diff --git a/.gitattributes b/.gitattributes
index 872226bdd20057ee7ecae09858ba3fb89d036c8a..83927c3a50fafe73fe66688e4ee9356a44bee892 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -950,3 +950,36 @@ camelyon_32_eps1.0trainval-2024-10-24-08-46-55/train/samples/iter_92000/sample.p
 camelyon_32_eps1.0trainval-2024-10-24-08-46-55/train/samples/iter_94000/sample.png filter=lfs diff=lfs merge=lfs -text
 camelyon_32_eps1.0trainval-2024-10-24-08-46-55/train/samples/iter_96000/sample.png filter=lfs diff=lfs merge=lfs -text
 camelyon_32_eps1.0trainval-2024-10-24-08-46-55/train/samples/iter_98000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_10000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_12000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_14000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_16000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_18000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_2000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_20000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_22000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_24000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_26000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_28000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_30000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_32000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_34000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_36000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_38000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_4000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_40000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_42000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_44000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_46000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_48000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_50000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_52000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_54000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_56000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_58000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_6000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_60000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_62000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_64000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_66000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_8000/sample.png filter=lfs diff=lfs merge=lfs -text
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/stdout.txt b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/stdout.txt
new file mode 100644
index 0000000000000000000000000000000000000000..5bfe751667ea19417e6d2522e9dee504698a1389
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/stdout.txt
@@ -0,0 +1,1174 @@
+INFO - utils.py - 2024-10-22 22:42:17,377 - {'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/mnist_28_eps10.0trainval-2024-10-22-22-42-07', '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': 'mnist', 'num_channels': 1, 'resolution': 28, 'n_classes': 10, 'train_path': 'dataset/mnist/train_28.zip', 'test_path': 'dataset/mnist/test_28.zip', 'fid_stats': 'dataset/mnist/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': 0.05, 's_max': 50, 'num_steps': 1000, 'tmin': 0.002, 'tmax': 80.0, 'rho': 7.0, 'guid_scale': 0.25}, '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/mnist/fid_stats_28.npz'}, 'pretrain': {'log_dir': 'exp/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/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/mnist_28_eps10.0trainval-2024-10-22-22-42-07/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/mnist_28_eps10.0trainval-2024-10-22-22-42-07/gen'}, 'eval': {'batch_size': 1000}}
+INFO - dataset_loader.py - 2024-10-22 22:42:19,500 - delta is reset as 1.6657508770018431e-06
+INFO - dpsgd_diffusion.py - 2024-10-22 22:42:27,534 - Number of trainable parameters in model: 0
+INFO - dpsgd_diffusion.py - 2024-10-22 22:42:27,534 - Number of total epochs: 150
+INFO - dpsgd_diffusion.py - 2024-10-22 22:42:27,534 - Starting training at step 0
+INFO - dpsgd_diffusion.py - 2024-10-22 22:47:09,220 - Loss: 1.3854, step: 100
+INFO - dpsgd_diffusion.py - 2024-10-22 22:50:02,783 - Loss: 1.2154, step: 200
+INFO - dpsgd_diffusion.py - 2024-10-22 22:52:27,394 - Loss: 1.0908, step: 300
+INFO - dpsgd_diffusion.py - 2024-10-22 22:54:55,491 - Loss: 1.0483, step: 400
+INFO - dpsgd_diffusion.py - 2024-10-22 22:56:04,737 - Eps-value after 1 epochs: 0.8691
+INFO - dpsgd_diffusion.py - 2024-10-22 22:57:18,258 - Loss: 1.0064, step: 500
+INFO - dpsgd_diffusion.py - 2024-10-22 22:59:50,417 - Loss: 0.9417, step: 600
+INFO - dpsgd_diffusion.py - 2024-10-22 23:02:16,725 - Loss: 0.8909, step: 700
+INFO - dpsgd_diffusion.py - 2024-10-22 23:04:41,020 - Loss: 0.8344, step: 800
+INFO - dpsgd_diffusion.py - 2024-10-22 23:06:58,800 - Eps-value after 2 epochs: 1.1293
+INFO - dpsgd_diffusion.py - 2024-10-22 23:07:03,924 - Loss: 0.7648, step: 900
+INFO - dpsgd_diffusion.py - 2024-10-22 23:09:29,503 - Loss: 0.7046, step: 1000
+INFO - dpsgd_diffusion.py - 2024-10-22 23:11:53,777 - Loss: 0.6570, step: 1100
+INFO - dpsgd_diffusion.py - 2024-10-22 23:14:19,838 - Loss: 0.6177, step: 1200
+INFO - dpsgd_diffusion.py - 2024-10-22 23:16:56,156 - Loss: 0.5809, step: 1300
+INFO - dpsgd_diffusion.py - 2024-10-22 23:18:04,846 - Eps-value after 3 epochs: 1.3393
+INFO - dpsgd_diffusion.py - 2024-10-22 23:19:22,855 - Loss: 0.5523, step: 1400
+INFO - dpsgd_diffusion.py - 2024-10-22 23:21:45,013 - Loss: 0.5175, step: 1500
+INFO - dpsgd_diffusion.py - 2024-10-22 23:24:08,007 - Loss: 0.4856, step: 1600
+INFO - dpsgd_diffusion.py - 2024-10-22 23:26:44,744 - Loss: 0.4579, step: 1700
+INFO - dpsgd_diffusion.py - 2024-10-22 23:29:14,650 - Eps-value after 4 epochs: 1.5222
+INFO - dpsgd_diffusion.py - 2024-10-22 23:29:25,451 - Loss: 0.4485, step: 1800
+INFO - dpsgd_diffusion.py - 2024-10-22 23:31:49,798 - Loss: 0.4026, step: 1900
+INFO - dpsgd_diffusion.py - 2024-10-22 23:34:11,130 - Loss: 0.4091, step: 2000
+INFO - dpsgd_diffusion.py - 2024-10-22 23:34:11,998 - Saving snapshot checkpoint and sampling single batch at iteration 2000.
+WARNING - image.py - 2024-10-22 23:34:13,530 - 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 - 2024-10-22 23:34:54,620 - FID at iteration 2000: 236.142049
+INFO - dpsgd_diffusion.py - 2024-10-22 23:37:17,950 - Loss: 0.3480, step: 2100
+INFO - dpsgd_diffusion.py - 2024-10-22 23:39:44,250 - Loss: 0.3747, step: 2200
+INFO - dpsgd_diffusion.py - 2024-10-22 23:40:42,646 - Eps-value after 5 epochs: 1.6851
+INFO - dpsgd_diffusion.py - 2024-10-22 23:42:06,332 - Loss: 0.3314, step: 2300
+INFO - dpsgd_diffusion.py - 2024-10-22 23:44:31,597 - Loss: 0.3077, step: 2400
+INFO - dpsgd_diffusion.py - 2024-10-22 23:46:52,420 - Loss: 0.2889, step: 2500
+INFO - dpsgd_diffusion.py - 2024-10-22 23:49:13,202 - Loss: 0.2868, step: 2600
+INFO - dpsgd_diffusion.py - 2024-10-22 23:51:17,080 - Eps-value after 6 epochs: 1.8363
+INFO - dpsgd_diffusion.py - 2024-10-22 23:51:33,586 - Loss: 0.2876, step: 2700
+INFO - dpsgd_diffusion.py - 2024-10-22 23:53:59,165 - Loss: 0.2773, step: 2800
+INFO - dpsgd_diffusion.py - 2024-10-22 23:56:21,551 - Loss: 0.2633, step: 2900
+INFO - dpsgd_diffusion.py - 2024-10-22 23:58:46,491 - Loss: 0.2624, step: 3000
+INFO - dpsgd_diffusion.py - 2024-10-23 00:01:07,442 - Loss: 0.2446, step: 3100
+INFO - dpsgd_diffusion.py - 2024-10-23 00:02:01,679 - Eps-value after 7 epochs: 1.9739
+INFO - dpsgd_diffusion.py - 2024-10-23 00:03:32,251 - Loss: 0.2320, step: 3200
+INFO - dpsgd_diffusion.py - 2024-10-23 00:06:03,485 - Loss: 0.2454, step: 3300
+INFO - dpsgd_diffusion.py - 2024-10-23 00:08:25,017 - Loss: 0.2348, step: 3400
+INFO - dpsgd_diffusion.py - 2024-10-23 00:10:48,052 - Loss: 0.2150, step: 3500
+INFO - dpsgd_diffusion.py - 2024-10-23 00:12:46,877 - Eps-value after 8 epochs: 2.1046
+INFO - dpsgd_diffusion.py - 2024-10-23 00:13:09,367 - Loss: 0.2254, step: 3600
+INFO - dpsgd_diffusion.py - 2024-10-23 00:15:35,955 - Loss: 0.2238, step: 3700
+INFO - dpsgd_diffusion.py - 2024-10-23 00:18:14,062 - Loss: 0.2156, step: 3800
+INFO - dpsgd_diffusion.py - 2024-10-23 00:20:42,101 - Loss: 0.2133, step: 3900
+INFO - dpsgd_diffusion.py - 2024-10-23 00:23:16,520 - Loss: 0.2024, step: 4000
+INFO - dpsgd_diffusion.py - 2024-10-23 00:23:16,540 - Saving snapshot checkpoint and sampling single batch at iteration 4000.
+WARNING - image.py - 2024-10-23 00:23:17,061 - 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 00:23:38,555 - FID at iteration 4000: 113.937888
+INFO - dpsgd_diffusion.py - 2024-10-23 00:24:34,762 - Eps-value after 9 epochs: 2.2283
+INFO - dpsgd_diffusion.py - 2024-10-23 00:26:26,764 - Loss: 0.2019, step: 4100
+INFO - dpsgd_diffusion.py - 2024-10-23 00:29:15,442 - Loss: 0.2229, step: 4200
+INFO - dpsgd_diffusion.py - 2024-10-23 00:32:02,011 - Loss: 0.1960, step: 4300
+INFO - dpsgd_diffusion.py - 2024-10-23 00:34:53,348 - Loss: 0.2145, step: 4400
+INFO - dpsgd_diffusion.py - 2024-10-23 00:36:59,734 - Eps-value after 10 epochs: 2.3462
+INFO - dpsgd_diffusion.py - 2024-10-23 00:37:32,702 - Loss: 0.2067, step: 4500
+INFO - dpsgd_diffusion.py - 2024-10-23 00:40:12,349 - Loss: 0.1940, step: 4600
+INFO - dpsgd_diffusion.py - 2024-10-23 00:42:51,371 - Loss: 0.1983, step: 4700
+INFO - dpsgd_diffusion.py - 2024-10-23 00:45:43,367 - Loss: 0.1806, step: 4800
+INFO - dpsgd_diffusion.py - 2024-10-23 00:48:29,670 - Loss: 0.1868, step: 4900
+INFO - dpsgd_diffusion.py - 2024-10-23 00:49:17,262 - Eps-value after 11 epochs: 2.4591
+INFO - dpsgd_diffusion.py - 2024-10-23 00:51:09,828 - Loss: 0.1886, step: 5000
+INFO - dpsgd_diffusion.py - 2024-10-23 00:53:42,991 - Loss: 0.1881, step: 5100
+INFO - dpsgd_diffusion.py - 2024-10-23 00:56:26,283 - Loss: 0.1765, step: 5200
+INFO - dpsgd_diffusion.py - 2024-10-23 00:59:14,186 - Loss: 0.1790, step: 5300
+INFO - dpsgd_diffusion.py - 2024-10-23 01:01:12,997 - Eps-value after 12 epochs: 2.5675
+INFO - dpsgd_diffusion.py - 2024-10-23 01:01:51,281 - Loss: 0.1854, step: 5400
+INFO - dpsgd_diffusion.py - 2024-10-23 01:04:34,450 - Loss: 0.1939, step: 5500
+INFO - dpsgd_diffusion.py - 2024-10-23 01:07:17,214 - Loss: 0.1726, step: 5600
+INFO - dpsgd_diffusion.py - 2024-10-23 01:10:02,495 - Loss: 0.1724, step: 5700
+INFO - dpsgd_diffusion.py - 2024-10-23 01:12:39,059 - Loss: 0.1790, step: 5800
+INFO - dpsgd_diffusion.py - 2024-10-23 01:13:20,782 - Eps-value after 13 epochs: 2.6723
+INFO - dpsgd_diffusion.py - 2024-10-23 01:15:21,106 - Loss: 0.1784, step: 5900
+INFO - dpsgd_diffusion.py - 2024-10-23 01:18:06,508 - Loss: 0.1802, step: 6000
+INFO - dpsgd_diffusion.py - 2024-10-23 01:18:07,510 - Saving snapshot checkpoint and sampling single batch at iteration 6000.
+WARNING - image.py - 2024-10-23 01:18:08,079 - 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 01:18:31,882 - FID at iteration 6000: 65.741956
+INFO - dpsgd_diffusion.py - 2024-10-23 01:21:08,648 - Loss: 0.1779, step: 6100
+INFO - dpsgd_diffusion.py - 2024-10-23 01:23:50,057 - Loss: 0.1757, step: 6200
+INFO - dpsgd_diffusion.py - 2024-10-23 01:25:48,354 - Eps-value after 14 epochs: 2.7735
+INFO - dpsgd_diffusion.py - 2024-10-23 01:26:38,027 - Loss: 0.1714, step: 6300
+INFO - dpsgd_diffusion.py - 2024-10-23 01:29:15,793 - Loss: 0.1650, step: 6400
+INFO - dpsgd_diffusion.py - 2024-10-23 01:32:01,173 - Loss: 0.1725, step: 6500
+INFO - dpsgd_diffusion.py - 2024-10-23 01:34:48,927 - Loss: 0.1607, step: 6600
+INFO - dpsgd_diffusion.py - 2024-10-23 01:37:36,922 - Loss: 0.1607, step: 6700
+INFO - dpsgd_diffusion.py - 2024-10-23 01:38:14,446 - Eps-value after 15 epochs: 2.8716
+INFO - dpsgd_diffusion.py - 2024-10-23 01:40:26,335 - Loss: 0.1667, step: 6800
+INFO - dpsgd_diffusion.py - 2024-10-23 01:43:15,116 - Loss: 0.1726, step: 6900
+INFO - dpsgd_diffusion.py - 2024-10-23 01:46:07,373 - Loss: 0.1771, step: 7000
+INFO - dpsgd_diffusion.py - 2024-10-23 01:48:45,930 - Loss: 0.1499, step: 7100
+INFO - dpsgd_diffusion.py - 2024-10-23 01:50:45,800 - Eps-value after 16 epochs: 2.9671
+INFO - dpsgd_diffusion.py - 2024-10-23 01:51:42,345 - Loss: 0.1620, step: 7200
+INFO - dpsgd_diffusion.py - 2024-10-23 01:54:37,229 - Loss: 0.1404, step: 7300
+INFO - dpsgd_diffusion.py - 2024-10-23 01:57:22,909 - Loss: 0.1645, step: 7400
+INFO - dpsgd_diffusion.py - 2024-10-23 02:00:02,284 - Loss: 0.1706, step: 7500
+INFO - dpsgd_diffusion.py - 2024-10-23 02:02:47,637 - Loss: 0.1567, step: 7600
+INFO - dpsgd_diffusion.py - 2024-10-23 02:03:17,335 - Eps-value after 17 epochs: 3.0599
+INFO - dpsgd_diffusion.py - 2024-10-23 02:05:36,773 - Loss: 0.1450, step: 7700
+INFO - dpsgd_diffusion.py - 2024-10-23 02:08:13,033 - Loss: 0.1707, step: 7800
+INFO - dpsgd_diffusion.py - 2024-10-23 02:11:01,049 - Loss: 0.1595, step: 7900
+INFO - dpsgd_diffusion.py - 2024-10-23 02:13:49,826 - Loss: 0.1613, step: 8000
+INFO - dpsgd_diffusion.py - 2024-10-23 02:13:49,843 - Saving snapshot checkpoint and sampling single batch at iteration 8000.
+WARNING - image.py - 2024-10-23 02:13:50,375 - 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 - 2024-10-23 02:14:12,398 - FID at iteration 8000: 50.403164
+INFO - dpsgd_diffusion.py - 2024-10-23 02:16:01,649 - Eps-value after 18 epochs: 3.1505
+INFO - dpsgd_diffusion.py - 2024-10-23 02:16:59,781 - Loss: 0.1509, step: 8100
+INFO - dpsgd_diffusion.py - 2024-10-23 02:19:44,737 - Loss: 0.1743, step: 8200
+INFO - dpsgd_diffusion.py - 2024-10-23 02:22:35,416 - Loss: 0.1647, step: 8300
+INFO - dpsgd_diffusion.py - 2024-10-23 02:25:22,357 - Loss: 0.1620, step: 8400
+INFO - dpsgd_diffusion.py - 2024-10-23 02:28:00,090 - Loss: 0.1749, step: 8500
+INFO - dpsgd_diffusion.py - 2024-10-23 02:28:23,175 - Eps-value after 19 epochs: 3.2390
+INFO - dpsgd_diffusion.py - 2024-10-23 02:30:49,304 - Loss: 0.1699, step: 8600
+INFO - dpsgd_diffusion.py - 2024-10-23 02:33:37,325 - Loss: 0.1685, step: 8700
+INFO - dpsgd_diffusion.py - 2024-10-23 02:36:17,145 - Loss: 0.1531, step: 8800
+INFO - dpsgd_diffusion.py - 2024-10-23 02:38:59,111 - Loss: 0.1661, step: 8900
+INFO - dpsgd_diffusion.py - 2024-10-23 02:40:43,573 - Eps-value after 20 epochs: 3.3255
+INFO - dpsgd_diffusion.py - 2024-10-23 02:41:51,416 - Loss: 0.1649, step: 9000
+INFO - dpsgd_diffusion.py - 2024-10-23 02:44:33,453 - Loss: 0.1768, step: 9100
+INFO - dpsgd_diffusion.py - 2024-10-23 02:47:20,733 - Loss: 0.1606, step: 9200
+INFO - dpsgd_diffusion.py - 2024-10-23 02:50:09,572 - Loss: 0.1696, step: 9300
+INFO - dpsgd_diffusion.py - 2024-10-23 02:53:01,615 - Loss: 0.1730, step: 9400
+INFO - dpsgd_diffusion.py - 2024-10-23 02:53:15,518 - Eps-value after 21 epochs: 3.4101
+INFO - dpsgd_diffusion.py - 2024-10-23 02:55:39,940 - Loss: 0.1511, step: 9500
+INFO - dpsgd_diffusion.py - 2024-10-23 02:58:24,177 - Loss: 0.1465, step: 9600
+INFO - dpsgd_diffusion.py - 2024-10-23 03:01:09,581 - Loss: 0.1418, step: 9700
+INFO - dpsgd_diffusion.py - 2024-10-23 03:03:54,200 - Loss: 0.1489, step: 9800
+INFO - dpsgd_diffusion.py - 2024-10-23 03:05:21,929 - Eps-value after 22 epochs: 3.4931
+INFO - dpsgd_diffusion.py - 2024-10-23 03:06:31,105 - Loss: 0.1614, step: 9900
+INFO - dpsgd_diffusion.py - 2024-10-23 03:09:12,994 - Loss: 0.1505, step: 10000
+INFO - dpsgd_diffusion.py - 2024-10-23 03:09:14,001 - Saving snapshot checkpoint and sampling single batch at iteration 10000.
+WARNING - image.py - 2024-10-23 03:09:14,541 - 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 03:09:36,402 - FID at iteration 10000: 42.494841
+INFO - dpsgd_diffusion.py - 2024-10-23 03:12:18,577 - Loss: 0.1541, step: 10100
+INFO - dpsgd_diffusion.py - 2024-10-23 03:15:00,805 - Loss: 0.1613, step: 10200
+INFO - dpsgd_diffusion.py - 2024-10-23 03:18:06,621 - Loss: 0.1537, step: 10300
+INFO - dpsgd_diffusion.py - 2024-10-23 03:18:13,602 - Eps-value after 23 epochs: 3.5746
+INFO - dpsgd_diffusion.py - 2024-10-23 03:20:54,137 - Loss: 0.1495, step: 10400
+INFO - dpsgd_diffusion.py - 2024-10-23 03:23:26,985 - Loss: 0.1515, step: 10500
+INFO - dpsgd_diffusion.py - 2024-10-23 03:26:01,120 - Loss: 0.1583, step: 10600
+INFO - dpsgd_diffusion.py - 2024-10-23 03:28:44,500 - Loss: 0.1470, step: 10700
+INFO - dpsgd_diffusion.py - 2024-10-23 03:30:08,824 - Eps-value after 24 epochs: 3.6546
+INFO - dpsgd_diffusion.py - 2024-10-23 03:31:23,583 - Loss: 0.1529, step: 10800
+INFO - dpsgd_diffusion.py - 2024-10-23 03:34:04,328 - Loss: 0.1485, step: 10900
+INFO - dpsgd_diffusion.py - 2024-10-23 03:36:42,312 - Loss: 0.1571, step: 11000
+INFO - dpsgd_diffusion.py - 2024-10-23 03:39:24,146 - Loss: 0.1393, step: 11100
+INFO - dpsgd_diffusion.py - 2024-10-23 03:41:56,407 - Loss: 0.1457, step: 11200
+INFO - dpsgd_diffusion.py - 2024-10-23 03:41:56,429 - Eps-value after 25 epochs: 3.7332
+INFO - dpsgd_diffusion.py - 2024-10-23 03:44:39,893 - Loss: 0.1582, step: 11300
+INFO - dpsgd_diffusion.py - 2024-10-23 03:47:25,920 - Loss: 0.1514, step: 11400
+INFO - dpsgd_diffusion.py - 2024-10-23 03:50:05,436 - Loss: 0.1496, step: 11500
+INFO - dpsgd_diffusion.py - 2024-10-23 03:52:50,748 - Loss: 0.1574, step: 11600
+INFO - dpsgd_diffusion.py - 2024-10-23 03:54:07,926 - Eps-value after 26 epochs: 3.8104
+INFO - dpsgd_diffusion.py - 2024-10-23 03:55:24,935 - Loss: 0.1573, step: 11700
+INFO - dpsgd_diffusion.py - 2024-10-23 03:58:08,997 - Loss: 0.1473, step: 11800
+INFO - dpsgd_diffusion.py - 2024-10-23 04:00:56,690 - Loss: 0.1557, step: 11900
+INFO - dpsgd_diffusion.py - 2024-10-23 04:03:41,772 - Loss: 0.1534, step: 12000
+INFO - dpsgd_diffusion.py - 2024-10-23 04:03:41,791 - Saving snapshot checkpoint and sampling single batch at iteration 12000.
+WARNING - image.py - 2024-10-23 04:03:42,309 - 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 04:04:04,702 - FID at iteration 12000: 36.181091
+INFO - dpsgd_diffusion.py - 2024-10-23 04:06:39,881 - Eps-value after 27 epochs: 3.8864
+INFO - dpsgd_diffusion.py - 2024-10-23 04:06:45,737 - Loss: 0.1468, step: 12100
+INFO - dpsgd_diffusion.py - 2024-10-23 04:09:24,375 - Loss: 0.1490, step: 12200
+INFO - dpsgd_diffusion.py - 2024-10-23 04:11:58,168 - Loss: 0.1535, step: 12300
+INFO - dpsgd_diffusion.py - 2024-10-23 04:14:33,693 - Loss: 0.1474, step: 12400
+INFO - dpsgd_diffusion.py - 2024-10-23 04:17:13,887 - Loss: 0.1409, step: 12500
+INFO - dpsgd_diffusion.py - 2024-10-23 04:18:28,272 - Eps-value after 28 epochs: 3.9612
+INFO - dpsgd_diffusion.py - 2024-10-23 04:20:00,146 - Loss: 0.1587, step: 12600
+INFO - dpsgd_diffusion.py - 2024-10-23 04:22:46,003 - Loss: 0.1381, step: 12700
+INFO - dpsgd_diffusion.py - 2024-10-23 04:25:33,478 - Loss: 0.1511, step: 12800
+INFO - dpsgd_diffusion.py - 2024-10-23 04:28:07,407 - Loss: 0.1522, step: 12900
+INFO - dpsgd_diffusion.py - 2024-10-23 04:30:36,290 - Eps-value after 29 epochs: 4.0349
+INFO - dpsgd_diffusion.py - 2024-10-23 04:30:47,758 - Loss: 0.1513, step: 13000
+INFO - dpsgd_diffusion.py - 2024-10-23 04:33:25,989 - Loss: 0.1383, step: 13100
+INFO - dpsgd_diffusion.py - 2024-10-23 04:36:09,829 - Loss: 0.1431, step: 13200
+INFO - dpsgd_diffusion.py - 2024-10-23 04:39:02,865 - Loss: 0.1342, step: 13300
+INFO - dpsgd_diffusion.py - 2024-10-23 04:41:45,653 - Loss: 0.1538, step: 13400
+INFO - dpsgd_diffusion.py - 2024-10-23 04:42:49,887 - Eps-value after 30 epochs: 4.1076
+INFO - dpsgd_diffusion.py - 2024-10-23 04:44:23,013 - Loss: 0.1569, step: 13500
+INFO - dpsgd_diffusion.py - 2024-10-23 04:47:13,154 - Loss: 0.1476, step: 13600
+INFO - dpsgd_diffusion.py - 2024-10-23 04:49:50,459 - Loss: 0.1352, step: 13700
+INFO - dpsgd_diffusion.py - 2024-10-23 04:52:28,025 - Loss: 0.1426, step: 13800
+INFO - dpsgd_diffusion.py - 2024-10-23 04:54:53,226 - Eps-value after 31 epochs: 4.1794
+INFO - dpsgd_diffusion.py - 2024-10-23 04:55:12,330 - Loss: 0.1452, step: 13900
+INFO - dpsgd_diffusion.py - 2024-10-23 04:57:50,794 - Loss: 0.1477, step: 14000
+INFO - dpsgd_diffusion.py - 2024-10-23 04:57:51,703 - Saving snapshot checkpoint and sampling single batch at iteration 14000.
+WARNING - image.py - 2024-10-23 04:57:52,236 - 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 04:58:17,293 - FID at iteration 14000: 31.480244
+INFO - dpsgd_diffusion.py - 2024-10-23 05:00:57,451 - Loss: 0.1355, step: 14100
+INFO - dpsgd_diffusion.py - 2024-10-23 05:03:45,296 - Loss: 0.1484, step: 14200
+INFO - dpsgd_diffusion.py - 2024-10-23 05:06:25,993 - Loss: 0.1428, step: 14300
+INFO - dpsgd_diffusion.py - 2024-10-23 05:07:27,225 - Eps-value after 32 epochs: 4.2501
+INFO - dpsgd_diffusion.py - 2024-10-23 05:09:11,633 - Loss: 0.1500, step: 14400
+INFO - dpsgd_diffusion.py - 2024-10-23 05:11:51,622 - Loss: 0.1440, step: 14500
+INFO - dpsgd_diffusion.py - 2024-10-23 05:14:30,151 - Loss: 0.1517, step: 14600
+INFO - dpsgd_diffusion.py - 2024-10-23 05:17:04,768 - Loss: 0.1401, step: 14700
+INFO - dpsgd_diffusion.py - 2024-10-23 05:19:15,170 - Eps-value after 33 epochs: 4.3198
+INFO - dpsgd_diffusion.py - 2024-10-23 05:19:40,972 - Loss: 0.1470, step: 14800
+INFO - dpsgd_diffusion.py - 2024-10-23 05:22:18,875 - Loss: 0.1579, step: 14900
+INFO - dpsgd_diffusion.py - 2024-10-23 05:24:58,362 - Loss: 0.1412, step: 15000
+INFO - dpsgd_diffusion.py - 2024-10-23 05:27:40,647 - Loss: 0.1382, step: 15100
+INFO - dpsgd_diffusion.py - 2024-10-23 05:30:24,276 - Loss: 0.1567, step: 15200
+INFO - dpsgd_diffusion.py - 2024-10-23 05:31:14,314 - Eps-value after 34 epochs: 4.3890
+INFO - dpsgd_diffusion.py - 2024-10-23 05:33:02,786 - Loss: 0.1540, step: 15300
+INFO - dpsgd_diffusion.py - 2024-10-23 05:35:47,278 - Loss: 0.1331, step: 15400
+INFO - dpsgd_diffusion.py - 2024-10-23 05:38:31,760 - Loss: 0.1364, step: 15500
+INFO - dpsgd_diffusion.py - 2024-10-23 05:41:08,258 - Loss: 0.1471, step: 15600
+INFO - dpsgd_diffusion.py - 2024-10-23 05:43:19,354 - Eps-value after 35 epochs: 4.4570
+INFO - dpsgd_diffusion.py - 2024-10-23 05:43:48,762 - Loss: 0.1428, step: 15700
+INFO - dpsgd_diffusion.py - 2024-10-23 05:46:25,854 - Loss: 0.1586, step: 15800
+INFO - dpsgd_diffusion.py - 2024-10-23 05:49:01,909 - Loss: 0.1580, step: 15900
+INFO - dpsgd_diffusion.py - 2024-10-23 05:51:51,979 - Loss: 0.1550, step: 16000
+INFO - dpsgd_diffusion.py - 2024-10-23 05:51:51,997 - Saving snapshot checkpoint and sampling single batch at iteration 16000.
+WARNING - image.py - 2024-10-23 05:51:52,537 - 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 05:52:10,415 - FID at iteration 16000: 29.361224
+INFO - dpsgd_diffusion.py - 2024-10-23 05:54:52,576 - Loss: 0.1322, step: 16100
+INFO - dpsgd_diffusion.py - 2024-10-23 05:55:44,017 - Eps-value after 36 epochs: 4.5243
+INFO - dpsgd_diffusion.py - 2024-10-23 05:57:41,558 - Loss: 0.1584, step: 16200
+INFO - dpsgd_diffusion.py - 2024-10-23 06:00:28,482 - Loss: 0.1448, step: 16300
+INFO - dpsgd_diffusion.py - 2024-10-23 06:03:09,237 - Loss: 0.1466, step: 16400
+INFO - dpsgd_diffusion.py - 2024-10-23 06:05:42,922 - Loss: 0.1454, step: 16500
+INFO - dpsgd_diffusion.py - 2024-10-23 06:07:47,802 - Eps-value after 37 epochs: 4.5911
+INFO - dpsgd_diffusion.py - 2024-10-23 06:08:23,517 - Loss: 0.1489, step: 16600
+INFO - dpsgd_diffusion.py - 2024-10-23 06:11:00,607 - Loss: 0.1430, step: 16700
+INFO - dpsgd_diffusion.py - 2024-10-23 06:13:36,877 - Loss: 0.1364, step: 16800
+INFO - dpsgd_diffusion.py - 2024-10-23 06:16:14,611 - Loss: 0.1473, step: 16900
+INFO - dpsgd_diffusion.py - 2024-10-23 06:18:55,963 - Loss: 0.1419, step: 17000
+INFO - dpsgd_diffusion.py - 2024-10-23 06:19:35,832 - Eps-value after 38 epochs: 4.6567
+INFO - dpsgd_diffusion.py - 2024-10-23 06:21:41,338 - Loss: 0.1282, step: 17100
+INFO - dpsgd_diffusion.py - 2024-10-23 06:24:20,943 - Loss: 0.1439, step: 17200
+INFO - dpsgd_diffusion.py - 2024-10-23 06:27:03,029 - Loss: 0.1524, step: 17300
+INFO - dpsgd_diffusion.py - 2024-10-23 06:29:46,886 - Loss: 0.1515, step: 17400
+INFO - dpsgd_diffusion.py - 2024-10-23 06:31:38,383 - Eps-value after 39 epochs: 4.7221
+INFO - dpsgd_diffusion.py - 2024-10-23 06:32:20,969 - Loss: 0.1433, step: 17500
+INFO - dpsgd_diffusion.py - 2024-10-23 06:35:00,359 - Loss: 0.1427, step: 17600
+INFO - dpsgd_diffusion.py - 2024-10-23 06:37:44,877 - Loss: 0.1311, step: 17700
+INFO - dpsgd_diffusion.py - 2024-10-23 06:40:16,440 - Loss: 0.1496, step: 17800
+INFO - dpsgd_diffusion.py - 2024-10-23 06:43:07,934 - Loss: 0.1442, step: 17900
+INFO - dpsgd_diffusion.py - 2024-10-23 06:43:38,690 - Eps-value after 40 epochs: 4.7863
+INFO - dpsgd_diffusion.py - 2024-10-23 06:45:45,760 - Loss: 0.1394, step: 18000
+INFO - dpsgd_diffusion.py - 2024-10-23 06:45:46,942 - Saving snapshot checkpoint and sampling single batch at iteration 18000.
+WARNING - image.py - 2024-10-23 06:45:47,485 - 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 06:46:09,159 - FID at iteration 18000: 26.364344
+INFO - dpsgd_diffusion.py - 2024-10-23 06:48:52,402 - Loss: 0.1406, step: 18100
+INFO - dpsgd_diffusion.py - 2024-10-23 06:51:31,078 - Loss: 0.1399, step: 18200
+INFO - dpsgd_diffusion.py - 2024-10-23 06:54:16,696 - Loss: 0.1412, step: 18300
+INFO - dpsgd_diffusion.py - 2024-10-23 06:56:10,364 - Eps-value after 41 epochs: 4.8503
+INFO - dpsgd_diffusion.py - 2024-10-23 06:56:57,277 - Loss: 0.1349, step: 18400
+INFO - dpsgd_diffusion.py - 2024-10-23 06:59:27,528 - Loss: 0.1453, step: 18500
+INFO - dpsgd_diffusion.py - 2024-10-23 07:02:17,042 - Loss: 0.1318, step: 18600
+INFO - dpsgd_diffusion.py - 2024-10-23 07:05:01,199 - Loss: 0.1434, step: 18700
+INFO - dpsgd_diffusion.py - 2024-10-23 07:07:37,548 - Loss: 0.1299, step: 18800
+INFO - dpsgd_diffusion.py - 2024-10-23 07:08:04,604 - Eps-value after 42 epochs: 4.9133
+INFO - dpsgd_diffusion.py - 2024-10-23 07:10:23,913 - Loss: 0.1378, step: 18900
+INFO - dpsgd_diffusion.py - 2024-10-23 07:13:04,624 - Loss: 0.1581, step: 19000
+INFO - dpsgd_diffusion.py - 2024-10-23 07:15:45,202 - Loss: 0.1507, step: 19100
+INFO - dpsgd_diffusion.py - 2024-10-23 07:18:17,255 - Loss: 0.1383, step: 19200
+INFO - dpsgd_diffusion.py - 2024-10-23 07:19:55,995 - Eps-value after 43 epochs: 4.9761
+INFO - dpsgd_diffusion.py - 2024-10-23 07:20:55,259 - Loss: 0.1339, step: 19300
+INFO - dpsgd_diffusion.py - 2024-10-23 07:23:39,585 - Loss: 0.1488, step: 19400
+INFO - dpsgd_diffusion.py - 2024-10-23 07:26:23,106 - Loss: 0.1330, step: 19500
+INFO - dpsgd_diffusion.py - 2024-10-23 07:29:05,312 - Loss: 0.1549, step: 19600
+INFO - dpsgd_diffusion.py - 2024-10-23 07:31:49,975 - Loss: 0.1400, step: 19700
+INFO - dpsgd_diffusion.py - 2024-10-23 07:32:11,984 - Eps-value after 44 epochs: 5.0379
+INFO - dpsgd_diffusion.py - 2024-10-23 07:34:33,295 - Loss: 0.1470, step: 19800
+INFO - dpsgd_diffusion.py - 2024-10-23 07:37:12,504 - Loss: 0.1408, step: 19900
+INFO - dpsgd_diffusion.py - 2024-10-23 07:39:57,457 - Loss: 0.1433, step: 20000
+INFO - dpsgd_diffusion.py - 2024-10-23 07:39:57,477 - Saving snapshot checkpoint and sampling single batch at iteration 20000.
+WARNING - image.py - 2024-10-23 07:39:57,998 - 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 07:40:20,935 - FID at iteration 20000: 24.641408
+INFO - dpsgd_diffusion.py - 2024-10-23 07:43:08,992 - Loss: 0.1287, step: 20100
+INFO - dpsgd_diffusion.py - 2024-10-23 07:44:54,961 - Eps-value after 45 epochs: 5.0996
+INFO - dpsgd_diffusion.py - 2024-10-23 07:45:52,428 - Loss: 0.1485, step: 20200
+INFO - dpsgd_diffusion.py - 2024-10-23 07:48:28,277 - Loss: 0.1471, step: 20300
+INFO - dpsgd_diffusion.py - 2024-10-23 07:50:59,188 - Loss: 0.1419, step: 20400
+INFO - dpsgd_diffusion.py - 2024-10-23 07:53:33,475 - Loss: 0.1417, step: 20500
+INFO - dpsgd_diffusion.py - 2024-10-23 07:56:16,309 - Loss: 0.1397, step: 20600
+INFO - dpsgd_diffusion.py - 2024-10-23 07:56:32,166 - Eps-value after 46 epochs: 5.1602
+INFO - dpsgd_diffusion.py - 2024-10-23 07:59:01,076 - Loss: 0.1448, step: 20700
+INFO - dpsgd_diffusion.py - 2024-10-23 08:01:42,352 - Loss: 0.1448, step: 20800
+INFO - dpsgd_diffusion.py - 2024-10-23 08:04:12,916 - Loss: 0.1442, step: 20900
+INFO - dpsgd_diffusion.py - 2024-10-23 08:06:57,103 - Loss: 0.1404, step: 21000
+INFO - dpsgd_diffusion.py - 2024-10-23 08:08:27,107 - Eps-value after 47 epochs: 5.2207
+INFO - dpsgd_diffusion.py - 2024-10-23 08:09:44,594 - Loss: 0.1492, step: 21100
+INFO - dpsgd_diffusion.py - 2024-10-23 08:12:26,453 - Loss: 0.1432, step: 21200
+INFO - dpsgd_diffusion.py - 2024-10-23 08:15:03,842 - Loss: 0.1344, step: 21300
+INFO - dpsgd_diffusion.py - 2024-10-23 08:17:34,185 - Loss: 0.1342, step: 21400
+INFO - dpsgd_diffusion.py - 2024-10-23 08:20:14,468 - Loss: 0.1398, step: 21500
+INFO - dpsgd_diffusion.py - 2024-10-23 08:20:21,675 - Eps-value after 48 epochs: 5.2804
+INFO - dpsgd_diffusion.py - 2024-10-23 08:23:01,673 - Loss: 0.1343, step: 21600
+INFO - dpsgd_diffusion.py - 2024-10-23 08:25:41,854 - Loss: 0.1505, step: 21700
+INFO - dpsgd_diffusion.py - 2024-10-23 08:28:27,267 - Loss: 0.1500, step: 21800
+INFO - dpsgd_diffusion.py - 2024-10-23 08:31:08,107 - Loss: 0.1387, step: 21900
+INFO - dpsgd_diffusion.py - 2024-10-23 08:32:26,153 - Eps-value after 49 epochs: 5.3397
+INFO - dpsgd_diffusion.py - 2024-10-23 08:33:49,444 - Loss: 0.1341, step: 22000
+INFO - dpsgd_diffusion.py - 2024-10-23 08:33:50,443 - Saving snapshot checkpoint and sampling single batch at iteration 22000.
+WARNING - image.py - 2024-10-23 08:33:50,973 - 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 08:34:14,505 - FID at iteration 22000: 23.080533
+INFO - dpsgd_diffusion.py - 2024-10-23 08:37:01,389 - Loss: 0.1376, step: 22100
+INFO - dpsgd_diffusion.py - 2024-10-23 08:39:43,655 - Loss: 0.1462, step: 22200
+INFO - dpsgd_diffusion.py - 2024-10-23 08:42:16,881 - Loss: 0.1353, step: 22300
+INFO - dpsgd_diffusion.py - 2024-10-23 08:45:04,441 - Loss: 0.1394, step: 22400
+INFO - dpsgd_diffusion.py - 2024-10-23 08:45:04,468 - Eps-value after 50 epochs: 5.3989
+INFO - dpsgd_diffusion.py - 2024-10-23 08:47:46,695 - Loss: 0.1283, step: 22500
+INFO - dpsgd_diffusion.py - 2024-10-23 08:50:33,036 - Loss: 0.1350, step: 22600
+INFO - dpsgd_diffusion.py - 2024-10-23 08:53:12,512 - Loss: 0.1325, step: 22700
+INFO - dpsgd_diffusion.py - 2024-10-23 08:55:51,556 - Loss: 0.1384, step: 22800
+INFO - dpsgd_diffusion.py - 2024-10-23 08:57:07,775 - Eps-value after 51 epochs: 5.4569
+INFO - dpsgd_diffusion.py - 2024-10-23 08:58:33,270 - Loss: 0.1421, step: 22900
+INFO - dpsgd_diffusion.py - 2024-10-23 09:01:10,714 - Loss: 0.1471, step: 23000
+INFO - dpsgd_diffusion.py - 2024-10-23 09:03:51,441 - Loss: 0.1431, step: 23100
+INFO - dpsgd_diffusion.py - 2024-10-23 09:06:32,693 - Loss: 0.1305, step: 23200
+INFO - dpsgd_diffusion.py - 2024-10-23 09:09:08,234 - Eps-value after 52 epochs: 5.5149
+INFO - dpsgd_diffusion.py - 2024-10-23 09:09:13,518 - Loss: 0.1394, step: 23300
+INFO - dpsgd_diffusion.py - 2024-10-23 09:11:53,184 - Loss: 0.1341, step: 23400
+INFO - dpsgd_diffusion.py - 2024-10-23 09:14:33,392 - Loss: 0.1432, step: 23500
+INFO - dpsgd_diffusion.py - 2024-10-23 09:17:16,492 - Loss: 0.1450, step: 23600
+INFO - dpsgd_diffusion.py - 2024-10-23 09:19:55,110 - Loss: 0.1320, step: 23700
+INFO - dpsgd_diffusion.py - 2024-10-23 09:21:06,067 - Eps-value after 53 epochs: 5.5725
+INFO - dpsgd_diffusion.py - 2024-10-23 09:22:30,175 - Loss: 0.1384, step: 23800
+INFO - dpsgd_diffusion.py - 2024-10-23 09:25:11,521 - Loss: 0.1406, step: 23900
+INFO - dpsgd_diffusion.py - 2024-10-23 09:27:55,701 - Loss: 0.1379, step: 24000
+INFO - dpsgd_diffusion.py - 2024-10-23 09:27:55,718 - Saving snapshot checkpoint and sampling single batch at iteration 24000.
+WARNING - image.py - 2024-10-23 09:27:56,243 - 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 09:28:18,348 - FID at iteration 24000: 21.888813
+INFO - dpsgd_diffusion.py - 2024-10-23 09:31:06,880 - Loss: 0.1345, step: 24100
+INFO - dpsgd_diffusion.py - 2024-10-23 09:33:29,610 - Eps-value after 54 epochs: 5.6293
+INFO - dpsgd_diffusion.py - 2024-10-23 09:33:39,330 - Loss: 0.1393, step: 24200
+INFO - dpsgd_diffusion.py - 2024-10-23 09:36:26,833 - Loss: 0.1427, step: 24300
+INFO - dpsgd_diffusion.py - 2024-10-23 09:39:05,527 - Loss: 0.1422, step: 24400
+INFO - dpsgd_diffusion.py - 2024-10-23 09:41:40,159 - Loss: 0.1373, step: 24500
+INFO - dpsgd_diffusion.py - 2024-10-23 09:44:21,081 - Loss: 0.1348, step: 24600
+INFO - dpsgd_diffusion.py - 2024-10-23 09:45:31,557 - Eps-value after 55 epochs: 5.6861
+INFO - dpsgd_diffusion.py - 2024-10-23 09:47:04,666 - Loss: 0.1340, step: 24700
+INFO - dpsgd_diffusion.py - 2024-10-23 09:49:39,333 - Loss: 0.1424, step: 24800
+INFO - dpsgd_diffusion.py - 2024-10-23 09:52:24,751 - Loss: 0.1393, step: 24900
+INFO - dpsgd_diffusion.py - 2024-10-23 09:55:03,729 - Loss: 0.1474, step: 25000
+INFO - dpsgd_diffusion.py - 2024-10-23 09:57:27,571 - Eps-value after 56 epochs: 5.7424
+INFO - dpsgd_diffusion.py - 2024-10-23 09:57:44,857 - Loss: 0.1380, step: 25100
+INFO - dpsgd_diffusion.py - 2024-10-23 10:00:11,109 - Loss: 0.1438, step: 25200
+INFO - dpsgd_diffusion.py - 2024-10-23 10:02:52,284 - Loss: 0.1358, step: 25300
+INFO - dpsgd_diffusion.py - 2024-10-23 10:05:31,186 - Loss: 0.1486, step: 25400
+INFO - dpsgd_diffusion.py - 2024-10-23 10:08:02,416 - Loss: 0.1457, step: 25500
+INFO - dpsgd_diffusion.py - 2024-10-23 10:09:03,576 - Eps-value after 57 epochs: 5.7980
+INFO - dpsgd_diffusion.py - 2024-10-23 10:10:43,766 - Loss: 0.1358, step: 25600
+INFO - dpsgd_diffusion.py - 2024-10-23 10:13:30,944 - Loss: 0.1398, step: 25700
+INFO - dpsgd_diffusion.py - 2024-10-23 10:16:04,584 - Loss: 0.1343, step: 25800
+INFO - dpsgd_diffusion.py - 2024-10-23 10:18:41,987 - Loss: 0.1455, step: 25900
+INFO - dpsgd_diffusion.py - 2024-10-23 10:20:51,757 - Eps-value after 58 epochs: 5.8536
+INFO - dpsgd_diffusion.py - 2024-10-23 10:21:16,995 - Loss: 0.1331, step: 26000
+INFO - dpsgd_diffusion.py - 2024-10-23 10:21:17,846 - Saving snapshot checkpoint and sampling single batch at iteration 26000.
+WARNING - image.py - 2024-10-23 10:21:18,373 - 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 10:21:43,111 - FID at iteration 26000: 20.773476
+INFO - dpsgd_diffusion.py - 2024-10-23 10:24:12,864 - Loss: 0.1447, step: 26100
+INFO - dpsgd_diffusion.py - 2024-10-23 10:26:53,474 - Loss: 0.1432, step: 26200
+INFO - dpsgd_diffusion.py - 2024-10-23 10:29:29,657 - Loss: 0.1316, step: 26300
+INFO - dpsgd_diffusion.py - 2024-10-23 10:31:46,609 - Loss: 0.1398, step: 26400
+INFO - dpsgd_diffusion.py - 2024-10-23 10:32:32,773 - Eps-value after 59 epochs: 5.9088
+INFO - dpsgd_diffusion.py - 2024-10-23 10:34:06,987 - Loss: 0.1546, step: 26500
+INFO - dpsgd_diffusion.py - 2024-10-23 10:36:20,925 - Loss: 0.1392, step: 26600
+INFO - dpsgd_diffusion.py - 2024-10-23 10:38:01,288 - Loss: 0.1458, step: 26700
+INFO - dpsgd_diffusion.py - 2024-10-23 10:39:01,941 - Loss: 0.1443, step: 26800
+INFO - dpsgd_diffusion.py - 2024-10-23 10:39:50,581 - Eps-value after 60 epochs: 5.9632
+INFO - dpsgd_diffusion.py - 2024-10-23 10:40:02,743 - Loss: 0.1307, step: 26900
+INFO - dpsgd_diffusion.py - 2024-10-23 10:41:03,224 - Loss: 0.1338, step: 27000
+INFO - dpsgd_diffusion.py - 2024-10-23 10:42:05,074 - Loss: 0.1304, step: 27100
+INFO - dpsgd_diffusion.py - 2024-10-23 10:43:05,631 - Loss: 0.1325, step: 27200
+INFO - dpsgd_diffusion.py - 2024-10-23 10:44:07,134 - Loss: 0.1425, step: 27300
+INFO - dpsgd_diffusion.py - 2024-10-23 10:44:24,248 - Eps-value after 61 epochs: 6.0175
+INFO - dpsgd_diffusion.py - 2024-10-23 10:45:08,152 - Loss: 0.1356, step: 27400
+INFO - dpsgd_diffusion.py - 2024-10-23 10:46:09,078 - Loss: 0.1310, step: 27500
+INFO - dpsgd_diffusion.py - 2024-10-23 10:47:10,567 - Loss: 0.1332, step: 27600
+INFO - dpsgd_diffusion.py - 2024-10-23 10:48:11,945 - Loss: 0.1377, step: 27700
+INFO - dpsgd_diffusion.py - 2024-10-23 10:48:58,296 - Eps-value after 62 epochs: 6.0719
+INFO - dpsgd_diffusion.py - 2024-10-23 10:49:12,610 - Loss: 0.1228, step: 27800
+INFO - dpsgd_diffusion.py - 2024-10-23 10:50:12,531 - Loss: 0.1338, step: 27900
+INFO - dpsgd_diffusion.py - 2024-10-23 10:51:12,012 - Loss: 0.1296, step: 28000
+INFO - dpsgd_diffusion.py - 2024-10-23 10:51:12,032 - Saving snapshot checkpoint and sampling single batch at iteration 28000.
+WARNING - image.py - 2024-10-23 10:51:12,548 - 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 10:51:26,172 - FID at iteration 28000: 20.412090
+INFO - dpsgd_diffusion.py - 2024-10-23 10:52:31,048 - Loss: 0.1311, step: 28100
+INFO - dpsgd_diffusion.py - 2024-10-23 10:53:31,945 - Loss: 0.1399, step: 28200
+INFO - dpsgd_diffusion.py - 2024-10-23 10:53:46,645 - Eps-value after 63 epochs: 6.1252
+INFO - dpsgd_diffusion.py - 2024-10-23 10:54:34,417 - Loss: 0.1460, step: 28300
+INFO - dpsgd_diffusion.py - 2024-10-23 10:55:34,081 - Loss: 0.1400, step: 28400
+INFO - dpsgd_diffusion.py - 2024-10-23 10:56:34,586 - Loss: 0.1304, step: 28500
+INFO - dpsgd_diffusion.py - 2024-10-23 10:57:37,534 - Loss: 0.1464, step: 28600
+INFO - dpsgd_diffusion.py - 2024-10-23 10:58:21,616 - Eps-value after 64 epochs: 6.1784
+INFO - dpsgd_diffusion.py - 2024-10-23 10:58:38,501 - Loss: 0.1397, step: 28700
+INFO - dpsgd_diffusion.py - 2024-10-23 10:59:38,322 - Loss: 0.1298, step: 28800
+INFO - dpsgd_diffusion.py - 2024-10-23 11:00:39,057 - Loss: 0.1407, step: 28900
+INFO - dpsgd_diffusion.py - 2024-10-23 11:01:41,042 - Loss: 0.1283, step: 29000
+INFO - dpsgd_diffusion.py - 2024-10-23 11:02:41,850 - Loss: 0.1237, step: 29100
+INFO - dpsgd_diffusion.py - 2024-10-23 11:02:54,487 - Eps-value after 65 epochs: 6.2316
+INFO - dpsgd_diffusion.py - 2024-10-23 11:03:43,610 - Loss: 0.1448, step: 29200
+INFO - dpsgd_diffusion.py - 2024-10-23 11:04:44,067 - Loss: 0.1352, step: 29300
+INFO - dpsgd_diffusion.py - 2024-10-23 11:05:44,788 - Loss: 0.1467, step: 29400
+INFO - dpsgd_diffusion.py - 2024-10-23 11:06:44,426 - Loss: 0.1237, step: 29500
+INFO - dpsgd_diffusion.py - 2024-10-23 11:07:25,456 - Eps-value after 66 epochs: 6.2845
+INFO - dpsgd_diffusion.py - 2024-10-23 11:07:44,698 - Loss: 0.1244, step: 29600
+INFO - dpsgd_diffusion.py - 2024-10-23 11:08:46,738 - Loss: 0.1263, step: 29700
+INFO - dpsgd_diffusion.py - 2024-10-23 11:09:46,604 - Loss: 0.1472, step: 29800
+INFO - dpsgd_diffusion.py - 2024-10-23 11:10:47,813 - Loss: 0.1409, step: 29900
+INFO - dpsgd_diffusion.py - 2024-10-23 11:11:47,484 - Loss: 0.1398, step: 30000
+INFO - dpsgd_diffusion.py - 2024-10-23 11:11:47,497 - Saving snapshot checkpoint and sampling single batch at iteration 30000.
+WARNING - image.py - 2024-10-23 11:11:48,018 - 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 11:12:00,936 - FID at iteration 30000: 18.338658
+INFO - dpsgd_diffusion.py - 2024-10-23 11:12:10,508 - Eps-value after 67 epochs: 6.3365
+INFO - dpsgd_diffusion.py - 2024-10-23 11:13:03,602 - Loss: 0.1386, step: 30100
+INFO - dpsgd_diffusion.py - 2024-10-23 11:14:06,920 - Loss: 0.1479, step: 30200
+INFO - dpsgd_diffusion.py - 2024-10-23 11:15:08,351 - Loss: 0.1337, step: 30300
+INFO - dpsgd_diffusion.py - 2024-10-23 11:16:08,751 - Loss: 0.1333, step: 30400
+INFO - dpsgd_diffusion.py - 2024-10-23 11:16:47,514 - Eps-value after 68 epochs: 6.3884
+INFO - dpsgd_diffusion.py - 2024-10-23 11:17:09,363 - Loss: 0.1407, step: 30500
+INFO - dpsgd_diffusion.py - 2024-10-23 11:18:10,659 - Loss: 0.1456, step: 30600
+INFO - dpsgd_diffusion.py - 2024-10-23 11:19:11,976 - Loss: 0.1471, step: 30700
+INFO - dpsgd_diffusion.py - 2024-10-23 11:20:13,359 - Loss: 0.1370, step: 30800
+INFO - dpsgd_diffusion.py - 2024-10-23 11:21:14,972 - Loss: 0.1361, step: 30900
+INFO - dpsgd_diffusion.py - 2024-10-23 11:21:22,333 - Eps-value after 69 epochs: 6.4404
+INFO - dpsgd_diffusion.py - 2024-10-23 11:22:15,333 - Loss: 0.1432, step: 31000
+INFO - dpsgd_diffusion.py - 2024-10-23 11:23:16,662 - Loss: 0.1400, step: 31100
+INFO - dpsgd_diffusion.py - 2024-10-23 11:24:17,358 - Loss: 0.1403, step: 31200
+INFO - dpsgd_diffusion.py - 2024-10-23 11:25:17,967 - Loss: 0.1225, step: 31300
+INFO - dpsgd_diffusion.py - 2024-10-23 11:25:54,697 - Eps-value after 70 epochs: 6.4921
+INFO - dpsgd_diffusion.py - 2024-10-23 11:26:19,299 - Loss: 0.1340, step: 31400
+INFO - dpsgd_diffusion.py - 2024-10-23 11:27:22,360 - Loss: 0.1412, step: 31500
+INFO - dpsgd_diffusion.py - 2024-10-23 11:28:26,341 - Loss: 0.1324, step: 31600
+INFO - dpsgd_diffusion.py - 2024-10-23 11:29:28,895 - Loss: 0.1356, step: 31700
+INFO - dpsgd_diffusion.py - 2024-10-23 11:30:39,718 - Loss: 0.1481, step: 31800
+INFO - dpsgd_diffusion.py - 2024-10-23 11:30:48,087 - Eps-value after 71 epochs: 6.5429
+INFO - dpsgd_diffusion.py - 2024-10-23 11:32:49,465 - Loss: 0.1417, step: 31900
+INFO - dpsgd_diffusion.py - 2024-10-23 11:35:03,937 - Loss: 0.1286, step: 32000
+INFO - dpsgd_diffusion.py - 2024-10-23 11:35:03,956 - Saving snapshot checkpoint and sampling single batch at iteration 32000.
+WARNING - image.py - 2024-10-23 11:35:04,831 - 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 11:35:24,821 - FID at iteration 32000: 17.270695
+INFO - dpsgd_diffusion.py - 2024-10-23 11:37:47,263 - Loss: 0.1395, step: 32100
+INFO - dpsgd_diffusion.py - 2024-10-23 11:40:01,696 - Loss: 0.1383, step: 32200
+INFO - dpsgd_diffusion.py - 2024-10-23 11:41:23,063 - Eps-value after 72 epochs: 6.5937
+INFO - dpsgd_diffusion.py - 2024-10-23 11:42:29,032 - Loss: 0.1366, step: 32300
+INFO - dpsgd_diffusion.py - 2024-10-23 11:44:42,418 - Loss: 0.1316, step: 32400
+INFO - dpsgd_diffusion.py - 2024-10-23 11:47:00,515 - Loss: 0.1290, step: 32500
+INFO - dpsgd_diffusion.py - 2024-10-23 11:49:17,992 - Loss: 0.1449, step: 32600
+INFO - dpsgd_diffusion.py - 2024-10-23 11:51:30,637 - Loss: 0.1462, step: 32700
+INFO - dpsgd_diffusion.py - 2024-10-23 11:51:35,722 - Eps-value after 73 epochs: 6.6444
+INFO - dpsgd_diffusion.py - 2024-10-23 11:53:45,975 - Loss: 0.1461, step: 32800
+INFO - dpsgd_diffusion.py - 2024-10-23 11:55:18,302 - Loss: 0.1402, step: 32900
+INFO - dpsgd_diffusion.py - 2024-10-23 11:56:19,093 - Loss: 0.1423, step: 33000
+INFO - dpsgd_diffusion.py - 2024-10-23 11:57:19,075 - Loss: 0.1341, step: 33100
+INFO - dpsgd_diffusion.py - 2024-10-23 11:57:51,432 - Eps-value after 74 epochs: 6.6952
+INFO - dpsgd_diffusion.py - 2024-10-23 11:58:20,592 - Loss: 0.1310, step: 33200
+INFO - dpsgd_diffusion.py - 2024-10-23 11:59:21,470 - Loss: 0.1377, step: 33300
+INFO - dpsgd_diffusion.py - 2024-10-23 12:00:21,817 - Loss: 0.1420, step: 33400
+INFO - dpsgd_diffusion.py - 2024-10-23 12:01:22,781 - Loss: 0.1310, step: 33500
+INFO - dpsgd_diffusion.py - 2024-10-23 12:02:23,674 - Loss: 0.1302, step: 33600
+INFO - dpsgd_diffusion.py - 2024-10-23 12:02:23,698 - Eps-value after 75 epochs: 6.7450
+INFO - dpsgd_diffusion.py - 2024-10-23 12:03:24,331 - Loss: 0.1458, step: 33700
+INFO - dpsgd_diffusion.py - 2024-10-23 12:04:25,143 - Loss: 0.1255, step: 33800
+INFO - dpsgd_diffusion.py - 2024-10-23 12:05:25,968 - Loss: 0.1338, step: 33900
+INFO - dpsgd_diffusion.py - 2024-10-23 12:06:25,708 - Loss: 0.1325, step: 34000
+INFO - dpsgd_diffusion.py - 2024-10-23 12:06:25,723 - Saving snapshot checkpoint and sampling single batch at iteration 34000.
+WARNING - image.py - 2024-10-23 12:06:26,262 - 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 12:06:38,871 - FID at iteration 34000: 17.572965
+INFO - dpsgd_diffusion.py - 2024-10-23 12:07:09,183 - Eps-value after 76 epochs: 6.7946
+INFO - dpsgd_diffusion.py - 2024-10-23 12:07:41,705 - Loss: 0.1288, step: 34100
+INFO - dpsgd_diffusion.py - 2024-10-23 12:08:43,556 - Loss: 0.1308, step: 34200
+INFO - dpsgd_diffusion.py - 2024-10-23 12:09:43,067 - Loss: 0.1374, step: 34300
+INFO - dpsgd_diffusion.py - 2024-10-23 12:10:43,695 - Loss: 0.1247, step: 34400
+INFO - dpsgd_diffusion.py - 2024-10-23 12:11:43,326 - Eps-value after 77 epochs: 6.8441
+INFO - dpsgd_diffusion.py - 2024-10-23 12:11:45,738 - Loss: 0.1327, step: 34500
+INFO - dpsgd_diffusion.py - 2024-10-23 12:12:46,286 - Loss: 0.1474, step: 34600
+INFO - dpsgd_diffusion.py - 2024-10-23 12:13:46,639 - Loss: 0.1311, step: 34700
+INFO - dpsgd_diffusion.py - 2024-10-23 12:14:48,082 - Loss: 0.1296, step: 34800
+INFO - dpsgd_diffusion.py - 2024-10-23 12:15:50,027 - Loss: 0.1398, step: 34900
+INFO - dpsgd_diffusion.py - 2024-10-23 12:16:17,406 - Eps-value after 78 epochs: 6.8937
+INFO - dpsgd_diffusion.py - 2024-10-23 12:16:50,921 - Loss: 0.1352, step: 35000
+INFO - dpsgd_diffusion.py - 2024-10-23 12:17:51,104 - Loss: 0.1362, step: 35100
+INFO - dpsgd_diffusion.py - 2024-10-23 12:18:51,223 - Loss: 0.1411, step: 35200
+INFO - dpsgd_diffusion.py - 2024-10-23 12:19:51,095 - Loss: 0.1374, step: 35300
+INFO - dpsgd_diffusion.py - 2024-10-23 12:20:46,868 - Eps-value after 79 epochs: 6.9432
+INFO - dpsgd_diffusion.py - 2024-10-23 12:20:51,670 - Loss: 0.1365, step: 35400
+INFO - dpsgd_diffusion.py - 2024-10-23 12:21:52,540 - Loss: 0.1237, step: 35500
+INFO - dpsgd_diffusion.py - 2024-10-23 12:22:52,889 - Loss: 0.1314, step: 35600
+INFO - dpsgd_diffusion.py - 2024-10-23 12:23:52,525 - Loss: 0.1396, step: 35700
+INFO - dpsgd_diffusion.py - 2024-10-23 12:24:53,043 - Loss: 0.1451, step: 35800
+INFO - dpsgd_diffusion.py - 2024-10-23 12:25:17,747 - Eps-value after 80 epochs: 6.9916
+INFO - dpsgd_diffusion.py - 2024-10-23 12:25:53,661 - Loss: 0.1362, step: 35900
+INFO - dpsgd_diffusion.py - 2024-10-23 12:26:53,992 - Loss: 0.1299, step: 36000
+INFO - dpsgd_diffusion.py - 2024-10-23 12:26:54,010 - Saving snapshot checkpoint and sampling single batch at iteration 36000.
+WARNING - image.py - 2024-10-23 12:26:54,586 - 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 12:27:07,660 - FID at iteration 36000: 16.619073
+INFO - dpsgd_diffusion.py - 2024-10-23 12:28:10,964 - Loss: 0.1290, step: 36100
+INFO - dpsgd_diffusion.py - 2024-10-23 12:29:13,631 - Loss: 0.1333, step: 36200
+INFO - dpsgd_diffusion.py - 2024-10-23 12:30:06,792 - Eps-value after 81 epochs: 7.0400
+INFO - dpsgd_diffusion.py - 2024-10-23 12:30:14,045 - Loss: 0.1383, step: 36300
+INFO - dpsgd_diffusion.py - 2024-10-23 12:31:16,290 - Loss: 0.1362, step: 36400
+INFO - dpsgd_diffusion.py - 2024-10-23 12:32:17,688 - Loss: 0.1460, step: 36500
+INFO - dpsgd_diffusion.py - 2024-10-23 12:33:18,270 - Loss: 0.1298, step: 36600
+INFO - dpsgd_diffusion.py - 2024-10-23 12:34:19,480 - Loss: 0.1298, step: 36700
+INFO - dpsgd_diffusion.py - 2024-10-23 12:34:41,141 - Eps-value after 82 epochs: 7.0884
+INFO - dpsgd_diffusion.py - 2024-10-23 12:35:19,839 - Loss: 0.1338, step: 36800
+INFO - dpsgd_diffusion.py - 2024-10-23 12:36:22,747 - Loss: 0.1323, step: 36900
+INFO - dpsgd_diffusion.py - 2024-10-23 12:37:23,160 - Loss: 0.1382, step: 37000
+INFO - dpsgd_diffusion.py - 2024-10-23 12:38:23,687 - Loss: 0.1460, step: 37100
+INFO - dpsgd_diffusion.py - 2024-10-23 12:39:14,326 - Eps-value after 83 epochs: 7.1367
+INFO - dpsgd_diffusion.py - 2024-10-23 12:39:24,158 - Loss: 0.1366, step: 37200
+INFO - dpsgd_diffusion.py - 2024-10-23 12:40:26,181 - Loss: 0.1286, step: 37300
+INFO - dpsgd_diffusion.py - 2024-10-23 12:41:27,686 - Loss: 0.1400, step: 37400
+INFO - dpsgd_diffusion.py - 2024-10-23 12:42:27,269 - Loss: 0.1391, step: 37500
+INFO - dpsgd_diffusion.py - 2024-10-23 12:43:28,287 - Loss: 0.1301, step: 37600
+INFO - dpsgd_diffusion.py - 2024-10-23 12:43:47,445 - Eps-value after 84 epochs: 7.1851
+INFO - dpsgd_diffusion.py - 2024-10-23 12:44:28,316 - Loss: 0.1494, step: 37700
+INFO - dpsgd_diffusion.py - 2024-10-23 12:45:28,623 - Loss: 0.1254, step: 37800
+INFO - dpsgd_diffusion.py - 2024-10-23 12:46:28,251 - Loss: 0.1493, step: 37900
+INFO - dpsgd_diffusion.py - 2024-10-23 12:47:29,616 - Loss: 0.1279, step: 38000
+INFO - dpsgd_diffusion.py - 2024-10-23 12:47:29,648 - Saving snapshot checkpoint and sampling single batch at iteration 38000.
+WARNING - image.py - 2024-10-23 12:47:30,424 - 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 12:47:45,636 - FID at iteration 38000: 15.776199
+INFO - dpsgd_diffusion.py - 2024-10-23 12:48:35,480 - Eps-value after 85 epochs: 7.2325
+INFO - dpsgd_diffusion.py - 2024-10-23 12:48:47,600 - Loss: 0.1475, step: 38100
+INFO - dpsgd_diffusion.py - 2024-10-23 12:49:50,379 - Loss: 0.1492, step: 38200
+INFO - dpsgd_diffusion.py - 2024-10-23 12:50:51,821 - Loss: 0.1281, step: 38300
+INFO - dpsgd_diffusion.py - 2024-10-23 12:51:52,356 - Loss: 0.1287, step: 38400
+INFO - dpsgd_diffusion.py - 2024-10-23 12:52:54,353 - Loss: 0.1234, step: 38500
+INFO - dpsgd_diffusion.py - 2024-10-23 12:53:11,498 - Eps-value after 86 epochs: 7.2797
+INFO - dpsgd_diffusion.py - 2024-10-23 12:53:54,999 - Loss: 0.1384, step: 38600
+INFO - dpsgd_diffusion.py - 2024-10-23 12:54:56,173 - Loss: 0.1320, step: 38700
+INFO - dpsgd_diffusion.py - 2024-10-23 12:55:56,302 - Loss: 0.1408, step: 38800
+INFO - dpsgd_diffusion.py - 2024-10-23 12:56:56,096 - Loss: 0.1279, step: 38900
+INFO - dpsgd_diffusion.py - 2024-10-23 12:57:42,690 - Eps-value after 87 epochs: 7.3269
+INFO - dpsgd_diffusion.py - 2024-10-23 12:57:57,219 - Loss: 0.1385, step: 39000
+INFO - dpsgd_diffusion.py - 2024-10-23 12:58:58,719 - Loss: 0.1301, step: 39100
+INFO - dpsgd_diffusion.py - 2024-10-23 12:59:57,987 - Loss: 0.1343, step: 39200
+INFO - dpsgd_diffusion.py - 2024-10-23 13:00:59,329 - Loss: 0.1157, step: 39300
+INFO - dpsgd_diffusion.py - 2024-10-23 13:01:59,921 - Loss: 0.1404, step: 39400
+INFO - dpsgd_diffusion.py - 2024-10-23 13:02:14,384 - Eps-value after 88 epochs: 7.3741
+INFO - dpsgd_diffusion.py - 2024-10-23 13:03:00,951 - Loss: 0.1366, step: 39500
+INFO - dpsgd_diffusion.py - 2024-10-23 13:04:00,469 - Loss: 0.1410, step: 39600
+INFO - dpsgd_diffusion.py - 2024-10-23 13:05:00,481 - Loss: 0.1428, step: 39700
+INFO - dpsgd_diffusion.py - 2024-10-23 13:06:00,695 - Loss: 0.1372, step: 39800
+INFO - dpsgd_diffusion.py - 2024-10-23 13:06:43,593 - Eps-value after 89 epochs: 7.4213
+INFO - dpsgd_diffusion.py - 2024-10-23 13:07:00,213 - Loss: 0.1340, step: 39900
+INFO - dpsgd_diffusion.py - 2024-10-23 13:08:01,636 - Loss: 0.1355, step: 40000
+INFO - dpsgd_diffusion.py - 2024-10-23 13:08:01,656 - Saving snapshot checkpoint and sampling single batch at iteration 40000.
+WARNING - image.py - 2024-10-23 13:08:02,170 - 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 13:08:14,874 - FID at iteration 40000: 15.797221
+INFO - dpsgd_diffusion.py - 2024-10-23 13:09:18,437 - Loss: 0.1345, step: 40100
+INFO - dpsgd_diffusion.py - 2024-10-23 13:10:19,780 - Loss: 0.1354, step: 40200
+INFO - dpsgd_diffusion.py - 2024-10-23 13:11:20,251 - Loss: 0.1334, step: 40300
+INFO - dpsgd_diffusion.py - 2024-10-23 13:11:32,316 - Eps-value after 90 epochs: 7.4683
+INFO - dpsgd_diffusion.py - 2024-10-23 13:12:21,125 - Loss: 0.1221, step: 40400
+INFO - dpsgd_diffusion.py - 2024-10-23 13:13:21,710 - Loss: 0.1199, step: 40500
+INFO - dpsgd_diffusion.py - 2024-10-23 13:14:21,800 - Loss: 0.1365, step: 40600
+INFO - dpsgd_diffusion.py - 2024-10-23 13:15:22,513 - Loss: 0.1219, step: 40700
+INFO - dpsgd_diffusion.py - 2024-10-23 13:16:03,817 - Eps-value after 91 epochs: 7.5143
+INFO - dpsgd_diffusion.py - 2024-10-23 13:16:23,289 - Loss: 0.1317, step: 40800
+INFO - dpsgd_diffusion.py - 2024-10-23 13:17:22,854 - Loss: 0.1241, step: 40900
+INFO - dpsgd_diffusion.py - 2024-10-23 13:18:24,107 - Loss: 0.1353, step: 41000
+INFO - dpsgd_diffusion.py - 2024-10-23 13:19:24,290 - Loss: 0.1410, step: 41100
+INFO - dpsgd_diffusion.py - 2024-10-23 13:20:25,258 - Loss: 0.1347, step: 41200
+INFO - dpsgd_diffusion.py - 2024-10-23 13:20:34,818 - Eps-value after 92 epochs: 7.5603
+INFO - dpsgd_diffusion.py - 2024-10-23 13:21:25,431 - Loss: 0.1318, step: 41300
+INFO - dpsgd_diffusion.py - 2024-10-23 13:22:27,178 - Loss: 0.1313, step: 41400
+INFO - dpsgd_diffusion.py - 2024-10-23 13:23:27,792 - Loss: 0.1216, step: 41500
+INFO - dpsgd_diffusion.py - 2024-10-23 13:24:28,321 - Loss: 0.1397, step: 41600
+INFO - dpsgd_diffusion.py - 2024-10-23 13:25:07,100 - Eps-value after 93 epochs: 7.6064
+INFO - dpsgd_diffusion.py - 2024-10-23 13:25:29,095 - Loss: 0.1327, step: 41700
+INFO - dpsgd_diffusion.py - 2024-10-23 13:26:29,458 - Loss: 0.1314, step: 41800
+INFO - dpsgd_diffusion.py - 2024-10-23 13:27:29,295 - Loss: 0.1342, step: 41900
+INFO - dpsgd_diffusion.py - 2024-10-23 13:28:30,296 - Loss: 0.1471, step: 42000
+INFO - dpsgd_diffusion.py - 2024-10-23 13:28:30,311 - Saving snapshot checkpoint and sampling single batch at iteration 42000.
+WARNING - image.py - 2024-10-23 13:28:30,824 - 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 13:28:43,423 - FID at iteration 42000: 15.459157
+INFO - dpsgd_diffusion.py - 2024-10-23 13:29:45,118 - Loss: 0.1346, step: 42100
+INFO - dpsgd_diffusion.py - 2024-10-23 13:29:52,318 - Eps-value after 94 epochs: 7.6524
+INFO - dpsgd_diffusion.py - 2024-10-23 13:30:47,422 - Loss: 0.1293, step: 42200
+INFO - dpsgd_diffusion.py - 2024-10-23 13:31:48,253 - Loss: 0.1358, step: 42300
+INFO - dpsgd_diffusion.py - 2024-10-23 13:32:48,778 - Loss: 0.1353, step: 42400
+INFO - dpsgd_diffusion.py - 2024-10-23 13:33:49,215 - Loss: 0.1387, step: 42500
+INFO - dpsgd_diffusion.py - 2024-10-23 13:34:25,165 - Eps-value after 95 epochs: 7.6985
+INFO - dpsgd_diffusion.py - 2024-10-23 13:34:48,837 - Loss: 0.1214, step: 42600
+INFO - dpsgd_diffusion.py - 2024-10-23 13:35:49,145 - Loss: 0.1238, step: 42700
+INFO - dpsgd_diffusion.py - 2024-10-23 13:36:50,076 - Loss: 0.1390, step: 42800
+INFO - dpsgd_diffusion.py - 2024-10-23 13:37:50,697 - Loss: 0.1399, step: 42900
+INFO - dpsgd_diffusion.py - 2024-10-23 13:38:51,511 - Loss: 0.1335, step: 43000
+INFO - dpsgd_diffusion.py - 2024-10-23 13:38:56,275 - Eps-value after 96 epochs: 7.7445
+INFO - dpsgd_diffusion.py - 2024-10-23 13:39:52,790 - Loss: 0.1330, step: 43100
+INFO - dpsgd_diffusion.py - 2024-10-23 13:40:54,243 - Loss: 0.1278, step: 43200
+INFO - dpsgd_diffusion.py - 2024-10-23 13:41:54,142 - Loss: 0.1329, step: 43300
+INFO - dpsgd_diffusion.py - 2024-10-23 13:42:54,397 - Loss: 0.1343, step: 43400
+INFO - dpsgd_diffusion.py - 2024-10-23 13:43:27,832 - Eps-value after 97 epochs: 7.7894
+INFO - dpsgd_diffusion.py - 2024-10-23 13:43:54,337 - Loss: 0.1383, step: 43500
+INFO - dpsgd_diffusion.py - 2024-10-23 13:44:54,428 - Loss: 0.1280, step: 43600
+INFO - dpsgd_diffusion.py - 2024-10-23 13:45:54,884 - Loss: 0.1297, step: 43700
+INFO - dpsgd_diffusion.py - 2024-10-23 13:46:54,986 - Loss: 0.1326, step: 43800
+INFO - dpsgd_diffusion.py - 2024-10-23 13:47:55,244 - Loss: 0.1345, step: 43900
+INFO - dpsgd_diffusion.py - 2024-10-23 13:47:57,634 - Eps-value after 98 epochs: 7.8342
+INFO - dpsgd_diffusion.py - 2024-10-23 13:48:56,160 - Loss: 0.1262, step: 44000
+INFO - dpsgd_diffusion.py - 2024-10-23 13:48:56,180 - Saving snapshot checkpoint and sampling single batch at iteration 44000.
+WARNING - image.py - 2024-10-23 13:48:56,688 - 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 13:49:10,079 - FID at iteration 44000: 14.968299
+INFO - dpsgd_diffusion.py - 2024-10-23 13:50:11,718 - Loss: 0.1377, step: 44100
+INFO - dpsgd_diffusion.py - 2024-10-23 13:51:11,701 - Loss: 0.1296, step: 44200
+INFO - dpsgd_diffusion.py - 2024-10-23 13:52:12,234 - Loss: 0.1329, step: 44300
+INFO - dpsgd_diffusion.py - 2024-10-23 13:52:43,541 - Eps-value after 99 epochs: 7.8791
+INFO - dpsgd_diffusion.py - 2024-10-23 13:53:13,460 - Loss: 0.1343, step: 44400
+INFO - dpsgd_diffusion.py - 2024-10-23 13:54:16,281 - Loss: 0.1341, step: 44500
+INFO - dpsgd_diffusion.py - 2024-10-23 13:55:17,617 - Loss: 0.1345, step: 44600
+INFO - dpsgd_diffusion.py - 2024-10-23 13:56:17,600 - Loss: 0.1295, step: 44700
+INFO - dpsgd_diffusion.py - 2024-10-23 13:57:19,265 - Loss: 0.1295, step: 44800
+INFO - dpsgd_diffusion.py - 2024-10-23 13:57:19,287 - Eps-value after 100 epochs: 7.9240
+INFO - dpsgd_diffusion.py - 2024-10-23 13:58:19,441 - Loss: 0.1361, step: 44900
+INFO - dpsgd_diffusion.py - 2024-10-23 13:59:27,100 - Loss: 0.1274, step: 45000
+INFO - dpsgd_diffusion.py - 2024-10-23 14:00:27,141 - Loss: 0.1236, step: 45100
+INFO - dpsgd_diffusion.py - 2024-10-23 14:01:28,879 - Loss: 0.1377, step: 45200
+INFO - dpsgd_diffusion.py - 2024-10-23 14:01:58,117 - Eps-value after 101 epochs: 7.9688
+INFO - dpsgd_diffusion.py - 2024-10-23 14:02:29,539 - Loss: 0.1315, step: 45300
+INFO - dpsgd_diffusion.py - 2024-10-23 14:03:29,331 - Loss: 0.1338, step: 45400
+INFO - dpsgd_diffusion.py - 2024-10-23 14:04:31,161 - Loss: 0.1303, step: 45500
+INFO - dpsgd_diffusion.py - 2024-10-23 14:05:30,735 - Loss: 0.1265, step: 45600
+INFO - dpsgd_diffusion.py - 2024-10-23 14:06:30,252 - Eps-value after 102 epochs: 8.0137
+INFO - dpsgd_diffusion.py - 2024-10-23 14:06:32,750 - Loss: 0.1216, step: 45700
+INFO - dpsgd_diffusion.py - 2024-10-23 14:07:32,585 - Loss: 0.1349, step: 45800
+INFO - dpsgd_diffusion.py - 2024-10-23 14:08:33,551 - Loss: 0.1368, step: 45900
+INFO - dpsgd_diffusion.py - 2024-10-23 14:09:34,301 - Loss: 0.1273, step: 46000
+INFO - dpsgd_diffusion.py - 2024-10-23 14:09:34,314 - Saving snapshot checkpoint and sampling single batch at iteration 46000.
+WARNING - image.py - 2024-10-23 14:09:34,888 - 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 14:09:48,034 - FID at iteration 46000: 14.186605
+INFO - dpsgd_diffusion.py - 2024-10-23 14:10:49,909 - Loss: 0.1313, step: 46100
+INFO - dpsgd_diffusion.py - 2024-10-23 14:11:16,445 - Eps-value after 103 epochs: 8.0585
+INFO - dpsgd_diffusion.py - 2024-10-23 14:11:49,928 - Loss: 0.1342, step: 46200
+INFO - dpsgd_diffusion.py - 2024-10-23 14:12:50,218 - Loss: 0.1238, step: 46300
+INFO - dpsgd_diffusion.py - 2024-10-23 14:13:54,387 - Loss: 0.1288, step: 46400
+INFO - dpsgd_diffusion.py - 2024-10-23 14:14:58,098 - Loss: 0.1412, step: 46500
+INFO - dpsgd_diffusion.py - 2024-10-23 14:15:52,964 - Eps-value after 104 epochs: 8.1022
+INFO - dpsgd_diffusion.py - 2024-10-23 14:15:57,864 - Loss: 0.1433, step: 46600
+INFO - dpsgd_diffusion.py - 2024-10-23 14:16:59,408 - Loss: 0.1196, step: 46700
+INFO - dpsgd_diffusion.py - 2024-10-23 14:17:59,733 - Loss: 0.1352, step: 46800
+INFO - dpsgd_diffusion.py - 2024-10-23 14:19:00,086 - Loss: 0.1342, step: 46900
+INFO - dpsgd_diffusion.py - 2024-10-23 14:19:59,595 - Loss: 0.1376, step: 47000
+INFO - dpsgd_diffusion.py - 2024-10-23 14:20:23,901 - Eps-value after 105 epochs: 8.1459
+INFO - dpsgd_diffusion.py - 2024-10-23 14:20:59,161 - Loss: 0.1288, step: 47100
+INFO - dpsgd_diffusion.py - 2024-10-23 14:22:00,215 - Loss: 0.1307, step: 47200
+INFO - dpsgd_diffusion.py - 2024-10-23 14:23:00,168 - Loss: 0.1455, step: 47300
+INFO - dpsgd_diffusion.py - 2024-10-23 14:24:00,583 - Loss: 0.1369, step: 47400
+INFO - dpsgd_diffusion.py - 2024-10-23 14:24:54,209 - Eps-value after 106 epochs: 8.1896
+INFO - dpsgd_diffusion.py - 2024-10-23 14:25:01,592 - Loss: 0.1327, step: 47500
+INFO - dpsgd_diffusion.py - 2024-10-23 14:26:02,411 - Loss: 0.1219, step: 47600
+INFO - dpsgd_diffusion.py - 2024-10-23 14:27:02,801 - Loss: 0.1403, step: 47700
+INFO - dpsgd_diffusion.py - 2024-10-23 14:28:03,659 - Loss: 0.1348, step: 47800
+INFO - dpsgd_diffusion.py - 2024-10-23 14:29:04,188 - Loss: 0.1296, step: 47900
+INFO - dpsgd_diffusion.py - 2024-10-23 14:29:25,987 - Eps-value after 107 epochs: 8.2333
+INFO - dpsgd_diffusion.py - 2024-10-23 14:30:03,542 - Loss: 0.1323, step: 48000
+INFO - dpsgd_diffusion.py - 2024-10-23 14:30:03,562 - Saving snapshot checkpoint and sampling single batch at iteration 48000.
+WARNING - image.py - 2024-10-23 14:30:04,097 - 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 14:30:17,180 - FID at iteration 48000: 14.063010
+INFO - dpsgd_diffusion.py - 2024-10-23 14:31:19,826 - Loss: 0.1294, step: 48100
+INFO - dpsgd_diffusion.py - 2024-10-23 14:32:20,110 - Loss: 0.1338, step: 48200
+INFO - dpsgd_diffusion.py - 2024-10-23 14:33:20,687 - Loss: 0.1370, step: 48300
+INFO - dpsgd_diffusion.py - 2024-10-23 14:34:10,879 - Eps-value after 108 epochs: 8.2770
+INFO - dpsgd_diffusion.py - 2024-10-23 14:34:21,580 - Loss: 0.1275, step: 48400
+INFO - dpsgd_diffusion.py - 2024-10-23 14:35:22,672 - Loss: 0.1242, step: 48500
+INFO - dpsgd_diffusion.py - 2024-10-23 14:36:23,001 - Loss: 0.1300, step: 48600
+INFO - dpsgd_diffusion.py - 2024-10-23 14:37:25,064 - Loss: 0.1338, step: 48700
+INFO - dpsgd_diffusion.py - 2024-10-23 14:38:25,355 - Loss: 0.1303, step: 48800
+INFO - dpsgd_diffusion.py - 2024-10-23 14:38:44,520 - Eps-value after 109 epochs: 8.3207
+INFO - dpsgd_diffusion.py - 2024-10-23 14:39:24,887 - Loss: 0.1215, step: 48900
+INFO - dpsgd_diffusion.py - 2024-10-23 14:40:26,270 - Loss: 0.1347, step: 49000
+INFO - dpsgd_diffusion.py - 2024-10-23 14:41:26,387 - Loss: 0.1312, step: 49100
+INFO - dpsgd_diffusion.py - 2024-10-23 14:42:27,546 - Loss: 0.1297, step: 49200
+INFO - dpsgd_diffusion.py - 2024-10-23 14:43:15,895 - Eps-value after 110 epochs: 8.3644
+INFO - dpsgd_diffusion.py - 2024-10-23 14:43:28,561 - Loss: 0.1273, step: 49300
+INFO - dpsgd_diffusion.py - 2024-10-23 14:44:30,617 - Loss: 0.1237, step: 49400
+INFO - dpsgd_diffusion.py - 2024-10-23 14:45:31,176 - Loss: 0.1310, step: 49500
+INFO - dpsgd_diffusion.py - 2024-10-23 14:46:31,828 - Loss: 0.1293, step: 49600
+INFO - dpsgd_diffusion.py - 2024-10-23 14:47:32,157 - Loss: 0.1292, step: 49700
+INFO - dpsgd_diffusion.py - 2024-10-23 14:47:49,041 - Eps-value after 111 epochs: 8.4075
+INFO - dpsgd_diffusion.py - 2024-10-23 14:48:32,931 - Loss: 0.1229, step: 49800
+INFO - dpsgd_diffusion.py - 2024-10-23 14:49:33,355 - Loss: 0.1339, step: 49900
+INFO - dpsgd_diffusion.py - 2024-10-23 14:50:34,385 - Loss: 0.1248, step: 50000
+INFO - dpsgd_diffusion.py - 2024-10-23 14:50:34,401 - Saving snapshot checkpoint and sampling single batch at iteration 50000.
+WARNING - image.py - 2024-10-23 14:50:34,917 - 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 14:50:47,376 - FID at iteration 50000: 13.408299
+INFO - dpsgd_diffusion.py - 2024-10-23 14:51:50,458 - Loss: 0.1249, step: 50100
+INFO - dpsgd_diffusion.py - 2024-10-23 14:52:37,122 - Eps-value after 112 epochs: 8.4500
+INFO - dpsgd_diffusion.py - 2024-10-23 14:52:52,175 - Loss: 0.1361, step: 50200
+INFO - dpsgd_diffusion.py - 2024-10-23 14:53:52,873 - Loss: 0.1272, step: 50300
+INFO - dpsgd_diffusion.py - 2024-10-23 14:55:09,543 - Loss: 0.1330, step: 50400
+INFO - dpsgd_diffusion.py - 2024-10-23 14:56:08,218 - Loss: 0.1312, step: 50500
+INFO - dpsgd_diffusion.py - 2024-10-23 14:57:06,573 - Loss: 0.1282, step: 50600
+INFO - dpsgd_diffusion.py - 2024-10-23 14:57:20,729 - Eps-value after 113 epochs: 8.4925
+INFO - dpsgd_diffusion.py - 2024-10-23 14:58:04,920 - Loss: 0.1404, step: 50700
+INFO - dpsgd_diffusion.py - 2024-10-23 14:59:03,130 - Loss: 0.1332, step: 50800
+INFO - dpsgd_diffusion.py - 2024-10-23 15:00:00,568 - Loss: 0.1290, step: 50900
+INFO - dpsgd_diffusion.py - 2024-10-23 15:00:59,094 - Loss: 0.1390, step: 51000
+INFO - dpsgd_diffusion.py - 2024-10-23 15:01:47,883 - Eps-value after 114 epochs: 8.5351
+INFO - dpsgd_diffusion.py - 2024-10-23 15:02:05,894 - Loss: 0.1271, step: 51100
+INFO - dpsgd_diffusion.py - 2024-10-23 15:03:03,923 - Loss: 0.1278, step: 51200
+INFO - dpsgd_diffusion.py - 2024-10-23 15:04:02,188 - Loss: 0.1373, step: 51300
+INFO - dpsgd_diffusion.py - 2024-10-23 15:05:00,638 - Loss: 0.1286, step: 51400
+INFO - dpsgd_diffusion.py - 2024-10-23 15:05:59,148 - Loss: 0.1324, step: 51500
+INFO - dpsgd_diffusion.py - 2024-10-23 15:06:10,999 - Eps-value after 115 epochs: 8.5776
+INFO - dpsgd_diffusion.py - 2024-10-23 15:06:58,278 - Loss: 0.1422, step: 51600
+INFO - dpsgd_diffusion.py - 2024-10-23 15:07:55,654 - Loss: 0.1219, step: 51700
+INFO - dpsgd_diffusion.py - 2024-10-23 15:08:53,253 - Loss: 0.1384, step: 51800
+INFO - dpsgd_diffusion.py - 2024-10-23 15:09:52,880 - Loss: 0.1314, step: 51900
+INFO - dpsgd_diffusion.py - 2024-10-23 15:10:32,450 - Eps-value after 116 epochs: 8.6202
+INFO - dpsgd_diffusion.py - 2024-10-23 15:10:51,002 - Loss: 0.1247, step: 52000
+INFO - dpsgd_diffusion.py - 2024-10-23 15:10:51,024 - Saving snapshot checkpoint and sampling single batch at iteration 52000.
+WARNING - image.py - 2024-10-23 15:10:51,569 - 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 15:11:05,562 - FID at iteration 52000: 13.468271
+INFO - dpsgd_diffusion.py - 2024-10-23 15:12:07,505 - Loss: 0.1363, step: 52100
+INFO - dpsgd_diffusion.py - 2024-10-23 15:13:21,567 - Loss: 0.1263, step: 52200
+INFO - dpsgd_diffusion.py - 2024-10-23 15:14:26,108 - Loss: 0.1331, step: 52300
+INFO - dpsgd_diffusion.py - 2024-10-23 15:15:24,280 - Loss: 0.1254, step: 52400
+INFO - dpsgd_diffusion.py - 2024-10-23 15:15:33,405 - Eps-value after 117 epochs: 8.6627
+INFO - dpsgd_diffusion.py - 2024-10-23 15:16:44,132 - Loss: 0.1311, step: 52500
+INFO - dpsgd_diffusion.py - 2024-10-23 15:17:43,660 - Loss: 0.1252, step: 52600
+INFO - dpsgd_diffusion.py - 2024-10-23 15:18:42,224 - Loss: 0.1229, step: 52700
+INFO - dpsgd_diffusion.py - 2024-10-23 15:19:40,039 - Loss: 0.1262, step: 52800
+INFO - dpsgd_diffusion.py - 2024-10-23 15:20:18,010 - Eps-value after 118 epochs: 8.7052
+INFO - dpsgd_diffusion.py - 2024-10-23 15:20:39,070 - Loss: 0.1247, step: 52900
+INFO - dpsgd_diffusion.py - 2024-10-23 15:21:37,796 - Loss: 0.1213, step: 53000
+INFO - dpsgd_diffusion.py - 2024-10-23 15:22:36,599 - Loss: 0.1342, step: 53100
+INFO - dpsgd_diffusion.py - 2024-10-23 15:23:35,231 - Loss: 0.1297, step: 53200
+INFO - dpsgd_diffusion.py - 2024-10-23 15:24:34,100 - Loss: 0.1343, step: 53300
+INFO - dpsgd_diffusion.py - 2024-10-23 15:24:41,234 - Eps-value after 119 epochs: 8.7477
+INFO - dpsgd_diffusion.py - 2024-10-23 15:25:35,648 - Loss: 0.1360, step: 53400
+INFO - dpsgd_diffusion.py - 2024-10-23 15:26:50,984 - Loss: 0.1144, step: 53500
+INFO - dpsgd_diffusion.py - 2024-10-23 15:28:04,406 - Loss: 0.1295, step: 53600
+INFO - dpsgd_diffusion.py - 2024-10-23 15:29:18,503 - Loss: 0.1234, step: 53700
+INFO - dpsgd_diffusion.py - 2024-10-23 15:30:08,204 - Eps-value after 120 epochs: 8.7890
+INFO - dpsgd_diffusion.py - 2024-10-23 15:30:42,503 - Loss: 0.1282, step: 53800
+INFO - dpsgd_diffusion.py - 2024-10-23 15:31:50,454 - Loss: 0.1361, step: 53900
+INFO - dpsgd_diffusion.py - 2024-10-23 15:33:17,625 - Loss: 0.1312, step: 54000
+INFO - dpsgd_diffusion.py - 2024-10-23 15:33:17,941 - Saving snapshot checkpoint and sampling single batch at iteration 54000.
+WARNING - image.py - 2024-10-23 15:33:18,515 - 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 15:33:34,170 - FID at iteration 54000: 13.203467
+INFO - dpsgd_diffusion.py - 2024-10-23 15:35:00,639 - Loss: 0.1306, step: 54100
+INFO - dpsgd_diffusion.py - 2024-10-23 15:36:20,667 - Loss: 0.1377, step: 54200
+INFO - dpsgd_diffusion.py - 2024-10-23 15:36:27,624 - Eps-value after 121 epochs: 8.8304
+INFO - dpsgd_diffusion.py - 2024-10-23 15:37:43,570 - Loss: 0.1219, step: 54300
+INFO - dpsgd_diffusion.py - 2024-10-23 15:39:02,767 - Loss: 0.1263, step: 54400
+INFO - dpsgd_diffusion.py - 2024-10-23 15:40:27,060 - Loss: 0.1223, step: 54500
+INFO - dpsgd_diffusion.py - 2024-10-23 15:41:53,257 - Loss: 0.1428, step: 54600
+INFO - dpsgd_diffusion.py - 2024-10-23 15:42:42,286 - Eps-value after 122 epochs: 8.8718
+INFO - dpsgd_diffusion.py - 2024-10-23 15:43:26,335 - Loss: 0.1229, step: 54700
+INFO - dpsgd_diffusion.py - 2024-10-23 15:44:46,633 - Loss: 0.1328, step: 54800
+INFO - dpsgd_diffusion.py - 2024-10-23 15:46:09,575 - Loss: 0.1333, step: 54900
+INFO - dpsgd_diffusion.py - 2024-10-23 15:47:34,782 - Loss: 0.1296, step: 55000
+INFO - dpsgd_diffusion.py - 2024-10-23 15:49:06,216 - Loss: 0.1259, step: 55100
+INFO - dpsgd_diffusion.py - 2024-10-23 15:49:09,143 - Eps-value after 123 epochs: 8.9132
+INFO - dpsgd_diffusion.py - 2024-10-23 15:50:21,458 - Loss: 0.1307, step: 55200
+INFO - dpsgd_diffusion.py - 2024-10-23 15:51:41,574 - Loss: 0.1265, step: 55300
+INFO - dpsgd_diffusion.py - 2024-10-23 15:52:55,886 - Loss: 0.1281, step: 55400
+INFO - dpsgd_diffusion.py - 2024-10-23 15:54:16,216 - Loss: 0.1289, step: 55500
+INFO - dpsgd_diffusion.py - 2024-10-23 15:54:59,316 - Eps-value after 124 epochs: 8.9546
+INFO - dpsgd_diffusion.py - 2024-10-23 15:55:39,758 - Loss: 0.1329, step: 55600
+INFO - dpsgd_diffusion.py - 2024-10-23 15:57:03,607 - Loss: 0.1274, step: 55700
+INFO - dpsgd_diffusion.py - 2024-10-23 15:58:24,567 - Loss: 0.1318, step: 55800
+INFO - dpsgd_diffusion.py - 2024-10-23 15:59:55,401 - Loss: 0.1295, step: 55900
+INFO - dpsgd_diffusion.py - 2024-10-23 16:01:21,759 - Loss: 0.1201, step: 56000
+INFO - dpsgd_diffusion.py - 2024-10-23 16:01:21,782 - Eps-value after 125 epochs: 8.9960
+INFO - dpsgd_diffusion.py - 2024-10-23 16:01:21,795 - Saving snapshot checkpoint and sampling single batch at iteration 56000.
+WARNING - image.py - 2024-10-23 16:01:22,613 - 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 16:01:37,733 - FID at iteration 56000: 12.421117
+INFO - dpsgd_diffusion.py - 2024-10-23 16:03:11,853 - Loss: 0.1419, step: 56100
+INFO - dpsgd_diffusion.py - 2024-10-23 16:04:31,572 - Loss: 0.1317, step: 56200
+INFO - dpsgd_diffusion.py - 2024-10-23 16:05:51,369 - Loss: 0.1216, step: 56300
+INFO - dpsgd_diffusion.py - 2024-10-23 16:07:20,329 - Loss: 0.1348, step: 56400
+INFO - dpsgd_diffusion.py - 2024-10-23 16:08:07,549 - Eps-value after 126 epochs: 9.0374
+INFO - dpsgd_diffusion.py - 2024-10-23 16:08:47,279 - Loss: 0.1273, step: 56500
+INFO - dpsgd_diffusion.py - 2024-10-23 16:10:16,062 - Loss: 0.1371, step: 56600
+INFO - dpsgd_diffusion.py - 2024-10-23 16:11:31,730 - Loss: 0.1253, step: 56700
+INFO - dpsgd_diffusion.py - 2024-10-23 16:12:57,743 - Loss: 0.1305, step: 56800
+INFO - dpsgd_diffusion.py - 2024-10-23 16:14:15,583 - Eps-value after 127 epochs: 9.0788
+INFO - dpsgd_diffusion.py - 2024-10-23 16:14:18,383 - Loss: 0.1273, step: 56900
+INFO - dpsgd_diffusion.py - 2024-10-23 16:15:37,131 - Loss: 0.1323, step: 57000
+INFO - dpsgd_diffusion.py - 2024-10-23 16:16:54,099 - Loss: 0.1305, step: 57100
+INFO - dpsgd_diffusion.py - 2024-10-23 16:18:17,270 - Loss: 0.1269, step: 57200
+INFO - dpsgd_diffusion.py - 2024-10-23 16:19:37,077 - Loss: 0.1306, step: 57300
+INFO - dpsgd_diffusion.py - 2024-10-23 16:20:14,022 - Eps-value after 128 epochs: 9.1201
+INFO - dpsgd_diffusion.py - 2024-10-23 16:20:58,715 - Loss: 0.1260, step: 57400
+INFO - dpsgd_diffusion.py - 2024-10-23 16:22:24,848 - Loss: 0.1226, step: 57500
+INFO - dpsgd_diffusion.py - 2024-10-23 16:23:47,536 - Loss: 0.1349, step: 57600
+INFO - dpsgd_diffusion.py - 2024-10-23 16:25:12,295 - Loss: 0.1208, step: 57700
+INFO - dpsgd_diffusion.py - 2024-10-23 16:26:27,483 - Eps-value after 129 epochs: 9.1606
+INFO - dpsgd_diffusion.py - 2024-10-23 16:26:34,354 - Loss: 0.1291, step: 57800
+INFO - dpsgd_diffusion.py - 2024-10-23 16:27:57,900 - Loss: 0.1205, step: 57900
+INFO - dpsgd_diffusion.py - 2024-10-23 16:29:14,751 - Loss: 0.1286, step: 58000
+INFO - dpsgd_diffusion.py - 2024-10-23 16:29:14,765 - Saving snapshot checkpoint and sampling single batch at iteration 58000.
+WARNING - image.py - 2024-10-23 16:29:15,330 - 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 16:29:31,884 - FID at iteration 58000: 13.037537
+INFO - dpsgd_diffusion.py - 2024-10-23 16:31:02,952 - Loss: 0.1341, step: 58100
+INFO - dpsgd_diffusion.py - 2024-10-23 16:32:28,580 - Loss: 0.1260, step: 58200
+INFO - dpsgd_diffusion.py - 2024-10-23 16:33:00,116 - Eps-value after 130 epochs: 9.2009
+INFO - dpsgd_diffusion.py - 2024-10-23 16:33:52,252 - Loss: 0.1331, step: 58300
+INFO - dpsgd_diffusion.py - 2024-10-23 16:35:17,897 - Loss: 0.1288, step: 58400
+INFO - dpsgd_diffusion.py - 2024-10-23 16:36:30,966 - Loss: 0.1332, step: 58500
+INFO - dpsgd_diffusion.py - 2024-10-23 16:37:44,439 - Loss: 0.1177, step: 58600
+INFO - dpsgd_diffusion.py - 2024-10-23 16:38:46,559 - Eps-value after 131 epochs: 9.2411
+INFO - dpsgd_diffusion.py - 2024-10-23 16:38:55,182 - Loss: 0.1240, step: 58700
+INFO - dpsgd_diffusion.py - 2024-10-23 16:40:11,536 - Loss: 0.1315, step: 58800
+INFO - dpsgd_diffusion.py - 2024-10-23 16:41:24,614 - Loss: 0.1285, step: 58900
+INFO - dpsgd_diffusion.py - 2024-10-23 16:42:38,440 - Loss: 0.1313, step: 59000
+INFO - dpsgd_diffusion.py - 2024-10-23 16:43:54,479 - Loss: 0.1318, step: 59100
+INFO - dpsgd_diffusion.py - 2024-10-23 16:44:21,472 - Eps-value after 132 epochs: 9.2814
+INFO - dpsgd_diffusion.py - 2024-10-23 16:45:08,633 - Loss: 0.1193, step: 59200
+INFO - dpsgd_diffusion.py - 2024-10-23 16:46:20,980 - Loss: 0.1359, step: 59300
+INFO - dpsgd_diffusion.py - 2024-10-23 16:47:38,170 - Loss: 0.1324, step: 59400
+INFO - dpsgd_diffusion.py - 2024-10-23 16:48:52,420 - Loss: 0.1236, step: 59500
+INFO - dpsgd_diffusion.py - 2024-10-23 16:49:59,852 - Eps-value after 133 epochs: 9.3216
+INFO - dpsgd_diffusion.py - 2024-10-23 16:50:14,948 - Loss: 0.1314, step: 59600
+INFO - dpsgd_diffusion.py - 2024-10-23 16:51:39,067 - Loss: 0.1342, step: 59700
+INFO - dpsgd_diffusion.py - 2024-10-23 16:53:07,858 - Loss: 0.1350, step: 59800
+INFO - dpsgd_diffusion.py - 2024-10-23 16:54:35,113 - Loss: 0.1263, step: 59900
+INFO - dpsgd_diffusion.py - 2024-10-23 16:55:59,839 - Loss: 0.1237, step: 60000
+INFO - dpsgd_diffusion.py - 2024-10-23 16:55:59,859 - Saving snapshot checkpoint and sampling single batch at iteration 60000.
+WARNING - image.py - 2024-10-23 16:56:00,525 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-23 16:56:14,650 - FID at iteration 60000: 12.468815
+INFO - dpsgd_diffusion.py - 2024-10-23 16:56:45,505 - Eps-value after 134 epochs: 9.3618
+INFO - dpsgd_diffusion.py - 2024-10-23 16:57:44,202 - Loss: 0.1147, step: 60100
+INFO - dpsgd_diffusion.py - 2024-10-23 16:59:16,503 - Loss: 0.1346, step: 60200
+INFO - dpsgd_diffusion.py - 2024-10-23 17:00:46,062 - Loss: 0.1269, step: 60300
+INFO - dpsgd_diffusion.py - 2024-10-23 17:02:07,333 - Loss: 0.1207, step: 60400
+INFO - dpsgd_diffusion.py - 2024-10-23 17:03:21,305 - Eps-value after 135 epochs: 9.4021
+INFO - dpsgd_diffusion.py - 2024-10-23 17:03:39,023 - Loss: 0.1379, step: 60500
+INFO - dpsgd_diffusion.py - 2024-10-23 17:05:07,473 - Loss: 0.1390, step: 60600
+INFO - dpsgd_diffusion.py - 2024-10-23 17:06:32,960 - Loss: 0.1379, step: 60700
+INFO - dpsgd_diffusion.py - 2024-10-23 17:07:59,918 - Loss: 0.1432, step: 60800
+INFO - dpsgd_diffusion.py - 2024-10-23 17:09:15,039 - Loss: 0.1212, step: 60900
+INFO - dpsgd_diffusion.py - 2024-10-23 17:09:36,718 - Eps-value after 136 epochs: 9.4423
+INFO - dpsgd_diffusion.py - 2024-10-23 17:10:34,684 - Loss: 0.1274, step: 61000
+INFO - dpsgd_diffusion.py - 2024-10-23 17:12:05,935 - Loss: 0.1230, step: 61100
+INFO - dpsgd_diffusion.py - 2024-10-23 17:13:23,371 - Loss: 0.1212, step: 61200
+INFO - dpsgd_diffusion.py - 2024-10-23 17:14:51,720 - Loss: 0.1380, step: 61300
+INFO - dpsgd_diffusion.py - 2024-10-23 17:15:55,302 - Eps-value after 137 epochs: 9.4826
+INFO - dpsgd_diffusion.py - 2024-10-23 17:16:17,296 - Loss: 0.1229, step: 61400
+INFO - dpsgd_diffusion.py - 2024-10-23 17:17:35,719 - Loss: 0.1185, step: 61500
+INFO - dpsgd_diffusion.py - 2024-10-23 17:19:04,889 - Loss: 0.1269, step: 61600
+INFO - dpsgd_diffusion.py - 2024-10-23 17:20:27,456 - Loss: 0.1334, step: 61700
+INFO - dpsgd_diffusion.py - 2024-10-23 17:21:44,563 - Loss: 0.1268, step: 61800
+INFO - dpsgd_diffusion.py - 2024-10-23 17:22:02,861 - Eps-value after 138 epochs: 9.5228
+INFO - dpsgd_diffusion.py - 2024-10-23 17:23:03,634 - Loss: 0.1242, step: 61900
+INFO - dpsgd_diffusion.py - 2024-10-23 17:24:27,235 - Loss: 0.1322, step: 62000
+INFO - dpsgd_diffusion.py - 2024-10-23 17:24:27,250 - Saving snapshot checkpoint and sampling single batch at iteration 62000.
+WARNING - image.py - 2024-10-23 17:24:27,805 - 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 17:24:41,791 - FID at iteration 62000: 12.504372
+INFO - dpsgd_diffusion.py - 2024-10-23 17:26:01,340 - Loss: 0.1378, step: 62100
+INFO - dpsgd_diffusion.py - 2024-10-23 17:27:19,482 - Loss: 0.1366, step: 62200
+INFO - dpsgd_diffusion.py - 2024-10-23 17:28:14,301 - Eps-value after 139 epochs: 9.5626
+INFO - dpsgd_diffusion.py - 2024-10-23 17:28:36,477 - Loss: 0.1265, step: 62300
+INFO - dpsgd_diffusion.py - 2024-10-23 17:30:08,497 - Loss: 0.1274, step: 62400
+INFO - dpsgd_diffusion.py - 2024-10-23 17:31:34,552 - Loss: 0.1360, step: 62500
+INFO - dpsgd_diffusion.py - 2024-10-23 17:32:55,416 - Loss: 0.1258, step: 62600
+INFO - dpsgd_diffusion.py - 2024-10-23 17:34:12,626 - Loss: 0.1320, step: 62700
+INFO - dpsgd_diffusion.py - 2024-10-23 17:34:28,230 - Eps-value after 140 epochs: 9.6017
+INFO - dpsgd_diffusion.py - 2024-10-23 17:35:37,341 - Loss: 0.1359, step: 62800
+INFO - dpsgd_diffusion.py - 2024-10-23 17:37:07,369 - Loss: 0.1242, step: 62900
+INFO - dpsgd_diffusion.py - 2024-10-23 17:38:27,585 - Loss: 0.1298, step: 63000
+INFO - dpsgd_diffusion.py - 2024-10-23 17:39:46,806 - Loss: 0.1341, step: 63100
+INFO - dpsgd_diffusion.py - 2024-10-23 17:40:41,642 - Eps-value after 141 epochs: 9.6408
+INFO - dpsgd_diffusion.py - 2024-10-23 17:41:10,667 - Loss: 0.1268, step: 63200
+INFO - dpsgd_diffusion.py - 2024-10-23 17:42:36,498 - Loss: 0.1233, step: 63300
+INFO - dpsgd_diffusion.py - 2024-10-23 17:43:57,517 - Loss: 0.1351, step: 63400
+INFO - dpsgd_diffusion.py - 2024-10-23 17:45:18,484 - Loss: 0.1334, step: 63500
+INFO - dpsgd_diffusion.py - 2024-10-23 17:46:37,700 - Loss: 0.1172, step: 63600
+INFO - dpsgd_diffusion.py - 2024-10-23 17:46:49,656 - Eps-value after 142 epochs: 9.6799
+INFO - dpsgd_diffusion.py - 2024-10-23 17:48:01,363 - Loss: 0.1312, step: 63700
+INFO - dpsgd_diffusion.py - 2024-10-23 17:49:25,050 - Loss: 0.1352, step: 63800
+INFO - dpsgd_diffusion.py - 2024-10-23 17:50:43,623 - Loss: 0.1253, step: 63900
+INFO - dpsgd_diffusion.py - 2024-10-23 17:52:09,173 - Loss: 0.1235, step: 64000
+INFO - dpsgd_diffusion.py - 2024-10-23 17:52:09,191 - Saving snapshot checkpoint and sampling single batch at iteration 64000.
+WARNING - image.py - 2024-10-23 17:52:09,711 - 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 17:52:24,300 - FID at iteration 64000: 12.295892
+INFO - dpsgd_diffusion.py - 2024-10-23 17:53:20,401 - Eps-value after 143 epochs: 9.7190
+INFO - dpsgd_diffusion.py - 2024-10-23 17:53:53,856 - Loss: 0.1300, step: 64100
+INFO - dpsgd_diffusion.py - 2024-10-23 17:55:10,242 - Loss: 0.1332, step: 64200
+INFO - dpsgd_diffusion.py - 2024-10-23 17:56:26,447 - Loss: 0.1377, step: 64300
+INFO - dpsgd_diffusion.py - 2024-10-23 17:57:42,692 - Loss: 0.1204, step: 64400
+INFO - dpsgd_diffusion.py - 2024-10-23 17:58:54,002 - Loss: 0.1382, step: 64500
+INFO - dpsgd_diffusion.py - 2024-10-23 17:59:02,209 - Eps-value after 144 epochs: 9.7581
+INFO - dpsgd_diffusion.py - 2024-10-23 18:00:07,421 - Loss: 0.1226, step: 64600
+INFO - dpsgd_diffusion.py - 2024-10-23 18:01:22,525 - Loss: 0.1260, step: 64700
+INFO - dpsgd_diffusion.py - 2024-10-23 18:02:36,519 - Loss: 0.1359, step: 64800
+INFO - dpsgd_diffusion.py - 2024-10-23 18:03:49,275 - Loss: 0.1223, step: 64900
+INFO - dpsgd_diffusion.py - 2024-10-23 18:04:32,942 - Eps-value after 145 epochs: 9.7972
+INFO - dpsgd_diffusion.py - 2024-10-23 18:05:05,556 - Loss: 0.1287, step: 65000
+INFO - dpsgd_diffusion.py - 2024-10-23 18:06:18,922 - Loss: 0.1286, step: 65100
+INFO - dpsgd_diffusion.py - 2024-10-23 18:07:31,004 - Loss: 0.1193, step: 65200
+INFO - dpsgd_diffusion.py - 2024-10-23 18:08:47,860 - Loss: 0.1292, step: 65300
+INFO - dpsgd_diffusion.py - 2024-10-23 18:10:03,209 - Loss: 0.1357, step: 65400
+INFO - dpsgd_diffusion.py - 2024-10-23 18:10:09,064 - Eps-value after 146 epochs: 9.8363
+INFO - dpsgd_diffusion.py - 2024-10-23 18:11:25,916 - Loss: 0.1358, step: 65500
+INFO - dpsgd_diffusion.py - 2024-10-23 18:12:48,326 - Loss: 0.1299, step: 65600
+INFO - dpsgd_diffusion.py - 2024-10-23 18:14:10,975 - Loss: 0.1229, step: 65700
+INFO - dpsgd_diffusion.py - 2024-10-23 18:15:41,532 - Loss: 0.1315, step: 65800
+INFO - dpsgd_diffusion.py - 2024-10-23 18:16:30,027 - Eps-value after 147 epochs: 9.8754
+INFO - dpsgd_diffusion.py - 2024-10-23 18:17:08,417 - Loss: 0.1288, step: 65900
+INFO - dpsgd_diffusion.py - 2024-10-23 18:18:30,661 - Loss: 0.1265, step: 66000
+INFO - dpsgd_diffusion.py - 2024-10-23 18:18:30,849 - Saving snapshot checkpoint and sampling single batch at iteration 66000.
+WARNING - image.py - 2024-10-23 18:18:31,400 - 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 18:18:46,578 - FID at iteration 66000: 11.479242
+INFO - dpsgd_diffusion.py - 2024-10-23 18:20:12,799 - Loss: 0.1252, step: 66100
+INFO - dpsgd_diffusion.py - 2024-10-23 18:21:32,551 - Loss: 0.1358, step: 66200
+INFO - dpsgd_diffusion.py - 2024-10-23 18:22:51,090 - Loss: 0.1414, step: 66300
+INFO - dpsgd_diffusion.py - 2024-10-23 18:22:55,162 - Eps-value after 148 epochs: 9.9145
+INFO - dpsgd_diffusion.py - 2024-10-23 18:24:12,590 - Loss: 0.1309, step: 66400
+INFO - dpsgd_diffusion.py - 2024-10-23 18:25:26,343 - Loss: 0.1244, step: 66500
+INFO - dpsgd_diffusion.py - 2024-10-23 18:26:46,725 - Loss: 0.1319, step: 66600
+INFO - dpsgd_diffusion.py - 2024-10-23 18:28:09,358 - Loss: 0.1136, step: 66700
+INFO - dpsgd_diffusion.py - 2024-10-23 18:28:51,094 - Eps-value after 149 epochs: 9.9536
+INFO - dpsgd_diffusion.py - 2024-10-23 18:29:28,467 - Loss: 0.1312, step: 66800
+INFO - dpsgd_diffusion.py - 2024-10-23 18:30:45,809 - Loss: 0.1279, step: 66900
+INFO - dpsgd_diffusion.py - 2024-10-23 18:32:12,148 - Loss: 0.1298, step: 67000
+INFO - dpsgd_diffusion.py - 2024-10-23 18:33:43,912 - Loss: 0.1177, step: 67100
+INFO - dpsgd_diffusion.py - 2024-10-23 18:35:10,588 - Loss: 0.1183, step: 67200
+INFO - dpsgd_diffusion.py - 2024-10-23 18:35:10,610 - Eps-value after 150 epochs: 9.9927
+INFO - dpsgd_diffusion.py - 2024-10-23 18:35:10,953 - Saving final checkpoint.
+INFO - dpsgd_diffusion.py - 2024-10-23 18:35:10,959 - start to generate 60000 samples
+INFO - dpsgd_diffusion.py - 2024-10-23 19:21:32,706 - Generation Finished!
+INFO - dataset_loader.py - 2024-10-24 13:51:21,358 - delta is reset as 1.6657508770018431e-06
+INFO - evaluator.py - 2024-10-24 13:52:16,733 - Epoch: 0 Train acc: 67.97090909090909 Val acc: 92.78 Test acc93.45; Train loss: 0.003784748126972805 Val loss: 0.00024786356985569
+INFO - evaluator.py - 2024-10-24 13:52:40,445 - Epoch: 1 Train acc: 93.97999999999999 Val acc: 96.2 Test acc96.63000000000001; Train loss: 0.0007785959134047681 Val loss: 0.00012326653003692626
+INFO - evaluator.py - 2024-10-24 13:53:03,932 - Epoch: 2 Train acc: 95.19818181818181 Val acc: 95.54 Test acc96.33; Train loss: 0.0006126508246768605 Val loss: 0.00014434102773666383
+INFO - evaluator.py - 2024-10-24 13:53:27,542 - Epoch: 3 Train acc: 95.65818181818182 Val acc: 91.72 Test acc92.04; Train loss: 0.000555522961372679 Val loss: 0.00025369436740875246
+INFO - evaluator.py - 2024-10-24 13:53:50,282 - Epoch: 4 Train acc: 95.87636363636364 Val acc: 94.42 Test acc95.34; Train loss: 0.0005103024895218286 Val loss: 0.0001836786776781082
+INFO - evaluator.py - 2024-10-24 13:54:13,430 - Epoch: 5 Train acc: 96.17090909090909 Val acc: 94.69999999999999 Test acc95.69; Train loss: 0.00047840098230676216 Val loss: 0.00015525994300842285
+INFO - evaluator.py - 2024-10-24 13:54:36,482 - Epoch: 6 Train acc: 96.38 Val acc: 92.08 Test acc92.82000000000001; Train loss: 0.000444936033541506 Val loss: 0.0002627044588327408
+INFO - evaluator.py - 2024-10-24 13:54:59,704 - Epoch: 7 Train acc: 96.39090909090909 Val acc: 86.53999999999999 Test acc87.13; Train loss: 0.0004411867999217727 Val loss: 0.0003837283968925476
+INFO - evaluator.py - 2024-10-24 13:55:23,026 - Epoch: 8 Train acc: 96.53454545454545 Val acc: 94.3 Test acc95.03; Train loss: 0.0004258164469491352 Val loss: 0.00018840023279190064
+INFO - evaluator.py - 2024-10-24 13:55:46,065 - Epoch: 9 Train acc: 96.60545454545455 Val acc: 88.02 Test acc88.94; Train loss: 0.0004188117013736205 Val loss: 0.0003580509305000305
+INFO - evaluator.py - 2024-10-24 13:56:09,122 - Epoch: 10 Train acc: 96.7909090909091 Val acc: 79.88 Test acc79.29; Train loss: 0.0003928024090149186 Val loss: 0.0005630006432533264
+INFO - evaluator.py - 2024-10-24 13:56:32,367 - Epoch: 11 Train acc: 96.84727272727272 Val acc: 91.88 Test acc92.71000000000001; Train loss: 0.00037717625295574013 Val loss: 0.00025214052200317385
+INFO - evaluator.py - 2024-10-24 13:56:56,033 - Epoch: 12 Train acc: 96.94363636363636 Val acc: 88.92 Test acc89.29; Train loss: 0.00037349421635947443 Val loss: 0.0003499084651470184
+INFO - evaluator.py - 2024-10-24 13:57:19,259 - Epoch: 13 Train acc: 97.0109090909091 Val acc: 80.66 Test acc80.77; Train loss: 0.00036281452185728334 Val loss: 0.0005906155109405518
+INFO - evaluator.py - 2024-10-24 13:57:41,824 - Epoch: 14 Train acc: 97.02 Val acc: 95.22 Test acc95.82000000000001; Train loss: 0.00035541277551515534 Val loss: 0.000157877516746521
+INFO - evaluator.py - 2024-10-24 13:58:04,435 - Epoch: 15 Train acc: 97.13272727272727 Val acc: 15.040000000000001 Test acc13.87; Train loss: 0.00034297237277708273 Val loss: 0.007883681678771973
+INFO - evaluator.py - 2024-10-24 13:58:27,856 - Epoch: 16 Train acc: 97.27090909090909 Val acc: 87.98 Test acc88.69; Train loss: 0.00033302434967322783 Val loss: 0.00037005335688591005
+INFO - evaluator.py - 2024-10-24 13:58:50,787 - Epoch: 17 Train acc: 97.18909090909091 Val acc: 12.04 Test acc10.91; Train loss: 0.00033322361639954827 Val loss: 0.010143883323669434
+INFO - evaluator.py - 2024-10-24 13:59:14,114 - Epoch: 18 Train acc: 97.35272727272726 Val acc: 70.92 Test acc70.02000000000001; Train loss: 0.00031521836573427373 Val loss: 0.0008515426397323609
+INFO - evaluator.py - 2024-10-24 13:59:36,411 - Epoch: 19 Train acc: 97.37818181818182 Val acc: 91.42 Test acc91.73; Train loss: 0.0003054551785473119 Val loss: 0.0002785489797592163
+INFO - evaluator.py - 2024-10-24 14:00:00,146 - Epoch: 20 Train acc: 98.21454545454546 Val acc: 96.5 Test acc97.2; Train loss: 0.00021036749978295782 Val loss: 0.00011117057651281357
+INFO - evaluator.py - 2024-10-24 14:00:23,578 - Epoch: 21 Train acc: 98.51454545454546 Val acc: 96.58 Test acc97.23; Train loss: 0.00017785717121918094 Val loss: 0.0001251378983259201
+INFO - evaluator.py - 2024-10-24 14:00:47,491 - Epoch: 22 Train acc: 98.59636363636363 Val acc: 96.94 Test acc97.59; Train loss: 0.0001635378715836189 Val loss: 0.000111991086602211
+INFO - evaluator.py - 2024-10-24 14:01:10,725 - Epoch: 23 Train acc: 98.78363636363636 Val acc: 95.16 Test acc96.09; Train loss: 0.0001457353084432808 Val loss: 0.0001914803832769394
+INFO - evaluator.py - 2024-10-24 14:01:34,138 - Epoch: 24 Train acc: 98.87454545454545 Val acc: 95.5 Test acc96.02000000000001; Train loss: 0.00013333696800876748 Val loss: 0.0001874072104692459
+INFO - evaluator.py - 2024-10-24 14:01:56,483 - Epoch: 25 Train acc: 98.89090909090909 Val acc: 96.78 Test acc97.49; Train loss: 0.0001273330277763307 Val loss: 0.00013033200651407242
+INFO - evaluator.py - 2024-10-24 14:02:20,433 - Epoch: 26 Train acc: 98.99454545454546 Val acc: 95.54 Test acc96.2; Train loss: 0.00011578304467892104 Val loss: 0.00019414188861846925
+INFO - evaluator.py - 2024-10-24 14:02:43,803 - Epoch: 27 Train acc: 99.08545454545454 Val acc: 95.34 Test acc95.83; Train loss: 0.00010602335570041428 Val loss: 0.00021417953968048097
+INFO - evaluator.py - 2024-10-24 14:03:06,576 - Epoch: 28 Train acc: 99.03454545454545 Val acc: 96.64 Test acc97.53; Train loss: 0.0001082820675462823 Val loss: 0.0001415296196937561
+INFO - evaluator.py - 2024-10-24 14:03:29,697 - Epoch: 29 Train acc: 99.28363636363636 Val acc: 96.7 Test acc97.24000000000001; Train loss: 8.301296520300886e-05 Val loss: 0.00016162199079990388
+INFO - evaluator.py - 2024-10-24 14:03:53,041 - Epoch: 30 Train acc: 99.26181818181819 Val acc: 95.74000000000001 Test acc96.36; Train loss: 8.447984019294381e-05 Val loss: 0.00020160214602947234
+INFO - evaluator.py - 2024-10-24 14:04:16,179 - Epoch: 31 Train acc: 99.33636363636363 Val acc: 96.6 Test acc97.11; Train loss: 7.538770065558227e-05 Val loss: 0.00017163579016923905
+INFO - evaluator.py - 2024-10-24 14:04:39,260 - Epoch: 32 Train acc: 99.3490909090909 Val acc: 96.96000000000001 Test acc97.55; Train loss: 7.270754963498224e-05 Val loss: 0.00014257095605134965
+INFO - evaluator.py - 2024-10-24 14:05:02,116 - Epoch: 33 Train acc: 99.42909090909092 Val acc: 95.82000000000001 Test acc96.26; Train loss: 5.94746734587137e-05 Val loss: 0.00020974591672420502
+INFO - evaluator.py - 2024-10-24 14:05:25,198 - Epoch: 34 Train acc: 99.39454545454545 Val acc: 96.92 Test acc97.63; Train loss: 6.529002241493965e-05 Val loss: 0.0001462183564901352
+INFO - evaluator.py - 2024-10-24 14:05:48,335 - Epoch: 35 Train acc: 99.54363636363637 Val acc: 96.26 Test acc96.88; Train loss: 5.386331145418808e-05 Val loss: 0.00020571849942207336
+INFO - evaluator.py - 2024-10-24 14:06:11,555 - Epoch: 36 Train acc: 99.44909090909091 Val acc: 96.56 Test acc96.61; Train loss: 6.163072638340634e-05 Val loss: 0.00019153561890125276
+INFO - evaluator.py - 2024-10-24 14:06:34,183 - Epoch: 37 Train acc: 99.67090909090909 Val acc: 96.88 Test acc97.31; Train loss: 4.0275286277756095e-05 Val loss: 0.0001704518437385559
+INFO - evaluator.py - 2024-10-24 14:06:57,491 - Epoch: 38 Train acc: 99.60181818181817 Val acc: 96.38 Test acc96.92; Train loss: 4.5012849267699164e-05 Val loss: 0.0002110461801290512
+INFO - evaluator.py - 2024-10-24 14:07:20,610 - Epoch: 39 Train acc: 99.68909090909091 Val acc: 96.89999999999999 Test acc97.23; Train loss: 3.769360432845794e-05 Val loss: 0.0001777258411049843
+INFO - evaluator.py - 2024-10-24 14:07:45,086 - Epoch: 40 Train acc: 99.90363636363637 Val acc: 96.84 Test acc97.37; Train loss: 1.4287123274036938e-05 Val loss: 0.00017627789974212647
+INFO - evaluator.py - 2024-10-24 14:08:07,841 - Epoch: 41 Train acc: 99.98181818181818 Val acc: 97.14 Test acc97.48; Train loss: 5.513482623924078e-06 Val loss: 0.00018305629193782807
+INFO - evaluator.py - 2024-10-24 14:08:31,520 - Epoch: 42 Train acc: 99.99272727272728 Val acc: 97.16 Test acc97.59; Train loss: 3.5898909040208143e-06 Val loss: 0.00018750280141830445
+INFO - evaluator.py - 2024-10-24 14:08:55,151 - Epoch: 43 Train acc: 99.99636363636364 Val acc: 97.11999999999999 Test acc97.48; Train loss: 2.73092587369981e-06 Val loss: 0.00019175391793251038
+INFO - evaluator.py - 2024-10-24 14:09:18,753 - Epoch: 44 Train acc: 99.99636363636364 Val acc: 97.08 Test acc97.53; Train loss: 2.2205837636482267e-06 Val loss: 0.00019393322467803955
+INFO - evaluator.py - 2024-10-24 14:09:42,131 - Epoch: 45 Train acc: 99.99454545454546 Val acc: 97.06 Test acc97.41; Train loss: 1.991779413087484e-06 Val loss: 0.00020487713813781738
+INFO - evaluator.py - 2024-10-24 14:10:05,653 - Epoch: 46 Train acc: 99.99454545454546 Val acc: 97.06 Test acc97.43; Train loss: 1.7548435870015634e-06 Val loss: 0.0002104994535446167
+INFO - evaluator.py - 2024-10-24 14:10:28,881 - Epoch: 47 Train acc: 100.0 Val acc: 97.02 Test acc97.37; Train loss: 1.1175438256032066e-06 Val loss: 0.00021353058815002442
+INFO - evaluator.py - 2024-10-24 14:10:51,941 - Epoch: 48 Train acc: 99.99818181818182 Val acc: 97.06 Test acc97.38; Train loss: 9.243336002493214e-07 Val loss: 0.00021194270253181458
+INFO - evaluator.py - 2024-10-24 14:11:15,310 - Epoch: 49 Train acc: 100.0 Val acc: 97.02 Test acc97.38; Train loss: 8.38651197649266e-07 Val loss: 0.0002211984544992447
+INFO - evaluator.py - 2024-10-24 14:11:15,331 - The best acc of synthetic images on sensitive val and the corresponding acc on test dataset from resnet is 97.16 and 97.59
+INFO - evaluator.py - 2024-10-24 14:11:15,331 - The best acc of synthetic images on noisy sensitive val and the corresponding acc on test dataset from resnet is 97.16 and 97.59
+INFO - evaluator.py - 2024-10-24 14:11:15,331 - The best acc test dataset from resnet is 97.63
+INFO - evaluator.py - 2024-10-24 14:11:43,591 - Epoch: 0 Train acc: 86.52363636363636 Val acc: 93.02 Test acc93.92; Train loss: 0.0016527599001472646 Val loss: 0.00022161238491535186
+INFO - evaluator.py - 2024-10-24 14:12:10,613 - Epoch: 1 Train acc: 94.64363636363636 Val acc: 91.82000000000001 Test acc92.56; Train loss: 0.0006656158815730702 Val loss: 0.00025606356859207154
+INFO - evaluator.py - 2024-10-24 14:12:36,977 - Epoch: 2 Train acc: 95.61272727272727 Val acc: 95.84 Test acc96.13000000000001; Train loss: 0.0005495609951290218 Val loss: 0.00013897116780281068
+INFO - evaluator.py - 2024-10-24 14:13:03,700 - Epoch: 3 Train acc: 96.01454545454546 Val acc: 92.58 Test acc93.46; Train loss: 0.0004938689215616747 Val loss: 0.0002389839142560959
+INFO - evaluator.py - 2024-10-24 14:13:30,247 - Epoch: 4 Train acc: 96.1490909090909 Val acc: 95.16 Test acc95.91; Train loss: 0.0004719756727191535 Val loss: 0.00015055001378059388
+INFO - evaluator.py - 2024-10-24 14:13:56,792 - Epoch: 5 Train acc: 96.48181818181818 Val acc: 93.84 Test acc94.73; Train loss: 0.0004406749774786559 Val loss: 0.00018695705533027649
+INFO - evaluator.py - 2024-10-24 14:14:23,205 - Epoch: 6 Train acc: 96.6290909090909 Val acc: 94.12 Test acc94.97; Train loss: 0.0004179120659828186 Val loss: 0.0001785611629486084
+INFO - evaluator.py - 2024-10-24 14:14:49,711 - Epoch: 7 Train acc: 96.63090909090909 Val acc: 96.24000000000001 Test acc96.92; Train loss: 0.0004064624643461271 Val loss: 0.00012332711815834046
+INFO - evaluator.py - 2024-10-24 14:15:16,244 - Epoch: 8 Train acc: 96.78909090909092 Val acc: 88.32 Test acc88.97; Train loss: 0.0003955454291945154 Val loss: 0.00038484560251235964
+INFO - evaluator.py - 2024-10-24 14:15:43,245 - Epoch: 9 Train acc: 96.8490909090909 Val acc: 90.68 Test acc91.53999999999999; Train loss: 0.00037763446779413655 Val loss: 0.0002904590547084808
+INFO - evaluator.py - 2024-10-24 14:16:10,047 - Epoch: 10 Train acc: 96.97636363636364 Val acc: 80.9 Test acc81.95; Train loss: 0.0003640056165781888 Val loss: 0.0005514697074890136
+INFO - evaluator.py - 2024-10-24 14:16:36,604 - Epoch: 11 Train acc: 97.14181818181818 Val acc: 33.08 Test acc31.900000000000002; Train loss: 0.00034558035782115027 Val loss: 0.004311897850036621
+INFO - evaluator.py - 2024-10-24 14:17:03,028 - Epoch: 12 Train acc: 97.26727272727273 Val acc: 81.38 Test acc82.8; Train loss: 0.0003297121750698848 Val loss: 0.0006039986848831177
+INFO - evaluator.py - 2024-10-24 14:17:29,484 - Epoch: 13 Train acc: 97.2909090909091 Val acc: 36.42 Test acc36.03; Train loss: 0.00032228018194437025 Val loss: 0.003968805265426636
+INFO - evaluator.py - 2024-10-24 14:17:56,117 - Epoch: 14 Train acc: 97.32909090909091 Val acc: 87.56 Test acc89.03999999999999; Train loss: 0.00032055646157400173 Val loss: 0.000414377748966217
+INFO - evaluator.py - 2024-10-24 14:18:22,590 - Epoch: 15 Train acc: 97.53090909090909 Val acc: 69.88 Test acc71.07; Train loss: 0.00029651874750852584 Val loss: 0.0010386816263198853
+INFO - evaluator.py - 2024-10-24 14:18:49,384 - Epoch: 16 Train acc: 97.54545454545455 Val acc: 91.14 Test acc92.25; Train loss: 0.0002919796401465481 Val loss: 0.00029776048064231875
+INFO - evaluator.py - 2024-10-24 14:19:15,941 - Epoch: 17 Train acc: 97.60181818181817 Val acc: 96.39999999999999 Test acc97.00999999999999; Train loss: 0.0002845724048939618 Val loss: 0.00011368528306484223
+INFO - evaluator.py - 2024-10-24 14:19:42,983 - Epoch: 18 Train acc: 97.61090909090909 Val acc: 83.39999999999999 Test acc83.69; Train loss: 0.00027024737601591783 Val loss: 0.0004907494008541107
+INFO - evaluator.py - 2024-10-24 14:20:09,703 - Epoch: 19 Train acc: 97.76727272727273 Val acc: 91.34 Test acc92.54; Train loss: 0.0002647632862356576 Val loss: 0.0002744375556707382
+INFO - evaluator.py - 2024-10-24 14:20:35,977 - Epoch: 20 Train acc: 98.46000000000001 Val acc: 96.96000000000001 Test acc97.61999999999999; Train loss: 0.00018127711692994292 Val loss: 0.00010114409625530243
+INFO - evaluator.py - 2024-10-24 14:21:02,613 - Epoch: 21 Train acc: 98.7109090909091 Val acc: 97.04 Test acc97.72; Train loss: 0.00015249947969039733 Val loss: 0.00010822914391756058
+INFO - evaluator.py - 2024-10-24 14:21:28,934 - Epoch: 22 Train acc: 98.88363636363636 Val acc: 96.7 Test acc97.32; Train loss: 0.00013442023482004349 Val loss: 0.00013583226203918458
+INFO - evaluator.py - 2024-10-24 14:21:55,281 - Epoch: 23 Train acc: 98.87090909090908 Val acc: 96.78 Test acc97.52; Train loss: 0.00012837877867912705 Val loss: 0.00013227932006120682
+INFO - evaluator.py - 2024-10-24 14:22:21,569 - Epoch: 24 Train acc: 98.99454545454546 Val acc: 96.58 Test acc97.18; Train loss: 0.00011488791921768676 Val loss: 0.00014716987162828444
+INFO - evaluator.py - 2024-10-24 14:22:47,995 - Epoch: 25 Train acc: 99.08181818181818 Val acc: 96.44 Test acc96.93; Train loss: 0.00010823331854983487 Val loss: 0.0001714364379644394
+INFO - evaluator.py - 2024-10-24 14:23:14,417 - Epoch: 26 Train acc: 99.10909090909091 Val acc: 96.72 Test acc97.33000000000001; Train loss: 0.00010211155669001693 Val loss: 0.00015187785923480987
+INFO - evaluator.py - 2024-10-24 14:23:41,339 - Epoch: 27 Train acc: 99.28545454545454 Val acc: 96.64 Test acc97.06; Train loss: 8.72372032312507e-05 Val loss: 0.00016489003896713256
+INFO - evaluator.py - 2024-10-24 14:24:07,564 - Epoch: 28 Train acc: 99.3 Val acc: 96.67999999999999 Test acc97.31; Train loss: 8.245198154737326e-05 Val loss: 0.00015541560798883438
+INFO - evaluator.py - 2024-10-24 14:24:33,743 - Epoch: 29 Train acc: 99.39818181818183 Val acc: 96.36 Test acc96.86; Train loss: 7.282749334858223e-05 Val loss: 0.00018731055557727813
+INFO - evaluator.py - 2024-10-24 14:25:00,078 - Epoch: 30 Train acc: 99.37454545454545 Val acc: 96.61999999999999 Test acc97.19; Train loss: 7.099206083115529e-05 Val loss: 0.0001660961240530014
+INFO - evaluator.py - 2024-10-24 14:25:26,344 - Epoch: 31 Train acc: 99.42909090909092 Val acc: 95.89999999999999 Test acc96.44; Train loss: 6.566461082971232e-05 Val loss: 0.0002466306149959564
+INFO - evaluator.py - 2024-10-24 14:25:52,764 - Epoch: 32 Train acc: 99.45454545454545 Val acc: 96.36 Test acc97.00999999999999; Train loss: 6.0767201636917886e-05 Val loss: 0.00020748532116413116
+INFO - evaluator.py - 2024-10-24 14:26:18,805 - Epoch: 33 Train acc: 99.47454545454546 Val acc: 95.98 Test acc96.78999999999999; Train loss: 5.7887181611096655e-05 Val loss: 0.0002382228046655655
+INFO - evaluator.py - 2024-10-24 14:26:45,276 - Epoch: 34 Train acc: 99.54727272727273 Val acc: 96.52 Test acc97.18; Train loss: 5.188201662491668e-05 Val loss: 0.00019849611520767212
+INFO - evaluator.py - 2024-10-24 14:27:11,994 - Epoch: 35 Train acc: 99.58 Val acc: 96.6 Test acc97.46000000000001; Train loss: 4.838933323467658e-05 Val loss: 0.00017488348186016082
+INFO - evaluator.py - 2024-10-24 14:27:38,134 - Epoch: 36 Train acc: 99.62181818181818 Val acc: 96.56 Test acc97.32; Train loss: 4.341384089943445e-05 Val loss: 0.00019191605746746062
+INFO - evaluator.py - 2024-10-24 14:28:04,296 - Epoch: 37 Train acc: 99.67636363636365 Val acc: 96.3 Test acc97.1; Train loss: 4.0257031920323655e-05 Val loss: 0.0002125656545162201
+INFO - evaluator.py - 2024-10-24 14:28:30,573 - Epoch: 38 Train acc: 99.7309090909091 Val acc: 96.78 Test acc97.56; Train loss: 3.3147712045518514e-05 Val loss: 0.0001770731642842293
+INFO - evaluator.py - 2024-10-24 14:28:57,000 - Epoch: 39 Train acc: 99.64181818181818 Val acc: 96.64 Test acc97.63; Train loss: 4.104271088620987e-05 Val loss: 0.00018289183676242828
+INFO - evaluator.py - 2024-10-24 14:29:23,258 - Epoch: 40 Train acc: 99.79272727272728 Val acc: 96.6 Test acc97.58; Train loss: 2.5585226103430615e-05 Val loss: 0.00018752272129058837
+INFO - evaluator.py - 2024-10-24 14:29:49,485 - Epoch: 41 Train acc: 99.85818181818182 Val acc: 96.72 Test acc97.56; Train loss: 1.793350338279693e-05 Val loss: 0.00018849769532680512
+INFO - evaluator.py - 2024-10-24 14:30:15,705 - Epoch: 42 Train acc: 99.85090909090908 Val acc: 96.67999999999999 Test acc97.61; Train loss: 1.8851994909346104e-05 Val loss: 0.00018906972706317902
+INFO - evaluator.py - 2024-10-24 14:30:42,410 - Epoch: 43 Train acc: 99.87454545454545 Val acc: 96.61999999999999 Test acc97.54; Train loss: 1.600148070296696e-05 Val loss: 0.0001974196881055832
+INFO - evaluator.py - 2024-10-24 14:31:08,780 - Epoch: 44 Train acc: 99.91272727272728 Val acc: 96.7 Test acc97.5; Train loss: 1.3652955014681952e-05 Val loss: 0.00019671379625797272
+INFO - evaluator.py - 2024-10-24 14:31:34,744 - Epoch: 45 Train acc: 99.91454545454546 Val acc: 96.61999999999999 Test acc97.39; Train loss: 1.2056448281774382e-05 Val loss: 0.00021514504849910737
+INFO - evaluator.py - 2024-10-24 14:32:01,142 - Epoch: 46 Train acc: 99.90545454545455 Val acc: 96.61999999999999 Test acc97.54; Train loss: 1.2149343854451382e-05 Val loss: 0.00020849835574626922
+INFO - evaluator.py - 2024-10-24 14:32:27,480 - Epoch: 47 Train acc: 99.90727272727273 Val acc: 96.72 Test acc97.56; Train loss: 1.1904038733337074e-05 Val loss: 0.0001982998162508011
+INFO - evaluator.py - 2024-10-24 14:32:53,675 - Epoch: 48 Train acc: 99.92909090909092 Val acc: 96.64 Test acc97.41; Train loss: 1.088384029333776e-05 Val loss: 0.0002125587582588196
+INFO - evaluator.py - 2024-10-24 14:33:19,883 - Epoch: 49 Train acc: 99.93636363636364 Val acc: 96.56 Test acc97.38; Train loss: 9.367216084898576e-06 Val loss: 0.00021579490303993225
+INFO - evaluator.py - 2024-10-24 14:33:19,888 - The best acc of synthetic images on sensitive val and the corresponding acc on test dataset from wrn is 97.04 and 97.72
+INFO - evaluator.py - 2024-10-24 14:33:19,889 - The best acc of synthetic images on noisy sensitive val and the corresponding acc on test dataset from wrn is 97.04 and 97.72
+INFO - evaluator.py - 2024-10-24 14:33:19,889 - The best acc test dataset from wrn is 97.72
+INFO - evaluator.py - 2024-10-24 14:35:01,338 - Epoch: 0 Train acc: 79.03636363636363 Val acc: 94.17999999999999 Test acc94.72; Train loss: 0.0032538017161867837 Val loss: 0.0001921001046895981
+INFO - evaluator.py - 2024-10-24 14:36:42,527 - Epoch: 1 Train acc: 94.67272727272727 Val acc: 95.5 Test acc95.57; Train loss: 0.0006782876717773351 Val loss: 0.00014143398106098175
+INFO - evaluator.py - 2024-10-24 14:38:23,406 - Epoch: 2 Train acc: 95.42181818181818 Val acc: 95.78 Test acc95.91; Train loss: 0.0005835709530521523 Val loss: 0.0001348336786031723
+INFO - evaluator.py - 2024-10-24 14:40:04,409 - Epoch: 3 Train acc: 95.93272727272726 Val acc: 95.17999999999999 Test acc96.06; Train loss: 0.000509300236268477 Val loss: 0.00014231915175914764
+INFO - evaluator.py - 2024-10-24 14:41:45,164 - Epoch: 4 Train acc: 96.27818181818182 Val acc: 92.25999999999999 Test acc92.91; Train loss: 0.00046718286289410156 Val loss: 0.00024398060739040374
+INFO - evaluator.py - 2024-10-24 14:43:26,056 - Epoch: 5 Train acc: 96.52727272727273 Val acc: 94.76 Test acc95.26; Train loss: 0.00041948916207660327 Val loss: 0.0001650694042444229
+INFO - evaluator.py - 2024-10-24 14:45:06,936 - Epoch: 6 Train acc: 96.66545454545454 Val acc: 91.14 Test acc91.51; Train loss: 0.0004011365381154147 Val loss: 0.00029152843356132507
+INFO - evaluator.py - 2024-10-24 14:46:47,769 - Epoch: 7 Train acc: 96.91636363636363 Val acc: 94.69999999999999 Test acc94.74000000000001; Train loss: 0.000378968644277616 Val loss: 0.00018140571415424346
+INFO - evaluator.py - 2024-10-24 14:48:28,557 - Epoch: 8 Train acc: 97.02545454545455 Val acc: 95.92 Test acc96.55; Train loss: 0.0003472545160149986 Val loss: 0.0001322479873895645
+INFO - evaluator.py - 2024-10-24 14:50:09,354 - Epoch: 9 Train acc: 97.05454545454546 Val acc: 91.72 Test acc92.43; Train loss: 0.00034715874777598813 Val loss: 0.0002654936462640762
+INFO - evaluator.py - 2024-10-24 14:51:50,368 - Epoch: 10 Train acc: 97.21272727272728 Val acc: 92.78 Test acc93.16; Train loss: 0.0003335896528918635 Val loss: 0.00023848320841789246
+INFO - evaluator.py - 2024-10-24 14:53:31,161 - Epoch: 11 Train acc: 97.45818181818183 Val acc: 90.60000000000001 Test acc91.73; Train loss: 0.0003037638592787764 Val loss: 0.00030407130122184754
+INFO - evaluator.py - 2024-10-24 14:55:11,896 - Epoch: 12 Train acc: 97.36545454545454 Val acc: 84.74000000000001 Test acc85.95; Train loss: 0.0003048894430426034 Val loss: 0.0005362992227077485
+INFO - evaluator.py - 2024-10-24 14:56:52,794 - Epoch: 13 Train acc: 97.58545454545454 Val acc: 94.76 Test acc95.50999999999999; Train loss: 0.0002914728459309448 Val loss: 0.00016979033946990966
+INFO - evaluator.py - 2024-10-24 14:58:33,605 - Epoch: 14 Train acc: 97.65818181818182 Val acc: 78.12 Test acc78.75; Train loss: 0.0002714021150361408 Val loss: 0.0006839081645011902
+INFO - evaluator.py - 2024-10-24 15:00:14,363 - Epoch: 15 Train acc: 97.66181818181818 Val acc: 80.2 Test acc80.04; Train loss: 0.00027063410092483865 Val loss: 0.0007844877600669861
+INFO - evaluator.py - 2024-10-24 15:01:55,344 - Epoch: 16 Train acc: 98.05090909090909 Val acc: 86.3 Test acc86.83999999999999; Train loss: 0.0002305472403426062 Val loss: 0.0004804627239704132
+INFO - evaluator.py - 2024-10-24 15:03:36,259 - Epoch: 17 Train acc: 98.04 Val acc: 34.52 Test acc33.45; Train loss: 0.00022615631986409426 Val loss: 0.0041861631393432614
+INFO - evaluator.py - 2024-10-24 15:05:16,981 - Epoch: 18 Train acc: 98.01272727272728 Val acc: 73.32 Test acc72.58; Train loss: 0.00022514456617222592 Val loss: 0.0010733292818069459
+INFO - evaluator.py - 2024-10-24 15:06:57,746 - Epoch: 19 Train acc: 98.26 Val acc: 65.7 Test acc65.47; Train loss: 0.00019472912163050337 Val loss: 0.0016746376752853395
+INFO - evaluator.py - 2024-10-24 15:08:38,671 - Epoch: 20 Train acc: 99.40545454545455 Val acc: 94.44 Test acc95.02000000000001; Train loss: 7.702009943313897e-05 Val loss: 0.00020477780401706696
+INFO - evaluator.py - 2024-10-24 15:10:19,401 - Epoch: 21 Train acc: 99.79090909090908 Val acc: 97.0 Test acc97.59; Train loss: 3.6050485758195544e-05 Val loss: 0.00010159326791763305
+INFO - evaluator.py - 2024-10-24 15:12:00,132 - Epoch: 22 Train acc: 99.90727272727273 Val acc: 97.1 Test acc97.58; Train loss: 1.9932141464034265e-05 Val loss: 0.00010733856111764908
+INFO - evaluator.py - 2024-10-24 15:13:40,832 - Epoch: 23 Train acc: 99.96363636363637 Val acc: 97.22 Test acc97.6; Train loss: 1.1571493630551479e-05 Val loss: 0.00011093721687793732
+INFO - evaluator.py - 2024-10-24 15:15:21,721 - Epoch: 24 Train acc: 99.9890909090909 Val acc: 97.08 Test acc97.46000000000001; Train loss: 6.96449460175989e-06 Val loss: 0.00012190409004688263
+INFO - evaluator.py - 2024-10-24 15:17:02,450 - Epoch: 25 Train acc: 99.99636363636364 Val acc: 96.98 Test acc97.43; Train loss: 3.941047649343752e-06 Val loss: 0.00013277028650045394
+INFO - evaluator.py - 2024-10-24 15:18:43,175 - Epoch: 26 Train acc: 100.0 Val acc: 97.04 Test acc97.3; Train loss: 2.539663449384865e-06 Val loss: 0.0001381123036146164
+INFO - evaluator.py - 2024-10-24 15:20:24,074 - Epoch: 27 Train acc: 100.0 Val acc: 97.06 Test acc97.42; Train loss: 1.756783827229149e-06 Val loss: 0.00013887120336294174
+INFO - evaluator.py - 2024-10-24 15:22:04,829 - Epoch: 28 Train acc: 100.0 Val acc: 97.14 Test acc97.44; Train loss: 1.423986322929109e-06 Val loss: 0.00014279593378305436
+INFO - evaluator.py - 2024-10-24 15:23:45,526 - Epoch: 29 Train acc: 100.0 Val acc: 97.1 Test acc97.42; Train loss: 1.1356451325065626e-06 Val loss: 0.00014839075356721878
+INFO - evaluator.py - 2024-10-24 15:25:26,195 - Epoch: 30 Train acc: 100.0 Val acc: 97.04 Test acc97.49; Train loss: 8.453485526842996e-07 Val loss: 0.00015111406445503234
+INFO - evaluator.py - 2024-10-24 15:27:07,087 - Epoch: 31 Train acc: 100.0 Val acc: 97.04 Test acc97.41; Train loss: 7.776968244632537e-07 Val loss: 0.0001590302348136902
+INFO - evaluator.py - 2024-10-24 15:28:47,841 - Epoch: 32 Train acc: 100.0 Val acc: 97.18 Test acc97.5; Train loss: 6.399950903208016e-07 Val loss: 0.00015902468264102936
+INFO - evaluator.py - 2024-10-24 15:30:28,582 - Epoch: 33 Train acc: 100.0 Val acc: 97.11999999999999 Test acc97.43; Train loss: 4.858852196114391e-07 Val loss: 0.0001614765852689743
+INFO - evaluator.py - 2024-10-24 15:32:09,460 - Epoch: 34 Train acc: 100.0 Val acc: 97.16 Test acc97.53; Train loss: 4.7117638390442485e-07 Val loss: 0.00016172462403774262
+INFO - evaluator.py - 2024-10-24 15:33:50,139 - Epoch: 35 Train acc: 100.0 Val acc: 97.11999999999999 Test acc97.48; Train loss: 3.6723991070175546e-07 Val loss: 0.00016407718658447267
+INFO - evaluator.py - 2024-10-24 15:35:30,824 - Epoch: 36 Train acc: 100.0 Val acc: 97.11999999999999 Test acc97.46000000000001; Train loss: 2.8759565691209654e-07 Val loss: 0.00016867017447948457
+INFO - evaluator.py - 2024-10-24 15:37:11,537 - Epoch: 37 Train acc: 100.0 Val acc: 97.06 Test acc97.48; Train loss: 2.3957116756553824e-07 Val loss: 0.00016981122195720673
+INFO - evaluator.py - 2024-10-24 15:38:52,521 - Epoch: 38 Train acc: 100.0 Val acc: 97.2 Test acc97.55; Train loss: 2.1594850664273096e-07 Val loss: 0.00017007402181625365
+INFO - evaluator.py - 2024-10-24 15:40:33,283 - Epoch: 39 Train acc: 100.0 Val acc: 97.1 Test acc97.58; Train loss: 1.7740944051845212e-07 Val loss: 0.0001714925229549408
+INFO - evaluator.py - 2024-10-24 15:42:14,059 - Epoch: 40 Train acc: 100.0 Val acc: 97.14 Test acc97.5; Train loss: 1.5827912357880533e-07 Val loss: 0.00017522028386592864
+INFO - evaluator.py - 2024-10-24 15:43:54,761 - Epoch: 41 Train acc: 100.0 Val acc: 97.08 Test acc97.47; Train loss: 1.518896127890912e-07 Val loss: 0.00017669513523578645
+INFO - evaluator.py - 2024-10-24 15:45:35,571 - Epoch: 42 Train acc: 100.0 Val acc: 97.18 Test acc97.5; Train loss: 1.4608784349547932e-07 Val loss: 0.00017541203796863557
+INFO - evaluator.py - 2024-10-24 15:47:16,337 - Epoch: 43 Train acc: 100.0 Val acc: 97.2 Test acc97.5; Train loss: 1.4710992173521928e-07 Val loss: 0.0001758388727903366
+INFO - evaluator.py - 2024-10-24 15:48:56,996 - Epoch: 44 Train acc: 100.0 Val acc: 97.22 Test acc97.52; Train loss: 1.2779035479814577e-07 Val loss: 0.00017774434089660643
+INFO - evaluator.py - 2024-10-24 15:50:37,975 - Epoch: 45 Train acc: 100.0 Val acc: 97.22 Test acc97.53; Train loss: 1.2815259630191247e-07 Val loss: 0.00017803117036819459
+INFO - evaluator.py - 2024-10-24 15:52:18,723 - Epoch: 46 Train acc: 100.0 Val acc: 97.24000000000001 Test acc97.5; Train loss: 1.2376240231539917e-07 Val loss: 0.00017742985188961028
+INFO - evaluator.py - 2024-10-24 15:53:59,531 - Epoch: 47 Train acc: 100.0 Val acc: 97.28 Test acc97.52; Train loss: 1.1628047188258444e-07 Val loss: 0.00017614993751049042
+INFO - evaluator.py - 2024-10-24 15:55:40,572 - Epoch: 48 Train acc: 100.0 Val acc: 97.22 Test acc97.49; Train loss: 1.0853574778428248e-07 Val loss: 0.0001778471201658249
+INFO - evaluator.py - 2024-10-24 15:57:21,350 - Epoch: 49 Train acc: 100.0 Val acc: 97.18 Test acc97.52; Train loss: 1.0627598408477339e-07 Val loss: 0.00017725574374198913
+INFO - evaluator.py - 2024-10-24 15:57:21,353 - The best acc of synthetic images on sensitive val and the corresponding acc on test dataset from resnext is 97.28 and 97.52
+INFO - evaluator.py - 2024-10-24 15:57:21,354 - The best acc of synthetic images on noisy sensitive val and the corresponding acc on test dataset from resnext is 97.28 and 97.52
+INFO - evaluator.py - 2024-10-24 15:57:21,354 - The best acc test dataset from resnext is 97.6
+INFO - evaluator.py - 2024-10-24 15:57:21,354 - The best acc of accuracy (using synthetic images as the validation set) of synthetic images from resnet, wrn, and resnext are [97.59, 97.72, 97.52].
+INFO - evaluator.py - 2024-10-24 15:57:21,354 - The average and std of accuracy of synthetic images are 97.61 and 0.08
+INFO - dataset_loader.py - 2024-10-28 19:02:37,013 - delta is reset as 1.6657508770018431e-06
+INFO - evaluator.py - 2024-10-28 19:03:31,095 - Epoch: 0 Train acc: 69.12727272727273 Val acc: 94.08 Test acc95.15; Train loss: 0.003610309259728952 Val loss: 0.00020137958824634553
+INFO - evaluator.py - 2024-10-28 19:04:08,203 - Epoch: 1 Train acc: 94.11454545454545 Val acc: 95.08 Test acc95.56; Train loss: 0.0007610411929813299 Val loss: 0.00016330405175685883
+INFO - evaluator.py - 2024-10-28 19:04:45,969 - Epoch: 2 Train acc: 95.19090909090909 Val acc: 93.76 Test acc94.3; Train loss: 0.0006185078977183862 Val loss: 0.0002273010313510895
+INFO - evaluator.py - 2024-10-28 19:05:22,683 - Epoch: 3 Train acc: 95.61090909090909 Val acc: 95.78 Test acc96.35000000000001; Train loss: 0.0005558941122483123 Val loss: 0.00014219559133052826
+INFO - evaluator.py - 2024-10-28 19:05:59,209 - Epoch: 4 Train acc: 95.88181818181818 Val acc: 95.88 Test acc96.28; Train loss: 0.0005166368346999992 Val loss: 0.00013682536035776138
+INFO - evaluator.py - 2024-10-28 19:06:36,091 - Epoch: 5 Train acc: 96.14181818181818 Val acc: 94.36 Test acc95.19; Train loss: 0.0004762157352810556 Val loss: 0.00017691964507102965
+INFO - evaluator.py - 2024-10-28 19:07:12,402 - Epoch: 6 Train acc: 96.39636363636363 Val acc: 86.61999999999999 Test acc86.72; Train loss: 0.00045090115009383723 Val loss: 0.0004109108686447144
+INFO - evaluator.py - 2024-10-28 19:07:48,976 - Epoch: 7 Train acc: 96.52727272727273 Val acc: 91.46 Test acc92.47999999999999; Train loss: 0.0004325340936807069 Val loss: 0.0002868983656167984
+INFO - evaluator.py - 2024-10-28 19:08:26,792 - Epoch: 8 Train acc: 96.60727272727273 Val acc: 94.88 Test acc95.75; Train loss: 0.00042463301528583873 Val loss: 0.00019016166031360625
+INFO - evaluator.py - 2024-10-28 19:09:02,359 - Epoch: 9 Train acc: 96.82181818181819 Val acc: 95.26 Test acc96.02000000000001; Train loss: 0.0004006765087897127 Val loss: 0.0001530488520860672
+INFO - evaluator.py - 2024-10-28 19:09:38,380 - Epoch: 10 Train acc: 96.93272727272728 Val acc: 93.62 Test acc94.12; Train loss: 0.00038345492814074864 Val loss: 0.00021184039413928987
+INFO - evaluator.py - 2024-10-28 19:10:13,932 - Epoch: 11 Train acc: 96.97090909090909 Val acc: 91.64 Test acc92.61; Train loss: 0.0003732364243404432 Val loss: 0.00028108850717544555
+INFO - evaluator.py - 2024-10-28 19:10:49,570 - Epoch: 12 Train acc: 96.98909090909092 Val acc: 94.42 Test acc95.07; Train loss: 0.0003648060898211869 Val loss: 0.00019824465215206147
+INFO - evaluator.py - 2024-10-28 19:11:26,072 - Epoch: 13 Train acc: 97.07636363636364 Val acc: 92.4 Test acc93.42; Train loss: 0.0003470562051981688 Val loss: 0.00025030050575733186
+INFO - evaluator.py - 2024-10-28 19:12:01,748 - Epoch: 14 Train acc: 97.07272727272728 Val acc: 92.66 Test acc93.72; Train loss: 0.0003506753576750105 Val loss: 0.0002344325929880142
+INFO - evaluator.py - 2024-10-28 19:12:37,627 - Epoch: 15 Train acc: 97.26363636363637 Val acc: 90.46 Test acc91.34; Train loss: 0.00032147990194233983 Val loss: 0.0003249340832233429
+INFO - evaluator.py - 2024-10-28 19:13:13,690 - Epoch: 16 Train acc: 97.43454545454546 Val acc: 85.44 Test acc85.75; Train loss: 0.0003175170399587263 Val loss: 0.00043171316385269163
+INFO - evaluator.py - 2024-10-28 19:13:49,771 - Epoch: 17 Train acc: 97.42545454545454 Val acc: 93.0 Test acc94.15; Train loss: 0.0003089175983247432 Val loss: 0.00024124562442302705
+INFO - evaluator.py - 2024-10-28 19:14:25,495 - Epoch: 18 Train acc: 97.56727272727272 Val acc: 88.74 Test acc89.48; Train loss: 0.00028715897405689415 Val loss: 0.00036829556226730345
+INFO - evaluator.py - 2024-10-28 19:15:00,850 - Epoch: 19 Train acc: 97.66 Val acc: 87.83999999999999 Test acc88.53999999999999; Train loss: 0.0002736184494739229 Val loss: 0.00035601123571395876
+INFO - evaluator.py - 2024-10-28 19:15:36,407 - Epoch: 20 Train acc: 98.59272727272727 Val acc: 96.44 Test acc97.25; Train loss: 0.00016667699541219257 Val loss: 0.00010739440619945527
+INFO - evaluator.py - 2024-10-28 19:16:11,172 - Epoch: 21 Train acc: 98.95272727272727 Val acc: 97.42 Test acc97.75; Train loss: 0.00012728704660284248 Val loss: 9.381439536809921e-05
+INFO - evaluator.py - 2024-10-28 19:16:46,721 - Epoch: 22 Train acc: 99.05636363636363 Val acc: 96.84 Test acc97.49; Train loss: 0.00011237557821653106 Val loss: 0.00011908593624830245
+INFO - evaluator.py - 2024-10-28 19:17:22,279 - Epoch: 23 Train acc: 99.25090909090909 Val acc: 96.3 Test acc96.94; Train loss: 9.12512610073794e-05 Val loss: 0.00016437128186225892
+INFO - evaluator.py - 2024-10-28 19:17:58,502 - Epoch: 24 Train acc: 99.33090909090909 Val acc: 95.89999999999999 Test acc96.21; Train loss: 7.799424947324124e-05 Val loss: 0.00020532554686069487
+INFO - evaluator.py - 2024-10-28 19:18:34,523 - Epoch: 25 Train acc: 99.40363636363637 Val acc: 96.22 Test acc96.61; Train loss: 7.06739854067564e-05 Val loss: 0.00018941760063171387
+INFO - evaluator.py - 2024-10-28 19:19:10,956 - Epoch: 26 Train acc: 99.41636363636364 Val acc: 96.36 Test acc97.11; Train loss: 6.60195914181796e-05 Val loss: 0.0001780856966972351
+INFO - evaluator.py - 2024-10-28 19:19:46,625 - Epoch: 27 Train acc: 99.49818181818182 Val acc: 95.96000000000001 Test acc96.6; Train loss: 5.5945185235362836e-05 Val loss: 0.00021610855162143707
+INFO - evaluator.py - 2024-10-28 19:20:22,077 - Epoch: 28 Train acc: 99.43636363636364 Val acc: 96.89999999999999 Test acc97.24000000000001; Train loss: 5.912750019395555e-05 Val loss: 0.00015779561400413512
+INFO - evaluator.py - 2024-10-28 19:20:57,561 - Epoch: 29 Train acc: 99.57818181818182 Val acc: 96.39999999999999 Test acc96.99; Train loss: 4.912246290636672e-05 Val loss: 0.00017162129282951354
+INFO - evaluator.py - 2024-10-28 19:21:32,465 - Epoch: 30 Train acc: 99.65454545454546 Val acc: 96.88 Test acc97.5; Train loss: 3.908351953458888e-05 Val loss: 0.00015799909681081772
+INFO - evaluator.py - 2024-10-28 19:22:07,890 - Epoch: 31 Train acc: 99.55636363636363 Val acc: 96.48 Test acc96.98; Train loss: 4.81307567012581e-05 Val loss: 0.000205861234664917
+INFO - dataset_loader.py - 2024-10-28 19:23:03,769 - delta is reset as 1.6657508770018431e-06
+INFO - evaluator.py - 2024-10-28 22:05:48,605 - The FID of synthetic images is 5.299168517870299
+INFO - evaluator.py - 2024-10-28 22:05:48,615 - The Inception Score of synthetic images is 2.0705909729003906
+INFO - evaluator.py - 2024-10-28 22:05:48,615 - The Precision and Recall of synthetic images is 0.6196718811988831 and 0.7205166816711426
+INFO - evaluator.py - 2024-10-28 22:05:48,615 - The FLD of synthetic images is 3.6166906356811523
+INFO - evaluator.py - 2024-10-28 22:05:48,615 - The ImageReward of synthetic images is -2.0137405571872367
+INFO - dataset_loader.py - 2024-10-28 22:46:40,279 - delta is reset as 1.6657508770018431e-06
+INFO - dataset_loader.py - 2024-10-29 10:14:57,630 - delta is reset as 1.5148623360286113e-06
+INFO - evaluator.py - 2024-10-29 11:06:17,358 - The FID of synthetic images is 5.286480673016143
+INFO - evaluator.py - 2024-10-29 11:06:17,363 - The Inception Score of synthetic images is 2.071159601211548
+INFO - evaluator.py - 2024-10-29 11:06:17,363 - The Precision and Recall of synthetic images is 0.6194375157356262 and 0.7204999923706055
+INFO - evaluator.py - 2024-10-29 11:06:17,364 - The FLD of synthetic images is 3.7299275398254395
+INFO - evaluator.py - 2024-10-29 11:06:17,364 - The ImageReward of synthetic images is -2.0137405606759713
+INFO - dataset_loader.py - 2024-10-29 11:06:17,775 - delta is reset as 4.329102935418938e-06
+INFO - evaluator.py - 2024-10-29 11:39:57,591 - The FID of synthetic images is 168.59217462930627
+INFO - evaluator.py - 2024-10-29 11:39:57,596 - The Inception Score of synthetic images is 1.6652277708053589
+INFO - evaluator.py - 2024-10-29 11:39:57,596 - The Precision and Recall of synthetic images is 0.6194375157356262 and 0.00952173862606287
+INFO - evaluator.py - 2024-10-29 11:39:57,596 - The FLD of synthetic images is 20.778346061706543
+INFO - evaluator.py - 2024-10-29 11:39:57,596 - The ImageReward of synthetic images is -1.5740511079076678
+INFO - dataset_loader.py - 2024-10-29 11:39:58,114 - delta is reset as 1.8484667129285888e-06
+INFO - evaluator.py - 2024-10-29 12:12:19,140 - The FID of synthetic images is 231.37436795903784
+INFO - evaluator.py - 2024-10-29 12:12:19,145 - The Inception Score of synthetic images is 1.7306236028671265
+INFO - evaluator.py - 2024-10-29 12:12:19,145 - The Precision and Recall of synthetic images is 0.7602222561836243 and 0.00043999997433274984
+INFO - evaluator.py - 2024-10-29 12:12:19,145 - The FLD of synthetic images is 23.48649501800537
+INFO - evaluator.py - 2024-10-29 12:12:19,146 - The ImageReward of synthetic images is -2.2615407764571054
+INFO - dataset_loader.py - 2024-10-29 12:12:19,367 - delta is reset as 4.329102935418938e-06
+INFO - evaluator.py - 2024-10-29 12:45:16,662 - The FID of synthetic images is 237.36948091544997
+INFO - evaluator.py - 2024-10-29 12:45:16,666 - The Inception Score of synthetic images is 1.2807329893112183
+INFO - evaluator.py - 2024-10-29 12:45:16,667 - The Precision and Recall of synthetic images is 0.5577656626701355 and 4.347825961303897e-05
+INFO - evaluator.py - 2024-10-29 12:45:16,667 - The FLD of synthetic images is 30.49933910369873
+INFO - evaluator.py - 2024-10-29 12:45:16,667 - The ImageReward of synthetic images is -1.8509714604625478
+INFO - dataset_loader.py - 2024-10-29 12:45:17,305 - delta is reset as 1.5148623360286113e-06
+INFO - evaluator.py - 2024-10-29 13:18:11,048 - The FID of synthetic images is 53.50594213505724
+INFO - evaluator.py - 2024-10-29 13:18:11,054 - The Inception Score of synthetic images is 3.4386539459228516
+INFO - evaluator.py - 2024-10-29 13:18:11,055 - The Precision and Recall of synthetic images is 0.26606249809265137 and 0.12056666612625122
+INFO - evaluator.py - 2024-10-29 13:18:11,055 - The FLD of synthetic images is 20.395588874816895
+INFO - evaluator.py - 2024-10-29 13:18:11,055 - The ImageReward of synthetic images is -1.8617446345779531
+INFO - dataset_loader.py - 2024-10-29 13:18:11,648 - delta is reset as 1.5148623360286113e-06
+INFO - evaluator.py - 2024-10-29 13:50:35,681 - The FID of synthetic images is 4.446889068230405
+INFO - evaluator.py - 2024-10-29 13:50:35,832 - The Inception Score of synthetic images is 2.0761497020721436
+INFO - evaluator.py - 2024-10-29 13:50:35,832 - The Precision and Recall of synthetic images is 0.6322698593139648 and 0.7390333414077759
+INFO - evaluator.py - 2024-10-29 13:50:35,833 - The FLD of synthetic images is 3.283095359802246
+INFO - evaluator.py - 2024-10-29 13:50:35,833 - The ImageReward of synthetic images is -2.0057078354216755
+INFO - dataset_loader.py - 2024-10-29 13:50:37,371 - delta is reset as 5.11965868690912e-07
+INFO - evaluator.py - 2024-10-29 14:31:49,267 - The FID of synthetic images is 28.848900967099837
+INFO - evaluator.py - 2024-10-29 14:31:49,353 - The Inception Score of synthetic images is 2.238304853439331
+INFO - evaluator.py - 2024-10-29 14:31:49,353 - The Precision and Recall of synthetic images is 0.6088594198226929 and 0.1520366072654724
+INFO - evaluator.py - 2024-10-29 14:31:49,354 - The FLD of synthetic images is nan
+INFO - evaluator.py - 2024-10-29 14:31:49,354 - The ImageReward of synthetic images is -1.3833920579410202
+INFO - dataset_loader.py - 2024-10-29 14:31:49,986 - delta is reset as 1.8484667129285888e-06
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/checkpoints/final_checkpoint.pth b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/checkpoints/final_checkpoint.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ab9191dfe9fb9aae3af0a83392f84e3903e99df3
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/checkpoints/final_checkpoint.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52dd94582ed1d97706a3609b13b17ebdde11b6dd97e34f6f06f11a375771dfb4
+size 24084886
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/checkpoints/snapshot_checkpoint.pth b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/checkpoints/snapshot_checkpoint.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b114668af5d59d5fcfd10df542cb2f53abf543ec
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/checkpoints/snapshot_checkpoint.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99ce8f2a4d550829734522698e10f47a5a33890a5106660f7eb661bd8d201ee3
+size 24088033
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_10000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_10000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..5a54fc83f5508ea4dcdcb40ba3090c360e98f471
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_10000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7616784fdc1fa3c9ab145f6686eb05d99ca5967139cac59576c33808b785b06
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_10000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_10000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..92fe8eaa874df192b068b059d1bfbad1d17285bc
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_10000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4be7710c08d03d0e90735f603a5d073a5f24776729b49f3b844451a911b8e068
+size 146247
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_12000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_12000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..12e5b7278816140a69c04bfd278c9418472f4a8d
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_12000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2acbbb0e5eee4fcc45798d06cbb5e289621f7e8b43efdccb21c0a2fdd545aab2
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_12000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_12000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..c7b5bcfde865aed12653f056826b15ccae494f6d
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_12000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43b111a7ee740e3835d7df059b83c429d657ab5e05f1c58c7eb7c5d2d7dfe807
+size 143467
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_14000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_14000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..3a766c74b0818c517bfa68e8463ea6cea0b23e53
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_14000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1185d97237bb3615000a219aa7d9c3320a8e48bfb65fd2290d61329e8d48202
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_14000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_14000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..4bad4dbcdd1dfe43f6e6ece955077c39dfe4fce1
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_14000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be09ac4fada352e3deb5d73f2cab15c661adf607d10e5c48f4643d1ce3512d5c
+size 140260
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_16000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_16000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..3882865c435a8aacd5df4d6eb38d1ade1b25aafd
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_16000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b82504ae3151edd514b33e0fffde74298e8bc46b4924a15681bf18cf439a958a
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_16000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_16000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..763868238e7f2ed0e4450b664c0582a34b60d0a9
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_16000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9a628968f36735d3cde1259f9b82ff79b41dcecb6a6033c44453e0123cfe868
+size 136855
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_18000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_18000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..6eb142cab41ba492a593d55b47666303085efd5d
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_18000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3eff82e2263e8f916a8aa9dbb15fefb008267b7fcdb5cd90928fc37ee84735f8
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_18000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_18000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..f7037089bdafac35b3b70780b4f37888bf0cdde2
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_18000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee8f1f8168e45ed4a293caf28f7a6afc435fbb2e0a6b5c7f2f946f6012566979
+size 140465
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_2000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_2000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..560c6a5a26a24fc3f39341066c3198e91a8a5779
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_2000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4402598a6d0d6710bde0f5cdf89a3f2f676b84191dc0bd7dfa7cbf290a2adaee
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_2000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_2000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..25b33ae49eb2f9cdaecff4c8863f496e05c0640a
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_2000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c256d1ecba013ad5655dc72839e3769034131cf0d5c6e8fddc4dd58bdaf9b6e
+size 211577
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_20000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_20000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..4eb162e4b752a9af91f195de98d2db84f28247af
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_20000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01bcbc202ed081a7ae9b0817af98a2319d49062b3b13f9655d40258fd2990041
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_20000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_20000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..868378788479c1ca46bff78eef38f7f2ccd1e93a
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_20000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9273160d60a30098b6908cfac4352053e13440b42cb5d6e1ade5828fea8bc0f7
+size 135648
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_22000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_22000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..5ffee18ecdec1fa355f635c294eb81666bf36db2
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_22000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef6da70643ebc834edfd0155c971191ea8bc87a5580844443f02230e73ddc309
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_22000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_22000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..03c8d8dd566396a14855cce6a9fec2f4d83cd171
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_22000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e86504045bb6fbfd6dbe4476cb419ec48a062aa474541eca722e040a21d2a3e8
+size 140021
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_24000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_24000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..132a3937dc62618fa5000282bb9a33e20b421382
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_24000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df521d4b76e447fb3af3e50357466d0896a81ed99b4a7e88f21aa929055de6f5
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_24000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_24000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..b9dc361a153c94ad140ea93ddfa1aa65f0be7408
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_24000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb3f71b916ae97f73910e2ffed7d28d6ddfc5b2b20c864454052074956f03e7c
+size 137814
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_26000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_26000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..f70f54686f3afd4e655a9b147d61bbf11aa0b5ba
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_26000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e4c406e373946d70ea57c97fa6950f1e0c2e2f3231cba14d98d4d99289b387b
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_26000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_26000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..c5a1b4f817929b2384a4f6cb86c9f62f655965bf
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_26000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9520d4cd9a48e36369b3e33b82614e0fe06d8741f867423ad4281015a7c9be30
+size 136497
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_28000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_28000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..fcdeec8ff9ee1db9c62a2ace9135b0a6895346c2
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_28000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da3160dddccd577c5cd2278319592ba0f0c1b9d07f0bccf5359749635c6e40b3
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_28000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_28000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..ed1043b3795905eda52b43e4eab00216e5cc6d06
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_28000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcd688216884b88430ea25fffba29428336399b078aea6f374a576480b138543
+size 134552
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_30000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_30000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..9abb68df0497fb4e435b82971c841bc3b94158dc
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_30000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09ba55f9d76279913aa4e6d3d5ecb53eb387fbb36e23db7be36b206114138551
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_30000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_30000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..f84a7e5190ec4d7395fc5b59574798a4164b1e2b
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_30000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f234fe824ac09f7aab0a8d5a3d480686c86ca10f65dc440f56f932ff392b6cf1
+size 134054
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_32000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_32000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..4ae8b6ca29c296721d4cdd9cb53514fc01a4fdf3
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_32000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd88535cad55595ee10616049ea308b7deae04a7017c4e422449157edf250034
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_32000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_32000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..b587b45ee2b221fb3efa793f78e8dfe7fbc9efc9
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_32000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f24b84625a4c8e8714eb67a180e584e10c24719d5c47838c10cb0984ba013be2
+size 132994
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_34000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_34000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..ad00e48bf8284e941c3c3cea3cdf4db36d413af0
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_34000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3979065c475270197267ede01a83708488ab081918bf6194b8d18a4c2f39715
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_34000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_34000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..e6b29b4ab30814950eda8d139f8c65ea6cbc015d
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_34000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95dbb57eda179f8b771a28569439e003948bbeea22fe8856a74ffe80d7cc5e44
+size 129848
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_36000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_36000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..8cd1a1aecd16706ddff394fe7376ba0de23330c4
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_36000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11ffa0c0d52d9f847f0e007a7230c687683c48b5fb920798a2821caea47f501f
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_36000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_36000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..b36690f2df1df39e1b5ba88708f501514140b0ba
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_36000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c18155c289539999e83abd097074a85106372754da789ae32dd6f2a6915a9c28
+size 133693
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_38000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_38000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..987de8ea5f0dccdc4bab75e3924c27e4f27460c5
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_38000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ecc98228cb0c78f6af09ef7442ab88cb85b96358036b1c02e9838559cb5cccc
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_38000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_38000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..e632491544d537ad1e6bcb649c4786ed324a01de
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_38000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5ea144a9eb5005f5c961a4d31d41d7b076bdef41b6e0eea3fcddb16336dc302
+size 128465
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_4000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_4000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..f6b5845789e1b2aebbb3d441d4681f2cc6823ee9
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_4000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07b565410c02203612e099c700caccc1e42dc8dcb6cb2408693dd2ad3248fbd9
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_4000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_4000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..f1241c29ddedebb09b92cf749c6b7555b7e0b749
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_4000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f642625243a1e50b1c66694d610fcc11dfbf8ac495001cd91f2040a73f2fedf6
+size 171279
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_40000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_40000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..9645e37ae32d139fae9ab9cae55b6ebcd6582167
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_40000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd9be995918b7ca997c188308eb3d02276ad23a0239ffae8389c2b1feae17311
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_40000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_40000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..4106ce8bcbe7311472ce2375e280309e7176869d
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_40000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35264158adcf33b5aa232b74cc5656777e972b6409884c345a382debcecf318e
+size 127509
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_42000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_42000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..f9d46872c17efaa16985c4a828aa0bf30f2c0b75
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_42000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7308d147523577c618bd97f0ea78179897ac2798332320289a36ac3986b5520d
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_42000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_42000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..5fea16f297932f9358334725d22acb834ac4f9ab
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_42000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c823ebb0687a6040c3cfa036f39a4947997a005910e2325c71dfe5d1d1499c51
+size 132541
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_44000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_44000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..f21ddd4420d0dcb91b10ef55cc3b04353b18eb90
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_44000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15d340feb4a2402162f72127dc0529aaeefc379a2892555c0e0a0145239f4d09
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_44000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_44000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..ec6128d804825d99804767f5d838c8a7c0ccf55e
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_44000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14f3638fa2c875e463d825f963b55ef1f016647f7738cbabf182ad916b3751ab
+size 127990
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_46000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_46000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..12a90ddfee871e38c9c45a901db4cc8fe36e8fae
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_46000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7daff6c0316112ccf69f1335f8c6e169ad1ca096d3d1fe3a01983a801526567
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_46000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_46000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..f9673a6b99885305cd25cd7eee21f688cd8fa449
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_46000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:272ffd2ff87895d9c21a17bdc462ccc9fd7c2e23804e07283966f1ee1f934245
+size 129757
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_48000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_48000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..44f4d6c54e3aea62996b5dcbe322a4c059e6dcfc
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_48000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d13cd4698bd4e19cae26c04f3805d1f3bf4cda8c916576d6315174525b7765a6
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_48000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_48000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..598ee98d2cec6ee4b15de6c44a2fe204bb2a60b2
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_48000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab1ed9d5e00f3815153d7effff5223e2931363729eac6cbc83250fb2c8ecddce
+size 132137
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_50000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_50000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..24ed72f44e760e7cc3d3bf9d2757bef68765828d
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_50000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b262cb9e52d573401b5e60c6dc00585d2237e5464d9b1d0c077b0bfa197106fd
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_50000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_50000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..f3349b4a03fee8f9db59d47dfb2ae6d9cd7aa971
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_50000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7069f928524e976bb6526f4b25da4dbe673ad70ab21ddf439e1b9043e71c8151
+size 127152
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_52000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_52000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..707e86077e9e9383ec27c1e769602d9cc6a374c7
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_52000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f154616323b69b617f0e08ad5a580981de4177e54c968d818217e62fbf7ba305
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_52000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_52000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..d9ba3856e14e94a86b1b54a4446dd59433514a22
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_52000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fc513267e7f17ac99a247e1f475aafddd33669819e10c72bedb9dfede04c3e3
+size 129331
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_54000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_54000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..4f0d96bfe35a516299a3d436b26e0f5ee4939a9c
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_54000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7421a0ef4e8a62424ca2447144f4d77a85a903966a4d7dcb6af4151d0a1a1f2a
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_54000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_54000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..7adabe000d0394915eee15e66e33d465207b6a29
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_54000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf7af0787b728d4d842f1641451248357502d4fe844a6715f4bf1fb6f06c85f1
+size 121538
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_56000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_56000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..d3408e31872b590025fa753c61ea6f1e9179a78d
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_56000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:553765926c9c98bc1f048b266054e31f3a7b2c6c4274b1bc86f214c5b97c5486
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_56000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_56000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..006ae29dfc18edaff6031d6ff6bfad48154d5124
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_56000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:630bf527a0817b33618c19f430d0ea78d4971f88aac78e42274c3188aa6196de
+size 126852
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_58000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_58000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..ab46f42475597ea806612ec1c71c1ed91c6a4149
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_58000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d313307109a22c84c11a503243aff3442b19463c4972dc79d16b705b0ac809ba
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_58000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_58000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..12d2dd7142e0c0bdff6f07699a9ead92b2de5ce8
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_58000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec72efa8e8a8a5a4399eb7777675ae364fe34b16d120e679826405d38f9a575d
+size 127801
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_6000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_6000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..dea2d8dae7362d581ebbc0c8f9b2c638ad626706
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_6000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:336b292850eb17f15b13d453d67ce861c88fbfb81c9f00821f359448ccc699b1
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_6000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_6000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..2be2da7fb722d2b6011a30329f04c67a7f9f08c4
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_6000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6568a4bef3a6e83f7c5e0bd3017600e34fa750e23efda4eaed3f2e6f4f8b3f4b
+size 157574
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_60000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_60000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..870ae530964e36065a65882cb05f76073bd16715
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_60000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a440cd32335ccab87226e4903c77a246a0cc51aab07b7ec4e60530c9fee857c
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_60000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_60000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..667f9837671d47e7e796d2994935fe3b977d380e
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_60000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0b8aa270348e601d9d680289e35b729fd9233463a03122296c6f85f533ea616
+size 125666
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_62000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_62000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..884a5b7198cc7022604b21b0b980c73b61d8c6ca
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_62000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e4ea0199bd5c1e1c91de62b8ba4a759beb8f6e2bf98f68d81218a7be1658b35
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_62000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_62000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..a7a2e7f69ea0df23586016bf4acf5ac3552864f4
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_62000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d993f00299f81dc72fa90854b63b9a057a5ad9c1a59821f1aa04ef807ef25ae3
+size 125368
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_64000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_64000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..455c7bc1beb9a61ce749fbc02e8502ce6410144a
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_64000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf540974442cf848bcc4302c96dd0f2df3fe9bd1927a210618032208aafd1cda
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_64000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_64000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..24fc110abf222ca858b1c5252c245c95deca89e3
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_64000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d4e968caf448aa417f1b01d43ee67418ab0281b7e652ba6a5a4ea57c3711d57
+size 124926
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_66000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_66000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..068bf06f5d286a6558156eea9303e8ae47fd7c75
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_66000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c342c020f24c4a77c79446339d749080742b3a68b2d299fd4b1c99b8b2bed4f8
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_66000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_66000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..fff20c57933609e3b12a6424aaccf812a4657954
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_66000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f613f4c9c2e5876efb3e117f65b9e229c2a767920f4da7982b97754503d75a8
+size 125510
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_8000/sample.npy b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_8000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..a35ff623e4177e4612cd513da1afdc2a12e1b3d5
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_8000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:014483d36ba3686d5ec6adaae043290b7fc28371c04af155fa514414e803917a
+size 251008
diff --git a/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_8000/sample.png b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_8000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..669ec626f8773debe650c16f239ae45c84960b93
--- /dev/null
+++ b/dpdm/mnist_28_eps10.0trainval-2024-10-22-22-42-07/train/samples/iter_8000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37148dd95678c0d78ebab2b2ceb2612c299cac6138e40a0abc03ff6629853473
+size 148785