpsgd_diffusion.py - 2024-10-25 03:14:30,201 - Loss: 0.2848, step: 81300
+INFO - dpsgd_diffusion.py - 2024-10-25 03:16:13,280 - Loss: 0.2915, step: 81400
+INFO - dpsgd_diffusion.py - 2024-10-25 03:17:56,097 - Loss: 0.2775, step: 81500
+INFO - dpsgd_diffusion.py - 2024-10-25 03:19:36,339 - Loss: 0.2886, step: 81600
+INFO - dpsgd_diffusion.py - 2024-10-25 03:20:41,018 - Eps-value after 116 epochs: 0.8710
+INFO - dpsgd_diffusion.py - 2024-10-25 03:21:18,593 - Loss: 0.2738, step: 81700
+INFO - dpsgd_diffusion.py - 2024-10-25 03:23:00,964 - Loss: 0.3164, step: 81800
+INFO - dpsgd_diffusion.py - 2024-10-25 03:24:43,473 - Loss: 0.2770, step: 81900
+INFO - dpsgd_diffusion.py - 2024-10-25 03:26:26,856 - Loss: 0.2995, step: 82000
+INFO - dpsgd_diffusion.py - 2024-10-25 03:26:26,908 - Saving snapshot checkpoint and sampling single batch at iteration 82000.
+WARNING - image.py - 2024-10-25 03:26:27,971 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-25 03:26:57,661 - FID at iteration 82000: 246.749669
+INFO - dpsgd_diffusion.py - 2024-10-25 03:28:40,216 - Loss: 0.2739, step: 82100
+INFO - dpsgd_diffusion.py - 2024-10-25 03:30:22,983 - Loss: 0.3084, step: 82200
+INFO - dpsgd_diffusion.py - 2024-10-25 03:32:02,639 - Loss: 0.3073, step: 82300
+INFO - dpsgd_diffusion.py - 2024-10-25 03:33:10,612 - Eps-value after 117 epochs: 0.8750
+INFO - dpsgd_diffusion.py - 2024-10-25 03:33:46,090 - Loss: 0.2919, step: 82400
+INFO - dpsgd_diffusion.py - 2024-10-25 03:35:29,582 - Loss: 0.3047, step: 82500
+INFO - dpsgd_diffusion.py - 2024-10-25 03:37:14,496 - Loss: 0.2718, step: 82600
+INFO - dpsgd_diffusion.py - 2024-10-25 03:38:57,230 - Loss: 0.2606, step: 82700
+INFO - dpsgd_diffusion.py - 2024-10-25 03:40:40,495 - Loss: 0.2970, step: 82800
+INFO - dpsgd_diffusion.py - 2024-10-25 03:42:22,114 - Loss: 0.2560, step: 82900
+INFO - dpsgd_diffusion.py - 2024-10-25 03:44:04,642 - Loss: 0.2937, step: 83000
+INFO - dpsgd_diffusion.py - 2024-10-25 03:45:18,748 - Eps-value after 118 epochs: 0.8790
+INFO - dpsgd_diffusion.py - 2024-10-25 03:45:47,064 - Loss: 0.2845, step: 83100
+INFO - dpsgd_diffusion.py - 2024-10-25 03:47:27,931 - Loss: 0.2884, step: 83200
+INFO - dpsgd_diffusion.py - 2024-10-25 03:49:10,173 - Loss: 0.3039, step: 83300
+INFO - dpsgd_diffusion.py - 2024-10-25 03:50:52,703 - Loss: 0.2869, step: 83400
+INFO - dpsgd_diffusion.py - 2024-10-25 03:52:34,918 - Loss: 0.2621, step: 83500
+INFO - dpsgd_diffusion.py - 2024-10-25 03:54:16,623 - Loss: 0.2715, step: 83600
+INFO - dpsgd_diffusion.py - 2024-10-25 03:55:59,779 - Loss: 0.2702, step: 83700
+INFO - dpsgd_diffusion.py - 2024-10-25 03:57:18,656 - Eps-value after 119 epochs: 0.8830
+INFO - dpsgd_diffusion.py - 2024-10-25 03:57:43,415 - Loss: 0.3138, step: 83800
+INFO - dpsgd_diffusion.py - 2024-10-25 03:59:24,863 - Loss: 0.2843, step: 83900
+INFO - dpsgd_diffusion.py - 2024-10-25 04:01:07,846 - Loss: 0.2930, step: 84000
+INFO - dpsgd_diffusion.py - 2024-10-25 04:01:07,938 - Saving snapshot checkpoint and sampling single batch at iteration 84000.
+WARNING - image.py - 2024-10-25 04:01:09,001 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-25 04:01:38,728 - FID at iteration 84000: 246.974198
+INFO - dpsgd_diffusion.py - 2024-10-25 04:03:23,311 - Loss: 0.2861, step: 84100
+INFO - dpsgd_diffusion.py - 2024-10-25 04:05:06,245 - Loss: 0.2802, step: 84200
+INFO - dpsgd_diffusion.py - 2024-10-25 04:06:50,837 - Loss: 0.2894, step: 84300
+INFO - dpsgd_diffusion.py - 2024-10-25 04:08:33,440 - Loss: 0.3005, step: 84400
+INFO - dpsgd_diffusion.py - 2024-10-25 04:09:56,846 - Eps-value after 120 epochs: 0.8870
+INFO - dpsgd_diffusion.py - 2024-10-25 04:10:17,466 - Loss: 0.3077, step: 84500
+INFO - dpsgd_diffusion.py - 2024-10-25 04:11:59,933 - Loss: 0.2758, step: 84600
+INFO - dpsgd_diffusion.py - 2024-10-25 04:13:40,520 - Loss: 0.2811, step: 84700
+INFO - dpsgd_diffusion.py - 2024-10-25 04:15:23,320 - Loss: 0.2836, step: 84800
+INFO - dpsgd_diffusion.py - 2024-10-25 04:17:06,860 - Loss: 0.2710, step: 84900
+INFO - dpsgd_diffusion.py - 2024-10-25 04:18:50,252 - Loss: 0.2974, step: 85000
+INFO - dpsgd_diffusion.py - 2024-10-25 04:20:35,670 - Loss: 0.2863, step: 85100
+INFO - dpsgd_diffusion.py - 2024-10-25 04:22:05,169 - Eps-value after 121 epochs: 0.8910
+INFO - dpsgd_diffusion.py - 2024-10-25 04:22:22,405 - Loss: 0.2989, step: 85200
+INFO - dpsgd_diffusion.py - 2024-10-25 04:24:05,554 - Loss: 0.2781, step: 85300
+INFO - dpsgd_diffusion.py - 2024-10-25 04:25:47,634 - Loss: 0.2796, step: 85400
+INFO - dpsgd_diffusion.py - 2024-10-25 04:27:30,663 - Loss: 0.2945, step: 85500
+INFO - dpsgd_diffusion.py - 2024-10-25 04:29:12,652 - Loss: 0.2963, step: 85600
+INFO - dpsgd_diffusion.py - 2024-10-25 04:30:55,755 - Loss: 0.2955, step: 85700
+INFO - dpsgd_diffusion.py - 2024-10-25 04:32:36,335 - Loss: 0.2838, step: 85800
+INFO - dpsgd_diffusion.py - 2024-10-25 04:34:05,400 - Eps-value after 122 epochs: 0.8950
+INFO - dpsgd_diffusion.py - 2024-10-25 04:34:17,746 - Loss: 0.2789, step: 85900
+INFO - dpsgd_diffusion.py - 2024-10-25 04:35:59,595 - Loss: 0.3018, step: 86000
+INFO - dpsgd_diffusion.py - 2024-10-25 04:35:59,600 - Saving snapshot checkpoint and sampling single batch at iteration 86000.
+WARNING - image.py - 2024-10-25 04:36:00,666 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-25 04:36:30,390 - FID at iteration 86000: 245.003593
+INFO - dpsgd_diffusion.py - 2024-10-25 04:38:10,145 - Loss: 0.2927, step: 86100
+INFO - dpsgd_diffusion.py - 2024-10-25 04:39:51,047 - Loss: 0.2581, step: 86200
+INFO - dpsgd_diffusion.py - 2024-10-25 04:41:32,164 - Loss: 0.2813, step: 86300
+INFO - dpsgd_diffusion.py - 2024-10-25 04:43:12,452 - Loss: 0.2870, step: 86400
+INFO - dpsgd_diffusion.py - 2024-10-25 04:44:55,636 - Loss: 0.2957, step: 86500
+INFO - dpsgd_diffusion.py - 2024-10-25 04:46:28,456 - Eps-value after 123 epochs: 0.8990
+INFO - dpsgd_diffusion.py - 2024-10-25 04:46:36,731 - Loss: 0.3141, step: 86600
+INFO - dpsgd_diffusion.py - 2024-10-25 04:48:17,133 - Loss: 0.2755, step: 86700
+INFO - dpsgd_diffusion.py - 2024-10-25 04:49:58,651 - Loss: 0.2862, step: 86800
+INFO - dpsgd_diffusion.py - 2024-10-25 04:51:39,345 - Loss: 0.2961, step: 86900
+INFO - dpsgd_diffusion.py - 2024-10-25 04:53:22,235 - Loss: 0.3040, step: 87000
+INFO - dpsgd_diffusion.py - 2024-10-25 04:55:03,527 - Loss: 0.3245, step: 87100
+INFO - dpsgd_diffusion.py - 2024-10-25 04:56:46,242 - Loss: 0.3147, step: 87200
+INFO - dpsgd_diffusion.py - 2024-10-25 04:58:24,093 - Eps-value after 124 epochs: 0.9029
+INFO - dpsgd_diffusion.py - 2024-10-25 04:58:28,230 - Loss: 0.2800, step: 87300
+INFO - dpsgd_diffusion.py - 2024-10-25 05:00:11,497 - Loss: 0.3224, step: 87400
+INFO - dpsgd_diffusion.py - 2024-10-25 05:01:54,408 - Loss: 0.2930, step: 87500
+INFO - dpsgd_diffusion.py - 2024-10-25 05:03:37,470 - Loss: 0.2697, step: 87600
+INFO - dpsgd_diffusion.py - 2024-10-25 05:05:18,250 - Loss: 0.3138, step: 87700
+INFO - dpsgd_diffusion.py - 2024-10-25 05:06:59,462 - Loss: 0.2977, step: 87800
+INFO - dpsgd_diffusion.py - 2024-10-25 05:08:40,364 - Loss: 0.2719, step: 87900
+INFO - dpsgd_diffusion.py - 2024-10-25 05:10:20,019 - Loss: 0.2823, step: 88000
+INFO - dpsgd_diffusion.py - 2024-10-25 05:10:20,031 - Eps-value after 125 epochs: 0.9067
+INFO - dpsgd_diffusion.py - 2024-10-25 05:10:20,037 - Saving snapshot checkpoint and sampling single batch at iteration 88000.
+WARNING - image.py - 2024-10-25 05:10:21,101 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-25 05:10:50,803 - FID at iteration 88000: 244.110875
+INFO - dpsgd_diffusion.py - 2024-10-25 05:12:34,286 - Loss: 0.2768, step: 88100
+INFO - dpsgd_diffusion.py - 2024-10-25 05:14:15,972 - Loss: 0.2979, step: 88200
+INFO - dpsgd_diffusion.py - 2024-10-25 05:15:58,612 - Loss: 0.2822, step: 88300
+INFO - dpsgd_diffusion.py - 2024-10-25 05:17:38,225 - Loss: 0.2974, step: 88400
+INFO - dpsgd_diffusion.py - 2024-10-25 05:19:20,558 - Loss: 0.2959, step: 88500
+INFO - dpsgd_diffusion.py - 2024-10-25 05:21:02,224 - Loss: 0.2759, step: 88600
+INFO - dpsgd_diffusion.py - 2024-10-25 05:22:45,245 - Loss: 0.2691, step: 88700
+INFO - dpsgd_diffusion.py - 2024-10-25 05:22:49,214 - Eps-value after 126 epochs: 0.9105
+INFO - dpsgd_diffusion.py - 2024-10-25 05:24:26,880 - Loss: 0.2585, step: 88800
+INFO - dpsgd_diffusion.py - 2024-10-25 05:26:08,932 - Loss: 0.2765, step: 88900
+INFO - dpsgd_diffusion.py - 2024-10-25 05:27:51,929 - Loss: 0.3034, step: 89000
+INFO - dpsgd_diffusion.py - 2024-10-25 05:29:35,570 - Loss: 0.2686, step: 89100
+INFO - dpsgd_diffusion.py - 2024-10-25 05:31:17,298 - Loss: 0.2989, step: 89200
+INFO - dpsgd_diffusion.py - 2024-10-25 05:32:59,309 - Loss: 0.2561, step: 89300
+INFO - dpsgd_diffusion.py - 2024-10-25 05:34:40,210 - Loss: 0.2846, step: 89400
+INFO - dpsgd_diffusion.py - 2024-10-25 05:34:48,164 - Eps-value after 127 epochs: 0.9143
+INFO - dpsgd_diffusion.py - 2024-10-25 05:36:21,288 - Loss: 0.2908, step: 89500
+INFO - dpsgd_diffusion.py - 2024-10-25 05:37:59,121 - Loss: 0.2648, step: 89600
+INFO - dpsgd_diffusion.py - 2024-10-25 05:39:42,762 - Loss: 0.3011, step: 89700
+INFO - dpsgd_diffusion.py - 2024-10-25 05:41:24,440 - Loss: 0.3109, step: 89800
+INFO - dpsgd_diffusion.py - 2024-10-25 05:43:07,910 - Loss: 0.3095, step: 89900
+INFO - dpsgd_diffusion.py - 2024-10-25 05:44:50,199 - Loss: 0.2667, step: 90000
+INFO - dpsgd_diffusion.py - 2024-10-25 05:44:50,249 - Saving snapshot checkpoint and sampling single batch at iteration 90000.
+WARNING - image.py - 2024-10-25 05:44:51,313 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-25 05:45:21,046 - FID at iteration 90000: 245.871861
+INFO - dpsgd_diffusion.py - 2024-10-25 05:47:02,794 - Loss: 0.2939, step: 90100
+INFO - dpsgd_diffusion.py - 2024-10-25 05:47:14,651 - Eps-value after 128 epochs: 0.9181
+INFO - dpsgd_diffusion.py - 2024-10-25 05:48:45,533 - Loss: 0.2931, step: 90200
+INFO - dpsgd_diffusion.py - 2024-10-25 05:50:25,638 - Loss: 0.2792, step: 90300
+INFO - dpsgd_diffusion.py - 2024-10-25 05:52:07,400 - Loss: 0.2777, step: 90400
+INFO - dpsgd_diffusion.py - 2024-10-25 05:53:47,614 - Loss: 0.2987, step: 90500
+INFO - dpsgd_diffusion.py - 2024-10-25 05:55:29,649 - Loss: 0.2601, step: 90600
+INFO - dpsgd_diffusion.py - 2024-10-25 05:57:11,781 - Loss: 0.2907, step: 90700
+INFO - dpsgd_diffusion.py - 2024-10-25 05:58:54,887 - Loss: 0.2738, step: 90800
+INFO - dpsgd_diffusion.py - 2024-10-25 05:59:10,700 - Eps-value after 129 epochs: 0.9220
+INFO - dpsgd_diffusion.py - 2024-10-25 06:00:36,638 - Loss: 0.2676, step: 90900
+INFO - dpsgd_diffusion.py - 2024-10-25 06:02:17,411 - Loss: 0.3004, step: 91000
+INFO - dpsgd_diffusion.py - 2024-10-25 06:03:59,913 - Loss: 0.2739, step: 91100
+INFO - dpsgd_diffusion.py - 2024-10-25 06:05:40,631 - Loss: 0.3009, step: 91200
+INFO - dpsgd_diffusion.py - 2024-10-25 06:07:25,671 - Loss: 0.2826, step: 91300
+INFO - dpsgd_diffusion.py - 2024-10-25 06:09:06,667 - Loss: 0.2889, step: 91400
+INFO - dpsgd_diffusion.py - 2024-10-25 06:10:49,877 - Loss: 0.3041, step: 91500
+INFO - dpsgd_diffusion.py - 2024-10-25 06:11:10,460 - Eps-value after 130 epochs: 0.9258
+INFO - dpsgd_diffusion.py - 2024-10-25 06:12:34,190 - Loss: 0.2700, step: 91600
+INFO - dpsgd_diffusion.py - 2024-10-25 06:14:17,483 - Loss: 0.2724, step: 91700
+INFO - dpsgd_diffusion.py - 2024-10-25 06:16:00,843 - Loss: 0.2603, step: 91800
+INFO - dpsgd_diffusion.py - 2024-10-25 06:17:41,608 - Loss: 0.2973, step: 91900
+INFO - dpsgd_diffusion.py - 2024-10-25 06:19:25,435 - Loss: 0.2925, step: 92000
+INFO - dpsgd_diffusion.py - 2024-10-25 06:19:25,445 - Saving snapshot checkpoint and sampling single batch at iteration 92000.
+WARNING - image.py - 2024-10-25 06:19:26,534 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-25 06:19:56,294 - FID at iteration 92000: 241.327242
+INFO - dpsgd_diffusion.py - 2024-10-25 06:21:39,784 - Loss: 0.2819, step: 92100
+INFO - dpsgd_diffusion.py - 2024-10-25 06:23:21,426 - Loss: 0.2851, step: 92200
+INFO - dpsgd_diffusion.py - 2024-10-25 06:23:45,575 - Eps-value after 131 epochs: 0.9296
+INFO - dpsgd_diffusion.py - 2024-10-25 06:25:02,059 - Loss: 0.2928, step: 92300
+INFO - dpsgd_diffusion.py - 2024-10-25 06:26:46,441 - Loss: 0.2861, step: 92400
+INFO - dpsgd_diffusion.py - 2024-10-25 06:28:30,875 - Loss: 0.2804, step: 92500
+INFO - dpsgd_diffusion.py - 2024-10-25 06:30:13,054 - Loss: 0.3146, step: 92600
+INFO - dpsgd_diffusion.py - 2024-10-25 06:31:52,817 - Loss: 0.2537, step: 92700
+INFO - dpsgd_diffusion.py - 2024-10-25 06:33:35,840 - Loss: 0.3115, step: 92800
+INFO - dpsgd_diffusion.py - 2024-10-25 06:35:18,198 - Loss: 0.2947, step: 92900
+INFO - dpsgd_diffusion.py - 2024-10-25 06:35:45,852 - Eps-value after 132 epochs: 0.9334
+INFO - dpsgd_diffusion.py - 2024-10-25 06:37:00,797 - Loss: 0.2812, step: 93000
+INFO - dpsgd_diffusion.py - 2024-10-25 06:38:41,867 - Loss: 0.2702, step: 93100
+INFO - dpsgd_diffusion.py - 2024-10-25 06:40:24,341 - Loss: 0.2841, step: 93200
+INFO - dpsgd_diffusion.py - 2024-10-25 06:42:03,991 - Loss: 0.2999, step: 93300
+INFO - dpsgd_diffusion.py - 2024-10-25 06:43:45,138 - Loss: 0.2811, step: 93400
+INFO - dpsgd_diffusion.py - 2024-10-25 06:45:28,280 - Loss: 0.2791, step: 93500
+INFO - dpsgd_diffusion.py - 2024-10-25 06:47:12,082 - Loss: 0.2803, step: 93600
+INFO - dpsgd_diffusion.py - 2024-10-25 06:47:45,191 - Eps-value after 133 epochs: 0.9372
+INFO - dpsgd_diffusion.py - 2024-10-25 06:48:55,546 - Loss: 0.2534, step: 93700
+INFO - dpsgd_diffusion.py - 2024-10-25 06:50:36,629 - Loss: 0.2552, step: 93800
+INFO - dpsgd_diffusion.py - 2024-10-25 06:52:21,122 - Loss: 0.3007, step: 93900
+INFO - dpsgd_diffusion.py - 2024-10-25 06:54:02,567 - Loss: 0.2941, step: 94000
+INFO - dpsgd_diffusion.py - 2024-10-25 06:54:02,573 - Saving snapshot checkpoint and sampling single batch at iteration 94000.
+WARNING - image.py - 2024-10-25 06:54:03,637 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-25 06:54:33,384 - FID at iteration 94000: 241.808952
+INFO - dpsgd_diffusion.py - 2024-10-25 06:56:14,659 - Loss: 0.2857, step: 94100
+INFO - dpsgd_diffusion.py - 2024-10-25 06:57:57,238 - Loss: 0.2948, step: 94200
+INFO - dpsgd_diffusion.py - 2024-10-25 06:59:40,458 - Loss: 0.2616, step: 94300
+INFO - dpsgd_diffusion.py - 2024-10-25 07:00:16,628 - Eps-value after 134 epochs: 0.9411
+INFO - dpsgd_diffusion.py - 2024-10-25 07:01:23,956 - Loss: 0.2797, step: 94400
+INFO - dpsgd_diffusion.py - 2024-10-25 07:03:06,981 - Loss: 0.2589, step: 94500
+INFO - dpsgd_diffusion.py - 2024-10-25 07:04:48,819 - Loss: 0.2918, step: 94600
+INFO - dpsgd_diffusion.py - 2024-10-25 07:06:29,528 - Loss: 0.2700, step: 94700
+INFO - dpsgd_diffusion.py - 2024-10-25 07:08:10,222 - Loss: 0.2667, step: 94800
+INFO - dpsgd_diffusion.py - 2024-10-25 07:09:49,743 - Loss: 0.2915, step: 94900
+INFO - dpsgd_diffusion.py - 2024-10-25 07:11:34,335 - Loss: 0.2670, step: 95000
+INFO - dpsgd_diffusion.py - 2024-10-25 07:12:16,339 - Eps-value after 135 epochs: 0.9449
+INFO - dpsgd_diffusion.py - 2024-10-25 07:13:15,623 - Loss: 0.2938, step: 95100
+INFO - dpsgd_diffusion.py - 2024-10-25 07:14:57,544 - Loss: 0.2831, step: 95200
+INFO - dpsgd_diffusion.py - 2024-10-25 07:16:37,913 - Loss: 0.2832, step: 95300
+INFO - dpsgd_diffusion.py - 2024-10-25 07:18:22,458 - Loss: 0.2804, step: 95400
+INFO - dpsgd_diffusion.py - 2024-10-25 07:20:06,287 - Loss: 0.2941, step: 95500
+INFO - dpsgd_diffusion.py - 2024-10-25 07:21:49,907 - Loss: 0.2756, step: 95600
+INFO - dpsgd_diffusion.py - 2024-10-25 07:23:32,132 - Loss: 0.2948, step: 95700
+INFO - dpsgd_diffusion.py - 2024-10-25 07:24:16,642 - Eps-value after 136 epochs: 0.9487
+INFO - dpsgd_diffusion.py - 2024-10-25 07:25:14,973 - Loss: 0.2996, step: 95800
+INFO - dpsgd_diffusion.py - 2024-10-25 07:26:56,532 - Loss: 0.2747, step: 95900
+INFO - dpsgd_diffusion.py - 2024-10-25 07:28:38,648 - Loss: 0.2789, step: 96000
+INFO - dpsgd_diffusion.py - 2024-10-25 07:28:38,658 - Saving snapshot checkpoint and sampling single batch at iteration 96000.
+WARNING - image.py - 2024-10-25 07:28:39,723 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-25 07:29:09,419 - FID at iteration 96000: 241.046160
+INFO - dpsgd_diffusion.py - 2024-10-25 07:30:54,256 - Loss: 0.3075, step: 96100
+INFO - dpsgd_diffusion.py - 2024-10-25 07:32:38,167 - Loss: 0.3090, step: 96200
+INFO - dpsgd_diffusion.py - 2024-10-25 07:34:23,549 - Loss: 0.2928, step: 96300
+INFO - dpsgd_diffusion.py - 2024-10-25 07:36:05,927 - Loss: 0.2888, step: 96400
+INFO - dpsgd_diffusion.py - 2024-10-25 07:36:55,756 - Eps-value after 137 epochs: 0.9524
+INFO - dpsgd_diffusion.py - 2024-10-25 07:37:47,644 - Loss: 0.2871, step: 96500
+INFO - dpsgd_diffusion.py - 2024-10-25 07:39:31,264 - Loss: 0.2858, step: 96600
+INFO - dpsgd_diffusion.py - 2024-10-25 07:41:11,653 - Loss: 0.2763, step: 96700
+INFO - dpsgd_diffusion.py - 2024-10-25 07:42:54,134 - Loss: 0.2862, step: 96800
+INFO - dpsgd_diffusion.py - 2024-10-25 07:44:38,582 - Loss: 0.2709, step: 96900
+INFO - dpsgd_diffusion.py - 2024-10-25 07:46:19,331 - Loss: 0.2886, step: 97000
+INFO - dpsgd_diffusion.py - 2024-10-25 07:47:58,708 - Loss: 0.2693, step: 97100
+INFO - dpsgd_diffusion.py - 2024-10-25 07:48:51,613 - Eps-value after 138 epochs: 0.9561
+INFO - dpsgd_diffusion.py - 2024-10-25 07:49:40,496 - Loss: 0.2872, step: 97200
+INFO - dpsgd_diffusion.py - 2024-10-25 07:51:23,267 - Loss: 0.2656, step: 97300
+INFO - dpsgd_diffusion.py - 2024-10-25 07:53:06,915 - Loss: 0.2834, step: 97400
+INFO - dpsgd_diffusion.py - 2024-10-25 07:54:48,103 - Loss: 0.2790, step: 97500
+INFO - dpsgd_diffusion.py - 2024-10-25 07:56:29,975 - Loss: 0.2827, step: 97600
+INFO - dpsgd_diffusion.py - 2024-10-25 07:58:14,255 - Loss: 0.3023, step: 97700
+INFO - dpsgd_diffusion.py - 2024-10-25 07:59:55,825 - Loss: 0.2517, step: 97800
+INFO - dpsgd_diffusion.py - 2024-10-25 08:00:53,812 - Eps-value after 139 epochs: 0.9597
+INFO - dpsgd_diffusion.py - 2024-10-25 08:01:39,597 - Loss: 0.2668, step: 97900
+INFO - dpsgd_diffusion.py - 2024-10-25 08:03:23,460 - Loss: 0.2696, step: 98000
+INFO - dpsgd_diffusion.py - 2024-10-25 08:03:23,480 - Saving snapshot checkpoint and sampling single batch at iteration 98000.
+WARNING - image.py - 2024-10-25 08:03:24,546 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-25 08:03:54,514 - FID at iteration 98000: 240.685949
+INFO - dpsgd_diffusion.py - 2024-10-25 08:05:35,482 - Loss: 0.2859, step: 98100
+INFO - dpsgd_diffusion.py - 2024-10-25 08:07:17,970 - Loss: 0.2858, step: 98200
+INFO - dpsgd_diffusion.py - 2024-10-25 08:08:58,821 - Loss: 0.3040, step: 98300
+INFO - dpsgd_diffusion.py - 2024-10-25 08:10:40,791 - Loss: 0.2773, step: 98400
+INFO - dpsgd_diffusion.py - 2024-10-25 08:12:21,697 - Loss: 0.2563, step: 98500
+INFO - dpsgd_diffusion.py - 2024-10-25 08:13:23,841 - Eps-value after 140 epochs: 0.9634
+INFO - dpsgd_diffusion.py - 2024-10-25 08:14:04,999 - Loss: 0.2619, step: 98600
+INFO - dpsgd_diffusion.py - 2024-10-25 08:15:50,286 - Loss: 0.2573, step: 98700
+INFO - dpsgd_diffusion.py - 2024-10-25 08:17:34,834 - Loss: 0.2787, step: 98800
+INFO - dpsgd_diffusion.py - 2024-10-25 08:19:16,625 - Loss: 0.2990, step: 98900
+INFO - dpsgd_diffusion.py - 2024-10-25 08:20:58,513 - Loss: 0.2484, step: 99000
+INFO - dpsgd_diffusion.py - 2024-10-25 08:22:41,395 - Loss: 0.2794, step: 99100
+INFO - dpsgd_diffusion.py - 2024-10-25 08:24:20,753 - Loss: 0.2715, step: 99200
+INFO - dpsgd_diffusion.py - 2024-10-25 08:25:24,487 - Eps-value after 141 epochs: 0.9670
+INFO - dpsgd_diffusion.py - 2024-10-25 08:26:01,630 - Loss: 0.2800, step: 99300
+INFO - dpsgd_diffusion.py - 2024-10-25 08:27:43,238 - Loss: 0.2647, step: 99400
+INFO - dpsgd_diffusion.py - 2024-10-25 08:29:26,100 - Loss: 0.2759, step: 99500
+INFO - dpsgd_diffusion.py - 2024-10-25 08:31:10,679 - Loss: 0.2631, step: 99600
+INFO - dpsgd_diffusion.py - 2024-10-25 08:32:53,823 - Loss: 0.2548, step: 99700
+INFO - dpsgd_diffusion.py - 2024-10-25 08:34:37,033 - Loss: 0.2904, step: 99800
+INFO - dpsgd_diffusion.py - 2024-10-25 08:36:19,230 - Loss: 0.2801, step: 99900
+INFO - dpsgd_diffusion.py - 2024-10-25 08:37:30,001 - Eps-value after 142 epochs: 0.9706
+INFO - dpsgd_diffusion.py - 2024-10-25 08:38:03,118 - Loss: 0.2720, step: 100000
+INFO - dpsgd_diffusion.py - 2024-10-25 08:38:03,124 - Saving snapshot checkpoint and sampling single batch at iteration 100000.
+WARNING - image.py - 2024-10-25 08:38:04,204 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-25 08:38:34,646 - FID at iteration 100000: 238.215976
+INFO - dpsgd_diffusion.py - 2024-10-25 08:38:35,351 - Saving  checkpoint at iteration 100000
+INFO - dpsgd_diffusion.py - 2024-10-25 08:40:17,246 - Loss: 0.2757, step: 100100
+INFO - dpsgd_diffusion.py - 2024-10-25 08:41:58,651 - Loss: 0.2532, step: 100200
+INFO - dpsgd_diffusion.py - 2024-10-25 08:43:39,364 - Loss: 0.2791, step: 100300
+INFO - dpsgd_diffusion.py - 2024-10-25 08:45:19,435 - Loss: 0.2765, step: 100400
+INFO - dpsgd_diffusion.py - 2024-10-25 08:47:02,557 - Loss: 0.2863, step: 100500
+INFO - dpsgd_diffusion.py - 2024-10-25 08:48:45,557 - Loss: 0.3015, step: 100600
+INFO - dpsgd_diffusion.py - 2024-10-25 08:49:57,920 - Eps-value after 143 epochs: 0.9743
+INFO - dpsgd_diffusion.py - 2024-10-25 08:50:26,178 - Loss: 0.2743, step: 100700
+INFO - dpsgd_diffusion.py - 2024-10-25 08:52:07,463 - Loss: 0.2866, step: 100800
+INFO - dpsgd_diffusion.py - 2024-10-25 08:53:49,839 - Loss: 0.2580, step: 100900
+INFO - dpsgd_diffusion.py - 2024-10-25 08:55:34,417 - Loss: 0.2928, step: 101000
+INFO - dpsgd_diffusion.py - 2024-10-25 08:57:16,707 - Loss: 0.2810, step: 101100
+INFO - dpsgd_diffusion.py - 2024-10-25 08:58:59,495 - Loss: 0.2658, step: 101200
+INFO - dpsgd_diffusion.py - 2024-10-25 09:00:41,718 - Loss: 0.2660, step: 101300
+INFO - dpsgd_diffusion.py - 2024-10-25 09:01:58,987 - Eps-value after 144 epochs: 0.9779
+INFO - dpsgd_diffusion.py - 2024-10-25 09:02:23,376 - Loss: 0.2717, step: 101400
+INFO - dpsgd_diffusion.py - 2024-10-25 09:04:04,590 - Loss: 0.2850, step: 101500
+INFO - dpsgd_diffusion.py - 2024-10-25 09:05:49,379 - Loss: 0.2818, step: 101600
+INFO - dpsgd_diffusion.py - 2024-10-25 09:07:33,820 - Loss: 0.2838, step: 101700
+INFO - dpsgd_diffusion.py - 2024-10-25 09:09:14,074 - Loss: 0.2472, step: 101800
+INFO - dpsgd_diffusion.py - 2024-10-25 09:10:54,657 - Loss: 0.2853, step: 101900
+INFO - dpsgd_diffusion.py - 2024-10-25 09:12:38,906 - Loss: 0.2675, step: 102000
+INFO - dpsgd_diffusion.py - 2024-10-25 09:12:38,912 - Saving snapshot checkpoint and sampling single batch at iteration 102000.
+WARNING - image.py - 2024-10-25 09:12:39,975 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-25 09:13:09,683 - FID at iteration 102000: 237.768631
+INFO - dpsgd_diffusion.py - 2024-10-25 09:14:32,088 - Eps-value after 145 epochs: 0.9816
+INFO - dpsgd_diffusion.py - 2024-10-25 09:14:52,768 - Loss: 0.2711, step: 102100
+INFO - dpsgd_diffusion.py - 2024-10-25 09:16:33,749 - Loss: 0.2894, step: 102200
+INFO - dpsgd_diffusion.py - 2024-10-25 09:18:14,759 - Loss: 0.2906, step: 102300
+INFO - dpsgd_diffusion.py - 2024-10-25 09:19:56,687 - Loss: 0.2849, step: 102400
+INFO - dpsgd_diffusion.py - 2024-10-25 09:21:40,167 - Loss: 0.2655, step: 102500
+INFO - dpsgd_diffusion.py - 2024-10-25 09:23:23,510 - Loss: 0.2871, step: 102600
+INFO - dpsgd_diffusion.py - 2024-10-25 09:25:08,554 - Loss: 0.2683, step: 102700
+INFO - dpsgd_diffusion.py - 2024-10-25 09:26:32,950 - Eps-value after 146 epochs: 0.9852
+INFO - dpsgd_diffusion.py - 2024-10-25 09:26:49,407 - Loss: 0.2711, step: 102800
+INFO - dpsgd_diffusion.py - 2024-10-25 09:28:31,369 - Loss: 0.3000, step: 102900
+INFO - dpsgd_diffusion.py - 2024-10-25 09:30:14,090 - Loss: 0.2714, step: 103000
+INFO - dpsgd_diffusion.py - 2024-10-25 09:31:55,471 - Loss: 0.2863, step: 103100
+INFO - dpsgd_diffusion.py - 2024-10-25 09:33:37,296 - Loss: 0.2795, step: 103200
+INFO - dpsgd_diffusion.py - 2024-10-25 09:35:17,847 - Loss: 0.3093, step: 103300
+INFO - dpsgd_diffusion.py - 2024-10-25 09:36:59,906 - Loss: 0.2889, step: 103400
+INFO - dpsgd_diffusion.py - 2024-10-25 09:38:28,984 - Eps-value after 147 epochs: 0.9889
+INFO - dpsgd_diffusion.py - 2024-10-25 09:38:41,312 - Loss: 0.3015, step: 103500
+INFO - dpsgd_diffusion.py - 2024-10-25 09:40:22,720 - Loss: 0.2802, step: 103600
+INFO - dpsgd_diffusion.py - 2024-10-25 09:42:04,933 - Loss: 0.2501, step: 103700
+INFO - dpsgd_diffusion.py - 2024-10-25 09:43:45,467 - Loss: 0.2829, step: 103800
+INFO - dpsgd_diffusion.py - 2024-10-25 09:45:25,038 - Loss: 0.2717, step: 103900
+INFO - dpsgd_diffusion.py - 2024-10-25 09:47:05,993 - Loss: 0.2791, step: 104000
+INFO - dpsgd_diffusion.py - 2024-10-25 09:47:06,002 - Saving snapshot checkpoint and sampling single batch at iteration 104000.
+WARNING - image.py - 2024-10-25 09:47:07,066 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-25 09:47:36,841 - FID at iteration 104000: 236.881917
+INFO - dpsgd_diffusion.py - 2024-10-25 09:49:19,249 - Loss: 0.2829, step: 104100
+INFO - dpsgd_diffusion.py - 2024-10-25 09:50:52,947 - Eps-value after 148 epochs: 0.9925
+INFO - dpsgd_diffusion.py - 2024-10-25 09:51:01,223 - Loss: 0.2846, step: 104200
+INFO - dpsgd_diffusion.py - 2024-10-25 09:52:40,445 - Loss: 0.2939, step: 104300
+INFO - dpsgd_diffusion.py - 2024-10-25 09:54:21,304 - Loss: 0.3035, step: 104400
+INFO - dpsgd_diffusion.py - 2024-10-25 09:56:01,794 - Loss: 0.2948, step: 104500
+INFO - dpsgd_diffusion.py - 2024-10-25 09:57:43,741 - Loss: 0.3106, step: 104600
+INFO - dpsgd_diffusion.py - 2024-10-25 09:59:23,702 - Loss: 0.2815, step: 104700
+INFO - dpsgd_diffusion.py - 2024-10-25 10:01:03,704 - Loss: 0.2851, step: 104800
+INFO - dpsgd_diffusion.py - 2024-10-25 10:02:40,015 - Eps-value after 149 epochs: 0.9962
+INFO - dpsgd_diffusion.py - 2024-10-25 10:02:44,155 - Loss: 0.2882, step: 104900
+INFO - dpsgd_diffusion.py - 2024-10-25 10:04:24,910 - Loss: 0.2764, step: 105000
+INFO - dpsgd_diffusion.py - 2024-10-25 10:06:05,558 - Loss: 0.2899, step: 105100
+INFO - dpsgd_diffusion.py - 2024-10-25 10:07:46,777 - Loss: 0.3061, step: 105200
+INFO - dpsgd_diffusion.py - 2024-10-25 10:09:28,196 - Loss: 0.2730, step: 105300
+INFO - dpsgd_diffusion.py - 2024-10-25 10:11:10,379 - Loss: 0.2809, step: 105400
+INFO - dpsgd_diffusion.py - 2024-10-25 10:12:50,239 - Loss: 0.2644, step: 105500
+INFO - dpsgd_diffusion.py - 2024-10-25 10:14:34,144 - Loss: 0.2774, step: 105600
+INFO - dpsgd_diffusion.py - 2024-10-25 10:14:34,157 - Eps-value after 150 epochs: 0.9998
+INFO - dpsgd_diffusion.py - 2024-10-25 10:14:34,752 - Saving final checkpoint.
+INFO - dpsgd_diffusion.py - 2024-10-25 10:14:34,754 - start to generate 60000 samples
+INFO - dpsgd_diffusion.py - 2024-10-25 10:35:42,250 - Generation Finished!
+INFO - dataset_loader.py - 2024-10-26 01:23:26,133 - delta is reset as 2.07404851125286e-06
+INFO - evaluator.py - 2024-10-26 01:24:07,273 - Epoch: 0 Train acc: 1.3636363636363635 Val acc: 1.2 Test acc1.58; Train loss: 0.036844904691522774 Val loss: 0.009031436729431153
+INFO - evaluator.py - 2024-10-26 01:24:25,501 - Epoch: 1 Train acc: 2.4672727272727273 Val acc: 1.34 Test acc1.18; Train loss: 0.03499116795279763 Val loss: 0.09572283477783203
+INFO - dataset_loader.py - 2024-10-26 01:25:52,343 - delta is reset as 2.07404851125286e-06
+INFO - evaluator.py - 2024-10-26 01:26:11,681 - Epoch: 0 Train acc: 1.1636363636363636 Val acc: 1.0 Test acc1.22; Train loss: 0.03692365917725997 Val loss: 0.004897337627410889
+INFO - dataset_loader.py - 2024-10-26 01:28:09,933 - delta is reset as 2.07404851125286e-06
+INFO - evaluator.py - 2024-10-26 01:28:28,790 - Epoch: 0 Train acc: 0.9836363636363636 Val acc: 1.0 Test acc1.0699999999999998; Train loss: 0.03700994666706432 Val loss: 0.0046895973205566405
+INFO - evaluator.py - 2024-10-26 01:28:46,720 - Epoch: 1 Train acc: 0.9981818181818182 Val acc: 0.9400000000000001 Test acc1.08; Train loss: 0.036599818290363656 Val loss: 0.004985813426971435
+INFO - evaluator.py - 2024-10-26 01:29:04,558 - Epoch: 2 Train acc: 1.7927272727272725 Val acc: 1.4000000000000001 Test acc1.23; Train loss: 0.035773026570406825 Val loss: 0.03924920120239258
+INFO - evaluator.py - 2024-10-26 01:29:22,587 - Epoch: 3 Train acc: 2.5309090909090908 Val acc: 1.02 Test acc1.22; Train loss: 0.0347663816018538 Val loss: 0.11365941772460937
+INFO - evaluator.py - 2024-10-26 01:29:40,417 - Epoch: 4 Train acc: 2.8781818181818184 Val acc: 1.1199999999999999 Test acc1.08; Train loss: 0.03442995048002763 Val loss: 0.27437840576171874
+INFO - evaluator.py - 2024-10-26 01:29:58,250 - Epoch: 5 Train acc: 3.7254545454545456 Val acc: 1.48 Test acc1.22; Train loss: 0.03381801065965132 Val loss: 3.83501904296875
+INFO - evaluator.py - 2024-10-26 01:30:16,390 - Epoch: 6 Train acc: 5.050909090909091 Val acc: 1.54 Test acc1.15; Train loss: 0.0330302530635487 Val loss: 9.9809875
+INFO - dataset_loader.py - 2024-10-26 01:30:18,211 - delta is reset as 2.07404851125286e-06
+INFO - dataset_loader.py - 2024-10-26 01:51:04,778 - delta is reset as 2.07404851125286e-06
+INFO - evaluator.py - 2024-10-26 01:52:35,870 - Epoch: 0 Train acc: 1.2054545454545456 Val acc: 1.04 Test acc1.08; Train loss: 0.03682083904959939 Val loss: 0.004721940994262696
+INFO - evaluator.py - 2024-10-26 01:53:18,046 - Epoch: 1 Train acc: 2.630909090909091 Val acc: 1.66 Test acc1.7500000000000002; Train loss: 0.03481026205583052 Val loss: 0.008979265022277833
+INFO - evaluator.py - 2024-10-26 01:54:01,770 - Epoch: 2 Train acc: 4.003636363636363 Val acc: 1.28 Test acc1.63; Train loss: 0.03369287033948031 Val loss: 0.008529768562316895
+INFO - evaluator.py - 2024-10-26 01:54:49,368 - Epoch: 3 Train acc: 4.772727272727273 Val acc: 1.0999999999999999 Test acc1.46; Train loss: 0.03315838144909252 Val loss: 0.012337771797180175
+INFO - evaluator.py - 2024-10-26 01:55:36,788 - Epoch: 4 Train acc: 5.232727272727273 Val acc: 0.6 Test acc0.75; Train loss: 0.03283057773329995 Val loss: 0.02569211540222168
+INFO - evaluator.py - 2024-10-26 01:56:19,653 - Epoch: 5 Train acc: 6.1872727272727275 Val acc: 0.8200000000000001 Test acc1.01; Train loss: 0.032414915735071353 Val loss: 0.017478840637207033
+INFO - evaluator.py - 2024-10-26 01:57:02,427 - Epoch: 6 Train acc: 7.558181818181818 Val acc: 0.5 Test acc0.7000000000000001; Train loss: 0.03170342148000544 Val loss: 0.022880932998657226
+INFO - evaluator.py - 2024-10-26 01:57:46,062 - Epoch: 7 Train acc: 16.88909090909091 Val acc: 1.66 Test acc1.9; Train loss: 0.026672393790158358 Val loss: 0.007724753379821777
+INFO - evaluator.py - 2024-10-26 01:58:33,089 - Epoch: 8 Train acc: 30.14363636363636 Val acc: 2.56 Test acc2.22; Train loss: 0.020947421281987972 Val loss: 0.007919673728942872
+INFO - evaluator.py - 2024-10-26 01:59:19,450 - Epoch: 9 Train acc: 40.49818181818182 Val acc: 1.46 Test acc1.38; Train loss: 0.017291760667887603 Val loss: 0.014107126808166504
+INFO - evaluator.py - 2024-10-26 02:00:04,002 - Epoch: 10 Train acc: 51.770909090909086 Val acc: 2.1999999999999997 Test acc2.0500000000000003; Train loss: 0.013484224560044028 Val loss: 0.011013140678405762
+INFO - evaluator.py - 2024-10-26 02:00:45,338 - Epoch: 11 Train acc: 61.85636363636363 Val acc: 1.8599999999999999 Test acc1.8800000000000001; Train loss: 0.010473700928688049 Val loss: 0.014643829154968261
+INFO - evaluator.py - 2024-10-26 02:01:28,102 - Epoch: 12 Train acc: 69.02363636363637 Val acc: 1.2 Test acc1.4200000000000002; Train loss: 0.008327450662309473 Val loss: 0.01788907928466797
+INFO - evaluator.py - 2024-10-26 02:02:14,936 - Epoch: 13 Train acc: 75.88181818181819 Val acc: 1.6 Test acc1.47; Train loss: 0.0063720963954925535 Val loss: 0.016580286407470703
+INFO - evaluator.py - 2024-10-26 02:02:57,943 - Epoch: 14 Train acc: 79.24363636363636 Val acc: 2.2800000000000002 Test acc1.9900000000000002; Train loss: 0.005477860226956281 Val loss: 0.01710151824951172
+INFO - evaluator.py - 2024-10-26 02:03:40,916 - Epoch: 15 Train acc: 82.5 Val acc: 2.1999999999999997 Test acc1.7500000000000002; Train loss: 0.00460809475237673 Val loss: 0.02462294578552246
+INFO - evaluator.py - 2024-10-26 02:04:23,662 - Epoch: 16 Train acc: 84.23272727272727 Val acc: 1.32 Test acc1.68; Train loss: 0.0041382745623588565 Val loss: 0.02491909523010254
+INFO - evaluator.py - 2024-10-26 02:05:06,738 - Epoch: 17 Train acc: 85.57272727272728 Val acc: 1.5599999999999998 Test acc1.55; Train loss: 0.003785812186652964 Val loss: 0.028349155807495117
+INFO - evaluator.py - 2024-10-26 02:05:51,769 - Epoch: 18 Train acc: 86.16363636363637 Val acc: 2.02 Test acc1.68; Train loss: 0.0035755790558728304 Val loss: 0.018740613174438477
+INFO - evaluator.py - 2024-10-26 02:06:39,238 - Epoch: 19 Train acc: 86.90545454545455 Val acc: 1.2 Test acc1.38; Train loss: 0.003397551346637986 Val loss: 0.02905209312438965
+INFO - evaluator.py - 2024-10-26 02:07:21,657 - Epoch: 20 Train acc: 87.48 Val acc: 1.26 Test acc1.41; Train loss: 0.0032559226913885637 Val loss: 0.02875423240661621
+INFO - evaluator.py - 2024-10-26 02:08:06,679 - Epoch: 21 Train acc: 87.88363636363637 Val acc: 1.0999999999999999 Test acc1.26; Train loss: 0.003124800318208608 Val loss: 0.02671566619873047
+INFO - evaluator.py - 2024-10-26 02:08:50,657 - Epoch: 22 Train acc: 88.22545454545454 Val acc: 1.58 Test acc1.8399999999999999; Train loss: 0.003033344140648842 Val loss: 0.01989682846069336
+INFO - evaluator.py - 2024-10-26 02:09:36,052 - Epoch: 23 Train acc: 88.5909090909091 Val acc: 1.16 Test acc1.13; Train loss: 0.0029567513864148746 Val loss: 0.025143228912353516
+INFO - evaluator.py - 2024-10-26 02:10:21,629 - Epoch: 24 Train acc: 88.73818181818181 Val acc: 1.6199999999999999 Test acc1.29; Train loss: 0.002864091967723586 Val loss: 0.03265081024169922
+INFO - evaluator.py - 2024-10-26 02:11:06,182 - Epoch: 25 Train acc: 88.80363636363636 Val acc: 1.18 Test acc1.1199999999999999; Train loss: 0.0028729198664426804 Val loss: 0.024243865966796875
+INFO - evaluator.py - 2024-10-26 02:11:48,758 - Epoch: 26 Train acc: 89.02 Val acc: 1.0999999999999999 Test acc1.03; Train loss: 0.002819455469467423 Val loss: 0.02985216484069824
+INFO - evaluator.py - 2024-10-26 02:12:36,626 - Epoch: 27 Train acc: 89.12181818181818 Val acc: 1.1199999999999999 Test acc1.3599999999999999; Train loss: 0.0027648026777939362 Val loss: 0.02707285461425781
+INFO - evaluator.py - 2024-10-26 02:13:23,795 - Epoch: 28 Train acc: 89.60000000000001 Val acc: 0.76 Test acc0.8999999999999999; Train loss: 0.0026877976796843787 Val loss: 0.0317248291015625
+INFO - evaluator.py - 2024-10-26 02:14:08,377 - Epoch: 29 Train acc: 89.22363636363636 Val acc: 1.4000000000000001 Test acc1.44; Train loss: 0.0027318969333713704 Val loss: 0.023964437103271483
+INFO - evaluator.py - 2024-10-26 02:14:53,442 - Epoch: 30 Train acc: 89.29454545454546 Val acc: 0.7000000000000001 Test acc0.54; Train loss: 0.002740677628462965 Val loss: 0.032437761306762694
+INFO - evaluator.py - 2024-10-26 02:15:37,680 - Epoch: 31 Train acc: 89.67818181818183 Val acc: 1.6 Test acc1.69; Train loss: 0.002658041919903322 Val loss: 0.021789305877685548
+INFO - evaluator.py - 2024-10-26 02:16:26,879 - Epoch: 32 Train acc: 89.92545454545454 Val acc: 1.52 Test acc1.34; Train loss: 0.002616739365729419 Val loss: 0.020375735473632813
+INFO - evaluator.py - 2024-10-26 02:17:14,213 - Epoch: 33 Train acc: 89.6509090909091 Val acc: 0.9199999999999999 Test acc1.06; Train loss: 0.0026223257807168093 Val loss: 0.05019336929321289
+INFO - evaluator.py - 2024-10-26 02:18:00,194 - Epoch: 34 Train acc: 90.0090909090909 Val acc: 1.8599999999999999 Test acc1.9300000000000002; Train loss: 0.002557562005519867 Val loss: 0.024315472793579103
+INFO - evaluator.py - 2024-10-26 02:18:43,108 - Epoch: 35 Train acc: 90.12909090909092 Val acc: 1.68 Test acc1.58; Train loss: 0.0025320332146503708 Val loss: 0.032206517791748046
+INFO - evaluator.py - 2024-10-26 02:19:28,648 - Epoch: 36 Train acc: 89.8509090909091 Val acc: 1.4000000000000001 Test acc1.59; Train loss: 0.0025776954436844044 Val loss: 0.027976639556884765
+INFO - evaluator.py - 2024-10-26 02:20:14,493 - Epoch: 37 Train acc: 90.19636363636364 Val acc: 1.0999999999999999 Test acc1.27; Train loss: 0.002519257568635724 Val loss: 0.029934245681762697
+INFO - evaluator.py - 2024-10-26 02:20:59,203 - Epoch: 38 Train acc: 90.44181818181818 Val acc: 1.2 Test acc1.09; Train loss: 0.002451756871288473 Val loss: 0.04353181381225586
+INFO - evaluator.py - 2024-10-26 02:21:44,176 - Epoch: 39 Train acc: 90.21272727272728 Val acc: 1.6199999999999999 Test acc1.68; Train loss: 0.002512457792054523 Val loss: 0.02820320053100586
+INFO - evaluator.py - 2024-10-26 02:22:29,198 - Epoch: 40 Train acc: 90.28545454545454 Val acc: 1.24 Test acc1.54; Train loss: 0.002500611633468758 Val loss: 0.022811281204223634
+INFO - evaluator.py - 2024-10-26 02:23:14,903 - Epoch: 41 Train acc: 89.99636363636364 Val acc: 1.3599999999999999 Test acc1.47; Train loss: 0.002599609078331427 Val loss: 0.03369574508666992
+INFO - evaluator.py - 2024-10-26 02:24:03,614 - Epoch: 42 Train acc: 90.63272727272728 Val acc: 0.8200000000000001 Test acc0.8999999999999999; Train loss: 0.0023842965157194573 Val loss: 0.04530824432373047
+INFO - evaluator.py - 2024-10-26 02:24:50,693 - Epoch: 43 Train acc: 90.25090909090909 Val acc: 1.94 Test acc1.8399999999999999; Train loss: 0.0025021826589649372 Val loss: 0.02660302963256836
+INFO - evaluator.py - 2024-10-26 02:25:39,514 - Epoch: 44 Train acc: 90.50363636363636 Val acc: 0.9199999999999999 Test acc1.01; Train loss: 0.0024173653506419875 Val loss: 0.06220863418579101
+INFO - evaluator.py - 2024-10-26 02:26:27,997 - Epoch: 45 Train acc: 90.16545454545455 Val acc: 1.0999999999999999 Test acc1.02; Train loss: 0.0025287344669753854 Val loss: 0.036489313507080075
+INFO - evaluator.py - 2024-10-26 02:27:12,123 - Epoch: 46 Train acc: 90.84545454545454 Val acc: 0.8200000000000001 Test acc1.1900000000000002; Train loss: 0.0023555417372421784 Val loss: 0.04347014923095703
+INFO - evaluator.py - 2024-10-26 02:27:58,008 - Epoch: 47 Train acc: 90.83636363636364 Val acc: 1.1400000000000001 Test acc1.21; Train loss: 0.0023726028152487493 Val loss: 0.03286384582519531
+INFO - evaluator.py - 2024-10-26 02:28:44,091 - Epoch: 48 Train acc: 90.42545454545454 Val acc: 1.16 Test acc1.0699999999999998; Train loss: 0.0024378947910937395 Val loss: 0.027107114410400392
+INFO - evaluator.py - 2024-10-26 02:29:31,604 - Epoch: 49 Train acc: 90.5690909090909 Val acc: 1.24 Test acc1.4000000000000001; Train loss: 0.0024371513904495675 Val loss: 0.02914052963256836
+INFO - evaluator.py - 2024-10-26 02:30:19,536 - Epoch: 50 Train acc: 90.89636363636365 Val acc: 0.96 Test acc1.24; Train loss: 0.0023714360046115787 Val loss: 0.03918651275634766
+INFO - evaluator.py - 2024-10-26 02:31:04,984 - Epoch: 51 Train acc: 90.38363636363637 Val acc: 1.08 Test acc1.1400000000000001; Train loss: 0.0024555882012302225 Val loss: 0.02477993125915527
+INFO - evaluator.py - 2024-10-26 02:31:48,495 - Epoch: 52 Train acc: 90.53454545454545 Val acc: 1.18 Test acc1.32; Train loss: 0.0024027754420583897 Val loss: 0.02256829032897949
+INFO - evaluator.py - 2024-10-26 02:32:34,434 - Epoch: 53 Train acc: 90.71454545454546 Val acc: 1.4000000000000001 Test acc1.7000000000000002; Train loss: 0.002402385388179259 Val loss: 0.03709230194091797
+INFO - evaluator.py - 2024-10-26 02:33:17,747 - Epoch: 54 Train acc: 90.93636363636364 Val acc: 1.04 Test acc1.11; Train loss: 0.00232958392013203 Val loss: 0.03333511276245117
+INFO - evaluator.py - 2024-10-26 02:34:00,964 - Epoch: 55 Train acc: 91.06181818181818 Val acc: 1.22 Test acc0.91; Train loss: 0.002293201109902425 Val loss: 0.04024138946533203
+INFO - evaluator.py - 2024-10-26 02:34:47,697 - Epoch: 56 Train acc: 90.5690909090909 Val acc: 1.26 Test acc1.16; Train loss: 0.002426476251943545 Val loss: 0.03682632141113281
+INFO - evaluator.py - 2024-10-26 02:35:30,051 - Epoch: 57 Train acc: 90.9890909090909 Val acc: 1.6400000000000001 Test acc1.53; Train loss: 0.0023242581538178704 Val loss: 0.02461484451293945
+INFO - evaluator.py - 2024-10-26 02:36:14,614 - Epoch: 58 Train acc: 90.88000000000001 Val acc: 0.8200000000000001 Test acc0.8999999999999999; Train loss: 0.002323138661818071 Val loss: 0.028201923751831056
+INFO - evaluator.py - 2024-10-26 02:37:00,017 - Epoch: 59 Train acc: 90.71636363636364 Val acc: 1.7399999999999998 Test acc1.79; Train loss: 0.002367373406074264 Val loss: 0.02221501235961914
+INFO - evaluator.py - 2024-10-26 02:37:45,152 - Epoch: 60 Train acc: 98.55272727272727 Val acc: 1.7399999999999998 Test acc1.4500000000000002; Train loss: 0.00044106784236024727 Val loss: 0.024027822875976563
+INFO - evaluator.py - 2024-10-26 02:38:35,025 - Epoch: 61 Train acc: 99.60727272727271 Val acc: 1.34 Test acc1.05; Train loss: 0.00018137660759755156 Val loss: 0.04132310333251953
+INFO - evaluator.py - 2024-10-26 02:39:22,398 - Epoch: 62 Train acc: 99.84545454545454 Val acc: 1.22 Test acc1.11; Train loss: 0.00011822836814786901 Val loss: 0.060058578491210934
+INFO - evaluator.py - 2024-10-26 02:40:08,429 - Epoch: 63 Train acc: 99.95454545454545 Val acc: 1.22 Test acc1.01; Train loss: 8.812327310019596e-05 Val loss: 0.10265152282714844
+INFO - evaluator.py - 2024-10-26 02:40:53,589 - Epoch: 64 Train acc: 99.97818181818182 Val acc: 1.26 Test acc1.04; Train loss: 7.669571599584411e-05 Val loss: 0.15617223510742187
+INFO - evaluator.py - 2024-10-26 02:41:37,666 - Epoch: 65 Train acc: 99.98181818181818 Val acc: 1.26 Test acc1.04; Train loss: 7.361037160100585e-05 Val loss: 0.21576370849609375
+INFO - evaluator.py - 2024-10-26 02:42:22,742 - Epoch: 66 Train acc: 99.98727272727272 Val acc: 1.18 Test acc1.02; Train loss: 6.557049089619382e-05 Val loss: 0.2976035888671875
+INFO - evaluator.py - 2024-10-26 02:43:08,830 - Epoch: 67 Train acc: 99.99272727272728 Val acc: 1.18 Test acc1.0; Train loss: 5.969994760711085e-05 Val loss: 0.42389818725585937
+INFO - evaluator.py - 2024-10-26 02:43:53,534 - Epoch: 68 Train acc: 99.99090909090908 Val acc: 1.3599999999999999 Test acc1.06; Train loss: 5.949700883674351e-05 Val loss: 0.5631099243164063
+INFO - evaluator.py - 2024-10-26 02:44:39,519 - Epoch: 69 Train acc: 99.99636363636364 Val acc: 1.26 Test acc0.9199999999999999; Train loss: 5.7687401902777224e-05 Val loss: 0.8357513305664063
+INFO - evaluator.py - 2024-10-26 02:45:27,843 - Epoch: 70 Train acc: 99.99636363636364 Val acc: 1.0999999999999999 Test acc1.0999999999999999; Train loss: 5.408330221491104e-05 Val loss: 1.161866259765625
+INFO - evaluator.py - 2024-10-26 02:46:13,090 - Epoch: 71 Train acc: 99.99818181818182 Val acc: 0.9400000000000001 Test acc1.02; Train loss: 5.276412050747736e-05 Val loss: 1.9005162841796874
+INFO - evaluator.py - 2024-10-26 02:46:59,482 - Epoch: 72 Train acc: 99.9890909090909 Val acc: 0.9199999999999999 Test acc0.98; Train loss: 5.5732085687023674e-05 Val loss: 2.46158525390625
+INFO - evaluator.py - 2024-10-26 02:47:47,191 - Epoch: 73 Train acc: 99.89454545454547 Val acc: 0.8200000000000001 Test acc1.06; Train loss: 9.77647717280144e-05 Val loss: 2.25282236328125
+INFO - evaluator.py - 2024-10-26 02:48:33,737 - Epoch: 74 Train acc: 99.61454545454545 Val acc: 0.88 Test acc1.0; Train loss: 0.0001959839924069291 Val loss: 2.246778759765625
+INFO - evaluator.py - 2024-10-26 02:49:20,807 - Epoch: 75 Train acc: 98.67636363636365 Val acc: 0.8999999999999999 Test acc1.01; Train loss: 0.00043517796473408285 Val loss: 1.4471267333984374
+INFO - evaluator.py - 2024-10-26 02:50:07,184 - Epoch: 76 Train acc: 98.21636363636364 Val acc: 0.9199999999999999 Test acc1.01; Train loss: 0.0005282177118584514 Val loss: 0.8389562377929688
+INFO - evaluator.py - 2024-10-26 02:50:50,434 - Epoch: 77 Train acc: 97.74181818181819 Val acc: 1.08 Test acc1.09; Train loss: 0.0006351205840706825 Val loss: 0.4393079650878906
+INFO - evaluator.py - 2024-10-26 02:51:36,109 - Epoch: 78 Train acc: 97.57454545454546 Val acc: 0.96 Test acc1.0; Train loss: 0.0006568083176220005 Val loss: 0.20020372314453125
+INFO - evaluator.py - 2024-10-26 02:52:21,591 - Epoch: 79 Train acc: 98.14181818181818 Val acc: 1.26 Test acc1.06; Train loss: 0.0005341380027376793 Val loss: 0.15514382934570312
+INFO - evaluator.py - 2024-10-26 02:53:07,121 - Epoch: 80 Train acc: 97.79454545454546 Val acc: 0.9400000000000001 Test acc1.01; Train loss: 0.0005922690259631384 Val loss: 0.13513471069335936
+INFO - evaluator.py - 2024-10-26 02:53:55,186 - Epoch: 81 Train acc: 97.87636363636364 Val acc: 1.24 Test acc1.0699999999999998; Train loss: 0.0005636285601691766 Val loss: 0.101213818359375
+INFO - evaluator.py - 2024-10-26 02:54:40,111 - Epoch: 82 Train acc: 98.06727272727272 Val acc: 1.04 Test acc1.04; Train loss: 0.0005646907833828167 Val loss: 0.08272873077392578
+INFO - evaluator.py - 2024-10-26 02:55:26,610 - Epoch: 83 Train acc: 98.21272727272728 Val acc: 1.0999999999999999 Test acc1.02; Train loss: 0.0004983069496567954 Val loss: 0.06859024047851563
+INFO - evaluator.py - 2024-10-26 02:56:14,589 - Epoch: 84 Train acc: 98.47636363636364 Val acc: 0.9400000000000001 Test acc1.03; Train loss: 0.0004319373138079589 Val loss: 0.06710496063232421
+INFO - evaluator.py - 2024-10-26 02:56:59,270 - Epoch: 85 Train acc: 97.91090909090909 Val acc: 1.28 Test acc1.0999999999999999; Train loss: 0.0005696188551797108 Val loss: 0.06071983184814453
+INFO - evaluator.py - 2024-10-26 02:57:44,709 - Epoch: 86 Train acc: 98.0690909090909 Val acc: 0.9199999999999999 Test acc1.0; Train loss: 0.0005323705489831892 Val loss: 0.05367492294311523
+INFO - evaluator.py - 2024-10-26 02:58:29,172 - Epoch: 87 Train acc: 97.9309090909091 Val acc: 1.16 Test acc0.86; Train loss: 0.0005631236374886198 Val loss: 0.050950350952148435
+INFO - evaluator.py - 2024-10-26 02:59:15,189 - Epoch: 88 Train acc: 98.04727272727273 Val acc: 1.6400000000000001 Test acc1.52; Train loss: 0.0005332249431108886 Val loss: 0.03977857437133789
+INFO - evaluator.py - 2024-10-26 03:00:06,148 - Epoch: 89 Train acc: 98.33272727272727 Val acc: 1.96 Test acc1.9; Train loss: 0.00047542982711033387 Val loss: 0.0368554313659668
+INFO - evaluator.py - 2024-10-26 03:00:53,781 - Epoch: 90 Train acc: 97.85454545454544 Val acc: 1.24 Test acc1.01; Train loss: 0.0005734685869548808 Val loss: 0.05105727767944336
+INFO - evaluator.py - 2024-10-26 03:01:38,732 - Epoch: 91 Train acc: 97.45636363636365 Val acc: 1.3 Test acc1.48; Train loss: 0.0006759053454480387 Val loss: 0.03518069152832031
+INFO - evaluator.py - 2024-10-26 03:02:25,762 - Epoch: 92 Train acc: 98.48545454545454 Val acc: 1.6 Test acc1.4200000000000002; Train loss: 0.00042243386273357 Val loss: 0.03175640869140625
+INFO - evaluator.py - 2024-10-26 03:03:13,492 - Epoch: 93 Train acc: 98.22727272727273 Val acc: 0.9400000000000001 Test acc0.9199999999999999; Train loss: 0.00047451071930541236 Val loss: 0.047538141632080075
+INFO - evaluator.py - 2024-10-26 03:03:59,821 - Epoch: 94 Train acc: 98.36181818181818 Val acc: 1.1199999999999999 Test acc1.03; Train loss: 0.0004550537306984717 Val loss: 0.03980860061645508
+INFO - evaluator.py - 2024-10-26 03:04:48,115 - Epoch: 95 Train acc: 98.49636363636364 Val acc: 0.8 Test acc0.9400000000000001; Train loss: 0.0004302308740432967 Val loss: 0.037778533172607424
+INFO - evaluator.py - 2024-10-26 03:05:33,265 - Epoch: 96 Train acc: 98.16 Val acc: 0.88 Test acc0.8500000000000001; Train loss: 0.0005007187883792953 Val loss: 0.04486921920776367
+INFO - evaluator.py - 2024-10-26 03:06:18,665 - Epoch: 97 Train acc: 97.68363636363637 Val acc: 1.08 Test acc1.0999999999999999; Train loss: 0.0006176288883625107 Val loss: 0.030105482482910156
+INFO - evaluator.py - 2024-10-26 03:07:04,050 - Epoch: 98 Train acc: 98.1290909090909 Val acc: 1.06 Test acc0.86; Train loss: 0.0005130585808814927 Val loss: 0.0420948112487793
+INFO - evaluator.py - 2024-10-26 03:07:49,967 - Epoch: 99 Train acc: 98.46545454545455 Val acc: 0.98 Test acc1.1199999999999999; Train loss: 0.0004327759291468696 Val loss: 0.04061830596923828
+INFO - evaluator.py - 2024-10-26 03:08:33,587 - Epoch: 100 Train acc: 98.07090909090908 Val acc: 1.52 Test acc1.47; Train loss: 0.0005328231693330136 Val loss: 0.02898427085876465
+INFO - evaluator.py - 2024-10-26 03:09:19,494 - Epoch: 101 Train acc: 98.13272727272727 Val acc: 0.8200000000000001 Test acc1.25; Train loss: 0.0005143476137891412 Val loss: 0.027128710174560547
+INFO - evaluator.py - 2024-10-26 03:10:07,148 - Epoch: 102 Train acc: 98.39636363636363 Val acc: 1.3 Test acc1.54; Train loss: 0.00044764043505896223 Val loss: 0.02723431282043457
+INFO - evaluator.py - 2024-10-26 03:10:52,622 - Epoch: 103 Train acc: 97.38363636363636 Val acc: 1.5 Test acc1.39; Train loss: 0.0006946541458029638 Val loss: 0.03844362716674805
+INFO - evaluator.py - 2024-10-26 03:11:37,877 - Epoch: 104 Train acc: 98.57090909090908 Val acc: 1.28 Test acc1.4500000000000002; Train loss: 0.0004116066241467541 Val loss: 0.021357050704956054
+INFO - evaluator.py - 2024-10-26 03:12:21,946 - Epoch: 105 Train acc: 99.10363636363635 Val acc: 1.38 Test acc1.04; Train loss: 0.0002824003392576494 Val loss: 0.03336034088134766
+INFO - evaluator.py - 2024-10-26 03:13:07,741 - Epoch: 106 Train acc: 97.93818181818182 Val acc: 1.04 Test acc1.21; Train loss: 0.000549123201908713 Val loss: 0.02909744644165039
+INFO - evaluator.py - 2024-10-26 03:13:53,950 - Epoch: 107 Train acc: 97.23636363636363 Val acc: 1.1199999999999999 Test acc1.44; Train loss: 0.0007132958771999587 Val loss: 0.030194104385375977
+INFO - evaluator.py - 2024-10-26 03:14:40,981 - Epoch: 108 Train acc: 98.21818181818182 Val acc: 1.08 Test acc1.15; Train loss: 0.0005005027081478726 Val loss: 0.027708096313476562
+INFO - evaluator.py - 2024-10-26 03:15:26,759 - Epoch: 109 Train acc: 98.68181818181819 Val acc: 1.26 Test acc1.27; Train loss: 0.0003695280337198214 Val loss: 0.028577485275268554
+INFO - evaluator.py - 2024-10-26 03:16:12,954 - Epoch: 110 Train acc: 98.36545454545454 Val acc: 1.0 Test acc1.0; Train loss: 0.00044835637803612786 Val loss: 0.027174417495727538
+INFO - evaluator.py - 2024-10-26 03:17:00,565 - Epoch: 111 Train acc: 97.44 Val acc: 2.08 Test acc1.9; Train loss: 0.0006675930343398994 Val loss: 0.025679094314575195
+INFO - evaluator.py - 2024-10-26 03:17:46,082 - Epoch: 112 Train acc: 98.14727272727272 Val acc: 1.0999999999999999 Test acc1.43; Train loss: 0.0005212000554766168 Val loss: 0.025549671173095704
+INFO - evaluator.py - 2024-10-26 03:18:33,242 - Epoch: 113 Train acc: 99.02 Val acc: 1.46 Test acc1.69; Train loss: 0.000307539440064945 Val loss: 0.02125059814453125
+INFO - evaluator.py - 2024-10-26 03:19:19,475 - Epoch: 114 Train acc: 97.75818181818182 Val acc: 1.38 Test acc1.06; Train loss: 0.0005757034239782529 Val loss: 0.0282278564453125
+INFO - evaluator.py - 2024-10-26 03:20:04,591 - Epoch: 115 Train acc: 97.56181818181818 Val acc: 1.6 Test acc1.5599999999999998; Train loss: 0.0006631946973841299 Val loss: 0.022518689346313476
+INFO - evaluator.py - 2024-10-26 03:20:51,554 - Epoch: 116 Train acc: 97.78727272727272 Val acc: 0.96 Test acc0.95; Train loss: 0.0005762745334682139 Val loss: 0.027291732406616212
+INFO - evaluator.py - 2024-10-26 03:21:40,255 - Epoch: 117 Train acc: 98.5890909090909 Val acc: 1.34 Test acc1.0999999999999999; Train loss: 0.0003925475116480481 Val loss: 0.021403993606567383
+INFO - evaluator.py - 2024-10-26 03:22:25,848 - Epoch: 118 Train acc: 98.67818181818183 Val acc: 1.46 Test acc1.0999999999999999; Train loss: 0.0003796158878471364 Val loss: 0.02203141288757324
+INFO - evaluator.py - 2024-10-26 03:23:09,723 - Epoch: 119 Train acc: 98.93454545454546 Val acc: 1.04 Test acc0.95; Train loss: 0.00031032147204334084 Val loss: 0.03325586776733398
+INFO - evaluator.py - 2024-10-26 03:23:54,315 - Epoch: 120 Train acc: 99.90181818181819 Val acc: 1.1199999999999999 Test acc1.13; Train loss: 6.23664961238815e-05 Val loss: 0.03474256973266602
+INFO - evaluator.py - 2024-10-26 03:24:39,027 - Epoch: 121 Train acc: 99.99454545454546 Val acc: 1.1199999999999999 Test acc1.1900000000000002; Train loss: 2.463947295486419e-05 Val loss: 0.03491526641845703
+INFO - evaluator.py - 2024-10-26 03:25:24,010 - Epoch: 122 Train acc: 100.0 Val acc: 1.2 Test acc1.2; Train loss: 1.963782712753693e-05 Val loss: 0.034561223602294924
+INFO - evaluator.py - 2024-10-26 03:26:11,745 - Epoch: 123 Train acc: 100.0 Val acc: 1.22 Test acc1.24; Train loss: 1.8366117327770387e-05 Val loss: 0.034967996215820314
+INFO - evaluator.py - 2024-10-26 03:27:02,298 - Epoch: 124 Train acc: 100.0 Val acc: 1.34 Test acc1.24; Train loss: 1.7255770707164297e-05 Val loss: 0.03507944564819336
+INFO - evaluator.py - 2024-10-26 03:27:48,844 - Epoch: 125 Train acc: 100.0 Val acc: 1.1400000000000001 Test acc1.23; Train loss: 1.6665754895868964e-05 Val loss: 0.03659334335327148
+INFO - evaluator.py - 2024-10-26 03:28:35,213 - Epoch: 126 Train acc: 100.0 Val acc: 1.22 Test acc1.25; Train loss: 1.6330076598519968e-05 Val loss: 0.03891688995361328
+INFO - evaluator.py - 2024-10-26 03:29:23,558 - Epoch: 127 Train acc: 100.0 Val acc: 1.28 Test acc1.21; Train loss: 1.585599529154768e-05 Val loss: 0.04044876327514649
+INFO - evaluator.py - 2024-10-26 03:30:09,752 - Epoch: 128 Train acc: 100.0 Val acc: 1.3599999999999999 Test acc1.25; Train loss: 1.618914453270422e-05 Val loss: 0.04235735092163086
+INFO - evaluator.py - 2024-10-26 03:30:53,921 - Epoch: 129 Train acc: 100.0 Val acc: 1.26 Test acc1.29; Train loss: 1.6448501218110323e-05 Val loss: 0.04433580474853516
+INFO - evaluator.py - 2024-10-26 03:31:36,068 - Epoch: 130 Train acc: 100.0 Val acc: 1.32 Test acc1.24; Train loss: 1.641294848893515e-05 Val loss: 0.046998411560058594
+INFO - evaluator.py - 2024-10-26 03:32:19,203 - Epoch: 131 Train acc: 100.0 Val acc: 1.32 Test acc1.1400000000000001; Train loss: 1.640193188160827e-05 Val loss: 0.05117471771240235
+INFO - evaluator.py - 2024-10-26 03:33:01,716 - Epoch: 132 Train acc: 100.0 Val acc: 1.34 Test acc1.1900000000000002; Train loss: 1.681875242872841e-05 Val loss: 0.052911500549316405
+INFO - evaluator.py - 2024-10-26 03:33:50,454 - Epoch: 133 Train acc: 100.0 Val acc: 1.32 Test acc1.21; Train loss: 1.6950132180301642e-05 Val loss: 0.05462663879394531
+INFO - evaluator.py - 2024-10-26 03:34:36,605 - Epoch: 134 Train acc: 100.0 Val acc: 1.32 Test acc1.23; Train loss: 1.759002138013867e-05 Val loss: 0.056764524841308596
+INFO - evaluator.py - 2024-10-26 03:35:22,587 - Epoch: 135 Train acc: 100.0 Val acc: 1.3 Test acc1.2; Train loss: 1.8099469934928825e-05 Val loss: 0.06202569351196289
+INFO - evaluator.py - 2024-10-26 03:36:09,161 - Epoch: 136 Train acc: 100.0 Val acc: 1.16 Test acc1.2; Train loss: 1.833579501518133e-05 Val loss: 0.06477064514160157
+INFO - evaluator.py - 2024-10-26 03:36:55,188 - Epoch: 137 Train acc: 100.0 Val acc: 1.1199999999999999 Test acc1.18; Train loss: 1.8604317982681097e-05 Val loss: 0.06831514282226563
+INFO - evaluator.py - 2024-10-26 03:37:41,824 - Epoch: 138 Train acc: 100.0 Val acc: 1.06 Test acc1.1900000000000002; Train loss: 1.9049782191657206e-05 Val loss: 0.07237774200439454
+INFO - evaluator.py - 2024-10-26 03:38:25,904 - Epoch: 139 Train acc: 100.0 Val acc: 1.0999999999999999 Test acc1.1900000000000002; Train loss: 1.9196641237728976e-05 Val loss: 0.07504159545898438
+INFO - evaluator.py - 2024-10-26 03:39:09,782 - Epoch: 140 Train acc: 100.0 Val acc: 1.0 Test acc1.2; Train loss: 1.948351718866351e-05 Val loss: 0.07900317993164062
+INFO - evaluator.py - 2024-10-26 03:39:54,116 - Epoch: 141 Train acc: 100.0 Val acc: 0.96 Test acc1.16; Train loss: 1.9926266865381463e-05 Val loss: 0.0843493408203125
+INFO - evaluator.py - 2024-10-26 03:40:38,727 - Epoch: 142 Train acc: 100.0 Val acc: 1.0 Test acc1.1900000000000002; Train loss: 1.9964161229489202e-05 Val loss: 0.08739111785888672
+INFO - evaluator.py - 2024-10-26 03:41:24,093 - Epoch: 143 Train acc: 100.0 Val acc: 0.96 Test acc1.16; Train loss: 2.015792168465189e-05 Val loss: 0.09211621704101562
+INFO - evaluator.py - 2024-10-26 03:42:11,560 - Epoch: 144 Train acc: 100.0 Val acc: 0.9400000000000001 Test acc1.1400000000000001; Train loss: 2.0771120075898414e-05 Val loss: 0.08936607360839843
+INFO - evaluator.py - 2024-10-26 03:42:56,929 - Epoch: 145 Train acc: 100.0 Val acc: 0.98 Test acc1.21; Train loss: 2.113050028724088e-05 Val loss: 0.0928270263671875
+INFO - evaluator.py - 2024-10-26 03:43:44,663 - Epoch: 146 Train acc: 100.0 Val acc: 1.0 Test acc1.15; Train loss: 2.166185318492353e-05 Val loss: 0.09787379302978516
+INFO - evaluator.py - 2024-10-26 03:44:28,272 - Epoch: 147 Train acc: 100.0 Val acc: 1.0 Test acc1.1900000000000002; Train loss: 2.1245251490141857e-05 Val loss: 0.10014410247802734
+INFO - evaluator.py - 2024-10-26 03:45:16,970 - Epoch: 148 Train acc: 100.0 Val acc: 1.0 Test acc1.18; Train loss: 2.1406818166459825e-05 Val loss: 0.10224484100341796
+INFO - evaluator.py - 2024-10-26 03:46:05,381 - Epoch: 149 Train acc: 100.0 Val acc: 0.96 Test acc1.1400000000000001; Train loss: 2.2463901093314316e-05 Val loss: 0.11078888244628907
+INFO - evaluator.py - 2024-10-26 03:46:52,215 - Epoch: 150 Train acc: 100.0 Val acc: 0.98 Test acc1.17; Train loss: 2.2095910360274666e-05 Val loss: 0.1088430908203125
+INFO - evaluator.py - 2024-10-26 03:47:38,446 - Epoch: 151 Train acc: 100.0 Val acc: 1.0 Test acc1.18; Train loss: 2.1850857303731822e-05 Val loss: 0.11559195861816406
+INFO - evaluator.py - 2024-10-26 03:48:25,187 - Epoch: 152 Train acc: 100.0 Val acc: 0.96 Test acc1.13; Train loss: 2.1718914792026307e-05 Val loss: 0.12064563598632813
+INFO - evaluator.py - 2024-10-26 03:49:09,753 - Epoch: 153 Train acc: 100.0 Val acc: 0.96 Test acc1.15; Train loss: 2.234399649102918e-05 Val loss: 0.12112979736328125
+INFO - evaluator.py - 2024-10-26 03:49:54,218 - Epoch: 154 Train acc: 100.0 Val acc: 0.96 Test acc1.17; Train loss: 2.281722526954995e-05 Val loss: 0.12233509979248047
+INFO - evaluator.py - 2024-10-26 03:50:38,988 - Epoch: 155 Train acc: 100.0 Val acc: 0.96 Test acc1.13; Train loss: 2.2671426022001964e-05 Val loss: 0.12910484161376953
+INFO - evaluator.py - 2024-10-26 03:51:24,791 - Epoch: 156 Train acc: 100.0 Val acc: 0.96 Test acc1.15; Train loss: 2.297131798907437e-05 Val loss: 0.1304818862915039
+INFO - evaluator.py - 2024-10-26 03:52:10,854 - Epoch: 157 Train acc: 100.0 Val acc: 1.0 Test acc1.18; Train loss: 2.2758008061315526e-05 Val loss: 0.13642513732910155
+INFO - evaluator.py - 2024-10-26 03:52:57,075 - Epoch: 158 Train acc: 100.0 Val acc: 0.9400000000000001 Test acc1.0699999999999998; Train loss: 2.2963798204860227e-05 Val loss: 0.14566981506347657
+INFO - evaluator.py - 2024-10-26 03:53:41,774 - Epoch: 159 Train acc: 100.0 Val acc: 0.9400000000000001 Test acc1.11; Train loss: 2.2787205000746657e-05 Val loss: 0.14265720520019531
+INFO - evaluator.py - 2024-10-26 03:54:27,914 - Epoch: 160 Train acc: 100.0 Val acc: 0.98 Test acc1.15; Train loss: 2.353041727434505e-05 Val loss: 0.14480274047851563
+INFO - evaluator.py - 2024-10-26 03:55:11,735 - Epoch: 161 Train acc: 100.0 Val acc: 0.98 Test acc1.18; Train loss: 2.349480446851389e-05 Val loss: 0.14770849304199218
+INFO - evaluator.py - 2024-10-26 03:55:55,826 - Epoch: 162 Train acc: 100.0 Val acc: 0.9400000000000001 Test acc1.0999999999999999; Train loss: 2.285812093918635e-05 Val loss: 0.15424117431640624
+INFO - evaluator.py - 2024-10-26 03:56:38,952 - Epoch: 163 Train acc: 100.0 Val acc: 0.9400000000000001 Test acc1.11; Train loss: 2.311284986155277e-05 Val loss: 0.15595648803710938
+INFO - evaluator.py - 2024-10-26 03:57:25,703 - Epoch: 164 Train acc: 100.0 Val acc: 0.98 Test acc1.16; Train loss: 2.307832537811588e-05 Val loss: 0.156669189453125
+INFO - evaluator.py - 2024-10-26 03:58:12,364 - Epoch: 165 Train acc: 100.0 Val acc: 1.0 Test acc1.18; Train loss: 2.280212678861889e-05 Val loss: 0.15603155517578124
+INFO - evaluator.py - 2024-10-26 03:58:59,750 - Epoch: 166 Train acc: 100.0 Val acc: 0.96 Test acc1.17; Train loss: 2.2975191437977957e-05 Val loss: 0.16569906311035157
+INFO - evaluator.py - 2024-10-26 03:59:48,425 - Epoch: 167 Train acc: 100.0 Val acc: 0.96 Test acc1.0999999999999999; Train loss: 2.3338990853252735e-05 Val loss: 0.1637861541748047
+INFO - evaluator.py - 2024-10-26 04:00:33,224 - Epoch: 168 Train acc: 100.0 Val acc: 0.9400000000000001 Test acc1.09; Train loss: 2.2648307344537567e-05 Val loss: 0.17311487426757813
+INFO - evaluator.py - 2024-10-26 04:01:16,725 - Epoch: 169 Train acc: 100.0 Val acc: 0.98 Test acc1.1400000000000001; Train loss: 2.28593814144419e-05 Val loss: 0.16997346801757812
+INFO - evaluator.py - 2024-10-26 04:02:00,649 - Epoch: 170 Train acc: 100.0 Val acc: 0.9400000000000001 Test acc1.08; Train loss: 2.2915963868779892e-05 Val loss: 0.17278863525390625
+INFO - evaluator.py - 2024-10-26 04:02:44,699 - Epoch: 171 Train acc: 100.0 Val acc: 0.9400000000000001 Test acc1.08; Train loss: 2.3078377525830132e-05 Val loss: 0.18462256469726562
+INFO - evaluator.py - 2024-10-26 04:03:31,229 - Epoch: 172 Train acc: 100.0 Val acc: 0.9400000000000001 Test acc1.0999999999999999; Train loss: 2.3041810156692836e-05 Val loss: 0.1774590087890625
+INFO - evaluator.py - 2024-10-26 04:04:17,005 - Epoch: 173 Train acc: 100.0 Val acc: 0.9400000000000001 Test acc1.11; Train loss: 2.3122773933309044e-05 Val loss: 0.1827936981201172
+INFO - evaluator.py - 2024-10-26 04:05:04,280 - Epoch: 174 Train acc: 100.0 Val acc: 0.9400000000000001 Test acc1.09; Train loss: 2.3166740260256286e-05 Val loss: 0.1826856658935547
+INFO - evaluator.py - 2024-10-26 04:05:48,698 - Epoch: 175 Train acc: 100.0 Val acc: 0.9400000000000001 Test acc1.09; Train loss: 2.286430552644147e-05 Val loss: 0.19239959716796876
+INFO - evaluator.py - 2024-10-26 04:06:34,129 - Epoch: 176 Train acc: 100.0 Val acc: 0.9400000000000001 Test acc1.0999999999999999; Train loss: 2.241398203398355e-05 Val loss: 0.18830140380859375
+INFO - evaluator.py - 2024-10-26 04:07:20,165 - Epoch: 177 Train acc: 100.0 Val acc: 0.9400000000000001 Test acc1.0699999999999998; Train loss: 2.2225601941516453e-05 Val loss: 0.19571219787597657
+INFO - evaluator.py - 2024-10-26 04:08:05,206 - Epoch: 178 Train acc: 100.0 Val acc: 0.9400000000000001 Test acc1.09; Train loss: 2.275681790938093e-05 Val loss: 0.18886591186523438
+INFO - evaluator.py - 2024-10-26 04:08:52,028 - Epoch: 179 Train acc: 100.0 Val acc: 0.9400000000000001 Test acc1.04; Train loss: 2.233509151265025e-05 Val loss: 0.19656297607421874
+INFO - evaluator.py - 2024-10-26 04:09:37,979 - Epoch: 180 Train acc: 100.0 Val acc: 0.9400000000000001 Test acc1.09; Train loss: 2.1995460881258954e-05 Val loss: 0.17457930908203126
+INFO - evaluator.py - 2024-10-26 04:10:24,517 - Epoch: 181 Train acc: 100.0 Val acc: 0.9400000000000001 Test acc1.08; Train loss: 2.1479809540323915e-05 Val loss: 0.14084217834472657
+INFO - evaluator.py - 2024-10-26 04:11:10,979 - Epoch: 182 Train acc: 100.0 Val acc: 0.9400000000000001 Test acc1.06; Train loss: 2.1482331775636836e-05 Val loss: 0.1284965316772461
+INFO - evaluator.py - 2024-10-26 04:11:57,427 - Epoch: 183 Train acc: 100.0 Val acc: 0.9199999999999999 Test acc1.0699999999999998; Train loss: 2.133735646705397e-05 Val loss: 0.11225003967285156
+INFO - evaluator.py - 2024-10-26 04:12:42,782 - Epoch: 184 Train acc: 100.0 Val acc: 0.9400000000000001 Test acc1.11; Train loss: 2.155254604929889e-05 Val loss: 0.09827306213378906
+INFO - evaluator.py - 2024-10-26 04:13:28,615 - Epoch: 185 Train acc: 100.0 Val acc: 0.8999999999999999 Test acc1.05; Train loss: 2.1170071565376765e-05 Val loss: 0.09450130920410156
+INFO - evaluator.py - 2024-10-26 04:14:12,885 - Epoch: 186 Train acc: 100.0 Val acc: 0.8999999999999999 Test acc1.0699999999999998; Train loss: 2.1523444807495582e-05 Val loss: 0.08320385589599609
+INFO - evaluator.py - 2024-10-26 04:14:58,130 - Epoch: 187 Train acc: 100.0 Val acc: 0.8999999999999999 Test acc1.06; Train loss: 2.142010772050443e-05 Val loss: 0.07408435974121094
+INFO - evaluator.py - 2024-10-26 04:15:43,163 - Epoch: 188 Train acc: 100.0 Val acc: 0.9199999999999999 Test acc1.08; Train loss: 2.113118291493844e-05 Val loss: 0.06540577545166015
+INFO - evaluator.py - 2024-10-26 04:16:27,810 - Epoch: 189 Train acc: 100.0 Val acc: 0.8999999999999999 Test acc1.09; Train loss: 2.1529756719246506e-05 Val loss: 0.061421526336669925
+INFO - evaluator.py - 2024-10-26 04:17:14,535 - Epoch: 190 Train acc: 100.0 Val acc: 0.98 Test acc1.1199999999999999; Train loss: 2.0990733095360073e-05 Val loss: 0.056482769012451174
+INFO - evaluator.py - 2024-10-26 04:17:58,444 - Epoch: 191 Train acc: 100.0 Val acc: 0.9199999999999999 Test acc1.05; Train loss: 2.152279735204171e-05 Val loss: 0.05243412399291992
+INFO - evaluator.py - 2024-10-26 04:18:44,722 - Epoch: 192 Train acc: 100.0 Val acc: 0.98 Test acc1.08; Train loss: 2.1315643828446894e-05 Val loss: 0.04803819808959961
+INFO - evaluator.py - 2024-10-26 04:19:29,768 - Epoch: 193 Train acc: 100.0 Val acc: 1.04 Test acc1.0999999999999999; Train loss: 2.1349237533286214e-05 Val loss: 0.04521836776733398
+INFO - evaluator.py - 2024-10-26 04:20:16,083 - Epoch: 194 Train acc: 100.0 Val acc: 1.02 Test acc1.05; Train loss: 2.1323798825456337e-05 Val loss: 0.04262155609130859
+INFO - evaluator.py - 2024-10-26 04:21:00,658 - Epoch: 195 Train acc: 100.0 Val acc: 0.98 Test acc1.08; Train loss: 2.1095548047345472e-05 Val loss: 0.04073702011108398
+INFO - evaluator.py - 2024-10-26 04:21:46,618 - Epoch: 196 Train acc: 100.0 Val acc: 1.04 Test acc1.03; Train loss: 2.1365015278570353e-05 Val loss: 0.03901129379272461
+INFO - evaluator.py - 2024-10-26 04:22:30,710 - Epoch: 197 Train acc: 100.0 Val acc: 1.08 Test acc0.98; Train loss: 2.1310568967072124e-05 Val loss: 0.036598711395263675
+INFO - evaluator.py - 2024-10-26 04:23:15,320 - Epoch: 198 Train acc: 100.0 Val acc: 1.0999999999999999 Test acc0.96; Train loss: 2.1006980201822113e-05 Val loss: 0.03435097274780274
+INFO - evaluator.py - 2024-10-26 04:23:57,355 - Epoch: 199 Train acc: 100.0 Val acc: 1.06 Test acc0.96; Train loss: 2.0875469635410065e-05 Val loss: 0.03306039733886719
+INFO - evaluator.py - 2024-10-26 04:23:57,374 - The best acc of synthetic images on sensitive val and the corresponding acc on test dataset from resnet is 2.56 and 2.22
+INFO - evaluator.py - 2024-10-26 04:23:57,374 - The best acc of synthetic images on noisy sensitive val and the corresponding acc on test dataset from resnet is 2.56 and 2.22
+INFO - evaluator.py - 2024-10-26 04:23:57,374 - The best acc test dataset from resnet is 2.22
+INFO - evaluator.py - 2024-10-26 04:25:26,413 - Epoch: 0 Train acc: 3.7163636363636363 Val acc: 2.7199999999999998 Test acc2.17; Train loss: 0.0342097666090185 Val loss: 0.006250953865051269
+INFO - evaluator.py - 2024-10-26 04:26:55,020 - Epoch: 1 Train acc: 6.421818181818181 Val acc: 2.3800000000000003 Test acc2.39; Train loss: 0.0322685820015994 Val loss: 0.008995512580871582
+INFO - evaluator.py - 2024-10-26 04:28:23,324 - Epoch: 2 Train acc: 8.472727272727273 Val acc: 2.32 Test acc2.36; Train loss: 0.03123859034018083 Val loss: 0.008613738441467286
+INFO - evaluator.py - 2024-10-26 04:29:51,803 - Epoch: 3 Train acc: 13.176363636363636 Val acc: 2.8000000000000003 Test acc2.29; Train loss: 0.0289669584274292 Val loss: 0.008656187057495117
+INFO - evaluator.py - 2024-10-26 04:31:20,458 - Epoch: 4 Train acc: 42.02363636363636 Val acc: 2.56 Test acc2.3800000000000003; Train loss: 0.01688611813025041 Val loss: 0.009417916488647461
+INFO - evaluator.py - 2024-10-26 04:32:49,024 - Epoch: 5 Train acc: 68.76545454545455 Val acc: 2.0 Test acc2.27; Train loss: 0.008447054637562144 Val loss: 0.0144447509765625
+INFO - evaluator.py - 2024-10-26 04:34:17,320 - Epoch: 6 Train acc: 81.0109090909091 Val acc: 1.9800000000000002 Test acc1.81; Train loss: 0.005097224660353227 Val loss: 0.018716676712036133
+INFO - evaluator.py - 2024-10-26 04:35:45,632 - Epoch: 7 Train acc: 86.48363636363636 Val acc: 1.72 Test acc1.4500000000000002; Train loss: 0.003649201819029721 Val loss: 0.019502586364746093
+INFO - evaluator.py - 2024-10-26 04:37:14,014 - Epoch: 8 Train acc: 88.89454545454547 Val acc: 1.7999999999999998 Test acc1.6099999999999999; Train loss: 0.002990180374004624 Val loss: 0.018176304626464843
+INFO - evaluator.py - 2024-10-26 04:38:42,270 - Epoch: 9 Train acc: 90.52545454545454 Val acc: 1.8800000000000001 Test acc1.8599999999999999; Train loss: 0.0025636261408979242 Val loss: 0.01692248191833496
+INFO - evaluator.py - 2024-10-26 04:40:10,672 - Epoch: 10 Train acc: 91.56363636363636 Val acc: 1.8599999999999999 Test acc2.15; Train loss: 0.002300617756626823 Val loss: 0.01686544532775879
+INFO - evaluator.py - 2024-10-26 04:41:38,900 - Epoch: 11 Train acc: 92.82363636363637 Val acc: 2.36 Test acc2.56; Train loss: 0.002012315312705257 Val loss: 0.014273247909545898
+INFO - evaluator.py - 2024-10-26 04:43:07,222 - Epoch: 12 Train acc: 93.28181818181818 Val acc: 2.02 Test acc2.01; Train loss: 0.0018744824314659292 Val loss: 0.014313158416748047
+INFO - evaluator.py - 2024-10-26 04:44:35,402 - Epoch: 13 Train acc: 93.41090909090909 Val acc: 1.7399999999999998 Test acc1.91; Train loss: 0.0018397045780311932 Val loss: 0.014016406440734864
+INFO - evaluator.py - 2024-10-26 04:46:03,761 - Epoch: 14 Train acc: 94.11090909090909 Val acc: 1.8800000000000001 Test acc1.69; Train loss: 0.0016724608371203595 Val loss: 0.01722252388000488
+INFO - evaluator.py - 2024-10-26 04:47:32,123 - Epoch: 15 Train acc: 93.88363636363637 Val acc: 1.66 Test acc1.9300000000000002; Train loss: 0.0017116051226854325 Val loss: 0.015037686157226563
+INFO - evaluator.py - 2024-10-26 04:49:00,443 - Epoch: 16 Train acc: 94.39454545454545 Val acc: 2.36 Test acc1.8900000000000001; Train loss: 0.0016091418106447567 Val loss: 0.013454133033752442
+INFO - evaluator.py - 2024-10-26 04:50:29,023 - Epoch: 17 Train acc: 94.48545454545454 Val acc: 2.18 Test acc1.96; Train loss: 0.001577234709262848 Val loss: 0.015363685417175293
+INFO - evaluator.py - 2024-10-26 04:51:57,436 - Epoch: 18 Train acc: 94.76727272727273 Val acc: 1.46 Test acc1.4200000000000002; Train loss: 0.001522672246328809 Val loss: 0.01652770767211914
+INFO - evaluator.py - 2024-10-26 04:53:25,890 - Epoch: 19 Train acc: 94.24 Val acc: 1.46 Test acc1.09; Train loss: 0.0016215499546040188 Val loss: 0.013762329483032227
+INFO - evaluator.py - 2024-10-26 04:54:54,385 - Epoch: 20 Train acc: 94.97090909090909 Val acc: 1.8800000000000001 Test acc1.7399999999999998; Train loss: 0.0014516785934567452 Val loss: 0.014513308715820312
+INFO - evaluator.py - 2024-10-26 04:56:23,331 - Epoch: 21 Train acc: 94.70727272727272 Val acc: 1.5 Test acc1.49; Train loss: 0.0015199327915906907 Val loss: 0.016688166046142577
+INFO - evaluator.py - 2024-10-26 04:57:51,650 - Epoch: 22 Train acc: 94.72909090909091 Val acc: 1.52 Test acc1.63; Train loss: 0.001512835239280354 Val loss: 0.014190552711486816
+INFO - evaluator.py - 2024-10-26 04:59:19,990 - Epoch: 23 Train acc: 94.79454545454546 Val acc: 1.7000000000000002 Test acc1.9; Train loss: 0.0015093313194134018 Val loss: 0.013848727989196776
+INFO - evaluator.py - 2024-10-26 05:00:48,414 - Epoch: 24 Train acc: 94.93454545454544 Val acc: 1.4000000000000001 Test acc1.53; Train loss: 0.0014165474872697484 Val loss: 0.014202471923828125
+INFO - evaluator.py - 2024-10-26 05:02:16,901 - Epoch: 25 Train acc: 94.81090909090909 Val acc: 1.48 Test acc1.34; Train loss: 0.0014664297722957352 Val loss: 0.012872862243652344
+INFO - evaluator.py - 2024-10-26 05:03:45,505 - Epoch: 26 Train acc: 95.16 Val acc: 1.92 Test acc1.73; Train loss: 0.0013990411433306607 Val loss: 0.012622687721252442
+INFO - evaluator.py - 2024-10-26 05:05:14,216 - Epoch: 27 Train acc: 95.06545454545454 Val acc: 1.76 Test acc1.5; Train loss: 0.0014248904881829566 Val loss: 0.013793394088745118
+INFO - evaluator.py - 2024-10-26 05:06:42,833 - Epoch: 28 Train acc: 95.37636363636364 Val acc: 1.7000000000000002 Test acc1.32; Train loss: 0.0013358351715586402 Val loss: 0.01858111152648926
+INFO - evaluator.py - 2024-10-26 05:08:11,314 - Epoch: 29 Train acc: 94.72181818181818 Val acc: 1.22 Test acc1.38; Train loss: 0.0014911538997157054 Val loss: 0.022850880813598633
+INFO - evaluator.py - 2024-10-26 05:09:39,935 - Epoch: 30 Train acc: 95.64 Val acc: 1.7000000000000002 Test acc1.58; Train loss: 0.0013070479407906533 Val loss: 0.012960066986083985
+INFO - evaluator.py - 2024-10-26 05:11:08,180 - Epoch: 31 Train acc: 95.25818181818182 Val acc: 1.6400000000000001 Test acc1.26; Train loss: 0.0013591218705881725 Val loss: 0.014122181510925293
+INFO - evaluator.py - 2024-10-26 05:12:36,491 - Epoch: 32 Train acc: 95.24181818181819 Val acc: 1.5599999999999998 Test acc1.81; Train loss: 0.0013765083068473772 Val loss: 0.01534745273590088
+INFO - evaluator.py - 2024-10-26 05:14:04,747 - Epoch: 33 Train acc: 94.98 Val acc: 2.1 Test acc1.9300000000000002; Train loss: 0.0014375891894779422 Val loss: 0.012163386726379394
+INFO - evaluator.py - 2024-10-26 05:15:32,871 - Epoch: 34 Train acc: 95.29454545454546 Val acc: 1.28 Test acc1.3599999999999999; Train loss: 0.0013650490235198628 Val loss: 0.015345995712280274
+INFO - evaluator.py - 2024-10-26 05:17:01,226 - Epoch: 35 Train acc: 95.22545454545454 Val acc: 1.4200000000000002 Test acc1.4200000000000002; Train loss: 0.0013802534893832424 Val loss: 0.013704808235168457
+INFO - evaluator.py - 2024-10-26 05:18:30,032 - Epoch: 36 Train acc: 95.39272727272727 Val acc: 2.02 Test acc2.0; Train loss: 0.0013429667432877151 Val loss: 0.01443824348449707
+INFO - evaluator.py - 2024-10-26 05:19:58,788 - Epoch: 37 Train acc: 95.15636363636364 Val acc: 1.72 Test acc1.6400000000000001; Train loss: 0.00139474552212791 Val loss: 0.012380222511291504
+INFO - evaluator.py - 2024-10-26 05:21:27,028 - Epoch: 38 Train acc: 95.62545454545455 Val acc: 1.8800000000000001 Test acc1.6199999999999999; Train loss: 0.0012842730006033724 Val loss: 0.015942941093444823
+INFO - evaluator.py - 2024-10-26 05:22:55,455 - Epoch: 39 Train acc: 95.12181818181818 Val acc: 1.28 Test acc1.26; Train loss: 0.0014140543613921513 Val loss: 0.012130700874328612
+INFO - evaluator.py - 2024-10-26 05:24:23,562 - Epoch: 40 Train acc: 95.44545454545454 Val acc: 1.58 Test acc1.25; Train loss: 0.0013224902287125588 Val loss: 0.012782248115539551
+INFO - evaluator.py - 2024-10-26 05:25:51,865 - Epoch: 41 Train acc: 95.20727272727272 Val acc: 2.1399999999999997 Test acc2.23; Train loss: 0.0013726246561516415 Val loss: 0.012802657318115234
+INFO - evaluator.py - 2024-10-26 05:27:20,045 - Epoch: 42 Train acc: 95.47818181818182 Val acc: 2.58 Test acc2.67; Train loss: 0.0012976661869070747 Val loss: 0.012879035186767578
+INFO - evaluator.py - 2024-10-26 05:28:47,941 - Epoch: 43 Train acc: 95.32909090909091 Val acc: 1.9800000000000002 Test acc1.6199999999999999; Train loss: 0.0013405978397889571 Val loss: 0.011923258781433105
+INFO - evaluator.py - 2024-10-26 05:30:15,703 - Epoch: 44 Train acc: 95.26181818181819 Val acc: 1.8599999999999999 Test acc1.94; Train loss: 0.0013635395751758056 Val loss: 0.013344238090515137
+INFO - evaluator.py - 2024-10-26 05:31:44,398 - Epoch: 45 Train acc: 95.16545454545454 Val acc: 1.92 Test acc1.8499999999999999; Train loss: 0.0013911347004500303 Val loss: 0.013753895568847657
+INFO - evaluator.py - 2024-10-26 05:33:12,319 - Epoch: 46 Train acc: 95.50545454545455 Val acc: 1.82 Test acc2.01; Train loss: 0.0013173008481887254 Val loss: 0.013821771049499512
+INFO - evaluator.py - 2024-10-26 05:34:40,668 - Epoch: 47 Train acc: 95.47636363636364 Val acc: 1.54 Test acc1.34; Train loss: 0.0013015701553360983 Val loss: 0.017448382186889648
+INFO - evaluator.py - 2024-10-26 05:36:08,489 - Epoch: 48 Train acc: 95.23454545454545 Val acc: 1.58 Test acc1.28; Train loss: 0.001379264303635467 Val loss: 0.020217427444458008
+INFO - evaluator.py - 2024-10-26 05:37:36,661 - Epoch: 49 Train acc: 95.60727272727273 Val acc: 1.4000000000000001 Test acc1.66; Train loss: 0.0012936940742487256 Val loss: 0.014436205291748046
+INFO - evaluator.py - 2024-10-26 05:39:04,946 - Epoch: 50 Train acc: 95.50545454545455 Val acc: 1.76 Test acc1.48; Train loss: 0.0013094904491169886 Val loss: 0.012573521232604981
+INFO - evaluator.py - 2024-10-26 05:40:33,241 - Epoch: 51 Train acc: 95.60909090909091 Val acc: 1.28 Test acc1.3; Train loss: 0.0012942797163670713 Val loss: 0.01608934898376465
+INFO - evaluator.py - 2024-10-26 05:42:01,254 - Epoch: 52 Train acc: 94.91636363636363 Val acc: 1.26 Test acc1.22; Train loss: 0.0014438749031587081 Val loss: 0.014847907257080078
+INFO - evaluator.py - 2024-10-26 05:43:29,593 - Epoch: 53 Train acc: 95.72363636363636 Val acc: 1.8599999999999999 Test acc1.8499999999999999; Train loss: 0.001243795680999756 Val loss: 0.01770910186767578
+INFO - evaluator.py - 2024-10-26 05:44:58,061 - Epoch: 54 Train acc: 95.63454545454545 Val acc: 1.4200000000000002 Test acc1.6199999999999999; Train loss: 0.0013005147597329183 Val loss: 0.014418421554565429
+INFO - evaluator.py - 2024-10-26 05:46:26,240 - Epoch: 55 Train acc: 95.50909090909092 Val acc: 1.44 Test acc1.23; Train loss: 0.0013169871185313572 Val loss: 0.012881710815429687
+INFO - evaluator.py - 2024-10-26 05:47:54,544 - Epoch: 56 Train acc: 95.10363636363637 Val acc: 1.7000000000000002 Test acc1.66; Train loss: 0.0014340045113455165 Val loss: 0.01709843864440918
+INFO - evaluator.py - 2024-10-26 05:49:22,679 - Epoch: 57 Train acc: 95.79454545454546 Val acc: 1.7399999999999998 Test acc2.03; Train loss: 0.0012264623162421312 Val loss: 0.01645931282043457
+INFO - evaluator.py - 2024-10-26 05:50:51,073 - Epoch: 58 Train acc: 94.93454545454544 Val acc: 2.7 Test acc2.52; Train loss: 0.0014501744569025256 Val loss: 0.010999393081665039
+INFO - evaluator.py - 2024-10-26 05:52:19,186 - Epoch: 59 Train acc: 95.78363636363636 Val acc: 1.18 Test acc1.03; Train loss: 0.0012294658563353799 Val loss: 0.020102984237670898
+INFO - evaluator.py - 2024-10-26 05:53:47,848 - Epoch: 60 Train acc: 99.36 Val acc: 2.02 Test acc2.12; Train loss: 0.0002857621813616292 Val loss: 0.022078401947021483
+INFO - evaluator.py - 2024-10-26 05:55:16,052 - Epoch: 61 Train acc: 99.86545454545454 Val acc: 2.18 Test acc2.35; Train loss: 0.0001170620278455317 Val loss: 0.026187763595581056
+INFO - evaluator.py - 2024-10-26 05:56:44,051 - Epoch: 62 Train acc: 99.93454545454546 Val acc: 2.36 Test acc2.29; Train loss: 9.940977794202891e-05 Val loss: 0.03752970657348633
+INFO - evaluator.py - 2024-10-26 05:58:11,859 - Epoch: 63 Train acc: 99.96909090909091 Val acc: 2.16 Test acc2.15; Train loss: 8.64925112744624e-05 Val loss: 0.04969029312133789
+INFO - evaluator.py - 2024-10-26 05:59:39,666 - Epoch: 64 Train acc: 99.98 Val acc: 1.92 Test acc1.8399999999999999; Train loss: 8.302067300643433e-05 Val loss: 0.06927252349853516
+INFO - evaluator.py - 2024-10-26 06:01:08,157 - Epoch: 65 Train acc: 99.97818181818182 Val acc: 1.52 Test acc1.6199999999999999; Train loss: 8.201235672459007e-05 Val loss: 0.0887023193359375
+INFO - evaluator.py - 2024-10-26 06:02:35,959 - Epoch: 66 Train acc: 99.97818181818182 Val acc: 1.4000000000000001 Test acc1.6099999999999999; Train loss: 8.570043476806446e-05 Val loss: 0.11309268493652344
+INFO - evaluator.py - 2024-10-26 06:04:04,441 - Epoch: 67 Train acc: 99.97454545454545 Val acc: 1.4000000000000001 Test acc1.81; Train loss: 8.476020471954887e-05 Val loss: 0.13947151184082032
+INFO - evaluator.py - 2024-10-26 06:05:32,756 - Epoch: 68 Train acc: 99.97090909090909 Val acc: 1.58 Test acc1.96; Train loss: 8.907751588320191e-05 Val loss: 0.18298486022949217
+INFO - evaluator.py - 2024-10-26 06:07:00,573 - Epoch: 69 Train acc: 99.97636363636364 Val acc: 1.4000000000000001 Test acc1.71; Train loss: 8.811824563044038e-05 Val loss: 0.223997314453125
+INFO - evaluator.py - 2024-10-26 06:08:28,601 - Epoch: 70 Train acc: 99.96181818181819 Val acc: 1.6199999999999999 Test acc1.87; Train loss: 9.519863219254397e-05 Val loss: 0.27130450439453124
+INFO - evaluator.py - 2024-10-26 06:09:56,347 - Epoch: 71 Train acc: 99.92909090909092 Val acc: 1.3599999999999999 Test acc1.52; Train loss: 0.0001027300210330974 Val loss: 0.335753466796875
+INFO - evaluator.py - 2024-10-26 06:11:24,151 - Epoch: 72 Train acc: 99.89636363636365 Val acc: 1.44 Test acc1.54; Train loss: 0.00012061207662759857 Val loss: 0.42316181030273436
+INFO - evaluator.py - 2024-10-26 06:12:51,957 - Epoch: 73 Train acc: 99.87272727272727 Val acc: 1.1400000000000001 Test acc1.31; Train loss: 0.00013595866016535596 Val loss: 0.45759232177734377
+INFO - evaluator.py - 2024-10-26 06:14:19,697 - Epoch: 74 Train acc: 99.69636363636364 Val acc: 1.24 Test acc1.48; Train loss: 0.0001993563091721047 Val loss: 0.4146224853515625
+INFO - evaluator.py - 2024-10-26 06:15:47,946 - Epoch: 75 Train acc: 99.56363636363636 Val acc: 1.0999999999999999 Test acc1.0; Train loss: 0.0002567698619413105 Val loss: 0.36065121459960936
+INFO - evaluator.py - 2024-10-26 06:17:15,789 - Epoch: 76 Train acc: 99.53636363636363 Val acc: 1.0 Test acc0.9199999999999999; Train loss: 0.00027265225752172147 Val loss: 0.2435225830078125
+INFO - evaluator.py - 2024-10-26 06:18:43,619 - Epoch: 77 Train acc: 99.3709090909091 Val acc: 0.96 Test acc0.8999999999999999; Train loss: 0.00031665433740073987 Val loss: 0.17244837951660155
+INFO - evaluator.py - 2024-10-26 06:20:11,205 - Epoch: 78 Train acc: 99.11454545454545 Val acc: 1.1400000000000001 Test acc1.05; Train loss: 0.00037752697284926067 Val loss: 0.08691216278076172
+INFO - evaluator.py - 2024-10-26 06:21:38,914 - Epoch: 79 Train acc: 98.79454545454546 Val acc: 1.3 Test acc1.25; Train loss: 0.0004664663152938539 Val loss: 0.04974160537719727
+INFO - evaluator.py - 2024-10-26 06:23:06,775 - Epoch: 80 Train acc: 98.91818181818182 Val acc: 1.24 Test acc1.22; Train loss: 0.00041615765626457606 Val loss: 0.03095379943847656
+INFO - evaluator.py - 2024-10-26 06:24:34,565 - Epoch: 81 Train acc: 98.98363636363636 Val acc: 0.9199999999999999 Test acc1.16; Train loss: 0.00039226894697005096 Val loss: 0.02123005142211914
+INFO - evaluator.py - 2024-10-26 06:26:02,127 - Epoch: 82 Train acc: 99.0909090909091 Val acc: 1.52 Test acc1.8599999999999999; Train loss: 0.0003633012730966915 Val loss: 0.013790719223022462
+INFO - evaluator.py - 2024-10-26 06:27:30,284 - Epoch: 83 Train acc: 98.9890909090909 Val acc: 1.58 Test acc1.9; Train loss: 0.0003835176046599041 Val loss: 0.011713498878479004
+INFO - evaluator.py - 2024-10-26 06:28:57,998 - Epoch: 84 Train acc: 99.11090909090909 Val acc: 1.44 Test acc1.5599999999999998; Train loss: 0.00034653415263376453 Val loss: 0.011201602363586426
+INFO - evaluator.py - 2024-10-26 06:30:25,953 - Epoch: 85 Train acc: 99.00909090909092 Val acc: 1.6199999999999999 Test acc1.6199999999999999; Train loss: 0.00037295385481451044 Val loss: 0.010627849388122558
+INFO - evaluator.py - 2024-10-26 06:31:53,704 - Epoch: 86 Train acc: 98.86545454545454 Val acc: 1.32 Test acc1.53; Train loss: 0.0004215636801143939 Val loss: 0.011128030967712402
+INFO - evaluator.py - 2024-10-26 06:33:21,628 - Epoch: 87 Train acc: 99.07090909090908 Val acc: 1.1199999999999999 Test acc1.03; Train loss: 0.00035692966468632223 Val loss: 0.011062592887878418
+INFO - evaluator.py - 2024-10-26 06:34:49,683 - Epoch: 88 Train acc: 99.18363636363637 Val acc: 1.24 Test acc1.5; Train loss: 0.0003082292988388376 Val loss: 0.010050154876708984
+INFO - evaluator.py - 2024-10-26 06:36:17,393 - Epoch: 89 Train acc: 99.15818181818182 Val acc: 1.46 Test acc1.6; Train loss: 0.0003236616803502495 Val loss: 0.010320128059387207
+INFO - evaluator.py - 2024-10-26 06:37:45,190 - Epoch: 90 Train acc: 98.86727272727272 Val acc: 1.66 Test acc1.4500000000000002; Train loss: 0.0004100640918551521 Val loss: 0.010005558204650879
+INFO - evaluator.py - 2024-10-26 06:39:12,841 - Epoch: 91 Train acc: 99.06181818181818 Val acc: 1.7000000000000002 Test acc1.5699999999999998; Train loss: 0.0003436419588429007 Val loss: 0.01015644645690918
+INFO - evaluator.py - 2024-10-26 06:40:40,908 - Epoch: 92 Train acc: 99.17272727272727 Val acc: 1.8599999999999999 Test acc1.83; Train loss: 0.00033511252420192415 Val loss: 0.013137949562072754
+INFO - evaluator.py - 2024-10-26 06:42:08,632 - Epoch: 93 Train acc: 99.11818181818181 Val acc: 1.52 Test acc1.52; Train loss: 0.0003445075544613329 Val loss: 0.010778630638122559
+INFO - evaluator.py - 2024-10-26 06:43:36,394 - Epoch: 94 Train acc: 99.04363636363637 Val acc: 1.48 Test acc1.53; Train loss: 0.0003590943257070401 Val loss: 0.00932255630493164
+INFO - evaluator.py - 2024-10-26 06:45:04,393 - Epoch: 95 Train acc: 99.23272727272727 Val acc: 1.8800000000000001 Test acc1.7500000000000002; Train loss: 0.0003069007997316393 Val loss: 0.01240787124633789
+INFO - evaluator.py - 2024-10-26 06:46:32,259 - Epoch: 96 Train acc: 99.1909090909091 Val acc: 1.52 Test acc1.63; Train loss: 0.0003167491058226336 Val loss: 0.008930841255187989
+INFO - evaluator.py - 2024-10-26 06:48:00,528 - Epoch: 97 Train acc: 98.92909090909092 Val acc: 2.4 Test acc2.31; Train loss: 0.00039502954847094686 Val loss: 0.008912242126464845
+INFO - evaluator.py - 2024-10-26 06:49:28,778 - Epoch: 98 Train acc: 99.12181818181818 Val acc: 1.5 Test acc1.41; Train loss: 0.0003334193531931801 Val loss: 0.008617444038391113
+INFO - evaluator.py - 2024-10-26 06:50:56,672 - Epoch: 99 Train acc: 99.06181818181818 Val acc: 1.48 Test acc1.27; Train loss: 0.0003543244963511825 Val loss: 0.00835606746673584
+INFO - evaluator.py - 2024-10-26 06:52:24,531 - Epoch: 100 Train acc: 98.97818181818182 Val acc: 1.28 Test acc1.3; Train loss: 0.0003754712219265374 Val loss: 0.010059988021850586
+INFO - evaluator.py - 2024-10-26 06:53:52,370 - Epoch: 101 Train acc: 98.9309090909091 Val acc: 1.26 Test acc1.08; Train loss: 0.00038277816906232725 Val loss: 0.007841364669799804
+INFO - evaluator.py - 2024-10-26 06:55:20,479 - Epoch: 102 Train acc: 98.98 Val acc: 1.46 Test acc1.49; Train loss: 0.0003814188799736175 Val loss: 0.009139167594909669
+INFO - evaluator.py - 2024-10-26 06:56:48,197 - Epoch: 103 Train acc: 99.17454545454547 Val acc: 1.68 Test acc1.69; Train loss: 0.0003074514406987212 Val loss: 0.009717130279541016
+INFO - evaluator.py - 2024-10-26 06:58:15,822 - Epoch: 104 Train acc: 99.0909090909091 Val acc: 1.8599999999999999 Test acc1.81; Train loss: 0.0003502765603702177 Val loss: 0.008496711349487304
+INFO - evaluator.py - 2024-10-26 06:59:43,494 - Epoch: 105 Train acc: 98.87636363636364 Val acc: 1.6 Test acc1.31; Train loss: 0.00040403037245639346 Val loss: 0.008011517429351807
+INFO - evaluator.py - 2024-10-26 07:01:11,089 - Epoch: 106 Train acc: 99.33090909090909 Val acc: 2.32 Test acc1.87; Train loss: 0.00027053345523943956 Val loss: 0.008998249244689942
+INFO - evaluator.py - 2024-10-26 07:02:38,973 - Epoch: 107 Train acc: 99.17454545454547 Val acc: 2.34 Test acc2.4299999999999997; Train loss: 0.0003136266058649529 Val loss: 0.009428902626037598
+INFO - evaluator.py - 2024-10-26 07:04:07,009 - Epoch: 108 Train acc: 98.98 Val acc: 1.68 Test acc2.01; Train loss: 0.00038606275006790054 Val loss: 0.00964776840209961
+INFO - evaluator.py - 2024-10-26 07:05:34,972 - Epoch: 109 Train acc: 99.00909090909092 Val acc: 1.32 Test acc1.29; Train loss: 0.00037116169758479706 Val loss: 0.009487469100952148
+INFO - evaluator.py - 2024-10-26 07:07:02,792 - Epoch: 110 Train acc: 99.1 Val acc: 2.02 Test acc1.68; Train loss: 0.0003354525679553097 Val loss: 0.009603358840942383
+INFO - evaluator.py - 2024-10-26 07:08:30,701 - Epoch: 111 Train acc: 99.03636363636363 Val acc: 1.7399999999999998 Test acc1.66; Train loss: 0.00035924641887911344 Val loss: 0.00853315715789795
+INFO - evaluator.py - 2024-10-26 07:09:58,477 - Epoch: 112 Train acc: 99.02363636363636 Val acc: 1.96 Test acc1.81; Train loss: 0.00035183549762110816 Val loss: 0.009880636215209961
+INFO - evaluator.py - 2024-10-26 07:11:26,244 - Epoch: 113 Train acc: 99.01636363636364 Val acc: 1.34 Test acc1.43; Train loss: 0.00035379438288509846 Val loss: 0.008107324790954589
+INFO - evaluator.py - 2024-10-26 07:12:53,784 - Epoch: 114 Train acc: 99.16363636363637 Val acc: 1.54 Test acc1.4500000000000002; Train loss: 0.00031992048944600604 Val loss: 0.008439115524291992
+INFO - evaluator.py - 2024-10-26 07:14:22,003 - Epoch: 115 Train acc: 98.9509090909091 Val acc: 2.34 Test acc2.34; Train loss: 0.0003813459384847771 Val loss: 0.00873910026550293
+INFO - evaluator.py - 2024-10-26 07:15:50,455 - Epoch: 116 Train acc: 99.10909090909091 Val acc: 1.6400000000000001 Test acc1.46; Train loss: 0.00033918291088193655 Val loss: 0.008757334327697755
+INFO - evaluator.py - 2024-10-26 07:17:18,340 - Epoch: 117 Train acc: 98.95454545454545 Val acc: 1.52 Test acc1.4000000000000001; Train loss: 0.0003645858350971883 Val loss: 0.008514750289916993
+INFO - evaluator.py - 2024-10-26 07:18:46,271 - Epoch: 118 Train acc: 98.88727272727273 Val acc: 1.6 Test acc1.2; Train loss: 0.0003938987396657467 Val loss: 0.00863414192199707
+INFO - evaluator.py - 2024-10-26 07:20:14,111 - Epoch: 119 Train acc: 99.02909090909091 Val acc: 1.26 Test acc1.11; Train loss: 0.0003575788777998903 Val loss: 0.008072014331817628
+INFO - evaluator.py - 2024-10-26 07:21:42,004 - Epoch: 120 Train acc: 99.86545454545454 Val acc: 1.4200000000000002 Test acc1.3599999999999999; Train loss: 8.451341714456e-05 Val loss: 0.00860063762664795
+INFO - evaluator.py - 2024-10-26 07:23:09,990 - Epoch: 121 Train acc: 99.95636363636363 Val acc: 1.48 Test acc1.44; Train loss: 4.877979289740324e-05 Val loss: 0.008990542793273926
+INFO - evaluator.py - 2024-10-26 07:24:37,663 - Epoch: 122 Train acc: 99.98181818181818 Val acc: 1.68 Test acc1.6; Train loss: 3.908945083067837e-05 Val loss: 0.00900686321258545
+INFO - evaluator.py - 2024-10-26 07:26:05,455 - Epoch: 123 Train acc: 99.96909090909091 Val acc: 1.78 Test acc1.55; Train loss: 3.748459692155434e-05 Val loss: 0.009164995765686036
+INFO - evaluator.py - 2024-10-26 07:27:33,584 - Epoch: 124 Train acc: 99.97090909090909 Val acc: 1.96 Test acc1.55; Train loss: 3.4752084882083264e-05 Val loss: 0.00935016746520996
+INFO - evaluator.py - 2024-10-26 07:29:01,373 - Epoch: 125 Train acc: 99.98727272727272 Val acc: 2.04 Test acc1.49; Train loss: 3.36141616889191e-05 Val loss: 0.009304554748535157
+INFO - evaluator.py - 2024-10-26 07:30:29,588 - Epoch: 126 Train acc: 99.98727272727272 Val acc: 1.78 Test acc1.6099999999999999; Train loss: 3.217225751035254e-05 Val loss: 0.00970247745513916
+INFO - evaluator.py - 2024-10-26 07:31:57,554 - Epoch: 127 Train acc: 99.99636363636364 Val acc: 1.76 Test acc1.7000000000000002; Train loss: 3.0645887166346336e-05 Val loss: 0.009877902030944824
+INFO - evaluator.py - 2024-10-26 07:33:25,274 - Epoch: 128 Train acc: 99.98181818181818 Val acc: 1.7399999999999998 Test acc1.6199999999999999; Train loss: 3.353649600493637e-05 Val loss: 0.010235688781738281
+INFO - evaluator.py - 2024-10-26 07:34:52,950 - Epoch: 129 Train acc: 99.99090909090908 Val acc: 1.68 Test acc1.7000000000000002; Train loss: 3.327792074361986e-05 Val loss: 0.010624435424804688
+INFO - evaluator.py - 2024-10-26 07:36:21,131 - Epoch: 130 Train acc: 99.98181818181818 Val acc: 1.7999999999999998 Test acc1.6400000000000001; Train loss: 3.491730727467009e-05 Val loss: 0.011337299156188965
+INFO - evaluator.py - 2024-10-26 07:37:49,064 - Epoch: 131 Train acc: 99.99636363636364 Val acc: 1.8800000000000001 Test acc1.69; Train loss: 3.317942930893464e-05 Val loss: 0.011646426582336425
+INFO - evaluator.py - 2024-10-26 07:39:17,042 - Epoch: 132 Train acc: 99.99636363636364 Val acc: 1.7999999999999998 Test acc1.67; Train loss: 3.376803765158084e-05 Val loss: 0.012033226776123047
+INFO - evaluator.py - 2024-10-26 07:40:45,018 - Epoch: 133 Train acc: 99.99818181818182 Val acc: 1.9 Test acc1.6400000000000001; Train loss: 3.428991687145423e-05 Val loss: 0.01248959846496582
+INFO - evaluator.py - 2024-10-26 07:42:12,598 - Epoch: 134 Train acc: 99.99090909090908 Val acc: 1.7999999999999998 Test acc1.76; Train loss: 3.5584499521858315e-05 Val loss: 0.012866222763061524
+INFO - evaluator.py - 2024-10-26 07:43:40,401 - Epoch: 135 Train acc: 99.98363636363636 Val acc: 1.68 Test acc1.7500000000000002; Train loss: 3.836884954944253e-05 Val loss: 0.013817955017089843
+INFO - evaluator.py - 2024-10-26 07:45:08,347 - Epoch: 136 Train acc: 99.99272727272728 Val acc: 1.66 Test acc1.76; Train loss: 3.783905148421499e-05 Val loss: 0.014568577957153321
+INFO - evaluator.py - 2024-10-26 07:46:36,439 - Epoch: 137 Train acc: 99.9890909090909 Val acc: 1.66 Test acc1.7399999999999998; Train loss: 3.9642622287977825e-05 Val loss: 0.01511151008605957
+INFO - evaluator.py - 2024-10-26 07:48:04,136 - Epoch: 138 Train acc: 99.99090909090908 Val acc: 1.5 Test acc1.6400000000000001; Train loss: 4.0610503024336966e-05 Val loss: 0.016831127166748047
+INFO - evaluator.py - 2024-10-26 07:49:31,933 - Epoch: 139 Train acc: 99.98727272727272 Val acc: 1.5599999999999998 Test acc1.69; Train loss: 4.294578749263151e-05 Val loss: 0.01642604866027832
+INFO - evaluator.py - 2024-10-26 07:51:00,187 - Epoch: 140 Train acc: 99.99636363636364 Val acc: 1.5599999999999998 Test acc1.47; Train loss: 3.985775769264861e-05 Val loss: 0.01862589797973633
+INFO - evaluator.py - 2024-10-26 07:52:27,793 - Epoch: 141 Train acc: 99.99090909090908 Val acc: 1.52 Test acc1.47; Train loss: 4.299895470030606e-05 Val loss: 0.021208724975585937
+INFO - evaluator.py - 2024-10-26 07:53:55,706 - Epoch: 142 Train acc: 99.99454545454546 Val acc: 1.58 Test acc1.48; Train loss: 4.441577935676006e-05 Val loss: 0.021450881958007813
+INFO - evaluator.py - 2024-10-26 07:55:23,539 - Epoch: 143 Train acc: 99.99090909090908 Val acc: 1.6199999999999999 Test acc1.39; Train loss: 4.499345054341988e-05 Val loss: 0.023082176971435546
+INFO - evaluator.py - 2024-10-26 07:56:51,186 - Epoch: 144 Train acc: 99.99272727272728 Val acc: 1.46 Test acc1.44; Train loss: 4.429788286797702e-05 Val loss: 0.024175754165649415
+INFO - evaluator.py - 2024-10-26 07:58:19,265 - Epoch: 145 Train acc: 99.98545454545454 Val acc: 1.4000000000000001 Test acc1.52; Train loss: 4.834632973440669e-05 Val loss: 0.026642925262451173
+INFO - evaluator.py - 2024-10-26 07:59:47,395 - Epoch: 146 Train acc: 99.99454545454546 Val acc: 1.38 Test acc1.4000000000000001; Train loss: 4.601573922078718e-05 Val loss: 0.02998967590332031
+INFO - evaluator.py - 2024-10-26 08:01:15,581 - Epoch: 147 Train acc: 99.99454545454546 Val acc: 1.3599999999999999 Test acc1.4500000000000002; Train loss: 4.6825227336111395e-05 Val loss: 0.028160212326049806
+INFO - evaluator.py - 2024-10-26 08:02:43,158 - Epoch: 148 Train acc: 99.99636363636364 Val acc: 1.38 Test acc1.49; Train loss: 4.745991623706438e-05 Val loss: 0.03014423370361328
+INFO - evaluator.py - 2024-10-26 08:04:10,853 - Epoch: 149 Train acc: 99.99272727272728 Val acc: 1.3599999999999999 Test acc1.43; Train loss: 4.7673355364664035e-05 Val loss: 0.030556745910644532
+INFO - evaluator.py - 2024-10-26 08:05:38,533 - Epoch: 150 Train acc: 99.99090909090908 Val acc: 1.2 Test acc1.32; Train loss: 4.9850631302053275e-05 Val loss: 0.03629016342163086
+INFO - evaluator.py - 2024-10-26 08:07:06,178 - Epoch: 151 Train acc: 99.99272727272728 Val acc: 1.16 Test acc1.27; Train loss: 4.9640710546042433e-05 Val loss: 0.041909449005126956
+INFO - evaluator.py - 2024-10-26 08:08:33,941 - Epoch: 152 Train acc: 99.99272727272728 Val acc: 1.18 Test acc1.27; Train loss: 5.0787061723795807e-05 Val loss: 0.040488933563232424
+INFO - evaluator.py - 2024-10-26 08:10:01,512 - Epoch: 153 Train acc: 99.99636363636364 Val acc: 1.16 Test acc1.2; Train loss: 4.937501441348683e-05 Val loss: 0.0449131477355957
+INFO - evaluator.py - 2024-10-26 08:11:29,544 - Epoch: 154 Train acc: 99.99818181818182 Val acc: 1.1400000000000001 Test acc1.15; Train loss: 5.015549194491045e-05 Val loss: 0.04993664779663086
+INFO - evaluator.py - 2024-10-26 08:12:57,415 - Epoch: 155 Train acc: 100.0 Val acc: 1.1400000000000001 Test acc1.13; Train loss: 5.080486214296384e-05 Val loss: 0.05189599304199219
+INFO - evaluator.py - 2024-10-26 08:14:25,491 - Epoch: 156 Train acc: 99.99636363636364 Val acc: 1.1400000000000001 Test acc1.13; Train loss: 5.1033001503145154e-05 Val loss: 0.052395136260986325
+INFO - evaluator.py - 2024-10-26 08:15:53,326 - Epoch: 157 Train acc: 99.99636363636364 Val acc: 1.1199999999999999 Test acc1.1400000000000001; Train loss: 5.1376344966278833e-05 Val loss: 0.058531346130371094
+INFO - evaluator.py - 2024-10-26 08:17:21,151 - Epoch: 158 Train acc: 99.99272727272728 Val acc: 1.04 Test acc1.0999999999999999; Train loss: 5.221664166416634e-05 Val loss: 0.061377833557128905
+INFO - evaluator.py - 2024-10-26 08:18:49,262 - Epoch: 159 Train acc: 99.99636363636364 Val acc: 1.1199999999999999 Test acc1.13; Train loss: 5.1350912062281915e-05 Val loss: 0.06516065139770508
+INFO - evaluator.py - 2024-10-26 08:20:17,372 - Epoch: 160 Train acc: 99.9890909090909 Val acc: 1.1400000000000001 Test acc1.11; Train loss: 5.550309512764215e-05 Val loss: 0.06499602584838868
+INFO - evaluator.py - 2024-10-26 08:21:45,013 - Epoch: 161 Train acc: 99.99272727272728 Val acc: 1.0999999999999999 Test acc1.08; Train loss: 5.384573271836747e-05 Val loss: 0.06378588256835938
+INFO - evaluator.py - 2024-10-26 08:23:12,921 - Epoch: 162 Train acc: 99.9890909090909 Val acc: 1.0999999999999999 Test acc1.0999999999999999; Train loss: 5.774059690196406e-05 Val loss: 0.06919073944091797
+INFO - evaluator.py - 2024-10-26 08:24:40,774 - Epoch: 163 Train acc: 99.99272727272728 Val acc: 1.06 Test acc1.0699999999999998; Train loss: 5.578780687329444e-05 Val loss: 0.07971501007080078
+INFO - dataset_loader.py - 2024-10-28 22:08:16,004 - delta is reset as 1.8484667129285888e-06
+INFO - evaluator.py - 2024-10-28 22:57:35,449 - The FID of synthetic images is 245.40488293234682
+INFO - evaluator.py - 2024-10-28 22:57:35,451 - The Inception Score of synthetic images is 1.675389289855957
+INFO - evaluator.py - 2024-10-28 22:57:35,451 - The Precision and Recall of synthetic images is 0.7455397248268127 and 0.00019999999494757503
+INFO - evaluator.py - 2024-10-28 22:57:35,451 - The FLD of synthetic images is 24.606788158416748
+INFO - evaluator.py - 2024-10-28 22:57:35,451 - The ImageReward of synthetic images is -2.263369669710833
+INFO - dataset_loader.py - 2024-10-28 22:57:36,837 - delta is reset as 5.11965868690912e-07
+INFO - evaluator.py - 2024-10-28 23:59:51,090 - The FID of synthetic images is 127.70160766828963
+INFO - evaluator.py - 2024-10-28 23:59:51,094 - The Inception Score of synthetic images is 2.396092653274536
+INFO - evaluator.py - 2024-10-28 23:59:51,094 - The Precision and Recall of synthetic images is 0.4320312738418579 and 0.0016833568224683404
+INFO - evaluator.py - 2024-10-28 23:59:51,094 - The FLD of synthetic images is 20.96329927444458
+INFO - evaluator.py - 2024-10-28 23:59:51,094 - The ImageReward of synthetic images is -2.0141066952829716
+INFO - dataset_loader.py - 2024-10-28 23:59:52,126 - delta is reset as 1.5148623360286113e-06
+INFO - evaluator.py - 2024-10-29 00:51:02,489 - The FID of synthetic images is 17.081697814953657
+INFO - evaluator.py - 2024-10-29 00:51:02,492 - The Inception Score of synthetic images is 3.9322965145111084
+INFO - evaluator.py - 2024-10-29 00:51:02,492 - The Precision and Recall of synthetic images is 0.5424844026565552 and 0.3853333294391632
+INFO - evaluator.py - 2024-10-29 00:51:02,492 - The FLD of synthetic images is 6.554317474365234
+INFO - evaluator.py - 2024-10-29 00:51:02,492 - The ImageReward of synthetic images is -1.6361236040304448
+INFO - dataset_loader.py - 2024-10-29 00:51:03,058 - delta is reset as 4.329102935418938e-06
+INFO - evaluator.py - 2024-10-29 01:42:24,877 - The FID of synthetic images is 164.97207247508004
+INFO - evaluator.py - 2024-10-29 01:42:24,879 - The Inception Score of synthetic images is 1.6467124223709106
+INFO - evaluator.py - 2024-10-29 01:42:24,879 - The Precision and Recall of synthetic images is 0.602484405040741 and 0.011652173474431038
+INFO - evaluator.py - 2024-10-29 01:42:24,879 - The FLD of synthetic images is 18.773305416107178
+INFO - evaluator.py - 2024-10-29 01:42:24,879 - The ImageReward of synthetic images is -1.579579470070079
+INFO - dataset_loader.py - 2024-10-29 01:42:25,242 - delta is reset as 1.8484667129285888e-06
+INFO - evaluator.py - 2024-10-29 02:35:25,718 - The FID of synthetic images is 109.95839653086716
+INFO - evaluator.py - 2024-10-29 02:35:25,751 - The Inception Score of synthetic images is 3.1288182735443115
+INFO - evaluator.py - 2024-10-29 02:35:25,751 - The Precision and Recall of synthetic images is 0.5966984033584595 and 0.036159999668598175
+INFO - evaluator.py - 2024-10-29 02:35:25,751 - The FLD of synthetic images is 19.213759899139404
+INFO - evaluator.py - 2024-10-29 02:35:25,751 - The ImageReward of synthetic images is -2.214698282242767
+INFO - dataset_loader.py - 2024-10-29 02:35:26,383 - delta is reset as 1.8484667129285888e-06
+INFO - evaluator.py - 2024-10-29 03:27:02,083 - The FID of synthetic images is 219.54836766661845
+INFO - evaluator.py - 2024-10-29 03:27:02,086 - The Inception Score of synthetic images is 1.7984269857406616
+INFO - evaluator.py - 2024-10-29 03:27:02,086 - The Precision and Recall of synthetic images is 0.6327812671661377 and 0.0003600000054575503
+INFO - evaluator.py - 2024-10-29 03:27:02,086 - The FLD of synthetic images is 27.920222282409668
+INFO - evaluator.py - 2024-10-29 03:27:02,086 - The ImageReward of synthetic images is -2.2739594591539354
+INFO - dataset_loader.py - 2024-10-29 03:27:02,840 - delta is reset as 1.8484667129285888e-06
+INFO - evaluator.py - 2024-10-29 04:18:40,193 - The FID of synthetic images is 201.61100378723972
+INFO - evaluator.py - 2024-10-29 04:18:40,221 - The Inception Score of synthetic images is 1.9011380672454834
+INFO - evaluator.py - 2024-10-29 04:18:40,221 - The Precision and Recall of synthetic images is 0.6231746077537537 and 0.0005200000014156103
+INFO - evaluator.py - 2024-10-29 04:18:40,221 - The FLD of synthetic images is 27.509820461273193
+INFO - evaluator.py - 2024-10-29 04:18:40,221 - The ImageReward of synthetic images is -2.2687564725081124
+INFO - dataset_loader.py - 2024-10-29 04:18:42,924 - delta is reset as 2.6201132658294697e-07
+INFO - evaluator.py - 2024-10-29 05:19:05,639 - The FID of synthetic images is 22.085653876120773
+INFO - evaluator.py - 2024-10-29 05:19:05,642 - The Inception Score of synthetic images is 1.7683465480804443
+INFO - evaluator.py - 2024-10-29 05:19:05,642 - The Precision and Recall of synthetic images is 0.7516825795173645 and 0.3393147587776184
+INFO - evaluator.py - 2024-10-29 05:19:05,642 - The FLD of synthetic images is -6.095540523529053
+INFO - evaluator.py - 2024-10-29 05:19:05,642 - The ImageReward of synthetic images is -1.793093251128755
+INFO - dataset_loader.py - 2024-10-29 05:19:06,164 - delta is reset as 1.5148623360286113e-06
+INFO - evaluator.py - 2024-10-29 06:19:12,182 - The FID of synthetic images is 36.55868340206811
+INFO - evaluator.py - 2024-10-29 06:19:12,189 - The Inception Score of synthetic images is 1.9821124076843262
+INFO - evaluator.py - 2024-10-29 06:19:12,189 - The Precision and Recall of synthetic images is 0.19395314157009125 and 0.42188334465026855
+INFO - evaluator.py - 2024-10-29 06:19:12,189 - The FLD of synthetic images is 16.948330402374268
+INFO - evaluator.py - 2024-10-29 06:19:12,189 - The ImageReward of synthetic images is -2.130454104746692
+INFO - dataset_loader.py - 2024-10-29 06:19:12,548 - delta is reset as 1.8484667129285888e-06
+INFO - evaluator.py - 2024-10-29 07:17:08,735 - The FID of synthetic images is 103.17130225064335
+INFO - evaluator.py - 2024-10-29 07:17:08,757 - The Inception Score of synthetic images is 3.3248043060302734
+INFO - evaluator.py - 2024-10-29 07:17:08,757 - The Precision and Recall of synthetic images is 0.5925872921943665 and 0.05226000025868416
+INFO - evaluator.py - 2024-10-29 07:17:08,757 - The FLD of synthetic images is 18.80326271057129
+INFO - evaluator.py - 2024-10-29 07:17:08,757 - The ImageReward of synthetic images is -2.2046342791773026
+INFO - dataset_loader.py - 2024-10-29 07:17:09,384 - delta is reset as 1.5148623360286113e-06
+INFO - evaluator.py - 2024-10-29 08:12:19,400 - The FID of synthetic images is 36.16871462142183
+INFO - evaluator.py - 2024-10-29 08:12:19,442 - The Inception Score of synthetic images is 1.9785420894622803
+INFO - evaluator.py - 2024-10-29 08:12:19,442 - The Precision and Recall of synthetic images is 0.2151111215353012 and 0.38750001788139343
+INFO - evaluator.py - 2024-10-29 08:12:19,442 - The FLD of synthetic images is 16.76713228225708
+INFO - evaluator.py - 2024-10-29 08:12:19,442 - The ImageReward of synthetic images is -2.120978381105832
+INFO - dataset_loader.py - 2024-10-29 08:12:21,784 - delta is reset as 2.6201132658294697e-07
+INFO - evaluator.py - 2024-10-29 09:12:37,637 - The FID of synthetic images is 57.79238987775261
+INFO - evaluator.py - 2024-10-29 09:12:37,646 - The Inception Score of synthetic images is 1.4734785556793213
+INFO - evaluator.py - 2024-10-29 09:12:37,647 - The Precision and Recall of synthetic images is 0.6569206714630127 and 0.13006387650966644
+INFO - evaluator.py - 2024-10-29 09:12:37,647 - The FLD of synthetic images is -1.181638240814209
+INFO - evaluator.py - 2024-10-29 09:12:37,647 - The ImageReward of synthetic images is -2.0049813007896855
+INFO - dataset_loader.py - 2024-10-29 09:12:39,948 - delta is reset as 2.6201132658294697e-07
+INFO - evaluator.py - 2024-10-29 10:14:57,218 - The FID of synthetic images is 29.3289837710725
+INFO - evaluator.py - 2024-10-29 10:14:57,224 - The Inception Score of synthetic images is 1.652750849723816
+INFO - evaluator.py - 2024-10-29 10:14:57,224 - The Precision and Recall of synthetic images is 0.7476875185966492 and 0.285733163356781
+INFO - evaluator.py - 2024-10-29 10:14:57,224 - The FLD of synthetic images is -4.951715469360352
+INFO - evaluator.py - 2024-10-29 10:14:57,224 - The ImageReward of synthetic images is -1.871033944573719
+INFO - dataset_loader.py - 2024-10-29 10:14:57,630 - delta is reset as 1.5148623360286113e-06
+INFO - evaluator.py - 2024-10-29 11:06:17,358 - The FID of synthetic images is 5.286480673016143
+INFO - evaluator.py - 2024-10-29 11:06:17,363 - The Inception Score of synthetic images is 2.071159601211548
+INFO - evaluator.py - 2024-10-29 11:06:17,363 - The Precision and Recall of synthetic images is 0.6194375157356262 and 0.7204999923706055
+INFO - evaluator.py - 2024-10-29 11:06:17,364 - The FLD of synthetic images is 3.7299275398254395
+INFO - evaluator.py - 2024-10-29 11:06:17,364 - The ImageReward of synthetic images is -2.0137405606759713
+INFO - dataset_loader.py - 2024-10-29 11:06:17,775 - delta is reset as 4.329102935418938e-06
+INFO - evaluator.py - 2024-10-29 11:39:57,591 - The FID of synthetic images is 168.59217462930627
+INFO - evaluator.py - 2024-10-29 11:39:57,596 - The Inception Score of synthetic images is 1.6652277708053589
+INFO - evaluator.py - 2024-10-29 11:39:57,596 - The Precision and Recall of synthetic images is 0.6194375157356262 and 0.00952173862606287
+INFO - evaluator.py - 2024-10-29 11:39:57,596 - The FLD of synthetic images is 20.778346061706543
+INFO - evaluator.py - 2024-10-29 11:39:57,596 - The ImageReward of synthetic images is -1.5740511079076678
+INFO - dataset_loader.py - 2024-10-29 11:39:58,114 - delta is reset as 1.8484667129285888e-06
+INFO - evaluator.py - 2024-10-29 12:12:19,140 - The FID of synthetic images is 231.37436795903784
+INFO - evaluator.py - 2024-10-29 12:12:19,145 - The Inception Score of synthetic images is 1.7306236028671265
+INFO - evaluator.py - 2024-10-29 12:12:19,145 - The Precision and Recall of synthetic images is 0.7602222561836243 and 0.00043999997433274984
+INFO - evaluator.py - 2024-10-29 12:12:19,145 - The FLD of synthetic images is 23.48649501800537
+INFO - evaluator.py - 2024-10-29 12:12:19,146 - The ImageReward of synthetic images is -2.2615407764571054
+INFO - dataset_loader.py - 2024-10-29 12:12:19,367 - delta is reset as 4.329102935418938e-06
+INFO - evaluator.py - 2024-10-29 12:45:16,662 - The FID of synthetic images is 237.36948091544997
+INFO - evaluator.py - 2024-10-29 12:45:16,666 - The Inception Score of synthetic images is 1.2807329893112183
+INFO - evaluator.py - 2024-10-29 12:45:16,667 - The Precision and Recall of synthetic images is 0.5577656626701355 and 4.347825961303897e-05
+INFO - evaluator.py - 2024-10-29 12:45:16,667 - The FLD of synthetic images is 30.49933910369873
+INFO - evaluator.py - 2024-10-29 12:45:16,667 - The ImageReward of synthetic images is -1.8509714604625478
+INFO - dataset_loader.py - 2024-10-29 12:45:17,305 - delta is reset as 1.5148623360286113e-06
+INFO - evaluator.py - 2024-10-29 13:18:11,048 - The FID of synthetic images is 53.50594213505724
+INFO - evaluator.py - 2024-10-29 13:18:11,054 - The Inception Score of synthetic images is 3.4386539459228516
+INFO - evaluator.py - 2024-10-29 13:18:11,055 - The Precision and Recall of synthetic images is 0.26606249809265137 and 0.12056666612625122
+INFO - evaluator.py - 2024-10-29 13:18:11,055 - The FLD of synthetic images is 20.395588874816895
+INFO - evaluator.py - 2024-10-29 13:18:11,055 - The ImageReward of synthetic images is -1.8617446345779531
+INFO - dataset_loader.py - 2024-10-29 13:18:11,648 - delta is reset as 1.5148623360286113e-06
+INFO - evaluator.py - 2024-10-29 13:50:35,681 - The FID of synthetic images is 4.446889068230405
+INFO - evaluator.py - 2024-10-29 13:50:35,832 - The Inception Score of synthetic images is 2.0761497020721436
+INFO - evaluator.py - 2024-10-29 13:50:35,832 - The Precision and Recall of synthetic images is 0.6322698593139648 and 0.7390333414077759
+INFO - evaluator.py - 2024-10-29 13:50:35,833 - The FLD of synthetic images is 3.283095359802246
+INFO - evaluator.py - 2024-10-29 13:50:35,833 - The ImageReward of synthetic images is -2.0057078354216755
+INFO - dataset_loader.py - 2024-10-29 13:50:37,371 - delta is reset as 5.11965868690912e-07
+INFO - evaluator.py - 2024-10-29 14:31:49,267 - The FID of synthetic images is 28.848900967099837
+INFO - evaluator.py - 2024-10-29 14:31:49,353 - The Inception Score of synthetic images is 2.238304853439331
+INFO - evaluator.py - 2024-10-29 14:31:49,353 - The Precision and Recall of synthetic images is 0.6088594198226929 and 0.1520366072654724
+INFO - evaluator.py - 2024-10-29 14:31:49,354 - The FLD of synthetic images is nan
+INFO - evaluator.py - 2024-10-29 14:31:49,354 - The ImageReward of synthetic images is -1.3833920579410202
+INFO - dataset_loader.py - 2024-10-29 14:31:49,986 - delta is reset as 1.8484667129285888e-06
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/checkpoints/checkpoint_100000.pth b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/checkpoints/checkpoint_100000.pth
new file mode 100644
index 0000000000000000000000000000000000000000..981e6c919c1c9eaa9b8ea1630d2b3d25a3c096e2
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/checkpoints/checkpoint_100000.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:050db974fe9be59200db1545421dc98cb5652d0283aaef15889542e5d49d1fc6
+size 61741705
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/checkpoints/final_checkpoint.pth b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/checkpoints/final_checkpoint.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6f209f210193b804e3092edd14ed7b387d2c6ab7
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/checkpoints/final_checkpoint.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c23cd04ebc4732b24f7b3d41f039746064bb1522f40797b6a2e1bea8fff78b
+size 61740646
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/checkpoints/snapshot_checkpoint.pth b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/checkpoints/snapshot_checkpoint.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2937583b77204913338f3d3ba770a75f05820a05
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/checkpoints/snapshot_checkpoint.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bb0d269fa9bcc2a2a932fadbe5ec7856dd0bfea7b4b201c8ad7aab80c311203
+size 61743823
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_10000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_10000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..b7cd5396917fc02ddbc1ff08b0adef28f9d0c311
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_10000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebd7b2f62ee8460a570e24bcf07fc1cc593ed446d8e662d64cd43503ac303aaa
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_10000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_10000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..5855cb3894a69fd46d05b397b779ec45912e4cde
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_10000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a52bc36ee0ed2a4fdf1d0e2703836d81520b1090f2b522aff45e10b10d317fd
+size 375026
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_100000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_100000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..2e803c3a2707d8246f30e4cb499848fb4f8a4a2f
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_100000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff52c05d202ac9e5dc8946d30b22168389355ee6bdd48eda91c39ae7650c6928
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_100000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_100000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..07df9dcef6196e75516f876575cc0c69ee1314bf
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_100000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d39fbe04ddbe696f5b13f2e4e8a253a740d14e094cffddc6430964031ce0bc7b
+size 360880
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_102000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_102000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..d2cb706a36537f5282ddb9468bef77aad52c0c66
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_102000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d558cef6cd76718131cadc5bff30b81eb28b1728b8ed22a4c2e9ca5152337d94
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_102000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_102000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..48cf4454dc977bd8b29be212ca9fa8b2dd815661
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_102000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:635c0421ad62f2daba61e70b22b654b9b5e81f591325a38d1edc3a1421ec97ba
+size 360481
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_104000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_104000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..6ca3e9bafb068e2c04508e49692105a6ff69a5cb
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_104000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcd6e0455384c7de8d66c9c72082f5933edd345ed75807855a9c3d74273be
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_104000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_104000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..0485b6adf0162306a03ca9c48c7ac3463f6874c9
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_104000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e93595e81e082d5f9b4450a268a76b4361e807d474c7c8514eca65aefe752a64
+size 359721
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_12000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_12000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..4622bd4eee03f5aac1708329492f328a1e281209
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_12000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8368603afc430ef6a56c659f5ad89b09099e7462cabe63b739bdb2fae859c9cc
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_12000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_12000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..807ba145bfa16c90ae79df8a0ad2e1110f7ce804
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_12000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3984944206339bede0d5be85ac08d98d9f219c8f71a283c72d8834ac5a18a3c
+size 371524
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_14000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_14000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..3d64f8393be1bbbb5480638f92842319b06a361f
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_14000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c0eeeb0ac8a9bb9579495cc195a33804a1ce6934838fc960a112cac015bf3cc
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_14000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_14000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..bea2f2da96b99a8fd29219af083726823a6b5cb9
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_14000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f4737b20b00514549903ade033d924194b82a921c4f9f0e1bc1cac6728d41ad
+size 370425
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_16000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_16000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..4bc3bb7bc9acb6e10fb05327c45ba7d53a84fb9e
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_16000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0667f3f6261379f65498486c57955663542f4dec0e4a2ecb6a94a12c36a6b417
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_16000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_16000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..924fc9d896da2aba4c4673308811b8ceee742d12
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_16000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00143230e452a95e80d6fcca5a9d475f019af32d27b4258025ab0da6ce9c02bf
+size 371879
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_18000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_18000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..93d0864d495af676d922ac150e4fb314de362eab
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_18000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75969a6b81c09a34092465109ed54cdeecccf652d5db878422803937843ebe65
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_18000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_18000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..30fee55345096f8d47c36821ab75e76af7508231
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_18000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4de65a9861c0c2d4d9ca7a58125e99ba421760fd3d38d686bf71d47b9fb2eb43
+size 374175
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_2000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_2000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..677868f63656870620394180030b7fc796a4a16c
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_2000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2230ce7889929d177e4c1aeaebb6e10c2b15cc3b18e828baf546c0f2a5eddc9
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_2000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_2000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..83fb0fa582d9a95cadd4605796ab3ec0e731fc93
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_2000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16459e623b82d13d4f6aa1223f71a1978a7966c8eeb9404fd0c38e9fd0b6f4a2
+size 482856
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_20000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_20000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..8fe54266677d0d9188ac12e1274943590fc9df02
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_20000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3101473786d2774f0b5e43039b796f0cb1a733f22a2011fafaa06aab7677c07e
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_20000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_20000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..4dbc5207750c547e3d0cec5abe463be1598ca632
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_20000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:604dfed2926c66f8fae19c97e52520a5b84947fa3823a3ce27ce755e73eb0e6e
+size 375521
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_22000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_22000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..86890a8c8ee4b9646d1827bc96c4ec0cb4f04f1f
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_22000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1217a5fc157a9c0c932c0673555e6f960e426b2e574af2997c08d0052ce1ecaa
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_22000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_22000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..990e2825922129fd956ce60dd7b5dc2294dc0829
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_22000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1fa84658453d10d2dfdcea13d6f16804b00cf3b008571675cb9ae36df83e137
+size 375477
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_24000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_24000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..4cae29c6987261d9e4448767e02553f7fb162ed7
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_24000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:061b39269bae9a44bf02dbc7b8ea31da93269147c2098c652e1052ecb5dc55d1
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_24000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_24000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..b0e02f65939d17500b751eabe7230821119f0fc0
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_24000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e857a74d9bb88e038238e7b883acd00cde6472e578c4c1e6ed14109fc138cf7
+size 376347
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_26000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_26000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..cfe994df4f266c3cbff088a3d292c7716bb12beb
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_26000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65a6eac215095dc348de3a239b68eb4f085e3acfc47ae02ab65492bb88f52272
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_26000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_26000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..f5ba721a6253a33ddca11adfd09d81855b85b028
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_26000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eecdf8079c82099cc7be8ab3a4c32e46410d94f2524feb83860a0b982e7dbefd
+size 375166
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_28000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_28000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..a485eab1bddf52742a9cbad688fe500fa17a1f67
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_28000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dbce4e5fb119d88e7aa838291fbdb5d4b1d63740b09d0dc2dde2dbafc2407b6
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_28000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_28000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..5af28f5f24da1489e0cd0f4e03e129a8017409e9
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_28000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8b3ee173421edb5018f971f57deae4a6acb717e55cca12be532725bc3fb8243
+size 374250
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_30000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_30000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..cba9591055f591965ec77a6828efb560a7e5cbf3
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_30000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ad691acbaa127737277cb1baac9e8edb53f702a0fed22923d1d375e35d36010
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_30000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_30000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..ee1551918fcdfee5a11086f16e51ae18f0e1bd3e
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_30000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0643ad76cbabbdd5b0cd7ef30300fa979aa44f5d0280e31e09ad13b0712a44f2
+size 374044
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_32000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_32000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..3cddeb5dfcef86efb9f1dfd59a200af235877df1
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_32000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1987d120776326212180cccbafd6a95f238d053ba44c4e6a6907a70807089f9
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_32000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_32000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..71ab5a1f495f10379fb2648819596e3d1ac74269
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_32000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a13ac75e642c9e3dd9c7f3abce4da9e9fe132b3f88f2e83e4f9e26fff0518858
+size 371446
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_34000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_34000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..e75def9a53ef82768bda0dee5f98f2a789299e2c
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_34000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebfd9fcb755b5c16dd34cb2055bb1dc015e510d7c25e20d526c101f31d72fe68
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_34000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_34000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..366ab144604df52f9f4a5e7d5a3b910739e2db9d
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_34000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:923e125d3190385d06291b4636facfd2eeb1fb0857d206492e39ee576fd21d8f
+size 371270
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_36000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_36000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..5c4100d5cf12416ecbd5609bb3a696f4dcfa78ab
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_36000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:935b7280d67625fbaa6441e8a057127e5d5e03e3b292af489cb128e25b3ac7e1
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_36000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_36000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..0bcfaa20fee9008c39138df7adf85e0932b3641f
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_36000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2df7addda6b5ccea26d2d2d42b4e29abde359cf712c7e8dca549778dfd5b4e81
+size 371508
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_38000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_38000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..a61b9dd7ce6661b00e1a98588d62885da6befa98
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_38000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff82defeea5e40a64aeb193cc679dfd88a82376e1b553507452827082353018b
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_38000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_38000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..b6854450667f56ae265a7db1681e80798156d7db
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_38000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46484c45a3e44f509395c93cc92db9b51a04864758e3456d921f559266ead991
+size 368430
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_4000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_4000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..6a39e9a44c09f5832fbb759aa990fb25dd6452da
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_4000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f33bcc2673901568cadd2d0d6cb305c620bec91d724ffa408471a76ab4419d8
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_4000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_4000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..1ec0f6185e0a0c1311d61fa81f5d4c4e4f3e5244
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_4000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e124a4fcfcb4931f20805a7541522a3609195664295ccfe2c04d1aa4281b871f
+size 426430
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_40000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_40000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..83802005346d883b27248a66d96e140f8babffaf
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_40000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2986af7553e7cb00f056dbe98b0bc3151c15d4301e11c9505c7ea90b5893d5c
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_40000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_40000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..8f2b023aeffb0c320c0eaa1eb2f4c40631523298
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_40000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a198dcb0219e64fdbd6e12e832b5ece16de57e8d45e47159b6057fb35ade9dc8
+size 368885
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_42000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_42000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..288b34e4fc65c3b2a81c12f98dda3a19bc97fad6
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_42000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c09e0c9c0d9b91289f027d3ef172353769fa70133bda8ed74cd0b33d8e98ccc
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_42000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_42000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..a6dbb289725fc5f1587f4591bdf5b5e3ef27686b
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_42000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d62160f10b97b3372fe2ac91827ccc5aebc2e4da900b94588be2ba5ac4a330c2
+size 367579
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_44000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_44000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..9260ac959e13839389978f45508d8f534bac4345
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_44000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22df01a297277fc7406353d4b94a550532682cf5a4aa6a94c2e8522bfe4ee6b1
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_44000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_44000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..6415ad02b034598ab57635f296ec882b1418cb72
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_44000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3c3c48bd33c0eeab2a5e1f6e341d661d2168b9566af80a63143bba3d6c45885
+size 368578
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_46000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_46000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..c6f397f118e0f4662b5f34d0cd6ea3e496cebad6
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_46000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f2ae17e0c502b4f98def9a00399da0aaf5c118161297e2258364425bdf87fbf
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_46000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_46000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..51fc00fa2cde7712d6dabe56f21dafbd478ebe09
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_46000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cd8273d0372d05d08e833067245a5860ea8bedf7cad9689edaacdb187231c1a
+size 366985
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_48000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_48000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..0ad9a6cc01cd85db4d9b96bf7ab2906c1503475c
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_48000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b60d21f408aaed88948b62e2813ca2acf41b0aa0a88abbad9db1b5f8b026d56a
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_48000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_48000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..bac270dfe74f838faae6e536f194cc80783acbbc
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_48000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af2089721d620c797e7b6cb08eb8744a5da9aca1868bf09b29a1888482703c0f
+size 366394
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_50000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_50000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..ffcfa120c0cc52032e2ac495d0ddb9bce312d2bc
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_50000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7123ff30e4b260549c3c019f022e207c89a25d788ad2584fd36fea5d53961067
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_50000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_50000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..13cd0a37d884050961208fcdc300ea0a7e287f45
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_50000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fd239d1cb9beef948d1c7433238db7bea4ecf082edc8865061859f36e09cb7f
+size 366214
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_52000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_52000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..55384d7ca5e6752a066685452565b3b4e27ca7a6
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_52000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:337020e289c26f1e8626a29c7abef4fd2d4917bf63dc2a5f4d56e82f52bead4e
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_52000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_52000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..0bccd23d999ca2cbcd7d3293209cf97c58ff360f
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_52000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c149dc9de35d066fef13bc8b1133bf5e1c8096ab87f018a6ac484c7be806c4f1
+size 366330
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_54000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_54000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..939cf3c078cd51565359eb42c34aca45a3712e54
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_54000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c67356e463355f3b1c515d394c9f88db5fed5c293fdb0afa78a0262b120a7073
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_54000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_54000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..878b7db4270b8c54ade0f06511554e76b0716ba5
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_54000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20dd1b1bed69eeec60ee665f7e31b128ed286597b94d0be438553562a15eedd2
+size 364544
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_56000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_56000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..44bec15493d791882fbc4b7815452a345c9402aa
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_56000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:147671772d5c3858e5e45390b873f15c1ece74c364a9698d7a29288d0ca12d9d
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_56000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_56000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..b1d3054b78c1df36a7b9588de691d191978788c7
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_56000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05ae8b4ff736714a2f6d4df7c0a05ece2a647decc149d51b3c9d4ad31db4ecc6
+size 366542
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_58000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_58000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..f870a4c70e6ddd02b350278fff27f03b5a109845
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_58000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:554e15b7c12547ec679abf0a1bc120f0719819d155bb10da89396ae0fccba5e6
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_58000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_58000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..4e5ca2278bf708c5fc4c91988897eb4a7e7eb08b
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_58000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9cca19283c4c91e02d99e29a2e16e967bc7fc8f1f5daf7beacb8c86fcd1f97b
+size 365644
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_6000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_6000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..1bd53881fc0cf3c7230a3c621a1266a0ef012372
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_6000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74c59ae67b47afb2bbd5cab5329b41ee4b14c47c2ae2721b47a2f4cf4f114f57
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_6000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_6000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..99c339f45f2a2dd28fbac73032f5b3a89aad9a81
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_6000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b42cc2fbd3e27f7eaa0f70ec5b2d50ed4cc13da54f860460f75611d9d599d608
+size 395715
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_60000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_60000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..8c2c0fb373a5ca88ba477db659577e5082703fce
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_60000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b3b258092beaef4240dc52f5059eca48d611425100cff4a07b9d09f80f5b024
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_60000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_60000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..01d60a46e452a081a23a47fd59001dfd249d118b
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_60000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1cf65ae822ab088d595bcf07601dd7ec326264772492fc6c76f497a41f0897e
+size 364709
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_62000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_62000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..580161cb86f422491882940210ed762cf9199874
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_62000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c6c1f82bc37370e2631a4e16360216467b19668543e86b0198c566a9831544c
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_62000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_62000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..f1288ef8911058607118534f0af017731cded39a
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_62000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bccfcb23e02fd596362ca47f17935d7d0964865dcbc1f29edef8bb50f99518a
+size 364599
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_64000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_64000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..92adac79d785eedf932d3fd29970ed2368f641f5
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_64000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dc8816738e129926b30e1c889c35b9b056997ff9c17c99124a5e1aa8e9db757
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_64000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_64000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..e275a19f4514ae14c07a0726655732f9d9a8e0b0
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_64000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ef5d8774fde2aebce42d2c006e69d4c16016bd44e175761538f050074c839f0
+size 363681
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_66000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_66000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..ac7b9e2fad1c102a7494ca6d442ec4f4949e4245
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_66000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbbb2329d003cf270409e2139a9becda43f43800fa4637674f7df63e9de86c4d
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_66000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_66000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..e53a80b62e2abd8ff8b1d73f0fedb827bd3dd06b
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_66000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b76d2df2be2eb67714fc301b469f601ce802d5f7fbe10c839478ffde2180ad74
+size 366229
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_68000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_68000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..0d25fb7dcaff26285514227f5bfa80059068e9cb
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_68000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19fb64c70648c31b3171a5af4f7572b1c28898b449f87c183f786d869ae8f568
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_68000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_68000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..a5b6ff34ad232700607fa15a168553735b2499af
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_68000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63dde04daff76b356e2d7ae7af3930853da7e5d12fb61bb88bc0249833994160
+size 364614
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_70000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_70000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..14c9f3614eac93592c753dd2407c0d91ea5d722e
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_70000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f3b02dd8f9bee36324cdab59c1afd9957326e183f5d5f39664b1171d1dd3297
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_70000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_70000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..fa124b3954d1a27a2b9bd2c266476473e7ea1d42
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_70000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b77847f0dcbf11c8bbe77eefc6e5b87dab2d0d373fef5337ef41676196002523
+size 361386
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_72000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_72000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..3263db8d50a7e856da46de1486eadcba52c36d6b
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_72000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07ef7f007f6237b201408fa9340c139b02b4fc1369e559c26e1c256e38135fbe
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_72000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_72000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..2fb3646de61684a4fd1883fa9e401235c463b093
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_72000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa6ea3edb78e8ba1c6a18636113058bf0ca3e24dcf5591e6ed5b135a24687e85
+size 364604
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_74000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_74000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..7f4fbd4fd733f7acac1e534430d8c6659225f084
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_74000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94e1f9a1f90aaf7e3051cc01930a4e6ecfeb5ff9f7402a7e532e04b1a8b78923
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_74000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_74000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..cd2f3b22b62e7a97de8ef13c48ce4c94c63401d4
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_74000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d61e55da8cf0e395fbf53ee018c0de867cfdcb61d16a02764f36f1e9dfa0fd05
+size 363079
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_76000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_76000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..acff239399dfcb3f0a47175e022728cf6c2b199e
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_76000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8230559f4d7b9d42cd0053e4c5555b729195312994d5afe55b310aa9018f293c
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_76000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_76000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..76943f8c006dee0234b17ddcdb74f3a0be6a8f88
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_76000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7fca2614647868ae5d06aff160496e8d0408d06c3a24a20c06c2c5b6130a13b
+size 362892
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_78000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_78000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..bcd046431354066c694449c08d117bc5f824bbd2
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_78000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:524a38f837bea6154856dc38a70877127c3c5164f81d29df28618d70884e0fd0
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_78000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_78000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..82bc95c320f6694bb9b98c6099e3df3b57d24579
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_78000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f74870d91a7058af87e37bea1de607ac22f086512aa0148b640fe837df1d648d
+size 362333
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_8000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_8000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..1edbbbaa7bdbd0d806c8faa566c356ada567121e
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_8000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7adb32002693b972581e2ad11f770ace789d4ecc5485b80e1bb1eeb551dd190
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_8000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_8000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..5e2b30bdf9e0fbb7caa9a53c5fea1403819f1074
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_8000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aed6cd156acead2c2032fef5ccc71508ceb4f2d542ef648c4d4deadb39d91be4
+size 381635
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_80000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_80000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..ba73a85b87c2bcf53538883c503c8a931cc3ba7f
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_80000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f27dea6adefac10e4eaf88e04bc2956b0c3e7470c8d587b5a3d42a0396776c03
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_80000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_80000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..9ba0d5bedb7d4b1990a335fab61996bf7fdc5cee
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_80000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd1c4d99d234dd567196468421b3a61e41e5b0c5d195af33298db7b4b3f234b7
+size 361758
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_82000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_82000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..563e90e707ebddf6ec6fd6b0042ffce49ab86526
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_82000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6373efbb7eca87f75b52810771fb02897247bbc44471d49f67bddc3d6913cdbf
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_82000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_82000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..15f8c35ee715241a57cd8d6da62a5d148b7b6660
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_82000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5656b6af76cb797d9cd32af36afe0a95362ed2664ffcac73a0e4cd365b6c37a7
+size 362445
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_84000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_84000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..5b43cf040a8338b496e742f1c4c23b1d467fd3eb
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_84000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93ec1a6c9d180d2931a53102d337c64d1675d039cd505f76d035a4338c3af7b8
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_84000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_84000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..0c5cd728f34638d36f5aa7a787deeca640b57624
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_84000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71e804fd39cef2e15837b6228f940d907b4dbfada7007a3d9ef0c3d80baca5ea
+size 361038
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_86000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_86000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..708c10d67f5fccc83d058b17f83a5fa3c8b0e7de
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_86000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c5b78716985c6f10710261f722e13e95eb29187f73bdfc2ca921126d5f91461
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_86000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_86000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..d0358c022318d0eaa9873dbb640eea9ef8f2efc5
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_86000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bcdd088460a7804617d3233c5bb65df6b02bda50a8b32855be83069a6648d3f
+size 360789
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_88000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_88000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..1a4bfe268ddd1042b745ca291bb86b5820b12841
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_88000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67e8ded0a775abfd26410cb5e687d63c78313613b1f012353288b09b1ea3d20c
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_88000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_88000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..7ba9b0b47e59b7250c2dde4a4845115441cadd75
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_88000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91cf9a2f26eb8308da986e9790d74f596ddebfa725277dd27fd6a15ac765bf39
+size 363226
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_90000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_90000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..31eec8a14c9eae018b8b7b478b767dc372ffc401
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_90000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0929451a86f1b1e6abd7a3faa0473ace4fa0066f451836bd2eea35cf83c450b1
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_90000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_90000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..a4f1be3b9389d2eac2fd1a6f5763673bfe131994
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_90000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31e0d48c203f5aac06ee01ea9794bcf8c612041387331cd3d253a0437b68427c
+size 363251
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_92000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_92000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..0aeeb1c58e151048548f5c70a079989c90fc99a8
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_92000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d84715a787a7602be064d36589980d1bb18f77f012ff7d757b01a3a5299a4f61
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_92000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_92000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..b77b14b627e1660607e0276f0619cbba869e2fda
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_92000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b87ee2ba737d9da3f63a8fb5d51eeb8664e4c36561d821c2bddf7b382280e483
+size 363132
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_94000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_94000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..e61c531e0d3e5411262f7e24004f3f1390138af0
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_94000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce235ccd552b387aa5f6d179d28894b6de0339107c9fc9328b770841c180d83e
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_94000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_94000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..1f29eb06d515bd5d1409eba13990a7ee8a97511f
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_94000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcabdbe0b81c7f43c7b06873e2d7bda0df7eecfa4bac35bb0b0c5e779c9d324a
+size 361390
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_96000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_96000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..e764279b6be1cb832b64f8b5866a5d2a473681de
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_96000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bec96a8b51153bc1b9188030a8b0073726e9720e354e7527ae7758e5b2edd08
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_96000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_96000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..f4048620c874644921dda67fcca6a1dd2f855331
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_96000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81948cf4f8a2a728778b7c822e0399945d76c3a4c78553c2f542dc4d10ea246f
+size 363008
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_98000/sample.npy b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_98000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..70aad5783a5b8f9cee2d0c73f0f01375bb022c93
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_98000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04794c3f47e172d028d88dae9d98cdbdbe36797f5b7a93b727f4dc0f7f4bce9b
+size 983168
diff --git a/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_98000/sample.png b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_98000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..41ad3b7cf01b56cb6a8f93f8256f7339b1549b98
--- /dev/null
+++ b/dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_98000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6523903f827a156c49eb67075d227c43659f9726e4f3f1829fcb61920bc4f11
+size 361226