diff --git a/.gitattributes b/.gitattributes
index c94b5765ac764b38ba5af84de8701df737fbef44..43b72edaac2868cf6c431bf526ccf64220038fe1 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -1016,3 +1016,36 @@ dpdm/mnist_28_eps1.0trainval-2024-10-23-00-58-27/train/samples/iter_62000/sample
 dpdm/mnist_28_eps1.0trainval-2024-10-23-00-58-27/train/samples/iter_64000/sample.png filter=lfs diff=lfs merge=lfs -text
 dpdm/mnist_28_eps1.0trainval-2024-10-23-00-58-27/train/samples/iter_66000/sample.png filter=lfs diff=lfs merge=lfs -text
 dpdm/mnist_28_eps1.0trainval-2024-10-23-00-58-27/train/samples/iter_8000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_10000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_12000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_14000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_16000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_18000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_2000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_20000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_22000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_24000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_26000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_28000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_30000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_32000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_34000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_36000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_38000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_4000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_40000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_42000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_44000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_46000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_48000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_50000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_52000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_54000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_56000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_58000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_6000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_60000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_62000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_64000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_66000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_8000/sample.png filter=lfs diff=lfs merge=lfs -text
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/stdout.txt b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/stdout.txt
new file mode 100644
index 0000000000000000000000000000000000000000..57c7d1a8f6a47de466ef8eda2de6efa3fd7189bd
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/stdout.txt
@@ -0,0 +1,1379 @@
+INFO - utils.py - 2024-10-23 19:31:20,330 - {'setup': {'method': 'dpsgd-diffusion', 'run_type': 'torchmp', 'n_gpus_per_node': 4, 'n_nodes': 1, 'node_rank': 0, 'master_address': '127.0.0.1', 'master_port': 6025, 'omp_n_threads': 8, 'workdir': 'exp/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12', 'local_rank': 0, 'global_rank': 0, 'global_size': 4, 'root_folder': '.'}, 'public_data': {'name': None, 'num_channels': 1, 'resolution': 28, 'n_classes': 1000, 'train_path': 'dataset/imagenet/imagenet_32', 'selective': {'ratio': 1.0}}, 'sensitive_data': {'name': 'fmnist', 'num_channels': 1, 'resolution': 28, 'n_classes': 10, 'train_path': 'dataset/fmnist/train_28.zip', 'test_path': 'dataset/fmnist/test_28.zip', 'fid_stats': 'dataset/fmnist/fid_stats_28.npz', 'train_num': 'val'}, 'model': {'ckpt': None, 'denoiser_name': 'edm', 'denoiser_network': 'song', 'ema_rate': 0.999, 'network': {'image_size': 28, 'num_in_channels': 1, 'num_out_channels': 1, 'label_dim': 10, 'attn_resolutions': [14], 'ch_mult': [2, 2]}, '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': 'edm', 's_churn': 50, 's_min': 0.025, 's_max': 50, 'num_steps': 1000, 'tmin': 0.002, 'tmax': 80.0, 'rho': 7.0, 'guid_scale': 1.0}, 'sampler_acc': {'type': 'edm', 's_churn': 10, 's_min': 0.025, 's_max': 50, 'num_steps': 1000, 'tmin': 0.002, 'tmax': 80.0, 'rho': 7.0, 'guid_scale': 0.0, 'labels': 10}, 'local_rank': 0, 'global_rank': 0, 'global_size': 4, 'fid_stats': 'dataset/fmnist/fid_stats_28.npz'}, 'pretrain': {'log_dir': 'exp/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/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': 10}}, 'train': {'log_dir': 'exp/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/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': 10}, 'dp': {'sdq': None, 'privacy_history': [[5, 0.1, 75]], 'alpha_num': 0, 'max_grad_norm': 1.0, 'delta': 1e-05, 'epsilon': 10.0, 'max_physical_batch_size': 8192, 'n_splits': 32}}, 'gen': {'data_num': 60000, 'batch_size': 1000, 'log_dir': 'exp/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/gen'}, 'eval': {'batch_size': 1000}}
+INFO - dataset_loader.py - 2024-10-23 19:31:21,935 - delta is reset as 1.6657508770018431e-06
+INFO - dpsgd_diffusion.py - 2024-10-23 19:31:24,634 - Number of trainable parameters in model: 0
+INFO - dpsgd_diffusion.py - 2024-10-23 19:31:24,634 - Number of total epochs: 150
+INFO - dpsgd_diffusion.py - 2024-10-23 19:31:24,634 - Starting training at step 0
+INFO - dpsgd_diffusion.py - 2024-10-23 19:34:15,295 - Loss: 1.1760, step: 100
+INFO - dpsgd_diffusion.py - 2024-10-23 19:35:58,441 - Loss: 1.0597, step: 200
+INFO - dpsgd_diffusion.py - 2024-10-23 19:37:29,056 - Loss: 1.0022, step: 300
+INFO - dpsgd_diffusion.py - 2024-10-23 19:39:02,782 - Loss: 0.9862, step: 400
+INFO - dpsgd_diffusion.py - 2024-10-23 19:39:44,891 - Eps-value after 1 epochs: 0.8691
+INFO - dpsgd_diffusion.py - 2024-10-23 19:40:29,987 - Loss: 0.9323, step: 500
+INFO - dpsgd_diffusion.py - 2024-10-23 19:42:10,072 - Loss: 0.9219, step: 600
+INFO - dpsgd_diffusion.py - 2024-10-23 19:43:45,852 - Loss: 0.8940, step: 700
+INFO - dpsgd_diffusion.py - 2024-10-23 19:45:19,718 - Loss: 0.8599, step: 800
+INFO - dpsgd_diffusion.py - 2024-10-23 19:46:48,080 - Eps-value after 2 epochs: 1.1293
+INFO - dpsgd_diffusion.py - 2024-10-23 19:46:51,087 - Loss: 0.7819, step: 900
+INFO - dpsgd_diffusion.py - 2024-10-23 19:48:21,864 - Loss: 0.7190, step: 1000
+INFO - dpsgd_diffusion.py - 2024-10-23 19:49:58,840 - Loss: 0.6796, step: 1100
+INFO - dpsgd_diffusion.py - 2024-10-23 19:51:19,337 - Loss: 0.6542, step: 1200
+INFO - dpsgd_diffusion.py - 2024-10-23 19:52:58,026 - Loss: 0.6071, step: 1300
+INFO - dpsgd_diffusion.py - 2024-10-23 19:53:35,882 - Eps-value after 3 epochs: 1.3393
+INFO - dpsgd_diffusion.py - 2024-10-23 19:54:22,641 - Loss: 0.6004, step: 1400
+INFO - dpsgd_diffusion.py - 2024-10-23 19:55:48,937 - Loss: 0.5613, step: 1500
+INFO - dpsgd_diffusion.py - 2024-10-23 19:57:24,331 - Loss: 0.5503, step: 1600
+INFO - dpsgd_diffusion.py - 2024-10-23 19:59:00,650 - Loss: 0.5595, step: 1700
+INFO - dpsgd_diffusion.py - 2024-10-23 20:00:33,883 - Eps-value after 4 epochs: 1.5222
+INFO - dpsgd_diffusion.py - 2024-10-23 20:00:42,567 - Loss: 0.4926, step: 1800
+INFO - dpsgd_diffusion.py - 2024-10-23 20:02:20,469 - Loss: 0.4859, step: 1900
+INFO - dpsgd_diffusion.py - 2024-10-23 20:03:56,926 - Loss: 0.4726, step: 2000
+INFO - dpsgd_diffusion.py - 2024-10-23 20:03:57,228 - Saving snapshot checkpoint and sampling single batch at iteration 2000.
+WARNING - image.py - 2024-10-23 20:03:59,357 - 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 - 2024-10-23 20:04:24,422 - FID at iteration 2000: 193.119017
+INFO - dpsgd_diffusion.py - 2024-10-23 20:05:55,694 - Loss: 0.4620, step: 2100
+INFO - dpsgd_diffusion.py - 2024-10-23 20:07:21,240 - Loss: 0.4672, step: 2200
+INFO - dpsgd_diffusion.py - 2024-10-23 20:08:00,935 - Eps-value after 5 epochs: 1.6851
+INFO - dpsgd_diffusion.py - 2024-10-23 20:08:55,276 - Loss: 0.4542, step: 2300
+INFO - dpsgd_diffusion.py - 2024-10-23 20:10:30,810 - Loss: 0.4554, step: 2400
+INFO - dpsgd_diffusion.py - 2024-10-23 20:12:06,291 - Loss: 0.4148, step: 2500
+INFO - dpsgd_diffusion.py - 2024-10-23 20:13:28,877 - Loss: 0.3863, step: 2600
+INFO - dpsgd_diffusion.py - 2024-10-23 20:14:53,533 - Eps-value after 6 epochs: 1.8363
+INFO - dpsgd_diffusion.py - 2024-10-23 20:15:04,157 - Loss: 0.3808, step: 2700
+INFO - dpsgd_diffusion.py - 2024-10-23 20:16:23,817 - Loss: 0.4269, step: 2800
+INFO - dpsgd_diffusion.py - 2024-10-23 20:17:39,052 - Loss: 0.3634, step: 2900
+INFO - dpsgd_diffusion.py - 2024-10-23 20:18:59,662 - Loss: 0.4043, step: 3000
+INFO - dpsgd_diffusion.py - 2024-10-23 20:20:16,233 - Loss: 0.3697, step: 3100
+INFO - dpsgd_diffusion.py - 2024-10-23 20:20:45,852 - Eps-value after 7 epochs: 1.9739
+INFO - dpsgd_diffusion.py - 2024-10-23 20:21:38,680 - Loss: 0.3340, step: 3200
+INFO - dpsgd_diffusion.py - 2024-10-23 20:23:02,984 - Loss: 0.3775, step: 3300
+INFO - dpsgd_diffusion.py - 2024-10-23 20:24:22,076 - Loss: 0.3583, step: 3400
+INFO - dpsgd_diffusion.py - 2024-10-23 20:25:39,742 - Loss: 0.3069, step: 3500
+INFO - dpsgd_diffusion.py - 2024-10-23 20:26:49,933 - Eps-value after 8 epochs: 2.1046
+INFO - dpsgd_diffusion.py - 2024-10-23 20:27:02,756 - Loss: 0.3370, step: 3600
+INFO - dpsgd_diffusion.py - 2024-10-23 20:28:23,276 - Loss: 0.3371, step: 3700
+INFO - dpsgd_diffusion.py - 2024-10-23 20:29:51,407 - Loss: 0.3406, step: 3800
+INFO - dpsgd_diffusion.py - 2024-10-23 20:31:16,281 - Loss: 0.3096, step: 3900
+INFO - dpsgd_diffusion.py - 2024-10-23 20:32:45,489 - Loss: 0.3297, step: 4000
+INFO - dpsgd_diffusion.py - 2024-10-23 20:32:45,505 - Saving snapshot checkpoint and sampling single batch at iteration 4000.
+WARNING - image.py - 2024-10-23 20:32:46,054 - 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 - 2024-10-23 20:33:00,424 - FID at iteration 4000: 90.058311
+INFO - dpsgd_diffusion.py - 2024-10-23 20:33:31,869 - Eps-value after 9 epochs: 2.2283
+INFO - dpsgd_diffusion.py - 2024-10-23 20:34:29,960 - Loss: 0.2970, step: 4100
+INFO - dpsgd_diffusion.py - 2024-10-23 20:35:58,702 - Loss: 0.3294, step: 4200
+INFO - dpsgd_diffusion.py - 2024-10-23 20:37:30,533 - Loss: 0.3084, step: 4300
+INFO - dpsgd_diffusion.py - 2024-10-23 20:39:00,745 - Loss: 0.3234, step: 4400
+INFO - dpsgd_diffusion.py - 2024-10-23 20:40:14,074 - Eps-value after 10 epochs: 2.3462
+INFO - dpsgd_diffusion.py - 2024-10-23 20:40:32,749 - Loss: 0.2667, step: 4500
+INFO - dpsgd_diffusion.py - 2024-10-23 20:42:02,838 - Loss: 0.3024, step: 4600
+INFO - dpsgd_diffusion.py - 2024-10-23 20:43:35,461 - Loss: 0.3010, step: 4700
+INFO - dpsgd_diffusion.py - 2024-10-23 20:44:55,928 - Loss: 0.3358, step: 4800
+INFO - dpsgd_diffusion.py - 2024-10-23 20:46:29,734 - Loss: 0.3116, step: 4900
+INFO - dpsgd_diffusion.py - 2024-10-23 20:46:59,559 - Eps-value after 11 epochs: 2.4591
+INFO - dpsgd_diffusion.py - 2024-10-23 20:48:06,457 - Loss: 0.2881, step: 5000
+INFO - dpsgd_diffusion.py - 2024-10-23 20:49:32,392 - Loss: 0.2911, step: 5100
+INFO - dpsgd_diffusion.py - 2024-10-23 20:51:03,722 - Loss: 0.2854, step: 5200
+INFO - dpsgd_diffusion.py - 2024-10-23 20:52:29,405 - Loss: 0.3147, step: 5300
+INFO - dpsgd_diffusion.py - 2024-10-23 20:53:28,196 - Eps-value after 12 epochs: 2.5675
+INFO - dpsgd_diffusion.py - 2024-10-23 20:53:49,599 - Loss: 0.2766, step: 5400
+INFO - dpsgd_diffusion.py - 2024-10-23 20:55:20,283 - Loss: 0.2912, step: 5500
+INFO - dpsgd_diffusion.py - 2024-10-23 20:56:58,047 - Loss: 0.3034, step: 5600
+INFO - dpsgd_diffusion.py - 2024-10-23 20:58:33,551 - Loss: 0.2817, step: 5700
+INFO - dpsgd_diffusion.py - 2024-10-23 21:00:06,794 - Loss: 0.3140, step: 5800
+INFO - dpsgd_diffusion.py - 2024-10-23 21:00:27,606 - Eps-value after 13 epochs: 2.6723
+INFO - dpsgd_diffusion.py - 2024-10-23 21:01:36,155 - Loss: 0.2719, step: 5900
+INFO - dpsgd_diffusion.py - 2024-10-23 21:03:11,126 - Loss: 0.3207, step: 6000
+INFO - dpsgd_diffusion.py - 2024-10-23 21:03:11,536 - Saving snapshot checkpoint and sampling single batch at iteration 6000.
+WARNING - image.py - 2024-10-23 21:03:12,184 - 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 - 2024-10-23 21:03:27,285 - FID at iteration 6000: 61.460786
+INFO - dpsgd_diffusion.py - 2024-10-23 21:05:10,011 - Loss: 0.2796, step: 6100
+INFO - dpsgd_diffusion.py - 2024-10-23 21:06:32,857 - Loss: 0.2943, step: 6200
+INFO - dpsgd_diffusion.py - 2024-10-23 21:07:44,132 - Eps-value after 14 epochs: 2.7735
+INFO - dpsgd_diffusion.py - 2024-10-23 21:08:10,870 - Loss: 0.2762, step: 6300
+INFO - dpsgd_diffusion.py - 2024-10-23 21:09:49,566 - Loss: 0.2642, step: 6400
+INFO - dpsgd_diffusion.py - 2024-10-23 21:11:18,869 - Loss: 0.2701, step: 6500
+INFO - dpsgd_diffusion.py - 2024-10-23 21:12:53,984 - Loss: 0.2597, step: 6600
+INFO - dpsgd_diffusion.py - 2024-10-23 21:14:22,345 - Loss: 0.2757, step: 6700
+INFO - dpsgd_diffusion.py - 2024-10-23 21:14:40,524 - Eps-value after 15 epochs: 2.8716
+INFO - dpsgd_diffusion.py - 2024-10-23 21:15:49,863 - Loss: 0.2680, step: 6800
+INFO - dpsgd_diffusion.py - 2024-10-23 21:17:27,327 - Loss: 0.2630, step: 6900
+INFO - dpsgd_diffusion.py - 2024-10-23 21:18:53,742 - Loss: 0.2668, step: 7000
+INFO - dpsgd_diffusion.py - 2024-10-23 21:20:28,061 - Loss: 0.2847, step: 7100
+INFO - dpsgd_diffusion.py - 2024-10-23 21:21:27,541 - Eps-value after 16 epochs: 2.9671
+INFO - dpsgd_diffusion.py - 2024-10-23 21:21:59,419 - Loss: 0.2909, step: 7200
+INFO - dpsgd_diffusion.py - 2024-10-23 21:23:25,399 - Loss: 0.2809, step: 7300
+INFO - dpsgd_diffusion.py - 2024-10-23 21:25:02,059 - Loss: 0.3251, step: 7400
+INFO - dpsgd_diffusion.py - 2024-10-23 21:26:32,526 - Loss: 0.2589, step: 7500
+INFO - dpsgd_diffusion.py - 2024-10-23 21:27:59,503 - Loss: 0.2555, step: 7600
+INFO - dpsgd_diffusion.py - 2024-10-23 21:28:12,249 - Eps-value after 17 epochs: 3.0599
+INFO - dpsgd_diffusion.py - 2024-10-23 21:29:27,573 - Loss: 0.2709, step: 7700
+INFO - dpsgd_diffusion.py - 2024-10-23 21:30:53,345 - Loss: 0.2632, step: 7800
+INFO - dpsgd_diffusion.py - 2024-10-23 21:32:20,466 - Loss: 0.2456, step: 7900
+INFO - dpsgd_diffusion.py - 2024-10-23 21:33:43,224 - Loss: 0.3006, step: 8000
+INFO - dpsgd_diffusion.py - 2024-10-23 21:33:43,242 - Saving snapshot checkpoint and sampling single batch at iteration 8000.
+WARNING - image.py - 2024-10-23 21:33:43,747 - 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 - 2024-10-23 21:33:58,524 - FID at iteration 8000: 51.349234
+INFO - dpsgd_diffusion.py - 2024-10-23 21:34:53,066 - Eps-value after 18 epochs: 3.1505
+INFO - dpsgd_diffusion.py - 2024-10-23 21:35:25,333 - Loss: 0.2843, step: 8100
+INFO - dpsgd_diffusion.py - 2024-10-23 21:37:03,063 - Loss: 0.2911, step: 8200
+INFO - dpsgd_diffusion.py - 2024-10-23 21:38:32,621 - Loss: 0.3080, step: 8300
+INFO - dpsgd_diffusion.py - 2024-10-23 21:40:02,216 - Loss: 0.2704, step: 8400
+INFO - dpsgd_diffusion.py - 2024-10-23 21:41:23,023 - Loss: 0.2929, step: 8500
+INFO - dpsgd_diffusion.py - 2024-10-23 21:41:32,645 - Eps-value after 19 epochs: 3.2390
+INFO - dpsgd_diffusion.py - 2024-10-23 21:42:41,029 - Loss: 0.2615, step: 8600
+INFO - dpsgd_diffusion.py - 2024-10-23 21:44:01,945 - Loss: 0.2471, step: 8700
+INFO - dpsgd_diffusion.py - 2024-10-23 21:45:20,004 - Loss: 0.2735, step: 8800
+INFO - dpsgd_diffusion.py - 2024-10-23 21:46:39,806 - Loss: 0.2824, step: 8900
+INFO - dpsgd_diffusion.py - 2024-10-23 21:47:23,453 - Eps-value after 20 epochs: 3.3255
+INFO - dpsgd_diffusion.py - 2024-10-23 21:47:54,815 - Loss: 0.2850, step: 9000
+INFO - dpsgd_diffusion.py - 2024-10-23 21:49:16,593 - Loss: 0.2812, step: 9100
+INFO - dpsgd_diffusion.py - 2024-10-23 21:50:34,188 - Loss: 0.2670, step: 9200
+INFO - dpsgd_diffusion.py - 2024-10-23 21:51:55,614 - Loss: 0.2691, step: 9300
+INFO - dpsgd_diffusion.py - 2024-10-23 21:53:16,093 - Loss: 0.2614, step: 9400
+INFO - dpsgd_diffusion.py - 2024-10-23 21:53:23,904 - Eps-value after 21 epochs: 3.4101
+INFO - dpsgd_diffusion.py - 2024-10-23 21:54:43,136 - Loss: 0.2610, step: 9500
+INFO - dpsgd_diffusion.py - 2024-10-23 21:56:19,086 - Loss: 0.2793, step: 9600
+INFO - dpsgd_diffusion.py - 2024-10-23 21:57:49,578 - Loss: 0.2919, step: 9700
+INFO - dpsgd_diffusion.py - 2024-10-23 21:59:16,505 - Loss: 0.2790, step: 9800
+INFO - dpsgd_diffusion.py - 2024-10-23 22:00:06,478 - Eps-value after 22 epochs: 3.4931
+INFO - dpsgd_diffusion.py - 2024-10-23 22:00:46,443 - Loss: 0.2667, step: 9900
+INFO - dpsgd_diffusion.py - 2024-10-23 22:02:22,091 - Loss: 0.2935, step: 10000
+INFO - dpsgd_diffusion.py - 2024-10-23 22:02:22,972 - Saving snapshot checkpoint and sampling single batch at iteration 10000.
+WARNING - image.py - 2024-10-23 22:02:23,504 - 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 - 2024-10-23 22:02:38,469 - FID at iteration 10000: 45.704430
+INFO - dpsgd_diffusion.py - 2024-10-23 22:04:09,180 - Loss: 0.2635, step: 10100
+INFO - dpsgd_diffusion.py - 2024-10-23 22:05:39,927 - Loss: 0.2597, step: 10200
+INFO - dpsgd_diffusion.py - 2024-10-23 22:07:11,318 - Loss: 0.2399, step: 10300
+INFO - dpsgd_diffusion.py - 2024-10-23 22:07:15,839 - Eps-value after 23 epochs: 3.5746
+INFO - dpsgd_diffusion.py - 2024-10-23 22:08:43,129 - Loss: 0.2812, step: 10400
+INFO - dpsgd_diffusion.py - 2024-10-23 22:10:15,469 - Loss: 0.2459, step: 10500
+INFO - dpsgd_diffusion.py - 2024-10-23 22:11:49,220 - Loss: 0.2646, step: 10600
+INFO - dpsgd_diffusion.py - 2024-10-23 22:13:13,852 - Loss: 0.2533, step: 10700
+INFO - dpsgd_diffusion.py - 2024-10-23 22:14:02,260 - Eps-value after 24 epochs: 3.6546
+INFO - dpsgd_diffusion.py - 2024-10-23 22:14:51,500 - Loss: 0.2647, step: 10800
+INFO - dpsgd_diffusion.py - 2024-10-23 22:16:11,611 - Loss: 0.2289, step: 10900
+INFO - dpsgd_diffusion.py - 2024-10-23 22:17:32,761 - Loss: 0.2960, step: 11000
+INFO - dpsgd_diffusion.py - 2024-10-23 22:18:54,784 - Loss: 0.2428, step: 11100
+INFO - dpsgd_diffusion.py - 2024-10-23 22:20:24,737 - Loss: 0.2480, step: 11200
+INFO - dpsgd_diffusion.py - 2024-10-23 22:20:24,759 - Eps-value after 25 epochs: 3.7332
+INFO - dpsgd_diffusion.py - 2024-10-23 22:21:54,215 - Loss: 0.2754, step: 11300
+INFO - dpsgd_diffusion.py - 2024-10-23 22:23:20,588 - Loss: 0.2630, step: 11400
+INFO - dpsgd_diffusion.py - 2024-10-23 22:25:05,537 - Loss: 0.2630, step: 11500
+INFO - dpsgd_diffusion.py - 2024-10-23 22:26:38,230 - Loss: 0.2654, step: 11600
+INFO - dpsgd_diffusion.py - 2024-10-23 22:27:17,967 - Eps-value after 26 epochs: 3.8104
+INFO - dpsgd_diffusion.py - 2024-10-23 22:28:04,167 - Loss: 0.2963, step: 11700
+INFO - dpsgd_diffusion.py - 2024-10-23 22:29:35,797 - Loss: 0.2693, step: 11800
+INFO - dpsgd_diffusion.py - 2024-10-23 22:31:05,019 - Loss: 0.2634, step: 11900
+INFO - dpsgd_diffusion.py - 2024-10-23 22:32:31,503 - Loss: 0.2670, step: 12000
+INFO - dpsgd_diffusion.py - 2024-10-23 22:32:31,519 - Saving snapshot checkpoint and sampling single batch at iteration 12000.
+WARNING - image.py - 2024-10-23 22:32:32,039 - 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 - 2024-10-23 22:32:45,770 - FID at iteration 12000: 43.482681
+INFO - dpsgd_diffusion.py - 2024-10-23 22:34:05,448 - Eps-value after 27 epochs: 3.8864
+INFO - dpsgd_diffusion.py - 2024-10-23 22:34:09,021 - Loss: 0.2576, step: 12100
+INFO - dpsgd_diffusion.py - 2024-10-23 22:35:30,299 - Loss: 0.2910, step: 12200
+INFO - dpsgd_diffusion.py - 2024-10-23 22:37:03,232 - Loss: 0.2643, step: 12300
+INFO - dpsgd_diffusion.py - 2024-10-23 22:38:33,617 - Loss: 0.2726, step: 12400
+INFO - dpsgd_diffusion.py - 2024-10-23 22:39:58,521 - Loss: 0.2966, step: 12500
+INFO - dpsgd_diffusion.py - 2024-10-23 22:40:37,574 - Eps-value after 28 epochs: 3.9612
+INFO - dpsgd_diffusion.py - 2024-10-23 22:41:24,968 - Loss: 0.2803, step: 12600
+INFO - dpsgd_diffusion.py - 2024-10-23 22:43:04,317 - Loss: 0.2431, step: 12700
+INFO - dpsgd_diffusion.py - 2024-10-23 22:44:47,544 - Loss: 0.2394, step: 12800
+INFO - dpsgd_diffusion.py - 2024-10-23 22:46:07,705 - Loss: 0.2515, step: 12900
+INFO - dpsgd_diffusion.py - 2024-10-23 22:47:36,178 - Eps-value after 29 epochs: 4.0349
+INFO - dpsgd_diffusion.py - 2024-10-23 22:47:43,046 - Loss: 0.2464, step: 13000
+INFO - dpsgd_diffusion.py - 2024-10-23 22:49:06,577 - Loss: 0.2979, step: 13100
+INFO - dpsgd_diffusion.py - 2024-10-23 22:50:37,836 - Loss: 0.2686, step: 13200
+INFO - dpsgd_diffusion.py - 2024-10-23 22:52:08,423 - Loss: 0.2498, step: 13300
+INFO - dpsgd_diffusion.py - 2024-10-23 22:53:37,438 - Loss: 0.2453, step: 13400
+INFO - dpsgd_diffusion.py - 2024-10-23 22:54:16,971 - Eps-value after 30 epochs: 4.1076
+INFO - dpsgd_diffusion.py - 2024-10-23 22:55:13,282 - Loss: 0.2392, step: 13500
+INFO - dpsgd_diffusion.py - 2024-10-23 22:56:37,393 - Loss: 0.2652, step: 13600
+INFO - dpsgd_diffusion.py - 2024-10-23 22:57:57,444 - Loss: 0.2633, step: 13700
+INFO - dpsgd_diffusion.py - 2024-10-23 22:59:22,737 - Loss: 0.2595, step: 13800
+INFO - dpsgd_diffusion.py - 2024-10-23 23:00:42,556 - Eps-value after 31 epochs: 4.1794
+INFO - dpsgd_diffusion.py - 2024-10-23 23:00:54,671 - Loss: 0.2560, step: 13900
+INFO - dpsgd_diffusion.py - 2024-10-23 23:02:17,736 - Loss: 0.2462, step: 14000
+INFO - dpsgd_diffusion.py - 2024-10-23 23:02:17,972 - Saving snapshot checkpoint and sampling single batch at iteration 14000.
+WARNING - image.py - 2024-10-23 23:02:18,591 - 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 - 2024-10-23 23:02:33,418 - FID at iteration 14000: 40.147415
+INFO - dpsgd_diffusion.py - 2024-10-23 23:03:52,181 - Loss: 0.2520, step: 14100
+INFO - dpsgd_diffusion.py - 2024-10-23 23:05:11,561 - Loss: 0.2377, step: 14200
+INFO - dpsgd_diffusion.py - 2024-10-23 23:06:29,380 - Loss: 0.2475, step: 14300
+INFO - dpsgd_diffusion.py - 2024-10-23 23:06:57,468 - Eps-value after 32 epochs: 4.2501
+INFO - dpsgd_diffusion.py - 2024-10-23 23:07:50,593 - Loss: 0.2469, step: 14400
+INFO - dpsgd_diffusion.py - 2024-10-23 23:09:09,115 - Loss: 0.2511, step: 14500
+INFO - dpsgd_diffusion.py - 2024-10-23 23:10:27,708 - Loss: 0.2465, step: 14600
+INFO - dpsgd_diffusion.py - 2024-10-23 23:11:45,466 - Loss: 0.2370, step: 14700
+INFO - dpsgd_diffusion.py - 2024-10-23 23:12:55,563 - Eps-value after 33 epochs: 4.3198
+INFO - dpsgd_diffusion.py - 2024-10-23 23:13:08,233 - Loss: 0.2628, step: 14800
+INFO - dpsgd_diffusion.py - 2024-10-23 23:14:26,147 - Loss: 0.2796, step: 14900
+INFO - dpsgd_diffusion.py - 2024-10-23 23:15:57,391 - Loss: 0.2518, step: 15000
+INFO - dpsgd_diffusion.py - 2024-10-23 23:17:24,278 - Loss: 0.2411, step: 15100
+INFO - dpsgd_diffusion.py - 2024-10-23 23:18:45,873 - Loss: 0.2330, step: 15200
+INFO - dpsgd_diffusion.py - 2024-10-23 23:19:18,376 - Eps-value after 34 epochs: 4.3890
+INFO - dpsgd_diffusion.py - 2024-10-23 23:20:18,010 - Loss: 0.2373, step: 15300
+INFO - dpsgd_diffusion.py - 2024-10-23 23:21:47,944 - Loss: 0.2439, step: 15400
+INFO - dpsgd_diffusion.py - 2024-10-23 23:23:16,236 - Loss: 0.2362, step: 15500
+INFO - dpsgd_diffusion.py - 2024-10-23 23:24:48,879 - Loss: 0.2588, step: 15600
+INFO - dpsgd_diffusion.py - 2024-10-23 23:25:56,391 - Eps-value after 35 epochs: 4.4570
+INFO - dpsgd_diffusion.py - 2024-10-23 23:26:12,126 - Loss: 0.2564, step: 15700
+INFO - dpsgd_diffusion.py - 2024-10-23 23:27:34,143 - Loss: 0.2631, step: 15800
+INFO - dpsgd_diffusion.py - 2024-10-23 23:29:00,382 - Loss: 0.2655, step: 15900
+INFO - dpsgd_diffusion.py - 2024-10-23 23:30:42,243 - Loss: 0.2529, step: 16000
+INFO - dpsgd_diffusion.py - 2024-10-23 23:30:42,259 - Saving snapshot checkpoint and sampling single batch at iteration 16000.
+WARNING - image.py - 2024-10-23 23:30:42,767 - 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 - 2024-10-23 23:30:57,698 - FID at iteration 16000: 37.904503
+INFO - dpsgd_diffusion.py - 2024-10-23 23:32:27,379 - Loss: 0.2653, step: 16100
+INFO - dpsgd_diffusion.py - 2024-10-23 23:32:50,281 - Eps-value after 36 epochs: 4.5243
+INFO - dpsgd_diffusion.py - 2024-10-23 23:33:47,108 - Loss: 0.2511, step: 16200
+INFO - dpsgd_diffusion.py - 2024-10-23 23:35:11,745 - Loss: 0.2492, step: 16300
+INFO - dpsgd_diffusion.py - 2024-10-23 23:36:34,841 - Loss: 0.2615, step: 16400
+INFO - dpsgd_diffusion.py - 2024-10-23 23:38:00,281 - Loss: 0.2533, step: 16500
+INFO - dpsgd_diffusion.py - 2024-10-23 23:39:06,453 - Eps-value after 37 epochs: 4.5911
+INFO - dpsgd_diffusion.py - 2024-10-23 23:39:26,747 - Loss: 0.2594, step: 16600
+INFO - dpsgd_diffusion.py - 2024-10-23 23:41:01,191 - Loss: 0.2306, step: 16700
+INFO - dpsgd_diffusion.py - 2024-10-23 23:42:33,284 - Loss: 0.2359, step: 16800
+INFO - dpsgd_diffusion.py - 2024-10-23 23:43:59,863 - Loss: 0.2603, step: 16900
+INFO - dpsgd_diffusion.py - 2024-10-23 23:45:34,701 - Loss: 0.2508, step: 17000
+INFO - dpsgd_diffusion.py - 2024-10-23 23:45:59,901 - Eps-value after 38 epochs: 4.6567
+INFO - dpsgd_diffusion.py - 2024-10-23 23:47:08,059 - Loss: 0.2542, step: 17100
+INFO - dpsgd_diffusion.py - 2024-10-23 23:48:44,537 - Loss: 0.2704, step: 17200
+INFO - dpsgd_diffusion.py - 2024-10-23 23:50:04,589 - Loss: 0.2418, step: 17300
+INFO - dpsgd_diffusion.py - 2024-10-23 23:51:31,514 - Loss: 0.2793, step: 17400
+INFO - dpsgd_diffusion.py - 2024-10-23 23:52:35,584 - Eps-value after 39 epochs: 4.7221
+INFO - dpsgd_diffusion.py - 2024-10-23 23:53:02,108 - Loss: 0.2307, step: 17500
+INFO - dpsgd_diffusion.py - 2024-10-23 23:54:27,278 - Loss: 0.2519, step: 17600
+INFO - dpsgd_diffusion.py - 2024-10-23 23:56:03,412 - Loss: 0.2413, step: 17700
+INFO - dpsgd_diffusion.py - 2024-10-23 23:57:25,162 - Loss: 0.2261, step: 17800
+INFO - dpsgd_diffusion.py - 2024-10-23 23:58:48,971 - Loss: 0.2453, step: 17900
+INFO - dpsgd_diffusion.py - 2024-10-23 23:59:06,335 - Eps-value after 40 epochs: 4.7863
+INFO - dpsgd_diffusion.py - 2024-10-24 00:00:12,054 - Loss: 0.2354, step: 18000
+INFO - dpsgd_diffusion.py - 2024-10-24 00:00:12,252 - Saving snapshot checkpoint and sampling single batch at iteration 18000.
+WARNING - image.py - 2024-10-24 00:00:12,772 - 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 00:00:27,285 - FID at iteration 18000: 35.896712
+INFO - dpsgd_diffusion.py - 2024-10-24 00:01:55,775 - Loss: 0.2503, step: 18100
+INFO - dpsgd_diffusion.py - 2024-10-24 00:03:27,067 - Loss: 0.2497, step: 18200
+INFO - dpsgd_diffusion.py - 2024-10-24 00:05:00,790 - Loss: 0.2483, step: 18300
+INFO - dpsgd_diffusion.py - 2024-10-24 00:06:01,090 - Eps-value after 41 epochs: 4.8503
+INFO - dpsgd_diffusion.py - 2024-10-24 00:06:31,407 - Loss: 0.2348, step: 18400
+INFO - dpsgd_diffusion.py - 2024-10-24 00:08:11,484 - Loss: 0.2456, step: 18500
+INFO - dpsgd_diffusion.py - 2024-10-24 00:09:38,193 - Loss: 0.2396, step: 18600
+INFO - dpsgd_diffusion.py - 2024-10-24 00:11:08,114 - Loss: 0.2438, step: 18700
+INFO - dpsgd_diffusion.py - 2024-10-24 00:12:34,832 - Loss: 0.2598, step: 18800
+INFO - dpsgd_diffusion.py - 2024-10-24 00:12:48,677 - Eps-value after 42 epochs: 4.9133
+INFO - dpsgd_diffusion.py - 2024-10-24 00:14:06,207 - Loss: 0.2499, step: 18900
+INFO - dpsgd_diffusion.py - 2024-10-24 00:15:40,722 - Loss: 0.2444, step: 19000
+INFO - dpsgd_diffusion.py - 2024-10-24 00:17:22,181 - Loss: 0.2576, step: 19100
+INFO - dpsgd_diffusion.py - 2024-10-24 00:18:49,624 - Loss: 0.2599, step: 19200
+INFO - dpsgd_diffusion.py - 2024-10-24 00:19:48,473 - Eps-value after 43 epochs: 4.9761
+INFO - dpsgd_diffusion.py - 2024-10-24 00:20:18,894 - Loss: 0.2335, step: 19300
+INFO - dpsgd_diffusion.py - 2024-10-24 00:21:49,056 - Loss: 0.2261, step: 19400
+INFO - dpsgd_diffusion.py - 2024-10-24 00:23:08,384 - Loss: 0.2693, step: 19500
+INFO - dpsgd_diffusion.py - 2024-10-24 00:24:24,883 - Loss: 0.2835, step: 19600
+INFO - dpsgd_diffusion.py - 2024-10-24 00:25:46,501 - Loss: 0.2529, step: 19700
+INFO - dpsgd_diffusion.py - 2024-10-24 00:25:56,143 - Eps-value after 44 epochs: 5.0379
+INFO - dpsgd_diffusion.py - 2024-10-24 00:27:03,939 - Loss: 0.2571, step: 19800
+INFO - dpsgd_diffusion.py - 2024-10-24 00:28:25,747 - Loss: 0.2569, step: 19900
+INFO - dpsgd_diffusion.py - 2024-10-24 00:29:42,834 - Loss: 0.2413, step: 20000
+INFO - dpsgd_diffusion.py - 2024-10-24 00:29:42,849 - Saving snapshot checkpoint and sampling single batch at iteration 20000.
+WARNING - image.py - 2024-10-24 00:29:43,375 - 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 00:29:57,832 - FID at iteration 20000: 34.595416
+INFO - dpsgd_diffusion.py - 2024-10-24 00:31:15,912 - Loss: 0.2402, step: 20100
+INFO - dpsgd_diffusion.py - 2024-10-24 00:32:03,956 - Eps-value after 45 epochs: 5.0996
+INFO - dpsgd_diffusion.py - 2024-10-24 00:32:35,806 - Loss: 0.2254, step: 20200
+INFO - dpsgd_diffusion.py - 2024-10-24 00:33:56,962 - Loss: 0.2511, step: 20300
+INFO - dpsgd_diffusion.py - 2024-10-24 00:35:21,796 - Loss: 0.2335, step: 20400
+INFO - dpsgd_diffusion.py - 2024-10-24 00:36:45,945 - Loss: 0.2253, step: 20500
+INFO - dpsgd_diffusion.py - 2024-10-24 00:38:17,408 - Loss: 0.2456, step: 20600
+INFO - dpsgd_diffusion.py - 2024-10-24 00:38:23,508 - Eps-value after 46 epochs: 5.1602
+INFO - dpsgd_diffusion.py - 2024-10-24 00:39:37,069 - Loss: 0.2495, step: 20700
+INFO - dpsgd_diffusion.py - 2024-10-24 00:41:03,386 - Loss: 0.2469, step: 20800
+INFO - dpsgd_diffusion.py - 2024-10-24 00:42:30,349 - Loss: 0.2719, step: 20900
+INFO - dpsgd_diffusion.py - 2024-10-24 00:44:08,396 - Loss: 0.2446, step: 21000
+INFO - dpsgd_diffusion.py - 2024-10-24 00:44:55,706 - Eps-value after 47 epochs: 5.2207
+INFO - dpsgd_diffusion.py - 2024-10-24 00:45:38,330 - Loss: 0.2428, step: 21100
+INFO - dpsgd_diffusion.py - 2024-10-24 00:47:12,675 - Loss: 0.2392, step: 21200
+INFO - dpsgd_diffusion.py - 2024-10-24 00:48:45,136 - Loss: 0.2203, step: 21300
+INFO - dpsgd_diffusion.py - 2024-10-24 00:50:20,496 - Loss: 0.2427, step: 21400
+INFO - dpsgd_diffusion.py - 2024-10-24 00:51:57,302 - Loss: 0.2425, step: 21500
+INFO - dpsgd_diffusion.py - 2024-10-24 00:52:00,542 - Eps-value after 48 epochs: 5.2804
+INFO - dpsgd_diffusion.py - 2024-10-24 00:53:24,204 - Loss: 0.2308, step: 21600
+INFO - dpsgd_diffusion.py - 2024-10-24 00:54:58,750 - Loss: 0.2448, step: 21700
+INFO - dpsgd_diffusion.py - 2024-10-24 00:56:34,755 - Loss: 0.2231, step: 21800
+INFO - dpsgd_diffusion.py - 2024-10-24 00:58:11,221 - Loss: 0.2370, step: 21900
+INFO - dpsgd_diffusion.py - 2024-10-24 00:58:53,958 - Eps-value after 49 epochs: 5.3397
+INFO - dpsgd_diffusion.py - 2024-10-24 00:59:34,112 - Loss: 0.2523, step: 22000
+INFO - dpsgd_diffusion.py - 2024-10-24 00:59:34,477 - Saving snapshot checkpoint and sampling single batch at iteration 22000.
+WARNING - image.py - 2024-10-24 00:59:35,011 - 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 00:59:49,303 - FID at iteration 22000: 33.657468
+INFO - dpsgd_diffusion.py - 2024-10-24 01:01:24,557 - Loss: 0.2291, step: 22100
+INFO - dpsgd_diffusion.py - 2024-10-24 01:02:51,460 - Loss: 0.2913, step: 22200
+INFO - dpsgd_diffusion.py - 2024-10-24 01:04:15,931 - Loss: 0.2282, step: 22300
+INFO - dpsgd_diffusion.py - 2024-10-24 01:05:43,511 - Loss: 0.2406, step: 22400
+INFO - dpsgd_diffusion.py - 2024-10-24 01:05:43,537 - Eps-value after 50 epochs: 5.3989
+INFO - dpsgd_diffusion.py - 2024-10-24 01:07:14,538 - Loss: 0.2460, step: 22500
+INFO - dpsgd_diffusion.py - 2024-10-24 01:08:43,175 - Loss: 0.2389, step: 22600
+INFO - dpsgd_diffusion.py - 2024-10-24 01:10:08,719 - Loss: 0.2523, step: 22700
+INFO - dpsgd_diffusion.py - 2024-10-24 01:11:46,280 - Loss: 0.2650, step: 22800
+INFO - dpsgd_diffusion.py - 2024-10-24 01:12:24,422 - Eps-value after 51 epochs: 5.4569
+INFO - dpsgd_diffusion.py - 2024-10-24 01:13:08,383 - Loss: 0.2165, step: 22900
+INFO - dpsgd_diffusion.py - 2024-10-24 01:14:36,441 - Loss: 0.2518, step: 23000
+INFO - dpsgd_diffusion.py - 2024-10-24 01:16:09,704 - Loss: 0.2325, step: 23100
+INFO - dpsgd_diffusion.py - 2024-10-24 01:17:41,434 - Loss: 0.2481, step: 23200
+INFO - dpsgd_diffusion.py - 2024-10-24 01:19:06,985 - Eps-value after 52 epochs: 5.5149
+INFO - dpsgd_diffusion.py - 2024-10-24 01:19:09,907 - Loss: 0.2574, step: 23300
+INFO - dpsgd_diffusion.py - 2024-10-24 01:20:43,715 - Loss: 0.2258, step: 23400
+INFO - dpsgd_diffusion.py - 2024-10-24 01:22:14,534 - Loss: 0.2510, step: 23500
+INFO - dpsgd_diffusion.py - 2024-10-24 01:23:41,732 - Loss: 0.2107, step: 23600
+INFO - dpsgd_diffusion.py - 2024-10-24 01:25:14,683 - Loss: 0.2625, step: 23700
+INFO - dpsgd_diffusion.py - 2024-10-24 01:25:49,089 - Eps-value after 53 epochs: 5.5725
+INFO - dpsgd_diffusion.py - 2024-10-24 01:26:33,618 - Loss: 0.2576, step: 23800
+INFO - dpsgd_diffusion.py - 2024-10-24 01:28:04,968 - Loss: 0.2363, step: 23900
+INFO - dpsgd_diffusion.py - 2024-10-24 01:29:38,476 - Loss: 0.2436, step: 24000
+INFO - dpsgd_diffusion.py - 2024-10-24 01:29:38,495 - Saving snapshot checkpoint and sampling single batch at iteration 24000.
+WARNING - image.py - 2024-10-24 01:29:39,195 - 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 01:29:53,777 - FID at iteration 24000: 31.545023
+INFO - dpsgd_diffusion.py - 2024-10-24 01:31:30,401 - Loss: 0.2413, step: 24100
+INFO - dpsgd_diffusion.py - 2024-10-24 01:32:58,187 - Eps-value after 54 epochs: 5.6293
+INFO - dpsgd_diffusion.py - 2024-10-24 01:33:04,535 - Loss: 0.2538, step: 24200
+INFO - dpsgd_diffusion.py - 2024-10-24 01:34:30,513 - Loss: 0.2362, step: 24300
+INFO - dpsgd_diffusion.py - 2024-10-24 01:36:07,395 - Loss: 0.2315, step: 24400
+INFO - dpsgd_diffusion.py - 2024-10-24 01:37:48,061 - Loss: 0.2452, step: 24500
+INFO - dpsgd_diffusion.py - 2024-10-24 01:39:21,082 - Loss: 0.2489, step: 24600
+INFO - dpsgd_diffusion.py - 2024-10-24 01:39:54,091 - Eps-value after 55 epochs: 5.6861
+INFO - dpsgd_diffusion.py - 2024-10-24 01:40:52,020 - Loss: 0.2648, step: 24700
+INFO - dpsgd_diffusion.py - 2024-10-24 01:42:30,290 - Loss: 0.2287, step: 24800
+INFO - dpsgd_diffusion.py - 2024-10-24 01:44:02,982 - Loss: 0.2553, step: 24900
+INFO - dpsgd_diffusion.py - 2024-10-24 01:45:36,348 - Loss: 0.2641, step: 25000
+INFO - dpsgd_diffusion.py - 2024-10-24 01:47:02,979 - Eps-value after 56 epochs: 5.7424
+INFO - dpsgd_diffusion.py - 2024-10-24 01:47:11,858 - Loss: 0.2552, step: 25100
+INFO - dpsgd_diffusion.py - 2024-10-24 01:48:31,854 - Loss: 0.2685, step: 25200
+INFO - dpsgd_diffusion.py - 2024-10-24 01:49:49,190 - Loss: 0.2422, step: 25300
+INFO - dpsgd_diffusion.py - 2024-10-24 01:51:04,631 - Loss: 0.2462, step: 25400
+INFO - dpsgd_diffusion.py - 2024-10-24 01:52:23,495 - Loss: 0.2551, step: 25500
+INFO - dpsgd_diffusion.py - 2024-10-24 01:52:51,729 - Eps-value after 57 epochs: 5.7980
+INFO - dpsgd_diffusion.py - 2024-10-24 01:53:41,110 - Loss: 0.2515, step: 25600
+INFO - dpsgd_diffusion.py - 2024-10-24 01:55:03,131 - Loss: 0.2443, step: 25700
+INFO - dpsgd_diffusion.py - 2024-10-24 01:56:19,667 - Loss: 0.2278, step: 25800
+INFO - dpsgd_diffusion.py - 2024-10-24 01:57:39,514 - Loss: 0.2469, step: 25900
+INFO - dpsgd_diffusion.py - 2024-10-24 01:58:44,537 - Eps-value after 58 epochs: 5.8536
+INFO - dpsgd_diffusion.py - 2024-10-24 01:58:56,614 - Loss: 0.2289, step: 26000
+INFO - dpsgd_diffusion.py - 2024-10-24 01:58:56,672 - Saving snapshot checkpoint and sampling single batch at iteration 26000.
+WARNING - image.py - 2024-10-24 01:58:57,288 - 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 01:59:11,730 - FID at iteration 26000: 31.352700
+INFO - dpsgd_diffusion.py - 2024-10-24 02:00:34,189 - Loss: 0.2491, step: 26100
+INFO - dpsgd_diffusion.py - 2024-10-24 02:01:56,771 - Loss: 0.2309, step: 26200
+INFO - dpsgd_diffusion.py - 2024-10-24 02:03:34,421 - Loss: 0.2467, step: 26300
+INFO - dpsgd_diffusion.py - 2024-10-24 02:05:01,871 - Loss: 0.2330, step: 26400
+INFO - dpsgd_diffusion.py - 2024-10-24 02:05:32,151 - Eps-value after 59 epochs: 5.9088
+INFO - dpsgd_diffusion.py - 2024-10-24 02:06:36,277 - Loss: 0.2552, step: 26500
+INFO - dpsgd_diffusion.py - 2024-10-24 02:08:10,543 - Loss: 0.2462, step: 26600
+INFO - dpsgd_diffusion.py - 2024-10-24 02:09:35,957 - Loss: 0.2586, step: 26700
+INFO - dpsgd_diffusion.py - 2024-10-24 02:11:13,322 - Loss: 0.2459, step: 26800
+INFO - dpsgd_diffusion.py - 2024-10-24 02:12:25,731 - Eps-value after 60 epochs: 5.9632
+INFO - dpsgd_diffusion.py - 2024-10-24 02:12:43,028 - Loss: 0.2339, step: 26900
+INFO - dpsgd_diffusion.py - 2024-10-24 02:14:07,473 - Loss: 0.2538, step: 27000
+INFO - dpsgd_diffusion.py - 2024-10-24 02:15:37,386 - Loss: 0.2457, step: 27100
+INFO - dpsgd_diffusion.py - 2024-10-24 02:17:03,756 - Loss: 0.2197, step: 27200
+INFO - dpsgd_diffusion.py - 2024-10-24 02:18:31,618 - Loss: 0.2546, step: 27300
+INFO - dpsgd_diffusion.py - 2024-10-24 02:18:54,637 - Eps-value after 61 epochs: 6.0175
+INFO - dpsgd_diffusion.py - 2024-10-24 02:19:54,186 - Loss: 0.2286, step: 27400
+INFO - dpsgd_diffusion.py - 2024-10-24 02:21:19,464 - Loss: 0.2404, step: 27500
+INFO - dpsgd_diffusion.py - 2024-10-24 02:22:58,946 - Loss: 0.2381, step: 27600
+INFO - dpsgd_diffusion.py - 2024-10-24 02:24:30,613 - Loss: 0.2632, step: 27700
+INFO - dpsgd_diffusion.py - 2024-10-24 02:25:37,786 - Eps-value after 62 epochs: 6.0719
+INFO - dpsgd_diffusion.py - 2024-10-24 02:26:01,534 - Loss: 0.2714, step: 27800
+INFO - dpsgd_diffusion.py - 2024-10-24 02:27:28,907 - Loss: 0.2361, step: 27900
+INFO - dpsgd_diffusion.py - 2024-10-24 02:28:57,523 - Loss: 0.2337, step: 28000
+INFO - dpsgd_diffusion.py - 2024-10-24 02:28:57,540 - Saving snapshot checkpoint and sampling single batch at iteration 28000.
+WARNING - image.py - 2024-10-24 02:28:58,142 - 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 02:29:13,518 - FID at iteration 28000: 30.188820
+INFO - dpsgd_diffusion.py - 2024-10-24 02:30:48,048 - Loss: 0.2577, step: 28100
+INFO - dpsgd_diffusion.py - 2024-10-24 02:32:14,948 - Loss: 0.2884, step: 28200
+INFO - dpsgd_diffusion.py - 2024-10-24 02:32:36,116 - Eps-value after 63 epochs: 6.1252
+INFO - dpsgd_diffusion.py - 2024-10-24 02:33:44,796 - Loss: 0.2461, step: 28300
+INFO - dpsgd_diffusion.py - 2024-10-24 02:35:18,213 - Loss: 0.2352, step: 28400
+INFO - dpsgd_diffusion.py - 2024-10-24 02:36:52,330 - Loss: 0.2417, step: 28500
+INFO - dpsgd_diffusion.py - 2024-10-24 02:38:24,680 - Loss: 0.2226, step: 28600
+INFO - dpsgd_diffusion.py - 2024-10-24 02:39:31,728 - Eps-value after 64 epochs: 6.1784
+INFO - dpsgd_diffusion.py - 2024-10-24 02:39:53,966 - Loss: 0.2437, step: 28700
+INFO - dpsgd_diffusion.py - 2024-10-24 02:41:22,447 - Loss: 0.2612, step: 28800
+INFO - dpsgd_diffusion.py - 2024-10-24 02:42:55,279 - Loss: 0.2441, step: 28900
+INFO - dpsgd_diffusion.py - 2024-10-24 02:44:22,513 - Loss: 0.2313, step: 29000
+INFO - dpsgd_diffusion.py - 2024-10-24 02:45:57,925 - Loss: 0.2484, step: 29100
+INFO - dpsgd_diffusion.py - 2024-10-24 02:46:13,264 - Eps-value after 65 epochs: 6.2316
+INFO - dpsgd_diffusion.py - 2024-10-24 02:47:22,377 - Loss: 0.2247, step: 29200
+INFO - dpsgd_diffusion.py - 2024-10-24 02:48:54,884 - Loss: 0.2531, step: 29300
+INFO - dpsgd_diffusion.py - 2024-10-24 02:50:15,473 - Loss: 0.2620, step: 29400
+INFO - dpsgd_diffusion.py - 2024-10-24 02:51:40,526 - Loss: 0.2390, step: 29500
+INFO - dpsgd_diffusion.py - 2024-10-24 02:52:37,886 - Eps-value after 66 epochs: 6.2845
+INFO - dpsgd_diffusion.py - 2024-10-24 02:53:07,333 - Loss: 0.2262, step: 29600
+INFO - dpsgd_diffusion.py - 2024-10-24 02:54:41,404 - Loss: 0.2231, step: 29700
+INFO - dpsgd_diffusion.py - 2024-10-24 02:56:12,099 - Loss: 0.2507, step: 29800
+INFO - dpsgd_diffusion.py - 2024-10-24 02:57:42,847 - Loss: 0.2298, step: 29900
+INFO - dpsgd_diffusion.py - 2024-10-24 02:59:18,941 - Loss: 0.2471, step: 30000
+INFO - dpsgd_diffusion.py - 2024-10-24 02:59:19,144 - Saving snapshot checkpoint and sampling single batch at iteration 30000.
+WARNING - image.py - 2024-10-24 02:59:19,671 - 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 02:59:35,568 - FID at iteration 30000: 29.706246
+INFO - dpsgd_diffusion.py - 2024-10-24 02:59:51,676 - Eps-value after 67 epochs: 6.3365
+INFO - dpsgd_diffusion.py - 2024-10-24 03:01:02,761 - Loss: 0.2348, step: 30100
+INFO - dpsgd_diffusion.py - 2024-10-24 03:02:36,489 - Loss: 0.2266, step: 30200
+INFO - dpsgd_diffusion.py - 2024-10-24 03:04:08,836 - Loss: 0.2239, step: 30300
+INFO - dpsgd_diffusion.py - 2024-10-24 03:05:33,718 - Loss: 0.2216, step: 30400
+INFO - dpsgd_diffusion.py - 2024-10-24 03:06:33,976 - Eps-value after 68 epochs: 6.3884
+INFO - dpsgd_diffusion.py - 2024-10-24 03:07:02,865 - Loss: 0.2380, step: 30500
+INFO - dpsgd_diffusion.py - 2024-10-24 03:08:21,520 - Loss: 0.2595, step: 30600
+INFO - dpsgd_diffusion.py - 2024-10-24 03:09:51,599 - Loss: 0.2397, step: 30700
+INFO - dpsgd_diffusion.py - 2024-10-24 03:11:13,011 - Loss: 0.2355, step: 30800
+INFO - dpsgd_diffusion.py - 2024-10-24 03:12:27,976 - Loss: 0.2544, step: 30900
+INFO - dpsgd_diffusion.py - 2024-10-24 03:12:37,397 - Eps-value after 69 epochs: 6.4404
+INFO - dpsgd_diffusion.py - 2024-10-24 03:13:47,125 - Loss: 0.2667, step: 31000
+INFO - dpsgd_diffusion.py - 2024-10-24 03:15:04,557 - Loss: 0.2429, step: 31100
+INFO - dpsgd_diffusion.py - 2024-10-24 03:16:25,685 - Loss: 0.2421, step: 31200
+INFO - dpsgd_diffusion.py - 2024-10-24 03:17:41,979 - Loss: 0.2226, step: 31300
+INFO - dpsgd_diffusion.py - 2024-10-24 03:18:31,922 - Eps-value after 70 epochs: 6.4921
+INFO - dpsgd_diffusion.py - 2024-10-24 03:19:03,889 - Loss: 0.2283, step: 31400
+INFO - dpsgd_diffusion.py - 2024-10-24 03:20:20,657 - Loss: 0.2380, step: 31500
+INFO - dpsgd_diffusion.py - 2024-10-24 03:21:39,999 - Loss: 0.2376, step: 31600
+INFO - dpsgd_diffusion.py - 2024-10-24 03:23:00,588 - Loss: 0.2467, step: 31700
+INFO - dpsgd_diffusion.py - 2024-10-24 03:24:29,936 - Loss: 0.2159, step: 31800
+INFO - dpsgd_diffusion.py - 2024-10-24 03:24:36,179 - Eps-value after 71 epochs: 6.5429
+INFO - dpsgd_diffusion.py - 2024-10-24 03:25:58,282 - Loss: 0.2211, step: 31900
+INFO - dpsgd_diffusion.py - 2024-10-24 03:27:20,922 - Loss: 0.2415, step: 32000
+INFO - dpsgd_diffusion.py - 2024-10-24 03:27:20,942 - Saving snapshot checkpoint and sampling single batch at iteration 32000.
+WARNING - image.py - 2024-10-24 03:27:21,489 - 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 03:27:34,771 - FID at iteration 32000: 28.762993
+INFO - dpsgd_diffusion.py - 2024-10-24 03:29:17,121 - Loss: 0.2120, step: 32100
+INFO - dpsgd_diffusion.py - 2024-10-24 03:31:00,310 - Loss: 0.2289, step: 32200
+INFO - dpsgd_diffusion.py - 2024-10-24 03:31:45,561 - Eps-value after 72 epochs: 6.5937
+INFO - dpsgd_diffusion.py - 2024-10-24 03:32:21,657 - Loss: 0.2456, step: 32300
+INFO - dpsgd_diffusion.py - 2024-10-24 03:33:53,655 - Loss: 0.2402, step: 32400
+INFO - dpsgd_diffusion.py - 2024-10-24 03:35:18,340 - Loss: 0.2189, step: 32500
+INFO - dpsgd_diffusion.py - 2024-10-24 03:36:48,592 - Loss: 0.2466, step: 32600
+INFO - dpsgd_diffusion.py - 2024-10-24 03:38:18,950 - Loss: 0.2439, step: 32700
+INFO - dpsgd_diffusion.py - 2024-10-24 03:38:23,062 - Eps-value after 73 epochs: 6.6444
+INFO - dpsgd_diffusion.py - 2024-10-24 03:39:48,919 - Loss: 0.2225, step: 32800
+INFO - dpsgd_diffusion.py - 2024-10-24 03:41:29,007 - Loss: 0.2381, step: 32900
+INFO - dpsgd_diffusion.py - 2024-10-24 03:42:52,753 - Loss: 0.2909, step: 33000
+INFO - dpsgd_diffusion.py - 2024-10-24 03:44:12,766 - Loss: 0.2687, step: 33100
+INFO - dpsgd_diffusion.py - 2024-10-24 03:44:56,521 - Eps-value after 74 epochs: 6.6952
+INFO - dpsgd_diffusion.py - 2024-10-24 03:45:36,651 - Loss: 0.2417, step: 33200
+INFO - dpsgd_diffusion.py - 2024-10-24 03:47:07,951 - Loss: 0.2625, step: 33300
+INFO - dpsgd_diffusion.py - 2024-10-24 03:48:33,699 - Loss: 0.2654, step: 33400
+INFO - dpsgd_diffusion.py - 2024-10-24 03:50:06,762 - Loss: 0.2209, step: 33500
+INFO - dpsgd_diffusion.py - 2024-10-24 03:51:27,941 - Loss: 0.2467, step: 33600
+INFO - dpsgd_diffusion.py - 2024-10-24 03:51:27,964 - Eps-value after 75 epochs: 6.7450
+INFO - dpsgd_diffusion.py - 2024-10-24 03:52:59,392 - Loss: 0.2371, step: 33700
+INFO - dpsgd_diffusion.py - 2024-10-24 03:54:30,424 - Loss: 0.2334, step: 33800
+INFO - dpsgd_diffusion.py - 2024-10-24 03:55:47,805 - Loss: 0.2262, step: 33900
+INFO - dpsgd_diffusion.py - 2024-10-24 03:57:18,033 - Loss: 0.2317, step: 34000
+INFO - dpsgd_diffusion.py - 2024-10-24 03:57:18,253 - Saving snapshot checkpoint and sampling single batch at iteration 34000.
+WARNING - image.py - 2024-10-24 03:57:18,784 - 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 03:57:33,549 - FID at iteration 34000: 28.291121
+INFO - dpsgd_diffusion.py - 2024-10-24 03:58:18,685 - Eps-value after 76 epochs: 6.7946
+INFO - dpsgd_diffusion.py - 2024-10-24 03:59:03,086 - Loss: 0.2305, step: 34100
+INFO - dpsgd_diffusion.py - 2024-10-24 04:00:22,743 - Loss: 0.2363, step: 34200
+INFO - dpsgd_diffusion.py - 2024-10-24 04:01:44,709 - Loss: 0.2062, step: 34300
+INFO - dpsgd_diffusion.py - 2024-10-24 04:03:27,434 - Loss: 0.2219, step: 34400
+INFO - dpsgd_diffusion.py - 2024-10-24 04:04:59,620 - Eps-value after 77 epochs: 6.8441
+INFO - dpsgd_diffusion.py - 2024-10-24 04:05:03,203 - Loss: 0.2244, step: 34500
+INFO - dpsgd_diffusion.py - 2024-10-24 04:06:27,468 - Loss: 0.2017, step: 34600
+INFO - dpsgd_diffusion.py - 2024-10-24 04:07:51,505 - Loss: 0.2135, step: 34700
+INFO - dpsgd_diffusion.py - 2024-10-24 04:09:19,679 - Loss: 0.1944, step: 34800
+INFO - dpsgd_diffusion.py - 2024-10-24 04:10:40,424 - Loss: 0.2337, step: 34900
+INFO - dpsgd_diffusion.py - 2024-10-24 04:11:19,763 - Eps-value after 78 epochs: 6.8937
+INFO - dpsgd_diffusion.py - 2024-10-24 04:12:08,392 - Loss: 0.2414, step: 35000
+INFO - dpsgd_diffusion.py - 2024-10-24 04:13:36,651 - Loss: 0.2456, step: 35100
+INFO - dpsgd_diffusion.py - 2024-10-24 04:15:13,383 - Loss: 0.2430, step: 35200
+INFO - dpsgd_diffusion.py - 2024-10-24 04:16:39,206 - Loss: 0.2098, step: 35300
+INFO - dpsgd_diffusion.py - 2024-10-24 04:17:56,274 - Eps-value after 79 epochs: 6.9432
+INFO - dpsgd_diffusion.py - 2024-10-24 04:18:02,470 - Loss: 0.2410, step: 35400
+INFO - dpsgd_diffusion.py - 2024-10-24 04:19:40,625 - Loss: 0.2402, step: 35500
+INFO - dpsgd_diffusion.py - 2024-10-24 04:21:14,520 - Loss: 0.2332, step: 35600
+INFO - dpsgd_diffusion.py - 2024-10-24 04:22:45,816 - Loss: 0.2453, step: 35700
+INFO - dpsgd_diffusion.py - 2024-10-24 04:24:04,660 - Loss: 0.2795, step: 35800
+INFO - dpsgd_diffusion.py - 2024-10-24 04:24:38,575 - Eps-value after 80 epochs: 6.9916
+INFO - dpsgd_diffusion.py - 2024-10-24 04:25:37,382 - Loss: 0.2263, step: 35900
+INFO - dpsgd_diffusion.py - 2024-10-24 04:27:10,655 - Loss: 0.2430, step: 36000
+INFO - dpsgd_diffusion.py - 2024-10-24 04:27:10,671 - Saving snapshot checkpoint and sampling single batch at iteration 36000.
+WARNING - image.py - 2024-10-24 04:27:11,241 - 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 04:27:25,168 - FID at iteration 36000: 27.306067
+INFO - dpsgd_diffusion.py - 2024-10-24 04:29:01,090 - Loss: 0.2312, step: 36100
+INFO - dpsgd_diffusion.py - 2024-10-24 04:30:25,372 - Loss: 0.2380, step: 36200
+INFO - dpsgd_diffusion.py - 2024-10-24 04:31:31,713 - Eps-value after 81 epochs: 7.0400
+INFO - dpsgd_diffusion.py - 2024-10-24 04:31:40,845 - Loss: 0.2121, step: 36300
+INFO - dpsgd_diffusion.py - 2024-10-24 04:33:02,249 - Loss: 0.2425, step: 36400
+INFO - dpsgd_diffusion.py - 2024-10-24 04:34:20,391 - Loss: 0.2653, step: 36500
+INFO - dpsgd_diffusion.py - 2024-10-24 04:35:41,442 - Loss: 0.2489, step: 36600
+INFO - dpsgd_diffusion.py - 2024-10-24 04:36:58,120 - Loss: 0.2082, step: 36700
+INFO - dpsgd_diffusion.py - 2024-10-24 04:37:27,623 - Eps-value after 82 epochs: 7.0884
+INFO - dpsgd_diffusion.py - 2024-10-24 04:38:19,896 - Loss: 0.2470, step: 36800
+INFO - dpsgd_diffusion.py - 2024-10-24 04:39:37,854 - Loss: 0.2141, step: 36900
+INFO - dpsgd_diffusion.py - 2024-10-24 04:40:58,394 - Loss: 0.2374, step: 37000
+INFO - dpsgd_diffusion.py - 2024-10-24 04:42:16,709 - Loss: 0.2595, step: 37100
+INFO - dpsgd_diffusion.py - 2024-10-24 04:43:26,401 - Eps-value after 83 epochs: 7.1367
+INFO - dpsgd_diffusion.py - 2024-10-24 04:43:39,163 - Loss: 0.2551, step: 37200
+INFO - dpsgd_diffusion.py - 2024-10-24 04:45:04,631 - Loss: 0.2488, step: 37300
+INFO - dpsgd_diffusion.py - 2024-10-24 04:46:28,870 - Loss: 0.2388, step: 37400
+INFO - dpsgd_diffusion.py - 2024-10-24 04:47:32,354 - Loss: 0.2168, step: 37500
+INFO - dpsgd_diffusion.py - 2024-10-24 04:48:30,962 - Loss: 0.2162, step: 37600
+INFO - dpsgd_diffusion.py - 2024-10-24 04:48:49,239 - Eps-value after 84 epochs: 7.1851
+INFO - dpsgd_diffusion.py - 2024-10-24 04:49:28,665 - Loss: 0.2350, step: 37700
+INFO - dpsgd_diffusion.py - 2024-10-24 04:50:26,793 - Loss: 0.2337, step: 37800
+INFO - dpsgd_diffusion.py - 2024-10-24 04:51:23,983 - Loss: 0.2191, step: 37900
+INFO - dpsgd_diffusion.py - 2024-10-24 04:52:23,112 - Loss: 0.2495, step: 38000
+INFO - dpsgd_diffusion.py - 2024-10-24 04:52:23,141 - Saving snapshot checkpoint and sampling single batch at iteration 38000.
+WARNING - image.py - 2024-10-24 04:52:23,869 - 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 04:52:36,359 - FID at iteration 38000: 26.821191
+INFO - dpsgd_diffusion.py - 2024-10-24 04:53:24,713 - Eps-value after 85 epochs: 7.2325
+INFO - dpsgd_diffusion.py - 2024-10-24 04:53:36,431 - Loss: 0.2553, step: 38100
+INFO - dpsgd_diffusion.py - 2024-10-24 04:54:37,404 - Loss: 0.2373, step: 38200
+INFO - dpsgd_diffusion.py - 2024-10-24 04:55:36,657 - Loss: 0.2350, step: 38300
+INFO - dpsgd_diffusion.py - 2024-10-24 04:56:34,693 - Loss: 0.2339, step: 38400
+INFO - dpsgd_diffusion.py - 2024-10-24 04:57:33,466 - Loss: 0.2324, step: 38500
+INFO - dpsgd_diffusion.py - 2024-10-24 04:57:50,050 - Eps-value after 86 epochs: 7.2797
+INFO - dpsgd_diffusion.py - 2024-10-24 04:58:31,714 - Loss: 0.2453, step: 38600
+INFO - dpsgd_diffusion.py - 2024-10-24 04:59:30,481 - Loss: 0.2363, step: 38700
+INFO - dpsgd_diffusion.py - 2024-10-24 05:00:28,326 - Loss: 0.2221, step: 38800
+INFO - dpsgd_diffusion.py - 2024-10-24 05:01:26,100 - Loss: 0.2296, step: 38900
+INFO - dpsgd_diffusion.py - 2024-10-24 05:02:10,615 - Eps-value after 87 epochs: 7.3269
+INFO - dpsgd_diffusion.py - 2024-10-24 05:02:24,813 - Loss: 0.2242, step: 39000
+INFO - dpsgd_diffusion.py - 2024-10-24 05:03:23,849 - Loss: 0.2443, step: 39100
+INFO - dpsgd_diffusion.py - 2024-10-24 05:04:20,946 - Loss: 0.2371, step: 39200
+INFO - dpsgd_diffusion.py - 2024-10-24 05:05:20,385 - Loss: 0.2414, step: 39300
+INFO - dpsgd_diffusion.py - 2024-10-24 05:06:18,847 - Loss: 0.2247, step: 39400
+INFO - dpsgd_diffusion.py - 2024-10-24 05:06:32,720 - Eps-value after 88 epochs: 7.3741
+INFO - dpsgd_diffusion.py - 2024-10-24 05:07:17,607 - Loss: 0.2218, step: 39500
+INFO - dpsgd_diffusion.py - 2024-10-24 05:08:14,946 - Loss: 0.2234, step: 39600
+INFO - dpsgd_diffusion.py - 2024-10-24 05:09:12,581 - Loss: 0.2208, step: 39700
+INFO - dpsgd_diffusion.py - 2024-10-24 05:10:10,681 - Loss: 0.2282, step: 39800
+INFO - dpsgd_diffusion.py - 2024-10-24 05:10:51,989 - Eps-value after 89 epochs: 7.4213
+INFO - dpsgd_diffusion.py - 2024-10-24 05:11:07,870 - Loss: 0.2095, step: 39900
+INFO - dpsgd_diffusion.py - 2024-10-24 05:12:07,095 - Loss: 0.2208, step: 40000
+INFO - dpsgd_diffusion.py - 2024-10-24 05:12:07,114 - Saving snapshot checkpoint and sampling single batch at iteration 40000.
+WARNING - image.py - 2024-10-24 05:12:07,648 - 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 05:12:20,825 - FID at iteration 40000: 26.094855
+INFO - dpsgd_diffusion.py - 2024-10-24 05:13:21,887 - Loss: 0.2039, step: 40100
+INFO - dpsgd_diffusion.py - 2024-10-24 05:14:21,078 - Loss: 0.2353, step: 40200
+INFO - dpsgd_diffusion.py - 2024-10-24 05:15:19,046 - Loss: 0.2292, step: 40300
+INFO - dpsgd_diffusion.py - 2024-10-24 05:15:30,516 - Eps-value after 90 epochs: 7.4683
+INFO - dpsgd_diffusion.py - 2024-10-24 05:16:17,302 - Loss: 0.2354, step: 40400
+INFO - dpsgd_diffusion.py - 2024-10-24 05:17:15,072 - Loss: 0.2590, step: 40500
+INFO - dpsgd_diffusion.py - 2024-10-24 05:18:12,596 - Loss: 0.2243, step: 40600
+INFO - dpsgd_diffusion.py - 2024-10-24 05:19:10,711 - Loss: 0.2359, step: 40700
+INFO - dpsgd_diffusion.py - 2024-10-24 05:19:50,360 - Eps-value after 91 epochs: 7.5143
+INFO - dpsgd_diffusion.py - 2024-10-24 05:20:09,111 - Loss: 0.2315, step: 40800
+INFO - dpsgd_diffusion.py - 2024-10-24 05:21:06,574 - Loss: 0.2162, step: 40900
+INFO - dpsgd_diffusion.py - 2024-10-24 05:22:05,788 - Loss: 0.2405, step: 41000
+INFO - dpsgd_diffusion.py - 2024-10-24 05:23:04,003 - Loss: 0.2430, step: 41100
+INFO - dpsgd_diffusion.py - 2024-10-24 05:24:02,475 - Loss: 0.2496, step: 41200
+INFO - dpsgd_diffusion.py - 2024-10-24 05:24:11,684 - Eps-value after 92 epochs: 7.5603
+INFO - dpsgd_diffusion.py - 2024-10-24 05:25:00,173 - Loss: 0.2524, step: 41300
+INFO - dpsgd_diffusion.py - 2024-10-24 05:25:59,062 - Loss: 0.2571, step: 41400
+INFO - dpsgd_diffusion.py - 2024-10-24 05:26:57,279 - Loss: 0.2166, step: 41500
+INFO - dpsgd_diffusion.py - 2024-10-24 05:27:56,217 - Loss: 0.2123, step: 41600
+INFO - dpsgd_diffusion.py - 2024-10-24 05:28:34,835 - Eps-value after 93 epochs: 7.6064
+INFO - dpsgd_diffusion.py - 2024-10-24 05:28:56,003 - Loss: 0.2042, step: 41700
+INFO - dpsgd_diffusion.py - 2024-10-24 05:29:54,107 - Loss: 0.2277, step: 41800
+INFO - dpsgd_diffusion.py - 2024-10-24 05:30:51,549 - Loss: 0.2509, step: 41900
+INFO - dpsgd_diffusion.py - 2024-10-24 05:31:50,195 - Loss: 0.2494, step: 42000
+INFO - dpsgd_diffusion.py - 2024-10-24 05:31:50,208 - Saving snapshot checkpoint and sampling single batch at iteration 42000.
+WARNING - image.py - 2024-10-24 05:31:50,748 - 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 05:32:03,196 - FID at iteration 42000: 25.298357
+INFO - dpsgd_diffusion.py - 2024-10-24 05:33:04,150 - Loss: 0.2359, step: 42100
+INFO - dpsgd_diffusion.py - 2024-10-24 05:33:11,025 - Eps-value after 94 epochs: 7.6524
+INFO - dpsgd_diffusion.py - 2024-10-24 05:34:04,140 - Loss: 0.2424, step: 42200
+INFO - dpsgd_diffusion.py - 2024-10-24 05:35:02,226 - Loss: 0.2235, step: 42300
+INFO - dpsgd_diffusion.py - 2024-10-24 05:35:59,944 - Loss: 0.2432, step: 42400
+INFO - dpsgd_diffusion.py - 2024-10-24 05:36:57,851 - Loss: 0.2335, step: 42500
+INFO - dpsgd_diffusion.py - 2024-10-24 05:37:32,554 - Eps-value after 95 epochs: 7.6985
+INFO - dpsgd_diffusion.py - 2024-10-24 05:37:55,153 - Loss: 0.2058, step: 42600
+INFO - dpsgd_diffusion.py - 2024-10-24 05:38:52,875 - Loss: 0.2244, step: 42700
+INFO - dpsgd_diffusion.py - 2024-10-24 05:39:51,752 - Loss: 0.2113, step: 42800
+INFO - dpsgd_diffusion.py - 2024-10-24 05:40:52,134 - Loss: 0.2532, step: 42900
+INFO - dpsgd_diffusion.py - 2024-10-24 05:41:50,339 - Loss: 0.2308, step: 43000
+INFO - dpsgd_diffusion.py - 2024-10-24 05:41:54,943 - Eps-value after 96 epochs: 7.7445
+INFO - dpsgd_diffusion.py - 2024-10-24 05:42:48,843 - Loss: 0.2281, step: 43100
+INFO - dpsgd_diffusion.py - 2024-10-24 05:43:47,958 - Loss: 0.2229, step: 43200
+INFO - dpsgd_diffusion.py - 2024-10-24 05:44:45,868 - Loss: 0.2295, step: 43300
+INFO - dpsgd_diffusion.py - 2024-10-24 05:45:44,301 - Loss: 0.2252, step: 43400
+INFO - dpsgd_diffusion.py - 2024-10-24 05:46:16,549 - Eps-value after 97 epochs: 7.7894
+INFO - dpsgd_diffusion.py - 2024-10-24 05:46:42,241 - Loss: 0.2363, step: 43500
+INFO - dpsgd_diffusion.py - 2024-10-24 05:47:40,573 - Loss: 0.2437, step: 43600
+INFO - dpsgd_diffusion.py - 2024-10-24 05:48:42,431 - Loss: 0.2079, step: 43700
+INFO - dpsgd_diffusion.py - 2024-10-24 05:49:40,603 - Loss: 0.2209, step: 43800
+INFO - dpsgd_diffusion.py - 2024-10-24 05:50:38,391 - Loss: 0.2216, step: 43900
+INFO - dpsgd_diffusion.py - 2024-10-24 05:50:40,664 - Eps-value after 98 epochs: 7.8342
+INFO - dpsgd_diffusion.py - 2024-10-24 05:51:36,778 - Loss: 0.2260, step: 44000
+INFO - dpsgd_diffusion.py - 2024-10-24 05:51:36,797 - Saving snapshot checkpoint and sampling single batch at iteration 44000.
+WARNING - image.py - 2024-10-24 05:51:37,345 - 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 05:51:50,110 - FID at iteration 44000: 24.938015
+INFO - dpsgd_diffusion.py - 2024-10-24 05:52:48,893 - Loss: 0.2225, step: 44100
+INFO - dpsgd_diffusion.py - 2024-10-24 05:53:47,036 - Loss: 0.2270, step: 44200
+INFO - dpsgd_diffusion.py - 2024-10-24 05:54:45,153 - Loss: 0.2241, step: 44300
+INFO - dpsgd_diffusion.py - 2024-10-24 05:55:15,151 - Eps-value after 99 epochs: 7.8791
+INFO - dpsgd_diffusion.py - 2024-10-24 05:55:44,527 - Loss: 0.2220, step: 44400
+INFO - dpsgd_diffusion.py - 2024-10-24 05:56:53,451 - Loss: 0.2855, step: 44500
+INFO - dpsgd_diffusion.py - 2024-10-24 05:58:29,784 - Loss: 0.2166, step: 44600
+INFO - dpsgd_diffusion.py - 2024-10-24 06:00:13,780 - Loss: 0.2223, step: 44700
+INFO - dpsgd_diffusion.py - 2024-10-24 06:01:58,950 - Loss: 0.2181, step: 44800
+INFO - dpsgd_diffusion.py - 2024-10-24 06:01:58,973 - Eps-value after 100 epochs: 7.9240
+INFO - dpsgd_diffusion.py - 2024-10-24 06:03:39,742 - Loss: 0.2274, step: 44900
+INFO - dpsgd_diffusion.py - 2024-10-24 06:05:29,522 - Loss: 0.2233, step: 45000
+INFO - dpsgd_diffusion.py - 2024-10-24 06:07:09,242 - Loss: 0.2090, step: 45100
+INFO - dpsgd_diffusion.py - 2024-10-24 06:08:51,947 - Loss: 0.2206, step: 45200
+INFO - dpsgd_diffusion.py - 2024-10-24 06:09:38,738 - Eps-value after 101 epochs: 7.9688
+INFO - dpsgd_diffusion.py - 2024-10-24 06:10:31,700 - Loss: 0.2179, step: 45300
+INFO - dpsgd_diffusion.py - 2024-10-24 06:12:06,989 - Loss: 0.2173, step: 45400
+INFO - dpsgd_diffusion.py - 2024-10-24 06:13:48,044 - Loss: 0.2221, step: 45500
+INFO - dpsgd_diffusion.py - 2024-10-24 06:15:30,129 - Loss: 0.2288, step: 45600
+INFO - dpsgd_diffusion.py - 2024-10-24 06:17:06,139 - Eps-value after 102 epochs: 8.0137
+INFO - dpsgd_diffusion.py - 2024-10-24 06:17:10,241 - Loss: 0.2308, step: 45700
+INFO - dpsgd_diffusion.py - 2024-10-24 06:18:55,077 - Loss: 0.2308, step: 45800
+INFO - dpsgd_diffusion.py - 2024-10-24 06:20:33,955 - Loss: 0.2257, step: 45900
+INFO - dpsgd_diffusion.py - 2024-10-24 06:22:16,634 - Loss: 0.2218, step: 46000
+INFO - dpsgd_diffusion.py - 2024-10-24 06:22:16,647 - Saving snapshot checkpoint and sampling single batch at iteration 46000.
+WARNING - image.py - 2024-10-24 06:22:17,268 - 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 06:22:33,749 - FID at iteration 46000: 24.731247
+INFO - dpsgd_diffusion.py - 2024-10-24 06:24:14,033 - Loss: 0.2662, step: 46100
+INFO - dpsgd_diffusion.py - 2024-10-24 06:25:00,698 - Eps-value after 103 epochs: 8.0585
+INFO - dpsgd_diffusion.py - 2024-10-24 06:25:56,676 - Loss: 0.2186, step: 46200
+INFO - dpsgd_diffusion.py - 2024-10-24 06:27:36,179 - Loss: 0.2046, step: 46300
+INFO - dpsgd_diffusion.py - 2024-10-24 06:29:23,856 - Loss: 0.2247, step: 46400
+INFO - dpsgd_diffusion.py - 2024-10-24 06:31:10,928 - Loss: 0.2415, step: 46500
+INFO - dpsgd_diffusion.py - 2024-10-24 06:32:37,759 - Eps-value after 104 epochs: 8.1022
+INFO - dpsgd_diffusion.py - 2024-10-24 06:32:46,081 - Loss: 0.2125, step: 46600
+INFO - dpsgd_diffusion.py - 2024-10-24 06:34:25,645 - Loss: 0.2096, step: 46700
+INFO - dpsgd_diffusion.py - 2024-10-24 06:35:58,009 - Loss: 0.2412, step: 46800
+INFO - dpsgd_diffusion.py - 2024-10-24 06:37:39,765 - Loss: 0.2404, step: 46900
+INFO - dpsgd_diffusion.py - 2024-10-24 06:39:18,663 - Loss: 0.2119, step: 47000
+INFO - dpsgd_diffusion.py - 2024-10-24 06:39:59,978 - Eps-value after 105 epochs: 8.1459
+INFO - dpsgd_diffusion.py - 2024-10-24 06:40:59,017 - Loss: 0.2079, step: 47100
+INFO - dpsgd_diffusion.py - 2024-10-24 06:42:36,856 - Loss: 0.2614, step: 47200
+INFO - dpsgd_diffusion.py - 2024-10-24 06:44:16,631 - Loss: 0.2348, step: 47300
+INFO - dpsgd_diffusion.py - 2024-10-24 06:45:57,437 - Loss: 0.2189, step: 47400
+INFO - dpsgd_diffusion.py - 2024-10-24 06:47:29,619 - Eps-value after 106 epochs: 8.1896
+INFO - dpsgd_diffusion.py - 2024-10-24 06:47:41,227 - Loss: 0.2115, step: 47500
+INFO - dpsgd_diffusion.py - 2024-10-24 06:49:20,830 - Loss: 0.2372, step: 47600
+INFO - dpsgd_diffusion.py - 2024-10-24 06:51:02,475 - Loss: 0.2325, step: 47700
+INFO - dpsgd_diffusion.py - 2024-10-24 06:52:42,135 - Loss: 0.2168, step: 47800
+INFO - dpsgd_diffusion.py - 2024-10-24 06:54:24,919 - Loss: 0.2352, step: 47900
+INFO - dpsgd_diffusion.py - 2024-10-24 06:54:59,437 - Eps-value after 107 epochs: 8.2333
+INFO - dpsgd_diffusion.py - 2024-10-24 06:55:58,493 - Loss: 0.2555, step: 48000
+INFO - dpsgd_diffusion.py - 2024-10-24 06:55:58,509 - Saving snapshot checkpoint and sampling single batch at iteration 48000.
+WARNING - image.py - 2024-10-24 06:55:59,039 - 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 06:56:14,721 - FID at iteration 48000: 24.196436
+INFO - dpsgd_diffusion.py - 2024-10-24 06:57:51,675 - Loss: 0.2487, step: 48100
+INFO - dpsgd_diffusion.py - 2024-10-24 06:59:32,838 - Loss: 0.2574, step: 48200
+INFO - dpsgd_diffusion.py - 2024-10-24 07:01:12,456 - Loss: 0.2134, step: 48300
+INFO - dpsgd_diffusion.py - 2024-10-24 07:02:36,918 - Eps-value after 108 epochs: 8.2770
+INFO - dpsgd_diffusion.py - 2024-10-24 07:02:51,911 - Loss: 0.2417, step: 48400
+INFO - dpsgd_diffusion.py - 2024-10-24 07:04:31,570 - Loss: 0.2096, step: 48500
+INFO - dpsgd_diffusion.py - 2024-10-24 07:06:06,830 - Loss: 0.2477, step: 48600
+INFO - dpsgd_diffusion.py - 2024-10-24 07:07:48,347 - Loss: 0.2070, step: 48700
+INFO - dpsgd_diffusion.py - 2024-10-24 07:09:29,889 - Loss: 0.2354, step: 48800
+INFO - dpsgd_diffusion.py - 2024-10-24 07:10:01,992 - Eps-value after 109 epochs: 8.3207
+INFO - dpsgd_diffusion.py - 2024-10-24 07:11:09,078 - Loss: 0.2250, step: 48900
+INFO - dpsgd_diffusion.py - 2024-10-24 07:12:51,395 - Loss: 0.2723, step: 49000
+INFO - dpsgd_diffusion.py - 2024-10-24 07:13:48,998 - Loss: 0.2152, step: 49100
+INFO - dpsgd_diffusion.py - 2024-10-24 07:14:47,520 - Loss: 0.2177, step: 49200
+INFO - dpsgd_diffusion.py - 2024-10-24 07:15:33,822 - Eps-value after 110 epochs: 8.3644
+INFO - dpsgd_diffusion.py - 2024-10-24 07:15:45,613 - Loss: 0.2398, step: 49300
+INFO - dpsgd_diffusion.py - 2024-10-24 07:16:44,697 - Loss: 0.2225, step: 49400
+INFO - dpsgd_diffusion.py - 2024-10-24 07:17:43,619 - Loss: 0.2143, step: 49500
+INFO - dpsgd_diffusion.py - 2024-10-24 07:18:42,277 - Loss: 0.2306, step: 49600
+INFO - dpsgd_diffusion.py - 2024-10-24 07:19:41,036 - Loss: 0.2386, step: 49700
+INFO - dpsgd_diffusion.py - 2024-10-24 07:19:57,396 - Eps-value after 111 epochs: 8.4075
+INFO - dpsgd_diffusion.py - 2024-10-24 07:20:40,143 - Loss: 0.2609, step: 49800
+INFO - dpsgd_diffusion.py - 2024-10-24 07:21:39,140 - Loss: 0.2369, step: 49900
+INFO - dpsgd_diffusion.py - 2024-10-24 07:22:39,770 - Loss: 0.2293, step: 50000
+INFO - dpsgd_diffusion.py - 2024-10-24 07:22:39,797 - Saving snapshot checkpoint and sampling single batch at iteration 50000.
+WARNING - image.py - 2024-10-24 07:22:40,374 - 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 07:22:54,815 - FID at iteration 50000: 23.177873
+INFO - dpsgd_diffusion.py - 2024-10-24 07:24:24,052 - Loss: 0.2423, step: 50100
+INFO - dpsgd_diffusion.py - 2024-10-24 07:25:33,425 - Eps-value after 112 epochs: 8.4500
+INFO - dpsgd_diffusion.py - 2024-10-24 07:25:47,564 - Loss: 0.2430, step: 50200
+INFO - dpsgd_diffusion.py - 2024-10-24 07:26:47,185 - Loss: 0.2097, step: 50300
+INFO - dpsgd_diffusion.py - 2024-10-24 07:27:47,924 - Loss: 0.2149, step: 50400
+INFO - dpsgd_diffusion.py - 2024-10-24 07:28:47,734 - Loss: 0.2269, step: 50500
+INFO - dpsgd_diffusion.py - 2024-10-24 07:29:47,391 - Loss: 0.2206, step: 50600
+INFO - dpsgd_diffusion.py - 2024-10-24 07:30:01,855 - Eps-value after 113 epochs: 8.4925
+INFO - dpsgd_diffusion.py - 2024-10-24 07:30:50,712 - Loss: 0.2308, step: 50700
+INFO - dpsgd_diffusion.py - 2024-10-24 07:32:21,700 - Loss: 0.2233, step: 50800
+INFO - dpsgd_diffusion.py - 2024-10-24 07:34:41,810 - Loss: 0.2293, step: 50900
+INFO - dpsgd_diffusion.py - 2024-10-24 07:36:56,015 - Loss: 0.2286, step: 51000
+INFO - dpsgd_diffusion.py - 2024-10-24 07:38:34,476 - Eps-value after 114 epochs: 8.5351
+INFO - dpsgd_diffusion.py - 2024-10-24 07:39:13,508 - Loss: 0.2093, step: 51100
+INFO - dpsgd_diffusion.py - 2024-10-24 07:41:33,169 - Loss: 0.2205, step: 51200
+INFO - dpsgd_diffusion.py - 2024-10-24 07:43:55,772 - Loss: 0.2127, step: 51300
+INFO - dpsgd_diffusion.py - 2024-10-24 07:46:17,603 - Loss: 0.2287, step: 51400
+INFO - dpsgd_diffusion.py - 2024-10-24 07:48:43,910 - Loss: 0.2167, step: 51500
+INFO - dpsgd_diffusion.py - 2024-10-24 07:49:11,675 - Eps-value after 115 epochs: 8.5776
+INFO - dpsgd_diffusion.py - 2024-10-24 07:51:03,528 - Loss: 0.2433, step: 51600
+INFO - dpsgd_diffusion.py - 2024-10-24 07:53:23,277 - Loss: 0.2015, step: 51700
+INFO - dpsgd_diffusion.py - 2024-10-24 07:55:13,489 - Loss: 0.2221, step: 51800
+INFO - dpsgd_diffusion.py - 2024-10-24 07:56:16,715 - Loss: 0.2573, step: 51900
+INFO - dpsgd_diffusion.py - 2024-10-24 07:56:56,246 - Eps-value after 116 epochs: 8.6202
+INFO - dpsgd_diffusion.py - 2024-10-24 07:57:14,763 - Loss: 0.2441, step: 52000
+INFO - dpsgd_diffusion.py - 2024-10-24 07:57:14,784 - Saving snapshot checkpoint and sampling single batch at iteration 52000.
+WARNING - image.py - 2024-10-24 07:57:15,313 - 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 - 2024-10-24 07:57:27,974 - FID at iteration 52000: 23.116939
+INFO - dpsgd_diffusion.py - 2024-10-24 07:58:27,689 - Loss: 0.2323, step: 52100
+INFO - dpsgd_diffusion.py - 2024-10-24 07:59:25,947 - Loss: 0.2263, step: 52200
+INFO - dpsgd_diffusion.py - 2024-10-24 08:00:27,152 - Loss: 0.2419, step: 52300
+INFO - dpsgd_diffusion.py - 2024-10-24 08:01:26,227 - Loss: 0.2271, step: 52400
+INFO - dpsgd_diffusion.py - 2024-10-24 08:01:35,443 - Eps-value after 117 epochs: 8.6627
+INFO - dpsgd_diffusion.py - 2024-10-24 08:02:26,769 - Loss: 0.2309, step: 52500
+INFO - dpsgd_diffusion.py - 2024-10-24 08:03:32,343 - Loss: 0.2615, step: 52600
+INFO - dpsgd_diffusion.py - 2024-10-24 08:05:20,071 - Loss: 0.2189, step: 52700
+INFO - dpsgd_diffusion.py - 2024-10-24 08:07:36,652 - Loss: 0.2173, step: 52800
+INFO - dpsgd_diffusion.py - 2024-10-24 08:09:07,986 - Eps-value after 118 epochs: 8.7052
+INFO - dpsgd_diffusion.py - 2024-10-24 08:09:58,767 - Loss: 0.2165, step: 52900
+INFO - dpsgd_diffusion.py - 2024-10-24 08:12:18,977 - Loss: 0.2175, step: 53000
+INFO - dpsgd_diffusion.py - 2024-10-24 08:14:39,451 - Loss: 0.2302, step: 53100
+INFO - dpsgd_diffusion.py - 2024-10-24 08:17:02,026 - Loss: 0.2284, step: 53200
+INFO - dpsgd_diffusion.py - 2024-10-24 08:19:22,653 - Loss: 0.2617, step: 53300
+INFO - dpsgd_diffusion.py - 2024-10-24 08:19:39,895 - Eps-value after 119 epochs: 8.7477
+INFO - dpsgd_diffusion.py - 2024-10-24 08:21:21,132 - Loss: 0.2814, step: 53400
+INFO - dpsgd_diffusion.py - 2024-10-24 08:23:43,215 - Loss: 0.2378, step: 53500
+INFO - dpsgd_diffusion.py - 2024-10-24 08:26:06,002 - Loss: 0.2089, step: 53600
+INFO - dpsgd_diffusion.py - 2024-10-24 08:28:30,188 - Loss: 0.2136, step: 53700
+INFO - dpsgd_diffusion.py - 2024-10-24 08:29:57,546 - Eps-value after 120 epochs: 8.7890
+INFO - dpsgd_diffusion.py - 2024-10-24 08:30:54,712 - Loss: 0.2137, step: 53800
+INFO - dpsgd_diffusion.py - 2024-10-24 08:33:14,089 - Loss: 0.2314, step: 53900
+INFO - dpsgd_diffusion.py - 2024-10-24 08:35:36,263 - Loss: 0.2095, step: 54000
+INFO - dpsgd_diffusion.py - 2024-10-24 08:35:36,723 - Saving snapshot checkpoint and sampling single batch at iteration 54000.
+WARNING - image.py - 2024-10-24 08:35:37,473 - 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 08:36:00,271 - FID at iteration 54000: 22.909948
+INFO - dpsgd_diffusion.py - 2024-10-24 08:38:20,474 - Loss: 0.1995, step: 54100
+INFO - dpsgd_diffusion.py - 2024-10-24 08:40:40,976 - Loss: 0.2476, step: 54200
+INFO - dpsgd_diffusion.py - 2024-10-24 08:40:52,685 - Eps-value after 121 epochs: 8.8304
+INFO - dpsgd_diffusion.py - 2024-10-24 08:43:03,571 - Loss: 0.2317, step: 54300
+INFO - dpsgd_diffusion.py - 2024-10-24 08:45:23,402 - Loss: 0.2385, step: 54400
+INFO - dpsgd_diffusion.py - 2024-10-24 08:47:46,534 - Loss: 0.2266, step: 54500
+INFO - dpsgd_diffusion.py - 2024-10-24 08:50:07,287 - Loss: 0.2247, step: 54600
+INFO - dpsgd_diffusion.py - 2024-10-24 08:51:26,168 - Eps-value after 122 epochs: 8.8718
+INFO - dpsgd_diffusion.py - 2024-10-24 08:52:27,437 - Loss: 0.2154, step: 54700
+INFO - dpsgd_diffusion.py - 2024-10-24 08:54:44,241 - Loss: 0.2170, step: 54800
+INFO - dpsgd_diffusion.py - 2024-10-24 08:57:07,138 - Loss: 0.2243, step: 54900
+INFO - dpsgd_diffusion.py - 2024-10-24 08:59:25,764 - Loss: 0.2198, step: 55000
+INFO - dpsgd_diffusion.py - 2024-10-24 09:01:54,440 - Loss: 0.2016, step: 55100
+INFO - dpsgd_diffusion.py - 2024-10-24 09:02:00,276 - Eps-value after 123 epochs: 8.9132
+INFO - dpsgd_diffusion.py - 2024-10-24 09:04:14,563 - Loss: 0.2084, step: 55200
+INFO - dpsgd_diffusion.py - 2024-10-24 09:06:32,837 - Loss: 0.2324, step: 55300
+INFO - dpsgd_diffusion.py - 2024-10-24 09:08:54,078 - Loss: 0.2351, step: 55400
+INFO - dpsgd_diffusion.py - 2024-10-24 09:10:52,299 - Loss: 0.2342, step: 55500
+INFO - dpsgd_diffusion.py - 2024-10-24 09:12:05,432 - Eps-value after 124 epochs: 8.9546
+INFO - dpsgd_diffusion.py - 2024-10-24 09:13:12,097 - Loss: 0.2227, step: 55600
+INFO - dpsgd_diffusion.py - 2024-10-24 09:15:34,634 - Loss: 0.2614, step: 55700
+INFO - dpsgd_diffusion.py - 2024-10-24 09:17:56,507 - Loss: 0.2399, step: 55800
+INFO - dpsgd_diffusion.py - 2024-10-24 09:20:16,577 - Loss: 0.2187, step: 55900
+INFO - dpsgd_diffusion.py - 2024-10-24 09:22:43,251 - Loss: 0.2195, step: 56000
+INFO - dpsgd_diffusion.py - 2024-10-24 09:22:43,274 - Eps-value after 125 epochs: 8.9960
+INFO - dpsgd_diffusion.py - 2024-10-24 09:22:43,287 - Saving snapshot checkpoint and sampling single batch at iteration 56000.
+WARNING - image.py - 2024-10-24 09:22:43,901 - 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 09:23:05,716 - FID at iteration 56000: 22.583436
+INFO - dpsgd_diffusion.py - 2024-10-24 09:25:17,363 - Loss: 0.2267, step: 56100
+INFO - dpsgd_diffusion.py - 2024-10-24 09:27:41,840 - Loss: 0.2275, step: 56200
+INFO - dpsgd_diffusion.py - 2024-10-24 09:29:55,721 - Loss: 0.2411, step: 56300
+INFO - dpsgd_diffusion.py - 2024-10-24 09:32:15,180 - Loss: 0.2351, step: 56400
+INFO - dpsgd_diffusion.py - 2024-10-24 09:33:22,181 - Eps-value after 126 epochs: 9.0374
+INFO - dpsgd_diffusion.py - 2024-10-24 09:34:33,868 - Loss: 0.2253, step: 56500
+INFO - dpsgd_diffusion.py - 2024-10-24 09:36:56,018 - Loss: 0.2351, step: 56600
+INFO - dpsgd_diffusion.py - 2024-10-24 09:39:14,746 - Loss: 0.2401, step: 56700
+INFO - dpsgd_diffusion.py - 2024-10-24 09:41:31,592 - Loss: 0.2330, step: 56800
+INFO - dpsgd_diffusion.py - 2024-10-24 09:43:34,143 - Eps-value after 127 epochs: 9.0788
+INFO - dpsgd_diffusion.py - 2024-10-24 09:43:40,453 - Loss: 0.2223, step: 56900
+INFO - dpsgd_diffusion.py - 2024-10-24 09:46:03,962 - Loss: 0.2203, step: 57000
+INFO - dpsgd_diffusion.py - 2024-10-24 09:48:25,620 - Loss: 0.2455, step: 57100
+INFO - dpsgd_diffusion.py - 2024-10-24 09:50:43,749 - Loss: 0.2178, step: 57200
+INFO - dpsgd_diffusion.py - 2024-10-24 09:53:06,265 - Loss: 0.2198, step: 57300
+INFO - dpsgd_diffusion.py - 2024-10-24 09:54:08,314 - Eps-value after 128 epochs: 9.1201
+INFO - dpsgd_diffusion.py - 2024-10-24 09:55:27,029 - Loss: 0.2227, step: 57400
+INFO - dpsgd_diffusion.py - 2024-10-24 09:57:47,179 - Loss: 0.2165, step: 57500
+INFO - dpsgd_diffusion.py - 2024-10-24 09:59:57,429 - Loss: 0.2413, step: 57600
+INFO - dpsgd_diffusion.py - 2024-10-24 10:02:18,998 - Loss: 0.2259, step: 57700
+INFO - dpsgd_diffusion.py - 2024-10-24 10:04:25,223 - Eps-value after 129 epochs: 9.1606
+INFO - dpsgd_diffusion.py - 2024-10-24 10:04:37,052 - Loss: 0.2124, step: 57800
+INFO - dpsgd_diffusion.py - 2024-10-24 10:06:57,963 - Loss: 0.2064, step: 57900
+INFO - dpsgd_diffusion.py - 2024-10-24 10:09:18,913 - Loss: 0.2538, step: 58000
+INFO - dpsgd_diffusion.py - 2024-10-24 10:09:18,929 - Saving snapshot checkpoint and sampling single batch at iteration 58000.
+WARNING - image.py - 2024-10-24 10:09:19,580 - 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 10:09:41,474 - FID at iteration 58000: 22.866725
+INFO - dpsgd_diffusion.py - 2024-10-24 10:12:06,802 - Loss: 0.2327, step: 58100
+INFO - dpsgd_diffusion.py - 2024-10-24 10:14:18,784 - Loss: 0.2269, step: 58200
+INFO - dpsgd_diffusion.py - 2024-10-24 10:15:09,944 - Eps-value after 130 epochs: 9.2009
+INFO - dpsgd_diffusion.py - 2024-10-24 10:16:33,394 - Loss: 0.2343, step: 58300
+INFO - dpsgd_diffusion.py - 2024-10-24 10:18:56,064 - Loss: 0.2122, step: 58400
+INFO - dpsgd_diffusion.py - 2024-10-24 10:21:16,553 - Loss: 0.2022, step: 58500
+INFO - dpsgd_diffusion.py - 2024-10-24 10:23:37,340 - Loss: 0.2387, step: 58600
+INFO - dpsgd_diffusion.py - 2024-10-24 10:25:39,690 - Eps-value after 131 epochs: 9.2411
+INFO - dpsgd_diffusion.py - 2024-10-24 10:25:55,068 - Loss: 0.2248, step: 58700
+INFO - dpsgd_diffusion.py - 2024-10-24 10:28:16,783 - Loss: 0.2253, step: 58800
+INFO - dpsgd_diffusion.py - 2024-10-24 10:30:39,145 - Loss: 0.2093, step: 58900
+INFO - dpsgd_diffusion.py - 2024-10-24 10:32:44,988 - Loss: 0.2397, step: 59000
+INFO - dpsgd_diffusion.py - 2024-10-24 10:35:05,990 - Loss: 0.1918, step: 59100
+INFO - dpsgd_diffusion.py - 2024-10-24 10:35:55,903 - Eps-value after 132 epochs: 9.2814
+INFO - dpsgd_diffusion.py - 2024-10-24 10:37:26,525 - Loss: 0.2094, step: 59200
+INFO - dpsgd_diffusion.py - 2024-10-24 10:39:46,423 - Loss: 0.2187, step: 59300
+INFO - dpsgd_diffusion.py - 2024-10-24 10:42:10,309 - Loss: 0.2424, step: 59400
+INFO - dpsgd_diffusion.py - 2024-10-24 10:44:33,375 - Loss: 0.2058, step: 59500
+INFO - dpsgd_diffusion.py - 2024-10-24 10:46:32,525 - Eps-value after 133 epochs: 9.3216
+INFO - dpsgd_diffusion.py - 2024-10-24 10:46:54,659 - Loss: 0.2402, step: 59600
+INFO - dpsgd_diffusion.py - 2024-10-24 10:49:03,901 - Loss: 0.2298, step: 59700
+INFO - dpsgd_diffusion.py - 2024-10-24 10:51:23,928 - Loss: 0.2047, step: 59800
+INFO - dpsgd_diffusion.py - 2024-10-24 10:53:42,525 - Loss: 0.2133, step: 59900
+INFO - dpsgd_diffusion.py - 2024-10-24 10:56:05,267 - Loss: 0.2111, step: 60000
+INFO - dpsgd_diffusion.py - 2024-10-24 10:56:05,285 - Saving snapshot checkpoint and sampling single batch at iteration 60000.
+WARNING - image.py - 2024-10-24 10:56:06,340 - 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 10:56:29,484 - FID at iteration 60000: 22.124927
+INFO - dpsgd_diffusion.py - 2024-10-24 10:57:20,404 - Eps-value after 134 epochs: 9.3618
+INFO - dpsgd_diffusion.py - 2024-10-24 10:58:59,837 - Loss: 0.2189, step: 60100
+INFO - dpsgd_diffusion.py - 2024-10-24 11:01:17,493 - Loss: 0.2190, step: 60200
+INFO - dpsgd_diffusion.py - 2024-10-24 11:03:36,507 - Loss: 0.2319, step: 60300
+INFO - dpsgd_diffusion.py - 2024-10-24 11:05:57,687 - Loss: 0.2193, step: 60400
+INFO - dpsgd_diffusion.py - 2024-10-24 11:07:53,789 - Eps-value after 135 epochs: 9.4021
+INFO - dpsgd_diffusion.py - 2024-10-24 11:08:22,101 - Loss: 0.2278, step: 60500
+INFO - dpsgd_diffusion.py - 2024-10-24 11:10:45,891 - Loss: 0.1877, step: 60600
+INFO - dpsgd_diffusion.py - 2024-10-24 11:13:02,554 - Loss: 0.2070, step: 60700
+INFO - dpsgd_diffusion.py - 2024-10-24 11:15:23,612 - Loss: 0.2313, step: 60800
+INFO - dpsgd_diffusion.py - 2024-10-24 11:17:42,252 - Loss: 0.2245, step: 60900
+INFO - dpsgd_diffusion.py - 2024-10-24 11:18:24,133 - Eps-value after 136 epochs: 9.4423
+INFO - dpsgd_diffusion.py - 2024-10-24 11:20:00,005 - Loss: 0.2293, step: 61000
+INFO - dpsgd_diffusion.py - 2024-10-24 11:22:23,551 - Loss: 0.2217, step: 61100
+INFO - dpsgd_diffusion.py - 2024-10-24 11:24:42,636 - Loss: 0.2535, step: 61200
+INFO - dpsgd_diffusion.py - 2024-10-24 11:27:02,601 - Loss: 0.2272, step: 61300
+INFO - dpsgd_diffusion.py - 2024-10-24 11:28:48,540 - Eps-value after 137 epochs: 9.4826
+INFO - dpsgd_diffusion.py - 2024-10-24 11:29:21,972 - Loss: 0.2414, step: 61400
+INFO - dpsgd_diffusion.py - 2024-10-24 11:31:42,517 - Loss: 0.2369, step: 61500
+INFO - dpsgd_diffusion.py - 2024-10-24 11:34:00,373 - Loss: 0.2403, step: 61600
+INFO - dpsgd_diffusion.py - 2024-10-24 11:36:14,884 - Loss: 0.2376, step: 61700
+INFO - dpsgd_diffusion.py - 2024-10-24 11:38:38,979 - Loss: 0.2256, step: 61800
+INFO - dpsgd_diffusion.py - 2024-10-24 11:39:11,425 - Eps-value after 138 epochs: 9.5228
+INFO - dpsgd_diffusion.py - 2024-10-24 11:41:00,590 - Loss: 0.2153, step: 61900
+INFO - dpsgd_diffusion.py - 2024-10-24 11:43:23,387 - Loss: 0.2100, step: 62000
+INFO - dpsgd_diffusion.py - 2024-10-24 11:43:23,400 - Saving snapshot checkpoint and sampling single batch at iteration 62000.
+WARNING - image.py - 2024-10-24 11:43:24,203 - 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 11:43:48,051 - FID at iteration 62000: 22.101074
+INFO - dpsgd_diffusion.py - 2024-10-24 11:46:10,885 - Loss: 0.2491, step: 62100
+INFO - dpsgd_diffusion.py - 2024-10-24 11:48:33,476 - Loss: 0.2314, step: 62200
+INFO - dpsgd_diffusion.py - 2024-10-24 11:50:12,828 - Eps-value after 139 epochs: 9.5626
+INFO - dpsgd_diffusion.py - 2024-10-24 11:50:50,029 - Loss: 0.2223, step: 62300
+INFO - dpsgd_diffusion.py - 2024-10-24 11:52:44,305 - Loss: 0.2385, step: 62400
+INFO - dpsgd_diffusion.py - 2024-10-24 11:55:04,849 - Loss: 0.2418, step: 62500
+INFO - dpsgd_diffusion.py - 2024-10-24 11:57:27,379 - Loss: 0.2113, step: 62600
+INFO - dpsgd_diffusion.py - 2024-10-24 11:59:46,302 - Loss: 0.2437, step: 62700
+INFO - dpsgd_diffusion.py - 2024-10-24 12:00:13,822 - Eps-value after 140 epochs: 9.6017
+INFO - dpsgd_diffusion.py - 2024-10-24 12:02:08,969 - Loss: 0.2292, step: 62800
+INFO - dpsgd_diffusion.py - 2024-10-24 12:04:26,810 - Loss: 0.2175, step: 62900
+INFO - dpsgd_diffusion.py - 2024-10-24 12:06:45,300 - Loss: 0.2469, step: 63000
+INFO - dpsgd_diffusion.py - 2024-10-24 12:08:58,495 - Loss: 0.2158, step: 63100
+INFO - dpsgd_diffusion.py - 2024-10-24 12:10:35,278 - Eps-value after 141 epochs: 9.6408
+INFO - dpsgd_diffusion.py - 2024-10-24 12:11:20,663 - Loss: 0.2266, step: 63200
+INFO - dpsgd_diffusion.py - 2024-10-24 12:13:40,525 - Loss: 0.2448, step: 63300
+INFO - dpsgd_diffusion.py - 2024-10-24 12:16:04,793 - Loss: 0.2199, step: 63400
+INFO - dpsgd_diffusion.py - 2024-10-24 12:18:28,172 - Loss: 0.2291, step: 63500
+INFO - dpsgd_diffusion.py - 2024-10-24 12:20:49,576 - Loss: 0.2146, step: 63600
+INFO - dpsgd_diffusion.py - 2024-10-24 12:21:12,609 - Eps-value after 142 epochs: 9.6799
+INFO - dpsgd_diffusion.py - 2024-10-24 12:23:09,228 - Loss: 0.2365, step: 63700
+INFO - dpsgd_diffusion.py - 2024-10-24 12:25:10,245 - Loss: 0.2253, step: 63800
+INFO - dpsgd_diffusion.py - 2024-10-24 12:27:32,149 - Loss: 0.2193, step: 63900
+INFO - dpsgd_diffusion.py - 2024-10-24 12:29:55,542 - Loss: 0.2136, step: 64000
+INFO - dpsgd_diffusion.py - 2024-10-24 12:29:55,560 - Saving snapshot checkpoint and sampling single batch at iteration 64000.
+WARNING - image.py - 2024-10-24 12:29:56,239 - 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 12:30:16,493 - FID at iteration 64000: 21.504730
+INFO - dpsgd_diffusion.py - 2024-10-24 12:31:52,349 - Eps-value after 143 epochs: 9.7190
+INFO - dpsgd_diffusion.py - 2024-10-24 12:32:44,076 - Loss: 0.2114, step: 64100
+INFO - dpsgd_diffusion.py - 2024-10-24 12:35:06,963 - Loss: 0.2327, step: 64200
+INFO - dpsgd_diffusion.py - 2024-10-24 12:37:26,805 - Loss: 0.2264, step: 64300
+INFO - dpsgd_diffusion.py - 2024-10-24 12:39:52,549 - Loss: 0.2250, step: 64400
+INFO - dpsgd_diffusion.py - 2024-10-24 12:42:10,673 - Loss: 0.2267, step: 64500
+INFO - dpsgd_diffusion.py - 2024-10-24 12:42:27,847 - Eps-value after 144 epochs: 9.7581
+INFO - dpsgd_diffusion.py - 2024-10-24 12:44:30,615 - Loss: 0.2206, step: 64600
+INFO - dpsgd_diffusion.py - 2024-10-24 12:46:54,417 - Loss: 0.2215, step: 64700
+INFO - dpsgd_diffusion.py - 2024-10-24 12:49:15,289 - Loss: 0.2106, step: 64800
+INFO - dpsgd_diffusion.py - 2024-10-24 12:51:35,916 - Loss: 0.2357, step: 64900
+INFO - dpsgd_diffusion.py - 2024-10-24 12:52:57,244 - Eps-value after 145 epochs: 9.7972
+INFO - dpsgd_diffusion.py - 2024-10-24 12:53:56,904 - Loss: 0.1992, step: 65000
+INFO - dpsgd_diffusion.py - 2024-10-24 12:56:16,382 - Loss: 0.2201, step: 65100
+INFO - dpsgd_diffusion.py - 2024-10-24 12:58:28,288 - Loss: 0.2202, step: 65200
+INFO - dpsgd_diffusion.py - 2024-10-24 13:00:46,582 - Loss: 0.2201, step: 65300
+INFO - dpsgd_diffusion.py - 2024-10-24 13:03:07,384 - Loss: 0.2086, step: 65400
+INFO - dpsgd_diffusion.py - 2024-10-24 13:03:18,674 - Eps-value after 146 epochs: 9.8363
+INFO - dpsgd_diffusion.py - 2024-10-24 13:05:24,699 - Loss: 0.2200, step: 65500
+INFO - dpsgd_diffusion.py - 2024-10-24 13:07:46,861 - Loss: 0.2228, step: 65600
+INFO - dpsgd_diffusion.py - 2024-10-24 13:10:06,759 - Loss: 0.2296, step: 65700
+INFO - dpsgd_diffusion.py - 2024-10-24 13:12:27,481 - Loss: 0.1913, step: 65800
+INFO - dpsgd_diffusion.py - 2024-10-24 13:13:36,116 - Eps-value after 147 epochs: 9.8754
+INFO - dpsgd_diffusion.py - 2024-10-24 13:14:41,644 - Loss: 0.2183, step: 65900
+INFO - dpsgd_diffusion.py - 2024-10-24 13:17:04,992 - Loss: 0.2076, step: 66000
+INFO - dpsgd_diffusion.py - 2024-10-24 13:17:05,007 - Saving snapshot checkpoint and sampling single batch at iteration 66000.
+WARNING - image.py - 2024-10-24 13:17:05,896 - 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 13:17:28,868 - FID at iteration 66000: 21.328273
+INFO - dpsgd_diffusion.py - 2024-10-24 13:19:55,670 - Loss: 0.2445, step: 66100
+INFO - dpsgd_diffusion.py - 2024-10-24 13:22:19,383 - Loss: 0.2383, step: 66200
+INFO - dpsgd_diffusion.py - 2024-10-24 13:24:40,188 - Loss: 0.2114, step: 66300
+INFO - dpsgd_diffusion.py - 2024-10-24 13:24:46,118 - Eps-value after 148 epochs: 9.9145
+INFO - dpsgd_diffusion.py - 2024-10-24 13:27:00,432 - Loss: 0.2214, step: 66400
+INFO - dpsgd_diffusion.py - 2024-10-24 13:29:15,098 - Loss: 0.2059, step: 66500
+INFO - dpsgd_diffusion.py - 2024-10-24 13:31:36,839 - Loss: 0.2382, step: 66600
+INFO - dpsgd_diffusion.py - 2024-10-24 13:33:58,138 - Loss: 0.2035, step: 66700
+INFO - dpsgd_diffusion.py - 2024-10-24 13:35:11,513 - Eps-value after 149 epochs: 9.9536
+INFO - dpsgd_diffusion.py - 2024-10-24 13:36:21,569 - Loss: 0.2059, step: 66800
+INFO - dpsgd_diffusion.py - 2024-10-24 13:38:40,719 - Loss: 0.2525, step: 66900
+INFO - dpsgd_diffusion.py - 2024-10-24 13:40:59,816 - Loss: 0.2273, step: 67000
+INFO - dpsgd_diffusion.py - 2024-10-24 13:43:18,661 - Loss: 0.2137, step: 67100
+INFO - dpsgd_diffusion.py - 2024-10-24 13:45:32,316 - Loss: 0.2068, step: 67200
+INFO - dpsgd_diffusion.py - 2024-10-24 13:45:32,414 - Eps-value after 150 epochs: 9.9927
+INFO - dpsgd_diffusion.py - 2024-10-24 13:45:32,933 - Saving final checkpoint.
+INFO - dpsgd_diffusion.py - 2024-10-24 13:45:32,936 - start to generate 60000 samples
+INFO - dpsgd_diffusion.py - 2024-10-24 15:22:14,893 - Generation Finished!
+INFO - dataset_loader.py - 2024-10-24 17:20:35,141 - delta is reset as 1.6657508770018431e-06
+INFO - evaluator.py - 2024-10-24 17:21:21,336 - Epoch: 0 Train acc: 64.30727272727272 Val acc: 73.92 Test acc74.26; Train loss: 0.003753715387799523 Val loss: 0.0007997158408164978
+INFO - evaluator.py - 2024-10-24 17:21:44,054 - Epoch: 1 Train acc: 84.63272727272727 Val acc: 80.67999999999999 Test acc80.5; Train loss: 0.0016207402256402101 Val loss: 0.0005832382082939148
+INFO - evaluator.py - 2024-10-24 17:22:07,007 - Epoch: 2 Train acc: 89.32181818181817 Val acc: 81.74 Test acc81.44; Train loss: 0.001162975063920021 Val loss: 0.0005607245922088623
+INFO - evaluator.py - 2024-10-24 17:22:29,767 - Epoch: 3 Train acc: 91.02909090909091 Val acc: 56.86 Test acc56.99999999999999; Train loss: 0.0009719948012720455 Val loss: 0.00165966694355011
+INFO - evaluator.py - 2024-10-24 17:22:52,578 - Epoch: 4 Train acc: 91.74 Val acc: 78.82000000000001 Test acc78.31; Train loss: 0.0008848793410442092 Val loss: 0.0007536486268043518
+INFO - evaluator.py - 2024-10-24 17:23:14,419 - Epoch: 5 Train acc: 92.53818181818183 Val acc: 73.98 Test acc74.65; Train loss: 0.0008067886967550624 Val loss: 0.0007662242889404297
+INFO - evaluator.py - 2024-10-24 17:23:36,209 - Epoch: 6 Train acc: 93.02363636363637 Val acc: 58.34 Test acc58.26; Train loss: 0.0007541830100796439 Val loss: 0.0016630279064178467
+INFO - evaluator.py - 2024-10-24 17:23:58,633 - Epoch: 7 Train acc: 93.25818181818181 Val acc: 36.8 Test acc36.85; Train loss: 0.0007252473809502342 Val loss: 0.00561295108795166
+INFO - evaluator.py - 2024-10-24 17:24:21,387 - Epoch: 8 Train acc: 93.57272727272728 Val acc: 83.39999999999999 Test acc82.69999999999999; Train loss: 0.0006866924327882854 Val loss: 0.0005627961993217468
+INFO - evaluator.py - 2024-10-24 17:24:44,136 - Epoch: 9 Train acc: 93.97818181818181 Val acc: 77.25999999999999 Test acc77.03999999999999; Train loss: 0.0006422600842335008 Val loss: 0.0008108100414276123
+INFO - evaluator.py - 2024-10-24 17:25:06,219 - Epoch: 10 Train acc: 94.30909090909091 Val acc: 29.98 Test acc30.330000000000002; Train loss: 0.0006104734164747325 Val loss: 0.005041713142395019
+INFO - evaluator.py - 2024-10-24 17:25:29,106 - Epoch: 11 Train acc: 94.58909090909091 Val acc: 66.62 Test acc65.75; Train loss: 0.0005831104411320253 Val loss: 0.0016334578275680543
+INFO - evaluator.py - 2024-10-24 17:25:52,234 - Epoch: 12 Train acc: 94.77818181818182 Val acc: 47.9 Test acc48.39; Train loss: 0.0005605590584603223 Val loss: 0.0022773327350616456
+INFO - evaluator.py - 2024-10-24 17:26:15,288 - Epoch: 13 Train acc: 94.92545454545454 Val acc: 23.200000000000003 Test acc24.37; Train loss: 0.0005440835446119309 Val loss: 0.008411535835266113
+INFO - evaluator.py - 2024-10-24 17:26:38,516 - Epoch: 14 Train acc: 95.20363636363636 Val acc: 37.5 Test acc37.66; Train loss: 0.0005107785581865094 Val loss: 0.003887231159210205
+INFO - evaluator.py - 2024-10-24 17:27:01,740 - Epoch: 15 Train acc: 95.27818181818182 Val acc: 39.72 Test acc40.53; Train loss: 0.0005028716865588318 Val loss: 0.004193485069274902
+INFO - evaluator.py - 2024-10-24 17:27:23,852 - Epoch: 16 Train acc: 95.02909090909091 Val acc: 25.1 Test acc26.41; Train loss: 0.0005336968469348821 Val loss: 0.008315167427062987
+INFO - evaluator.py - 2024-10-24 17:27:45,684 - Epoch: 17 Train acc: 95.81818181818181 Val acc: 75.7 Test acc74.49; Train loss: 0.0004490585555407134 Val loss: 0.0009738222479820252
+INFO - evaluator.py - 2024-10-24 17:28:08,554 - Epoch: 18 Train acc: 95.9509090909091 Val acc: 78.94 Test acc77.78; Train loss: 0.0004287759461186149 Val loss: 0.0008525321364402771
+INFO - evaluator.py - 2024-10-24 17:28:30,657 - Epoch: 19 Train acc: 96.30727272727273 Val acc: 83.04 Test acc81.86; Train loss: 0.0003902865738353946 Val loss: 0.0006767844796180725
+INFO - evaluator.py - 2024-10-24 17:28:53,642 - Epoch: 20 Train acc: 98.06545454545454 Val acc: 84.54 Test acc83.7; Train loss: 0.00021204372542825612 Val loss: 0.0008075594067573547
+INFO - evaluator.py - 2024-10-24 17:29:16,314 - Epoch: 21 Train acc: 98.68363636363637 Val acc: 82.69999999999999 Test acc81.69999999999999; Train loss: 0.0001529895251786167 Val loss: 0.001267413282394409
+INFO - evaluator.py - 2024-10-24 17:29:38,749 - Epoch: 22 Train acc: 98.94727272727273 Val acc: 84.06 Test acc83.54; Train loss: 0.00012023433514616706 Val loss: 0.001219278073310852
+INFO - evaluator.py - 2024-10-24 17:30:01,153 - Epoch: 23 Train acc: 99.16909090909091 Val acc: 85.04 Test acc85.07000000000001; Train loss: 9.56639385570518e-05 Val loss: 0.0011879462242126465
+INFO - evaluator.py - 2024-10-24 17:30:23,077 - Epoch: 24 Train acc: 99.31818181818181 Val acc: 83.8 Test acc83.2; Train loss: 7.817751932889223e-05 Val loss: 0.001442926788330078
+INFO - evaluator.py - 2024-10-24 17:30:45,150 - Epoch: 25 Train acc: 99.38727272727273 Val acc: 85.0 Test acc84.64; Train loss: 6.778416837650267e-05 Val loss: 0.0013426559686660767
+INFO - evaluator.py - 2024-10-24 17:31:07,476 - Epoch: 26 Train acc: 99.44727272727273 Val acc: 83.94 Test acc83.26; Train loss: 5.835836260283196e-05 Val loss: 0.0016970876693725586
+INFO - evaluator.py - 2024-10-24 17:31:30,387 - Epoch: 27 Train acc: 99.56545454545454 Val acc: 85.52 Test acc85.27; Train loss: 4.7750307380391114e-05 Val loss: 0.0013500331163406373
+INFO - evaluator.py - 2024-10-24 17:31:52,293 - Epoch: 28 Train acc: 99.44727272727273 Val acc: 85.0 Test acc85.28999999999999; Train loss: 6.203616530401633e-05 Val loss: 0.0014658351182937621
+INFO - evaluator.py - 2024-10-24 17:32:14,452 - Epoch: 29 Train acc: 99.60909090909091 Val acc: 84.82 Test acc84.50999999999999; Train loss: 4.247985666787083e-05 Val loss: 0.0014904929399490357
+INFO - evaluator.py - 2024-10-24 17:32:36,274 - Epoch: 30 Train acc: 99.63090909090909 Val acc: 84.16 Test acc83.43; Train loss: 4.1652466733516616e-05 Val loss: 0.0018512935400009155
+INFO - evaluator.py - 2024-10-24 17:32:59,427 - Epoch: 31 Train acc: 99.65636363636364 Val acc: 86.02 Test acc85.31; Train loss: 3.906589172018523e-05 Val loss: 0.00145367329120636
+INFO - evaluator.py - 2024-10-24 17:33:22,269 - Epoch: 32 Train acc: 99.62 Val acc: 85.2 Test acc85.08; Train loss: 4.243580973389643e-05 Val loss: 0.0014548216342926026
+INFO - evaluator.py - 2024-10-24 17:33:44,445 - Epoch: 33 Train acc: 99.6509090909091 Val acc: 84.89999999999999 Test acc84.68; Train loss: 4.1017453248125755e-05 Val loss: 0.0016705624580383301
+INFO - evaluator.py - 2024-10-24 17:34:06,636 - Epoch: 34 Train acc: 99.66727272727273 Val acc: 84.89999999999999 Test acc84.85000000000001; Train loss: 3.611718320435929e-05 Val loss: 0.0016702004194259644
+INFO - evaluator.py - 2024-10-24 17:34:29,486 - Epoch: 35 Train acc: 99.73454545454545 Val acc: 85.42 Test acc85.3; Train loss: 3.0263206850081173e-05 Val loss: 0.0016155192852020264
+INFO - evaluator.py - 2024-10-24 17:34:51,548 - Epoch: 36 Train acc: 99.62363636363636 Val acc: 85.64 Test acc85.35000000000001; Train loss: 4.1134740305873986e-05 Val loss: 0.0015072488307952881
+INFO - evaluator.py - 2024-10-24 17:35:14,488 - Epoch: 37 Train acc: 99.69090909090909 Val acc: 84.78 Test acc84.8; Train loss: 4.008559372741729e-05 Val loss: 0.00168885817527771
+INFO - evaluator.py - 2024-10-24 17:35:36,634 - Epoch: 38 Train acc: 99.83818181818181 Val acc: 85.24000000000001 Test acc84.82; Train loss: 1.9509106735561296e-05 Val loss: 0.0017437598943710326
+INFO - evaluator.py - 2024-10-24 17:35:59,245 - Epoch: 39 Train acc: 99.72545454545455 Val acc: 84.94 Test acc84.93; Train loss: 2.93604274203641e-05 Val loss: 0.001749902081489563
+INFO - evaluator.py - 2024-10-24 17:36:21,149 - Epoch: 40 Train acc: 99.91454545454546 Val acc: 85.64 Test acc85.66; Train loss: 1.29160111351997e-05 Val loss: 0.0016751119136810303
+INFO - evaluator.py - 2024-10-24 17:36:42,814 - Epoch: 41 Train acc: 99.98363636363636 Val acc: 86.08 Test acc85.92; Train loss: 3.899563797974472e-06 Val loss: 0.0016873961687088013
+INFO - evaluator.py - 2024-10-24 17:37:05,445 - Epoch: 42 Train acc: 99.99272727272728 Val acc: 85.48 Test acc85.75; Train loss: 2.8333440420365977e-06 Val loss: 0.001826008629798889
+INFO - evaluator.py - 2024-10-24 17:37:28,187 - Epoch: 43 Train acc: 99.99818181818182 Val acc: 85.72 Test acc85.67; Train loss: 1.949200876498997e-06 Val loss: 0.001815032696723938
+INFO - evaluator.py - 2024-10-24 17:37:49,844 - Epoch: 44 Train acc: 99.99090909090908 Val acc: 85.7 Test acc85.61999999999999; Train loss: 1.8984577580505918e-06 Val loss: 0.0018932823181152343
+INFO - evaluator.py - 2024-10-24 17:38:12,448 - Epoch: 45 Train acc: 100.0 Val acc: 85.88 Test acc85.69; Train loss: 1.4112823796412241e-06 Val loss: 0.0019312548160552979
+INFO - evaluator.py - 2024-10-24 17:38:35,805 - Epoch: 46 Train acc: 99.99454545454546 Val acc: 86.1 Test acc85.66; Train loss: 1.6415826815401405e-06 Val loss: 0.0019189673900604249
+INFO - evaluator.py - 2024-10-24 17:38:58,488 - Epoch: 47 Train acc: 99.99272727272728 Val acc: 86.24000000000001 Test acc85.59; Train loss: 1.5877449450602977e-06 Val loss: 0.0019503499984741212
+INFO - evaluator.py - 2024-10-24 17:39:21,018 - Epoch: 48 Train acc: 100.0 Val acc: 85.84 Test acc85.50999999999999; Train loss: 8.448122165646055e-07 Val loss: 0.0019804360628128052
+INFO - evaluator.py - 2024-10-24 17:39:43,821 - Epoch: 49 Train acc: 99.99818181818182 Val acc: 86.04 Test acc85.50999999999999; Train loss: 1.1089960662502563e-06 Val loss: 0.002022393250465393
+INFO - evaluator.py - 2024-10-24 17:39:43,831 - The best acc of synthetic images on sensitive val and the corresponding acc on test dataset from resnet is 86.24000000000001 and 85.59
+INFO - evaluator.py - 2024-10-24 17:39:43,831 - The best acc of synthetic images on noisy sensitive val and the corresponding acc on test dataset from resnet is 86.24000000000001 and 85.59
+INFO - evaluator.py - 2024-10-24 17:39:43,831 - The best acc test dataset from resnet is 85.92
+INFO - evaluator.py - 2024-10-24 17:40:12,900 - Epoch: 0 Train acc: 74.57090909090908 Val acc: 77.52 Test acc77.45; Train loss: 0.0025919899647886104 Val loss: 0.0006274552345275878
+INFO - evaluator.py - 2024-10-24 17:40:39,142 - Epoch: 1 Train acc: 85.84727272727272 Val acc: 77.4 Test acc77.81; Train loss: 0.0014849605606360868 Val loss: 0.000697551167011261
+INFO - evaluator.py - 2024-10-24 17:41:05,559 - Epoch: 2 Train acc: 88.75636363636363 Val acc: 82.92 Test acc83.42; Train loss: 0.0011956000818447634 Val loss: 0.0005051714956760407
+INFO - evaluator.py - 2024-10-24 17:41:31,750 - Epoch: 3 Train acc: 90.77636363636363 Val acc: 84.3 Test acc84.45; Train loss: 0.0009816305087371306 Val loss: 0.0004621264636516571
+INFO - evaluator.py - 2024-10-24 17:41:58,091 - Epoch: 4 Train acc: 91.61818181818182 Val acc: 83.94 Test acc83.57; Train loss: 0.0009007347032427788 Val loss: 0.0005112506866455078
+INFO - evaluator.py - 2024-10-24 17:42:24,375 - Epoch: 5 Train acc: 92.12545454545455 Val acc: 84.61999999999999 Test acc85.03; Train loss: 0.0008409535246816549 Val loss: 0.000508880603313446
+INFO - evaluator.py - 2024-10-24 17:42:50,595 - Epoch: 6 Train acc: 92.79454545454546 Val acc: 85.72 Test acc85.97; Train loss: 0.000781183712048964 Val loss: 0.0004662060558795929
+INFO - evaluator.py - 2024-10-24 17:43:16,670 - Epoch: 7 Train acc: 93.25272727272727 Val acc: 85.5 Test acc85.76; Train loss: 0.0007267287078228864 Val loss: 0.00047241470217704773
+INFO - evaluator.py - 2024-10-24 17:43:42,954 - Epoch: 8 Train acc: 93.46909090909091 Val acc: 84.84 Test acc85.36; Train loss: 0.0006951599748297172 Val loss: 0.0005106703341007233
+INFO - evaluator.py - 2024-10-24 17:44:09,129 - Epoch: 9 Train acc: 93.74727272727273 Val acc: 84.22 Test acc83.78999999999999; Train loss: 0.0006707284576513551 Val loss: 0.0005440201997756958
+INFO - evaluator.py - 2024-10-24 17:44:35,274 - Epoch: 10 Train acc: 93.94363636363636 Val acc: 26.44 Test acc27.43; Train loss: 0.0006486997490579431 Val loss: 0.0074091547966003415
+INFO - evaluator.py - 2024-10-24 17:45:01,545 - Epoch: 11 Train acc: 94.16181818181818 Val acc: 84.3 Test acc84.0; Train loss: 0.0006297780268571594 Val loss: 0.0005492975711822509
+INFO - evaluator.py - 2024-10-24 17:45:27,672 - Epoch: 12 Train acc: 94.47090909090909 Val acc: 86.2 Test acc86.42; Train loss: 0.000591125882213766 Val loss: 0.00047593092918396
+INFO - evaluator.py - 2024-10-24 17:45:53,986 - Epoch: 13 Train acc: 94.43636363636364 Val acc: 82.89999999999999 Test acc82.82000000000001; Train loss: 0.0005825845099308274 Val loss: 0.0006000389218330383
+INFO - evaluator.py - 2024-10-24 17:46:20,361 - Epoch: 14 Train acc: 94.84545454545454 Val acc: 86.16 Test acc85.84; Train loss: 0.000550245008549907 Val loss: 0.000497216385602951
+INFO - evaluator.py - 2024-10-24 17:46:46,446 - Epoch: 15 Train acc: 95.07818181818182 Val acc: 83.24000000000001 Test acc83.36; Train loss: 0.0005294839439066974 Val loss: 0.0006444903492927552
+INFO - evaluator.py - 2024-10-24 17:47:12,566 - Epoch: 16 Train acc: 95.39999999999999 Val acc: 41.120000000000005 Test acc41.839999999999996; Train loss: 0.0005038399970666928 Val loss: 0.006891429424285889
+INFO - evaluator.py - 2024-10-24 17:47:38,591 - Epoch: 17 Train acc: 95.29636363636364 Val acc: 36.34 Test acc36.8; Train loss: 0.000495240083810958 Val loss: 0.006648624229431153
+INFO - evaluator.py - 2024-10-24 17:48:04,891 - Epoch: 18 Train acc: 95.63090909090909 Val acc: 38.42 Test acc39.17; Train loss: 0.00045436246987770905 Val loss: 0.0074730626106262205
+INFO - evaluator.py - 2024-10-24 17:48:31,045 - Epoch: 19 Train acc: 95.96363636363637 Val acc: 46.18 Test acc46.72; Train loss: 0.0004345520513301546 Val loss: 0.005500161743164062
+INFO - evaluator.py - 2024-10-24 17:48:56,965 - Epoch: 20 Train acc: 97.15090909090908 Val acc: 84.17999999999999 Test acc84.44; Train loss: 0.0003116978539661928 Val loss: 0.000852451491355896
+INFO - evaluator.py - 2024-10-24 17:49:23,070 - Epoch: 21 Train acc: 97.67090909090909 Val acc: 84.61999999999999 Test acc84.82; Train loss: 0.00026206952353770085 Val loss: 0.0009206931948661805
+INFO - evaluator.py - 2024-10-24 17:49:49,040 - Epoch: 22 Train acc: 97.77090909090909 Val acc: 85.84 Test acc86.05000000000001; Train loss: 0.00024437820491465654 Val loss: 0.0008267824053764343
+INFO - evaluator.py - 2024-10-24 17:50:15,199 - Epoch: 23 Train acc: 97.96000000000001 Val acc: 85.42 Test acc85.77; Train loss: 0.00021815181774171915 Val loss: 0.0009680254101753235
+INFO - evaluator.py - 2024-10-24 17:50:41,343 - Epoch: 24 Train acc: 98.07454545454546 Val acc: 84.7 Test acc85.42999999999999; Train loss: 0.00020730305698446252 Val loss: 0.0010661823868751525
+INFO - evaluator.py - 2024-10-24 17:51:07,461 - Epoch: 25 Train acc: 98.22 Val acc: 85.04 Test acc85.13; Train loss: 0.0001839050910689614 Val loss: 0.0011269762754440307
+INFO - evaluator.py - 2024-10-24 17:51:33,366 - Epoch: 26 Train acc: 98.45636363636365 Val acc: 84.76 Test acc85.31; Train loss: 0.00016720507812093604 Val loss: 0.0011911512851715087
+INFO - evaluator.py - 2024-10-24 17:51:59,354 - Epoch: 27 Train acc: 98.46181818181819 Val acc: 85.84 Test acc85.95; Train loss: 0.00015931589257988063 Val loss: 0.0011341878175735473
+INFO - evaluator.py - 2024-10-24 17:52:25,376 - Epoch: 28 Train acc: 98.66909090909091 Val acc: 84.92 Test acc84.68; Train loss: 0.00014438075270842423 Val loss: 0.0013848757028579713
+INFO - evaluator.py - 2024-10-24 17:52:51,447 - Epoch: 29 Train acc: 98.7309090909091 Val acc: 86.14 Test acc86.1; Train loss: 0.00013872523707422342 Val loss: 0.0011089305400848388
+INFO - evaluator.py - 2024-10-24 17:53:17,342 - Epoch: 30 Train acc: 98.86363636363636 Val acc: 85.18 Test acc85.64; Train loss: 0.00012140386899594556 Val loss: 0.0013660449266433715
+INFO - evaluator.py - 2024-10-24 17:53:43,523 - Epoch: 31 Train acc: 99.00727272727273 Val acc: 84.3 Test acc84.7; Train loss: 0.00011006722981110216 Val loss: 0.0014213927030563354
+INFO - evaluator.py - 2024-10-24 17:54:09,635 - Epoch: 32 Train acc: 98.95272727272727 Val acc: 85.54 Test acc85.97; Train loss: 0.0001079705350143327 Val loss: 0.0012749929189682008
+INFO - evaluator.py - 2024-10-24 17:54:35,558 - Epoch: 33 Train acc: 99.05454545454545 Val acc: 85.32 Test acc85.3; Train loss: 0.00010192874325439334 Val loss: 0.0014124044895172118
+INFO - evaluator.py - 2024-10-24 17:55:01,549 - Epoch: 34 Train acc: 99.15454545454546 Val acc: 85.06 Test acc85.36; Train loss: 9.19679631309753e-05 Val loss: 0.0014102689027786254
+INFO - evaluator.py - 2024-10-24 17:55:27,547 - Epoch: 35 Train acc: 99.1909090909091 Val acc: 85.9 Test acc86.24000000000001; Train loss: 8.571998595514081e-05 Val loss: 0.0012600409269332886
+INFO - evaluator.py - 2024-10-24 17:55:53,523 - Epoch: 36 Train acc: 99.24181818181819 Val acc: 85.26 Test acc85.06; Train loss: 8.157807946289805e-05 Val loss: 0.0014149523496627809
+INFO - evaluator.py - 2024-10-24 17:56:19,290 - Epoch: 37 Train acc: 99.33454545454545 Val acc: 85.82 Test acc86.33999999999999; Train loss: 7.141796609132804e-05 Val loss: 0.0013091350317001342
+INFO - evaluator.py - 2024-10-24 17:56:45,255 - Epoch: 38 Train acc: 99.30545454545454 Val acc: 85.22 Test acc85.36; Train loss: 7.270417624280196e-05 Val loss: 0.0014853752851486206
+INFO - evaluator.py - 2024-10-24 17:57:11,307 - Epoch: 39 Train acc: 99.36363636363636 Val acc: 86.1 Test acc86.2; Train loss: 7.258843589066104e-05 Val loss: 0.001275508999824524
+INFO - evaluator.py - 2024-10-24 17:57:37,310 - Epoch: 40 Train acc: 99.59818181818181 Val acc: 86.5 Test acc86.61; Train loss: 4.3578559916932137e-05 Val loss: 0.0013271548986434937
+INFO - evaluator.py - 2024-10-24 17:58:03,343 - Epoch: 41 Train acc: 99.69636363636364 Val acc: 86.22 Test acc86.25; Train loss: 3.650370096279816e-05 Val loss: 0.0014511178255081176
+INFO - evaluator.py - 2024-10-24 17:58:29,261 - Epoch: 42 Train acc: 99.72363636363636 Val acc: 86.04 Test acc86.24000000000001; Train loss: 3.194598356388848e-05 Val loss: 0.001508809471130371
+INFO - evaluator.py - 2024-10-24 17:58:55,205 - Epoch: 43 Train acc: 99.77272727272727 Val acc: 86.24000000000001 Test acc86.16; Train loss: 2.6275281852576883e-05 Val loss: 0.0015005032062530518
+INFO - evaluator.py - 2024-10-24 17:59:21,192 - Epoch: 44 Train acc: 99.74545454545455 Val acc: 85.66 Test acc85.64; Train loss: 3.0929690558696165e-05 Val loss: 0.0016915035724639892
+INFO - evaluator.py - 2024-10-24 17:59:47,074 - Epoch: 45 Train acc: 99.75272727272727 Val acc: 86.08 Test acc86.03; Train loss: 2.9593640348916364e-05 Val loss: 0.0015806642532348633
+INFO - evaluator.py - 2024-10-24 18:00:13,145 - Epoch: 46 Train acc: 99.79272727272728 Val acc: 85.94000000000001 Test acc85.41; Train loss: 2.5016214453551748e-05 Val loss: 0.0016591663122177123
+INFO - evaluator.py - 2024-10-24 18:00:39,173 - Epoch: 47 Train acc: 99.7890909090909 Val acc: 86.32 Test acc85.97; Train loss: 2.3866231195543976e-05 Val loss: 0.0016281510591506958
+INFO - evaluator.py - 2024-10-24 18:01:05,234 - Epoch: 48 Train acc: 99.77454545454545 Val acc: 85.76 Test acc85.45; Train loss: 2.4479676892091942e-05 Val loss: 0.0018022691249847413
+INFO - evaluator.py - 2024-10-24 18:01:31,050 - Epoch: 49 Train acc: 99.78181818181818 Val acc: 86.02 Test acc85.54; Train loss: 2.358938516699709e-05 Val loss: 0.0016767558813095094
+INFO - evaluator.py - 2024-10-24 18:01:31,055 - The best acc of synthetic images on sensitive val and the corresponding acc on test dataset from wrn is 86.5 and 86.61
+INFO - evaluator.py - 2024-10-24 18:01:31,056 - The best acc of synthetic images on noisy sensitive val and the corresponding acc on test dataset from wrn is 86.5 and 86.61
+INFO - evaluator.py - 2024-10-24 18:01:31,056 - The best acc test dataset from wrn is 86.61
+INFO - evaluator.py - 2024-10-24 18:03:12,754 - Epoch: 0 Train acc: 70.04363636363637 Val acc: 77.18 Test acc76.92; Train loss: 0.0038500053134831514 Val loss: 0.0006925102591514588
+INFO - evaluator.py - 2024-10-24 18:04:53,589 - Epoch: 1 Train acc: 86.65818181818182 Val acc: 78.28 Test acc78.16; Train loss: 0.0014145384146408602 Val loss: 0.0007602760195732117
+INFO - evaluator.py - 2024-10-24 18:06:34,542 - Epoch: 2 Train acc: 90.23636363636363 Val acc: 83.02000000000001 Test acc82.77; Train loss: 0.0010583941424434835 Val loss: 0.0005551889061927795
+INFO - evaluator.py - 2024-10-24 18:08:15,687 - Epoch: 3 Train acc: 91.54363636363637 Val acc: 81.94 Test acc81.82000000000001; Train loss: 0.0009117378549142318 Val loss: 0.0007521409630775451
+INFO - evaluator.py - 2024-10-24 18:09:56,634 - Epoch: 4 Train acc: 92.41636363636364 Val acc: 83.02000000000001 Test acc82.69999999999999; Train loss: 0.0008185667536475442 Val loss: 0.0006446353316307068
+INFO - evaluator.py - 2024-10-24 18:11:37,586 - Epoch: 5 Train acc: 92.86363636363636 Val acc: 79.22 Test acc78.79; Train loss: 0.0007584509818391366 Val loss: 0.0008464594960212708
+INFO - evaluator.py - 2024-10-24 18:13:18,509 - Epoch: 6 Train acc: 93.61090909090909 Val acc: 82.66 Test acc82.22; Train loss: 0.0006931278525428338 Val loss: 0.0006640716671943665
+INFO - evaluator.py - 2024-10-24 18:14:59,376 - Epoch: 7 Train acc: 93.78909090909092 Val acc: 80.54 Test acc79.69000000000001; Train loss: 0.0006649813890457154 Val loss: 0.0007744394063949585
+INFO - evaluator.py - 2024-10-24 18:16:40,115 - Epoch: 8 Train acc: 94.08 Val acc: 77.68 Test acc77.57; Train loss: 0.0006321621106429534 Val loss: 0.0008975414872169495
+INFO - evaluator.py - 2024-10-24 18:18:21,016 - Epoch: 9 Train acc: 94.48727272727272 Val acc: 27.779999999999998 Test acc27.96; Train loss: 0.0005971092851324515 Val loss: 0.007165910816192627
+INFO - evaluator.py - 2024-10-24 18:20:02,102 - Epoch: 10 Train acc: 94.87818181818182 Val acc: 84.46000000000001 Test acc83.91999999999999; Train loss: 0.0005467949920079924 Val loss: 0.0006392867803573608
+INFO - evaluator.py - 2024-10-24 18:21:43,033 - Epoch: 11 Train acc: 95.16909090909091 Val acc: 54.08 Test acc54.97; Train loss: 0.0005208625693212856 Val loss: 0.002077006483078003
+INFO - evaluator.py - 2024-10-24 18:23:23,956 - Epoch: 12 Train acc: 95.31454545454545 Val acc: 83.32000000000001 Test acc82.95; Train loss: 0.0004997284245761958 Val loss: 0.0007106273889541626
+INFO - evaluator.py - 2024-10-24 18:25:04,916 - Epoch: 13 Train acc: 95.47636363636364 Val acc: 25.779999999999998 Test acc25.480000000000004; Train loss: 0.00048184815245595845 Val loss: 0.009476711463928223
+INFO - evaluator.py - 2024-10-24 18:26:45,812 - Epoch: 14 Train acc: 95.85090909090908 Val acc: 81.64 Test acc81.49; Train loss: 0.00043823834827000444 Val loss: 0.00081088787317276
+INFO - evaluator.py - 2024-10-24 18:28:26,707 - Epoch: 15 Train acc: 96.11090909090909 Val acc: 80.86 Test acc80.96; Train loss: 0.0004141608101400462 Val loss: 0.0007853264451026916
+INFO - evaluator.py - 2024-10-24 18:30:07,572 - Epoch: 16 Train acc: 96.48 Val acc: 77.4 Test acc77.59; Train loss: 0.0003710356350649487 Val loss: 0.0012602279901504517
+INFO - evaluator.py - 2024-10-24 18:31:48,602 - Epoch: 17 Train acc: 96.74727272727273 Val acc: 28.26 Test acc28.310000000000002; Train loss: 0.00035596192370761524 Val loss: 0.011037184715270995
+INFO - evaluator.py - 2024-10-24 18:33:29,245 - Epoch: 18 Train acc: 97.18545454545455 Val acc: 27.860000000000003 Test acc27.810000000000002; Train loss: 0.0003051492186432535 Val loss: 0.012182673072814941
+INFO - evaluator.py - 2024-10-24 18:35:09,940 - Epoch: 19 Train acc: 97.43272727272728 Val acc: 33.019999999999996 Test acc33.42; Train loss: 0.00028276830965822395 Val loss: 0.005020775699615478
+INFO - evaluator.py - 2024-10-24 18:36:50,748 - Epoch: 20 Train acc: 99.16181818181819 Val acc: 76.92 Test acc76.57000000000001; Train loss: 0.00010446498879993503 Val loss: 0.0014695037603378296
+INFO - evaluator.py - 2024-10-24 18:38:31,345 - Epoch: 21 Train acc: 99.77454545454545 Val acc: 83.84 Test acc83.07; Train loss: 3.511839786713773e-05 Val loss: 0.0013071451425552367
+INFO - evaluator.py - 2024-10-24 18:40:12,021 - Epoch: 22 Train acc: 99.91636363636364 Val acc: 85.1 Test acc84.45; Train loss: 1.6139877303926783e-05 Val loss: 0.0013702373743057251
+INFO - evaluator.py - 2024-10-24 18:41:52,692 - Epoch: 23 Train acc: 99.97090909090909 Val acc: 85.76 Test acc84.71; Train loss: 8.565211068807086e-06 Val loss: 0.0014060571908950806
+INFO - evaluator.py - 2024-10-24 18:43:33,520 - Epoch: 24 Train acc: 99.98 Val acc: 84.8 Test acc83.82; Train loss: 5.0563112697669895e-06 Val loss: 0.0016742568731307984
+INFO - dataset_loader.py - 2024-10-25 13:41:26,496 - delta is reset as 1.5148623360286113e-06
+INFO - evaluator.py - 2024-10-25 13:41:56,128 - Epoch: 0 Train acc: 65.2690909090909 Val acc: 85.13333333333334 Test acc77.46; Train loss: 0.0035248945599252526 Val loss: 0.0016244793004459804
+INFO - evaluator.py - 2024-10-25 13:42:17,851 - Epoch: 1 Train acc: 85.76727272727273 Val acc: 86.4888888888889 Test acc79.22; Train loss: 0.0014999411610039798 Val loss: 0.00148476599322425
+INFO - evaluator.py - 2024-10-25 13:42:39,339 - Epoch: 2 Train acc: 89.03818181818181 Val acc: 86.65555555555555 Test acc79.80000000000001; Train loss: 0.0011869215128096668 Val loss: 0.0014794857766893175
+INFO - evaluator.py - 2024-10-25 13:43:01,108 - Epoch: 3 Train acc: 90.66181818181818 Val acc: 88.94444444444444 Test acc82.92; Train loss: 0.0009989850878715516 Val loss: 0.0012532362325323953
+INFO - evaluator.py - 2024-10-25 13:43:22,874 - Epoch: 4 Train acc: 91.94 Val acc: 90.33333333333333 Test acc81.45; Train loss: 0.0008713242598555305 Val loss: 0.001100539474023713
+INFO - evaluator.py - 2024-10-25 13:43:44,561 - Epoch: 5 Train acc: 92.33454545454546 Val acc: 89.93333333333334 Test acc81.99; Train loss: 0.0008135517922314731 Val loss: 0.0010828906272848447
+INFO - evaluator.py - 2024-10-25 13:44:06,239 - Epoch: 6 Train acc: 92.94909090909091 Val acc: 89.18888888888888 Test acc80.43; Train loss: 0.000752015299553221 Val loss: 0.001102636141081651
+INFO - evaluator.py - 2024-10-25 13:44:27,788 - Epoch: 7 Train acc: 93.26363636363637 Val acc: 76.76666666666667 Test acc73.74000000000001; Train loss: 0.0007149735094471411 Val loss: 0.002835521356927024
+INFO - evaluator.py - 2024-10-25 13:44:49,555 - Epoch: 8 Train acc: 93.58363636363637 Val acc: 86.65555555555555 Test acc81.2; Train loss: 0.0006787185473875566 Val loss: 0.0013743337641159694
+INFO - evaluator.py - 2024-10-25 13:45:10,388 - Epoch: 9 Train acc: 93.96545454545453 Val acc: 87.1888888888889 Test acc79.94; Train loss: 0.0006413756249303167 Val loss: 0.0013920416914754443
+INFO - evaluator.py - 2024-10-25 13:45:31,957 - Epoch: 10 Train acc: 94.21090909090908 Val acc: 80.33333333333333 Test acc78.31; Train loss: 0.0006124121916565028 Val loss: 0.002863005002339681
+INFO - evaluator.py - 2024-10-25 13:45:53,557 - Epoch: 11 Train acc: 94.61454545454545 Val acc: 78.9 Test acc72.76; Train loss: 0.0005760341047563336 Val loss: 0.0035169703695509167
+INFO - evaluator.py - 2024-10-25 13:46:14,202 - Epoch: 12 Train acc: 94.62181818181818 Val acc: 80.41111111111111 Test acc75.5; Train loss: 0.0005707487405701117 Val loss: 0.0027879498932096695
+INFO - evaluator.py - 2024-10-25 13:46:35,178 - Epoch: 13 Train acc: 94.91818181818181 Val acc: 73.35555555555555 Test acc70.89; Train loss: 0.0005460276275195859 Val loss: 0.0042634791003333195
+INFO - evaluator.py - 2024-10-25 13:46:57,178 - Epoch: 14 Train acc: 95.19636363636363 Val acc: 73.91111111111111 Test acc66.97; Train loss: 0.0005161048030988736 Val loss: 0.004716316680113474
+INFO - evaluator.py - 2024-10-25 13:47:18,485 - Epoch: 15 Train acc: 95.26363636363637 Val acc: 75.84444444444445 Test acc71.47; Train loss: 0.0005092688598416069 Val loss: 0.003314987242221832
+INFO - evaluator.py - 2024-10-25 13:47:39,824 - Epoch: 16 Train acc: 95.40363636363637 Val acc: 75.78888888888888 Test acc74.44; Train loss: 0.0004889819907193834 Val loss: 0.003679179158475664
+INFO - evaluator.py - 2024-10-25 13:48:01,490 - Epoch: 17 Train acc: 95.68363636363635 Val acc: 60.633333333333326 Test acc61.5; Train loss: 0.0004571848661384799 Val loss: 0.00809208435482449
+INFO - evaluator.py - 2024-10-25 13:48:23,156 - Epoch: 18 Train acc: 95.95818181818181 Val acc: 50.088888888888896 Test acc48.370000000000005; Train loss: 0.0004325067118487575 Val loss: 0.01140657467312283
+INFO - evaluator.py - 2024-10-25 13:48:44,696 - Epoch: 19 Train acc: 96.22181818181818 Val acc: 75.42222222222222 Test acc72.1; Train loss: 0.000404639726199887 Val loss: 0.003754854659239451
+INFO - evaluator.py - 2024-10-25 13:49:06,302 - Epoch: 20 Train acc: 97.97454545454546 Val acc: 88.7 Test acc82.87; Train loss: 0.00022112593884495173 Val loss: 0.0015442994717094634
+INFO - evaluator.py - 2024-10-25 13:49:27,156 - Epoch: 21 Train acc: 98.60909090909091 Val acc: 92.18888888888888 Test acc83.91999999999999; Train loss: 0.00015543134612962603 Val loss: 0.0010650946282678181
+INFO - evaluator.py - 2024-10-25 13:49:47,792 - Epoch: 22 Train acc: 99.01636363636364 Val acc: 91.21111111111111 Test acc83.76; Train loss: 0.0001146528613414954 Val loss: 0.001310238523615731
+INFO - evaluator.py - 2024-10-25 13:50:09,489 - Epoch: 23 Train acc: 99.18 Val acc: 93.81111111111112 Test acc84.21; Train loss: 9.177100974643094e-05 Val loss: 0.0009588651532928149
+INFO - evaluator.py - 2024-10-25 13:50:30,247 - Epoch: 24 Train acc: 99.2909090909091 Val acc: 94.72222222222221 Test acc85.39999999999999; Train loss: 8.123031291179358e-05 Val loss: 0.000812945625020398
+INFO - evaluator.py - 2024-10-25 13:50:50,910 - Epoch: 25 Train acc: 99.40545454545455 Val acc: 91.38888888888889 Test acc83.6; Train loss: 6.864624055187133e-05 Val loss: 0.0016880643202198877
+INFO - evaluator.py - 2024-10-25 13:51:12,283 - Epoch: 26 Train acc: 99.47818181818182 Val acc: 94.28888888888889 Test acc85.31; Train loss: 6.262566012711349e-05 Val loss: 0.0010580181065532896
+INFO - evaluator.py - 2024-10-25 13:51:34,152 - Epoch: 27 Train acc: 99.53272727272727 Val acc: 92.63333333333334 Test acc82.84; Train loss: 5.2541519755455245e-05 Val loss: 0.0015032261924611198
+INFO - evaluator.py - 2024-10-25 13:51:55,711 - Epoch: 28 Train acc: 99.47090909090909 Val acc: 94.27777777777779 Test acc85.00999999999999; Train loss: 5.966900331814858e-05 Val loss: 0.001182419914338324
+INFO - evaluator.py - 2024-10-25 13:52:16,959 - Epoch: 29 Train acc: 99.53090909090909 Val acc: 93.66666666666667 Test acc84.39; Train loss: 5.258387119974941e-05 Val loss: 0.0012906156033277512
+INFO - evaluator.py - 2024-10-25 13:52:38,626 - Epoch: 30 Train acc: 99.50909090909092 Val acc: 92.06666666666666 Test acc83.81; Train loss: 5.4223492358472534e-05 Val loss: 0.0018423297223117616
+INFO - evaluator.py - 2024-10-25 13:52:59,729 - Epoch: 31 Train acc: 99.68727272727273 Val acc: 93.46666666666667 Test acc84.57000000000001; Train loss: 3.739200784422626e-05 Val loss: 0.0013859183192253112
+INFO - evaluator.py - 2024-10-25 13:53:21,261 - Epoch: 32 Train acc: 99.68909090909091 Val acc: 92.68888888888888 Test acc83.63000000000001; Train loss: 3.6625811203636906e-05 Val loss: 0.001618147451016638
+INFO - evaluator.py - 2024-10-25 13:53:42,878 - Epoch: 33 Train acc: 99.65818181818182 Val acc: 92.68888888888888 Test acc84.57000000000001; Train loss: 3.675599635568109e-05 Val loss: 0.001777411656247245
+INFO - evaluator.py - 2024-10-25 13:54:04,774 - Epoch: 34 Train acc: 99.59454545454545 Val acc: 91.57777777777778 Test acc83.72; Train loss: 4.4909567197530784e-05 Val loss: 0.00207866331603792
+INFO - evaluator.py - 2024-10-25 13:54:26,556 - Epoch: 35 Train acc: 99.6 Val acc: 91.08888888888889 Test acc82.49; Train loss: 4.242088925516741e-05 Val loss: 0.0023013799091180166
+INFO - evaluator.py - 2024-10-25 13:54:48,285 - Epoch: 36 Train acc: 99.68727272727273 Val acc: 91.02222222222223 Test acc83.45; Train loss: 3.549644305656495e-05 Val loss: 0.002483533180422253
+INFO - evaluator.py - 2024-10-25 13:55:09,915 - Epoch: 37 Train acc: 99.84363636363636 Val acc: 93.24444444444444 Test acc84.2; Train loss: 1.8330264157372187e-05 Val loss: 0.0016529358062479231
+INFO - evaluator.py - 2024-10-25 13:55:31,533 - Epoch: 38 Train acc: 99.69636363636364 Val acc: 94.41111111111111 Test acc85.07000000000001; Train loss: 3.6503316069402814e-05 Val loss: 0.0013123035579919815
+INFO - evaluator.py - 2024-10-25 13:55:53,126 - Epoch: 39 Train acc: 99.7690909090909 Val acc: 94.06666666666666 Test acc84.91; Train loss: 2.4537323939677497e-05 Val loss: 0.00135733028791017
+INFO - evaluator.py - 2024-10-25 13:56:14,954 - Epoch: 40 Train acc: 99.93636363636364 Val acc: 94.37777777777778 Test acc85.07000000000001; Train loss: 9.267636729716535e-06 Val loss: 0.0012932630827029545
+INFO - evaluator.py - 2024-10-25 13:56:36,547 - Epoch: 41 Train acc: 99.98545454545454 Val acc: 94.37777777777778 Test acc85.04; Train loss: 3.316980923938734e-06 Val loss: 0.0012436900271827148
+INFO - evaluator.py - 2024-10-25 13:56:57,184 - Epoch: 42 Train acc: 99.99636363636364 Val acc: 94.42222222222222 Test acc85.06; Train loss: 2.0779697625336914e-06 Val loss: 0.0013512312637435065
+INFO - evaluator.py - 2024-10-25 13:57:17,810 - Epoch: 43 Train acc: 99.99818181818182 Val acc: 94.55555555555556 Test acc85.15; Train loss: 1.5182325849309563e-06 Val loss: 0.0013144920385546155
+INFO - evaluator.py - 2024-10-25 13:57:38,812 - Epoch: 44 Train acc: 99.99636363636364 Val acc: 94.62222222222222 Test acc85.15; Train loss: 1.4545022870152025e-06 Val loss: 0.0014016557799445258
+INFO - evaluator.py - 2024-10-25 13:57:59,445 - Epoch: 45 Train acc: 99.99818181818182 Val acc: 94.53333333333333 Test acc85.26; Train loss: 1.0976670341981597e-06 Val loss: 0.0013638270033795076
+INFO - evaluator.py - 2024-10-25 13:58:20,253 - Epoch: 46 Train acc: 100.0 Val acc: 94.54444444444444 Test acc85.18; Train loss: 1.0920409749153558e-06 Val loss: 0.001381392387737934
+INFO - evaluator.py - 2024-10-25 13:58:41,334 - Epoch: 47 Train acc: 99.99818181818182 Val acc: 94.58888888888889 Test acc85.31; Train loss: 9.715943981063902e-07 Val loss: 0.0014348179410315221
+INFO - evaluator.py - 2024-10-25 13:59:03,040 - Epoch: 48 Train acc: 99.99272727272728 Val acc: 94.44444444444444 Test acc84.94; Train loss: 1.5440552877573117e-06 Val loss: 0.0015157215462790596
+INFO - evaluator.py - 2024-10-25 13:59:24,677 - Epoch: 49 Train acc: 99.99454545454546 Val acc: 94.61111111111111 Test acc85.31; Train loss: 1.0073305692540916e-06 Val loss: 0.0015340511674682299
+INFO - evaluator.py - 2024-10-25 13:59:24,687 - The best acc of synthetic images on val and the corresponding acc on test dataset from resnet is 94.72222222222221 and 85.39999999999999
+INFO - evaluator.py - 2024-10-25 13:59:24,687 - The best acc test dataset from resnet is 85.39999999999999
+INFO - evaluator.py - 2024-10-25 13:59:50,941 - Epoch: 0 Train acc: 74.23272727272727 Val acc: 84.75555555555555 Test acc77.57; Train loss: 0.0025270258475433697 Val loss: 0.0015847583678033617
+INFO - evaluator.py - 2024-10-25 14:00:15,871 - Epoch: 1 Train acc: 85.88 Val acc: 86.33333333333333 Test acc80.35; Train loss: 0.001481670967015353 Val loss: 0.001486545400487052
+INFO - evaluator.py - 2024-10-25 14:00:40,797 - Epoch: 2 Train acc: 89.56181818181818 Val acc: 84.24444444444444 Test acc78.92; Train loss: 0.0011028494330969723 Val loss: 0.0017177856961886088
+INFO - evaluator.py - 2024-10-25 14:01:05,862 - Epoch: 3 Train acc: 91.24363636363636 Val acc: 92.14444444444445 Test acc85.2; Train loss: 0.0009440761270848188 Val loss: 0.0008756862100627687
+INFO - evaluator.py - 2024-10-25 14:01:30,763 - Epoch: 4 Train acc: 91.80363636363637 Val acc: 88.56666666666668 Test acc82.28999999999999; Train loss: 0.0008643495418808677 Val loss: 0.0012394090708759097
+INFO - evaluator.py - 2024-10-25 14:01:55,706 - Epoch: 5 Train acc: 92.58 Val acc: 91.72222222222223 Test acc84.38; Train loss: 0.0007845633789896965 Val loss: 0.0009050019747681088
+INFO - evaluator.py - 2024-10-25 14:02:20,659 - Epoch: 6 Train acc: 92.99272727272727 Val acc: 60.3 Test acc55.620000000000005; Train loss: 0.0007515512123703956 Val loss: 0.006778333293067085
+INFO - evaluator.py - 2024-10-25 14:02:45,611 - Epoch: 7 Train acc: 93.44545454545454 Val acc: 92.72222222222221 Test acc84.50999999999999; Train loss: 0.0006956091502850705 Val loss: 0.0007652392867538664
+INFO - evaluator.py - 2024-10-25 14:03:10,515 - Epoch: 8 Train acc: 94.08909090909091 Val acc: 59.66666666666667 Test acc52.12; Train loss: 0.000647167048941959 Val loss: 0.00960610416200426
+INFO - evaluator.py - 2024-10-25 14:03:35,573 - Epoch: 9 Train acc: 93.94181818181818 Val acc: 92.4 Test acc85.08; Train loss: 0.0006431626235896891 Val loss: 0.0008276078585121367
+INFO - evaluator.py - 2024-10-25 14:04:00,517 - Epoch: 10 Train acc: 94.2290909090909 Val acc: 82.77777777777777 Test acc79.57; Train loss: 0.0006092716412110762 Val loss: 0.0024643313454257116
+INFO - evaluator.py - 2024-10-25 14:04:25,458 - Epoch: 11 Train acc: 94.74000000000001 Val acc: 72.55555555555556 Test acc68.26; Train loss: 0.0005610768560658802 Val loss: 0.0055891760852601795
+INFO - evaluator.py - 2024-10-25 14:04:50,404 - Epoch: 12 Train acc: 94.74545454545455 Val acc: 83.3 Test acc79.7; Train loss: 0.0005538612708449363 Val loss: 0.003271493593851725
+INFO - evaluator.py - 2024-10-25 14:05:15,279 - Epoch: 13 Train acc: 94.91818181818181 Val acc: 88.76666666666667 Test acc84.46000000000001; Train loss: 0.0005326683221892878 Val loss: 0.0015344844427373674
+INFO - evaluator.py - 2024-10-25 14:05:40,186 - Epoch: 14 Train acc: 95.45818181818181 Val acc: 81.94444444444444 Test acc79.72; Train loss: 0.0004826392926953056 Val loss: 0.0024033486247062685
+INFO - evaluator.py - 2024-10-25 14:06:05,115 - Epoch: 15 Train acc: 95.4490909090909 Val acc: 79.97777777777777 Test acc76.52; Train loss: 0.0004788744070990519 Val loss: 0.002661892586284214
+INFO - evaluator.py - 2024-10-25 14:06:30,158 - Epoch: 16 Train acc: 95.85818181818182 Val acc: 56.34444444444444 Test acc49.93; Train loss: 0.0004526831590993838 Val loss: 0.010820683413081698
+INFO - evaluator.py - 2024-10-25 14:06:55,098 - Epoch: 17 Train acc: 96.12181818181818 Val acc: 47.66666666666667 Test acc41.38; Train loss: 0.00041918848502365023 Val loss: 0.02024581872092353
+INFO - evaluator.py - 2024-10-25 14:07:20,006 - Epoch: 18 Train acc: 96.37636363636364 Val acc: 54.955555555555556 Test acc49.91; Train loss: 0.0003943378881297328 Val loss: 0.0162658834722307
+INFO - evaluator.py - 2024-10-25 14:07:44,959 - Epoch: 19 Train acc: 96.44181818181818 Val acc: 70.76666666666667 Test acc66.35; Train loss: 0.00038284728953784163 Val loss: 0.0062538440359963315
+INFO - evaluator.py - 2024-10-25 14:08:10,437 - Epoch: 20 Train acc: 97.88909090909091 Val acc: 90.85555555555555 Test acc84.49; Train loss: 0.0002333393463187597 Val loss: 0.0012702493882841535
+INFO - evaluator.py - 2024-10-25 14:08:35,368 - Epoch: 21 Train acc: 98.34363636363636 Val acc: 92.28888888888889 Test acc83.82; Train loss: 0.00018306435238231312 Val loss: 0.0010875512642992866
+INFO - evaluator.py - 2024-10-25 14:09:00,285 - Epoch: 22 Train acc: 98.54 Val acc: 92.08888888888889 Test acc84.61999999999999; Train loss: 0.00016199071918698876 Val loss: 0.0012117309388187197
+INFO - evaluator.py - 2024-10-25 14:09:25,407 - Epoch: 23 Train acc: 98.70545454545454 Val acc: 92.67777777777778 Test acc84.11; Train loss: 0.00014269931619478898 Val loss: 0.0011383304877413643
+INFO - evaluator.py - 2024-10-25 14:09:50,297 - Epoch: 24 Train acc: 98.81636363636363 Val acc: 93.06666666666666 Test acc84.56; Train loss: 0.00013003227018158544 Val loss: 0.0011526400140590139
+INFO - evaluator.py - 2024-10-25 14:10:15,185 - Epoch: 25 Train acc: 98.94727272727273 Val acc: 91.60000000000001 Test acc83.61; Train loss: 0.00011469665601510894 Val loss: 0.0014749372022019491
+INFO - evaluator.py - 2024-10-25 14:10:40,149 - Epoch: 26 Train acc: 99.03636363636363 Val acc: 94.15555555555557 Test acc84.61; Train loss: 0.00010519992825151845 Val loss: 0.0009488283163971371
+INFO - evaluator.py - 2024-10-25 14:11:05,043 - Epoch: 27 Train acc: 99.09272727272727 Val acc: 94.52222222222221 Test acc85.15; Train loss: 9.859395891597325e-05 Val loss: 0.0008988274849123425
+INFO - evaluator.py - 2024-10-25 14:11:29,986 - Epoch: 28 Train acc: 99.14727272727274 Val acc: 94.94444444444444 Test acc84.74000000000001; Train loss: 9.219122456217354e-05 Val loss: 0.0007819161340594292
+INFO - evaluator.py - 2024-10-25 14:11:55,106 - Epoch: 29 Train acc: 99.18909090909091 Val acc: 94.1 Test acc83.5; Train loss: 8.843046637167307e-05 Val loss: 0.001024346536749767
+INFO - evaluator.py - 2024-10-25 14:12:20,046 - Epoch: 30 Train acc: 99.25818181818182 Val acc: 94.28888888888889 Test acc85.15; Train loss: 7.839597006413069e-05 Val loss: 0.001017122555938032
+INFO - evaluator.py - 2024-10-25 14:12:44,958 - Epoch: 31 Train acc: 99.31454545454545 Val acc: 93.56666666666666 Test acc84.54; Train loss: 7.186658788387749e-05 Val loss: 0.0012307249125507143
+INFO - evaluator.py - 2024-10-25 14:13:09,850 - Epoch: 32 Train acc: 99.43272727272728 Val acc: 94.73333333333333 Test acc84.61999999999999; Train loss: 6.275478529701518e-05 Val loss: 0.000997123796906736
+INFO - evaluator.py - 2024-10-25 14:13:34,796 - Epoch: 33 Train acc: 99.37636363636364 Val acc: 95.17777777777778 Test acc84.82; Train loss: 6.666298072827472e-05 Val loss: 0.000913869221177366
+INFO - evaluator.py - 2024-10-25 14:13:59,724 - Epoch: 34 Train acc: 99.41272727272728 Val acc: 95.01111111111112 Test acc85.27; Train loss: 6.355622668581252e-05 Val loss: 0.0009462819149096807
+INFO - evaluator.py - 2024-10-25 14:14:24,671 - Epoch: 35 Train acc: 99.52909090909091 Val acc: 94.05555555555556 Test acc85.75; Train loss: 4.823751727923412e-05 Val loss: 0.0012459154066940148
+INFO - evaluator.py - 2024-10-25 14:14:49,717 - Epoch: 36 Train acc: 99.5490909090909 Val acc: 93.89999999999999 Test acc84.81; Train loss: 4.797799456441267e-05 Val loss: 0.0013456712663173676
+INFO - evaluator.py - 2024-10-25 14:15:14,662 - Epoch: 37 Train acc: 99.53636363636363 Val acc: 92.65555555555555 Test acc84.42; Train loss: 5.112057705409825e-05 Val loss: 0.001711397358112865
+INFO - evaluator.py - 2024-10-25 14:15:39,566 - Epoch: 38 Train acc: 99.55454545454545 Val acc: 93.26666666666667 Test acc84.48; Train loss: 4.920866325476461e-05 Val loss: 0.0014254549683796035
+INFO - evaluator.py - 2024-10-25 14:16:04,516 - Epoch: 39 Train acc: 99.52545454545455 Val acc: 90.11111111111111 Test acc84.00999999999999; Train loss: 4.920311441052366e-05 Val loss: 0.0026410182151529525
+INFO - evaluator.py - 2024-10-25 14:16:29,449 - Epoch: 40 Train acc: 99.76727272727273 Val acc: 92.9888888888889 Test acc84.89999999999999; Train loss: 2.6891794249902227e-05 Val loss: 0.0016593454281489054
+INFO - evaluator.py - 2024-10-25 14:16:54,391 - Epoch: 41 Train acc: 99.80909090909091 Val acc: 93.75555555555556 Test acc84.96000000000001; Train loss: 2.2397290393233893e-05 Val loss: 0.0014197529355684916
+INFO - evaluator.py - 2024-10-25 14:17:19,494 - Epoch: 42 Train acc: 99.80545454545454 Val acc: 94.75555555555556 Test acc85.28; Train loss: 2.205894597626122e-05 Val loss: 0.001112830018831624
+INFO - evaluator.py - 2024-10-25 14:17:44,392 - Epoch: 43 Train acc: 99.82363636363635 Val acc: 95.46666666666667 Test acc85.27; Train loss: 1.8805580467663028e-05 Val loss: 0.0009160324806968372
+INFO - evaluator.py - 2024-10-25 14:18:09,320 - Epoch: 44 Train acc: 99.83999999999999 Val acc: 95.45555555555556 Test acc85.24000000000001; Train loss: 1.870250576810742e-05 Val loss: 0.0008920392469606466
+INFO - evaluator.py - 2024-10-25 14:18:34,254 - Epoch: 45 Train acc: 99.83818181818181 Val acc: 95.03333333333333 Test acc85.47; Train loss: 1.8532898753817955e-05 Val loss: 0.001074301862054401
+INFO - evaluator.py - 2024-10-25 14:18:59,199 - Epoch: 46 Train acc: 99.83636363636363 Val acc: 95.93333333333334 Test acc84.8; Train loss: 1.8781562221490523e-05 Val loss: 0.0008551183222896523
+INFO - evaluator.py - 2024-10-25 14:19:24,137 - Epoch: 47 Train acc: 99.86909090909091 Val acc: 95.84444444444445 Test acc85.09; Train loss: 1.4790076492301358e-05 Val loss: 0.0008363180698619948
+INFO - evaluator.py - 2024-10-25 14:19:49,026 - Epoch: 48 Train acc: 99.85272727272726 Val acc: 95.54444444444444 Test acc85.15; Train loss: 1.6854490359864115e-05 Val loss: 0.0009634849367042383
+INFO - evaluator.py - 2024-10-25 14:20:14,076 - Epoch: 49 Train acc: 99.88909090909091 Val acc: 95.73333333333333 Test acc84.98; Train loss: 1.547673940155867e-05 Val loss: 0.0008978225746088558
+INFO - evaluator.py - 2024-10-25 14:20:14,081 - The best acc of synthetic images on val and the corresponding acc on test dataset from wrn is 95.93333333333334 and 84.8
+INFO - evaluator.py - 2024-10-25 14:20:14,081 - The best acc test dataset from wrn is 85.75
+INFO - evaluator.py - 2024-10-25 14:21:57,094 - Epoch: 0 Train acc: 73.25090909090909 Val acc: 87.92222222222222 Test acc79.49000000000001; Train loss: 0.003169458545338024 Val loss: 0.001325983809100257
+INFO - evaluator.py - 2024-10-25 14:23:38,560 - Epoch: 1 Train acc: 88.06363636363636 Val acc: 89.78888888888889 Test acc81.66; Train loss: 0.001273181994936683 Val loss: 0.0011283592184384663
+INFO - evaluator.py - 2024-10-25 14:25:20,069 - Epoch: 2 Train acc: 90.84545454545454 Val acc: 78.3 Test acc74.35000000000001; Train loss: 0.0009931388131596826 Val loss: 0.003338718725575341
+INFO - evaluator.py - 2024-10-25 14:27:01,569 - Epoch: 3 Train acc: 91.6290909090909 Val acc: 92.32222222222222 Test acc84.39999999999999; Train loss: 0.0008885238070379604 Val loss: 0.0008784245534075631
+INFO - evaluator.py - 2024-10-25 14:28:43,024 - Epoch: 4 Train acc: 92.23454545454545 Val acc: 79.08888888888889 Test acc76.59; Train loss: 0.0008325109787962653 Val loss: 0.0025089411470625134
+INFO - evaluator.py - 2024-10-25 14:30:24,671 - Epoch: 5 Train acc: 93.07272727272728 Val acc: 92.53333333333333 Test acc84.96000000000001; Train loss: 0.000750739341432398 Val loss: 0.0007985639969507853
+INFO - evaluator.py - 2024-10-25 14:32:06,127 - Epoch: 6 Train acc: 93.88545454545455 Val acc: 90.2 Test acc84.44; Train loss: 0.0006593299525705251 Val loss: 0.0010844199574655956
+INFO - evaluator.py - 2024-10-25 14:33:47,577 - Epoch: 7 Train acc: 94.15454545454546 Val acc: 91.82222222222222 Test acc84.5; Train loss: 0.0006288967587731101 Val loss: 0.0009343441062503391
+INFO - evaluator.py - 2024-10-25 14:35:29,056 - Epoch: 8 Train acc: 94.56 Val acc: 94.02222222222221 Test acc85.41; Train loss: 0.0005847908577458425 Val loss: 0.0006539194881916046
+INFO - evaluator.py - 2024-10-25 14:37:10,572 - Epoch: 9 Train acc: 94.5490909090909 Val acc: 92.71111111111111 Test acc85.19; Train loss: 0.0005740307329730554 Val loss: 0.00079751389225324
+INFO - evaluator.py - 2024-10-25 14:38:52,078 - Epoch: 10 Train acc: 95.16181818181818 Val acc: 75.14444444444445 Test acc69.96; Train loss: 0.0005175531044602394 Val loss: 0.005744102199872335
+INFO - evaluator.py - 2024-10-25 14:40:33,591 - Epoch: 11 Train acc: 95.52363636363637 Val acc: 40.97777777777778 Test acc34.949999999999996; Train loss: 0.0004776070827110247 Val loss: 0.026313154167599148
+INFO - evaluator.py - 2024-10-25 14:42:15,185 - Epoch: 12 Train acc: 89.85636363636364 Val acc: 16.5 Test acc15.590000000000002; Train loss: 0.001217372696914456 Val loss: 0.009919303099314372
+INFO - evaluator.py - 2024-10-25 14:43:56,586 - Epoch: 13 Train acc: 93.52363636363637 Val acc: 27.955555555555556 Test acc25.96; Train loss: 0.0007027099257165735 Val loss: 0.009578001737594604
+INFO - evaluator.py - 2024-10-25 14:45:37,999 - Epoch: 14 Train acc: 94.53818181818183 Val acc: 66.72222222222223 Test acc69.23; Train loss: 0.0005982609648596157 Val loss: 0.0036628927720917595
+INFO - evaluator.py - 2024-10-25 14:47:19,385 - Epoch: 15 Train acc: 95.08181818181818 Val acc: 87.87777777777778 Test acc81.96; Train loss: 0.00053181932433085 Val loss: 0.0013308150337802038
+INFO - evaluator.py - 2024-10-25 14:49:00,819 - Epoch: 16 Train acc: 95.4090909090909 Val acc: 90.16666666666666 Test acc82.39999999999999; Train loss: 0.000489290481263941 Val loss: 0.001065860167145729
+INFO - evaluator.py - 2024-10-25 14:50:42,188 - Epoch: 17 Train acc: 95.82545454545455 Val acc: 79.52222222222223 Test acc76.52; Train loss: 0.0004436689262363044 Val loss: 0.00299205207824707
+INFO - evaluator.py - 2024-10-25 14:52:23,710 - Epoch: 18 Train acc: 96.1490909090909 Val acc: 88.6 Test acc80.08; Train loss: 0.00041075628399848935 Val loss: 0.0013698426286379497
+INFO - evaluator.py - 2024-10-25 14:54:05,077 - Epoch: 19 Train acc: 96.55818181818182 Val acc: 81.58888888888889 Test acc72.82; Train loss: 0.0003716093165630644 Val loss: 0.0020762747923533122
+INFO - evaluator.py - 2024-10-25 14:55:46,809 - Epoch: 20 Train acc: 98.22727272727273 Val acc: 93.0111111111111 Test acc84.2; Train loss: 0.00020422012833031742 Val loss: 0.0008372653952489296
+INFO - evaluator.py - 2024-10-25 14:57:28,192 - Epoch: 21 Train acc: 98.9 Val acc: 94.0 Test acc84.96000000000001; Train loss: 0.00013690265811641108 Val loss: 0.000864873104625278
+INFO - evaluator.py - 2024-10-25 14:59:09,576 - Epoch: 22 Train acc: 99.17454545454547 Val acc: 94.81111111111112 Test acc84.84; Train loss: 0.00010104861774227836 Val loss: 0.0007887111397253142
+INFO - evaluator.py - 2024-10-25 15:00:50,944 - Epoch: 23 Train acc: 99.30363636363636 Val acc: 94.64444444444445 Test acc85.28999999999999; Train loss: 8.532799205488779e-05 Val loss: 0.0009258522689342499
+INFO - evaluator.py - 2024-10-25 15:02:32,315 - Epoch: 24 Train acc: 99.53454545454545 Val acc: 94.42222222222222 Test acc85.28999999999999; Train loss: 5.7741444401273676e-05 Val loss: 0.0009733421612117026
+INFO - evaluator.py - 2024-10-25 15:04:13,874 - Epoch: 25 Train acc: 99.45636363636363 Val acc: 94.54444444444444 Test acc85.11999999999999; Train loss: 5.9800087990747253e-05 Val loss: 0.0009760285433795717
+INFO - evaluator.py - 2024-10-25 15:05:55,278 - Epoch: 26 Train acc: 99.59272727272727 Val acc: 94.34444444444445 Test acc84.87; Train loss: 4.903442285827954e-05 Val loss: 0.001098387779461013
+INFO - evaluator.py - 2024-10-25 15:07:36,671 - Epoch: 27 Train acc: 99.68909090909091 Val acc: 94.9888888888889 Test acc84.37; Train loss: 3.653198789318346e-05 Val loss: 0.0009663555804226133
+INFO - evaluator.py - 2024-10-25 15:09:18,052 - Epoch: 28 Train acc: 99.64181818181818 Val acc: 95.01111111111112 Test acc84.67; Train loss: 4.388779421146451e-05 Val loss: 0.0010456416681408883
+INFO - evaluator.py - 2024-10-25 15:10:59,470 - Epoch: 29 Train acc: 99.56 Val acc: 94.86666666666666 Test acc84.37; Train loss: 5.012770487122576e-05 Val loss: 0.0009866433209843105
+INFO - evaluator.py - 2024-10-25 15:12:40,896 - Epoch: 30 Train acc: 99.69454545454546 Val acc: 94.16666666666667 Test acc84.05; Train loss: 3.3516203351742165e-05 Val loss: 0.0012096418200267685
+INFO - evaluator.py - 2024-10-25 15:14:22,431 - Epoch: 31 Train acc: 99.74545454545455 Val acc: 94.3 Test acc85.36; Train loss: 3.1348794714590026e-05 Val loss: 0.0012292870432138443
+INFO - evaluator.py - 2024-10-25 15:16:03,809 - Epoch: 32 Train acc: 99.62545454545455 Val acc: 94.43333333333334 Test acc84.38; Train loss: 4.228451747066257e-05 Val loss: 0.0010785626156462563
+INFO - evaluator.py - 2024-10-25 15:17:45,164 - Epoch: 33 Train acc: 99.66181818181819 Val acc: 94.47777777777779 Test acc85.22; Train loss: 3.727487684121694e-05 Val loss: 0.0011969635089238485
+INFO - evaluator.py - 2024-10-25 15:19:26,521 - Epoch: 34 Train acc: 99.74181818181819 Val acc: 90.47777777777777 Test acc84.00999999999999; Train loss: 2.8505861034235833e-05 Val loss: 0.002364510092470381
+INFO - evaluator.py - 2024-10-25 15:21:07,840 - Epoch: 35 Train acc: 99.64 Val acc: 93.35555555555555 Test acc83.43; Train loss: 4.0061074768362395e-05 Val loss: 0.001433146374921004
+INFO - evaluator.py - 2024-10-25 15:22:49,206 - Epoch: 36 Train acc: 99.69454545454546 Val acc: 93.53333333333333 Test acc85.06; Train loss: 3.36395751055203e-05 Val loss: 0.0014509807775417963
+INFO - evaluator.py - 2024-10-25 15:24:30,548 - Epoch: 37 Train acc: 99.64181818181818 Val acc: 93.83333333333333 Test acc84.39; Train loss: 4.1633732347558674e-05 Val loss: 0.0012683336502975887
+INFO - evaluator.py - 2024-10-25 15:26:12,092 - Epoch: 38 Train acc: 99.72 Val acc: 91.3111111111111 Test acc83.37; Train loss: 3.161757268720645e-05 Val loss: 0.0021217223819759157
+INFO - evaluator.py - 2024-10-25 15:27:53,421 - Epoch: 39 Train acc: 99.8 Val acc: 89.83333333333333 Test acc84.22; Train loss: 2.3758926064792005e-05 Val loss: 0.0026340854863325753
+INFO - evaluator.py - 2024-10-25 15:29:34,783 - Epoch: 40 Train acc: 99.96181818181819 Val acc: 92.08888888888889 Test acc84.96000000000001; Train loss: 6.146486288740893e-06 Val loss: 0.0021950556735197703
+INFO - evaluator.py - 2024-10-25 15:31:16,256 - Epoch: 41 Train acc: 99.99454545454546 Val acc: 93.38888888888889 Test acc85.25; Train loss: 2.1129901956803886e-06 Val loss: 0.0017763226495848762
+INFO - evaluator.py - 2024-10-25 15:32:57,617 - Epoch: 42 Train acc: 99.99636363636364 Val acc: 94.43333333333334 Test acc85.50999999999999; Train loss: 1.6145402867220003e-06 Val loss: 0.00143275106118785
+INFO - evaluator.py - 2024-10-25 15:34:38,993 - Epoch: 43 Train acc: 100.0 Val acc: 94.72222222222221 Test acc85.49; Train loss: 1.1029401968698948e-06 Val loss: 0.0013650167302952873
+INFO - evaluator.py - 2024-10-25 15:36:20,416 - Epoch: 44 Train acc: 100.0 Val acc: 94.84444444444445 Test acc85.31; Train loss: 7.476965971859913e-07 Val loss: 0.0012751343134376739
+INFO - evaluator.py - 2024-10-25 15:38:02,005 - Epoch: 45 Train acc: 100.0 Val acc: 95.15555555555557 Test acc85.28999999999999; Train loss: 9.051097953819078e-07 Val loss: 0.0012091248598363664
+INFO - evaluator.py - 2024-10-25 15:39:43,421 - Epoch: 46 Train acc: 100.0 Val acc: 95.27777777777777 Test acc85.34; Train loss: 6.348252523656067e-07 Val loss: 0.0012106527955685225
+INFO - evaluator.py - 2024-10-25 15:41:24,830 - Epoch: 47 Train acc: 99.99818181818182 Val acc: 95.36666666666666 Test acc85.2; Train loss: 6.864100459676013e-07 Val loss: 0.001225424682928456
+INFO - evaluator.py - 2024-10-25 15:43:06,191 - Epoch: 48 Train acc: 100.0 Val acc: 95.33333333333334 Test acc85.19; Train loss: 5.261486193458868e-07 Val loss: 0.00126484008712901
+INFO - evaluator.py - 2024-10-25 15:44:47,546 - Epoch: 49 Train acc: 100.0 Val acc: 95.37777777777777 Test acc85.04; Train loss: 4.424076378282652e-07 Val loss: 0.001238087446325355
+INFO - evaluator.py - 2024-10-25 15:44:47,549 - The best acc of synthetic images on val and the corresponding acc on test dataset from resnext is 95.37777777777777 and 85.04
+INFO - evaluator.py - 2024-10-25 15:44:47,550 - The best acc test dataset from resnext is 85.50999999999999
+INFO - evaluator.py - 2024-10-25 15:44:47,550 - The best acc of accuracy (using synthetic images as the validation set) of synthetic images from resnet, wrn, and resnext are [85.39999999999999, 84.8, 85.04].
+INFO - evaluator.py - 2024-10-25 15:44:47,550 - The average and std of accuracy of synthetic images are 85.08 and 0.25
+INFO - dataset_loader.py - 2024-10-28 19:02:37,131 - delta is reset as 1.6657508770018431e-06
+INFO - evaluator.py - 2024-10-28 19:03:30,422 - Epoch: 0 Train acc: 66.34363636363636 Val acc: 74.1 Test acc73.82; Train loss: 0.003519384549964558 Val loss: 0.0007214882135391235
+INFO - evaluator.py - 2024-10-28 19:04:06,413 - Epoch: 1 Train acc: 83.94 Val acc: 78.25999999999999 Test acc77.25; Train loss: 0.0016817096217112107 Val loss: 0.0006372876048088074
+INFO - evaluator.py - 2024-10-28 19:04:42,974 - Epoch: 2 Train acc: 88.55636363636363 Val acc: 80.42 Test acc79.89; Train loss: 0.0012271348601037805 Val loss: 0.0005960849046707154
+INFO - evaluator.py - 2024-10-28 19:05:19,550 - Epoch: 3 Train acc: 90.55454545454545 Val acc: 80.9 Test acc80.44; Train loss: 0.0010223158958283338 Val loss: 0.000605733335018158
+INFO - evaluator.py - 2024-10-28 19:05:55,572 - Epoch: 4 Train acc: 91.66181818181818 Val acc: 82.16 Test acc82.12; Train loss: 0.0008948483717712489 Val loss: 0.0006100993871688843
+INFO - evaluator.py - 2024-10-28 19:06:32,458 - Epoch: 5 Train acc: 92.4090909090909 Val acc: 39.4 Test acc39.839999999999996; Train loss: 0.0008134601686488499 Val loss: 0.00623225965499878
+INFO - evaluator.py - 2024-10-28 19:07:08,683 - Epoch: 6 Train acc: 92.81272727272727 Val acc: 83.12 Test acc83.11; Train loss: 0.0007789761877872727 Val loss: 0.0005856425523757935
+INFO - evaluator.py - 2024-10-28 19:07:45,197 - Epoch: 7 Train acc: 93.31272727272727 Val acc: 84.11999999999999 Test acc84.67; Train loss: 0.0007293461180546067 Val loss: 0.0005448946118354797
+INFO - evaluator.py - 2024-10-28 19:08:21,701 - Epoch: 8 Train acc: 93.41272727272727 Val acc: 51.6 Test acc52.11; Train loss: 0.0007108177438378334 Val loss: 0.0023097294330596922
+INFO - evaluator.py - 2024-10-28 19:08:57,916 - Epoch: 9 Train acc: 93.76181818181819 Val acc: 82.56 Test acc82.07; Train loss: 0.0006661502529274333 Val loss: 0.0006099442124366761
+INFO - evaluator.py - 2024-10-28 19:09:33,855 - Epoch: 10 Train acc: 94.16181818181818 Val acc: 35.92 Test acc35.69; Train loss: 0.0006220197715542533 Val loss: 0.006172195434570312
+INFO - evaluator.py - 2024-10-28 19:10:09,729 - Epoch: 11 Train acc: 94.41272727272727 Val acc: 73.96000000000001 Test acc72.71; Train loss: 0.0005973333051258867 Val loss: 0.000984394657611847
+INFO - evaluator.py - 2024-10-28 19:10:45,521 - Epoch: 12 Train acc: 94.68545454545455 Val acc: 44.800000000000004 Test acc44.16; Train loss: 0.0005762032621286133 Val loss: 0.003199753761291504
+INFO - evaluator.py - 2024-10-28 19:11:21,230 - Epoch: 13 Train acc: 94.70181818181818 Val acc: 61.44 Test acc62.529999999999994; Train loss: 0.0005616878445852887 Val loss: 0.0013522879362106322
+INFO - evaluator.py - 2024-10-28 19:11:56,781 - Epoch: 14 Train acc: 94.95818181818181 Val acc: 23.880000000000003 Test acc24.52; Train loss: 0.0005336400082165544 Val loss: 0.007207527542114258
+INFO - evaluator.py - 2024-10-28 19:12:32,361 - Epoch: 15 Train acc: 95.25636363636364 Val acc: 29.080000000000002 Test acc28.689999999999998; Train loss: 0.0005030743763528087 Val loss: 0.00578765287399292
+INFO - evaluator.py - 2024-10-28 19:13:08,098 - Epoch: 16 Train acc: 95.38 Val acc: 23.580000000000002 Test acc24.240000000000002; Train loss: 0.0004990192160687664 Val loss: 0.007527487087249756
+INFO - evaluator.py - 2024-10-28 19:13:44,085 - Epoch: 17 Train acc: 95.63636363636364 Val acc: 81.86 Test acc81.5; Train loss: 0.000464057936722582 Val loss: 0.000612789535522461
+INFO - evaluator.py - 2024-10-28 19:14:19,082 - Epoch: 18 Train acc: 95.76363636363637 Val acc: 77.96 Test acc77.27000000000001; Train loss: 0.00044551651985807854 Val loss: 0.0007611027002334595
+INFO - evaluator.py - 2024-10-28 19:14:54,411 - Epoch: 19 Train acc: 96.11636363636363 Val acc: 68.7 Test acc68.67; Train loss: 0.00040785303711891174 Val loss: 0.0010971710205078125
+INFO - evaluator.py - 2024-10-28 19:15:29,903 - Epoch: 20 Train acc: 98.04 Val acc: 84.06 Test acc83.39999999999999; Train loss: 0.0002215222705155611 Val loss: 0.0007641530632972718
+INFO - evaluator.py - 2024-10-28 19:16:06,575 - Epoch: 21 Train acc: 98.61818181818181 Val acc: 83.52000000000001 Test acc82.97; Train loss: 0.00016044941405681047 Val loss: 0.001067917561531067
+INFO - evaluator.py - 2024-10-28 19:16:42,149 - Epoch: 22 Train acc: 98.77272727272727 Val acc: 83.86 Test acc83.38; Train loss: 0.0001428662770004435 Val loss: 0.0010605573892593385
+INFO - evaluator.py - 2024-10-28 19:17:17,951 - Epoch: 23 Train acc: 99.03454545454545 Val acc: 84.34 Test acc84.00999999999999; Train loss: 0.00010791992017660629 Val loss: 0.001195838451385498
+INFO - evaluator.py - 2024-10-28 19:17:53,412 - Epoch: 24 Train acc: 99.20363636363636 Val acc: 83.74000000000001 Test acc83.43; Train loss: 9.192439103075726e-05 Val loss: 0.0013711277961730957
+INFO - evaluator.py - 2024-10-28 19:18:28,650 - Epoch: 25 Train acc: 99.30545454545454 Val acc: 84.08 Test acc83.96000000000001; Train loss: 7.887731794775887e-05 Val loss: 0.0013063583612442017
+INFO - evaluator.py - 2024-10-28 19:19:04,289 - Epoch: 26 Train acc: 99.40727272727273 Val acc: 85.42 Test acc85.28999999999999; Train loss: 6.602969714863734e-05 Val loss: 0.0012288742542266847
+INFO - evaluator.py - 2024-10-28 19:19:39,450 - Epoch: 27 Train acc: 99.36181818181818 Val acc: 84.1 Test acc83.57; Train loss: 6.862166142091155e-05 Val loss: 0.0014435487747192382
+INFO - evaluator.py - 2024-10-28 19:20:14,966 - Epoch: 28 Train acc: 99.50727272727272 Val acc: 85.52 Test acc84.93; Train loss: 5.446702937849543e-05 Val loss: 0.0013748021602630616
+INFO - evaluator.py - 2024-10-28 19:20:50,261 - Epoch: 29 Train acc: 99.55454545454545 Val acc: 79.62 Test acc79.36; Train loss: 5.039545688460666e-05 Val loss: 0.0017496371984481811
+INFO - evaluator.py - 2024-10-28 19:21:26,034 - Epoch: 30 Train acc: 99.59090909090908 Val acc: 83.8 Test acc83.65; Train loss: 4.688195417719808e-05 Val loss: 0.001837431526184082
+INFO - evaluator.py - 2024-10-28 19:22:01,975 - Epoch: 31 Train acc: 99.63818181818182 Val acc: 85.26 Test acc85.00999999999999; Train loss: 3.830344192789529e-05 Val loss: 0.001605417275428772
+INFO - evaluator.py - 2024-10-28 19:22:37,209 - Epoch: 32 Train acc: 99.57272727272726 Val acc: 84.06 Test acc84.16; Train loss: 4.907014648832211e-05 Val loss: 0.0016680625438690185
+INFO - dataset_loader.py - 2024-10-28 19:23:03,721 - delta is reset as 1.6657508770018431e-06
+INFO - evaluator.py - 2024-10-28 22:03:14,377 - The FID of synthetic images is 17.022592700223242
+INFO - evaluator.py - 2024-10-28 22:03:14,401 - The Inception Score of synthetic images is 3.9322755336761475
+INFO - evaluator.py - 2024-10-28 22:03:14,401 - The Precision and Recall of synthetic images is 0.5431250333786011 and 0.38545000553131104
+INFO - evaluator.py - 2024-10-28 22:03:14,401 - The FLD of synthetic images is 6.722414493560791
+INFO - evaluator.py - 2024-10-28 22:03:14,401 - The ImageReward of synthetic images is -1.6361236934935008
+INFO - dataset_loader.py - 2024-10-28 22:46:40,212 - delta is reset as 1.6657508770018431e-06
+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
+INFO - dataset_loader.py - 2024-10-29 21:46:57,873 - delta is reset as 1.6657508770018431e-06
+INFO - dataset_loader.py - 2024-10-29 22:18:02,859 - delta is reset as 1.6657508770018431e-06
+INFO - dataset_loader.py - 2024-10-29 22:19:02,929 - delta is reset as 1.6657508770018431e-06
+INFO - dataset_loader.py - 2024-10-29 22:30:16,771 - delta is reset as 1.6657508770018431e-06
+INFO - evaluator.py - 2024-10-29 23:08:18,783 - The FID of synthetic images is 17.07323521108424
+INFO - evaluator.py - 2024-10-29 23:08:18,784 - The Inception Score of synthetic images is 3.9322755336761475
+INFO - evaluator.py - 2024-10-29 23:08:18,784 - The Precision and Recall of synthetic images is 0.5431250333786011 and 0.38545000553131104
+INFO - evaluator.py - 2024-10-29 23:08:18,784 - The FLD of synthetic images is 6.597459316253662
+INFO - evaluator.py - 2024-10-29 23:08:18,784 - The ImageReward of synthetic images is -1.6361236934935008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/checkpoints/final_checkpoint.pth b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/checkpoints/final_checkpoint.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3580465ef1c8792be24d0212c80105fbf44914c6
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/checkpoints/final_checkpoint.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59f219c42d13dbc1ab22378011cef650990a56ae067f2315367f593ed8c11bf5
+size 24084886
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/checkpoints/snapshot_checkpoint.pth b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/checkpoints/snapshot_checkpoint.pth
new file mode 100644
index 0000000000000000000000000000000000000000..aa8743cf3dc245fa7ad9ea4ce145af315003410e
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/checkpoints/snapshot_checkpoint.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04cd84802a2948a19c5f6cdaef277b320147383793c8b1c7b5f368f9c59060cb
+size 24088033
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_10000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_10000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..029ef1965154e81085a60206dd6282c6cdd3622f
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_10000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:986d1d146073c941503dfb1cdb0f538b0c52f4b47748f8666ad4e44906e38976
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_10000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_10000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..37069ea930a14590b6431c2e572b696b02c97211
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_10000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c941dbc02aa6818d5952369890819b0ccff466c5bc3fac599a2e42964a160cf
+size 164529
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_12000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_12000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..7d0b90c1d704b430669cb5d51af1856a4b2bb4b9
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_12000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e85a5ff3b90a529ee1c71b3f1a9275f8dc54952b81deba23dcf693a4d46c85f
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_12000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_12000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..4e49a2f8f27c6862b759687b7af498f0a024a4ad
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_12000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c682994629fa7f19625d82e5e27e30a15b3254c7605874b26cfe9fab8f87e66
+size 163397
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_14000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_14000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..fcb9fa0d89fcf6bc4ec4cdb194db29f334bbbdd8
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_14000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2108370c41afaac3b179985a72083d987c47c074083ccb6980690978fd7254ab
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_14000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_14000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..657e701b1720de4d325af36c0cb0be7db2c04ee4
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_14000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:222881f072eda1fe953403e1aaa2bf41bab8f2191e6eaf7adda61170de79bea4
+size 161219
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_16000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_16000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..6de924a584c27e03089ca84be4e080c11e874030
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_16000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5517bcaf0e96b1678b0c737d419784649108d8960e13954e8005c6b134df018
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_16000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_16000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..d42533fedc59934f19fef4eecd63d88ca465c11f
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_16000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84828e7a8c0d1dad37a3aade42b8bcc385134589b040449124ea5bb03c54aaca
+size 160496
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_18000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_18000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..1b0a0b73ea6bf79f41b390f26ffed479b0daf2f2
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_18000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f7ea1cebc8a2de6054425257195d29bbdc3f685ac21ad52bf94ac7e331ff5e5
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_18000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_18000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..1ff2e5d354b4b4557e1af990ce10a16de117c940
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_18000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:778bd375c59f9ee2c0ccc5e5554cd0f963993bce3f9e96c55cedbc967610eafa
+size 158877
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_2000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_2000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..21936b8b67d5100bfe82075a9dd58d5c98639162
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_2000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb00fd78f29d54da2959c6acacb1aa2466b6d0d252540d5bf18eec81b3bad4ca
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_2000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_2000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..52c5c828671f62561c55dd7235c693513d425a75
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_2000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1e6e33e6914dcc94d9c248c6eddc4f260c1da7d0e548ce10e8673d26475f8f5
+size 204199
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_20000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_20000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..2b1c06dd7f55b83427985a601bb89bc496a6521d
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_20000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b837af870050e0a86fb98d6a59a9678c00c8278418f2e5b869d7a59753a1bc71
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_20000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_20000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..bc2dc0c5035a5cb89fcf8eb012e1c089b9a6ddd1
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_20000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f31d18c078b58dd2df6f0cdd4a19b9b022a749a222961f6e7086114011dd15cd
+size 159038
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_22000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_22000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..d10ffddbffe091dac639158b4d538a6429578a99
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_22000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:729622dd32606ce193327d5b06a8a5970f11a51436b4df5130dd5bbf5d16e866
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_22000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_22000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..71c7d2aec5687f1a7c47839ee10d655b42377791
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_22000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:436426a60d06ee8832650380b9a656e16d81891dc13619c375dc95285acf74e3
+size 156948
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_24000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_24000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..1963949b98f2fdb14db1f94ac43b9ee44c58734f
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_24000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbbb14baaba04ace495d303246fb9bbdd3e0b7248230e6a081fc65e3d01a0776
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_24000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_24000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..06aaee00e7ad60ab2814fb82016853fb21f8c15e
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_24000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59dd63eeda67d73e1f7a387c82d9724381fc94a7c78077d41fba66ff77a17c61
+size 153905
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_26000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_26000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..eddaefbfb3dbe454a57cf741afba0bfffe846785
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_26000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aaa61e66db86e65c07995b0e0786e08b7cf064e86f04c127950cb8005a96e7e
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_26000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_26000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..f5558bbcbe24a0ffae6272b95e14f1712190ba77
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_26000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aea6c89134fc20b9da846bf8120749455948bd181e4e75b6c4f8977154feb4e
+size 155885
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_28000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_28000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..bdf3c0eda1516d1496fbdc734896682684da5100
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_28000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:374919240b6390bf4b4e7262543212d7f7d042ae7a4f27d8de07af3d86574390
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_28000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_28000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..fde109081e98107326796502beab2b58a89f298d
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_28000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a997ff3e8f8ab1ef07109c64cec059fd1e2173926ebb6178522ec0b72abca860
+size 154143
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_30000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_30000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..8641971ce403c57a9122b3eff969a3e0d3ab6c74
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_30000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fed58d3e4b756d9814b28ed3f5080d0a03e2bbfe8b417af8fba7124276c8732d
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_30000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_30000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..ccaf9aeda66e9a03a8e5621c7681f88b800e9215
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_30000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af45a8d6944ff24e3e4c8abf8e4ec8e4282e043545c1c5e371b84ef06b710dc5
+size 153461
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_32000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_32000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..261b3814dd48ccf0139e75705bb22815f0c42e14
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_32000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3d19b25a2a6bc11c82221eb45f72bf8db33708b6f901a897149b074ca72d817
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_32000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_32000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..4dbf7c33e71fc36d60897f70709902b186bc678e
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_32000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b123ced884af78ea9742ab26cdc756a4579626eab8632f37f9b1b9bc3ff77ded
+size 154287
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_34000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_34000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..3181d2a3d01b2b7693571b2201a35553b1fb67f7
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_34000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a03123470d445348f7b752af783ae0c4cd688f226d5976d7d85768a09be2cc1
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_34000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_34000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..6e3e01785c3f813a3415d05554a86bec62346639
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_34000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67f5bc8b35699de30a2cb2bf5d700c02d0b093f1eee858d4730c8f4c6ab5754b
+size 147223
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_36000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_36000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..e1efe5af0c094ac65812a5a05798e1d590b23080
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_36000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ed5260ae01c9492a7d6eb2720c14dff7b67a74f4aff6804852877e7006d6ce9
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_36000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_36000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..b8e75d80ddddc500c2cc8962ff93472b112e3bbf
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_36000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edc0af59167e2e257dab81a0e551076638325e8961f5d7a225cb45cd3dc2a31e
+size 154892
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_38000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_38000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..a5897696dc86211bd47c7bfe3416d083ea025767
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_38000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1f04457e8d0c271cf48f0376df6a9c7870b433e6c9f617a0bfa1be562a231fd
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_38000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_38000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..e3d57a604786ef7bb081baa4f080ac1369b6f47d
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_38000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f8e3a9dbe1cb642ca9efa475a45fe98b32292ee82064f775e417ff12837ee26
+size 146397
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_4000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_4000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..d9f5fb8e09ace12650a8f1cc2ee1156ae9965a51
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_4000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:802343dd872afc314b788f9c87906a279be7ca612e3cb1e35ad213eb3f5f4a28
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_4000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_4000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..c07450229464109c86ac07bfeb24eccbeda8060f
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_4000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b1f239b73cba9a5e4fa7862e27382650edcd2708acb73e2373f09109025113a
+size 178708
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_40000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_40000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..aa352d80f710ce68b50496d93298ddf3c1d8b234
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_40000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf6da689eb39ea23d8d9d9eac9dbbc8cf0a536df4eca546d1cf538d15412b6cc
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_40000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_40000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..503d5988bbc29a692c2f49e638eec85fcf3864be
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_40000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da1b9a27c75796401dd9d4f266f88398475b23aba5a536f7709d650930566cca
+size 150967
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_42000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_42000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..5f1512858d6e51244bd60d2cb89f796d61c6ddf0
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_42000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14ace50fd00aee8f6eb4f92239d88abfff0e3d3c6ab0eefa225f60641060a732
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_42000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_42000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..c0e3a6a6ff344dbc57a842d460b5159cf6371c8e
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_42000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8707a151dddb576b7806790387442f2d1f90549b6ac4ede352c3ad66f64743a4
+size 149642
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_44000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_44000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..14ec3e83c0cbc3a14f9c1a166acc2a0d028f0fd2
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_44000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1049a2caad98b02bfaf54706d360e8d40fee2f56d4fcab9cce2bb46a0b0746fd
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_44000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_44000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..5a112d5c73a02405df7b0cb99d57272314829b4e
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_44000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e688f92f22cb0e236f4819505e75ab0c23e3729593453ddc89c7be80d61b1d20
+size 154204
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_46000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_46000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..df9006a1f389a7f746d2bae4bbd7c191ed691700
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_46000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:555ccb58ecaf4d0840a4a9f6c3c7916876c9a2056be1d39b382dcb0056c26dd1
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_46000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_46000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..bc295ff5afc086e8b31f6f531d443ef38da601dd
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_46000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15ad7a2938647ed36522e255d1408a389e4057c227978fcbf206b3108c444db7
+size 150777
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_48000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_48000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..76281cf8f2945fee1c2f10b0df696e657b092948
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_48000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f03024d13f01b612a47ea50d048757a5eefd652302424bd9033bb3f5283f493d
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_48000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_48000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..7ebc8c9faad5475544ff31544e56ee14fd7464f9
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_48000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ff2b7d12aa267732f75538650be7e15d43f20e287117b429c3a25fcf0ea4663
+size 153057
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_50000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_50000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..1cdc3879e906560b8339db803f7195c065e9a423
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_50000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:975f92aa2c85d6f8128c1986386a1748cd179224a57af893c0fe2c8ef6755d82
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_50000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_50000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..e34d438bc3bf78fb03ff44607f4cb6c6967912ea
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_50000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:681d3d50206379d29a6f124b6e860ff1967995588277757f63a91729a4c7c88f
+size 149301
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_52000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_52000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..07246b0863ed6dc143d5a11c54366bcd85ae64bc
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_52000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42d23949d4dd49adafffa8d78183890272135111c0876ebad6f34323e1e10546
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_52000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_52000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..87edcd6bebeb39c2e81ce5bfffdf6d52f615ddd7
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_52000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9204095a865736717040f4431ef4ebd3922838d87d257d96c81072e69a99f451
+size 147615
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_54000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_54000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..ab30a4e3ddabcb771b9cfc0bc020c17883f5a771
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_54000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d699b3b9350887d951d1b695722d0cb96431aa7df30148b70a1b5e23c4cf41cd
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_54000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_54000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..02cffcc91fab2bb30825d85dcddb9f23e4858d34
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_54000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aedcc3693c2fa480a52c7aee9aeecd7b7c7b09fc1665d6497dc10c8946d91831
+size 147371
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_56000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_56000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..d8e46fd17c384ed2874fd3b46217a74430848dcc
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_56000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3302c9a925f26a3b4dc4ed7cd7357142823c28056b8b7b5509dd14e4cf9a7efa
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_56000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_56000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..96de00b217b00f132a6d6da2f634cd3552b8632d
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_56000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a18107b0203722f7f25efe888bc0b8ceb99aee115959dc69e36ce59e2ca5e4f
+size 149304
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_58000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_58000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..c2ec44c9c937746ff3e4a35915a4f2a436deb285
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_58000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bde7c0ac63d52fe779eca39579f361c7371a220164ae87b7bc244f0f1c0f6f4
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_58000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_58000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..ef7e6b94b74fecbddee2323868b36afe20cc46e4
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_58000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66f7e4c6c362ba79f731bf2af8631ff75d114aa999b954236fcb3fb8f306b2d5
+size 147547
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_6000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_6000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..5e607210e031c2749bafe24d34d20f3ae04b8b23
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_6000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d90ee31a79d14815e00f6fcaa5a6f4f37f317519e55e770a5fe4a01f7784c8d4
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_6000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_6000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..1ad361e151c48144b0df0d76be8c426e164c8705
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_6000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbcfe325809c6d46d7032c252449945daeecb5326b56d751cc03750c97e71f4b
+size 171687
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_60000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_60000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..6b680b1d100f802a2f30d3ad3819dde7414d77d4
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_60000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c683ef1a78f643113f8487af2b360ca6d59a6e7e87cb966e8398de155c15771d
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_60000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_60000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..3c5541da04bee4c1e03996b0c785d60afa72a624
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_60000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dcdbfeee1a59a75a3031275000d432335b271d6aaf9e2ea34238cbc7b0d296b
+size 142259
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_62000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_62000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..001beafb628946353593ae7187db27982cd1dbe5
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_62000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84a15974bb3ed876a9e9d87c98a2af7768caef50b66902464d2dd88c4b7a6682
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_62000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_62000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..47741e8f4021e68ef904f027bc722c0c6212993d
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_62000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dabd926175ccda6ac8d3ccb4b6c51daa9fc4e82e7f1d16cfb95fdd6776ac1730
+size 148833
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_64000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_64000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..a37243008f29bf724800b48e982b2571e3419b67
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_64000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a68899d0e2419510d4d2d975057dcdeeb1566bc9daa139ea7674da0af58f47e
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_64000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_64000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..1d1d4ec3fc8aafd91449865f2b3cd0d9aa7d2a56
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_64000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25e2299a64c6b5941f405bd9db8dc780bc5ff6e6179eac5727cdb7e1d8e02fea
+size 146240
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_66000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_66000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..287d526f7e6e3a15d79cf9c827bbe55a13ad73bc
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_66000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a33cccd83045feedd6a3929592c5bd0d15eaaa14e74986616d4268093506ad80
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_66000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_66000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..cd3722d93d09002a45b2ac6d0e02ef489ab381ef
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_66000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27e396a67e7a9cedfb82580aa26b0d9f18c8c0b32d3fdf1e119297be77755dca
+size 143109
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_8000/sample.npy b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_8000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..2f506e236b1ca5ea4ac096a5923ab6d4db6c8c66
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_8000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d344b28f0c0035b6ce8f8340332cc825be4b812b964ededc605dc70d91563b4b
+size 251008
diff --git a/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_8000/sample.png b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_8000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..bd1173f046f18a8e1948674e0a7ab05aac04f892
--- /dev/null
+++ b/dpdm/fmnist_28_eps10.0trainval-2024-10-23-19-31-12/train/samples/iter_8000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:450a3ab2a179b0fdf14af1bfca843801f4a3c0cb49fb5d9b1a7a5de8ab08a429
+size 167372