diff --git a/.gitattributes b/.gitattributes
index fa5d1efd5776556cc674c88c8694117b884788a7..9602ec5f2bf8b5653db7bce2477f3c15537815d9 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -1162,3 +1162,55 @@ dpdm/eurosat_32_eps1.0trainval-2024-10-24-13-38-47/train/samples/iter_54000/samp
 dpdm/eurosat_32_eps1.0trainval-2024-10-24-13-38-47/train/samples/iter_56000/sample.png filter=lfs diff=lfs merge=lfs -text
 dpdm/eurosat_32_eps1.0trainval-2024-10-24-13-38-47/train/samples/iter_6000/sample.png filter=lfs diff=lfs merge=lfs -text
 dpdm/eurosat_32_eps1.0trainval-2024-10-24-13-38-47/train/samples/iter_8000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_10000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_100000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_102000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_104000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_12000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_14000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_16000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_18000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_2000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_20000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_22000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_24000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_26000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_28000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_30000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_32000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_34000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_36000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_38000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_4000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_40000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_42000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_44000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_46000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_48000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_50000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_52000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_54000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_56000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_58000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_6000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_60000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_62000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_64000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_66000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_68000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_70000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_72000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_74000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_76000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_78000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_8000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_80000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_82000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_84000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_86000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_88000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_90000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_92000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_94000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_96000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_98000/sample.png filter=lfs diff=lfs merge=lfs -text
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/stdout.txt b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/stdout.txt
new file mode 100644
index 0000000000000000000000000000000000000000..6f5497c0c910bf132fd0c8f204c476745527af99
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/stdout.txt
@@ -0,0 +1,1988 @@
+INFO - utils.py - 2025-03-24 08:04:55,409 - {'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/cifar100_32_eps10.0val-2025-03-24-08-04-47', 'local_rank': 0, 'global_rank': 0, 'global_size': 4, 'root_folder': '.'}, 'public_data': {'name': None, 'num_channels': 3, 'resolution': 32, 'n_classes': 1000, 'train_path': 'dataset/imagenet/imagenet_32', 'selective': {'ratio': 1.0}}, 'sensitive_data': {'name': 'cifar100', 'num_channels': 3, 'resolution': 32, 'n_classes': 100, 'train_path': 'dataset/cifar100/train_32.zip', 'test_path': 'dataset/cifar100/test_32.zip', 'fid_stats': 'dataset/cifar100/fid_stats_32.npz'}, 'model': {'ckpt': None, 'denoiser_name': 'edm', 'denoiser_network': 'song', 'ema_rate': 0.999, 'network': {'image_size': 32, 'num_in_channels': 3, 'num_out_channels': 3, 'label_dim': 1000, 'attn_resolutions': [16], 'ch_mult': [2, 4]}, 'sampler': {'type': 'ddim', 'stochastic': False, 'num_steps': 50, 'tmin': 0.002, 'tmax': 80.0, 'rho': 7.0, 'guid_scale': 0.0, 'snapshot_batch_size': 80, 'fid_batch_size': 256}, 'sampler_fid': {'type': 'ddim', 'stochastic': False, 'num_steps': 250, 'tmin': 0.002, 'tmax': 80.0, 'rho': 7.0, 'guid_scale': 0.0}, 'sampler_acc': {'type': 'ddim', 'stochastic': False, 'num_steps': 250, 'tmin': 0.002, 'tmax': 80.0, 'rho': 7.0, 'guid_scale': 0.0}, 'private_num_classes': 100, 'public_num_classes': 100, 'local_rank': 0, 'global_rank': 0, 'global_size': 4, 'fid_stats': 'dataset/cifar100/fid_stats_32.npz'}, 'pretrain': {'log_dir': 'exp/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/pretrain', 'seed': 0, 'batch_size': 1024, 'n_epochs': 160, 'log_freq': 100, 'snapshot_freq': 2000, 'snapshot_threshold': 1, 'save_freq': 100000, 'save_threshold': 1, 'fid_freq': 2000, 'fid_samples': 5000, 'fid_threshold': 1, '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': 1000}, 'cond': True}, 'train': {'log_dir': 'exp/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train', 'seed': 0, 'batch_size': 4096, 'n_epochs': 150, 'partly_finetune': False, 'log_freq': 100, 'snapshot_freq': 2000, 'snapshot_threshold': 1, 'save_freq': 100000, 'save_threshold': 1, 'fid_freq': 2000, 'fid_samples': 5000, 'final_fid_samples': 60000, 'fid_threshold': 1, 'gen': False, 'gen_batch_size': 8192, 'optim': {'optimizer': 'Adam', 'params': {'lr': 0.0003, 'weight_decay': 0.0}}, 'loss': {'version': 'edm', 'p_mean': -1.2, 'p_std': 1.2, 'n_noise_samples': 32, 'n_classes': 100}, 'dp': {'max_grad_norm': 0.001, 'delta': 1e-05, 'epsilon': 10.0, 'max_physical_batch_size': 8192, 'privacy_history': None}, 'n_splits': 64}, 'gen': {'data_num': 60000, 'batch_size': 1000, 'log_dir': 'exp/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/gen', 'n_classes': 100}, 'eval': {'batch_size': 1000, 'mode': 'val'}}
+INFO - dataset_loader.py - 2025-03-24 08:05:00,456 - train size: 45000 val size: 5000
+INFO - dataset_loader.py - 2025-03-24 08:05:00,457 - delta is reset as 2.07404851125286e-06
+INFO - dpsgd_diffusion.py - 2025-03-24 08:05:02,416 - Number of trainable parameters in model: 3838499
+INFO - dpsgd_diffusion.py - 2025-03-24 08:05:02,416 - Number of total epochs: 150
+INFO - dpsgd_diffusion.py - 2025-03-24 08:05:02,417 - Starting training at step 0
+INFO - dpsgd_diffusion.py - 2025-03-24 08:06:24,766 - Loss: 0.9015, step: 100
+INFO - dpsgd_diffusion.py - 2025-03-24 08:07:19,309 - Loss: 0.8179, step: 200
+INFO - dpsgd_diffusion.py - 2025-03-24 08:08:11,385 - Loss: 0.8907, step: 300
+INFO - dpsgd_diffusion.py - 2025-03-24 08:09:05,442 - Loss: 0.8115, step: 400
+INFO - dpsgd_diffusion.py - 2025-03-24 08:09:57,483 - Loss: 0.7950, step: 500
+INFO - dpsgd_diffusion.py - 2025-03-24 08:10:49,282 - Loss: 0.8563, step: 600
+INFO - dpsgd_diffusion.py - 2025-03-24 08:11:40,269 - Loss: 0.8007, step: 700
+INFO - dpsgd_diffusion.py - 2025-03-24 08:11:42,328 - Eps-value after 1 epochs: 0.8449
+INFO - dpsgd_diffusion.py - 2025-03-24 08:12:33,228 - Loss: 0.7650, step: 800
+INFO - dpsgd_diffusion.py - 2025-03-24 08:13:25,411 - Loss: 0.7767, step: 900
+INFO - dpsgd_diffusion.py - 2025-03-24 08:14:17,030 - Loss: 0.7524, step: 1000
+INFO - dpsgd_diffusion.py - 2025-03-24 08:15:07,692 - Loss: 0.7390, step: 1100
+INFO - dpsgd_diffusion.py - 2025-03-24 08:15:59,738 - Loss: 0.6842, step: 1200
+INFO - dpsgd_diffusion.py - 2025-03-24 08:16:51,418 - Loss: 0.6930, step: 1300
+INFO - dpsgd_diffusion.py - 2025-03-24 08:17:42,096 - Loss: 0.6912, step: 1400
+INFO - dpsgd_diffusion.py - 2025-03-24 08:17:46,174 - Eps-value after 2 epochs: 1.1114
+INFO - dpsgd_diffusion.py - 2025-03-24 08:18:34,916 - Loss: 0.6639, step: 1500
+INFO - dpsgd_diffusion.py - 2025-03-24 08:19:25,316 - Loss: 0.6267, step: 1600
+INFO - dpsgd_diffusion.py - 2025-03-24 08:20:17,573 - Loss: 0.5983, step: 1700
+INFO - dpsgd_diffusion.py - 2025-03-24 08:21:09,166 - Loss: 0.6183, step: 1800
+INFO - dpsgd_diffusion.py - 2025-03-24 08:22:00,844 - Loss: 0.6144, step: 1900
+INFO - dpsgd_diffusion.py - 2025-03-24 08:22:53,054 - Loss: 0.5585, step: 2000
+INFO - dpsgd_diffusion.py - 2025-03-24 08:22:53,093 - Saving snapshot checkpoint and sampling single batch at iteration 2000.
+WARNING - image.py - 2025-03-24 08:22:54,535 - 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 - 2025-03-24 08:23:26,257 - FID at iteration 2000: 377.340630
+INFO - dpsgd_diffusion.py - 2025-03-24 08:24:16,596 - Loss: 0.5580, step: 2100
+INFO - dpsgd_diffusion.py - 2025-03-24 08:24:22,673 - Eps-value after 3 epochs: 1.3227
+INFO - dpsgd_diffusion.py - 2025-03-24 08:25:07,734 - Loss: 0.6024, step: 2200
+INFO - dpsgd_diffusion.py - 2025-03-24 08:25:58,295 - Loss: 0.5932, step: 2300
+INFO - dpsgd_diffusion.py - 2025-03-24 08:26:52,632 - Loss: 0.5300, step: 2400
+INFO - dpsgd_diffusion.py - 2025-03-24 08:27:44,921 - Loss: 0.5384, step: 2500
+INFO - dpsgd_diffusion.py - 2025-03-24 08:28:35,404 - Loss: 0.5234, step: 2600
+INFO - dpsgd_diffusion.py - 2025-03-24 08:29:26,372 - Loss: 0.4881, step: 2700
+INFO - dpsgd_diffusion.py - 2025-03-24 08:30:16,111 - Loss: 0.4846, step: 2800
+INFO - dpsgd_diffusion.py - 2025-03-24 08:30:24,129 - Eps-value after 4 epochs: 1.5065
+INFO - dpsgd_diffusion.py - 2025-03-24 08:31:09,191 - Loss: 0.4855, step: 2900
+INFO - dpsgd_diffusion.py - 2025-03-24 08:32:00,128 - Loss: 0.4748, step: 3000
+INFO - dpsgd_diffusion.py - 2025-03-24 08:32:52,268 - Loss: 0.4574, step: 3100
+INFO - dpsgd_diffusion.py - 2025-03-24 08:33:45,577 - Loss: 0.4528, step: 3200
+INFO - dpsgd_diffusion.py - 2025-03-24 08:34:37,966 - Loss: 0.4469, step: 3300
+INFO - dpsgd_diffusion.py - 2025-03-24 08:35:30,039 - Loss: 0.4515, step: 3400
+INFO - dpsgd_diffusion.py - 2025-03-24 08:36:21,394 - Loss: 0.4258, step: 3500
+INFO - dpsgd_diffusion.py - 2025-03-24 08:36:31,440 - Eps-value after 5 epochs: 1.6699
+INFO - dpsgd_diffusion.py - 2025-03-24 08:37:14,069 - Loss: 0.4028, step: 3600
+INFO - dpsgd_diffusion.py - 2025-03-24 08:38:05,391 - Loss: 0.4076, step: 3700
+INFO - dpsgd_diffusion.py - 2025-03-24 08:38:58,752 - Loss: 0.3739, step: 3800
+INFO - dpsgd_diffusion.py - 2025-03-24 08:39:50,200 - Loss: 0.4297, step: 3900
+INFO - dpsgd_diffusion.py - 2025-03-24 08:40:40,616 - Loss: 0.4092, step: 4000
+INFO - dpsgd_diffusion.py - 2025-03-24 08:40:40,622 - Saving snapshot checkpoint and sampling single batch at iteration 4000.
+WARNING - image.py - 2025-03-24 08:40:41,214 - 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 - 2025-03-24 08:41:09,507 - FID at iteration 4000: 410.447745
+INFO - dpsgd_diffusion.py - 2025-03-24 08:42:01,354 - Loss: 0.4231, step: 4100
+INFO - dpsgd_diffusion.py - 2025-03-24 08:42:53,506 - Loss: 0.3577, step: 4200
+INFO - dpsgd_diffusion.py - 2025-03-24 08:43:05,675 - Eps-value after 6 epochs: 1.8209
+INFO - dpsgd_diffusion.py - 2025-03-24 08:43:44,483 - Loss: 0.3913, step: 4300
+INFO - dpsgd_diffusion.py - 2025-03-24 08:44:35,924 - Loss: 0.3722, step: 4400
+INFO - dpsgd_diffusion.py - 2025-03-24 08:45:27,629 - Loss: 0.3796, step: 4500
+INFO - dpsgd_diffusion.py - 2025-03-24 08:46:21,797 - Loss: 0.3820, step: 4600
+INFO - dpsgd_diffusion.py - 2025-03-24 08:47:12,959 - Loss: 0.3973, step: 4700
+INFO - dpsgd_diffusion.py - 2025-03-24 08:48:04,469 - Loss: 0.3476, step: 4800
+INFO - dpsgd_diffusion.py - 2025-03-24 08:48:56,590 - Loss: 0.3923, step: 4900
+INFO - dpsgd_diffusion.py - 2025-03-24 08:49:10,928 - Eps-value after 7 epochs: 1.9592
+INFO - dpsgd_diffusion.py - 2025-03-24 08:49:47,825 - Loss: 0.3863, step: 5000
+INFO - dpsgd_diffusion.py - 2025-03-24 08:50:41,135 - Loss: 0.3963, step: 5100
+INFO - dpsgd_diffusion.py - 2025-03-24 08:51:33,063 - Loss: 0.3442, step: 5200
+INFO - dpsgd_diffusion.py - 2025-03-24 08:52:23,739 - Loss: 0.3748, step: 5300
+INFO - dpsgd_diffusion.py - 2025-03-24 08:53:15,704 - Loss: 0.3668, step: 5400
+INFO - dpsgd_diffusion.py - 2025-03-24 08:54:06,300 - Loss: 0.3817, step: 5500
+INFO - dpsgd_diffusion.py - 2025-03-24 08:54:58,157 - Loss: 0.3784, step: 5600
+INFO - dpsgd_diffusion.py - 2025-03-24 08:55:14,208 - Eps-value after 8 epochs: 2.0901
+INFO - dpsgd_diffusion.py - 2025-03-24 08:55:50,098 - Loss: 0.3572, step: 5700
+INFO - dpsgd_diffusion.py - 2025-03-24 08:56:42,455 - Loss: 0.4020, step: 5800
+INFO - dpsgd_diffusion.py - 2025-03-24 08:57:36,832 - Loss: 0.3349, step: 5900
+INFO - dpsgd_diffusion.py - 2025-03-24 08:58:29,270 - Loss: 0.3169, step: 6000
+INFO - dpsgd_diffusion.py - 2025-03-24 08:58:29,277 - Saving snapshot checkpoint and sampling single batch at iteration 6000.
+WARNING - image.py - 2025-03-24 08:58:29,867 - 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 - 2025-03-24 08:58:57,882 - FID at iteration 6000: 333.291436
+INFO - dpsgd_diffusion.py - 2025-03-24 08:59:49,453 - Loss: 0.3261, step: 6100
+INFO - dpsgd_diffusion.py - 2025-03-24 09:00:40,788 - Loss: 0.3680, step: 6200
+INFO - dpsgd_diffusion.py - 2025-03-24 09:01:31,914 - Loss: 0.3312, step: 6300
+INFO - dpsgd_diffusion.py - 2025-03-24 09:01:49,936 - Eps-value after 9 epochs: 2.2140
+INFO - dpsgd_diffusion.py - 2025-03-24 09:02:22,149 - Loss: 0.3405, step: 6400
+INFO - dpsgd_diffusion.py - 2025-03-24 09:03:14,897 - Loss: 0.3481, step: 6500
+INFO - dpsgd_diffusion.py - 2025-03-24 09:04:06,151 - Loss: 0.3090, step: 6600
+INFO - dpsgd_diffusion.py - 2025-03-24 09:04:56,793 - Loss: 0.3148, step: 6700
+INFO - dpsgd_diffusion.py - 2025-03-24 09:05:46,495 - Loss: 0.3433, step: 6800
+INFO - dpsgd_diffusion.py - 2025-03-24 09:06:37,826 - Loss: 0.3455, step: 6900
+INFO - dpsgd_diffusion.py - 2025-03-24 09:07:30,069 - Loss: 0.3242, step: 7000
+INFO - dpsgd_diffusion.py - 2025-03-24 09:07:50,418 - Eps-value after 10 epochs: 2.3320
+INFO - dpsgd_diffusion.py - 2025-03-24 09:08:21,169 - Loss: 0.3053, step: 7100
+INFO - dpsgd_diffusion.py - 2025-03-24 09:09:11,822 - Loss: 0.3249, step: 7200
+INFO - dpsgd_diffusion.py - 2025-03-24 09:10:02,498 - Loss: 0.3137, step: 7300
+INFO - dpsgd_diffusion.py - 2025-03-24 09:10:55,536 - Loss: 0.2994, step: 7400
+INFO - dpsgd_diffusion.py - 2025-03-24 09:11:46,849 - Loss: 0.3142, step: 7500
+INFO - dpsgd_diffusion.py - 2025-03-24 09:12:37,976 - Loss: 0.3481, step: 7600
+INFO - dpsgd_diffusion.py - 2025-03-24 09:13:29,762 - Loss: 0.3091, step: 7700
+INFO - dpsgd_diffusion.py - 2025-03-24 09:13:53,225 - Eps-value after 11 epochs: 2.4450
+INFO - dpsgd_diffusion.py - 2025-03-24 09:14:22,893 - Loss: 0.3024, step: 7800
+INFO - dpsgd_diffusion.py - 2025-03-24 09:15:13,129 - Loss: 0.3052, step: 7900
+INFO - dpsgd_diffusion.py - 2025-03-24 09:16:03,180 - Loss: 0.3241, step: 8000
+INFO - dpsgd_diffusion.py - 2025-03-24 09:16:03,191 - Saving snapshot checkpoint and sampling single batch at iteration 8000.
+WARNING - image.py - 2025-03-24 09:16:03,791 - 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 - 2025-03-24 09:16:31,601 - FID at iteration 8000: 303.420116
+INFO - dpsgd_diffusion.py - 2025-03-24 09:17:22,137 - Loss: 0.3069, step: 8100
+INFO - dpsgd_diffusion.py - 2025-03-24 09:18:12,204 - Loss: 0.3073, step: 8200
+INFO - dpsgd_diffusion.py - 2025-03-24 09:19:03,981 - Loss: 0.3127, step: 8300
+INFO - dpsgd_diffusion.py - 2025-03-24 09:19:54,482 - Loss: 0.3146, step: 8400
+INFO - dpsgd_diffusion.py - 2025-03-24 09:20:18,571 - Eps-value after 12 epochs: 2.5536
+INFO - dpsgd_diffusion.py - 2025-03-24 09:20:45,353 - Loss: 0.2985, step: 8500
+INFO - dpsgd_diffusion.py - 2025-03-24 09:21:35,856 - Loss: 0.3201, step: 8600
+INFO - dpsgd_diffusion.py - 2025-03-24 09:22:26,562 - Loss: 0.3232, step: 8700
+INFO - dpsgd_diffusion.py - 2025-03-24 09:23:17,184 - Loss: 0.3351, step: 8800
+INFO - dpsgd_diffusion.py - 2025-03-24 09:24:07,663 - Loss: 0.3027, step: 8900
+INFO - dpsgd_diffusion.py - 2025-03-24 09:25:00,035 - Loss: 0.3051, step: 9000
+INFO - dpsgd_diffusion.py - 2025-03-24 09:25:51,135 - Loss: 0.3020, step: 9100
+INFO - dpsgd_diffusion.py - 2025-03-24 09:26:17,807 - Eps-value after 13 epochs: 2.6584
+INFO - dpsgd_diffusion.py - 2025-03-24 09:26:43,615 - Loss: 0.3059, step: 9200
+INFO - dpsgd_diffusion.py - 2025-03-24 09:27:35,847 - Loss: 0.3434, step: 9300
+INFO - dpsgd_diffusion.py - 2025-03-24 09:28:26,955 - Loss: 0.2991, step: 9400
+INFO - dpsgd_diffusion.py - 2025-03-24 09:29:21,779 - Loss: 0.2876, step: 9500
+INFO - dpsgd_diffusion.py - 2025-03-24 09:30:13,237 - Loss: 0.3081, step: 9600
+INFO - dpsgd_diffusion.py - 2025-03-24 09:31:05,836 - Loss: 0.3088, step: 9700
+INFO - dpsgd_diffusion.py - 2025-03-24 09:31:57,746 - Loss: 0.2934, step: 9800
+INFO - dpsgd_diffusion.py - 2025-03-24 09:32:25,749 - Eps-value after 14 epochs: 2.7598
+INFO - dpsgd_diffusion.py - 2025-03-24 09:32:48,570 - Loss: 0.2814, step: 9900
+INFO - dpsgd_diffusion.py - 2025-03-24 09:33:40,020 - Loss: 0.2954, step: 10000
+INFO - dpsgd_diffusion.py - 2025-03-24 09:33:40,027 - Saving snapshot checkpoint and sampling single batch at iteration 10000.
+WARNING - image.py - 2025-03-24 09:33:40,614 - 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 - 2025-03-24 09:34:09,915 - FID at iteration 10000: 292.199845
+INFO - dpsgd_diffusion.py - 2025-03-24 09:35:00,814 - Loss: 0.3039, step: 10100
+INFO - dpsgd_diffusion.py - 2025-03-24 09:35:53,379 - Loss: 0.2883, step: 10200
+INFO - dpsgd_diffusion.py - 2025-03-24 09:36:45,044 - Loss: 0.3223, step: 10300
+INFO - dpsgd_diffusion.py - 2025-03-24 09:37:36,514 - Loss: 0.2862, step: 10400
+INFO - dpsgd_diffusion.py - 2025-03-24 09:38:28,097 - Loss: 0.3154, step: 10500
+INFO - dpsgd_diffusion.py - 2025-03-24 09:38:59,762 - Eps-value after 15 epochs: 2.8581
+INFO - dpsgd_diffusion.py - 2025-03-24 09:39:20,387 - Loss: 0.2630, step: 10600
+INFO - dpsgd_diffusion.py - 2025-03-24 09:40:11,746 - Loss: 0.2938, step: 10700
+INFO - dpsgd_diffusion.py - 2025-03-24 09:41:02,560 - Loss: 0.2844, step: 10800
+INFO - dpsgd_diffusion.py - 2025-03-24 09:41:53,362 - Loss: 0.2892, step: 10900
+INFO - dpsgd_diffusion.py - 2025-03-24 09:42:45,031 - Loss: 0.2511, step: 11000
+INFO - dpsgd_diffusion.py - 2025-03-24 09:43:36,609 - Loss: 0.2685, step: 11100
+INFO - dpsgd_diffusion.py - 2025-03-24 09:44:28,075 - Loss: 0.2723, step: 11200
+INFO - dpsgd_diffusion.py - 2025-03-24 09:45:01,146 - Eps-value after 16 epochs: 2.9536
+INFO - dpsgd_diffusion.py - 2025-03-24 09:45:20,148 - Loss: 0.2826, step: 11300
+INFO - dpsgd_diffusion.py - 2025-03-24 09:46:11,248 - Loss: 0.2782, step: 11400
+INFO - dpsgd_diffusion.py - 2025-03-24 09:47:02,815 - Loss: 0.3069, step: 11500
+INFO - dpsgd_diffusion.py - 2025-03-24 09:47:54,489 - Loss: 0.3390, step: 11600
+INFO - dpsgd_diffusion.py - 2025-03-24 09:48:45,990 - Loss: 0.2773, step: 11700
+INFO - dpsgd_diffusion.py - 2025-03-24 09:49:36,874 - Loss: 0.3323, step: 11800
+INFO - dpsgd_diffusion.py - 2025-03-24 09:50:27,447 - Loss: 0.2684, step: 11900
+INFO - dpsgd_diffusion.py - 2025-03-24 09:51:01,640 - Eps-value after 17 epochs: 3.0466
+INFO - dpsgd_diffusion.py - 2025-03-24 09:51:18,578 - Loss: 0.3205, step: 12000
+INFO - dpsgd_diffusion.py - 2025-03-24 09:51:18,585 - Saving snapshot checkpoint and sampling single batch at iteration 12000.
+WARNING - image.py - 2025-03-24 09:51:19,160 - 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 - 2025-03-24 09:51:44,194 - FID at iteration 12000: 273.948849
+INFO - dpsgd_diffusion.py - 2025-03-24 09:52:37,326 - Loss: 0.2830, step: 12100
+INFO - dpsgd_diffusion.py - 2025-03-24 09:53:29,453 - Loss: 0.2873, step: 12200
+INFO - dpsgd_diffusion.py - 2025-03-24 09:54:20,012 - Loss: 0.2680, step: 12300
+INFO - dpsgd_diffusion.py - 2025-03-24 09:55:12,201 - Loss: 0.2869, step: 12400
+INFO - dpsgd_diffusion.py - 2025-03-24 09:56:03,222 - Loss: 0.3192, step: 12500
+INFO - dpsgd_diffusion.py - 2025-03-24 09:56:54,171 - Loss: 0.3069, step: 12600
+INFO - dpsgd_diffusion.py - 2025-03-24 09:57:29,873 - Eps-value after 18 epochs: 3.1373
+INFO - dpsgd_diffusion.py - 2025-03-24 09:57:44,745 - Loss: 0.2820, step: 12700
+INFO - dpsgd_diffusion.py - 2025-03-24 09:58:35,627 - Loss: 0.3027, step: 12800
+INFO - dpsgd_diffusion.py - 2025-03-24 09:59:25,870 - Loss: 0.2776, step: 12900
+INFO - dpsgd_diffusion.py - 2025-03-24 10:00:17,229 - Loss: 0.3062, step: 13000
+INFO - dpsgd_diffusion.py - 2025-03-24 10:01:09,807 - Loss: 0.2862, step: 13100
+INFO - dpsgd_diffusion.py - 2025-03-24 10:02:00,232 - Loss: 0.2803, step: 13200
+INFO - dpsgd_diffusion.py - 2025-03-24 10:02:50,711 - Loss: 0.3521, step: 13300
+INFO - dpsgd_diffusion.py - 2025-03-24 10:03:30,257 - Eps-value after 19 epochs: 3.2258
+INFO - dpsgd_diffusion.py - 2025-03-24 10:03:43,011 - Loss: 0.2866, step: 13400
+INFO - dpsgd_diffusion.py - 2025-03-24 10:04:35,129 - Loss: 0.3022, step: 13500
+INFO - dpsgd_diffusion.py - 2025-03-24 10:05:26,525 - Loss: 0.2999, step: 13600
+INFO - dpsgd_diffusion.py - 2025-03-24 10:06:19,116 - Loss: 0.2707, step: 13700
+INFO - dpsgd_diffusion.py - 2025-03-24 10:07:12,188 - Loss: 0.2641, step: 13800
+INFO - dpsgd_diffusion.py - 2025-03-24 10:08:03,777 - Loss: 0.3157, step: 13900
+INFO - dpsgd_diffusion.py - 2025-03-24 10:08:56,192 - Loss: 0.3194, step: 14000
+INFO - dpsgd_diffusion.py - 2025-03-24 10:08:56,199 - Saving snapshot checkpoint and sampling single batch at iteration 14000.
+WARNING - image.py - 2025-03-24 10:08:56,786 - 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 - 2025-03-24 10:09:22,199 - FID at iteration 14000: 258.465169
+INFO - dpsgd_diffusion.py - 2025-03-24 10:10:05,090 - Eps-value after 20 epochs: 3.3125
+INFO - dpsgd_diffusion.py - 2025-03-24 10:10:15,701 - Loss: 0.3060, step: 14100
+INFO - dpsgd_diffusion.py - 2025-03-24 10:11:06,950 - Loss: 0.2703, step: 14200
+INFO - dpsgd_diffusion.py - 2025-03-24 10:11:58,220 - Loss: 0.2674, step: 14300
+INFO - dpsgd_diffusion.py - 2025-03-24 10:12:49,335 - Loss: 0.2775, step: 14400
+INFO - dpsgd_diffusion.py - 2025-03-24 10:13:39,275 - Loss: 0.3054, step: 14500
+INFO - dpsgd_diffusion.py - 2025-03-24 10:14:31,103 - Loss: 0.2978, step: 14600
+INFO - dpsgd_diffusion.py - 2025-03-24 10:15:21,813 - Loss: 0.2505, step: 14700
+INFO - dpsgd_diffusion.py - 2025-03-24 10:16:04,908 - Eps-value after 21 epochs: 3.3973
+INFO - dpsgd_diffusion.py - 2025-03-24 10:16:12,902 - Loss: 0.2681, step: 14800
+INFO - dpsgd_diffusion.py - 2025-03-24 10:17:04,276 - Loss: 0.2826, step: 14900
+INFO - dpsgd_diffusion.py - 2025-03-24 10:17:56,174 - Loss: 0.2859, step: 15000
+INFO - dpsgd_diffusion.py - 2025-03-24 10:18:46,006 - Loss: 0.2843, step: 15100
+INFO - dpsgd_diffusion.py - 2025-03-24 10:19:37,920 - Loss: 0.3069, step: 15200
+INFO - dpsgd_diffusion.py - 2025-03-24 10:20:28,781 - Loss: 0.2771, step: 15300
+INFO - dpsgd_diffusion.py - 2025-03-24 10:21:19,387 - Loss: 0.3004, step: 15400
+INFO - dpsgd_diffusion.py - 2025-03-24 10:22:03,002 - Eps-value after 22 epochs: 3.4803
+INFO - dpsgd_diffusion.py - 2025-03-24 10:22:09,396 - Loss: 0.2882, step: 15500
+INFO - dpsgd_diffusion.py - 2025-03-24 10:23:00,470 - Loss: 0.2745, step: 15600
+INFO - dpsgd_diffusion.py - 2025-03-24 10:23:53,026 - Loss: 0.3024, step: 15700
+INFO - dpsgd_diffusion.py - 2025-03-24 10:24:43,141 - Loss: 0.3100, step: 15800
+INFO - dpsgd_diffusion.py - 2025-03-24 10:25:34,865 - Loss: 0.2547, step: 15900
+INFO - dpsgd_diffusion.py - 2025-03-24 10:26:26,710 - Loss: 0.2839, step: 16000
+INFO - dpsgd_diffusion.py - 2025-03-24 10:26:26,724 - Saving snapshot checkpoint and sampling single batch at iteration 16000.
+WARNING - image.py - 2025-03-24 10:26:27,317 - 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 - 2025-03-24 10:26:55,664 - FID at iteration 16000: 246.849152
+INFO - dpsgd_diffusion.py - 2025-03-24 10:27:46,735 - Loss: 0.2569, step: 16100
+INFO - dpsgd_diffusion.py - 2025-03-24 10:28:34,059 - Eps-value after 23 epochs: 3.5619
+INFO - dpsgd_diffusion.py - 2025-03-24 10:28:38,287 - Loss: 0.3092, step: 16200
+INFO - dpsgd_diffusion.py - 2025-03-24 10:29:30,970 - Loss: 0.3012, step: 16300
+INFO - dpsgd_diffusion.py - 2025-03-24 10:30:22,087 - Loss: 0.2746, step: 16400
+INFO - dpsgd_diffusion.py - 2025-03-24 10:31:12,270 - Loss: 0.2795, step: 16500
+INFO - dpsgd_diffusion.py - 2025-03-24 10:32:03,219 - Loss: 0.2795, step: 16600
+INFO - dpsgd_diffusion.py - 2025-03-24 10:32:53,670 - Loss: 0.2766, step: 16700
+INFO - dpsgd_diffusion.py - 2025-03-24 10:33:45,174 - Loss: 0.2676, step: 16800
+INFO - dpsgd_diffusion.py - 2025-03-24 10:34:34,469 - Eps-value after 24 epochs: 3.6419
+INFO - dpsgd_diffusion.py - 2025-03-24 10:34:36,565 - Loss: 0.2872, step: 16900
+INFO - dpsgd_diffusion.py - 2025-03-24 10:35:28,695 - Loss: 0.2804, step: 17000
+INFO - dpsgd_diffusion.py - 2025-03-24 10:36:19,684 - Loss: 0.2647, step: 17100
+INFO - dpsgd_diffusion.py - 2025-03-24 10:37:11,814 - Loss: 0.3039, step: 17200
+INFO - dpsgd_diffusion.py - 2025-03-24 10:38:03,100 - Loss: 0.2690, step: 17300
+INFO - dpsgd_diffusion.py - 2025-03-24 10:38:55,375 - Loss: 0.2686, step: 17400
+INFO - dpsgd_diffusion.py - 2025-03-24 10:39:46,910 - Loss: 0.2508, step: 17500
+INFO - dpsgd_diffusion.py - 2025-03-24 10:40:39,879 - Loss: 0.2765, step: 17600
+INFO - dpsgd_diffusion.py - 2025-03-24 10:40:39,917 - Eps-value after 25 epochs: 3.7206
+INFO - dpsgd_diffusion.py - 2025-03-24 10:41:31,583 - Loss: 0.2636, step: 17700
+INFO - dpsgd_diffusion.py - 2025-03-24 10:42:23,681 - Loss: 0.2382, step: 17800
+INFO - dpsgd_diffusion.py - 2025-03-24 10:43:14,509 - Loss: 0.2839, step: 17900
+INFO - dpsgd_diffusion.py - 2025-03-24 10:44:05,567 - Loss: 0.2734, step: 18000
+INFO - dpsgd_diffusion.py - 2025-03-24 10:44:05,574 - Saving snapshot checkpoint and sampling single batch at iteration 18000.
+WARNING - image.py - 2025-03-24 10:44:06,176 - 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 - 2025-03-24 10:44:32,777 - FID at iteration 18000: 232.493754
+INFO - dpsgd_diffusion.py - 2025-03-24 10:45:23,446 - Loss: 0.2529, step: 18100
+INFO - dpsgd_diffusion.py - 2025-03-24 10:46:16,017 - Loss: 0.2739, step: 18200
+INFO - dpsgd_diffusion.py - 2025-03-24 10:47:07,615 - Loss: 0.2728, step: 18300
+INFO - dpsgd_diffusion.py - 2025-03-24 10:47:09,689 - Eps-value after 26 epochs: 3.7979
+INFO - dpsgd_diffusion.py - 2025-03-24 10:47:59,063 - Loss: 0.2563, step: 18400
+INFO - dpsgd_diffusion.py - 2025-03-24 10:48:50,588 - Loss: 0.2660, step: 18500
+INFO - dpsgd_diffusion.py - 2025-03-24 10:49:42,634 - Loss: 0.2515, step: 18600
+INFO - dpsgd_diffusion.py - 2025-03-24 10:50:33,817 - Loss: 0.2922, step: 18700
+INFO - dpsgd_diffusion.py - 2025-03-24 10:51:26,017 - Loss: 0.2545, step: 18800
+INFO - dpsgd_diffusion.py - 2025-03-24 10:52:17,080 - Loss: 0.2556, step: 18900
+INFO - dpsgd_diffusion.py - 2025-03-24 10:53:07,495 - Loss: 0.2693, step: 19000
+INFO - dpsgd_diffusion.py - 2025-03-24 10:53:11,320 - Eps-value after 27 epochs: 3.8741
+INFO - dpsgd_diffusion.py - 2025-03-24 10:53:59,745 - Loss: 0.2904, step: 19100
+INFO - dpsgd_diffusion.py - 2025-03-24 10:54:51,673 - Loss: 0.3061, step: 19200
+INFO - dpsgd_diffusion.py - 2025-03-24 10:55:43,810 - Loss: 0.2483, step: 19300
+INFO - dpsgd_diffusion.py - 2025-03-24 10:56:35,326 - Loss: 0.2766, step: 19400
+INFO - dpsgd_diffusion.py - 2025-03-24 10:57:27,988 - Loss: 0.3094, step: 19500
+INFO - dpsgd_diffusion.py - 2025-03-24 10:58:20,335 - Loss: 0.2647, step: 19600
+INFO - dpsgd_diffusion.py - 2025-03-24 10:59:12,001 - Loss: 0.2513, step: 19700
+INFO - dpsgd_diffusion.py - 2025-03-24 10:59:18,047 - Eps-value after 28 epochs: 3.9490
+INFO - dpsgd_diffusion.py - 2025-03-24 11:00:04,067 - Loss: 0.2496, step: 19800
+INFO - dpsgd_diffusion.py - 2025-03-24 11:00:56,510 - Loss: 0.2951, step: 19900
+INFO - dpsgd_diffusion.py - 2025-03-24 11:01:48,855 - Loss: 0.2507, step: 20000
+INFO - dpsgd_diffusion.py - 2025-03-24 11:01:48,893 - Saving snapshot checkpoint and sampling single batch at iteration 20000.
+WARNING - image.py - 2025-03-24 11:01:49,485 - 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 - 2025-03-24 11:02:16,360 - FID at iteration 20000: 220.190391
+INFO - dpsgd_diffusion.py - 2025-03-24 11:03:07,965 - Loss: 0.2732, step: 20100
+INFO - dpsgd_diffusion.py - 2025-03-24 11:04:01,352 - Loss: 0.2728, step: 20200
+INFO - dpsgd_diffusion.py - 2025-03-24 11:04:52,138 - Loss: 0.2404, step: 20300
+INFO - dpsgd_diffusion.py - 2025-03-24 11:05:44,124 - Loss: 0.2473, step: 20400
+INFO - dpsgd_diffusion.py - 2025-03-24 11:05:52,168 - Eps-value after 29 epochs: 4.0230
+INFO - dpsgd_diffusion.py - 2025-03-24 11:06:36,977 - Loss: 0.2642, step: 20500
+INFO - dpsgd_diffusion.py - 2025-03-24 11:07:30,066 - Loss: 0.2637, step: 20600
+INFO - dpsgd_diffusion.py - 2025-03-24 11:08:22,566 - Loss: 0.2587, step: 20700
+INFO - dpsgd_diffusion.py - 2025-03-24 11:09:14,048 - Loss: 0.2426, step: 20800
+INFO - dpsgd_diffusion.py - 2025-03-24 11:10:07,520 - Loss: 0.2546, step: 20900
+INFO - dpsgd_diffusion.py - 2025-03-24 11:10:58,438 - Loss: 0.2646, step: 21000
+INFO - dpsgd_diffusion.py - 2025-03-24 11:11:51,223 - Loss: 0.2789, step: 21100
+INFO - dpsgd_diffusion.py - 2025-03-24 11:12:01,293 - Eps-value after 30 epochs: 4.0958
+INFO - dpsgd_diffusion.py - 2025-03-24 11:12:42,531 - Loss: 0.3002, step: 21200
+INFO - dpsgd_diffusion.py - 2025-03-24 11:13:34,678 - Loss: 0.2358, step: 21300
+INFO - dpsgd_diffusion.py - 2025-03-24 11:14:25,808 - Loss: 0.2420, step: 21400
+INFO - dpsgd_diffusion.py - 2025-03-24 11:15:18,109 - Loss: 0.2648, step: 21500
+INFO - dpsgd_diffusion.py - 2025-03-24 11:16:09,136 - Loss: 0.2761, step: 21600
+INFO - dpsgd_diffusion.py - 2025-03-24 11:17:00,939 - Loss: 0.2399, step: 21700
+INFO - dpsgd_diffusion.py - 2025-03-24 11:17:52,576 - Loss: 0.2758, step: 21800
+INFO - dpsgd_diffusion.py - 2025-03-24 11:18:04,632 - Eps-value after 31 epochs: 4.1675
+INFO - dpsgd_diffusion.py - 2025-03-24 11:18:44,067 - Loss: 0.2795, step: 21900
+INFO - dpsgd_diffusion.py - 2025-03-24 11:19:35,788 - Loss: 0.2528, step: 22000
+INFO - dpsgd_diffusion.py - 2025-03-24 11:19:35,793 - Saving snapshot checkpoint and sampling single batch at iteration 22000.
+WARNING - image.py - 2025-03-24 11:19:36,561 - 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 - 2025-03-24 11:20:02,678 - FID at iteration 22000: 213.955291
+INFO - dpsgd_diffusion.py - 2025-03-24 11:20:56,200 - Loss: 0.2644, step: 22100
+INFO - dpsgd_diffusion.py - 2025-03-24 11:21:47,948 - Loss: 0.2430, step: 22200
+INFO - dpsgd_diffusion.py - 2025-03-24 11:22:41,859 - Loss: 0.2481, step: 22300
+INFO - dpsgd_diffusion.py - 2025-03-24 11:23:32,195 - Loss: 0.2398, step: 22400
+INFO - dpsgd_diffusion.py - 2025-03-24 11:24:24,098 - Loss: 0.2702, step: 22500
+INFO - dpsgd_diffusion.py - 2025-03-24 11:24:39,102 - Eps-value after 32 epochs: 4.2383
+INFO - dpsgd_diffusion.py - 2025-03-24 11:25:16,483 - Loss: 0.2717, step: 22600
+INFO - dpsgd_diffusion.py - 2025-03-24 11:26:07,952 - Loss: 0.2228, step: 22700
+INFO - dpsgd_diffusion.py - 2025-03-24 11:26:57,908 - Loss: 0.2594, step: 22800
+INFO - dpsgd_diffusion.py - 2025-03-24 11:27:48,896 - Loss: 0.2541, step: 22900
+INFO - dpsgd_diffusion.py - 2025-03-24 11:28:39,956 - Loss: 0.2680, step: 23000
+INFO - dpsgd_diffusion.py - 2025-03-24 11:29:31,077 - Loss: 0.2921, step: 23100
+INFO - dpsgd_diffusion.py - 2025-03-24 11:30:23,851 - Loss: 0.2597, step: 23200
+INFO - dpsgd_diffusion.py - 2025-03-24 11:30:39,893 - Eps-value after 33 epochs: 4.3085
+INFO - dpsgd_diffusion.py - 2025-03-24 11:31:14,524 - Loss: 0.2704, step: 23300
+INFO - dpsgd_diffusion.py - 2025-03-24 11:32:06,795 - Loss: 0.2770, step: 23400
+INFO - dpsgd_diffusion.py - 2025-03-24 11:32:57,322 - Loss: 0.2533, step: 23500
+INFO - dpsgd_diffusion.py - 2025-03-24 11:33:49,242 - Loss: 0.2461, step: 23600
+INFO - dpsgd_diffusion.py - 2025-03-24 11:34:40,447 - Loss: 0.2578, step: 23700
+INFO - dpsgd_diffusion.py - 2025-03-24 11:35:32,557 - Loss: 0.2454, step: 23800
+INFO - dpsgd_diffusion.py - 2025-03-24 11:36:24,039 - Loss: 0.2450, step: 23900
+INFO - dpsgd_diffusion.py - 2025-03-24 11:36:43,150 - Eps-value after 34 epochs: 4.3774
+INFO - dpsgd_diffusion.py - 2025-03-24 11:37:17,164 - Loss: 0.2628, step: 24000
+INFO - dpsgd_diffusion.py - 2025-03-24 11:37:17,178 - Saving snapshot checkpoint and sampling single batch at iteration 24000.
+WARNING - image.py - 2025-03-24 11:37:17,746 - 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 - 2025-03-24 11:37:43,593 - FID at iteration 24000: 206.268329
+INFO - dpsgd_diffusion.py - 2025-03-24 11:38:38,121 - Loss: 0.2510, step: 24100
+INFO - dpsgd_diffusion.py - 2025-03-24 11:39:29,367 - Loss: 0.2587, step: 24200
+INFO - dpsgd_diffusion.py - 2025-03-24 11:40:20,540 - Loss: 0.2776, step: 24300
+INFO - dpsgd_diffusion.py - 2025-03-24 11:41:12,168 - Loss: 0.2503, step: 24400
+INFO - dpsgd_diffusion.py - 2025-03-24 11:42:02,940 - Loss: 0.2474, step: 24500
+INFO - dpsgd_diffusion.py - 2025-03-24 11:42:54,502 - Loss: 0.2605, step: 24600
+INFO - dpsgd_diffusion.py - 2025-03-24 11:43:14,130 - Eps-value after 35 epochs: 4.4456
+INFO - dpsgd_diffusion.py - 2025-03-24 11:43:44,076 - Loss: 0.2524, step: 24700
+INFO - dpsgd_diffusion.py - 2025-03-24 11:44:35,103 - Loss: 0.2860, step: 24800
+INFO - dpsgd_diffusion.py - 2025-03-24 11:45:25,867 - Loss: 0.2790, step: 24900
+INFO - dpsgd_diffusion.py - 2025-03-24 11:46:18,181 - Loss: 0.2463, step: 25000
+INFO - dpsgd_diffusion.py - 2025-03-24 11:47:08,506 - Loss: 0.2539, step: 25100
+INFO - dpsgd_diffusion.py - 2025-03-24 11:47:59,926 - Loss: 0.2673, step: 25200
+INFO - dpsgd_diffusion.py - 2025-03-24 11:48:51,677 - Loss: 0.2439, step: 25300
+INFO - dpsgd_diffusion.py - 2025-03-24 11:49:13,763 - Eps-value after 36 epochs: 4.5133
+INFO - dpsgd_diffusion.py - 2025-03-24 11:49:42,943 - Loss: 0.2685, step: 25400
+INFO - dpsgd_diffusion.py - 2025-03-24 11:50:35,128 - Loss: 0.2747, step: 25500
+INFO - dpsgd_diffusion.py - 2025-03-24 11:51:27,382 - Loss: 0.2681, step: 25600
+INFO - dpsgd_diffusion.py - 2025-03-24 11:52:18,057 - Loss: 0.2514, step: 25700
+INFO - dpsgd_diffusion.py - 2025-03-24 11:53:09,993 - Loss: 0.2569, step: 25800
+INFO - dpsgd_diffusion.py - 2025-03-24 11:54:01,133 - Loss: 0.2577, step: 25900
+INFO - dpsgd_diffusion.py - 2025-03-24 11:54:53,001 - Loss: 0.2502, step: 26000
+INFO - dpsgd_diffusion.py - 2025-03-24 11:54:53,006 - Saving snapshot checkpoint and sampling single batch at iteration 26000.
+WARNING - image.py - 2025-03-24 11:54:53,574 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2025-03-24 11:55:19,208 - FID at iteration 26000: 200.524884
+INFO - dpsgd_diffusion.py - 2025-03-24 11:55:45,966 - Eps-value after 37 epochs: 4.5798
+INFO - dpsgd_diffusion.py - 2025-03-24 11:56:11,891 - Loss: 0.2440, step: 26100
+INFO - dpsgd_diffusion.py - 2025-03-24 11:57:02,820 - Loss: 0.2599, step: 26200
+INFO - dpsgd_diffusion.py - 2025-03-24 11:57:54,487 - Loss: 0.2366, step: 26300
+INFO - dpsgd_diffusion.py - 2025-03-24 11:58:44,663 - Loss: 0.2366, step: 26400
+INFO - dpsgd_diffusion.py - 2025-03-24 11:59:34,985 - Loss: 0.2373, step: 26500
+INFO - dpsgd_diffusion.py - 2025-03-24 12:00:25,926 - Loss: 0.2635, step: 26600
+INFO - dpsgd_diffusion.py - 2025-03-24 12:01:17,985 - Loss: 0.2417, step: 26700
+INFO - dpsgd_diffusion.py - 2025-03-24 12:01:45,399 - Eps-value after 38 epochs: 4.6459
+INFO - dpsgd_diffusion.py - 2025-03-24 12:02:10,926 - Loss: 0.2701, step: 26800
+INFO - dpsgd_diffusion.py - 2025-03-24 12:03:03,131 - Loss: 0.2359, step: 26900
+INFO - dpsgd_diffusion.py - 2025-03-24 12:03:53,964 - Loss: 0.2602, step: 27000
+INFO - dpsgd_diffusion.py - 2025-03-24 12:04:46,094 - Loss: 0.2554, step: 27100
+INFO - dpsgd_diffusion.py - 2025-03-24 12:05:36,528 - Loss: 0.2813, step: 27200
+INFO - dpsgd_diffusion.py - 2025-03-24 12:06:26,972 - Loss: 0.2908, step: 27300
+INFO - dpsgd_diffusion.py - 2025-03-24 12:07:18,225 - Loss: 0.2250, step: 27400
+INFO - dpsgd_diffusion.py - 2025-03-24 12:07:47,078 - Eps-value after 39 epochs: 4.7110
+INFO - dpsgd_diffusion.py - 2025-03-24 12:08:09,887 - Loss: 0.2595, step: 27500
+INFO - dpsgd_diffusion.py - 2025-03-24 12:09:01,903 - Loss: 0.2471, step: 27600
+INFO - dpsgd_diffusion.py - 2025-03-24 12:09:53,758 - Loss: 0.2335, step: 27700
+INFO - dpsgd_diffusion.py - 2025-03-24 12:10:43,986 - Loss: 0.2424, step: 27800
+INFO - dpsgd_diffusion.py - 2025-03-24 12:11:34,036 - Loss: 0.2674, step: 27900
+INFO - dpsgd_diffusion.py - 2025-03-24 12:12:26,905 - Loss: 0.2410, step: 28000
+INFO - dpsgd_diffusion.py - 2025-03-24 12:12:26,911 - Saving snapshot checkpoint and sampling single batch at iteration 28000.
+WARNING - image.py - 2025-03-24 12:12:27,490 - 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 - 2025-03-24 12:12:53,145 - FID at iteration 28000: 193.374770
+INFO - dpsgd_diffusion.py - 2025-03-24 12:13:44,439 - Loss: 0.2501, step: 28100
+INFO - dpsgd_diffusion.py - 2025-03-24 12:14:15,694 - Eps-value after 40 epochs: 4.7757
+INFO - dpsgd_diffusion.py - 2025-03-24 12:14:35,973 - Loss: 0.2539, step: 28200
+INFO - dpsgd_diffusion.py - 2025-03-24 12:15:27,225 - Loss: 0.3050, step: 28300
+INFO - dpsgd_diffusion.py - 2025-03-24 12:16:17,797 - Loss: 0.2514, step: 28400
+INFO - dpsgd_diffusion.py - 2025-03-24 12:17:08,828 - Loss: 0.2499, step: 28500
+INFO - dpsgd_diffusion.py - 2025-03-24 12:17:59,543 - Loss: 0.2404, step: 28600
+INFO - dpsgd_diffusion.py - 2025-03-24 12:18:50,374 - Loss: 0.2271, step: 28700
+INFO - dpsgd_diffusion.py - 2025-03-24 12:19:42,672 - Loss: 0.2768, step: 28800
+INFO - dpsgd_diffusion.py - 2025-03-24 12:20:14,824 - Eps-value after 41 epochs: 4.8396
+INFO - dpsgd_diffusion.py - 2025-03-24 12:20:33,717 - Loss: 0.2445, step: 28900
+INFO - dpsgd_diffusion.py - 2025-03-24 12:21:24,749 - Loss: 0.2677, step: 29000
+INFO - dpsgd_diffusion.py - 2025-03-24 12:22:16,270 - Loss: 0.2475, step: 29100
+INFO - dpsgd_diffusion.py - 2025-03-24 12:23:07,044 - Loss: 0.2678, step: 29200
+INFO - dpsgd_diffusion.py - 2025-03-24 12:23:58,949 - Loss: 0.2623, step: 29300
+INFO - dpsgd_diffusion.py - 2025-03-24 12:24:52,015 - Loss: 0.2590, step: 29400
+INFO - dpsgd_diffusion.py - 2025-03-24 12:25:42,350 - Loss: 0.2417, step: 29500
+INFO - dpsgd_diffusion.py - 2025-03-24 12:26:17,507 - Eps-value after 42 epochs: 4.9030
+INFO - dpsgd_diffusion.py - 2025-03-24 12:26:34,194 - Loss: 0.2587, step: 29600
+INFO - dpsgd_diffusion.py - 2025-03-24 12:27:24,043 - Loss: 0.2402, step: 29700
+INFO - dpsgd_diffusion.py - 2025-03-24 12:28:15,936 - Loss: 0.2393, step: 29800
+INFO - dpsgd_diffusion.py - 2025-03-24 12:29:07,462 - Loss: 0.2598, step: 29900
+INFO - dpsgd_diffusion.py - 2025-03-24 12:29:59,150 - Loss: 0.2695, step: 30000
+INFO - dpsgd_diffusion.py - 2025-03-24 12:29:59,156 - Saving snapshot checkpoint and sampling single batch at iteration 30000.
+WARNING - image.py - 2025-03-24 12:29:59,758 - 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 - 2025-03-24 12:30:26,292 - FID at iteration 30000: 190.057406
+INFO - dpsgd_diffusion.py - 2025-03-24 12:31:19,224 - Loss: 0.2518, step: 30100
+INFO - dpsgd_diffusion.py - 2025-03-24 12:32:10,898 - Loss: 0.2596, step: 30200
+INFO - dpsgd_diffusion.py - 2025-03-24 12:32:49,240 - Eps-value after 43 epochs: 4.9656
+INFO - dpsgd_diffusion.py - 2025-03-24 12:33:04,035 - Loss: 0.2337, step: 30300
+INFO - dpsgd_diffusion.py - 2025-03-24 12:33:54,641 - Loss: 0.2905, step: 30400
+INFO - dpsgd_diffusion.py - 2025-03-24 12:34:45,929 - Loss: 0.2299, step: 30500
+INFO - dpsgd_diffusion.py - 2025-03-24 12:35:37,081 - Loss: 0.2534, step: 30600
+INFO - dpsgd_diffusion.py - 2025-03-24 12:36:28,624 - Loss: 0.2415, step: 30700
+INFO - dpsgd_diffusion.py - 2025-03-24 12:37:19,275 - Loss: 0.2379, step: 30800
+INFO - dpsgd_diffusion.py - 2025-03-24 12:38:11,376 - Loss: 0.2619, step: 30900
+INFO - dpsgd_diffusion.py - 2025-03-24 12:38:50,377 - Eps-value after 44 epochs: 5.0278
+INFO - dpsgd_diffusion.py - 2025-03-24 12:39:03,114 - Loss: 0.2356, step: 31000
+INFO - dpsgd_diffusion.py - 2025-03-24 12:39:55,069 - Loss: 0.2782, step: 31100
+INFO - dpsgd_diffusion.py - 2025-03-24 12:40:46,837 - Loss: 0.2179, step: 31200
+INFO - dpsgd_diffusion.py - 2025-03-24 12:41:39,316 - Loss: 0.2383, step: 31300
+INFO - dpsgd_diffusion.py - 2025-03-24 12:42:30,161 - Loss: 0.2183, step: 31400
+INFO - dpsgd_diffusion.py - 2025-03-24 12:43:21,799 - Loss: 0.2625, step: 31500
+INFO - dpsgd_diffusion.py - 2025-03-24 12:44:15,328 - Loss: 0.2480, step: 31600
+INFO - dpsgd_diffusion.py - 2025-03-24 12:44:56,638 - Eps-value after 45 epochs: 5.0892
+INFO - dpsgd_diffusion.py - 2025-03-24 12:45:07,259 - Loss: 0.2198, step: 31700
+INFO - dpsgd_diffusion.py - 2025-03-24 12:45:57,800 - Loss: 0.2361, step: 31800
+INFO - dpsgd_diffusion.py - 2025-03-24 12:46:48,947 - Loss: 0.2583, step: 31900
+INFO - dpsgd_diffusion.py - 2025-03-24 12:47:41,248 - Loss: 0.2298, step: 32000
+INFO - dpsgd_diffusion.py - 2025-03-24 12:47:41,260 - Saving snapshot checkpoint and sampling single batch at iteration 32000.
+WARNING - image.py - 2025-03-24 12:47:41,886 - 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 - 2025-03-24 12:48:08,615 - FID at iteration 32000: 183.299493
+INFO - dpsgd_diffusion.py - 2025-03-24 12:49:01,126 - Loss: 0.2463, step: 32100
+INFO - dpsgd_diffusion.py - 2025-03-24 12:49:52,635 - Loss: 0.2538, step: 32200
+INFO - dpsgd_diffusion.py - 2025-03-24 12:50:43,143 - Loss: 0.2774, step: 32300
+INFO - dpsgd_diffusion.py - 2025-03-24 12:51:26,807 - Eps-value after 46 epochs: 5.1505
+INFO - dpsgd_diffusion.py - 2025-03-24 12:51:35,296 - Loss: 0.2529, step: 32400
+INFO - dpsgd_diffusion.py - 2025-03-24 12:52:27,402 - Loss: 0.2231, step: 32500
+INFO - dpsgd_diffusion.py - 2025-03-24 12:53:18,604 - Loss: 0.2358, step: 32600
+INFO - dpsgd_diffusion.py - 2025-03-24 12:54:09,055 - Loss: 0.2551, step: 32700
+INFO - dpsgd_diffusion.py - 2025-03-24 12:55:00,561 - Loss: 0.2175, step: 32800
+INFO - dpsgd_diffusion.py - 2025-03-24 12:55:52,758 - Loss: 0.2570, step: 32900
+INFO - dpsgd_diffusion.py - 2025-03-24 12:56:43,566 - Loss: 0.2101, step: 33000
+INFO - dpsgd_diffusion.py - 2025-03-24 12:57:29,135 - Eps-value after 47 epochs: 5.2106
+INFO - dpsgd_diffusion.py - 2025-03-24 12:57:35,506 - Loss: 0.2500, step: 33100
+INFO - dpsgd_diffusion.py - 2025-03-24 12:58:26,229 - Loss: 0.2818, step: 33200
+INFO - dpsgd_diffusion.py - 2025-03-24 12:59:17,237 - Loss: 0.2519, step: 33300
+INFO - dpsgd_diffusion.py - 2025-03-24 13:00:08,588 - Loss: 0.2367, step: 33400
+INFO - dpsgd_diffusion.py - 2025-03-24 13:00:59,612 - Loss: 0.2268, step: 33500
+INFO - dpsgd_diffusion.py - 2025-03-24 13:01:52,257 - Loss: 0.2484, step: 33600
+INFO - dpsgd_diffusion.py - 2025-03-24 13:02:43,549 - Loss: 0.2648, step: 33700
+INFO - dpsgd_diffusion.py - 2025-03-24 13:03:30,428 - Eps-value after 48 epochs: 5.2707
+INFO - dpsgd_diffusion.py - 2025-03-24 13:03:34,686 - Loss: 0.2588, step: 33800
+INFO - dpsgd_diffusion.py - 2025-03-24 13:04:26,922 - Loss: 0.2345, step: 33900
+INFO - dpsgd_diffusion.py - 2025-03-24 13:05:18,184 - Loss: 0.2619, step: 34000
+INFO - dpsgd_diffusion.py - 2025-03-24 13:05:18,190 - Saving snapshot checkpoint and sampling single batch at iteration 34000.
+WARNING - image.py - 2025-03-24 13:05:18,786 - 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 - 2025-03-24 13:05:45,236 - FID at iteration 34000: 178.722233
+INFO - dpsgd_diffusion.py - 2025-03-24 13:06:38,836 - Loss: 0.2621, step: 34100
+INFO - dpsgd_diffusion.py - 2025-03-24 13:07:30,661 - Loss: 0.2268, step: 34200
+INFO - dpsgd_diffusion.py - 2025-03-24 13:08:22,441 - Loss: 0.2936, step: 34300
+INFO - dpsgd_diffusion.py - 2025-03-24 13:09:12,944 - Loss: 0.2576, step: 34400
+INFO - dpsgd_diffusion.py - 2025-03-24 13:10:01,738 - Eps-value after 49 epochs: 5.3302
+INFO - dpsgd_diffusion.py - 2025-03-24 13:10:03,833 - Loss: 0.2259, step: 34500
+INFO - dpsgd_diffusion.py - 2025-03-24 13:10:56,029 - Loss: 0.2465, step: 34600
+INFO - dpsgd_diffusion.py - 2025-03-24 13:11:47,182 - Loss: 0.2286, step: 34700
+INFO - dpsgd_diffusion.py - 2025-03-24 13:12:37,740 - Loss: 0.2271, step: 34800
+INFO - dpsgd_diffusion.py - 2025-03-24 13:13:29,860 - Loss: 0.2584, step: 34900
+INFO - dpsgd_diffusion.py - 2025-03-24 13:14:20,136 - Loss: 0.2408, step: 35000
+INFO - dpsgd_diffusion.py - 2025-03-24 13:15:11,912 - Loss: 0.2244, step: 35100
+INFO - dpsgd_diffusion.py - 2025-03-24 13:16:03,035 - Loss: 0.2346, step: 35200
+INFO - dpsgd_diffusion.py - 2025-03-24 13:16:03,070 - Eps-value after 50 epochs: 5.3890
+INFO - dpsgd_diffusion.py - 2025-03-24 13:16:54,978 - Loss: 0.2411, step: 35300
+INFO - dpsgd_diffusion.py - 2025-03-24 13:17:47,482 - Loss: 0.2315, step: 35400
+INFO - dpsgd_diffusion.py - 2025-03-24 13:18:40,089 - Loss: 0.2524, step: 35500
+INFO - dpsgd_diffusion.py - 2025-03-24 13:19:31,622 - Loss: 0.2506, step: 35600
+INFO - dpsgd_diffusion.py - 2025-03-24 13:20:22,144 - Loss: 0.2493, step: 35700
+INFO - dpsgd_diffusion.py - 2025-03-24 13:21:14,854 - Loss: 0.2426, step: 35800
+INFO - dpsgd_diffusion.py - 2025-03-24 13:22:06,022 - Loss: 0.2620, step: 35900
+INFO - dpsgd_diffusion.py - 2025-03-24 13:22:08,103 - Eps-value after 51 epochs: 5.4479
+INFO - dpsgd_diffusion.py - 2025-03-24 13:22:57,255 - Loss: 0.2644, step: 36000
+INFO - dpsgd_diffusion.py - 2025-03-24 13:22:57,261 - Saving snapshot checkpoint and sampling single batch at iteration 36000.
+WARNING - image.py - 2025-03-24 13:22:57,831 - 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 - 2025-03-24 13:23:26,210 - FID at iteration 36000: 176.013662
+INFO - dpsgd_diffusion.py - 2025-03-24 13:24:16,810 - Loss: 0.2413, step: 36100
+INFO - dpsgd_diffusion.py - 2025-03-24 13:25:07,518 - Loss: 0.2131, step: 36200
+INFO - dpsgd_diffusion.py - 2025-03-24 13:25:57,633 - Loss: 0.2348, step: 36300
+INFO - dpsgd_diffusion.py - 2025-03-24 13:26:50,506 - Loss: 0.2363, step: 36400
+INFO - dpsgd_diffusion.py - 2025-03-24 13:27:41,583 - Loss: 0.2267, step: 36500
+INFO - dpsgd_diffusion.py - 2025-03-24 13:28:32,627 - Loss: 0.2476, step: 36600
+INFO - dpsgd_diffusion.py - 2025-03-24 13:28:36,686 - Eps-value after 52 epochs: 5.5056
+INFO - dpsgd_diffusion.py - 2025-03-24 13:29:25,438 - Loss: 0.2501, step: 36700
+INFO - dpsgd_diffusion.py - 2025-03-24 13:30:18,634 - Loss: 0.2363, step: 36800
+INFO - dpsgd_diffusion.py - 2025-03-24 13:31:10,483 - Loss: 0.2232, step: 36900
+INFO - dpsgd_diffusion.py - 2025-03-24 13:32:00,933 - Loss: 0.2742, step: 37000
+INFO - dpsgd_diffusion.py - 2025-03-24 13:32:52,307 - Loss: 0.2566, step: 37100
+INFO - dpsgd_diffusion.py - 2025-03-24 13:33:44,202 - Loss: 0.2377, step: 37200
+INFO - dpsgd_diffusion.py - 2025-03-24 13:34:36,077 - Loss: 0.2432, step: 37300
+INFO - dpsgd_diffusion.py - 2025-03-24 13:34:42,130 - Eps-value after 53 epochs: 5.5632
+INFO - dpsgd_diffusion.py - 2025-03-24 13:35:29,090 - Loss: 0.2330, step: 37400
+INFO - dpsgd_diffusion.py - 2025-03-24 13:36:21,398 - Loss: 0.2892, step: 37500
+INFO - dpsgd_diffusion.py - 2025-03-24 13:37:13,616 - Loss: 0.2728, step: 37600
+INFO - dpsgd_diffusion.py - 2025-03-24 13:38:03,667 - Loss: 0.2370, step: 37700
+INFO - dpsgd_diffusion.py - 2025-03-24 13:38:54,362 - Loss: 0.2292, step: 37800
+INFO - dpsgd_diffusion.py - 2025-03-24 13:39:45,213 - Loss: 0.2344, step: 37900
+INFO - dpsgd_diffusion.py - 2025-03-24 13:40:36,746 - Loss: 0.2247, step: 38000
+INFO - dpsgd_diffusion.py - 2025-03-24 13:40:36,753 - Saving snapshot checkpoint and sampling single batch at iteration 38000.
+WARNING - image.py - 2025-03-24 13:40:37,332 - 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 - 2025-03-24 13:41:03,603 - FID at iteration 38000: 172.384432
+INFO - dpsgd_diffusion.py - 2025-03-24 13:41:12,897 - Eps-value after 54 epochs: 5.6207
+INFO - dpsgd_diffusion.py - 2025-03-24 13:41:57,077 - Loss: 0.2339, step: 38100
+INFO - dpsgd_diffusion.py - 2025-03-24 13:42:48,231 - Loss: 0.2435, step: 38200
+INFO - dpsgd_diffusion.py - 2025-03-24 13:43:41,304 - Loss: 0.2440, step: 38300
+INFO - dpsgd_diffusion.py - 2025-03-24 13:44:33,083 - Loss: 0.2428, step: 38400
+INFO - dpsgd_diffusion.py - 2025-03-24 13:45:24,905 - Loss: 0.2232, step: 38500
+INFO - dpsgd_diffusion.py - 2025-03-24 13:46:18,055 - Loss: 0.2239, step: 38600
+INFO - dpsgd_diffusion.py - 2025-03-24 13:47:11,298 - Loss: 0.2358, step: 38700
+INFO - dpsgd_diffusion.py - 2025-03-24 13:47:21,374 - Eps-value after 55 epochs: 5.6771
+INFO - dpsgd_diffusion.py - 2025-03-24 13:48:01,909 - Loss: 0.2367, step: 38800
+INFO - dpsgd_diffusion.py - 2025-03-24 13:48:52,640 - Loss: 0.2624, step: 38900
+INFO - dpsgd_diffusion.py - 2025-03-24 13:49:43,376 - Loss: 0.2211, step: 39000
+INFO - dpsgd_diffusion.py - 2025-03-24 13:50:33,460 - Loss: 0.2355, step: 39100
+INFO - dpsgd_diffusion.py - 2025-03-24 13:51:24,972 - Loss: 0.2480, step: 39200
+INFO - dpsgd_diffusion.py - 2025-03-24 13:52:16,686 - Loss: 0.2376, step: 39300
+INFO - dpsgd_diffusion.py - 2025-03-24 13:53:06,610 - Loss: 0.2124, step: 39400
+INFO - dpsgd_diffusion.py - 2025-03-24 13:53:18,508 - Eps-value after 56 epochs: 5.7335
+INFO - dpsgd_diffusion.py - 2025-03-24 13:53:57,278 - Loss: 0.2692, step: 39500
+INFO - dpsgd_diffusion.py - 2025-03-24 13:54:47,875 - Loss: 0.2307, step: 39600
+INFO - dpsgd_diffusion.py - 2025-03-24 13:55:38,704 - Loss: 0.2523, step: 39700
+INFO - dpsgd_diffusion.py - 2025-03-24 13:56:31,414 - Loss: 0.2310, step: 39800
+INFO - dpsgd_diffusion.py - 2025-03-24 13:57:23,056 - Loss: 0.2623, step: 39900
+INFO - dpsgd_diffusion.py - 2025-03-24 13:58:13,780 - Loss: 0.2494, step: 40000
+INFO - dpsgd_diffusion.py - 2025-03-24 13:58:13,795 - Saving snapshot checkpoint and sampling single batch at iteration 40000.
+WARNING - image.py - 2025-03-24 13:58:14,379 - 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 - 2025-03-24 13:58:40,774 - FID at iteration 40000: 169.537912
+INFO - dpsgd_diffusion.py - 2025-03-24 13:59:33,292 - Loss: 0.2436, step: 40100
+INFO - dpsgd_diffusion.py - 2025-03-24 13:59:47,345 - Eps-value after 57 epochs: 5.7898
+INFO - dpsgd_diffusion.py - 2025-03-24 14:00:24,079 - Loss: 0.2120, step: 40200
+INFO - dpsgd_diffusion.py - 2025-03-24 14:01:15,665 - Loss: 0.2194, step: 40300
+INFO - dpsgd_diffusion.py - 2025-03-24 14:02:06,872 - Loss: 0.2322, step: 40400
+INFO - dpsgd_diffusion.py - 2025-03-24 14:02:57,496 - Loss: 0.2442, step: 40500
+INFO - dpsgd_diffusion.py - 2025-03-24 14:03:48,542 - Loss: 0.2203, step: 40600
+INFO - dpsgd_diffusion.py - 2025-03-24 14:04:39,615 - Loss: 0.2479, step: 40700
+INFO - dpsgd_diffusion.py - 2025-03-24 14:05:32,742 - Loss: 0.2156, step: 40800
+INFO - dpsgd_diffusion.py - 2025-03-24 14:05:49,705 - Eps-value after 58 epochs: 5.8450
+INFO - dpsgd_diffusion.py - 2025-03-24 14:06:24,969 - Loss: 0.2489, step: 40900
+INFO - dpsgd_diffusion.py - 2025-03-24 14:07:16,744 - Loss: 0.2605, step: 41000
+INFO - dpsgd_diffusion.py - 2025-03-24 14:08:08,193 - Loss: 0.2320, step: 41100
+INFO - dpsgd_diffusion.py - 2025-03-24 14:08:58,985 - Loss: 0.2110, step: 41200
+INFO - dpsgd_diffusion.py - 2025-03-24 14:09:50,135 - Loss: 0.2520, step: 41300
+INFO - dpsgd_diffusion.py - 2025-03-24 14:10:39,564 - Loss: 0.2381, step: 41400
+INFO - dpsgd_diffusion.py - 2025-03-24 14:11:31,016 - Loss: 0.2452, step: 41500
+INFO - dpsgd_diffusion.py - 2025-03-24 14:11:48,479 - Eps-value after 59 epochs: 5.9001
+INFO - dpsgd_diffusion.py - 2025-03-24 14:12:20,915 - Loss: 0.2352, step: 41600
+INFO - dpsgd_diffusion.py - 2025-03-24 14:13:12,100 - Loss: 0.2770, step: 41700
+INFO - dpsgd_diffusion.py - 2025-03-24 14:14:03,918 - Loss: 0.2462, step: 41800
+INFO - dpsgd_diffusion.py - 2025-03-24 14:14:54,302 - Loss: 0.2503, step: 41900
+INFO - dpsgd_diffusion.py - 2025-03-24 14:15:47,243 - Loss: 0.2357, step: 42000
+INFO - dpsgd_diffusion.py - 2025-03-24 14:15:47,250 - Saving snapshot checkpoint and sampling single batch at iteration 42000.
+WARNING - image.py - 2025-03-24 14:15:47,839 - 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 - 2025-03-24 14:16:13,817 - FID at iteration 42000: 166.263423
+INFO - dpsgd_diffusion.py - 2025-03-24 14:17:06,394 - Loss: 0.2339, step: 42100
+INFO - dpsgd_diffusion.py - 2025-03-24 14:18:00,415 - Loss: 0.2164, step: 42200
+INFO - dpsgd_diffusion.py - 2025-03-24 14:18:21,810 - Eps-value after 60 epochs: 5.9553
+INFO - dpsgd_diffusion.py - 2025-03-24 14:18:53,582 - Loss: 0.2237, step: 42300
+INFO - dpsgd_diffusion.py - 2025-03-24 14:19:44,199 - Loss: 0.2471, step: 42400
+INFO - dpsgd_diffusion.py - 2025-03-24 14:20:34,800 - Loss: 0.2451, step: 42500
+INFO - dpsgd_diffusion.py - 2025-03-24 14:21:26,087 - Loss: 0.2575, step: 42600
+INFO - dpsgd_diffusion.py - 2025-03-24 14:22:16,816 - Loss: 0.2190, step: 42700
+INFO - dpsgd_diffusion.py - 2025-03-24 14:23:08,911 - Loss: 0.2385, step: 42800
+INFO - dpsgd_diffusion.py - 2025-03-24 14:24:01,781 - Loss: 0.2318, step: 42900
+INFO - dpsgd_diffusion.py - 2025-03-24 14:24:24,068 - Eps-value after 61 epochs: 6.0095
+INFO - dpsgd_diffusion.py - 2025-03-24 14:24:53,322 - Loss: 0.2307, step: 43000
+INFO - dpsgd_diffusion.py - 2025-03-24 14:25:44,920 - Loss: 0.2420, step: 43100
+INFO - dpsgd_diffusion.py - 2025-03-24 14:26:36,931 - Loss: 0.2581, step: 43200
+INFO - dpsgd_diffusion.py - 2025-03-24 14:27:29,758 - Loss: 0.1968, step: 43300
+INFO - dpsgd_diffusion.py - 2025-03-24 14:28:21,658 - Loss: 0.2426, step: 43400
+INFO - dpsgd_diffusion.py - 2025-03-24 14:29:12,002 - Loss: 0.2264, step: 43500
+INFO - dpsgd_diffusion.py - 2025-03-24 14:30:03,183 - Loss: 0.2170, step: 43600
+INFO - dpsgd_diffusion.py - 2025-03-24 14:30:27,725 - Eps-value after 62 epochs: 6.0635
+INFO - dpsgd_diffusion.py - 2025-03-24 14:30:54,936 - Loss: 0.2239, step: 43700
+INFO - dpsgd_diffusion.py - 2025-03-24 14:31:46,290 - Loss: 0.2265, step: 43800
+INFO - dpsgd_diffusion.py - 2025-03-24 14:32:37,179 - Loss: 0.1996, step: 43900
+INFO - dpsgd_diffusion.py - 2025-03-24 14:33:28,552 - Loss: 0.2352, step: 44000
+INFO - dpsgd_diffusion.py - 2025-03-24 14:33:28,586 - Saving snapshot checkpoint and sampling single batch at iteration 44000.
+WARNING - image.py - 2025-03-24 14:33:29,176 - 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 - 2025-03-24 14:33:55,452 - FID at iteration 44000: 164.211744
+INFO - dpsgd_diffusion.py - 2025-03-24 14:34:47,800 - Loss: 0.2188, step: 44100
+INFO - dpsgd_diffusion.py - 2025-03-24 14:35:39,556 - Loss: 0.2311, step: 44200
+INFO - dpsgd_diffusion.py - 2025-03-24 14:36:29,799 - Loss: 0.2344, step: 44300
+INFO - dpsgd_diffusion.py - 2025-03-24 14:36:56,875 - Eps-value after 63 epochs: 6.1174
+INFO - dpsgd_diffusion.py - 2025-03-24 14:37:22,130 - Loss: 0.2569, step: 44400
+INFO - dpsgd_diffusion.py - 2025-03-24 14:38:12,874 - Loss: 0.2276, step: 44500
+INFO - dpsgd_diffusion.py - 2025-03-24 14:39:04,211 - Loss: 0.2323, step: 44600
+INFO - dpsgd_diffusion.py - 2025-03-24 14:39:54,482 - Loss: 0.2424, step: 44700
+INFO - dpsgd_diffusion.py - 2025-03-24 14:40:45,347 - Loss: 0.2365, step: 44800
+INFO - dpsgd_diffusion.py - 2025-03-24 14:41:38,714 - Loss: 0.2580, step: 44900
+INFO - dpsgd_diffusion.py - 2025-03-24 14:42:30,413 - Loss: 0.2322, step: 45000
+INFO - dpsgd_diffusion.py - 2025-03-24 14:42:59,067 - Eps-value after 64 epochs: 6.1711
+INFO - dpsgd_diffusion.py - 2025-03-24 14:43:21,425 - Loss: 0.2263, step: 45100
+INFO - dpsgd_diffusion.py - 2025-03-24 14:44:12,015 - Loss: 0.2330, step: 45200
+INFO - dpsgd_diffusion.py - 2025-03-24 14:45:03,755 - Loss: 0.2288, step: 45300
+INFO - dpsgd_diffusion.py - 2025-03-24 14:45:55,436 - Loss: 0.2505, step: 45400
+INFO - dpsgd_diffusion.py - 2025-03-24 14:46:46,452 - Loss: 0.2713, step: 45500
+INFO - dpsgd_diffusion.py - 2025-03-24 14:47:37,904 - Loss: 0.2668, step: 45600
+INFO - dpsgd_diffusion.py - 2025-03-24 14:48:29,143 - Loss: 0.2514, step: 45700
+INFO - dpsgd_diffusion.py - 2025-03-24 14:48:59,723 - Eps-value after 65 epochs: 6.2238
+INFO - dpsgd_diffusion.py - 2025-03-24 14:49:20,982 - Loss: 0.2459, step: 45800
+INFO - dpsgd_diffusion.py - 2025-03-24 14:50:11,456 - Loss: 0.2096, step: 45900
+INFO - dpsgd_diffusion.py - 2025-03-24 14:51:03,539 - Loss: 0.2334, step: 46000
+INFO - dpsgd_diffusion.py - 2025-03-24 14:51:03,545 - Saving snapshot checkpoint and sampling single batch at iteration 46000.
+WARNING - image.py - 2025-03-24 14:51:04,155 - 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 - 2025-03-24 14:51:31,749 - FID at iteration 46000: 160.975047
+INFO - dpsgd_diffusion.py - 2025-03-24 14:52:23,771 - Loss: 0.2214, step: 46100
+INFO - dpsgd_diffusion.py - 2025-03-24 14:53:14,975 - Loss: 0.2473, step: 46200
+INFO - dpsgd_diffusion.py - 2025-03-24 14:54:06,597 - Loss: 0.2270, step: 46300
+INFO - dpsgd_diffusion.py - 2025-03-24 14:54:58,101 - Loss: 0.2477, step: 46400
+INFO - dpsgd_diffusion.py - 2025-03-24 14:55:31,229 - Eps-value after 66 epochs: 6.2766
+INFO - dpsgd_diffusion.py - 2025-03-24 14:55:49,974 - Loss: 0.2460, step: 46500
+INFO - dpsgd_diffusion.py - 2025-03-24 14:56:40,976 - Loss: 0.2635, step: 46600
+INFO - dpsgd_diffusion.py - 2025-03-24 14:57:33,076 - Loss: 0.2375, step: 46700
+INFO - dpsgd_diffusion.py - 2025-03-24 14:58:26,165 - Loss: 0.2261, step: 46800
+INFO - dpsgd_diffusion.py - 2025-03-24 14:59:18,811 - Loss: 0.2547, step: 46900
+INFO - dpsgd_diffusion.py - 2025-03-24 15:00:10,988 - Loss: 0.2558, step: 47000
+INFO - dpsgd_diffusion.py - 2025-03-24 15:01:01,468 - Loss: 0.2468, step: 47100
+INFO - dpsgd_diffusion.py - 2025-03-24 15:01:35,765 - Eps-value after 67 epochs: 6.3293
+INFO - dpsgd_diffusion.py - 2025-03-24 15:01:51,881 - Loss: 0.2489, step: 47200
+INFO - dpsgd_diffusion.py - 2025-03-24 15:02:42,771 - Loss: 0.2236, step: 47300
+INFO - dpsgd_diffusion.py - 2025-03-24 15:03:34,798 - Loss: 0.2329, step: 47400
+INFO - dpsgd_diffusion.py - 2025-03-24 15:04:25,359 - Loss: 0.2244, step: 47500
+INFO - dpsgd_diffusion.py - 2025-03-24 15:05:17,423 - Loss: 0.2556, step: 47600
+INFO - dpsgd_diffusion.py - 2025-03-24 15:06:08,434 - Loss: 0.2298, step: 47700
+INFO - dpsgd_diffusion.py - 2025-03-24 15:07:00,169 - Loss: 0.2264, step: 47800
+INFO - dpsgd_diffusion.py - 2025-03-24 15:07:38,581 - Eps-value after 68 epochs: 6.3816
+INFO - dpsgd_diffusion.py - 2025-03-24 15:07:53,489 - Loss: 0.2487, step: 47900
+INFO - dpsgd_diffusion.py - 2025-03-24 15:08:44,913 - Loss: 0.2550, step: 48000
+INFO - dpsgd_diffusion.py - 2025-03-24 15:08:44,928 - Saving snapshot checkpoint and sampling single batch at iteration 48000.
+WARNING - image.py - 2025-03-24 15:08:45,553 - 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 - 2025-03-24 15:09:13,509 - FID at iteration 48000: 159.019211
+INFO - dpsgd_diffusion.py - 2025-03-24 15:10:05,993 - Loss: 0.2574, step: 48100
+INFO - dpsgd_diffusion.py - 2025-03-24 15:10:58,207 - Loss: 0.2420, step: 48200
+INFO - dpsgd_diffusion.py - 2025-03-24 15:11:51,449 - Loss: 0.2326, step: 48300
+INFO - dpsgd_diffusion.py - 2025-03-24 15:12:43,310 - Loss: 0.2301, step: 48400
+INFO - dpsgd_diffusion.py - 2025-03-24 15:13:35,668 - Loss: 0.2355, step: 48500
+INFO - dpsgd_diffusion.py - 2025-03-24 15:14:14,862 - Eps-value after 69 epochs: 6.4332
+INFO - dpsgd_diffusion.py - 2025-03-24 15:14:26,857 - Loss: 0.2512, step: 48600
+INFO - dpsgd_diffusion.py - 2025-03-24 15:15:17,626 - Loss: 0.2290, step: 48700
+INFO - dpsgd_diffusion.py - 2025-03-24 15:16:08,729 - Loss: 0.2483, step: 48800
+INFO - dpsgd_diffusion.py - 2025-03-24 15:17:01,327 - Loss: 0.2404, step: 48900
+INFO - dpsgd_diffusion.py - 2025-03-24 15:17:52,183 - Loss: 0.2321, step: 49000
+INFO - dpsgd_diffusion.py - 2025-03-24 15:18:43,429 - Loss: 0.2408, step: 49100
+INFO - dpsgd_diffusion.py - 2025-03-24 15:19:34,295 - Loss: 0.2275, step: 49200
+INFO - dpsgd_diffusion.py - 2025-03-24 15:20:16,450 - Eps-value after 70 epochs: 6.4847
+INFO - dpsgd_diffusion.py - 2025-03-24 15:20:27,072 - Loss: 0.2200, step: 49300
+INFO - dpsgd_diffusion.py - 2025-03-24 15:21:19,546 - Loss: 0.2277, step: 49400
+INFO - dpsgd_diffusion.py - 2025-03-24 15:22:11,624 - Loss: 0.2215, step: 49500
+INFO - dpsgd_diffusion.py - 2025-03-24 15:23:02,851 - Loss: 0.2723, step: 49600
+INFO - dpsgd_diffusion.py - 2025-03-24 15:23:53,632 - Loss: 0.2289, step: 49700
+INFO - dpsgd_diffusion.py - 2025-03-24 15:24:44,198 - Loss: 0.2614, step: 49800
+INFO - dpsgd_diffusion.py - 2025-03-24 15:25:34,730 - Loss: 0.2527, step: 49900
+INFO - dpsgd_diffusion.py - 2025-03-24 15:26:17,138 - Eps-value after 71 epochs: 6.5362
+INFO - dpsgd_diffusion.py - 2025-03-24 15:26:25,667 - Loss: 0.2370, step: 50000
+INFO - dpsgd_diffusion.py - 2025-03-24 15:26:25,674 - Saving snapshot checkpoint and sampling single batch at iteration 50000.
+WARNING - image.py - 2025-03-24 15:26:26,254 - 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 - 2025-03-24 15:26:51,935 - FID at iteration 50000: 157.682278
+INFO - dpsgd_diffusion.py - 2025-03-24 15:27:45,808 - Loss: 0.2425, step: 50100
+INFO - dpsgd_diffusion.py - 2025-03-24 15:28:37,505 - Loss: 0.2489, step: 50200
+INFO - dpsgd_diffusion.py - 2025-03-24 15:29:27,592 - Loss: 0.2133, step: 50300
+INFO - dpsgd_diffusion.py - 2025-03-24 15:30:18,526 - Loss: 0.2355, step: 50400
+INFO - dpsgd_diffusion.py - 2025-03-24 15:31:09,517 - Loss: 0.2349, step: 50500
+INFO - dpsgd_diffusion.py - 2025-03-24 15:32:01,679 - Loss: 0.2637, step: 50600
+INFO - dpsgd_diffusion.py - 2025-03-24 15:32:46,281 - Eps-value after 72 epochs: 6.5876
+INFO - dpsgd_diffusion.py - 2025-03-24 15:32:52,658 - Loss: 0.2231, step: 50700
+INFO - dpsgd_diffusion.py - 2025-03-24 15:33:44,475 - Loss: 0.2439, step: 50800
+INFO - dpsgd_diffusion.py - 2025-03-24 15:34:36,153 - Loss: 0.2619, step: 50900
+INFO - dpsgd_diffusion.py - 2025-03-24 15:35:27,177 - Loss: 0.2188, step: 51000
+INFO - dpsgd_diffusion.py - 2025-03-24 15:36:19,211 - Loss: 0.2247, step: 51100
+INFO - dpsgd_diffusion.py - 2025-03-24 15:37:10,051 - Loss: 0.2515, step: 51200
+INFO - dpsgd_diffusion.py - 2025-03-24 15:38:01,493 - Loss: 0.2234, step: 51300
+INFO - dpsgd_diffusion.py - 2025-03-24 15:38:48,376 - Eps-value after 73 epochs: 6.6379
+INFO - dpsgd_diffusion.py - 2025-03-24 15:38:52,791 - Loss: 0.2182, step: 51400
+INFO - dpsgd_diffusion.py - 2025-03-24 15:39:46,622 - Loss: 0.2620, step: 51500
+INFO - dpsgd_diffusion.py - 2025-03-24 15:40:39,095 - Loss: 0.2395, step: 51600
+INFO - dpsgd_diffusion.py - 2025-03-24 15:41:30,329 - Loss: 0.2363, step: 51700
+INFO - dpsgd_diffusion.py - 2025-03-24 15:42:22,100 - Loss: 0.2297, step: 51800
+INFO - dpsgd_diffusion.py - 2025-03-24 15:43:13,033 - Loss: 0.2311, step: 51900
+INFO - dpsgd_diffusion.py - 2025-03-24 15:44:05,093 - Loss: 0.2428, step: 52000
+INFO - dpsgd_diffusion.py - 2025-03-24 15:44:05,098 - Saving snapshot checkpoint and sampling single batch at iteration 52000.
+WARNING - image.py - 2025-03-24 15:44:05,735 - 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 - 2025-03-24 15:44:34,400 - FID at iteration 52000: 156.595558
+INFO - dpsgd_diffusion.py - 2025-03-24 15:45:23,159 - Eps-value after 74 epochs: 6.6882
+INFO - dpsgd_diffusion.py - 2025-03-24 15:45:25,291 - Loss: 0.2553, step: 52100
+INFO - dpsgd_diffusion.py - 2025-03-24 15:46:17,755 - Loss: 0.2603, step: 52200
+INFO - dpsgd_diffusion.py - 2025-03-24 15:47:10,748 - Loss: 0.2418, step: 52300
+INFO - dpsgd_diffusion.py - 2025-03-24 15:48:02,988 - Loss: 0.2276, step: 52400
+INFO - dpsgd_diffusion.py - 2025-03-24 15:48:53,873 - Loss: 0.2598, step: 52500
+INFO - dpsgd_diffusion.py - 2025-03-24 15:49:46,285 - Loss: 0.2148, step: 52600
+INFO - dpsgd_diffusion.py - 2025-03-24 15:50:38,572 - Loss: 0.2630, step: 52700
+INFO - dpsgd_diffusion.py - 2025-03-24 15:51:29,057 - Loss: 0.2467, step: 52800
+INFO - dpsgd_diffusion.py - 2025-03-24 15:51:29,091 - Eps-value after 75 epochs: 6.7385
+INFO - dpsgd_diffusion.py - 2025-03-24 15:52:20,519 - Loss: 0.2294, step: 52900
+INFO - dpsgd_diffusion.py - 2025-03-24 15:53:11,793 - Loss: 0.2684, step: 53000
+INFO - dpsgd_diffusion.py - 2025-03-24 15:54:03,767 - Loss: 0.2335, step: 53100
+INFO - dpsgd_diffusion.py - 2025-03-24 15:54:54,818 - Loss: 0.2454, step: 53200
+INFO - dpsgd_diffusion.py - 2025-03-24 15:55:46,013 - Loss: 0.2170, step: 53300
+INFO - dpsgd_diffusion.py - 2025-03-24 15:56:38,618 - Loss: 0.2083, step: 53400
+INFO - dpsgd_diffusion.py - 2025-03-24 15:57:29,747 - Loss: 0.2274, step: 53500
+INFO - dpsgd_diffusion.py - 2025-03-24 15:57:31,829 - Eps-value after 76 epochs: 6.7888
+INFO - dpsgd_diffusion.py - 2025-03-24 15:58:20,960 - Loss: 0.2495, step: 53600
+INFO - dpsgd_diffusion.py - 2025-03-24 15:59:12,863 - Loss: 0.2490, step: 53700
+INFO - dpsgd_diffusion.py - 2025-03-24 16:00:03,771 - Loss: 0.2202, step: 53800
+INFO - dpsgd_diffusion.py - 2025-03-24 16:00:54,609 - Loss: 0.2333, step: 53900
+INFO - dpsgd_diffusion.py - 2025-03-24 16:01:45,049 - Loss: 0.2267, step: 54000
+INFO - dpsgd_diffusion.py - 2025-03-24 16:01:45,084 - Saving snapshot checkpoint and sampling single batch at iteration 54000.
+WARNING - image.py - 2025-03-24 16:01:45,654 - 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 - 2025-03-24 16:02:10,002 - FID at iteration 54000: 155.110413
+INFO - dpsgd_diffusion.py - 2025-03-24 16:03:05,018 - Loss: 0.2353, step: 54100
+INFO - dpsgd_diffusion.py - 2025-03-24 16:03:56,339 - Loss: 0.2060, step: 54200
+INFO - dpsgd_diffusion.py - 2025-03-24 16:04:00,417 - Eps-value after 77 epochs: 6.8385
+INFO - dpsgd_diffusion.py - 2025-03-24 16:04:47,279 - Loss: 0.2322, step: 54300
+INFO - dpsgd_diffusion.py - 2025-03-24 16:05:38,038 - Loss: 0.2224, step: 54400
+INFO - dpsgd_diffusion.py - 2025-03-24 16:06:29,123 - Loss: 0.2447, step: 54500
+INFO - dpsgd_diffusion.py - 2025-03-24 16:07:20,443 - Loss: 0.2561, step: 54600
+INFO - dpsgd_diffusion.py - 2025-03-24 16:08:11,479 - Loss: 0.2497, step: 54700
+INFO - dpsgd_diffusion.py - 2025-03-24 16:09:03,334 - Loss: 0.2688, step: 54800
+INFO - dpsgd_diffusion.py - 2025-03-24 16:09:55,909 - Loss: 0.2248, step: 54900
+INFO - dpsgd_diffusion.py - 2025-03-24 16:10:01,964 - Eps-value after 78 epochs: 6.8876
+INFO - dpsgd_diffusion.py - 2025-03-24 16:10:47,107 - Loss: 0.2313, step: 55000
+INFO - dpsgd_diffusion.py - 2025-03-24 16:11:38,402 - Loss: 0.2176, step: 55100
+INFO - dpsgd_diffusion.py - 2025-03-24 16:12:30,949 - Loss: 0.2420, step: 55200
+INFO - dpsgd_diffusion.py - 2025-03-24 16:13:21,704 - Loss: 0.2298, step: 55300
+INFO - dpsgd_diffusion.py - 2025-03-24 16:14:12,940 - Loss: 0.2275, step: 55400
+INFO - dpsgd_diffusion.py - 2025-03-24 16:15:04,056 - Loss: 0.2398, step: 55500
+INFO - dpsgd_diffusion.py - 2025-03-24 16:15:56,333 - Loss: 0.2025, step: 55600
+INFO - dpsgd_diffusion.py - 2025-03-24 16:16:04,378 - Eps-value after 79 epochs: 6.9367
+INFO - dpsgd_diffusion.py - 2025-03-24 16:16:48,839 - Loss: 0.2485, step: 55700
+INFO - dpsgd_diffusion.py - 2025-03-24 16:17:39,165 - Loss: 0.2292, step: 55800
+INFO - dpsgd_diffusion.py - 2025-03-24 16:18:31,997 - Loss: 0.2009, step: 55900
+INFO - dpsgd_diffusion.py - 2025-03-24 16:19:23,593 - Loss: 0.2007, step: 56000
+INFO - dpsgd_diffusion.py - 2025-03-24 16:19:23,607 - Saving snapshot checkpoint and sampling single batch at iteration 56000.
+WARNING - image.py - 2025-03-24 16:19:24,178 - 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 - 2025-03-24 16:19:48,810 - FID at iteration 56000: 152.359386
+INFO - dpsgd_diffusion.py - 2025-03-24 16:20:45,741 - Loss: 0.2225, step: 56100
+INFO - dpsgd_diffusion.py - 2025-03-24 16:21:36,479 - Loss: 0.2220, step: 56200
+INFO - dpsgd_diffusion.py - 2025-03-24 16:22:28,294 - Loss: 0.2376, step: 56300
+INFO - dpsgd_diffusion.py - 2025-03-24 16:22:38,334 - Eps-value after 80 epochs: 6.9858
+INFO - dpsgd_diffusion.py - 2025-03-24 16:23:19,639 - Loss: 0.2292, step: 56400
+INFO - dpsgd_diffusion.py - 2025-03-24 16:24:11,688 - Loss: 0.2246, step: 56500
+INFO - dpsgd_diffusion.py - 2025-03-24 16:25:02,099 - Loss: 0.2602, step: 56600
+INFO - dpsgd_diffusion.py - 2025-03-24 16:25:53,250 - Loss: 0.2413, step: 56700
+INFO - dpsgd_diffusion.py - 2025-03-24 16:26:44,338 - Loss: 0.2476, step: 56800
+INFO - dpsgd_diffusion.py - 2025-03-24 16:27:35,976 - Loss: 0.2327, step: 56900
+INFO - dpsgd_diffusion.py - 2025-03-24 16:28:27,170 - Loss: 0.2332, step: 57000
+INFO - dpsgd_diffusion.py - 2025-03-24 16:28:38,967 - Eps-value after 81 epochs: 7.0349
+INFO - dpsgd_diffusion.py - 2025-03-24 16:29:18,653 - Loss: 0.2359, step: 57100
+INFO - dpsgd_diffusion.py - 2025-03-24 16:30:08,492 - Loss: 0.2204, step: 57200
+INFO - dpsgd_diffusion.py - 2025-03-24 16:31:00,284 - Loss: 0.2205, step: 57300
+INFO - dpsgd_diffusion.py - 2025-03-24 16:31:51,397 - Loss: 0.2183, step: 57400
+INFO - dpsgd_diffusion.py - 2025-03-24 16:32:42,593 - Loss: 0.2169, step: 57500
+INFO - dpsgd_diffusion.py - 2025-03-24 16:33:35,224 - Loss: 0.2213, step: 57600
+INFO - dpsgd_diffusion.py - 2025-03-24 16:34:26,755 - Loss: 0.2634, step: 57700
+INFO - dpsgd_diffusion.py - 2025-03-24 16:34:40,794 - Eps-value after 82 epochs: 7.0835
+INFO - dpsgd_diffusion.py - 2025-03-24 16:35:18,034 - Loss: 0.2207, step: 57800
+INFO - dpsgd_diffusion.py - 2025-03-24 16:36:09,914 - Loss: 0.2269, step: 57900
+INFO - dpsgd_diffusion.py - 2025-03-24 16:37:02,680 - Loss: 0.2341, step: 58000
+INFO - dpsgd_diffusion.py - 2025-03-24 16:37:02,717 - Saving snapshot checkpoint and sampling single batch at iteration 58000.
+WARNING - image.py - 2025-03-24 16:37:03,287 - 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 - 2025-03-24 16:37:31,902 - FID at iteration 58000: 151.188748
+INFO - dpsgd_diffusion.py - 2025-03-24 16:38:22,528 - Loss: 0.2402, step: 58100
+INFO - dpsgd_diffusion.py - 2025-03-24 16:39:13,754 - Loss: 0.2372, step: 58200
+INFO - dpsgd_diffusion.py - 2025-03-24 16:40:06,793 - Loss: 0.2433, step: 58300
+INFO - dpsgd_diffusion.py - 2025-03-24 16:40:59,239 - Loss: 0.2255, step: 58400
+INFO - dpsgd_diffusion.py - 2025-03-24 16:41:14,962 - Eps-value after 83 epochs: 7.1314
+INFO - dpsgd_diffusion.py - 2025-03-24 16:41:50,137 - Loss: 0.2169, step: 58500
+INFO - dpsgd_diffusion.py - 2025-03-24 16:42:42,918 - Loss: 0.2420, step: 58600
+INFO - dpsgd_diffusion.py - 2025-03-24 16:43:34,753 - Loss: 0.2309, step: 58700
+INFO - dpsgd_diffusion.py - 2025-03-24 16:44:25,791 - Loss: 0.2547, step: 58800
+INFO - dpsgd_diffusion.py - 2025-03-24 16:45:17,615 - Loss: 0.2017, step: 58900
+INFO - dpsgd_diffusion.py - 2025-03-24 16:46:08,847 - Loss: 0.2363, step: 59000
+INFO - dpsgd_diffusion.py - 2025-03-24 16:46:59,782 - Loss: 0.2228, step: 59100
+INFO - dpsgd_diffusion.py - 2025-03-24 16:47:19,014 - Eps-value after 84 epochs: 7.1793
+INFO - dpsgd_diffusion.py - 2025-03-24 16:47:51,895 - Loss: 0.2354, step: 59200
+INFO - dpsgd_diffusion.py - 2025-03-24 16:48:42,837 - Loss: 0.2302, step: 59300
+INFO - dpsgd_diffusion.py - 2025-03-24 16:49:33,998 - Loss: 0.2382, step: 59400
+INFO - dpsgd_diffusion.py - 2025-03-24 16:50:24,612 - Loss: 0.2217, step: 59500
+INFO - dpsgd_diffusion.py - 2025-03-24 16:51:14,555 - Loss: 0.2265, step: 59600
+INFO - dpsgd_diffusion.py - 2025-03-24 16:52:06,115 - Loss: 0.2410, step: 59700
+INFO - dpsgd_diffusion.py - 2025-03-24 16:52:57,892 - Loss: 0.2086, step: 59800
+INFO - dpsgd_diffusion.py - 2025-03-24 16:53:18,176 - Eps-value after 85 epochs: 7.2272
+INFO - dpsgd_diffusion.py - 2025-03-24 16:53:49,823 - Loss: 0.2238, step: 59900
+INFO - dpsgd_diffusion.py - 2025-03-24 16:54:42,107 - Loss: 0.2257, step: 60000
+INFO - dpsgd_diffusion.py - 2025-03-24 16:54:42,112 - Saving snapshot checkpoint and sampling single batch at iteration 60000.
+WARNING - image.py - 2025-03-24 16:54:42,690 - 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 - 2025-03-24 16:55:12,679 - FID at iteration 60000: 148.962097
+INFO - dpsgd_diffusion.py - 2025-03-24 16:56:04,573 - Loss: 0.2266, step: 60100
+INFO - dpsgd_diffusion.py - 2025-03-24 16:56:56,390 - Loss: 0.2517, step: 60200
+INFO - dpsgd_diffusion.py - 2025-03-24 16:57:49,419 - Loss: 0.2276, step: 60300
+INFO - dpsgd_diffusion.py - 2025-03-24 16:58:41,396 - Loss: 0.2180, step: 60400
+INFO - dpsgd_diffusion.py - 2025-03-24 16:59:33,502 - Loss: 0.2104, step: 60500
+INFO - dpsgd_diffusion.py - 2025-03-24 16:59:56,548 - Eps-value after 86 epochs: 7.2751
+INFO - dpsgd_diffusion.py - 2025-03-24 17:00:25,072 - Loss: 0.2038, step: 60600
+INFO - dpsgd_diffusion.py - 2025-03-24 17:01:17,495 - Loss: 0.2013, step: 60700
+INFO - dpsgd_diffusion.py - 2025-03-24 17:02:07,992 - Loss: 0.2382, step: 60800
+INFO - dpsgd_diffusion.py - 2025-03-24 17:03:00,131 - Loss: 0.2188, step: 60900
+INFO - dpsgd_diffusion.py - 2025-03-24 17:03:51,711 - Loss: 0.2559, step: 61000
+INFO - dpsgd_diffusion.py - 2025-03-24 17:04:44,553 - Loss: 0.2444, step: 61100
+INFO - dpsgd_diffusion.py - 2025-03-24 17:05:36,915 - Loss: 0.2365, step: 61200
+INFO - dpsgd_diffusion.py - 2025-03-24 17:06:02,708 - Eps-value after 87 epochs: 7.3230
+INFO - dpsgd_diffusion.py - 2025-03-24 17:06:28,636 - Loss: 0.2127, step: 61300
+INFO - dpsgd_diffusion.py - 2025-03-24 17:07:21,184 - Loss: 0.2269, step: 61400
+INFO - dpsgd_diffusion.py - 2025-03-24 17:08:13,051 - Loss: 0.2437, step: 61500
+INFO - dpsgd_diffusion.py - 2025-03-24 17:09:06,750 - Loss: 0.2329, step: 61600
+INFO - dpsgd_diffusion.py - 2025-03-24 17:09:58,447 - Loss: 0.2114, step: 61700
+INFO - dpsgd_diffusion.py - 2025-03-24 17:10:49,788 - Loss: 0.2445, step: 61800
+INFO - dpsgd_diffusion.py - 2025-03-24 17:11:42,297 - Loss: 0.2214, step: 61900
+INFO - dpsgd_diffusion.py - 2025-03-24 17:12:10,025 - Eps-value after 88 epochs: 7.3698
+INFO - dpsgd_diffusion.py - 2025-03-24 17:12:35,513 - Loss: 0.2446, step: 62000
+INFO - dpsgd_diffusion.py - 2025-03-24 17:12:35,581 - Saving snapshot checkpoint and sampling single batch at iteration 62000.
+WARNING - image.py - 2025-03-24 17:12:36,150 - 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 - 2025-03-24 17:13:04,956 - FID at iteration 62000: 149.820769
+INFO - dpsgd_diffusion.py - 2025-03-24 17:13:58,689 - Loss: 0.2268, step: 62100
+INFO - dpsgd_diffusion.py - 2025-03-24 17:14:50,427 - Loss: 0.2073, step: 62200
+INFO - dpsgd_diffusion.py - 2025-03-24 17:15:42,694 - Loss: 0.2652, step: 62300
+INFO - dpsgd_diffusion.py - 2025-03-24 17:16:34,247 - Loss: 0.2190, step: 62400
+INFO - dpsgd_diffusion.py - 2025-03-24 17:17:25,922 - Loss: 0.2378, step: 62500
+INFO - dpsgd_diffusion.py - 2025-03-24 17:18:16,818 - Loss: 0.2122, step: 62600
+INFO - dpsgd_diffusion.py - 2025-03-24 17:18:46,717 - Eps-value after 89 epochs: 7.4165
+INFO - dpsgd_diffusion.py - 2025-03-24 17:19:10,077 - Loss: 0.2309, step: 62700
+INFO - dpsgd_diffusion.py - 2025-03-24 17:20:02,098 - Loss: 0.2542, step: 62800
+INFO - dpsgd_diffusion.py - 2025-03-24 17:20:53,510 - Loss: 0.2211, step: 62900
+INFO - dpsgd_diffusion.py - 2025-03-24 17:21:46,357 - Loss: 0.2237, step: 63000
+INFO - dpsgd_diffusion.py - 2025-03-24 17:22:36,702 - Loss: 0.2243, step: 63100
+INFO - dpsgd_diffusion.py - 2025-03-24 17:23:28,432 - Loss: 0.2317, step: 63200
+INFO - dpsgd_diffusion.py - 2025-03-24 17:24:19,142 - Loss: 0.1989, step: 63300
+INFO - dpsgd_diffusion.py - 2025-03-24 17:24:50,453 - Eps-value after 90 epochs: 7.4632
+INFO - dpsgd_diffusion.py - 2025-03-24 17:25:11,621 - Loss: 0.2507, step: 63400
+INFO - dpsgd_diffusion.py - 2025-03-24 17:26:03,220 - Loss: 0.2498, step: 63500
+INFO - dpsgd_diffusion.py - 2025-03-24 17:26:54,935 - Loss: 0.2393, step: 63600
+INFO - dpsgd_diffusion.py - 2025-03-24 17:27:46,900 - Loss: 0.2292, step: 63700
+INFO - dpsgd_diffusion.py - 2025-03-24 17:28:36,892 - Loss: 0.2389, step: 63800
+INFO - dpsgd_diffusion.py - 2025-03-24 17:29:28,835 - Loss: 0.2190, step: 63900
+INFO - dpsgd_diffusion.py - 2025-03-24 17:30:19,247 - Loss: 0.2055, step: 64000
+INFO - dpsgd_diffusion.py - 2025-03-24 17:30:19,258 - Saving snapshot checkpoint and sampling single batch at iteration 64000.
+WARNING - image.py - 2025-03-24 17:30:19,893 - 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 - 2025-03-24 17:30:48,786 - FID at iteration 64000: 147.629882
+INFO - dpsgd_diffusion.py - 2025-03-24 17:31:22,208 - Eps-value after 91 epochs: 7.5100
+INFO - dpsgd_diffusion.py - 2025-03-24 17:31:41,152 - Loss: 0.2207, step: 64100
+INFO - dpsgd_diffusion.py - 2025-03-24 17:32:32,233 - Loss: 0.2378, step: 64200
+INFO - dpsgd_diffusion.py - 2025-03-24 17:33:24,347 - Loss: 0.2502, step: 64300
+INFO - dpsgd_diffusion.py - 2025-03-24 17:34:16,161 - Loss: 0.2226, step: 64400
+INFO - dpsgd_diffusion.py - 2025-03-24 17:35:07,101 - Loss: 0.2248, step: 64500
+INFO - dpsgd_diffusion.py - 2025-03-24 17:35:59,720 - Loss: 0.2264, step: 64600
+INFO - dpsgd_diffusion.py - 2025-03-24 17:36:51,630 - Loss: 0.2529, step: 64700
+INFO - dpsgd_diffusion.py - 2025-03-24 17:37:26,917 - Eps-value after 92 epochs: 7.5567
+INFO - dpsgd_diffusion.py - 2025-03-24 17:37:43,215 - Loss: 0.2331, step: 64800
+INFO - dpsgd_diffusion.py - 2025-03-24 17:38:33,531 - Loss: 0.2315, step: 64900
+INFO - dpsgd_diffusion.py - 2025-03-24 17:39:25,327 - Loss: 0.2459, step: 65000
+INFO - dpsgd_diffusion.py - 2025-03-24 17:40:17,043 - Loss: 0.2450, step: 65100
+INFO - dpsgd_diffusion.py - 2025-03-24 17:41:08,198 - Loss: 0.2568, step: 65200
+INFO - dpsgd_diffusion.py - 2025-03-24 17:41:59,558 - Loss: 0.2466, step: 65300
+INFO - dpsgd_diffusion.py - 2025-03-24 17:42:50,978 - Loss: 0.2285, step: 65400
+INFO - dpsgd_diffusion.py - 2025-03-24 17:43:27,621 - Eps-value after 93 epochs: 7.6034
+INFO - dpsgd_diffusion.py - 2025-03-24 17:43:41,941 - Loss: 0.2062, step: 65500
+INFO - dpsgd_diffusion.py - 2025-03-24 17:44:33,093 - Loss: 0.2178, step: 65600
+INFO - dpsgd_diffusion.py - 2025-03-24 17:45:24,829 - Loss: 0.2533, step: 65700
+INFO - dpsgd_diffusion.py - 2025-03-24 17:46:14,583 - Loss: 0.2343, step: 65800
+INFO - dpsgd_diffusion.py - 2025-03-24 17:47:04,669 - Loss: 0.2324, step: 65900
+INFO - dpsgd_diffusion.py - 2025-03-24 17:47:55,115 - Loss: 0.2849, step: 66000
+INFO - dpsgd_diffusion.py - 2025-03-24 17:47:55,154 - Saving snapshot checkpoint and sampling single batch at iteration 66000.
+WARNING - image.py - 2025-03-24 17:47:55,768 - 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 - 2025-03-24 17:48:20,714 - FID at iteration 66000: 147.221193
+INFO - dpsgd_diffusion.py - 2025-03-24 17:49:15,442 - Loss: 0.2171, step: 66100
+INFO - dpsgd_diffusion.py - 2025-03-24 17:49:53,748 - Eps-value after 94 epochs: 7.6490
+INFO - dpsgd_diffusion.py - 2025-03-24 17:50:06,508 - Loss: 0.2034, step: 66200
+INFO - dpsgd_diffusion.py - 2025-03-24 17:50:57,866 - Loss: 0.2230, step: 66300
+INFO - dpsgd_diffusion.py - 2025-03-24 17:51:49,014 - Loss: 0.2195, step: 66400
+INFO - dpsgd_diffusion.py - 2025-03-24 17:52:41,217 - Loss: 0.2473, step: 66500
+INFO - dpsgd_diffusion.py - 2025-03-24 17:53:32,459 - Loss: 0.2198, step: 66600
+INFO - dpsgd_diffusion.py - 2025-03-24 17:54:24,513 - Loss: 0.2424, step: 66700
+INFO - dpsgd_diffusion.py - 2025-03-24 17:55:16,652 - Loss: 0.2476, step: 66800
+INFO - dpsgd_diffusion.py - 2025-03-24 17:55:58,596 - Eps-value after 95 epochs: 7.6946
+INFO - dpsgd_diffusion.py - 2025-03-24 17:56:08,917 - Loss: 0.2056, step: 66900
+INFO - dpsgd_diffusion.py - 2025-03-24 17:57:00,290 - Loss: 0.2206, step: 67000
+INFO - dpsgd_diffusion.py - 2025-03-24 17:57:52,892 - Loss: 0.2202, step: 67100
+INFO - dpsgd_diffusion.py - 2025-03-24 17:58:44,085 - Loss: 0.2465, step: 67200
+INFO - dpsgd_diffusion.py - 2025-03-24 17:59:35,868 - Loss: 0.2641, step: 67300
+INFO - dpsgd_diffusion.py - 2025-03-24 18:00:27,402 - Loss: 0.1984, step: 67400
+INFO - dpsgd_diffusion.py - 2025-03-24 18:01:18,548 - Loss: 0.2291, step: 67500
+INFO - dpsgd_diffusion.py - 2025-03-24 18:02:01,388 - Eps-value after 96 epochs: 7.7401
+INFO - dpsgd_diffusion.py - 2025-03-24 18:02:09,876 - Loss: 0.2399, step: 67600
+INFO - dpsgd_diffusion.py - 2025-03-24 18:03:02,169 - Loss: 0.2463, step: 67700
+INFO - dpsgd_diffusion.py - 2025-03-24 18:03:54,473 - Loss: 0.2066, step: 67800
+INFO - dpsgd_diffusion.py - 2025-03-24 18:04:44,690 - Loss: 0.2490, step: 67900
+INFO - dpsgd_diffusion.py - 2025-03-24 18:05:37,157 - Loss: 0.1972, step: 68000
+INFO - dpsgd_diffusion.py - 2025-03-24 18:05:37,162 - Saving snapshot checkpoint and sampling single batch at iteration 68000.
+WARNING - image.py - 2025-03-24 18:05:37,795 - 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 - 2025-03-24 18:06:04,625 - FID at iteration 68000: 145.919946
+INFO - dpsgd_diffusion.py - 2025-03-24 18:06:56,884 - Loss: 0.2035, step: 68100
+INFO - dpsgd_diffusion.py - 2025-03-24 18:07:48,447 - Loss: 0.2333, step: 68200
+INFO - dpsgd_diffusion.py - 2025-03-24 18:08:33,633 - Eps-value after 97 epochs: 7.7856
+INFO - dpsgd_diffusion.py - 2025-03-24 18:08:39,988 - Loss: 0.2322, step: 68300
+INFO - dpsgd_diffusion.py - 2025-03-24 18:09:31,945 - Loss: 0.2299, step: 68400
+INFO - dpsgd_diffusion.py - 2025-03-24 18:10:23,499 - Loss: 0.2416, step: 68500
+INFO - dpsgd_diffusion.py - 2025-03-24 18:11:13,945 - Loss: 0.2407, step: 68600
+INFO - dpsgd_diffusion.py - 2025-03-24 18:12:06,117 - Loss: 0.2183, step: 68700
+INFO - dpsgd_diffusion.py - 2025-03-24 18:12:57,374 - Loss: 0.2280, step: 68800
+INFO - dpsgd_diffusion.py - 2025-03-24 18:13:50,231 - Loss: 0.2360, step: 68900
+INFO - dpsgd_diffusion.py - 2025-03-24 18:14:37,915 - Eps-value after 98 epochs: 7.8311
+INFO - dpsgd_diffusion.py - 2025-03-24 18:14:42,165 - Loss: 0.1979, step: 69000
+INFO - dpsgd_diffusion.py - 2025-03-24 18:15:33,816 - Loss: 0.2126, step: 69100
+INFO - dpsgd_diffusion.py - 2025-03-24 18:16:25,375 - Loss: 0.2346, step: 69200
+INFO - dpsgd_diffusion.py - 2025-03-24 18:17:17,525 - Loss: 0.2224, step: 69300
+INFO - dpsgd_diffusion.py - 2025-03-24 18:18:08,905 - Loss: 0.2280, step: 69400
+INFO - dpsgd_diffusion.py - 2025-03-24 18:19:00,068 - Loss: 0.2370, step: 69500
+INFO - dpsgd_diffusion.py - 2025-03-24 18:19:50,837 - Loss: 0.2004, step: 69600
+INFO - dpsgd_diffusion.py - 2025-03-24 18:20:40,333 - Eps-value after 99 epochs: 7.8767
+INFO - dpsgd_diffusion.py - 2025-03-24 18:20:42,458 - Loss: 0.2313, step: 69700
+INFO - dpsgd_diffusion.py - 2025-03-24 18:21:34,542 - Loss: 0.2162, step: 69800
+INFO - dpsgd_diffusion.py - 2025-03-24 18:22:26,704 - Loss: 0.2103, step: 69900
+INFO - dpsgd_diffusion.py - 2025-03-24 18:23:18,465 - Loss: 0.2273, step: 70000
+INFO - dpsgd_diffusion.py - 2025-03-24 18:23:18,500 - Saving snapshot checkpoint and sampling single batch at iteration 70000.
+WARNING - image.py - 2025-03-24 18:23:19,069 - 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 - 2025-03-24 18:23:47,002 - FID at iteration 70000: 145.709806
+INFO - dpsgd_diffusion.py - 2025-03-24 18:24:38,955 - Loss: 0.2310, step: 70100
+INFO - dpsgd_diffusion.py - 2025-03-24 18:25:30,637 - Loss: 0.2204, step: 70200
+INFO - dpsgd_diffusion.py - 2025-03-24 18:26:22,261 - Loss: 0.2276, step: 70300
+INFO - dpsgd_diffusion.py - 2025-03-24 18:27:14,693 - Loss: 0.2254, step: 70400
+INFO - dpsgd_diffusion.py - 2025-03-24 18:27:14,727 - Eps-value after 100 epochs: 7.9219
+INFO - dpsgd_diffusion.py - 2025-03-24 18:28:05,241 - Loss: 0.2104, step: 70500
+INFO - dpsgd_diffusion.py - 2025-03-24 18:28:55,947 - Loss: 0.2420, step: 70600
+INFO - dpsgd_diffusion.py - 2025-03-24 18:29:46,104 - Loss: 0.2334, step: 70700
+INFO - dpsgd_diffusion.py - 2025-03-24 18:30:38,564 - Loss: 0.2294, step: 70800
+INFO - dpsgd_diffusion.py - 2025-03-24 18:31:31,169 - Loss: 0.2787, step: 70900
+INFO - dpsgd_diffusion.py - 2025-03-24 18:32:22,160 - Loss: 0.2324, step: 71000
+INFO - dpsgd_diffusion.py - 2025-03-24 18:33:13,695 - Loss: 0.2050, step: 71100
+INFO - dpsgd_diffusion.py - 2025-03-24 18:33:15,746 - Eps-value after 101 epochs: 7.9663
+INFO - dpsgd_diffusion.py - 2025-03-24 18:34:04,914 - Loss: 0.2057, step: 71200
+INFO - dpsgd_diffusion.py - 2025-03-24 18:34:56,104 - Loss: 0.2440, step: 71300
+INFO - dpsgd_diffusion.py - 2025-03-24 18:35:48,339 - Loss: 0.2514, step: 71400
+INFO - dpsgd_diffusion.py - 2025-03-24 18:36:39,359 - Loss: 0.2310, step: 71500
+INFO - dpsgd_diffusion.py - 2025-03-24 18:37:30,763 - Loss: 0.2067, step: 71600
+INFO - dpsgd_diffusion.py - 2025-03-24 18:38:22,066 - Loss: 0.2293, step: 71700
+INFO - dpsgd_diffusion.py - 2025-03-24 18:39:14,377 - Loss: 0.2145, step: 71800
+INFO - dpsgd_diffusion.py - 2025-03-24 18:39:18,738 - Eps-value after 102 epochs: 8.0106
+INFO - dpsgd_diffusion.py - 2025-03-24 18:40:07,610 - Loss: 0.2137, step: 71900
+INFO - dpsgd_diffusion.py - 2025-03-24 18:40:59,772 - Loss: 0.2233, step: 72000
+INFO - dpsgd_diffusion.py - 2025-03-24 18:40:59,784 - Saving snapshot checkpoint and sampling single batch at iteration 72000.
+WARNING - image.py - 2025-03-24 18:41:00,369 - 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 - 2025-03-24 18:41:29,367 - FID at iteration 72000: 144.691971
+INFO - dpsgd_diffusion.py - 2025-03-24 18:42:21,873 - Loss: 0.2187, step: 72100
+INFO - dpsgd_diffusion.py - 2025-03-24 18:43:13,359 - Loss: 0.2165, step: 72200
+INFO - dpsgd_diffusion.py - 2025-03-24 18:44:04,857 - Loss: 0.2185, step: 72300
+INFO - dpsgd_diffusion.py - 2025-03-24 18:44:57,458 - Loss: 0.2133, step: 72400
+INFO - dpsgd_diffusion.py - 2025-03-24 18:45:49,537 - Loss: 0.2148, step: 72500
+INFO - dpsgd_diffusion.py - 2025-03-24 18:45:55,590 - Eps-value after 103 epochs: 8.0550
+INFO - dpsgd_diffusion.py - 2025-03-24 18:46:41,399 - Loss: 0.2199, step: 72600
+INFO - dpsgd_diffusion.py - 2025-03-24 18:47:32,545 - Loss: 0.2737, step: 72700
+INFO - dpsgd_diffusion.py - 2025-03-24 18:48:24,186 - Loss: 0.2396, step: 72800
+INFO - dpsgd_diffusion.py - 2025-03-24 18:49:15,091 - Loss: 0.2272, step: 72900
+INFO - dpsgd_diffusion.py - 2025-03-24 18:50:05,919 - Loss: 0.2423, step: 73000
+INFO - dpsgd_diffusion.py - 2025-03-24 18:50:56,728 - Loss: 0.2337, step: 73100
+INFO - dpsgd_diffusion.py - 2025-03-24 18:51:47,219 - Loss: 0.1951, step: 73200
+INFO - dpsgd_diffusion.py - 2025-03-24 18:51:55,452 - Eps-value after 104 epochs: 8.0993
+INFO - dpsgd_diffusion.py - 2025-03-24 18:52:39,715 - Loss: 0.2347, step: 73300
+INFO - dpsgd_diffusion.py - 2025-03-24 18:53:31,874 - Loss: 0.2256, step: 73400
+INFO - dpsgd_diffusion.py - 2025-03-24 18:54:23,982 - Loss: 0.2294, step: 73500
+INFO - dpsgd_diffusion.py - 2025-03-24 18:55:17,587 - Loss: 0.1981, step: 73600
+INFO - dpsgd_diffusion.py - 2025-03-24 18:56:09,271 - Loss: 0.2198, step: 73700
+INFO - dpsgd_diffusion.py - 2025-03-24 18:57:00,777 - Loss: 0.2124, step: 73800
+INFO - dpsgd_diffusion.py - 2025-03-24 18:57:54,313 - Loss: 0.2354, step: 73900
+INFO - dpsgd_diffusion.py - 2025-03-24 18:58:04,587 - Eps-value after 105 epochs: 8.1437
+INFO - dpsgd_diffusion.py - 2025-03-24 18:58:45,525 - Loss: 0.2521, step: 74000
+INFO - dpsgd_diffusion.py - 2025-03-24 18:58:45,565 - Saving snapshot checkpoint and sampling single batch at iteration 74000.
+WARNING - image.py - 2025-03-24 18:58:46,277 - 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 - 2025-03-24 18:59:14,083 - FID at iteration 74000: 143.875876
+INFO - dpsgd_diffusion.py - 2025-03-24 19:00:06,286 - Loss: 0.2300, step: 74100
+INFO - dpsgd_diffusion.py - 2025-03-24 19:00:57,160 - Loss: 0.2074, step: 74200
+INFO - dpsgd_diffusion.py - 2025-03-24 19:01:46,958 - Loss: 0.2095, step: 74300
+INFO - dpsgd_diffusion.py - 2025-03-24 19:02:39,000 - Loss: 0.2056, step: 74400
+INFO - dpsgd_diffusion.py - 2025-03-24 19:03:29,970 - Loss: 0.2309, step: 74500
+INFO - dpsgd_diffusion.py - 2025-03-24 19:04:21,973 - Loss: 0.2453, step: 74600
+INFO - dpsgd_diffusion.py - 2025-03-24 19:04:34,017 - Eps-value after 106 epochs: 8.1880
+INFO - dpsgd_diffusion.py - 2025-03-24 19:05:13,596 - Loss: 0.2594, step: 74700
+INFO - dpsgd_diffusion.py - 2025-03-24 19:06:05,955 - Loss: 0.2008, step: 74800
+INFO - dpsgd_diffusion.py - 2025-03-24 19:06:57,850 - Loss: 0.2440, step: 74900
+INFO - dpsgd_diffusion.py - 2025-03-24 19:07:48,402 - Loss: 0.2486, step: 75000
+INFO - dpsgd_diffusion.py - 2025-03-24 19:08:40,875 - Loss: 0.2298, step: 75100
+INFO - dpsgd_diffusion.py - 2025-03-24 19:09:33,874 - Loss: 0.2159, step: 75200
+INFO - dpsgd_diffusion.py - 2025-03-24 19:10:24,162 - Loss: 0.2057, step: 75300
+INFO - dpsgd_diffusion.py - 2025-03-24 19:10:38,165 - Eps-value after 107 epochs: 8.2324
+INFO - dpsgd_diffusion.py - 2025-03-24 19:11:15,433 - Loss: 0.2157, step: 75400
+INFO - dpsgd_diffusion.py - 2025-03-24 19:12:05,532 - Loss: 0.2273, step: 75500
+INFO - dpsgd_diffusion.py - 2025-03-24 19:12:57,736 - Loss: 0.2589, step: 75600
+INFO - dpsgd_diffusion.py - 2025-03-24 19:13:50,281 - Loss: 0.2424, step: 75700
+INFO - dpsgd_diffusion.py - 2025-03-24 19:14:42,707 - Loss: 0.1995, step: 75800
+INFO - dpsgd_diffusion.py - 2025-03-24 19:15:33,275 - Loss: 0.1974, step: 75900
+INFO - dpsgd_diffusion.py - 2025-03-24 19:16:24,755 - Loss: 0.1989, step: 76000
+INFO - dpsgd_diffusion.py - 2025-03-24 19:16:24,762 - Saving snapshot checkpoint and sampling single batch at iteration 76000.
+WARNING - image.py - 2025-03-24 19:16:25,362 - 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 - 2025-03-24 19:16:51,684 - FID at iteration 76000: 143.333690
+INFO - dpsgd_diffusion.py - 2025-03-24 19:17:10,540 - Eps-value after 108 epochs: 8.2756
+INFO - dpsgd_diffusion.py - 2025-03-24 19:17:45,591 - Loss: 0.2180, step: 76100
+INFO - dpsgd_diffusion.py - 2025-03-24 19:18:37,429 - Loss: 0.2388, step: 76200
+INFO - dpsgd_diffusion.py - 2025-03-24 19:19:28,716 - Loss: 0.2261, step: 76300
+INFO - dpsgd_diffusion.py - 2025-03-24 19:20:18,996 - Loss: 0.2266, step: 76400
+INFO - dpsgd_diffusion.py - 2025-03-24 19:21:09,678 - Loss: 0.1886, step: 76500
+INFO - dpsgd_diffusion.py - 2025-03-24 19:22:00,472 - Loss: 0.2099, step: 76600
+INFO - dpsgd_diffusion.py - 2025-03-24 19:22:53,489 - Loss: 0.2303, step: 76700
+INFO - dpsgd_diffusion.py - 2025-03-24 19:23:12,744 - Eps-value after 109 epochs: 8.3188
+INFO - dpsgd_diffusion.py - 2025-03-24 19:23:45,268 - Loss: 0.2503, step: 76800
+INFO - dpsgd_diffusion.py - 2025-03-24 19:24:36,600 - Loss: 0.2238, step: 76900
+INFO - dpsgd_diffusion.py - 2025-03-24 19:25:28,460 - Loss: 0.2297, step: 77000
+INFO - dpsgd_diffusion.py - 2025-03-24 19:26:19,738 - Loss: 0.2202, step: 77100
+INFO - dpsgd_diffusion.py - 2025-03-24 19:27:10,226 - Loss: 0.2185, step: 77200
+INFO - dpsgd_diffusion.py - 2025-03-24 19:28:00,493 - Loss: 0.2165, step: 77300
+INFO - dpsgd_diffusion.py - 2025-03-24 19:28:52,833 - Loss: 0.2099, step: 77400
+INFO - dpsgd_diffusion.py - 2025-03-24 19:29:13,771 - Eps-value after 110 epochs: 8.3620
+INFO - dpsgd_diffusion.py - 2025-03-24 19:29:45,446 - Loss: 0.2425, step: 77500
+INFO - dpsgd_diffusion.py - 2025-03-24 19:30:36,239 - Loss: 0.2220, step: 77600
+INFO - dpsgd_diffusion.py - 2025-03-24 19:31:27,527 - Loss: 0.2403, step: 77700
+INFO - dpsgd_diffusion.py - 2025-03-24 19:32:18,995 - Loss: 0.2360, step: 77800
+INFO - dpsgd_diffusion.py - 2025-03-24 19:33:09,998 - Loss: 0.2210, step: 77900
+INFO - dpsgd_diffusion.py - 2025-03-24 19:34:00,984 - Loss: 0.2082, step: 78000
+INFO - dpsgd_diffusion.py - 2025-03-24 19:34:00,990 - Saving snapshot checkpoint and sampling single batch at iteration 78000.
+WARNING - image.py - 2025-03-24 19:34:01,627 - 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 - 2025-03-24 19:34:28,915 - FID at iteration 78000: 141.893035
+INFO - dpsgd_diffusion.py - 2025-03-24 19:35:20,952 - Loss: 0.2359, step: 78100
+INFO - dpsgd_diffusion.py - 2025-03-24 19:35:42,956 - Eps-value after 111 epochs: 8.4052
+INFO - dpsgd_diffusion.py - 2025-03-24 19:36:12,682 - Loss: 0.2502, step: 78200
+INFO - dpsgd_diffusion.py - 2025-03-24 19:37:05,006 - Loss: 0.2553, step: 78300
+INFO - dpsgd_diffusion.py - 2025-03-24 19:37:55,992 - Loss: 0.2021, step: 78400
+INFO - dpsgd_diffusion.py - 2025-03-24 19:38:47,696 - Loss: 0.2411, step: 78500
+INFO - dpsgd_diffusion.py - 2025-03-24 19:39:39,535 - Loss: 0.1949, step: 78600
+INFO - dpsgd_diffusion.py - 2025-03-24 19:40:32,735 - Loss: 0.2342, step: 78700
+INFO - dpsgd_diffusion.py - 2025-03-24 19:41:26,046 - Loss: 0.2428, step: 78800
+INFO - dpsgd_diffusion.py - 2025-03-24 19:41:51,205 - Eps-value after 112 epochs: 8.4484
+INFO - dpsgd_diffusion.py - 2025-03-24 19:42:17,887 - Loss: 0.2223, step: 78900
+INFO - dpsgd_diffusion.py - 2025-03-24 19:43:09,148 - Loss: 0.2371, step: 79000
+INFO - dpsgd_diffusion.py - 2025-03-24 19:44:01,236 - Loss: 0.2084, step: 79100
+INFO - dpsgd_diffusion.py - 2025-03-24 19:44:53,308 - Loss: 0.2217, step: 79200
+INFO - dpsgd_diffusion.py - 2025-03-24 19:45:43,544 - Loss: 0.2170, step: 79300
+INFO - dpsgd_diffusion.py - 2025-03-24 19:46:34,850 - Loss: 0.2310, step: 79400
+INFO - dpsgd_diffusion.py - 2025-03-24 19:47:26,575 - Loss: 0.2349, step: 79500
+INFO - dpsgd_diffusion.py - 2025-03-24 19:47:54,548 - Eps-value after 113 epochs: 8.4915
+INFO - dpsgd_diffusion.py - 2025-03-24 19:48:19,626 - Loss: 0.2166, step: 79600
+INFO - dpsgd_diffusion.py - 2025-03-24 19:49:11,549 - Loss: 0.2149, step: 79700
+INFO - dpsgd_diffusion.py - 2025-03-24 19:50:02,436 - Loss: 0.2359, step: 79800
+INFO - dpsgd_diffusion.py - 2025-03-24 19:50:53,216 - Loss: 0.2073, step: 79900
+INFO - dpsgd_diffusion.py - 2025-03-24 19:51:44,931 - Loss: 0.2447, step: 80000
+INFO - dpsgd_diffusion.py - 2025-03-24 19:51:44,945 - Saving snapshot checkpoint and sampling single batch at iteration 80000.
+WARNING - image.py - 2025-03-24 19:51:45,529 - 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 - 2025-03-24 19:52:11,642 - FID at iteration 80000: 140.833359
+INFO - dpsgd_diffusion.py - 2025-03-24 19:53:04,451 - Loss: 0.2383, step: 80100
+INFO - dpsgd_diffusion.py - 2025-03-24 19:53:55,177 - Loss: 0.2321, step: 80200
+INFO - dpsgd_diffusion.py - 2025-03-24 19:54:24,660 - Eps-value after 114 epochs: 8.5347
+INFO - dpsgd_diffusion.py - 2025-03-24 19:54:48,250 - Loss: 0.2085, step: 80300
+INFO - dpsgd_diffusion.py - 2025-03-24 19:55:40,665 - Loss: 0.2398, step: 80400
+INFO - dpsgd_diffusion.py - 2025-03-24 19:56:32,379 - Loss: 0.2181, step: 80500
+INFO - dpsgd_diffusion.py - 2025-03-24 19:57:24,578 - Loss: 0.2242, step: 80600
+INFO - dpsgd_diffusion.py - 2025-03-24 19:58:16,257 - Loss: 0.2190, step: 80700
+INFO - dpsgd_diffusion.py - 2025-03-24 19:59:08,021 - Loss: 0.2660, step: 80800
+INFO - dpsgd_diffusion.py - 2025-03-24 19:59:59,848 - Loss: 0.2124, step: 80900
+INFO - dpsgd_diffusion.py - 2025-03-24 20:00:31,415 - Eps-value after 115 epochs: 8.5779
+INFO - dpsgd_diffusion.py - 2025-03-24 20:00:52,647 - Loss: 0.2351, step: 81000
+INFO - dpsgd_diffusion.py - 2025-03-24 20:01:42,915 - Loss: 0.2362, step: 81100
+INFO - dpsgd_diffusion.py - 2025-03-24 20:02:34,073 - Loss: 0.2580, step: 81200
+INFO - dpsgd_diffusion.py - 2025-03-24 20:03:25,290 - Loss: 0.2510, step: 81300
+INFO - dpsgd_diffusion.py - 2025-03-24 20:04:15,777 - Loss: 0.2022, step: 81400
+INFO - dpsgd_diffusion.py - 2025-03-24 20:05:07,742 - Loss: 0.2217, step: 81500
+INFO - dpsgd_diffusion.py - 2025-03-24 20:05:58,488 - Loss: 0.2350, step: 81600
+INFO - dpsgd_diffusion.py - 2025-03-24 20:06:32,638 - Eps-value after 116 epochs: 8.6202
+INFO - dpsgd_diffusion.py - 2025-03-24 20:06:51,812 - Loss: 0.2256, step: 81700
+INFO - dpsgd_diffusion.py - 2025-03-24 20:07:43,365 - Loss: 0.2088, step: 81800
+INFO - dpsgd_diffusion.py - 2025-03-24 20:08:35,836 - Loss: 0.2145, step: 81900
+INFO - dpsgd_diffusion.py - 2025-03-24 20:09:27,158 - Loss: 0.2034, step: 82000
+INFO - dpsgd_diffusion.py - 2025-03-24 20:09:27,165 - Saving snapshot checkpoint and sampling single batch at iteration 82000.
+WARNING - image.py - 2025-03-24 20:09:27,747 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2025-03-24 20:09:56,141 - FID at iteration 82000: 140.324148
+INFO - dpsgd_diffusion.py - 2025-03-24 20:10:48,233 - Loss: 0.2304, step: 82100
+INFO - dpsgd_diffusion.py - 2025-03-24 20:11:38,887 - Loss: 0.2078, step: 82200
+INFO - dpsgd_diffusion.py - 2025-03-24 20:12:28,662 - Loss: 0.2294, step: 82300
+INFO - dpsgd_diffusion.py - 2025-03-24 20:13:03,602 - Eps-value after 117 epochs: 8.6622
+INFO - dpsgd_diffusion.py - 2025-03-24 20:13:19,945 - Loss: 0.2358, step: 82400
+INFO - dpsgd_diffusion.py - 2025-03-24 20:14:10,655 - Loss: 0.2332, step: 82500
+INFO - dpsgd_diffusion.py - 2025-03-24 20:15:02,636 - Loss: 0.2119, step: 82600
+INFO - dpsgd_diffusion.py - 2025-03-24 20:15:53,828 - Loss: 0.2282, step: 82700
+INFO - dpsgd_diffusion.py - 2025-03-24 20:16:45,603 - Loss: 0.2396, step: 82800
+INFO - dpsgd_diffusion.py - 2025-03-24 20:17:35,852 - Loss: 0.2264, step: 82900
+INFO - dpsgd_diffusion.py - 2025-03-24 20:18:27,328 - Loss: 0.2376, step: 83000
+INFO - dpsgd_diffusion.py - 2025-03-24 20:19:04,918 - Eps-value after 118 epochs: 8.7042
+INFO - dpsgd_diffusion.py - 2025-03-24 20:19:19,491 - Loss: 0.2122, step: 83100
+INFO - dpsgd_diffusion.py - 2025-03-24 20:20:10,064 - Loss: 0.2177, step: 83200
+INFO - dpsgd_diffusion.py - 2025-03-24 20:21:01,519 - Loss: 0.2046, step: 83300
+INFO - dpsgd_diffusion.py - 2025-03-24 20:21:53,167 - Loss: 0.2225, step: 83400
+INFO - dpsgd_diffusion.py - 2025-03-24 20:22:45,118 - Loss: 0.2580, step: 83500
+INFO - dpsgd_diffusion.py - 2025-03-24 20:23:36,920 - Loss: 0.2167, step: 83600
+INFO - dpsgd_diffusion.py - 2025-03-24 20:24:28,321 - Loss: 0.2549, step: 83700
+INFO - dpsgd_diffusion.py - 2025-03-24 20:25:07,546 - Eps-value after 119 epochs: 8.7462
+INFO - dpsgd_diffusion.py - 2025-03-24 20:25:20,066 - Loss: 0.1945, step: 83800
+INFO - dpsgd_diffusion.py - 2025-03-24 20:26:11,495 - Loss: 0.2198, step: 83900
+INFO - dpsgd_diffusion.py - 2025-03-24 20:27:02,798 - Loss: 0.2275, step: 84000
+INFO - dpsgd_diffusion.py - 2025-03-24 20:27:02,838 - Saving snapshot checkpoint and sampling single batch at iteration 84000.
+WARNING - image.py - 2025-03-24 20:27:03,425 - 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 - 2025-03-24 20:27:31,948 - FID at iteration 84000: 139.189438
+INFO - dpsgd_diffusion.py - 2025-03-24 20:28:23,650 - Loss: 0.2300, step: 84100
+INFO - dpsgd_diffusion.py - 2025-03-24 20:29:15,790 - Loss: 0.2228, step: 84200
+INFO - dpsgd_diffusion.py - 2025-03-24 20:30:07,979 - Loss: 0.2028, step: 84300
+INFO - dpsgd_diffusion.py - 2025-03-24 20:30:58,041 - Loss: 0.2170, step: 84400
+INFO - dpsgd_diffusion.py - 2025-03-24 20:31:38,986 - Eps-value after 120 epochs: 8.7882
+INFO - dpsgd_diffusion.py - 2025-03-24 20:31:49,619 - Loss: 0.2274, step: 84500
+INFO - dpsgd_diffusion.py - 2025-03-24 20:32:41,204 - Loss: 0.2169, step: 84600
+INFO - dpsgd_diffusion.py - 2025-03-24 20:33:33,703 - Loss: 0.2271, step: 84700
+INFO - dpsgd_diffusion.py - 2025-03-24 20:34:25,309 - Loss: 0.2163, step: 84800
+INFO - dpsgd_diffusion.py - 2025-03-24 20:35:16,306 - Loss: 0.2658, step: 84900
+INFO - dpsgd_diffusion.py - 2025-03-24 20:36:08,870 - Loss: 0.2239, step: 85000
+INFO - dpsgd_diffusion.py - 2025-03-24 20:37:00,426 - Loss: 0.2119, step: 85100
+INFO - dpsgd_diffusion.py - 2025-03-24 20:37:43,766 - Eps-value after 121 epochs: 8.8302
+INFO - dpsgd_diffusion.py - 2025-03-24 20:37:52,422 - Loss: 0.2270, step: 85200
+INFO - dpsgd_diffusion.py - 2025-03-24 20:38:44,116 - Loss: 0.2226, step: 85300
+INFO - dpsgd_diffusion.py - 2025-03-24 20:39:35,975 - Loss: 0.2035, step: 85400
+INFO - dpsgd_diffusion.py - 2025-03-24 20:40:27,033 - Loss: 0.2430, step: 85500
+INFO - dpsgd_diffusion.py - 2025-03-24 20:41:17,325 - Loss: 0.2149, step: 85600
+INFO - dpsgd_diffusion.py - 2025-03-24 20:42:07,357 - Loss: 0.2305, step: 85700
+INFO - dpsgd_diffusion.py - 2025-03-24 20:43:00,703 - Loss: 0.2155, step: 85800
+INFO - dpsgd_diffusion.py - 2025-03-24 20:43:47,342 - Eps-value after 122 epochs: 8.8722
+INFO - dpsgd_diffusion.py - 2025-03-24 20:43:53,730 - Loss: 0.2173, step: 85900
+INFO - dpsgd_diffusion.py - 2025-03-24 20:44:44,931 - Loss: 0.2432, step: 86000
+INFO - dpsgd_diffusion.py - 2025-03-24 20:44:44,937 - Saving snapshot checkpoint and sampling single batch at iteration 86000.
+WARNING - image.py - 2025-03-24 20:44:45,506 - 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 - 2025-03-24 20:45:11,966 - FID at iteration 86000: 138.730554
+INFO - dpsgd_diffusion.py - 2025-03-24 20:46:04,890 - Loss: 0.2293, step: 86100
+INFO - dpsgd_diffusion.py - 2025-03-24 20:46:54,425 - Loss: 0.2048, step: 86200
+INFO - dpsgd_diffusion.py - 2025-03-24 20:47:44,903 - Loss: 0.2084, step: 86300
+INFO - dpsgd_diffusion.py - 2025-03-24 20:48:36,510 - Loss: 0.2473, step: 86400
+INFO - dpsgd_diffusion.py - 2025-03-24 20:49:27,825 - Loss: 0.2570, step: 86500
+INFO - dpsgd_diffusion.py - 2025-03-24 20:50:14,157 - Eps-value after 123 epochs: 8.9142
+INFO - dpsgd_diffusion.py - 2025-03-24 20:50:18,388 - Loss: 0.2256, step: 86600
+INFO - dpsgd_diffusion.py - 2025-03-24 20:51:10,297 - Loss: 0.2215, step: 86700
+INFO - dpsgd_diffusion.py - 2025-03-24 20:52:00,430 - Loss: 0.2434, step: 86800
+INFO - dpsgd_diffusion.py - 2025-03-24 20:52:50,704 - Loss: 0.2198, step: 86900
+INFO - dpsgd_diffusion.py - 2025-03-24 20:53:42,315 - Loss: 0.2264, step: 87000
+INFO - dpsgd_diffusion.py - 2025-03-24 20:54:34,233 - Loss: 0.2122, step: 87100
+INFO - dpsgd_diffusion.py - 2025-03-24 20:55:24,952 - Loss: 0.2323, step: 87200
+INFO - dpsgd_diffusion.py - 2025-03-24 20:56:13,932 - Eps-value after 124 epochs: 8.9562
+INFO - dpsgd_diffusion.py - 2025-03-24 20:56:15,930 - Loss: 0.2363, step: 87300
+INFO - dpsgd_diffusion.py - 2025-03-24 20:57:05,675 - Loss: 0.2169, step: 87400
+INFO - dpsgd_diffusion.py - 2025-03-24 20:57:57,214 - Loss: 0.2139, step: 87500
+INFO - dpsgd_diffusion.py - 2025-03-24 20:58:48,296 - Loss: 0.2495, step: 87600
+INFO - dpsgd_diffusion.py - 2025-03-24 20:59:39,208 - Loss: 0.2286, step: 87700
+INFO - dpsgd_diffusion.py - 2025-03-24 21:00:30,339 - Loss: 0.2228, step: 87800
+INFO - dpsgd_diffusion.py - 2025-03-24 21:01:21,866 - Loss: 0.1974, step: 87900
+INFO - dpsgd_diffusion.py - 2025-03-24 21:02:14,003 - Loss: 0.2320, step: 88000
+INFO - dpsgd_diffusion.py - 2025-03-24 21:02:14,041 - Eps-value after 125 epochs: 8.9974
+INFO - dpsgd_diffusion.py - 2025-03-24 21:02:14,047 - Saving snapshot checkpoint and sampling single batch at iteration 88000.
+WARNING - image.py - 2025-03-24 21:02:14,628 - 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 - 2025-03-24 21:02:41,923 - FID at iteration 88000: 137.285706
+INFO - dpsgd_diffusion.py - 2025-03-24 21:03:34,566 - Loss: 0.2087, step: 88100
+INFO - dpsgd_diffusion.py - 2025-03-24 21:04:26,393 - Loss: 0.2230, step: 88200
+INFO - dpsgd_diffusion.py - 2025-03-24 21:05:18,625 - Loss: 0.2073, step: 88300
+INFO - dpsgd_diffusion.py - 2025-03-24 21:06:11,007 - Loss: 0.2376, step: 88400
+INFO - dpsgd_diffusion.py - 2025-03-24 21:07:01,328 - Loss: 0.2025, step: 88500
+INFO - dpsgd_diffusion.py - 2025-03-24 21:07:52,876 - Loss: 0.2360, step: 88600
+INFO - dpsgd_diffusion.py - 2025-03-24 21:08:44,177 - Loss: 0.2445, step: 88700
+INFO - dpsgd_diffusion.py - 2025-03-24 21:08:46,239 - Eps-value after 126 epochs: 9.0382
+INFO - dpsgd_diffusion.py - 2025-03-24 21:09:35,802 - Loss: 0.2475, step: 88800
+INFO - dpsgd_diffusion.py - 2025-03-24 21:10:27,330 - Loss: 0.2526, step: 88900
+INFO - dpsgd_diffusion.py - 2025-03-24 21:11:18,123 - Loss: 0.2362, step: 89000
+INFO - dpsgd_diffusion.py - 2025-03-24 21:12:08,206 - Loss: 0.2389, step: 89100
+INFO - dpsgd_diffusion.py - 2025-03-24 21:12:59,465 - Loss: 0.2158, step: 89200
+INFO - dpsgd_diffusion.py - 2025-03-24 21:13:50,134 - Loss: 0.2058, step: 89300
+INFO - dpsgd_diffusion.py - 2025-03-24 21:14:41,317 - Loss: 0.2197, step: 89400
+INFO - dpsgd_diffusion.py - 2025-03-24 21:14:45,376 - Eps-value after 127 epochs: 9.0791
+INFO - dpsgd_diffusion.py - 2025-03-24 21:15:32,999 - Loss: 0.2123, step: 89500
+INFO - dpsgd_diffusion.py - 2025-03-24 21:16:25,826 - Loss: 0.2143, step: 89600
+INFO - dpsgd_diffusion.py - 2025-03-24 21:17:17,729 - Loss: 0.2334, step: 89700
+INFO - dpsgd_diffusion.py - 2025-03-24 21:18:08,589 - Loss: 0.2643, step: 89800
+INFO - dpsgd_diffusion.py - 2025-03-24 21:18:58,466 - Loss: 0.2322, step: 89900
+INFO - dpsgd_diffusion.py - 2025-03-24 21:19:49,448 - Loss: 0.2117, step: 90000
+INFO - dpsgd_diffusion.py - 2025-03-24 21:19:49,454 - Saving snapshot checkpoint and sampling single batch at iteration 90000.
+WARNING - image.py - 2025-03-24 21:19:50,043 - 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 - 2025-03-24 21:20:18,082 - FID at iteration 90000: 137.417885
+INFO - dpsgd_diffusion.py - 2025-03-24 21:21:10,407 - Loss: 0.1955, step: 90100
+INFO - dpsgd_diffusion.py - 2025-03-24 21:21:16,483 - Eps-value after 128 epochs: 9.1199
+INFO - dpsgd_diffusion.py - 2025-03-24 21:22:01,752 - Loss: 0.2407, step: 90200
+INFO - dpsgd_diffusion.py - 2025-03-24 21:22:52,195 - Loss: 0.2401, step: 90300
+INFO - dpsgd_diffusion.py - 2025-03-24 21:23:44,209 - Loss: 0.2165, step: 90400
+INFO - dpsgd_diffusion.py - 2025-03-24 21:24:35,586 - Loss: 0.2375, step: 90500
+INFO - dpsgd_diffusion.py - 2025-03-24 21:25:27,682 - Loss: 0.2445, step: 90600
+INFO - dpsgd_diffusion.py - 2025-03-24 21:26:18,971 - Loss: 0.2309, step: 90700
+INFO - dpsgd_diffusion.py - 2025-03-24 21:27:10,491 - Loss: 0.1999, step: 90800
+INFO - dpsgd_diffusion.py - 2025-03-24 21:27:18,563 - Eps-value after 129 epochs: 9.1608
+INFO - dpsgd_diffusion.py - 2025-03-24 21:28:02,694 - Loss: 0.2430, step: 90900
+INFO - dpsgd_diffusion.py - 2025-03-24 21:28:52,920 - Loss: 0.2015, step: 91000
+INFO - dpsgd_diffusion.py - 2025-03-24 21:29:44,686 - Loss: 0.2186, step: 91100
+INFO - dpsgd_diffusion.py - 2025-03-24 21:30:34,757 - Loss: 0.2323, step: 91200
+INFO - dpsgd_diffusion.py - 2025-03-24 21:31:26,542 - Loss: 0.2373, step: 91300
+INFO - dpsgd_diffusion.py - 2025-03-24 21:32:17,439 - Loss: 0.2266, step: 91400
+INFO - dpsgd_diffusion.py - 2025-03-24 21:33:10,639 - Loss: 0.2229, step: 91500
+INFO - dpsgd_diffusion.py - 2025-03-24 21:33:20,678 - Eps-value after 130 epochs: 9.2016
+INFO - dpsgd_diffusion.py - 2025-03-24 21:34:01,992 - Loss: 0.2223, step: 91600
+INFO - dpsgd_diffusion.py - 2025-03-24 21:34:53,346 - Loss: 0.2266, step: 91700
+INFO - dpsgd_diffusion.py - 2025-03-24 21:35:44,798 - Loss: 0.2227, step: 91800
+INFO - dpsgd_diffusion.py - 2025-03-24 21:36:36,661 - Loss: 0.2309, step: 91900
+INFO - dpsgd_diffusion.py - 2025-03-24 21:37:28,614 - Loss: 0.2148, step: 92000
+INFO - dpsgd_diffusion.py - 2025-03-24 21:37:28,620 - Saving snapshot checkpoint and sampling single batch at iteration 92000.
+WARNING - image.py - 2025-03-24 21:37:29,190 - 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 - 2025-03-24 21:37:56,640 - FID at iteration 92000: 136.486493
+INFO - dpsgd_diffusion.py - 2025-03-24 21:38:47,631 - Loss: 0.2318, step: 92100
+INFO - dpsgd_diffusion.py - 2025-03-24 21:39:38,637 - Loss: 0.2195, step: 92200
+INFO - dpsgd_diffusion.py - 2025-03-24 21:39:50,637 - Eps-value after 131 epochs: 9.2425
+INFO - dpsgd_diffusion.py - 2025-03-24 21:40:28,785 - Loss: 0.2305, step: 92300
+INFO - dpsgd_diffusion.py - 2025-03-24 21:41:20,435 - Loss: 0.2168, step: 92400
+INFO - dpsgd_diffusion.py - 2025-03-24 21:42:12,085 - Loss: 0.2044, step: 92500
+INFO - dpsgd_diffusion.py - 2025-03-24 21:43:04,634 - Loss: 0.2239, step: 92600
+INFO - dpsgd_diffusion.py - 2025-03-24 21:43:55,851 - Loss: 0.1939, step: 92700
+INFO - dpsgd_diffusion.py - 2025-03-24 21:44:47,561 - Loss: 0.2488, step: 92800
+INFO - dpsgd_diffusion.py - 2025-03-24 21:45:38,923 - Loss: 0.2052, step: 92900
+INFO - dpsgd_diffusion.py - 2025-03-24 21:45:52,958 - Eps-value after 132 epochs: 9.2833
+INFO - dpsgd_diffusion.py - 2025-03-24 21:46:30,749 - Loss: 0.2202, step: 93000
+INFO - dpsgd_diffusion.py - 2025-03-24 21:47:22,443 - Loss: 0.2311, step: 93100
+INFO - dpsgd_diffusion.py - 2025-03-24 21:48:13,898 - Loss: 0.2288, step: 93200
+INFO - dpsgd_diffusion.py - 2025-03-24 21:49:05,228 - Loss: 0.2255, step: 93300
+INFO - dpsgd_diffusion.py - 2025-03-24 21:49:55,712 - Loss: 0.2227, step: 93400
+INFO - dpsgd_diffusion.py - 2025-03-24 21:50:46,751 - Loss: 0.2203, step: 93500
+INFO - dpsgd_diffusion.py - 2025-03-24 21:51:37,818 - Loss: 0.2156, step: 93600
+INFO - dpsgd_diffusion.py - 2025-03-24 21:51:53,842 - Eps-value after 133 epochs: 9.3242
+INFO - dpsgd_diffusion.py - 2025-03-24 21:52:27,878 - Loss: 0.2026, step: 93700
+INFO - dpsgd_diffusion.py - 2025-03-24 21:53:19,530 - Loss: 0.2632, step: 93800
+INFO - dpsgd_diffusion.py - 2025-03-24 21:54:12,305 - Loss: 0.2309, step: 93900
+INFO - dpsgd_diffusion.py - 2025-03-24 21:55:04,228 - Loss: 0.2344, step: 94000
+INFO - dpsgd_diffusion.py - 2025-03-24 21:55:04,263 - Saving snapshot checkpoint and sampling single batch at iteration 94000.
+WARNING - image.py - 2025-03-24 21:55:04,828 - 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 - 2025-03-24 21:55:32,466 - FID at iteration 94000: 136.591754
+INFO - dpsgd_diffusion.py - 2025-03-24 21:56:22,840 - Loss: 0.2176, step: 94100
+INFO - dpsgd_diffusion.py - 2025-03-24 21:57:14,522 - Loss: 0.2167, step: 94200
+INFO - dpsgd_diffusion.py - 2025-03-24 21:58:06,680 - Loss: 0.2474, step: 94300
+INFO - dpsgd_diffusion.py - 2025-03-24 21:58:24,528 - Eps-value after 134 epochs: 9.3650
+INFO - dpsgd_diffusion.py - 2025-03-24 21:58:56,871 - Loss: 0.2244, step: 94400
+INFO - dpsgd_diffusion.py - 2025-03-24 21:59:49,625 - Loss: 0.2526, step: 94500
+INFO - dpsgd_diffusion.py - 2025-03-24 22:00:40,972 - Loss: 0.2099, step: 94600
+INFO - dpsgd_diffusion.py - 2025-03-24 22:01:32,475 - Loss: 0.2323, step: 94700
+INFO - dpsgd_diffusion.py - 2025-03-24 22:02:24,932 - Loss: 0.2013, step: 94800
+INFO - dpsgd_diffusion.py - 2025-03-24 22:03:16,829 - Loss: 0.2230, step: 94900
+INFO - dpsgd_diffusion.py - 2025-03-24 22:04:07,711 - Loss: 0.2425, step: 95000
+INFO - dpsgd_diffusion.py - 2025-03-24 22:04:27,077 - Eps-value after 135 epochs: 9.4051
+INFO - dpsgd_diffusion.py - 2025-03-24 22:04:58,536 - Loss: 0.2244, step: 95100
+INFO - dpsgd_diffusion.py - 2025-03-24 22:05:49,853 - Loss: 0.2158, step: 95200
+INFO - dpsgd_diffusion.py - 2025-03-24 22:06:41,818 - Loss: 0.2222, step: 95300
+INFO - dpsgd_diffusion.py - 2025-03-24 22:07:33,892 - Loss: 0.2439, step: 95400
+INFO - dpsgd_diffusion.py - 2025-03-24 22:08:24,881 - Loss: 0.2304, step: 95500
+INFO - dpsgd_diffusion.py - 2025-03-24 22:09:16,741 - Loss: 0.1996, step: 95600
+INFO - dpsgd_diffusion.py - 2025-03-24 22:10:08,912 - Loss: 0.2034, step: 95700
+INFO - dpsgd_diffusion.py - 2025-03-24 22:10:32,194 - Eps-value after 136 epochs: 9.4448
+INFO - dpsgd_diffusion.py - 2025-03-24 22:11:01,344 - Loss: 0.1843, step: 95800
+INFO - dpsgd_diffusion.py - 2025-03-24 22:11:52,841 - Loss: 0.2116, step: 95900
+INFO - dpsgd_diffusion.py - 2025-03-24 22:12:44,561 - Loss: 0.2254, step: 96000
+INFO - dpsgd_diffusion.py - 2025-03-24 22:12:44,575 - Saving snapshot checkpoint and sampling single batch at iteration 96000.
+WARNING - image.py - 2025-03-24 22:12:45,142 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2025-03-24 22:13:11,836 - FID at iteration 96000: 136.717551
+INFO - dpsgd_diffusion.py - 2025-03-24 22:14:04,005 - Loss: 0.2353, step: 96100
+INFO - dpsgd_diffusion.py - 2025-03-24 22:14:55,275 - Loss: 0.2300, step: 96200
+INFO - dpsgd_diffusion.py - 2025-03-24 22:15:45,797 - Loss: 0.1936, step: 96300
+INFO - dpsgd_diffusion.py - 2025-03-24 22:16:36,948 - Loss: 0.2107, step: 96400
+INFO - dpsgd_diffusion.py - 2025-03-24 22:17:02,310 - Eps-value after 137 epochs: 9.4844
+INFO - dpsgd_diffusion.py - 2025-03-24 22:17:29,878 - Loss: 0.1955, step: 96500
+INFO - dpsgd_diffusion.py - 2025-03-24 22:18:22,029 - Loss: 0.2184, step: 96600
+INFO - dpsgd_diffusion.py - 2025-03-24 22:19:13,467 - Loss: 0.2323, step: 96700
+INFO - dpsgd_diffusion.py - 2025-03-24 22:20:04,094 - Loss: 0.2105, step: 96800
+INFO - dpsgd_diffusion.py - 2025-03-24 22:20:55,633 - Loss: 0.2199, step: 96900
+INFO - dpsgd_diffusion.py - 2025-03-24 22:21:46,602 - Loss: 0.2451, step: 97000
+INFO - dpsgd_diffusion.py - 2025-03-24 22:22:37,752 - Loss: 0.2167, step: 97100
+INFO - dpsgd_diffusion.py - 2025-03-24 22:23:04,268 - Eps-value after 138 epochs: 9.5241
+INFO - dpsgd_diffusion.py - 2025-03-24 22:23:29,801 - Loss: 0.2332, step: 97200
+INFO - dpsgd_diffusion.py - 2025-03-24 22:24:23,314 - Loss: 0.2413, step: 97300
+INFO - dpsgd_diffusion.py - 2025-03-24 22:25:15,697 - Loss: 0.1875, step: 97400
+INFO - dpsgd_diffusion.py - 2025-03-24 22:26:08,088 - Loss: 0.2079, step: 97500
+INFO - dpsgd_diffusion.py - 2025-03-24 22:26:58,555 - Loss: 0.2043, step: 97600
+INFO - dpsgd_diffusion.py - 2025-03-24 22:27:50,553 - Loss: 0.1984, step: 97700
+INFO - dpsgd_diffusion.py - 2025-03-24 22:28:41,980 - Loss: 0.1954, step: 97800
+INFO - dpsgd_diffusion.py - 2025-03-24 22:29:10,063 - Eps-value after 139 epochs: 9.5638
+INFO - dpsgd_diffusion.py - 2025-03-24 22:29:32,401 - Loss: 0.2086, step: 97900
+INFO - dpsgd_diffusion.py - 2025-03-24 22:30:23,023 - Loss: 0.1963, step: 98000
+INFO - dpsgd_diffusion.py - 2025-03-24 22:30:23,061 - Saving snapshot checkpoint and sampling single batch at iteration 98000.
+WARNING - image.py - 2025-03-24 22:30:23,628 - 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 - 2025-03-24 22:30:51,367 - FID at iteration 98000: 135.706454
+INFO - dpsgd_diffusion.py - 2025-03-24 22:31:44,643 - Loss: 0.1958, step: 98100
+INFO - dpsgd_diffusion.py - 2025-03-24 22:32:35,982 - Loss: 0.2179, step: 98200
+INFO - dpsgd_diffusion.py - 2025-03-24 22:33:26,824 - Loss: 0.2087, step: 98300
+INFO - dpsgd_diffusion.py - 2025-03-24 22:34:18,510 - Loss: 0.2189, step: 98400
+INFO - dpsgd_diffusion.py - 2025-03-24 22:35:09,213 - Loss: 0.2202, step: 98500
+INFO - dpsgd_diffusion.py - 2025-03-24 22:35:40,653 - Eps-value after 140 epochs: 9.6035
+INFO - dpsgd_diffusion.py - 2025-03-24 22:36:01,270 - Loss: 0.2216, step: 98600
+INFO - dpsgd_diffusion.py - 2025-03-24 22:36:51,386 - Loss: 0.2545, step: 98700
+INFO - dpsgd_diffusion.py - 2025-03-24 22:37:42,085 - Loss: 0.2292, step: 98800
+INFO - dpsgd_diffusion.py - 2025-03-24 22:38:33,172 - Loss: 0.2184, step: 98900
+INFO - dpsgd_diffusion.py - 2025-03-24 22:39:24,432 - Loss: 0.2163, step: 99000
+INFO - dpsgd_diffusion.py - 2025-03-24 22:40:16,727 - Loss: 0.2146, step: 99100
+INFO - dpsgd_diffusion.py - 2025-03-24 22:41:07,140 - Loss: 0.2151, step: 99200
+INFO - dpsgd_diffusion.py - 2025-03-24 22:41:40,223 - Eps-value after 141 epochs: 9.6432
+INFO - dpsgd_diffusion.py - 2025-03-24 22:41:58,804 - Loss: 0.2084, step: 99300
+INFO - dpsgd_diffusion.py - 2025-03-24 22:42:50,389 - Loss: 0.2528, step: 99400
+INFO - dpsgd_diffusion.py - 2025-03-24 22:43:41,685 - Loss: 0.2102, step: 99500
+INFO - dpsgd_diffusion.py - 2025-03-24 22:44:32,572 - Loss: 0.2557, step: 99600
+INFO - dpsgd_diffusion.py - 2025-03-24 22:45:23,968 - Loss: 0.2133, step: 99700
+INFO - dpsgd_diffusion.py - 2025-03-24 22:46:16,101 - Loss: 0.2363, step: 99800
+INFO - dpsgd_diffusion.py - 2025-03-24 22:47:06,998 - Loss: 0.2377, step: 99900
+INFO - dpsgd_diffusion.py - 2025-03-24 22:47:42,699 - Eps-value after 142 epochs: 9.6829
+INFO - dpsgd_diffusion.py - 2025-03-24 22:48:00,049 - Loss: 0.2180, step: 100000
+INFO - dpsgd_diffusion.py - 2025-03-24 22:48:00,088 - Saving snapshot checkpoint and sampling single batch at iteration 100000.
+WARNING - image.py - 2025-03-24 22:48:00,657 - 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 - 2025-03-24 22:48:27,403 - FID at iteration 100000: 134.817760
+INFO - dpsgd_diffusion.py - 2025-03-24 22:48:29,841 - Saving checkpoint at iteration 100000
+INFO - dpsgd_diffusion.py - 2025-03-24 22:49:22,052 - Loss: 0.2591, step: 100100
+INFO - dpsgd_diffusion.py - 2025-03-24 22:50:14,063 - Loss: 0.2206, step: 100200
+INFO - dpsgd_diffusion.py - 2025-03-24 22:51:05,999 - Loss: 0.2278, step: 100300
+INFO - dpsgd_diffusion.py - 2025-03-24 22:51:59,134 - Loss: 0.2243, step: 100400
+INFO - dpsgd_diffusion.py - 2025-03-24 22:52:50,128 - Loss: 0.2286, step: 100500
+INFO - dpsgd_diffusion.py - 2025-03-24 22:53:42,450 - Loss: 0.2175, step: 100600
+INFO - dpsgd_diffusion.py - 2025-03-24 22:54:20,085 - Eps-value after 143 epochs: 9.7226
+INFO - dpsgd_diffusion.py - 2025-03-24 22:54:35,012 - Loss: 0.2154, step: 100700
+INFO - dpsgd_diffusion.py - 2025-03-24 22:55:26,667 - Loss: 0.2510, step: 100800
+INFO - dpsgd_diffusion.py - 2025-03-24 22:56:18,427 - Loss: 0.1847, step: 100900
+INFO - dpsgd_diffusion.py - 2025-03-24 22:57:09,402 - Loss: 0.2322, step: 101000
+INFO - dpsgd_diffusion.py - 2025-03-24 22:58:00,662 - Loss: 0.2182, step: 101100
+INFO - dpsgd_diffusion.py - 2025-03-24 22:58:51,058 - Loss: 0.2053, step: 101200
+INFO - dpsgd_diffusion.py - 2025-03-24 22:59:42,659 - Loss: 0.2136, step: 101300
+INFO - dpsgd_diffusion.py - 2025-03-24 23:00:23,256 - Eps-value after 144 epochs: 9.7623
+INFO - dpsgd_diffusion.py - 2025-03-24 23:00:36,001 - Loss: 0.2162, step: 101400
+INFO - dpsgd_diffusion.py - 2025-03-24 23:01:27,427 - Loss: 0.2415, step: 101500
+INFO - dpsgd_diffusion.py - 2025-03-24 23:02:18,578 - Loss: 0.2388, step: 101600
+INFO - dpsgd_diffusion.py - 2025-03-24 23:03:10,666 - Loss: 0.2359, step: 101700
+INFO - dpsgd_diffusion.py - 2025-03-24 23:04:02,832 - Loss: 0.2188, step: 101800
+INFO - dpsgd_diffusion.py - 2025-03-24 23:04:53,919 - Loss: 0.2066, step: 101900
+INFO - dpsgd_diffusion.py - 2025-03-24 23:05:44,833 - Loss: 0.2298, step: 102000
+INFO - dpsgd_diffusion.py - 2025-03-24 23:05:44,840 - Saving snapshot checkpoint and sampling single batch at iteration 102000.
+WARNING - image.py - 2025-03-24 23:05:45,408 - 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 - 2025-03-24 23:06:13,065 - FID at iteration 102000: 134.072066
+INFO - dpsgd_diffusion.py - 2025-03-24 23:06:54,423 - Eps-value after 145 epochs: 9.8020
+INFO - dpsgd_diffusion.py - 2025-03-24 23:07:05,010 - Loss: 0.2272, step: 102100
+INFO - dpsgd_diffusion.py - 2025-03-24 23:07:57,549 - Loss: 0.2174, step: 102200
+INFO - dpsgd_diffusion.py - 2025-03-24 23:08:49,854 - Loss: 0.2288, step: 102300
+INFO - dpsgd_diffusion.py - 2025-03-24 23:09:41,966 - Loss: 0.2182, step: 102400
+INFO - dpsgd_diffusion.py - 2025-03-24 23:10:32,710 - Loss: 0.2388, step: 102500
+INFO - dpsgd_diffusion.py - 2025-03-24 23:11:24,681 - Loss: 0.2019, step: 102600
+INFO - dpsgd_diffusion.py - 2025-03-24 23:12:14,593 - Loss: 0.2344, step: 102700
+INFO - dpsgd_diffusion.py - 2025-03-24 23:12:57,270 - Eps-value after 146 epochs: 9.8412
+INFO - dpsgd_diffusion.py - 2025-03-24 23:13:06,124 - Loss: 0.2313, step: 102800
+INFO - dpsgd_diffusion.py - 2025-03-24 23:13:58,664 - Loss: 0.2476, step: 102900
+INFO - dpsgd_diffusion.py - 2025-03-24 23:14:50,362 - Loss: 0.2260, step: 103000
+INFO - dpsgd_diffusion.py - 2025-03-24 23:15:41,999 - Loss: 0.2230, step: 103100
+INFO - dpsgd_diffusion.py - 2025-03-24 23:16:35,032 - Loss: 0.1879, step: 103200
+INFO - dpsgd_diffusion.py - 2025-03-24 23:17:26,759 - Loss: 0.2305, step: 103300
+INFO - dpsgd_diffusion.py - 2025-03-24 23:18:18,814 - Loss: 0.2190, step: 103400
+INFO - dpsgd_diffusion.py - 2025-03-24 23:19:02,960 - Eps-value after 147 epochs: 9.8797
+INFO - dpsgd_diffusion.py - 2025-03-24 23:19:09,327 - Loss: 0.2295, step: 103500
+INFO - dpsgd_diffusion.py - 2025-03-24 23:20:00,007 - Loss: 0.2380, step: 103600
+INFO - dpsgd_diffusion.py - 2025-03-24 23:20:52,263 - Loss: 0.2197, step: 103700
+INFO - dpsgd_diffusion.py - 2025-03-24 23:21:44,432 - Loss: 0.2103, step: 103800
+INFO - dpsgd_diffusion.py - 2025-03-24 23:22:36,244 - Loss: 0.2562, step: 103900
+INFO - dpsgd_diffusion.py - 2025-03-24 23:23:28,114 - Loss: 0.2265, step: 104000
+INFO - dpsgd_diffusion.py - 2025-03-24 23:23:28,128 - Saving snapshot checkpoint and sampling single batch at iteration 104000.
+WARNING - image.py - 2025-03-24 23:23:28,694 - 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 - 2025-03-24 23:23:55,875 - FID at iteration 104000: 133.946968
+INFO - dpsgd_diffusion.py - 2025-03-24 23:24:47,844 - Loss: 0.2307, step: 104100
+INFO - dpsgd_diffusion.py - 2025-03-24 23:25:35,356 - Eps-value after 148 epochs: 9.9183
+INFO - dpsgd_diffusion.py - 2025-03-24 23:25:39,583 - Loss: 0.2189, step: 104200
+INFO - dpsgd_diffusion.py - 2025-03-24 23:26:30,815 - Loss: 0.2210, step: 104300
+INFO - dpsgd_diffusion.py - 2025-03-24 23:27:21,499 - Loss: 0.2280, step: 104400
+INFO - dpsgd_diffusion.py - 2025-03-24 23:28:12,536 - Loss: 0.1997, step: 104500
+INFO - dpsgd_diffusion.py - 2025-03-24 23:29:04,948 - Loss: 0.2083, step: 104600
+INFO - dpsgd_diffusion.py - 2025-03-24 23:29:56,656 - Loss: 0.2265, step: 104700
+INFO - dpsgd_diffusion.py - 2025-03-24 23:30:48,549 - Loss: 0.2330, step: 104800
+INFO - dpsgd_diffusion.py - 2025-03-24 23:31:38,325 - Eps-value after 149 epochs: 9.9568
+INFO - dpsgd_diffusion.py - 2025-03-24 23:31:40,421 - Loss: 0.2161, step: 104900
+INFO - dpsgd_diffusion.py - 2025-03-24 23:32:31,770 - Loss: 0.2123, step: 105000
+INFO - dpsgd_diffusion.py - 2025-03-24 23:33:22,891 - Loss: 0.2350, step: 105100
+INFO - dpsgd_diffusion.py - 2025-03-24 23:34:15,697 - Loss: 0.2217, step: 105200
+INFO - dpsgd_diffusion.py - 2025-03-24 23:35:07,292 - Loss: 0.2234, step: 105300
+INFO - dpsgd_diffusion.py - 2025-03-24 23:35:57,882 - Loss: 0.2158, step: 105400
+INFO - dpsgd_diffusion.py - 2025-03-24 23:36:50,746 - Loss: 0.2141, step: 105500
+INFO - dpsgd_diffusion.py - 2025-03-24 23:37:42,304 - Loss: 0.2069, step: 105600
+INFO - dpsgd_diffusion.py - 2025-03-24 23:37:42,338 - Eps-value after 150 epochs: 9.9953
+INFO - dpsgd_diffusion.py - 2025-03-24 23:37:43,046 - Saving final checkpoint.
+INFO - dpsgd_diffusion.py - 2025-03-24 23:37:43,053 - start to generate 60000 samples
+INFO - dpsgd_diffusion.py - 2025-03-24 23:45:51,425 - Generation Finished!
+INFO - evaluator.py - 2025-03-24 23:46:42,381 - Epoch: 0 Train acc: 1.4127272727272728 Val acc: 1.52 Test acc1.71; Train loss: 4.634569651950489 Val loss: 0.6209096717834472
+INFO - evaluator.py - 2025-03-24 23:47:21,449 - Epoch: 1 Train acc: 2.0363636363636366 Val acc: 1.32 Test acc1.63; Train loss: 4.510041514986211 Val loss: 2.3925251678466797
+INFO - evaluator.py - 2025-03-24 23:48:00,409 - Epoch: 2 Train acc: 2.5090909090909093 Val acc: 0.86 Test acc1.21; Train loss: 4.461707466992465 Val loss: 6.567560527038575
+INFO - evaluator.py - 2025-03-24 23:48:39,425 - Epoch: 3 Train acc: 3.3327272727272725 Val acc: 0.9199999999999999 Test acc1.08; Train loss: 4.354298827327382 Val loss: 11.843287673950195
+INFO - evaluator.py - 2025-03-24 23:49:18,506 - Epoch: 4 Train acc: 4.461818181818182 Val acc: 2.1399999999999997 Test acc2.5700000000000003; Train loss: 4.239197769823941 Val loss: 76.04144143066407
+INFO - evaluator.py - 2025-03-24 23:49:57,809 - Epoch: 5 Train acc: 5.176363636363637 Val acc: 1.34 Test acc1.4000000000000001; Train loss: 4.160667684433677 Val loss: 1121.8296796875002
+INFO - evaluator.py - 2025-03-24 23:50:36,903 - Epoch: 6 Train acc: 6.121818181818182 Val acc: 1.7000000000000002 Test acc1.76; Train loss: 4.080545703038302 Val loss: 540.91302890625
+INFO - evaluator.py - 2025-03-24 23:51:14,336 - Epoch: 7 Train acc: 7.581818181818181 Val acc: 0.88 Test acc1.05; Train loss: 3.9841724957032634 Val loss: 729.3135322265625
+INFO - evaluator.py - 2025-03-24 23:51:53,912 - Epoch: 8 Train acc: 8.943636363636363 Val acc: 0.86 Test acc0.97; Train loss: 3.8874479509787125 Val loss: 39.39719381103516
+INFO - evaluator.py - 2025-03-24 23:52:33,275 - Epoch: 9 Train acc: 10.76 Val acc: 1.5599999999999998 Test acc1.55; Train loss: 3.775945376066728 Val loss: 10.66206632080078
+INFO - evaluator.py - 2025-03-24 23:53:12,635 - Epoch: 10 Train acc: 12.512727272727272 Val acc: 1.24 Test acc1.15; Train loss: 3.6458693478324196 Val loss: 1.2559094604492187
+INFO - evaluator.py - 2025-03-24 23:53:51,812 - Epoch: 11 Train acc: 16.523636363636363 Val acc: 1.22 Test acc1.27; Train loss: 3.408556665359844 Val loss: 1.0319616485595702
+INFO - evaluator.py - 2025-03-24 23:54:31,256 - Epoch: 12 Train acc: 22.636363636363637 Val acc: 1.02 Test acc1.2; Train loss: 3.0774660241127014 Val loss: 0.8471093496322631
+INFO - evaluator.py - 2025-03-24 23:55:10,647 - Epoch: 13 Train acc: 27.847272727272728 Val acc: 1.8599999999999999 Test acc1.73; Train loss: 2.7909158402096144 Val loss: 1.255913570022583
+INFO - evaluator.py - 2025-03-24 23:55:49,967 - Epoch: 14 Train acc: 33.096363636363634 Val acc: 2.5 Test acc2.53; Train loss: 2.560954918488589 Val loss: 1.2885314220428465
+INFO - evaluator.py - 2025-03-24 23:56:29,129 - Epoch: 15 Train acc: 37.14 Val acc: 1.82 Test acc1.96; Train loss: 2.3762246079098093 Val loss: 1.840987113189697
+INFO - evaluator.py - 2025-03-24 23:57:08,340 - Epoch: 16 Train acc: 40.27636363636364 Val acc: 1.96 Test acc2.09; Train loss: 2.241889668052847 Val loss: 1.4846138271331786
+INFO - evaluator.py - 2025-03-24 23:57:47,340 - Epoch: 17 Train acc: 43.28545454545454 Val acc: 2.18 Test acc2.04; Train loss: 2.121456494548104 Val loss: 1.4190746395111082
+INFO - evaluator.py - 2025-03-24 23:58:26,735 - Epoch: 18 Train acc: 45.89818181818182 Val acc: 2.62 Test acc2.44; Train loss: 2.008329626057365 Val loss: 1.7090003299713135
+INFO - evaluator.py - 2025-03-24 23:59:06,150 - Epoch: 19 Train acc: 49.09636363636364 Val acc: 1.5599999999999998 Test acc2.11; Train loss: 1.8883394693678075 Val loss: 1.6055703712463378
+INFO - evaluator.py - 2025-03-24 23:59:45,452 - Epoch: 20 Train acc: 51.86727272727273 Val acc: 2.36 Test acc2.16; Train loss: 1.765587922707471 Val loss: 1.5656091201782227
+INFO - evaluator.py - 2025-03-25 00:00:25,840 - Epoch: 21 Train acc: 54.32 Val acc: 2.32 Test acc2.11; Train loss: 1.6778787441730498 Val loss: 2.2683087226867675
+INFO - evaluator.py - 2025-03-25 00:01:06,164 - Epoch: 22 Train acc: 55.96545454545454 Val acc: 1.18 Test acc1.4000000000000001; Train loss: 1.604293021735278 Val loss: 2.2050625808715822
+INFO - evaluator.py - 2025-03-25 00:01:46,574 - Epoch: 23 Train acc: 57.53636363636364 Val acc: 2.06 Test acc1.8599999999999999; Train loss: 1.5471543493574316 Val loss: 2.058121973419189
+INFO - evaluator.py - 2025-03-25 00:02:27,055 - Epoch: 24 Train acc: 59.290909090909096 Val acc: 2.42 Test acc2.26; Train loss: 1.4735515878113834 Val loss: 2.2267815559387207
+INFO - evaluator.py - 2025-03-25 00:03:07,290 - Epoch: 25 Train acc: 60.71454545454545 Val acc: 1.6 Test acc1.58; Train loss: 1.4235313281752846 Val loss: 4.299415466308594
+INFO - evaluator.py - 2025-03-25 00:03:47,490 - Epoch: 26 Train acc: 61.84727272727273 Val acc: 0.96 Test acc1.3599999999999999; Train loss: 1.3692400687954642 Val loss: 3.4511482383728027
+INFO - evaluator.py - 2025-03-25 00:04:27,790 - Epoch: 27 Train acc: 62.46000000000001 Val acc: 2.6 Test acc2.2800000000000002; Train loss: 1.3504820178508758 Val loss: 2.2611833953857423
+INFO - evaluator.py - 2025-03-25 00:05:08,534 - Epoch: 28 Train acc: 63.61454545454546 Val acc: 2.54 Test acc2.01; Train loss: 1.3048590926560488 Val loss: 2.693211836242676
+INFO - evaluator.py - 2025-03-25 00:05:48,999 - Epoch: 29 Train acc: 65.0690909090909 Val acc: 1.6199999999999999 Test acc1.78; Train loss: 1.2573165396712043 Val loss: 2.0215494140624997
+INFO - evaluator.py - 2025-03-25 00:06:29,506 - Epoch: 30 Train acc: 66.12363636363636 Val acc: 1.8599999999999999 Test acc1.6099999999999999; Train loss: 1.223335537687215 Val loss: 4.200938360595703
+INFO - evaluator.py - 2025-03-25 00:07:10,054 - Epoch: 31 Train acc: 66.25090909090909 Val acc: 2.8400000000000003 Test acc2.82; Train loss: 1.2060644336440347 Val loss: 1.3980446067810057
+INFO - evaluator.py - 2025-03-25 00:07:50,390 - Epoch: 32 Train acc: 67.32181818181819 Val acc: 1.7000000000000002 Test acc1.7999999999999998; Train loss: 1.1650969657724555 Val loss: 2.7393360054016114
+INFO - evaluator.py - 2025-03-25 00:08:30,548 - Epoch: 33 Train acc: 67.99818181818182 Val acc: 1.9 Test acc1.77; Train loss: 1.14534736309485 Val loss: 2.2550137962341306
+INFO - evaluator.py - 2025-03-25 00:09:10,727 - Epoch: 34 Train acc: 68.41090909090909 Val acc: 1.6400000000000001 Test acc1.6500000000000001; Train loss: 1.12053021977598 Val loss: 2.311057994842529
+INFO - evaluator.py - 2025-03-25 00:09:50,833 - Epoch: 35 Train acc: 69.39636363636363 Val acc: 1.3599999999999999 Test acc1.87; Train loss: 1.0883761192365127 Val loss: 3.8168551826477053
+INFO - evaluator.py - 2025-03-25 00:10:31,239 - Epoch: 36 Train acc: 69.43454545454546 Val acc: 1.38 Test acc1.34; Train loss: 1.0866368081266229 Val loss: 2.998070370483399
+INFO - evaluator.py - 2025-03-25 00:11:11,430 - Epoch: 37 Train acc: 70.62181818181818 Val acc: 1.68 Test acc1.5; Train loss: 1.0420317843545568 Val loss: 2.7630635765075686
+INFO - evaluator.py - 2025-03-25 00:11:51,599 - Epoch: 38 Train acc: 70.5709090909091 Val acc: 1.06 Test acc1.29; Train loss: 1.0436083743290467 Val loss: 4.298663150024414
+INFO - evaluator.py - 2025-03-25 00:12:31,777 - Epoch: 39 Train acc: 71.01272727272728 Val acc: 1.92 Test acc1.76; Train loss: 1.021763846579465 Val loss: 2.1343312477111813
+INFO - evaluator.py - 2025-03-25 00:13:12,167 - Epoch: 40 Train acc: 71.35090909090908 Val acc: 2.1 Test acc2.06; Train loss: 1.015605847659978 Val loss: 1.797116600418091
+INFO - evaluator.py - 2025-03-25 00:13:52,332 - Epoch: 41 Train acc: 71.81454545454545 Val acc: 1.7999999999999998 Test acc2.03; Train loss: 1.002910640222376 Val loss: 4.05057349319458
+INFO - evaluator.py - 2025-03-25 00:14:32,558 - Epoch: 42 Train acc: 71.72 Val acc: 2.92 Test acc2.9499999999999997; Train loss: 1.0005945838906547 Val loss: 1.6319433059692383
+INFO - evaluator.py - 2025-03-25 00:15:12,815 - Epoch: 43 Train acc: 72.3690909090909 Val acc: 1.68 Test acc1.67; Train loss: 0.9777951033158736 Val loss: 2.7305817489624027
+INFO - evaluator.py - 2025-03-25 00:15:53,194 - Epoch: 44 Train acc: 72.47090909090909 Val acc: 1.8599999999999999 Test acc1.51; Train loss: 0.9749610495719042 Val loss: 3.1574333290100096
+INFO - evaluator.py - 2025-03-25 00:16:33,395 - Epoch: 45 Train acc: 72.48181818181818 Val acc: 2.8400000000000003 Test acc2.69; Train loss: 0.9709861256361008 Val loss: 2.989559516143799
+INFO - evaluator.py - 2025-03-25 00:17:13,602 - Epoch: 46 Train acc: 72.39272727272727 Val acc: 2.0 Test acc1.83; Train loss: 0.9731598270893097 Val loss: 2.5150784133911133
+INFO - evaluator.py - 2025-03-25 00:17:53,817 - Epoch: 47 Train acc: 72.64727272727272 Val acc: 2.22 Test acc2.23; Train loss: 0.9600759880477732 Val loss: 2.3692138412475585
+INFO - evaluator.py - 2025-03-25 00:18:34,187 - Epoch: 48 Train acc: 72.97818181818182 Val acc: 0.86 Test acc1.22; Train loss: 0.9515519361279227 Val loss: 6.081711479187012
+INFO - evaluator.py - 2025-03-25 00:19:14,367 - Epoch: 49 Train acc: 73.26727272727273 Val acc: 1.54 Test acc1.39; Train loss: 0.9393884525364096 Val loss: 3.8056448913574217
+INFO - evaluator.py - 2025-03-25 00:19:54,527 - Epoch: 50 Train acc: 73.62727272727273 Val acc: 1.48 Test acc1.5699999999999998; Train loss: 0.9363102829521353 Val loss: 4.224193258666992
+INFO - evaluator.py - 2025-03-25 00:20:34,709 - Epoch: 51 Train acc: 73.60545454545453 Val acc: 0.98 Test acc1.13; Train loss: 0.9293981551993977 Val loss: 5.568352130126953
+INFO - evaluator.py - 2025-03-25 00:21:15,087 - Epoch: 52 Train acc: 73.72545454545455 Val acc: 2.2399999999999998 Test acc2.08; Train loss: 0.9287958850427108 Val loss: 1.447564917755127
+INFO - evaluator.py - 2025-03-25 00:21:55,217 - Epoch: 53 Train acc: 73.93454545454546 Val acc: 1.04 Test acc1.08; Train loss: 0.918026815087145 Val loss: 5.1868601943969725
+INFO - evaluator.py - 2025-03-25 00:22:35,325 - Epoch: 54 Train acc: 73.54727272727273 Val acc: 2.5 Test acc2.18; Train loss: 0.9261807805083014 Val loss: 1.6427445625305177
+INFO - evaluator.py - 2025-03-25 00:23:15,470 - Epoch: 55 Train acc: 74.31636363636363 Val acc: 1.34 Test acc1.0999999999999999; Train loss: 0.9069365384687077 Val loss: 4.391530471801758
+INFO - evaluator.py - 2025-03-25 00:23:55,812 - Epoch: 56 Train acc: 73.99818181818182 Val acc: 1.5599999999999998 Test acc1.66; Train loss: 0.9181685468933799 Val loss: 3.369808101654053
+INFO - evaluator.py - 2025-03-25 00:24:35,957 - Epoch: 57 Train acc: 74.13454545454545 Val acc: 0.96 Test acc1.23; Train loss: 0.907698263990879 Val loss: 2.8468091835021974
+INFO - evaluator.py - 2025-03-25 00:25:16,124 - Epoch: 58 Train acc: 74.50363636363636 Val acc: 2.1 Test acc2.06; Train loss: 0.8974052431713451 Val loss: 2.807323489379883
+INFO - evaluator.py - 2025-03-25 00:25:56,251 - Epoch: 59 Train acc: 74.62545454545455 Val acc: 1.04 Test acc1.23; Train loss: 0.891666690418937 Val loss: 4.702108666992188
+INFO - evaluator.py - 2025-03-25 00:26:36,636 - Epoch: 60 Train acc: 89.79272727272726 Val acc: 1.38 Test acc1.55; Train loss: 0.3697893348309127 Val loss: 4.284097091674805
+INFO - evaluator.py - 2025-03-25 00:27:16,758 - Epoch: 61 Train acc: 92.50545454545454 Val acc: 1.4000000000000001 Test acc1.55; Train loss: 0.2708502888549458 Val loss: 7.744732676696778
+INFO - evaluator.py - 2025-03-25 00:27:56,904 - Epoch: 62 Train acc: 93.66363636363636 Val acc: 1.44 Test acc1.3599999999999999; Train loss: 0.22717580937932838 Val loss: 12.085354330444336
+INFO - evaluator.py - 2025-03-25 00:28:37,070 - Epoch: 63 Train acc: 94.56363636363636 Val acc: 1.24 Test acc1.37; Train loss: 0.1993489746183157 Val loss: 12.379429632568359
+INFO - evaluator.py - 2025-03-25 00:29:17,480 - Epoch: 64 Train acc: 95.02181818181819 Val acc: 2.16 Test acc2.22; Train loss: 0.1815104330672459 Val loss: 8.423737536621093
+INFO - evaluator.py - 2025-03-25 00:29:57,623 - Epoch: 65 Train acc: 95.16909090909091 Val acc: 1.06 Test acc1.22; Train loss: 0.1759938492674719 Val loss: 21.182944427490234
+INFO - evaluator.py - 2025-03-25 00:30:37,767 - Epoch: 66 Train acc: 95.03090909090909 Val acc: 1.4000000000000001 Test acc1.32; Train loss: 0.173667835641991 Val loss: 20.42931307983398
+INFO - evaluator.py - 2025-03-25 00:31:17,928 - Epoch: 67 Train acc: 94.95090909090908 Val acc: 0.74 Test acc1.02; Train loss: 0.17740443164950068 Val loss: 33.921097229003905
+INFO - evaluator.py - 2025-03-25 00:31:58,268 - Epoch: 68 Train acc: 94.60181818181819 Val acc: 1.04 Test acc1.25; Train loss: 0.18625780155658722 Val loss: 20.393987475585938
+INFO - evaluator.py - 2025-03-25 00:32:38,425 - Epoch: 69 Train acc: 94.11090909090909 Val acc: 1.06 Test acc1.01; Train loss: 0.19845734347619792 Val loss: 28.734258471679688
+INFO - evaluator.py - 2025-03-25 00:33:18,604 - Epoch: 70 Train acc: 93.97818181818181 Val acc: 1.08 Test acc1.02; Train loss: 0.20543950913413006 Val loss: 20.594467364501952
+INFO - evaluator.py - 2025-03-25 00:33:58,748 - Epoch: 71 Train acc: 93.51454545454546 Val acc: 1.24 Test acc0.9900000000000001; Train loss: 0.21551158885522323 Val loss: 23.666863623046876
+INFO - evaluator.py - 2025-03-25 00:34:39,140 - Epoch: 72 Train acc: 93.68181818181817 Val acc: 1.08 Test acc1.0999999999999999; Train loss: 0.21340210578414526 Val loss: 24.683369622802736
+INFO - evaluator.py - 2025-03-25 00:35:19,288 - Epoch: 73 Train acc: 93.30181818181819 Val acc: 1.8399999999999999 Test acc1.58; Train loss: 0.22464892514754425 Val loss: 20.75262028198242
+INFO - evaluator.py - 2025-03-25 00:35:59,426 - Epoch: 74 Train acc: 93.33090909090909 Val acc: 1.46 Test acc1.23; Train loss: 0.22096969751634382 Val loss: 18.284665649414062
+INFO - evaluator.py - 2025-03-25 00:36:39,784 - Epoch: 75 Train acc: 92.73818181818181 Val acc: 1.5 Test acc1.63; Train loss: 0.2424283423044465 Val loss: 13.608260321044922
+INFO - evaluator.py - 2025-03-25 00:37:20,057 - Epoch: 76 Train acc: 92.97090909090909 Val acc: 1.8599999999999999 Test acc1.97; Train loss: 0.2334670429278504 Val loss: 11.903828466796876
+INFO - evaluator.py - 2025-03-25 00:38:00,201 - Epoch: 77 Train acc: 93.19636363636363 Val acc: 1.18 Test acc1.16; Train loss: 0.22975062658326192 Val loss: 14.718404223632811
+INFO - evaluator.py - 2025-03-25 00:38:40,546 - Epoch: 78 Train acc: 92.82363636363637 Val acc: 1.9800000000000002 Test acc1.72; Train loss: 0.23909683889557012 Val loss: 8.274545123291015
+INFO - evaluator.py - 2025-03-25 00:39:20,985 - Epoch: 79 Train acc: 92.83636363636364 Val acc: 1.48 Test acc1.0699999999999998; Train loss: 0.23527843507176097 Val loss: 12.454654147338866
+INFO - evaluator.py - 2025-03-25 00:40:01,172 - Epoch: 80 Train acc: 92.04545454545455 Val acc: 2.62 Test acc2.94; Train loss: 0.25804509593221275 Val loss: 5.616468168640136
+INFO - evaluator.py - 2025-03-25 00:40:41,481 - Epoch: 81 Train acc: 92.87636363636364 Val acc: 1.76 Test acc1.49; Train loss: 0.23484140677587553 Val loss: 11.698768927001954
+INFO - evaluator.py - 2025-03-25 00:41:21,720 - Epoch: 82 Train acc: 92.58 Val acc: 1.28 Test acc1.38; Train loss: 0.24507547941749747 Val loss: 8.70885887145996
+INFO - evaluator.py - 2025-03-25 00:42:02,055 - Epoch: 83 Train acc: 93.34 Val acc: 1.54 Test acc1.43; Train loss: 0.2221572365283966 Val loss: 9.247676138305664
+INFO - evaluator.py - 2025-03-25 00:42:42,269 - Epoch: 84 Train acc: 92.69454545454545 Val acc: 2.1999999999999997 Test acc2.25; Train loss: 0.24006141107326204 Val loss: 6.540763609313965
+INFO - evaluator.py - 2025-03-25 00:43:22,603 - Epoch: 85 Train acc: 93.10909090909091 Val acc: 2.08 Test acc2.01; Train loss: 0.23096111189099877 Val loss: 5.789010649108887
+INFO - evaluator.py - 2025-03-25 00:44:02,797 - Epoch: 86 Train acc: 92.76363636363637 Val acc: 0.8999999999999999 Test acc0.96; Train loss: 0.24033548350632192 Val loss: 8.098131857299803
+INFO - evaluator.py - 2025-03-25 00:44:43,168 - Epoch: 87 Train acc: 92.95636363636363 Val acc: 2.2399999999999998 Test acc2.04; Train loss: 0.23294097396108238 Val loss: 5.678342385864258
+INFO - evaluator.py - 2025-03-25 00:45:23,363 - Epoch: 88 Train acc: 92.84 Val acc: 1.82 Test acc1.97; Train loss: 0.2356120694014159 Val loss: 5.689148497009278
+INFO - evaluator.py - 2025-03-25 00:46:03,549 - Epoch: 89 Train acc: 93.23636363636363 Val acc: 1.4000000000000001 Test acc1.39; Train loss: 0.22403922907330773 Val loss: 5.782968566894532
+INFO - evaluator.py - 2025-03-25 00:46:43,765 - Epoch: 90 Train acc: 93.34363636363636 Val acc: 2.02 Test acc2.08; Train loss: 0.2201978505004536 Val loss: 4.304725708007813
+INFO - evaluator.py - 2025-03-25 00:47:24,101 - Epoch: 91 Train acc: 93.05818181818182 Val acc: 1.04 Test acc1.3599999999999999; Train loss: 0.2278765348214995 Val loss: 8.502990298461913
+INFO - evaluator.py - 2025-03-25 00:48:04,255 - Epoch: 92 Train acc: 93.30363636363637 Val acc: 1.8800000000000001 Test acc1.7399999999999998; Train loss: 0.21711841915385288 Val loss: 4.0577887985229495
+INFO - evaluator.py - 2025-03-25 00:48:44,425 - Epoch: 93 Train acc: 93.11272727272727 Val acc: 1.04 Test acc1.5; Train loss: 0.22840859553353354 Val loss: 6.109435285949707
+INFO - evaluator.py - 2025-03-25 00:49:24,620 - Epoch: 94 Train acc: 93.02909090909091 Val acc: 2.1399999999999997 Test acc2.21; Train loss: 0.22830662556669928 Val loss: 4.319153915405273
+INFO - evaluator.py - 2025-03-25 00:50:04,991 - Epoch: 95 Train acc: 92.75999999999999 Val acc: 1.6199999999999999 Test acc1.68; Train loss: 0.23511080891489983 Val loss: 5.377192657470703
+INFO - evaluator.py - 2025-03-25 00:50:45,181 - Epoch: 96 Train acc: 93.19454545454545 Val acc: 1.66 Test acc2.0500000000000003; Train loss: 0.22182882908284662 Val loss: 3.953346995544434
+INFO - evaluator.py - 2025-03-25 00:51:25,352 - Epoch: 97 Train acc: 93.38909090909091 Val acc: 1.4200000000000002 Test acc1.6199999999999999; Train loss: 0.21768262929618357 Val loss: 4.712991201782227
+INFO - evaluator.py - 2025-03-25 00:52:05,520 - Epoch: 98 Train acc: 93.09454545454545 Val acc: 1.66 Test acc1.7000000000000002; Train loss: 0.2225866672648625 Val loss: 4.6280609802246095
+INFO - evaluator.py - 2025-03-25 00:52:45,914 - Epoch: 99 Train acc: 93.22181818181818 Val acc: 1.5599999999999998 Test acc1.5599999999999998; Train loss: 0.22052966413931413 Val loss: 5.3188688232421875
+INFO - evaluator.py - 2025-03-25 00:53:26,122 - Epoch: 100 Train acc: 93.57636363636364 Val acc: 1.48 Test acc1.51; Train loss: 0.21333771161247383 Val loss: 4.734074322509766
+INFO - evaluator.py - 2025-03-25 00:54:06,263 - Epoch: 101 Train acc: 93.49272727272727 Val acc: 2.26 Test acc2.58; Train loss: 0.2148813890365037 Val loss: 5.022349118041992
+INFO - evaluator.py - 2025-03-25 00:54:46,461 - Epoch: 102 Train acc: 93.30909090909091 Val acc: 1.4200000000000002 Test acc1.5699999999999998; Train loss: 0.2175194174725901 Val loss: 4.553593492126464
+INFO - evaluator.py - 2025-03-25 00:55:27,030 - Epoch: 103 Train acc: 93.90363636363637 Val acc: 1.46 Test acc1.31; Train loss: 0.20405020979778332 Val loss: 5.308764944458008
+INFO - evaluator.py - 2025-03-25 00:56:07,237 - Epoch: 104 Train acc: 93.82000000000001 Val acc: 2.64 Test acc3.0; Train loss: 0.20103580327359113 Val loss: 2.919978382873535
+INFO - evaluator.py - 2025-03-25 00:56:47,455 - Epoch: 105 Train acc: 93.27454545454546 Val acc: 2.12 Test acc2.7; Train loss: 0.2218356460438533 Val loss: 3.500572563171387
+INFO - evaluator.py - 2025-03-25 00:57:27,725 - Epoch: 106 Train acc: 93.28181818181818 Val acc: 1.9800000000000002 Test acc1.7500000000000002; Train loss: 0.2198453438433734 Val loss: 4.3039964630126955
+INFO - evaluator.py - 2025-03-25 00:58:08,132 - Epoch: 107 Train acc: 93.34545454545454 Val acc: 1.78 Test acc1.8800000000000001; Train loss: 0.21724050708060913 Val loss: 3.925663851928711
+INFO - evaluator.py - 2025-03-25 00:58:48,354 - Epoch: 108 Train acc: 93.84545454545454 Val acc: 2.18 Test acc2.48; Train loss: 0.20328581503629686 Val loss: 3.982407543182373
+INFO - evaluator.py - 2025-03-25 00:59:28,567 - Epoch: 109 Train acc: 93.48363636363636 Val acc: 1.76 Test acc1.71; Train loss: 0.21168992206074977 Val loss: 3.733577297973633
+INFO - evaluator.py - 2025-03-25 01:00:08,740 - Epoch: 110 Train acc: 93.40363636363637 Val acc: 2.76 Test acc2.6; Train loss: 0.21346128283495253 Val loss: 2.5087617347717286
+INFO - evaluator.py - 2025-03-25 01:00:49,225 - Epoch: 111 Train acc: 93.96545454545453 Val acc: 1.22 Test acc1.26; Train loss: 0.19764582262662322 Val loss: 3.9512835571289058
+INFO - evaluator.py - 2025-03-25 01:01:29,457 - Epoch: 112 Train acc: 93.3490909090909 Val acc: 1.4000000000000001 Test acc1.5599999999999998; Train loss: 0.2168106514554132 Val loss: 3.4116918640136715
+INFO - evaluator.py - 2025-03-25 01:02:09,636 - Epoch: 113 Train acc: 94.23818181818181 Val acc: 1.08 Test acc1.63; Train loss: 0.19200198665776036 Val loss: 3.9526867240905763
+INFO - evaluator.py - 2025-03-25 01:02:49,849 - Epoch: 114 Train acc: 93.22363636363636 Val acc: 1.0999999999999999 Test acc1.2; Train loss: 0.21949446107609705 Val loss: 4.678816278076171
+INFO - evaluator.py - 2025-03-25 01:03:30,230 - Epoch: 115 Train acc: 93.56 Val acc: 2.2399999999999998 Test acc2.4; Train loss: 0.2076029874671589 Val loss: 3.5463624870300294
+INFO - evaluator.py - 2025-03-25 01:04:10,419 - Epoch: 116 Train acc: 93.84181818181818 Val acc: 1.0999999999999999 Test acc1.25; Train loss: 0.20234215920242396 Val loss: 4.960041641235352
+INFO - evaluator.py - 2025-03-25 01:04:50,547 - Epoch: 117 Train acc: 93.58727272727273 Val acc: 2.06 Test acc2.17; Train loss: 0.21058249121619896 Val loss: 3.158834573364258
+INFO - evaluator.py - 2025-03-25 01:05:30,681 - Epoch: 118 Train acc: 93.48181818181817 Val acc: 1.78 Test acc1.7000000000000002; Train loss: 0.21276053341139448 Val loss: 4.380363102722168
+INFO - evaluator.py - 2025-03-25 01:06:10,998 - Epoch: 119 Train acc: 93.6490909090909 Val acc: 1.34 Test acc1.59; Train loss: 0.20550691024742343 Val loss: 3.803756938934326
+INFO - evaluator.py - 2025-03-25 01:06:51,100 - Epoch: 120 Train acc: 99.18545454545455 Val acc: 3.08 Test acc3.11; Train loss: 0.0424522529960356 Val loss: 2.778905188751221
+INFO - evaluator.py - 2025-03-25 01:07:31,236 - Epoch: 121 Train acc: 99.94909090909091 Val acc: 3.46 Test acc3.62; Train loss: 0.015379657971520315 Val loss: 2.5034192893981935
+INFO - evaluator.py - 2025-03-25 01:08:11,353 - Epoch: 122 Train acc: 99.98545454545454 Val acc: 3.44 Test acc3.8; Train loss: 0.011119978311878036 Val loss: 2.647206916809082
+INFO - evaluator.py - 2025-03-25 01:08:51,691 - Epoch: 123 Train acc: 99.99818181818182 Val acc: 3.6799999999999997 Test acc3.71; Train loss: 0.008992799959958277 Val loss: 2.641732917022705
+INFO - evaluator.py - 2025-03-25 01:09:31,852 - Epoch: 124 Train acc: 99.99818181818182 Val acc: 3.38 Test acc3.56; Train loss: 0.008183805519630286 Val loss: 2.830917631530762
+INFO - evaluator.py - 2025-03-25 01:10:12,027 - Epoch: 125 Train acc: 99.99272727272728 Val acc: 3.36 Test acc3.51; Train loss: 0.007912457207310946 Val loss: 2.8640335350036623
+INFO - evaluator.py - 2025-03-25 01:10:52,161 - Epoch: 126 Train acc: 100.0 Val acc: 3.26 Test acc3.3300000000000005; Train loss: 0.006972587017791176 Val loss: 2.9392402656555174
+INFO - evaluator.py - 2025-03-25 01:11:32,532 - Epoch: 127 Train acc: 100.0 Val acc: 3.54 Test acc3.2199999999999998; Train loss: 0.006864765835765072 Val loss: 3.030262989807129
+INFO - evaluator.py - 2025-03-25 01:12:12,702 - Epoch: 128 Train acc: 100.0 Val acc: 2.94 Test acc2.92; Train loss: 0.006588561975329437 Val loss: 3.394808246612549
+INFO - evaluator.py - 2025-03-25 01:12:52,836 - Epoch: 129 Train acc: 100.0 Val acc: 2.86 Test acc2.55; Train loss: 0.006375151551387866 Val loss: 3.5992251068115237
+INFO - evaluator.py - 2025-03-25 01:13:33,010 - Epoch: 130 Train acc: 100.0 Val acc: 2.78 Test acc2.54; Train loss: 0.006298262840280818 Val loss: 3.656297467803955
+INFO - evaluator.py - 2025-03-25 01:14:13,386 - Epoch: 131 Train acc: 100.0 Val acc: 2.64 Test acc2.4699999999999998; Train loss: 0.006108701618710025 Val loss: 3.8753094177246092
+INFO - evaluator.py - 2025-03-25 01:14:53,513 - Epoch: 132 Train acc: 100.0 Val acc: 2.56 Test acc2.42; Train loss: 0.006154037588538433 Val loss: 3.930078158569336
+INFO - evaluator.py - 2025-03-25 01:15:33,662 - Epoch: 133 Train acc: 100.0 Val acc: 2.52 Test acc2.32; Train loss: 0.005938919400212101 Val loss: 4.039633328247071
+INFO - evaluator.py - 2025-03-25 01:16:14,033 - Epoch: 134 Train acc: 100.0 Val acc: 2.48 Test acc2.1399999999999997; Train loss: 0.00593705349308862 Val loss: 4.360396055603027
+INFO - evaluator.py - 2025-03-25 01:16:54,215 - Epoch: 135 Train acc: 100.0 Val acc: 2.2399999999999998 Test acc2.18; Train loss: 0.005940524964737283 Val loss: 4.703073623657226
+INFO - evaluator.py - 2025-03-25 01:17:34,366 - Epoch: 136 Train acc: 100.0 Val acc: 2.12 Test acc1.8499999999999999; Train loss: 0.005794992418036881 Val loss: 4.847700805664062
+INFO - evaluator.py - 2025-03-25 01:18:14,522 - Epoch: 137 Train acc: 100.0 Val acc: 2.1399999999999997 Test acc1.79; Train loss: 0.005843009010871703 Val loss: 5.016502565002441
+INFO - evaluator.py - 2025-03-25 01:18:54,906 - Epoch: 138 Train acc: 100.0 Val acc: 2.06 Test acc1.7000000000000002; Train loss: 0.005778284089148722 Val loss: 5.348841311645508
+INFO - evaluator.py - 2025-03-25 01:19:35,104 - Epoch: 139 Train acc: 100.0 Val acc: 1.92 Test acc1.6400000000000001; Train loss: 0.005902315844400701 Val loss: 5.867415733337403
+INFO - evaluator.py - 2025-03-25 01:20:15,297 - Epoch: 140 Train acc: 100.0 Val acc: 1.82 Test acc1.5599999999999998; Train loss: 0.005877320980873298 Val loss: 6.010111079406738
+INFO - evaluator.py - 2025-03-25 01:20:55,500 - Epoch: 141 Train acc: 100.0 Val acc: 1.7000000000000002 Test acc1.5599999999999998; Train loss: 0.005821056546321647 Val loss: 6.104339030456543
+INFO - evaluator.py - 2025-03-25 01:21:35,867 - Epoch: 142 Train acc: 100.0 Val acc: 1.46 Test acc1.34; Train loss: 0.005900510300924494 Val loss: 6.8654571075439454
+INFO - evaluator.py - 2025-03-25 01:22:16,019 - Epoch: 143 Train acc: 100.0 Val acc: 1.46 Test acc1.34; Train loss: 0.00579486833836206 Val loss: 7.162830642700195
+INFO - evaluator.py - 2025-03-25 01:22:56,198 - Epoch: 144 Train acc: 100.0 Val acc: 1.38 Test acc1.1400000000000001; Train loss: 0.005826890250193802 Val loss: 7.594300854492187
+INFO - evaluator.py - 2025-03-25 01:23:36,345 - Epoch: 145 Train acc: 100.0 Val acc: 1.34 Test acc1.1900000000000002; Train loss: 0.005921896537511863 Val loss: 8.085318640136718
+INFO - evaluator.py - 2025-03-25 01:24:16,685 - Epoch: 146 Train acc: 100.0 Val acc: 1.22 Test acc1.13; Train loss: 0.005934105967806483 Val loss: 8.513392373657227
+INFO - evaluator.py - 2025-03-25 01:24:56,886 - Epoch: 147 Train acc: 100.0 Val acc: 1.26 Test acc1.05; Train loss: 0.005756239888859404 Val loss: 9.18159958190918
+INFO - evaluator.py - 2025-03-25 01:25:37,073 - Epoch: 148 Train acc: 100.0 Val acc: 1.18 Test acc1.02; Train loss: 0.005859923354062167 Val loss: 9.263276559448242
+INFO - evaluator.py - 2025-03-25 01:26:17,266 - Epoch: 149 Train acc: 100.0 Val acc: 1.0999999999999999 Test acc1.02; Train loss: 0.005890971144195646 Val loss: 9.971319232177734
+INFO - evaluator.py - 2025-03-25 01:26:57,645 - Epoch: 150 Train acc: 100.0 Val acc: 1.0999999999999999 Test acc0.98; Train loss: 0.0058849913602864205 Val loss: 10.947362228393555
+INFO - evaluator.py - 2025-03-25 01:27:37,803 - Epoch: 151 Train acc: 100.0 Val acc: 1.06 Test acc1.04; Train loss: 0.005818115832478824 Val loss: 11.66736082763672
+INFO - evaluator.py - 2025-03-25 01:28:17,974 - Epoch: 152 Train acc: 100.0 Val acc: 1.06 Test acc1.06; Train loss: 0.005862732303091749 Val loss: 12.89787456665039
+INFO - evaluator.py - 2025-03-25 01:28:58,140 - Epoch: 153 Train acc: 100.0 Val acc: 1.08 Test acc1.06; Train loss: 0.005844631622663953 Val loss: 13.391004528808594
+INFO - evaluator.py - 2025-03-25 01:29:38,509 - Epoch: 154 Train acc: 100.0 Val acc: 0.96 Test acc1.08; Train loss: 0.005732170960764316 Val loss: 12.872666683959961
+INFO - evaluator.py - 2025-03-25 01:30:18,671 - Epoch: 155 Train acc: 100.0 Val acc: 1.08 Test acc1.05; Train loss: 0.005735118549520319 Val loss: 12.440282656860353
+INFO - evaluator.py - 2025-03-25 01:30:58,903 - Epoch: 156 Train acc: 100.0 Val acc: 1.06 Test acc1.06; Train loss: 0.005698694557010789 Val loss: 13.714604736328125
+INFO - evaluator.py - 2025-03-25 01:31:39,101 - Epoch: 157 Train acc: 100.0 Val acc: 1.08 Test acc1.06; Train loss: 0.005666987817463549 Val loss: 15.068298779296875
+INFO - evaluator.py - 2025-03-25 01:32:19,474 - Epoch: 158 Train acc: 100.0 Val acc: 1.04 Test acc1.06; Train loss: 0.005706805910178545 Val loss: 14.798067654418945
+INFO - evaluator.py - 2025-03-25 01:32:59,637 - Epoch: 159 Train acc: 100.0 Val acc: 1.06 Test acc1.04; Train loss: 0.0056742123687047175 Val loss: 16.19164791870117
+INFO - evaluator.py - 2025-03-25 01:33:39,851 - Epoch: 160 Train acc: 100.0 Val acc: 1.04 Test acc1.03; Train loss: 0.005676842603595419 Val loss: 16.135485479736328
+INFO - evaluator.py - 2025-03-25 01:34:20,074 - Epoch: 161 Train acc: 100.0 Val acc: 1.02 Test acc1.01; Train loss: 0.00577719974481416 Val loss: 16.457583361816408
+INFO - evaluator.py - 2025-03-25 01:35:00,459 - Epoch: 162 Train acc: 100.0 Val acc: 1.04 Test acc1.02; Train loss: 0.005757475264726038 Val loss: 17.982259497070313
+INFO - evaluator.py - 2025-03-25 01:35:40,612 - Epoch: 163 Train acc: 100.0 Val acc: 1.04 Test acc1.05; Train loss: 0.005606028593297709 Val loss: 18.36043406982422
+INFO - evaluator.py - 2025-03-25 01:36:20,772 - Epoch: 164 Train acc: 100.0 Val acc: 1.02 Test acc1.06; Train loss: 0.005520415193850005 Val loss: 19.703987127685547
+INFO - evaluator.py - 2025-03-25 01:37:00,939 - Epoch: 165 Train acc: 100.0 Val acc: 1.08 Test acc1.05; Train loss: 0.005611115705281157 Val loss: 20.370809674072266
+INFO - evaluator.py - 2025-03-25 01:37:41,303 - Epoch: 166 Train acc: 100.0 Val acc: 1.08 Test acc1.04; Train loss: 0.005554883161813698 Val loss: 21.4354423828125
+INFO - evaluator.py - 2025-03-25 01:38:21,460 - Epoch: 167 Train acc: 100.0 Val acc: 1.06 Test acc1.03; Train loss: 0.0054435154681601984 Val loss: 22.002666174316406
+INFO - evaluator.py - 2025-03-25 01:39:01,637 - Epoch: 168 Train acc: 100.0 Val acc: 1.0999999999999999 Test acc1.04; Train loss: 0.0054486517531881955 Val loss: 21.95562496948242
+INFO - evaluator.py - 2025-03-25 01:39:41,798 - Epoch: 169 Train acc: 100.0 Val acc: 1.06 Test acc1.03; Train loss: 0.005563202317753299 Val loss: 22.544073962402344
+INFO - evaluator.py - 2025-03-25 01:40:22,141 - Epoch: 170 Train acc: 100.0 Val acc: 1.08 Test acc1.05; Train loss: 0.005395311437530273 Val loss: 22.449398236083983
+INFO - evaluator.py - 2025-03-25 01:41:02,306 - Epoch: 171 Train acc: 100.0 Val acc: 1.04 Test acc1.03; Train loss: 0.00536014260659841 Val loss: 25.257161041259767
+INFO - evaluator.py - 2025-03-25 01:41:42,474 - Epoch: 172 Train acc: 100.0 Val acc: 1.0999999999999999 Test acc1.02; Train loss: 0.005305622348561884 Val loss: 24.10679811401367
+INFO - evaluator.py - 2025-03-25 01:42:22,647 - Epoch: 173 Train acc: 100.0 Val acc: 1.06 Test acc1.02; Train loss: 0.005359670651729473 Val loss: 25.37503610229492
+INFO - evaluator.py - 2025-03-25 01:43:02,991 - Epoch: 174 Train acc: 100.0 Val acc: 1.1199999999999999 Test acc0.9900000000000001; Train loss: 0.005284743823966181 Val loss: 24.228974047851562
+INFO - evaluator.py - 2025-03-25 01:43:43,185 - Epoch: 175 Train acc: 100.0 Val acc: 1.0999999999999999 Test acc1.01; Train loss: 0.005185583768404004 Val loss: 26.38803526611328
+INFO - evaluator.py - 2025-03-25 01:44:23,322 - Epoch: 176 Train acc: 100.0 Val acc: 1.08 Test acc0.9900000000000001; Train loss: 0.005138776256719773 Val loss: 26.15312455444336
+INFO - evaluator.py - 2025-03-25 01:45:03,463 - Epoch: 177 Train acc: 100.0 Val acc: 1.0999999999999999 Test acc1.0; Train loss: 0.005082814830406146 Val loss: 26.157883392333986
+INFO - evaluator.py - 2025-03-25 01:45:43,864 - Epoch: 178 Train acc: 100.0 Val acc: 1.1199999999999999 Test acc1.03; Train loss: 0.0050554427398876705 Val loss: 25.771735766601562
+INFO - evaluator.py - 2025-03-25 01:46:24,072 - Epoch: 179 Train acc: 99.99818181818182 Val acc: 1.1199999999999999 Test acc1.02; Train loss: 0.005219219811599363 Val loss: 26.162980224609374
+INFO - evaluator.py - 2025-03-25 01:47:04,278 - Epoch: 180 Train acc: 100.0 Val acc: 1.0999999999999999 Test acc1.0; Train loss: 0.0046989986532367765 Val loss: 24.371998736572266
+INFO - evaluator.py - 2025-03-25 01:47:44,465 - Epoch: 181 Train acc: 100.0 Val acc: 1.0999999999999999 Test acc1.03; Train loss: 0.004644713872577995 Val loss: 19.992197131347655
+INFO - evaluator.py - 2025-03-25 01:48:24,904 - Epoch: 182 Train acc: 100.0 Val acc: 1.08 Test acc1.05; Train loss: 0.004581244515678423 Val loss: 17.73906696166992
+INFO - evaluator.py - 2025-03-25 01:49:05,095 - Epoch: 183 Train acc: 100.0 Val acc: 1.08 Test acc1.03; Train loss: 0.0045864309157244865 Val loss: 15.298638876342775
+INFO - evaluator.py - 2025-03-25 01:49:45,304 - Epoch: 184 Train acc: 100.0 Val acc: 1.16 Test acc1.08; Train loss: 0.004563777835167606 Val loss: 13.213401361083985
+INFO - evaluator.py - 2025-03-25 01:50:25,456 - Epoch: 185 Train acc: 100.0 Val acc: 1.1199999999999999 Test acc1.04; Train loss: 0.004555911798893727 Val loss: 12.083396154785158
+INFO - evaluator.py - 2025-03-25 01:51:05,842 - Epoch: 186 Train acc: 100.0 Val acc: 1.1400000000000001 Test acc1.1400000000000001; Train loss: 0.00451209121002731 Val loss: 10.597362313842774
+INFO - evaluator.py - 2025-03-25 01:51:46,009 - Epoch: 187 Train acc: 100.0 Val acc: 1.06 Test acc1.1400000000000001; Train loss: 0.004605895052147521 Val loss: 9.29454969177246
+INFO - evaluator.py - 2025-03-25 01:52:26,172 - Epoch: 188 Train acc: 100.0 Val acc: 1.1199999999999999 Test acc1.1400000000000001; Train loss: 0.004487929442601108 Val loss: 8.37106693725586
+INFO - evaluator.py - 2025-03-25 01:53:06,350 - Epoch: 189 Train acc: 100.0 Val acc: 1.1400000000000001 Test acc1.1900000000000002; Train loss: 0.004534222034009342 Val loss: 7.582823272705078
+INFO - evaluator.py - 2025-03-25 01:53:46,723 - Epoch: 190 Train acc: 100.0 Val acc: 1.1400000000000001 Test acc1.17; Train loss: 0.004445930599582127 Val loss: 6.992778227233886
+INFO - evaluator.py - 2025-03-25 01:54:26,873 - Epoch: 191 Train acc: 100.0 Val acc: 1.06 Test acc1.17; Train loss: 0.004516150449682027 Val loss: 6.435010780334473
+INFO - evaluator.py - 2025-03-25 01:55:07,058 - Epoch: 192 Train acc: 100.0 Val acc: 1.1199999999999999 Test acc1.15; Train loss: 0.004491132422993806 Val loss: 5.9677687271118165
+INFO - evaluator.py - 2025-03-25 01:55:47,249 - Epoch: 193 Train acc: 100.0 Val acc: 1.16 Test acc1.1900000000000002; Train loss: 0.004470925203880126 Val loss: 5.382484057617188
+INFO - evaluator.py - 2025-03-25 01:56:27,626 - Epoch: 194 Train acc: 100.0 Val acc: 1.1400000000000001 Test acc1.18; Train loss: 0.0044633680613118815 Val loss: 5.1891451171875005
+INFO - evaluator.py - 2025-03-25 01:57:07,841 - Epoch: 195 Train acc: 100.0 Val acc: 1.18 Test acc1.22; Train loss: 0.004448035185513172 Val loss: 4.835767662048339
+INFO - evaluator.py - 2025-03-25 01:57:48,014 - Epoch: 196 Train acc: 100.0 Val acc: 1.26 Test acc1.1900000000000002; Train loss: 0.004462447274730287 Val loss: 4.407347955322265
+INFO - evaluator.py - 2025-03-25 01:58:28,164 - Epoch: 197 Train acc: 100.0 Val acc: 1.3 Test acc1.22; Train loss: 0.004498372372248294 Val loss: 4.165109513854981
+INFO - evaluator.py - 2025-03-25 01:59:08,542 - Epoch: 198 Train acc: 100.0 Val acc: 1.46 Test acc1.24; Train loss: 0.004370267492566597 Val loss: 3.875188774108887
+INFO - evaluator.py - 2025-03-25 01:59:48,699 - Epoch: 199 Train acc: 100.0 Val acc: 1.54 Test acc1.27; Train loss: 0.004371671004305509 Val loss: 3.6592526596069335
+INFO - evaluator.py - 2025-03-25 01:59:48,712 - The best acc of synthetic images on sensitive val and the corresponding acc on test dataset from resnet is 3.6799999999999997 and 3.71
+INFO - evaluator.py - 2025-03-25 01:59:48,713 - The best acc of synthetic images on noisy sensitive val and the corresponding acc on test dataset from resnet is 3.6799999999999997 and 3.71
+INFO - evaluator.py - 2025-03-25 01:59:48,713 - The best acc test dataset from resnet is 3.8
+INFO - evaluator.py - 2025-03-25 02:00:25,615 - Epoch: 0 Train acc: 3.2981818181818183 Val acc: 4.54 Test acc4.82; Train loss: 4.429082927357066 Val loss: 0.5645907205581665
+INFO - evaluator.py - 2025-03-25 02:00:59,717 - Epoch: 1 Train acc: 5.781818181818181 Val acc: 5.06 Test acc5.0; Train loss: 4.181747739367052 Val loss: 0.6927968404769896
+INFO - evaluator.py - 2025-03-25 02:01:33,825 - Epoch: 2 Train acc: 8.654545454545454 Val acc: 6.36 Test acc6.550000000000001; Train loss: 3.953011191948977 Val loss: 0.6709507570266724
+INFO - evaluator.py - 2025-03-25 02:02:07,922 - Epoch: 3 Train acc: 11.670909090909092 Val acc: 4.760000000000001 Test acc4.66; Train loss: 3.73675145072937 Val loss: 0.9822225328445434
+INFO - evaluator.py - 2025-03-25 02:02:42,030 - Epoch: 4 Train acc: 14.223636363636363 Val acc: 6.52 Test acc6.35; Train loss: 3.5569211908253755 Val loss: 0.9515760744094849
+INFO - evaluator.py - 2025-03-25 02:03:16,117 - Epoch: 5 Train acc: 17.52 Val acc: 5.0200000000000005 Test acc4.859999999999999; Train loss: 3.3686216043558987 Val loss: 1.3267229610443114
+INFO - evaluator.py - 2025-03-25 02:03:50,223 - Epoch: 6 Train acc: 22.770909090909093 Val acc: 5.1 Test acc5.01; Train loss: 3.087329899224368 Val loss: 1.452848194885254
+INFO - evaluator.py - 2025-03-25 02:04:24,313 - Epoch: 7 Train acc: 30.983636363636364 Val acc: 4.5600000000000005 Test acc4.45; Train loss: 2.6700003202785147 Val loss: 1.789144941329956
+INFO - evaluator.py - 2025-03-25 02:04:58,397 - Epoch: 8 Train acc: 41.943636363636365 Val acc: 4.68 Test acc4.84; Train loss: 2.181932268307426 Val loss: 1.5526110443115233
+INFO - evaluator.py - 2025-03-25 02:05:32,487 - Epoch: 9 Train acc: 51.654545454545456 Val acc: 4.08 Test acc4.08; Train loss: 1.7788531913020393 Val loss: 1.5954423877716064
+INFO - evaluator.py - 2025-03-25 02:06:06,576 - Epoch: 10 Train acc: 60.701818181818176 Val acc: 5.82 Test acc6.39; Train loss: 1.4287151935295626 Val loss: 1.3783558330535888
+INFO - evaluator.py - 2025-03-25 02:06:40,684 - Epoch: 11 Train acc: 67.14363636363636 Val acc: 3.82 Test acc4.109999999999999; Train loss: 1.1852655199007553 Val loss: 1.905956632232666
+INFO - evaluator.py - 2025-03-25 02:07:14,775 - Epoch: 12 Train acc: 70.9909090909091 Val acc: 4.6 Test acc4.77; Train loss: 1.0432930661656639 Val loss: 1.2106360450744629
+INFO - evaluator.py - 2025-03-25 02:07:48,875 - Epoch: 13 Train acc: 74.57272727272726 Val acc: 5.4399999999999995 Test acc5.09; Train loss: 0.9124262453295967 Val loss: 1.417073998260498
+INFO - evaluator.py - 2025-03-25 02:08:22,967 - Epoch: 14 Train acc: 76.56363636363636 Val acc: 5.1 Test acc5.08; Train loss: 0.8325771866603331 Val loss: 1.3215801544189454
+INFO - evaluator.py - 2025-03-25 02:08:57,068 - Epoch: 15 Train acc: 78.28 Val acc: 5.16 Test acc4.83; Train loss: 0.7730300558404489 Val loss: 1.598954150390625
+INFO - evaluator.py - 2025-03-25 02:09:31,166 - Epoch: 16 Train acc: 79.2890909090909 Val acc: 5.36 Test acc5.140000000000001; Train loss: 0.7333754772468046 Val loss: 1.313283118057251
+INFO - evaluator.py - 2025-03-25 02:10:05,252 - Epoch: 17 Train acc: 80.73636363636363 Val acc: 3.2399999999999998 Test acc3.71; Train loss: 0.6868946974559264 Val loss: 1.791840004348755
+INFO - evaluator.py - 2025-03-25 02:10:39,361 - Epoch: 18 Train acc: 81.35636363636364 Val acc: 3.82 Test acc4.05; Train loss: 0.6560985690853812 Val loss: 1.5549170917510986
+INFO - evaluator.py - 2025-03-25 02:11:13,458 - Epoch: 19 Train acc: 82.26 Val acc: 3.7199999999999998 Test acc3.7900000000000005; Train loss: 0.6213868443749168 Val loss: 1.7025408737182617
+INFO - evaluator.py - 2025-03-25 02:11:47,564 - Epoch: 20 Train acc: 82.86181818181818 Val acc: 4.12 Test acc4.41; Train loss: 0.6041698032877663 Val loss: 1.2562307521820069
+INFO - evaluator.py - 2025-03-25 02:12:21,655 - Epoch: 21 Train acc: 83.56727272727272 Val acc: 4.66 Test acc4.6; Train loss: 0.5775095322229645 Val loss: 1.2040027370452882
+INFO - evaluator.py - 2025-03-25 02:12:55,757 - Epoch: 22 Train acc: 84.16 Val acc: 3.92 Test acc4.02; Train loss: 0.5601564015269279 Val loss: 1.5319328968048096
+INFO - evaluator.py - 2025-03-25 02:13:29,848 - Epoch: 23 Train acc: 84.63272727272727 Val acc: 3.58 Test acc4.01; Train loss: 0.5448559866818515 Val loss: 1.7760811843872069
+INFO - evaluator.py - 2025-03-25 02:14:03,942 - Epoch: 24 Train acc: 84.95636363636365 Val acc: 5.4399999999999995 Test acc5.17; Train loss: 0.5314899985150857 Val loss: 1.130853076171875
+INFO - evaluator.py - 2025-03-25 02:14:38,059 - Epoch: 25 Train acc: 85.1 Val acc: 4.8 Test acc5.06; Train loss: 0.5239905119077727 Val loss: 1.3566979248046875
+INFO - evaluator.py - 2025-03-25 02:15:12,164 - Epoch: 26 Train acc: 84.69818181818182 Val acc: 3.7199999999999998 Test acc3.53; Train loss: 0.5362017590826208 Val loss: 1.9206997386932374
+INFO - evaluator.py - 2025-03-25 02:15:46,266 - Epoch: 27 Train acc: 85.38545454545454 Val acc: 4.34 Test acc4.22; Train loss: 0.5113372699856759 Val loss: 1.4952837455749513
+INFO - evaluator.py - 2025-03-25 02:16:20,551 - Epoch: 28 Train acc: 86.04545454545455 Val acc: 3.4000000000000004 Test acc3.18; Train loss: 0.49302210255048495 Val loss: 1.367482911300659
+INFO - evaluator.py - 2025-03-25 02:16:54,663 - Epoch: 29 Train acc: 85.55818181818182 Val acc: 2.96 Test acc3.38; Train loss: 0.5064506278932095 Val loss: 1.8881914752960205
+INFO - evaluator.py - 2025-03-25 02:17:28,759 - Epoch: 30 Train acc: 85.57272727272728 Val acc: 4.5600000000000005 Test acc3.9899999999999998; Train loss: 0.5036979588519443 Val loss: 1.2079647983551025
+INFO - evaluator.py - 2025-03-25 02:18:02,873 - Epoch: 31 Train acc: 86.10545454545453 Val acc: 3.56 Test acc3.6700000000000004; Train loss: 0.4939658161445098 Val loss: 1.6303554485321046
+INFO - evaluator.py - 2025-03-25 02:18:36,967 - Epoch: 32 Train acc: 86.45818181818183 Val acc: 3.88 Test acc3.8699999999999997; Train loss: 0.4797150917318734 Val loss: 1.1395186283111571
+INFO - evaluator.py - 2025-03-25 02:19:11,060 - Epoch: 33 Train acc: 85.69636363636364 Val acc: 4.3 Test acc4.26; Train loss: 0.4974502932022918 Val loss: 1.4812414775848388
+INFO - evaluator.py - 2025-03-25 02:19:45,146 - Epoch: 34 Train acc: 86.94181818181819 Val acc: 3.2199999999999998 Test acc3.2099999999999995; Train loss: 0.46364210361892527 Val loss: 1.4471210357666016
+INFO - evaluator.py - 2025-03-25 02:20:19,242 - Epoch: 35 Train acc: 86.48545454545454 Val acc: 4.3 Test acc3.85; Train loss: 0.4789141296224161 Val loss: 1.202765058517456
+INFO - evaluator.py - 2025-03-25 02:20:53,342 - Epoch: 36 Train acc: 86.5 Val acc: 4.18 Test acc4.24; Train loss: 0.477527528251843 Val loss: 1.3190020099639892
+INFO - evaluator.py - 2025-03-25 02:21:27,423 - Epoch: 37 Train acc: 86.86181818181818 Val acc: 3.56 Test acc3.5999999999999996; Train loss: 0.46027575102177537 Val loss: 1.3065678829193115
+INFO - evaluator.py - 2025-03-25 02:22:01,493 - Epoch: 38 Train acc: 86.29818181818182 Val acc: 3.66 Test acc3.5700000000000003; Train loss: 0.48352133117209783 Val loss: 1.71624923286438
+INFO - evaluator.py - 2025-03-25 02:22:35,547 - Epoch: 39 Train acc: 87.16000000000001 Val acc: 3.34 Test acc3.38; Train loss: 0.4496082278853113 Val loss: 1.750997886657715
+INFO - evaluator.py - 2025-03-25 02:23:09,622 - Epoch: 40 Train acc: 86.50727272727273 Val acc: 3.9 Test acc4.03; Train loss: 0.4743156030194326 Val loss: 1.4347664085388183
+INFO - evaluator.py - 2025-03-25 02:23:43,681 - Epoch: 41 Train acc: 87.17090909090909 Val acc: 3.56 Test acc3.8600000000000003; Train loss: 0.44953623210896143 Val loss: 1.2223971153259279
+INFO - evaluator.py - 2025-03-25 02:24:17,746 - Epoch: 42 Train acc: 86.78181818181818 Val acc: 4.78 Test acc4.3; Train loss: 0.4630531727460298 Val loss: 1.1335169929504394
+INFO - evaluator.py - 2025-03-25 02:24:51,802 - Epoch: 43 Train acc: 86.97272727272727 Val acc: 2.48 Test acc2.9899999999999998; Train loss: 0.4523081766892563 Val loss: 2.0983613296508787
+INFO - evaluator.py - 2025-03-25 02:25:25,860 - Epoch: 44 Train acc: 87.35818181818182 Val acc: 3.88 Test acc4.41; Train loss: 0.44542475351311944 Val loss: 1.197934939956665
+INFO - evaluator.py - 2025-03-25 02:25:59,915 - Epoch: 45 Train acc: 87.42363636363636 Val acc: 4.02 Test acc4.33; Train loss: 0.4403644183142619 Val loss: 1.4044873363494874
+INFO - evaluator.py - 2025-03-25 02:26:33,967 - Epoch: 46 Train acc: 87.10181818181817 Val acc: 3.56 Test acc3.66; Train loss: 0.453050728606094 Val loss: 1.3227576072692873
+INFO - evaluator.py - 2025-03-25 02:27:08,037 - Epoch: 47 Train acc: 87.30909090909091 Val acc: 4.16 Test acc4.37; Train loss: 0.44860074281638324 Val loss: 1.3691553394317628
+INFO - evaluator.py - 2025-03-25 02:27:42,081 - Epoch: 48 Train acc: 86.83999999999999 Val acc: 4.3 Test acc4.65; Train loss: 0.4600763305468993 Val loss: 1.2214299716949464
+INFO - evaluator.py - 2025-03-25 02:28:16,149 - Epoch: 49 Train acc: 87.2 Val acc: 3.44 Test acc3.7199999999999998; Train loss: 0.445278752883456 Val loss: 1.3015135162353517
+INFO - evaluator.py - 2025-03-25 02:28:50,205 - Epoch: 50 Train acc: 86.89818181818183 Val acc: 3.18 Test acc3.02; Train loss: 0.4606245203717188 Val loss: 1.35390651512146
+INFO - evaluator.py - 2025-03-25 02:29:24,266 - Epoch: 51 Train acc: 87.18545454545455 Val acc: 3.42 Test acc3.61; Train loss: 0.4489938171045347 Val loss: 1.479027258682251
+INFO - evaluator.py - 2025-03-25 02:29:58,321 - Epoch: 52 Train acc: 87.32545454545455 Val acc: 3.62 Test acc3.9; Train loss: 0.4419051434674046 Val loss: 1.258982748413086
+INFO - evaluator.py - 2025-03-25 02:30:32,384 - Epoch: 53 Train acc: 87.36 Val acc: 3.92 Test acc4.42; Train loss: 0.4447697356386618 Val loss: 1.4082653800964355
+INFO - evaluator.py - 2025-03-25 02:31:06,437 - Epoch: 54 Train acc: 87.59272727272727 Val acc: 3.3000000000000003 Test acc2.94; Train loss: 0.4363918873282996 Val loss: 1.2807152057647704
+INFO - evaluator.py - 2025-03-25 02:31:40,501 - Epoch: 55 Train acc: 87.44727272727273 Val acc: 3.7199999999999998 Test acc3.7199999999999998; Train loss: 0.4391412670108405 Val loss: 1.2989601253509522
+INFO - evaluator.py - 2025-03-25 02:32:14,554 - Epoch: 56 Train acc: 87.27272727272727 Val acc: 4.36 Test acc4.58; Train loss: 0.44797542509599164 Val loss: 1.099622097015381
+INFO - evaluator.py - 2025-03-25 02:32:48,604 - Epoch: 57 Train acc: 87.7109090909091 Val acc: 4.02 Test acc3.91; Train loss: 0.43491414139379153 Val loss: 1.1784457328796387
+INFO - evaluator.py - 2025-03-25 02:33:22,663 - Epoch: 58 Train acc: 86.79272727272728 Val acc: 3.4000000000000004 Test acc3.52; Train loss: 0.46241240387775684 Val loss: 1.3316786979675292
+INFO - evaluator.py - 2025-03-25 02:33:56,720 - Epoch: 59 Train acc: 87.65818181818182 Val acc: 2.6 Test acc2.4299999999999997; Train loss: 0.43581123066544536 Val loss: 1.508017102432251
+INFO - evaluator.py - 2025-03-25 02:34:30,778 - Epoch: 60 Train acc: 97.89454545454545 Val acc: 3.66 Test acc3.65; Train loss: 0.09573871492059394 Val loss: 1.7750721759796142
+INFO - evaluator.py - 2025-03-25 02:35:04,839 - Epoch: 61 Train acc: 99.47090909090909 Val acc: 5.0200000000000005 Test acc5.1; Train loss: 0.036011693437973204 Val loss: 1.7329274196624758
+INFO - evaluator.py - 2025-03-25 02:35:38,904 - Epoch: 62 Train acc: 99.74 Val acc: 4.760000000000001 Test acc4.859999999999999; Train loss: 0.023543442181125283 Val loss: 2.330722615814209
+INFO - evaluator.py - 2025-03-25 02:36:12,955 - Epoch: 63 Train acc: 99.8490909090909 Val acc: 3.4000000000000004 Test acc3.74; Train loss: 0.019548761420764706 Val loss: 3.6163000717163087
+INFO - evaluator.py - 2025-03-25 02:36:47,024 - Epoch: 64 Train acc: 99.87636363636364 Val acc: 2.76 Test acc2.8400000000000003; Train loss: 0.01711916612242772 Val loss: 5.367026870727539
+INFO - evaluator.py - 2025-03-25 02:37:21,078 - Epoch: 65 Train acc: 99.92909090909092 Val acc: 2.36 Test acc2.06; Train loss: 0.015571786229346286 Val loss: 8.87397797241211
+INFO - evaluator.py - 2025-03-25 02:37:55,149 - Epoch: 66 Train acc: 99.92909090909092 Val acc: 2.06 Test acc1.8800000000000001; Train loss: 0.01509733100105077 Val loss: 12.739764907836914
+INFO - evaluator.py - 2025-03-25 02:38:29,202 - Epoch: 67 Train acc: 99.92181818181818 Val acc: 1.7999999999999998 Test acc1.69; Train loss: 0.01579281576341865 Val loss: 17.617791577148434
+INFO - evaluator.py - 2025-03-25 02:39:03,256 - Epoch: 68 Train acc: 99.91272727272728 Val acc: 1.58 Test acc1.55; Train loss: 0.015561321213993838 Val loss: 21.06864503173828
+INFO - evaluator.py - 2025-03-25 02:39:37,324 - Epoch: 69 Train acc: 99.86 Val acc: 1.3599999999999999 Test acc1.32; Train loss: 0.01809710904027928 Val loss: 29.245914294433593
+INFO - evaluator.py - 2025-03-25 02:40:11,383 - Epoch: 70 Train acc: 99.9 Val acc: 1.24 Test acc1.34; Train loss: 0.01755655172070996 Val loss: 30.691079461669922
+INFO - evaluator.py - 2025-03-25 02:40:45,453 - Epoch: 71 Train acc: 99.83454545454545 Val acc: 1.1400000000000001 Test acc1.21; Train loss: 0.020533668188818476 Val loss: 33.3963419128418
+INFO - evaluator.py - 2025-03-25 02:41:19,503 - Epoch: 72 Train acc: 99.78363636363636 Val acc: 1.2 Test acc1.2; Train loss: 0.02261205360970714 Val loss: 29.450613537597658
+INFO - evaluator.py - 2025-03-25 02:41:53,577 - Epoch: 73 Train acc: 99.59090909090908 Val acc: 1.28 Test acc1.37; Train loss: 0.03179788305932148 Val loss: 28.454243389892575
+INFO - evaluator.py - 2025-03-25 02:42:27,625 - Epoch: 74 Train acc: 99.52545454545455 Val acc: 1.08 Test acc1.1400000000000001; Train loss: 0.03791048280021006 Val loss: 28.616738708496094
+INFO - evaluator.py - 2025-03-25 02:43:01,694 - Epoch: 75 Train acc: 99.34181818181818 Val acc: 1.18 Test acc1.3; Train loss: 0.045227725261822345 Val loss: 19.27615583496094
+INFO - evaluator.py - 2025-03-25 02:43:35,753 - Epoch: 76 Train acc: 98.66727272727273 Val acc: 1.04 Test acc1.01; Train loss: 0.07045888841490854 Val loss: 24.976401525878906
+INFO - evaluator.py - 2025-03-25 02:44:09,817 - Epoch: 77 Train acc: 97.77818181818182 Val acc: 1.16 Test acc1.0699999999999998; Train loss: 0.10030847114751285 Val loss: 12.174452380371093
+INFO - evaluator.py - 2025-03-25 02:44:43,874 - Epoch: 78 Train acc: 97.18545454545455 Val acc: 1.04 Test acc1.06; Train loss: 0.12096487621136687 Val loss: 7.694302395629882
+INFO - evaluator.py - 2025-03-25 02:45:17,932 - Epoch: 79 Train acc: 97.25090909090909 Val acc: 1.24 Test acc1.18; Train loss: 0.11625029519376429 Val loss: 5.0602594757080075
+INFO - evaluator.py - 2025-03-25 02:45:51,991 - Epoch: 80 Train acc: 97.45272727272727 Val acc: 1.24 Test acc1.22; Train loss: 0.10382050825100055 Val loss: 4.146434843444824
+INFO - evaluator.py - 2025-03-25 02:46:26,051 - Epoch: 81 Train acc: 97.75454545454545 Val acc: 1.6400000000000001 Test acc1.6; Train loss: 0.09593071702651003 Val loss: 3.142624925994873
+INFO - evaluator.py - 2025-03-25 02:47:00,124 - Epoch: 82 Train acc: 97.46909090909091 Val acc: 1.66 Test acc1.5; Train loss: 0.10266279497952623 Val loss: 2.777140042877197
+INFO - evaluator.py - 2025-03-25 02:47:34,174 - Epoch: 83 Train acc: 97.38181818181818 Val acc: 1.96 Test acc2.04; Train loss: 0.10628147186596286 Val loss: 2.2689825965881347
+INFO - evaluator.py - 2025-03-25 02:48:08,437 - Epoch: 84 Train acc: 97.97090909090909 Val acc: 2.9000000000000004 Test acc2.92; Train loss: 0.0851319029182873 Val loss: 1.6667073406219484
+INFO - evaluator.py - 2025-03-25 02:48:42,487 - Epoch: 85 Train acc: 97.90545454545455 Val acc: 2.74 Test acc3.01; Train loss: 0.08684004848761992 Val loss: 1.6616566749572754
+INFO - evaluator.py - 2025-03-25 02:49:16,558 - Epoch: 86 Train acc: 97.85636363636364 Val acc: 4.36 Test acc4.22; Train loss: 0.0887560682352971 Val loss: 1.206422843170166
+INFO - evaluator.py - 2025-03-25 02:49:50,615 - Epoch: 87 Train acc: 97.66 Val acc: 4.34 Test acc4.52; Train loss: 0.09482697315378623 Val loss: 1.1788708694458008
+INFO - evaluator.py - 2025-03-25 02:50:24,677 - Epoch: 88 Train acc: 97.80545454545455 Val acc: 3.6999999999999997 Test acc3.58; Train loss: 0.09392274176850915 Val loss: 1.4564334251403808
+INFO - evaluator.py - 2025-03-25 02:50:58,736 - Epoch: 89 Train acc: 98.2 Val acc: 4.18 Test acc4.2; Train loss: 0.07812307544560594 Val loss: 1.277392050933838
+INFO - evaluator.py - 2025-03-25 02:51:32,779 - Epoch: 90 Train acc: 97.90545454545455 Val acc: 4.22 Test acc4.35; Train loss: 0.08786305072151802 Val loss: 1.0985202266693115
+INFO - evaluator.py - 2025-03-25 02:52:06,851 - Epoch: 91 Train acc: 97.78363636363636 Val acc: 3.34 Test acc3.02; Train loss: 0.08980003556094386 Val loss: 1.2880304145812989
+INFO - evaluator.py - 2025-03-25 02:52:40,899 - Epoch: 92 Train acc: 97.8 Val acc: 4.9 Test acc4.82; Train loss: 0.09049852514415979 Val loss: 1.2515059204101562
+INFO - evaluator.py - 2025-03-25 02:53:14,970 - Epoch: 93 Train acc: 97.55818181818182 Val acc: 4.38 Test acc4.21; Train loss: 0.09969870219034228 Val loss: 1.221478277206421
+INFO - evaluator.py - 2025-03-25 02:53:49,024 - Epoch: 94 Train acc: 97.66363636363636 Val acc: 5.56 Test acc5.38; Train loss: 0.09517888885743239 Val loss: 0.9608816625595092
+INFO - evaluator.py - 2025-03-25 02:54:23,088 - Epoch: 95 Train acc: 97.89272727272727 Val acc: 5.0 Test acc5.0; Train loss: 0.08865076851689004 Val loss: 1.0451984642028809
+INFO - evaluator.py - 2025-03-25 02:54:57,098 - Epoch: 96 Train acc: 98.11090909090909 Val acc: 3.1 Test acc2.8899999999999997; Train loss: 0.08180226598673247 Val loss: 1.3928373447418214
+INFO - evaluator.py - 2025-03-25 02:55:31,109 - Epoch: 97 Train acc: 97.96727272727273 Val acc: 5.12 Test acc4.93; Train loss: 0.08421961458494717 Val loss: 1.1083239624023438
+INFO - evaluator.py - 2025-03-25 02:56:05,109 - Epoch: 98 Train acc: 98.09454545454545 Val acc: 4.22 Test acc4.08; Train loss: 0.08229987417202105 Val loss: 1.0013363388061522
+INFO - evaluator.py - 2025-03-25 02:56:39,179 - Epoch: 99 Train acc: 97.45636363636365 Val acc: 4.5 Test acc4.87; Train loss: 0.10155410905500704 Val loss: 1.037499094390869
+INFO - evaluator.py - 2025-03-25 02:57:13,227 - Epoch: 100 Train acc: 97.80545454545455 Val acc: 4.44 Test acc4.15; Train loss: 0.08945149410671809 Val loss: 1.0456145164489745
+INFO - evaluator.py - 2025-03-25 02:57:47,294 - Epoch: 101 Train acc: 97.89454545454545 Val acc: 3.94 Test acc4.29; Train loss: 0.08618221807865933 Val loss: 1.117967208480835
+INFO - evaluator.py - 2025-03-25 02:58:21,348 - Epoch: 102 Train acc: 98.0690909090909 Val acc: 4.6 Test acc4.569999999999999; Train loss: 0.08147576460486108 Val loss: 1.1452808269500732
+INFO - evaluator.py - 2025-03-25 02:58:55,410 - Epoch: 103 Train acc: 97.49272727272728 Val acc: 4.22 Test acc4.32; Train loss: 0.0996676291488111 Val loss: 1.1173604816436766
+INFO - evaluator.py - 2025-03-25 02:59:29,436 - Epoch: 104 Train acc: 97.94545454545455 Val acc: 4.34 Test acc3.82; Train loss: 0.08645147181044925 Val loss: 1.207551894378662
+INFO - evaluator.py - 2025-03-25 03:00:03,451 - Epoch: 105 Train acc: 98.11272727272727 Val acc: 4.44 Test acc4.25; Train loss: 0.07961197814006697 Val loss: 1.073412247467041
+INFO - evaluator.py - 2025-03-25 03:00:37,445 - Epoch: 106 Train acc: 98.01818181818182 Val acc: 4.36 Test acc4.08; Train loss: 0.08246078905666417 Val loss: 1.0403310710906983
+INFO - evaluator.py - 2025-03-25 03:01:11,462 - Epoch: 107 Train acc: 97.82545454545455 Val acc: 5.28 Test acc5.08; Train loss: 0.08983543616750024 Val loss: 1.028629866027832
+INFO - evaluator.py - 2025-03-25 03:01:45,470 - Epoch: 108 Train acc: 97.40545454545455 Val acc: 4.2 Test acc4.3999999999999995; Train loss: 0.10201461504765533 Val loss: 1.1322341571807861
+INFO - evaluator.py - 2025-03-25 03:02:19,532 - Epoch: 109 Train acc: 97.84545454545454 Val acc: 4.760000000000001 Test acc4.96; Train loss: 0.08883858939971437 Val loss: 1.2052562049865723
+INFO - evaluator.py - 2025-03-25 03:02:53,588 - Epoch: 110 Train acc: 97.78545454545454 Val acc: 4.6 Test acc4.4799999999999995; Train loss: 0.08929745876938104 Val loss: 1.0692474952697755
+INFO - evaluator.py - 2025-03-25 03:03:27,653 - Epoch: 111 Train acc: 98.13272727272727 Val acc: 3.6799999999999997 Test acc3.9; Train loss: 0.08071517808335749 Val loss: 1.0798618263244628
+INFO - evaluator.py - 2025-03-25 03:04:01,694 - Epoch: 112 Train acc: 97.85454545454544 Val acc: 3.62 Test acc3.53; Train loss: 0.08847810698138042 Val loss: 1.1655329486846924
+INFO - evaluator.py - 2025-03-25 03:04:35,741 - Epoch: 113 Train acc: 97.74363636363637 Val acc: 4.22 Test acc4.51; Train loss: 0.09172227202233943 Val loss: 1.0845339786529542
+INFO - evaluator.py - 2025-03-25 03:05:09,807 - Epoch: 114 Train acc: 97.99454545454546 Val acc: 3.58 Test acc3.83; Train loss: 0.08182800412977283 Val loss: 1.3364709171295166
+INFO - evaluator.py - 2025-03-25 03:05:43,863 - Epoch: 115 Train acc: 97.72181818181818 Val acc: 2.76 Test acc3.27; Train loss: 0.09261377343454144 Val loss: 1.311645729446411
+INFO - evaluator.py - 2025-03-25 03:06:17,918 - Epoch: 116 Train acc: 98.03090909090909 Val acc: 4.9 Test acc5.24; Train loss: 0.08280995710356669 Val loss: 1.0420331794738769
+INFO - evaluator.py - 2025-03-25 03:06:51,959 - Epoch: 117 Train acc: 98.03636363636363 Val acc: 3.8600000000000003 Test acc4.04; Train loss: 0.0806843323956159 Val loss: 1.2030714260101318
+INFO - evaluator.py - 2025-03-25 03:07:26,029 - Epoch: 118 Train acc: 97.74181818181819 Val acc: 3.58 Test acc3.7699999999999996; Train loss: 0.09204835592752154 Val loss: 1.2071126266479493
+INFO - evaluator.py - 2025-03-25 03:08:00,083 - Epoch: 119 Train acc: 97.6381818181818 Val acc: 4.24 Test acc4.130000000000001; Train loss: 0.09649705927202647 Val loss: 1.1447912590026856
+INFO - evaluator.py - 2025-03-25 03:08:34,167 - Epoch: 120 Train acc: 99.55454545454545 Val acc: 5.24 Test acc5.140000000000001; Train loss: 0.02568181115177206 Val loss: 1.0149881732940675
+INFO - evaluator.py - 2025-03-25 03:09:08,234 - Epoch: 121 Train acc: 99.88545454545455 Val acc: 5.26 Test acc5.34; Train loss: 0.01107409254421734 Val loss: 0.9761524887084961
+INFO - evaluator.py - 2025-03-25 03:09:42,300 - Epoch: 122 Train acc: 99.92545454545456 Val acc: 4.859999999999999 Test acc5.33; Train loss: 0.009047720700223 Val loss: 0.981003203201294
+INFO - evaluator.py - 2025-03-25 03:10:16,352 - Epoch: 123 Train acc: 99.93818181818182 Val acc: 5.12 Test acc5.38; Train loss: 0.007878831190052865 Val loss: 0.9526613862991333
+INFO - evaluator.py - 2025-03-25 03:10:50,411 - Epoch: 124 Train acc: 99.95454545454545 Val acc: 5.26 Test acc5.46; Train loss: 0.007066480822649531 Val loss: 0.9447735408782959
+INFO - evaluator.py - 2025-03-25 03:11:24,468 - Epoch: 125 Train acc: 99.96727272727273 Val acc: 5.16 Test acc5.46; Train loss: 0.0063011638032145455 Val loss: 0.9187302131652832
+INFO - evaluator.py - 2025-03-25 03:11:58,537 - Epoch: 126 Train acc: 99.98181818181818 Val acc: 5.12 Test acc5.29; Train loss: 0.0056606640884060075 Val loss: 0.9247069026947021
+INFO - evaluator.py - 2025-03-25 03:12:32,598 - Epoch: 127 Train acc: 99.95272727272727 Val acc: 5.0200000000000005 Test acc5.13; Train loss: 0.0060850385947914965 Val loss: 0.9302021352767944
+INFO - evaluator.py - 2025-03-25 03:13:06,649 - Epoch: 128 Train acc: 99.97454545454545 Val acc: 4.5600000000000005 Test acc4.91; Train loss: 0.005714419695438648 Val loss: 0.9430918842315674
+INFO - evaluator.py - 2025-03-25 03:13:40,708 - Epoch: 129 Train acc: 99.98 Val acc: 4.34 Test acc4.75; Train loss: 0.005286324829972265 Val loss: 0.9293124967575074
+INFO - evaluator.py - 2025-03-25 03:14:14,756 - Epoch: 130 Train acc: 99.98363636363636 Val acc: 4.14 Test acc4.569999999999999; Train loss: 0.005305890395234085 Val loss: 0.9332214340209961
+INFO - evaluator.py - 2025-03-25 03:14:48,809 - Epoch: 131 Train acc: 99.98181818181818 Val acc: 4.14 Test acc4.63; Train loss: 0.005442973955534399 Val loss: 0.9103741888046265
+INFO - evaluator.py - 2025-03-25 03:15:22,871 - Epoch: 132 Train acc: 99.97090909090909 Val acc: 3.84 Test acc4.0; Train loss: 0.005488446144547991 Val loss: 0.9632863878250122
+INFO - evaluator.py - 2025-03-25 03:15:56,939 - Epoch: 133 Train acc: 99.98545454545454 Val acc: 3.62 Test acc3.83; Train loss: 0.005304904764496975 Val loss: 0.9902033363342285
+INFO - evaluator.py - 2025-03-25 03:16:30,987 - Epoch: 134 Train acc: 99.98727272727272 Val acc: 3.7199999999999998 Test acc3.84; Train loss: 0.005487627888530154 Val loss: 0.9514351713180542
+INFO - evaluator.py - 2025-03-25 03:17:05,058 - Epoch: 135 Train acc: 99.99090909090908 Val acc: 3.2800000000000002 Test acc3.58; Train loss: 0.005147565892160954 Val loss: 0.9826894260406495
+INFO - evaluator.py - 2025-03-25 03:17:39,116 - Epoch: 136 Train acc: 99.99272727272728 Val acc: 3.1399999999999997 Test acc3.47; Train loss: 0.0053418313129466365 Val loss: 0.9818358003616333
+INFO - evaluator.py - 2025-03-25 03:18:13,181 - Epoch: 137 Train acc: 99.98545454545454 Val acc: 3.04 Test acc3.35; Train loss: 0.005619105658544736 Val loss: 0.9670276376724243
+INFO - evaluator.py - 2025-03-25 03:18:47,234 - Epoch: 138 Train acc: 99.98727272727272 Val acc: 2.68 Test acc3.0; Train loss: 0.005420230314838276 Val loss: 1.0422487037658692
+INFO - evaluator.py - 2025-03-25 03:19:21,286 - Epoch: 139 Train acc: 99.98545454545454 Val acc: 2.82 Test acc2.9899999999999998; Train loss: 0.005590426874736494 Val loss: 1.0170952308654786
+INFO - evaluator.py - 2025-03-25 03:19:55,319 - Epoch: 140 Train acc: 99.99090909090908 Val acc: 2.54 Test acc2.77; Train loss: 0.00562800931118598 Val loss: 1.0334181077957154
+INFO - evaluator.py - 2025-03-25 03:20:29,378 - Epoch: 141 Train acc: 99.99454545454546 Val acc: 2.5 Test acc2.8000000000000003; Train loss: 0.005671215924273499 Val loss: 1.0347472904205324
+INFO - evaluator.py - 2025-03-25 03:21:03,635 - Epoch: 142 Train acc: 99.99090909090908 Val acc: 2.2399999999999998 Test acc2.56; Train loss: 0.005724370300439609 Val loss: 1.0585867332458496
+INFO - evaluator.py - 2025-03-25 03:21:37,680 - Epoch: 143 Train acc: 99.99818181818182 Val acc: 2.18 Test acc2.53; Train loss: 0.005488083329525861 Val loss: 1.048674081802368
+INFO - evaluator.py - 2025-03-25 03:22:11,748 - Epoch: 144 Train acc: 99.9890909090909 Val acc: 2.1 Test acc2.39; Train loss: 0.005805166147014296 Val loss: 1.1162530838012694
+INFO - evaluator.py - 2025-03-25 03:22:45,801 - Epoch: 145 Train acc: 99.99818181818182 Val acc: 2.1 Test acc2.21; Train loss: 0.0055864109893329445 Val loss: 1.0739631706237793
+INFO - evaluator.py - 2025-03-25 03:23:19,873 - Epoch: 146 Train acc: 99.98727272727272 Val acc: 2.02 Test acc2.1999999999999997; Train loss: 0.00612462118559263 Val loss: 1.059408023071289
+INFO - evaluator.py - 2025-03-25 03:23:53,938 - Epoch: 147 Train acc: 99.98545454545454 Val acc: 1.96 Test acc2.11; Train loss: 0.005969568266160786 Val loss: 1.1315362266540527
+INFO - evaluator.py - 2025-03-25 03:24:28,002 - Epoch: 148 Train acc: 99.99090909090908 Val acc: 1.9 Test acc2.06; Train loss: 0.006109676833332262 Val loss: 1.0914141494750977
+INFO - evaluator.py - 2025-03-25 03:25:02,055 - Epoch: 149 Train acc: 99.99272727272728 Val acc: 1.9 Test acc2.07; Train loss: 0.00606231811138886 Val loss: 1.0243576761245727
+INFO - evaluator.py - 2025-03-25 03:25:36,098 - Epoch: 150 Train acc: 99.98727272727272 Val acc: 1.92 Test acc2.01; Train loss: 0.006340390415235676 Val loss: 1.0610571636199952
+INFO - evaluator.py - 2025-03-25 03:26:10,170 - Epoch: 151 Train acc: 99.99636363636364 Val acc: 1.96 Test acc2.07; Train loss: 0.006083548034778373 Val loss: 1.0373036613464355
+INFO - evaluator.py - 2025-03-25 03:26:44,235 - Epoch: 152 Train acc: 99.99454545454546 Val acc: 1.92 Test acc1.94; Train loss: 0.006201954196698286 Val loss: 1.001644412612915
+INFO - evaluator.py - 2025-03-25 03:27:18,304 - Epoch: 153 Train acc: 99.9890909090909 Val acc: 1.9 Test acc1.97; Train loss: 0.006566929714034565 Val loss: 0.9815988510131837
+INFO - evaluator.py - 2025-03-25 03:27:52,356 - Epoch: 154 Train acc: 99.98545454545454 Val acc: 1.92 Test acc1.87; Train loss: 0.0069869608274661 Val loss: 1.0049154527664184
+INFO - evaluator.py - 2025-03-25 03:28:26,429 - Epoch: 155 Train acc: 99.99272727272728 Val acc: 1.8599999999999999 Test acc1.8599999999999999; Train loss: 0.006701943095240065 Val loss: 1.0018212564468383
+INFO - evaluator.py - 2025-03-25 03:29:00,492 - Epoch: 156 Train acc: 99.98545454545454 Val acc: 1.7999999999999998 Test acc1.7999999999999998; Train loss: 0.0066057704457505185 Val loss: 1.013034323501587
+INFO - evaluator.py - 2025-03-25 03:29:34,559 - Epoch: 157 Train acc: 99.99090909090908 Val acc: 1.6400000000000001 Test acc1.66; Train loss: 0.006798779280263592 Val loss: 0.9745686807632445
+INFO - evaluator.py - 2025-03-25 03:30:08,613 - Epoch: 158 Train acc: 99.99272727272728 Val acc: 1.7000000000000002 Test acc1.73; Train loss: 0.006820417934817008 Val loss: 0.9609286703109741
+INFO - evaluator.py - 2025-03-25 03:30:42,672 - Epoch: 159 Train acc: 99.99272727272728 Val acc: 1.7999999999999998 Test acc1.81; Train loss: 0.006955374107933179 Val loss: 0.8972402927398682
+INFO - evaluator.py - 2025-03-25 03:31:16,718 - Epoch: 160 Train acc: 99.98727272727272 Val acc: 1.6400000000000001 Test acc1.76; Train loss: 0.006840117876121605 Val loss: 0.9138530628204345
+INFO - evaluator.py - 2025-03-25 03:31:50,773 - Epoch: 161 Train acc: 99.99090909090908 Val acc: 1.7399999999999998 Test acc1.7999999999999998; Train loss: 0.006943609073114666 Val loss: 0.908801315689087
+INFO - evaluator.py - 2025-03-25 03:32:24,839 - Epoch: 162 Train acc: 99.9890909090909 Val acc: 1.66 Test acc1.72; Train loss: 0.0069789962381463155 Val loss: 0.8995724756240845
+INFO - evaluator.py - 2025-03-25 03:32:58,881 - Epoch: 163 Train acc: 99.99636363636364 Val acc: 1.7000000000000002 Test acc1.69; Train loss: 0.0070722225651568315 Val loss: 0.9331922464370728
+INFO - evaluator.py - 2025-03-25 03:33:32,957 - Epoch: 164 Train acc: 99.99454545454546 Val acc: 1.66 Test acc1.7000000000000002; Train loss: 0.007013889988274737 Val loss: 0.9205438928604126
+INFO - evaluator.py - 2025-03-25 03:34:07,013 - Epoch: 165 Train acc: 99.98545454545454 Val acc: 1.7399999999999998 Test acc1.77; Train loss: 0.007462038543439386 Val loss: 0.8914833452224731
+INFO - evaluator.py - 2025-03-25 03:34:41,084 - Epoch: 166 Train acc: 99.98727272727272 Val acc: 1.68 Test acc1.6400000000000001; Train loss: 0.007569219907288524 Val loss: 0.9460345670700073
+INFO - evaluator.py - 2025-03-25 03:35:15,146 - Epoch: 167 Train acc: 99.98727272727272 Val acc: 1.68 Test acc1.59; Train loss: 0.007540541506990452 Val loss: 0.9552389059066773
+INFO - evaluator.py - 2025-03-25 03:35:49,214 - Epoch: 168 Train acc: 99.99454545454546 Val acc: 1.6400000000000001 Test acc1.66; Train loss: 0.007008531147868118 Val loss: 0.979420032119751
+INFO - evaluator.py - 2025-03-25 03:36:23,274 - Epoch: 169 Train acc: 99.9890909090909 Val acc: 1.6199999999999999 Test acc1.6099999999999999; Train loss: 0.007630082755188711 Val loss: 0.9749910896301269
+INFO - evaluator.py - 2025-03-25 03:36:57,346 - Epoch: 170 Train acc: 99.99272727272728 Val acc: 1.5599999999999998 Test acc1.5; Train loss: 0.00732528623431413 Val loss: 0.9892052507400513
+INFO - evaluator.py - 2025-03-25 03:37:31,411 - Epoch: 171 Train acc: 99.9890909090909 Val acc: 1.72 Test acc1.7000000000000002; Train loss: 0.007619767558964139 Val loss: 0.9502437675476074
+INFO - evaluator.py - 2025-03-25 03:38:05,465 - Epoch: 172 Train acc: 99.97636363636364 Val acc: 1.7000000000000002 Test acc1.69; Train loss: 0.008303663209402425 Val loss: 0.9229863973617554
+INFO - evaluator.py - 2025-03-25 03:38:39,537 - Epoch: 173 Train acc: 99.98727272727272 Val acc: 1.52 Test acc1.58; Train loss: 0.008352075156417083 Val loss: 0.9339524093627929
+INFO - evaluator.py - 2025-03-25 03:39:13,594 - Epoch: 174 Train acc: 99.98545454545454 Val acc: 1.58 Test acc1.53; Train loss: 0.007955606841668485 Val loss: 0.9052791229248046
+INFO - evaluator.py - 2025-03-25 03:39:47,668 - Epoch: 175 Train acc: 99.98181818181818 Val acc: 1.5 Test acc1.5; Train loss: 0.008382619313421574 Val loss: 0.957089511680603
+INFO - evaluator.py - 2025-03-25 03:40:21,724 - Epoch: 176 Train acc: 99.9890909090909 Val acc: 1.5599999999999998 Test acc1.46; Train loss: 0.007522487496389923 Val loss: 0.9926164129257203
+INFO - evaluator.py - 2025-03-25 03:40:55,783 - Epoch: 177 Train acc: 99.96545454545455 Val acc: 1.4200000000000002 Test acc1.3299999999999998; Train loss: 0.008823281003856523 Val loss: 0.9949657911300659
+INFO - evaluator.py - 2025-03-25 03:41:29,837 - Epoch: 178 Train acc: 99.97454545454545 Val acc: 1.4000000000000001 Test acc1.29; Train loss: 0.008559952365505424 Val loss: 0.993888854598999
+INFO - evaluator.py - 2025-03-25 03:42:03,913 - Epoch: 179 Train acc: 99.98545454545454 Val acc: 1.58 Test acc1.41; Train loss: 0.008370378242737867 Val loss: 0.9788234830856324
+INFO - evaluator.py - 2025-03-25 03:42:37,969 - Epoch: 180 Train acc: 99.9890909090909 Val acc: 1.46 Test acc1.44; Train loss: 0.007260922521031038 Val loss: 0.9081440963745118
+INFO - evaluator.py - 2025-03-25 03:43:12,034 - Epoch: 181 Train acc: 99.99090909090908 Val acc: 1.18 Test acc1.13; Train loss: 0.007120701149597087 Val loss: 0.840132772064209
+INFO - evaluator.py - 2025-03-25 03:43:46,086 - Epoch: 182 Train acc: 100.0 Val acc: 1.66 Test acc1.6199999999999999; Train loss: 0.006766374738895419 Val loss: 0.753256210899353
+INFO - evaluator.py - 2025-03-25 03:44:20,144 - Epoch: 183 Train acc: 99.99272727272728 Val acc: 1.4200000000000002 Test acc1.37; Train loss: 0.00671680186659267 Val loss: 0.7409212663650513
+INFO - evaluator.py - 2025-03-25 03:44:54,213 - Epoch: 184 Train acc: 99.99818181818182 Val acc: 1.6400000000000001 Test acc1.59; Train loss: 0.006555293082581325 Val loss: 0.6999889423370361
+INFO - evaluator.py - 2025-03-25 03:45:28,268 - Epoch: 185 Train acc: 99.99636363636364 Val acc: 1.66 Test acc1.67; Train loss: 0.006433851428600875 Val loss: 0.6712227098464966
+INFO - evaluator.py - 2025-03-25 03:46:02,329 - Epoch: 186 Train acc: 99.99454545454546 Val acc: 2.18 Test acc2.21; Train loss: 0.006444433451892638 Val loss: 0.6538381811141968
+INFO - evaluator.py - 2025-03-25 03:46:36,375 - Epoch: 187 Train acc: 99.99636363636364 Val acc: 2.12 Test acc2.19; Train loss: 0.006362236587728627 Val loss: 0.6371218425750732
+INFO - evaluator.py - 2025-03-25 03:47:10,398 - Epoch: 188 Train acc: 99.99818181818182 Val acc: 2.12 Test acc2.31; Train loss: 0.006435194677503949 Val loss: 0.6290058557510376
+INFO - evaluator.py - 2025-03-25 03:47:44,455 - Epoch: 189 Train acc: 100.0 Val acc: 2.26 Test acc2.5700000000000003; Train loss: 0.006337307076147673 Val loss: 0.6148265058517456
+INFO - evaluator.py - 2025-03-25 03:48:18,512 - Epoch: 190 Train acc: 99.99818181818182 Val acc: 2.16 Test acc2.5100000000000002; Train loss: 0.006359605419398708 Val loss: 0.6103171983718872
+INFO - evaluator.py - 2025-03-25 03:48:52,556 - Epoch: 191 Train acc: 99.99818181818182 Val acc: 2.1999999999999997 Test acc2.63; Train loss: 0.006322820793981241 Val loss: 0.6060234031677245
+INFO - evaluator.py - 2025-03-25 03:49:26,618 - Epoch: 192 Train acc: 99.99454545454546 Val acc: 2.16 Test acc2.5700000000000003; Train loss: 0.00620237731829455 Val loss: 0.6055738855361938
+INFO - evaluator.py - 2025-03-25 03:50:00,662 - Epoch: 193 Train acc: 99.99636363636364 Val acc: 2.4 Test acc2.8000000000000003; Train loss: 0.006390005481124602 Val loss: 0.6027493829727173
+INFO - evaluator.py - 2025-03-25 03:50:34,676 - Epoch: 194 Train acc: 99.99818181818182 Val acc: 2.62 Test acc3.02; Train loss: 0.006321131990147246 Val loss: 0.5986256423950196
+INFO - evaluator.py - 2025-03-25 03:51:08,691 - Epoch: 195 Train acc: 99.99818181818182 Val acc: 2.82 Test acc2.96; Train loss: 0.006372297631390393 Val loss: 0.5995141273498534
+INFO - evaluator.py - 2025-03-25 03:51:42,759 - Epoch: 196 Train acc: 100.0 Val acc: 2.76 Test acc3.04; Train loss: 0.0061146166374060245 Val loss: 0.6037844667434692
+INFO - evaluator.py - 2025-03-25 03:52:16,816 - Epoch: 197 Train acc: 99.99636363636364 Val acc: 3.08 Test acc3.15; Train loss: 0.006465195585152303 Val loss: 0.5988172422409058
+INFO - evaluator.py - 2025-03-25 03:52:51,070 - Epoch: 198 Train acc: 100.0 Val acc: 3.1199999999999997 Test acc3.1199999999999997; Train loss: 0.006154659912464293 Val loss: 0.6007577539443969
+INFO - evaluator.py - 2025-03-25 03:53:25,129 - Epoch: 199 Train acc: 99.99818181818182 Val acc: 3.2399999999999998 Test acc3.3000000000000003; Train loss: 0.006393027939706702 Val loss: 0.6000134044647217
+INFO - evaluator.py - 2025-03-25 03:53:25,134 - The best acc of synthetic images on sensitive val and the corresponding acc on test dataset from wrn is 6.52 and 6.35
+INFO - evaluator.py - 2025-03-25 03:53:25,134 - The best acc of synthetic images on noisy sensitive val and the corresponding acc on test dataset from wrn is 6.52 and 6.35
+INFO - evaluator.py - 2025-03-25 03:53:25,134 - The best acc test dataset from wrn is 6.550000000000001
+INFO - evaluator.py - 2025-03-25 03:54:34,827 - Epoch: 0 Train acc: 1.6945454545454546 Val acc: 1.92 Test acc1.9300000000000002; Train loss: 4.9194820703679865 Val loss: 0.7105044994354248
+INFO - evaluator.py - 2025-03-25 03:55:27,829 - Epoch: 1 Train acc: 3.329090909090909 Val acc: 1.34 Test acc1.31; Train loss: 4.4146417926094745 Val loss: 2.290356127166748
+INFO - evaluator.py - 2025-03-25 03:56:20,921 - Epoch: 2 Train acc: 4.498181818181818 Val acc: 0.88 Test acc0.86; Train loss: 4.30910107420141 Val loss: 4.756797427368164
+INFO - evaluator.py - 2025-03-25 03:57:14,039 - Epoch: 3 Train acc: 5.6000000000000005 Val acc: 0.98 Test acc1.01; Train loss: 4.1886261650952425 Val loss: 25.09403741455078
+INFO - evaluator.py - 2025-03-25 03:58:07,166 - Epoch: 4 Train acc: 7.110909090909091 Val acc: 1.0 Test acc1.0; Train loss: 4.061765846885335 Val loss: 15.369931658935547
+INFO - evaluator.py - 2025-03-25 03:59:00,294 - Epoch: 5 Train acc: 8.676363636363636 Val acc: 0.98 Test acc1.0; Train loss: 3.9510882830273024 Val loss: 63.93960516357422
+INFO - evaluator.py - 2025-03-25 03:59:53,416 - Epoch: 6 Train acc: 11.009090909090908 Val acc: 0.98 Test acc1.0; Train loss: 3.7902638036727905 Val loss: 133.7047723388672
+INFO - evaluator.py - 2025-03-25 04:00:46,529 - Epoch: 7 Train acc: 13.650909090909092 Val acc: 0.98 Test acc1.0; Train loss: 3.6165902669126337 Val loss: 11.453135256958008
+INFO - evaluator.py - 2025-03-25 04:01:39,648 - Epoch: 8 Train acc: 16.72 Val acc: 0.98 Test acc1.0; Train loss: 3.4182244110280817 Val loss: 31.728681463623047
+INFO - evaluator.py - 2025-03-25 04:02:32,760 - Epoch: 9 Train acc: 22.276363636363637 Val acc: 0.98 Test acc1.01; Train loss: 3.1204675248839635 Val loss: 6.718916162109375
+INFO - evaluator.py - 2025-03-25 04:03:25,863 - Epoch: 10 Train acc: 31.207272727272727 Val acc: 3.08 Test acc3.15; Train loss: 2.6813298683946782 Val loss: 2.1128165496826172
+INFO - evaluator.py - 2025-03-25 04:04:18,916 - Epoch: 11 Train acc: 42.78727272727273 Val acc: 2.78 Test acc2.8000000000000003; Train loss: 2.169964376839724 Val loss: 1.794307190322876
+INFO - evaluator.py - 2025-03-25 04:05:11,942 - Epoch: 12 Train acc: 55.89818181818181 Val acc: 4.36 Test acc4.45; Train loss: 1.6277016434669496 Val loss: 1.254907373428345
+INFO - evaluator.py - 2025-03-25 04:06:05,015 - Epoch: 13 Train acc: 66.20363636363636 Val acc: 5.16 Test acc4.96; Train loss: 1.2354692810817198 Val loss: 1.3257758365631105
+INFO - evaluator.py - 2025-03-25 04:06:58,124 - Epoch: 14 Train acc: 71.98545454545454 Val acc: 6.4399999999999995 Test acc6.140000000000001; Train loss: 1.004702520853823 Val loss: 1.0822121658325194
+INFO - evaluator.py - 2025-03-25 04:07:51,213 - Epoch: 15 Train acc: 75.99636363636364 Val acc: 4.32 Test acc3.92; Train loss: 0.8636901207251982 Val loss: 1.5250767826080323
+INFO - evaluator.py - 2025-03-25 04:08:44,326 - Epoch: 16 Train acc: 79.03454545454545 Val acc: 4.52 Test acc4.29; Train loss: 0.752621202752807 Val loss: 1.6742768383026123
+INFO - evaluator.py - 2025-03-25 04:09:37,415 - Epoch: 17 Train acc: 81.73272727272727 Val acc: 4.1000000000000005 Test acc4.52; Train loss: 0.6590901028795676 Val loss: 1.4598509319305422
+INFO - evaluator.py - 2025-03-25 04:10:30,514 - Epoch: 18 Train acc: 82.59454545454545 Val acc: 6.34 Test acc5.57; Train loss: 0.6172778768777847 Val loss: 1.1478383995056152
+INFO - evaluator.py - 2025-03-25 04:11:23,597 - Epoch: 19 Train acc: 83.54363636363637 Val acc: 4.74 Test acc4.83; Train loss: 0.583505178040266 Val loss: 1.559985637664795
+INFO - evaluator.py - 2025-03-25 04:12:16,684 - Epoch: 20 Train acc: 85.22545454545455 Val acc: 4.9 Test acc4.71; Train loss: 0.5295633050403812 Val loss: 1.7001476840972902
+INFO - evaluator.py - 2025-03-25 04:13:09,784 - Epoch: 21 Train acc: 85.74909090909091 Val acc: 4.46 Test acc4.49; Train loss: 0.5098041265693578 Val loss: 1.807076596069336
+INFO - evaluator.py - 2025-03-25 04:14:02,847 - Epoch: 22 Train acc: 86.57090909090908 Val acc: 4.18 Test acc4.33; Train loss: 0.47925834865353323 Val loss: 1.4672114181518554
+INFO - evaluator.py - 2025-03-25 04:14:55,927 - Epoch: 23 Train acc: 86.99272727272728 Val acc: 3.4799999999999995 Test acc3.56; Train loss: 0.46368407087542796 Val loss: 1.7143051643371583
+INFO - evaluator.py - 2025-03-25 04:15:49,025 - Epoch: 24 Train acc: 88.13272727272728 Val acc: 5.16 Test acc4.71; Train loss: 0.4301430566782301 Val loss: 1.699055955505371
+INFO - evaluator.py - 2025-03-25 04:16:42,120 - Epoch: 25 Train acc: 88.15636363636364 Val acc: 4.12 Test acc4.01; Train loss: 0.4183352815405889 Val loss: 2.080315880584717
+INFO - evaluator.py - 2025-03-25 04:17:35,239 - Epoch: 26 Train acc: 87.79636363636364 Val acc: 5.26 Test acc4.93; Train loss: 0.43249068227843807 Val loss: 1.5293400203704834
+INFO - evaluator.py - 2025-03-25 04:18:28,285 - Epoch: 27 Train acc: 88.63818181818182 Val acc: 4.32 Test acc4.75; Train loss: 0.400376629323851 Val loss: 1.524011706161499
+INFO - evaluator.py - 2025-03-25 04:19:21,301 - Epoch: 28 Train acc: 89.22181818181818 Val acc: 4.06 Test acc3.9899999999999998; Train loss: 0.38917969496629456 Val loss: 1.9228130687713623
+INFO - evaluator.py - 2025-03-25 04:20:14,383 - Epoch: 29 Train acc: 89.39454545454547 Val acc: 4.02 Test acc4.22; Train loss: 0.3790624014892361 Val loss: 1.801457367324829
+INFO - evaluator.py - 2025-03-25 04:21:07,408 - Epoch: 30 Train acc: 88.72909090909091 Val acc: 3.2199999999999998 Test acc3.17; Train loss: 0.3998855490299788 Val loss: 1.7199510692596436
+INFO - evaluator.py - 2025-03-25 04:22:00,409 - Epoch: 31 Train acc: 89.96727272727273 Val acc: 4.18 Test acc3.8; Train loss: 0.3619653078919107 Val loss: 1.467186015701294
+INFO - evaluator.py - 2025-03-25 04:22:53,468 - Epoch: 32 Train acc: 89.48 Val acc: 3.9600000000000004 Test acc4.19; Train loss: 0.37563959564891725 Val loss: 1.6230457191467287
+INFO - evaluator.py - 2025-03-25 04:23:46,545 - Epoch: 33 Train acc: 89.98 Val acc: 3.32 Test acc3.4799999999999995; Train loss: 0.36033845115520735 Val loss: 1.6178088249206541
+INFO - evaluator.py - 2025-03-25 04:24:39,620 - Epoch: 34 Train acc: 90.61454545454546 Val acc: 4.02 Test acc4.12; Train loss: 0.33943252029337667 Val loss: 1.7052048625946046
+INFO - evaluator.py - 2025-03-25 04:25:32,727 - Epoch: 35 Train acc: 89.32 Val acc: 3.9800000000000004 Test acc4.24; Train loss: 0.3830203516553749 Val loss: 1.391302575302124
+INFO - evaluator.py - 2025-03-25 04:26:25,822 - Epoch: 36 Train acc: 90.59818181818183 Val acc: 3.18 Test acc3.34; Train loss: 0.33475906513550063 Val loss: 1.7899065101623535
+INFO - evaluator.py - 2025-03-25 04:27:18,905 - Epoch: 37 Train acc: 90.0690909090909 Val acc: 3.9 Test acc3.7900000000000005; Train loss: 0.35365850245193997 Val loss: 1.6135784397125243
+INFO - evaluator.py - 2025-03-25 04:28:11,995 - Epoch: 38 Train acc: 90.8509090909091 Val acc: 3.94 Test acc4.26; Train loss: 0.3305327234111049 Val loss: 1.4428723617553711
+INFO - evaluator.py - 2025-03-25 04:29:05,053 - Epoch: 39 Train acc: 89.75090909090909 Val acc: 2.4 Test acc2.54; Train loss: 0.3655500980160453 Val loss: 1.607103674697876
+INFO - evaluator.py - 2025-03-25 04:29:58,155 - Epoch: 40 Train acc: 91.72363636363636 Val acc: 3.2 Test acc3.91; Train loss: 0.3043291451064023 Val loss: 2.0764915260314942
+INFO - evaluator.py - 2025-03-25 04:30:51,272 - Epoch: 41 Train acc: 90.3 Val acc: 3.2199999999999998 Test acc3.42; Train loss: 0.34530845783732156 Val loss: 1.6692177852630616
+INFO - evaluator.py - 2025-03-25 04:31:44,357 - Epoch: 42 Train acc: 89.32181818181817 Val acc: 3.8600000000000003 Test acc4.26; Train loss: 0.37390114565004 Val loss: 0.9468107957839966
+INFO - evaluator.py - 2025-03-25 04:32:37,464 - Epoch: 43 Train acc: 91.70545454545454 Val acc: 3.66 Test acc3.64; Train loss: 0.30206328040090474 Val loss: 1.7671335136413575
+INFO - evaluator.py - 2025-03-25 04:33:30,544 - Epoch: 44 Train acc: 89.83272727272727 Val acc: 3.2199999999999998 Test acc3.06; Train loss: 0.3575858430488543 Val loss: 1.3762333705902101
+INFO - evaluator.py - 2025-03-25 04:34:23,554 - Epoch: 45 Train acc: 91.67636363636363 Val acc: 4.34 Test acc3.9600000000000004; Train loss: 0.3040757348998026 Val loss: 1.4879527713775633
+INFO - evaluator.py - 2025-03-25 04:35:16,563 - Epoch: 46 Train acc: 90.0490909090909 Val acc: 4.4799999999999995 Test acc3.95; Train loss: 0.3488975966318087 Val loss: 1.5671982273101808
+INFO - evaluator.py - 2025-03-25 04:36:09,585 - Epoch: 47 Train acc: 91.04363636363637 Val acc: 3.56 Test acc4.03; Train loss: 0.32161214050379666 Val loss: 1.7035513240814208
+INFO - evaluator.py - 2025-03-25 04:37:02,601 - Epoch: 48 Train acc: 91.28363636363636 Val acc: 3.84 Test acc3.58; Train loss: 0.31349116638763386 Val loss: 1.7295680236816406
+INFO - evaluator.py - 2025-03-25 04:37:55,645 - Epoch: 49 Train acc: 90.85454545454546 Val acc: 3.44 Test acc3.5000000000000004; Train loss: 0.3306792487466877 Val loss: 1.9297519271850585
+INFO - evaluator.py - 2025-03-25 04:38:48,749 - Epoch: 50 Train acc: 90.81272727272727 Val acc: 3.64 Test acc3.62; Train loss: 0.3287504095779224 Val loss: 1.6858447345733643
+INFO - evaluator.py - 2025-03-25 04:39:41,835 - Epoch: 51 Train acc: 91.61818181818182 Val acc: 4.279999999999999 Test acc3.5900000000000003; Train loss: 0.30530492435802115 Val loss: 1.2408307628631592
+INFO - evaluator.py - 2025-03-25 04:40:34,903 - Epoch: 52 Train acc: 91.25999999999999 Val acc: 4.12 Test acc4.1000000000000005; Train loss: 0.31909376956197344 Val loss: 1.270968907928467
+INFO - evaluator.py - 2025-03-25 04:41:27,929 - Epoch: 53 Train acc: 91.19636363636363 Val acc: 3.1399999999999997 Test acc3.4799999999999995; Train loss: 0.31913277094391257 Val loss: 1.4662655673980713
+INFO - evaluator.py - 2025-03-25 04:42:21,230 - Epoch: 54 Train acc: 90.94909090909091 Val acc: 4.38 Test acc4.67; Train loss: 0.3251582902128046 Val loss: 1.03590989112854
+INFO - evaluator.py - 2025-03-25 04:43:14,337 - Epoch: 55 Train acc: 91.64181818181818 Val acc: 3.18 Test acc2.87; Train loss: 0.3051786063364961 Val loss: 1.6894485660552978
+INFO - evaluator.py - 2025-03-25 04:44:07,384 - Epoch: 56 Train acc: 90.68909090909091 Val acc: 2.92 Test acc2.71; Train loss: 0.33752748716581954 Val loss: 1.2546737766265867
+INFO - evaluator.py - 2025-03-25 04:45:00,396 - Epoch: 57 Train acc: 91.28363636363636 Val acc: 3.62 Test acc3.36; Train loss: 0.31802779051065444 Val loss: 1.3722215377807618
+INFO - evaluator.py - 2025-03-25 04:45:53,493 - Epoch: 58 Train acc: 91.74 Val acc: 3.2 Test acc3.29; Train loss: 0.29742902561073953 Val loss: 1.5193972080230713
+INFO - evaluator.py - 2025-03-25 04:46:46,564 - Epoch: 59 Train acc: 91.24363636363636 Val acc: 2.94 Test acc3.01; Train loss: 0.31511146770553156 Val loss: 1.7860234199523926
+INFO - evaluator.py - 2025-03-25 04:47:39,657 - Epoch: 60 Train acc: 99.27636363636364 Val acc: 4.0 Test acc4.109999999999999; Train loss: 0.04545232606926425 Val loss: 2.087693165588379
+INFO - evaluator.py - 2025-03-25 04:48:32,738 - Epoch: 61 Train acc: 99.99818181818182 Val acc: 3.3000000000000003 Test acc3.46; Train loss: 0.009572650348953902 Val loss: 4.299454591369629
+INFO - evaluator.py - 2025-03-25 04:49:25,816 - Epoch: 62 Train acc: 100.0 Val acc: 2.68 Test acc2.82; Train loss: 0.008891396766748619 Val loss: 9.927407455444335
+INFO - evaluator.py - 2025-03-25 04:50:18,823 - Epoch: 63 Train acc: 100.0 Val acc: 2.6 Test acc2.6; Train loss: 0.009294999891892076 Val loss: 22.42798154296875
+INFO - evaluator.py - 2025-03-25 04:51:11,829 - Epoch: 64 Train acc: 100.0 Val acc: 2.6 Test acc2.56; Train loss: 0.009965013981559738 Val loss: 46.47000047607422
+INFO - evaluator.py - 2025-03-25 04:52:04,838 - Epoch: 65 Train acc: 100.0 Val acc: 2.6 Test acc2.41; Train loss: 0.010746563382294369 Val loss: 89.30122492675781
+INFO - evaluator.py - 2025-03-25 04:52:57,900 - Epoch: 66 Train acc: 100.0 Val acc: 2.42 Test acc2.16; Train loss: 0.011237563914585521 Val loss: 166.45359814453124
+INFO - evaluator.py - 2025-03-25 04:53:50,981 - Epoch: 67 Train acc: 100.0 Val acc: 2.2399999999999998 Test acc1.87; Train loss: 0.011779382811926984 Val loss: 285.4360318359375
+INFO - evaluator.py - 2025-03-25 04:54:44,080 - Epoch: 68 Train acc: 100.0 Val acc: 2.0 Test acc1.5699999999999998; Train loss: 0.012071705927496606 Val loss: 480.0786169921875
+INFO - evaluator.py - 2025-03-25 04:55:37,155 - Epoch: 69 Train acc: 100.0 Val acc: 1.5 Test acc1.22; Train loss: 0.012354218025099147 Val loss: 784.148030859375
+INFO - evaluator.py - 2025-03-25 04:56:30,258 - Epoch: 70 Train acc: 100.0 Val acc: 1.3 Test acc1.13; Train loss: 0.012408018480952491 Val loss: 1201.736541796875
+INFO - evaluator.py - 2025-03-25 04:57:23,347 - Epoch: 71 Train acc: 100.0 Val acc: 1.22 Test acc1.01; Train loss: 0.012486171303452415 Val loss: 1789.3556296875
+INFO - evaluator.py - 2025-03-25 04:58:16,437 - Epoch: 72 Train acc: 100.0 Val acc: 1.18 Test acc1.0; Train loss: 0.01233173443576829 Val loss: 2626.44858984375
+INFO - evaluator.py - 2025-03-25 04:59:09,519 - Epoch: 73 Train acc: 100.0 Val acc: 1.22 Test acc1.0; Train loss: 0.01210240119817582 Val loss: 3601.72235390625
+INFO - evaluator.py - 2025-03-25 05:00:02,625 - Epoch: 74 Train acc: 100.0 Val acc: 1.2 Test acc1.01; Train loss: 0.01184135292409496 Val loss: 4846.5770062500005
+INFO - evaluator.py - 2025-03-25 05:00:55,706 - Epoch: 75 Train acc: 100.0 Val acc: 1.2 Test acc1.0; Train loss: 0.011551527467844162 Val loss: 6650.60878125
+INFO - evaluator.py - 2025-03-25 05:01:48,815 - Epoch: 76 Train acc: 100.0 Val acc: 1.2 Test acc1.0; Train loss: 0.011367441242255947 Val loss: 8749.078734375
+INFO - evaluator.py - 2025-03-25 05:02:41,919 - Epoch: 77 Train acc: 100.0 Val acc: 1.24 Test acc0.97; Train loss: 0.010859274382990869 Val loss: 11325.836024999999
+INFO - evaluator.py - 2025-03-25 05:03:35,005 - Epoch: 78 Train acc: 100.0 Val acc: 1.2 Test acc0.9900000000000001; Train loss: 0.01071558513018218 Val loss: 15321.9488625
+INFO - evaluator.py - 2025-03-25 05:04:28,098 - Epoch: 79 Train acc: 100.0 Val acc: 1.2 Test acc1.0; Train loss: 0.010318050984665752 Val loss: 19357.6186125
+INFO - evaluator.py - 2025-03-25 05:05:21,186 - Epoch: 80 Train acc: 100.0 Val acc: 1.24 Test acc0.9900000000000001; Train loss: 0.009993537322668866 Val loss: 22993.2777375
+INFO - evaluator.py - 2025-03-25 05:06:14,277 - Epoch: 81 Train acc: 100.0 Val acc: 1.24 Test acc0.97; Train loss: 0.0097356676438146 Val loss: 29024.0614125
+INFO - evaluator.py - 2025-03-25 05:07:07,363 - Epoch: 82 Train acc: 100.0 Val acc: 1.22 Test acc0.9900000000000001; Train loss: 0.009518627039021389 Val loss: 34074.969075
+INFO - evaluator.py - 2025-03-25 05:08:00,457 - Epoch: 83 Train acc: 100.0 Val acc: 1.2 Test acc1.04; Train loss: 0.009456651739064943 Val loss: 37253.030062499995
+INFO - evaluator.py - 2025-03-25 05:08:53,559 - Epoch: 84 Train acc: 100.0 Val acc: 1.26 Test acc0.9900000000000001; Train loss: 0.009155398086204447 Val loss: 42266.8512
+INFO - evaluator.py - 2025-03-25 05:09:46,645 - Epoch: 85 Train acc: 100.0 Val acc: 1.24 Test acc1.02; Train loss: 0.009163616720874878 Val loss: 46492.0036875
+INFO - evaluator.py - 2025-03-25 05:10:39,740 - Epoch: 86 Train acc: 100.0 Val acc: 1.22 Test acc1.05; Train loss: 0.009348146739737554 Val loss: 45678.5532
+INFO - evaluator.py - 2025-03-25 05:11:32,834 - Epoch: 87 Train acc: 100.0 Val acc: 1.06 Test acc1.0; Train loss: 0.009933386431261897 Val loss: 41367.214349999995
+INFO - evaluator.py - 2025-03-25 05:12:25,926 - Epoch: 88 Train acc: 100.0 Val acc: 1.18 Test acc1.06; Train loss: 0.010166178853775966 Val loss: 42453.950175
+INFO - evaluator.py - 2025-03-25 05:13:19,023 - Epoch: 89 Train acc: 100.0 Val acc: 1.08 Test acc1.03; Train loss: 0.010751250089925122 Val loss: 38151.29115
+INFO - evaluator.py - 2025-03-25 05:14:12,142 - Epoch: 90 Train acc: 99.99636363636364 Val acc: 1.16 Test acc0.9900000000000001; Train loss: 0.015954932391846723 Val loss: 18727.16146875
+INFO - evaluator.py - 2025-03-25 05:15:05,243 - Epoch: 91 Train acc: 87.54181818181819 Val acc: 1.24 Test acc1.1199999999999999; Train loss: 0.6255273549743674 Val loss: 0.69459917678833
+INFO - evaluator.py - 2025-03-25 05:15:58,358 - Epoch: 92 Train acc: 98.46181818181819 Val acc: 2.16 Test acc2.4299999999999997; Train loss: 0.10222137290523811 Val loss: 0.6888864492416382
+INFO - evaluator.py - 2025-03-25 05:16:51,467 - Epoch: 93 Train acc: 99.97272727272727 Val acc: 3.7800000000000002 Test acc3.82; Train loss: 0.014708899080567061 Val loss: 0.7988294929504395
+INFO - evaluator.py - 2025-03-25 05:17:44,557 - Epoch: 94 Train acc: 100.0 Val acc: 4.92 Test acc4.78; Train loss: 0.00499330490949479 Val loss: 1.0641279521942137
+INFO - evaluator.py - 2025-03-25 05:18:37,658 - Epoch: 95 Train acc: 100.0 Val acc: 3.84 Test acc3.7800000000000002; Train loss: 0.004954938982037658 Val loss: 2.189425966644287
+INFO - evaluator.py - 2025-03-25 05:19:30,748 - Epoch: 96 Train acc: 100.0 Val acc: 2.74 Test acc2.8000000000000003; Train loss: 0.005547877963454548 Val loss: 6.509495475769043
+INFO - evaluator.py - 2025-03-25 05:20:23,854 - Epoch: 97 Train acc: 100.0 Val acc: 2.52 Test acc2.6; Train loss: 0.006205674908885902 Val loss: 19.02210941162109
+INFO - evaluator.py - 2025-03-25 05:21:16,942 - Epoch: 98 Train acc: 100.0 Val acc: 2.4 Test acc2.22; Train loss: 0.006805800089460205 Val loss: 48.070896459960935
+INFO - evaluator.py - 2025-03-25 05:22:10,038 - Epoch: 99 Train acc: 100.0 Val acc: 2.02 Test acc1.8900000000000001; Train loss: 0.007242829796705734 Val loss: 107.55840959472656
+INFO - evaluator.py - 2025-03-25 05:23:03,146 - Epoch: 100 Train acc: 100.0 Val acc: 1.66 Test acc1.6099999999999999; Train loss: 0.007611559954878282 Val loss: 220.47748857421877
+INFO - evaluator.py - 2025-03-25 05:23:56,266 - Epoch: 101 Train acc: 100.0 Val acc: 1.58 Test acc1.48; Train loss: 0.007942937993393703 Val loss: 382.8773197265625
+INFO - evaluator.py - 2025-03-25 05:24:49,371 - Epoch: 102 Train acc: 100.0 Val acc: 1.48 Test acc1.38; Train loss: 0.00805061614906246 Val loss: 585.939350390625
+INFO - evaluator.py - 2025-03-25 05:25:42,472 - Epoch: 103 Train acc: 100.0 Val acc: 1.5599999999999998 Test acc1.46; Train loss: 0.008440251243893394 Val loss: 781.5302947265625
+INFO - evaluator.py - 2025-03-25 05:26:35,585 - Epoch: 104 Train acc: 100.0 Val acc: 1.52 Test acc1.41; Train loss: 0.00905170003108003 Val loss: 1101.109275
+INFO - evaluator.py - 2025-03-25 05:27:28,702 - Epoch: 105 Train acc: 100.0 Val acc: 1.5599999999999998 Test acc1.53; Train loss: 0.009130678643252363 Val loss: 1253.970826171875
+INFO - evaluator.py - 2025-03-25 05:28:21,789 - Epoch: 106 Train acc: 100.0 Val acc: 1.72 Test acc1.6099999999999999; Train loss: 0.010610440556840463 Val loss: 1125.139419140625
+INFO - evaluator.py - 2025-03-25 05:29:14,897 - Epoch: 107 Train acc: 81.38727272727273 Val acc: 0.9199999999999999 Test acc1.0; Train loss: 0.8436107676763764 Val loss: 0.6569581283569336
+INFO - evaluator.py - 2025-03-25 05:30:08,022 - Epoch: 108 Train acc: 95.75636363636364 Val acc: 0.9199999999999999 Test acc1.0; Train loss: 0.21598032935207542 Val loss: 0.6625437355041504
+INFO - evaluator.py - 2025-03-25 05:31:01,138 - Epoch: 109 Train acc: 99.59636363636363 Val acc: 1.1400000000000001 Test acc1.0; Train loss: 0.038833995700661435 Val loss: 0.6788453435897828
+INFO - evaluator.py - 2025-03-25 05:31:54,239 - Epoch: 110 Train acc: 99.99636363636364 Val acc: 1.0 Test acc0.98; Train loss: 0.006884602505112574 Val loss: 0.7001094417572021
+INFO - evaluator.py - 2025-03-25 05:32:47,358 - Epoch: 111 Train acc: 100.0 Val acc: 1.34 Test acc1.38; Train loss: 0.004614596445045688 Val loss: 0.7910933052062988
+INFO - evaluator.py - 2025-03-25 05:33:40,452 - Epoch: 112 Train acc: 100.0 Val acc: 3.26 Test acc3.1300000000000003; Train loss: 0.005004874817646024 Val loss: 0.8359398056030274
+INFO - evaluator.py - 2025-03-25 05:34:33,748 - Epoch: 113 Train acc: 100.0 Val acc: 4.88 Test acc5.0; Train loss: 0.00573932618200779 Val loss: 0.9505520456314087
+INFO - evaluator.py - 2025-03-25 05:35:26,847 - Epoch: 114 Train acc: 100.0 Val acc: 4.58 Test acc4.65; Train loss: 0.006440915108793839 Val loss: 1.4989393913269042
+INFO - evaluator.py - 2025-03-25 05:36:19,936 - Epoch: 115 Train acc: 100.0 Val acc: 2.98 Test acc3.25; Train loss: 0.0070173106141557745 Val loss: 4.055917957305908
+INFO - evaluator.py - 2025-03-25 05:37:13,034 - Epoch: 116 Train acc: 100.0 Val acc: 2.54 Test acc2.54; Train loss: 0.007319503051906147 Val loss: 11.685818435668944
+INFO - evaluator.py - 2025-03-25 05:38:06,113 - Epoch: 117 Train acc: 100.0 Val acc: 2.34 Test acc2.31; Train loss: 0.007849022775973108 Val loss: 33.015642187500006
+INFO - evaluator.py - 2025-03-25 05:38:59,203 - Epoch: 118 Train acc: 100.0 Val acc: 2.22 Test acc1.9300000000000002; Train loss: 0.007985382865674117 Val loss: 77.32304384765625
+INFO - evaluator.py - 2025-03-25 05:39:52,291 - Epoch: 119 Train acc: 100.0 Val acc: 1.94 Test acc1.67; Train loss: 0.008084184834750539 Val loss: 162.70962319335936
+INFO - evaluator.py - 2025-03-25 05:40:45,382 - Epoch: 120 Train acc: 100.0 Val acc: 2.2399999999999998 Test acc1.82; Train loss: 0.0067731551522897055 Val loss: 135.31302421875
+INFO - evaluator.py - 2025-03-25 05:41:38,478 - Epoch: 121 Train acc: 100.0 Val acc: 2.18 Test acc1.83; Train loss: 0.006512947911210358 Val loss: 116.4110231689453
+INFO - evaluator.py - 2025-03-25 05:42:31,550 - Epoch: 122 Train acc: 100.0 Val acc: 2.04 Test acc1.8499999999999999; Train loss: 0.006536561144414273 Val loss: 105.36094467773437
+INFO - evaluator.py - 2025-03-25 05:43:24,630 - Epoch: 123 Train acc: 100.0 Val acc: 2.32 Test acc1.9900000000000002; Train loss: 0.006338381967676634 Val loss: 88.73679660644531
+INFO - evaluator.py - 2025-03-25 05:44:17,706 - Epoch: 124 Train acc: 100.0 Val acc: 2.36 Test acc1.96; Train loss: 0.006507249895263125 Val loss: 75.39399184570313
+INFO - evaluator.py - 2025-03-25 05:45:10,791 - Epoch: 125 Train acc: 100.0 Val acc: 2.4 Test acc2.11; Train loss: 0.006559815055792304 Val loss: 64.98427697753907
+INFO - evaluator.py - 2025-03-25 05:46:03,888 - Epoch: 126 Train acc: 100.0 Val acc: 2.42 Test acc2.15; Train loss: 0.00664035638389601 Val loss: 56.67729400634766
+INFO - evaluator.py - 2025-03-25 05:46:56,965 - Epoch: 127 Train acc: 100.0 Val acc: 2.42 Test acc2.18; Train loss: 0.006680651387775486 Val loss: 51.58434462890625
+INFO - evaluator.py - 2025-03-25 05:47:50,048 - Epoch: 128 Train acc: 100.0 Val acc: 2.46 Test acc2.21; Train loss: 0.0067219933850860055 Val loss: 45.44381184082032
+INFO - evaluator.py - 2025-03-25 05:48:43,144 - Epoch: 129 Train acc: 100.0 Val acc: 2.34 Test acc2.13; Train loss: 0.006762291940301657 Val loss: 38.63633499755859
+INFO - evaluator.py - 2025-03-25 05:49:36,242 - Epoch: 130 Train acc: 100.0 Val acc: 2.3800000000000003 Test acc2.26; Train loss: 0.0069630042641169645 Val loss: 34.61636206054687
+INFO - evaluator.py - 2025-03-25 05:50:29,312 - Epoch: 131 Train acc: 100.0 Val acc: 2.42 Test acc2.2800000000000002; Train loss: 0.00698362798594277 Val loss: 31.566818298339847
+INFO - evaluator.py - 2025-03-25 05:51:22,370 - Epoch: 132 Train acc: 100.0 Val acc: 2.4 Test acc2.29; Train loss: 0.0069947033083913 Val loss: 28.201403979492188
+INFO - evaluator.py - 2025-03-25 05:52:15,441 - Epoch: 133 Train acc: 100.0 Val acc: 2.36 Test acc2.31; Train loss: 0.006965670862065797 Val loss: 25.307363012695312
+INFO - evaluator.py - 2025-03-25 05:53:08,534 - Epoch: 134 Train acc: 100.0 Val acc: 2.52 Test acc2.3; Train loss: 0.00703763347092 Val loss: 23.674828216552733
+INFO - evaluator.py - 2025-03-25 05:54:01,609 - Epoch: 135 Train acc: 100.0 Val acc: 2.42 Test acc2.29; Train loss: 0.007178223312950947 Val loss: 20.4424541015625
+INFO - evaluator.py - 2025-03-25 05:54:54,708 - Epoch: 136 Train acc: 100.0 Val acc: 2.4 Test acc2.29; Train loss: 0.00705521088772538 Val loss: 19.923397009277345
+INFO - evaluator.py - 2025-03-25 05:55:47,819 - Epoch: 137 Train acc: 100.0 Val acc: 2.4 Test acc2.2800000000000002; Train loss: 0.007200173781541261 Val loss: 16.338125802612307
+INFO - evaluator.py - 2025-03-25 05:56:40,936 - Epoch: 138 Train acc: 100.0 Val acc: 2.4 Test acc2.2399999999999998; Train loss: 0.007187223210642961 Val loss: 16.250173626708985
+INFO - evaluator.py - 2025-03-25 05:57:34,050 - Epoch: 139 Train acc: 100.0 Val acc: 2.4 Test acc2.34; Train loss: 0.007141992627168921 Val loss: 14.768873052978517
+INFO - evaluator.py - 2025-03-25 05:58:27,164 - Epoch: 140 Train acc: 100.0 Val acc: 2.32 Test acc2.34; Train loss: 0.007264688090573657 Val loss: 13.349319323730468
+INFO - evaluator.py - 2025-03-25 05:59:20,274 - Epoch: 141 Train acc: 100.0 Val acc: 2.3800000000000003 Test acc2.35; Train loss: 0.007311670786396347 Val loss: 12.054120611572266
+INFO - evaluator.py - 2025-03-25 06:00:13,407 - Epoch: 142 Train acc: 100.0 Val acc: 2.3800000000000003 Test acc2.34; Train loss: 0.00731025644142858 Val loss: 11.528134057617187
+INFO - evaluator.py - 2025-03-25 06:01:06,500 - Epoch: 143 Train acc: 100.0 Val acc: 2.44 Test acc2.39; Train loss: 0.00738628092223609 Val loss: 10.561698138427735
+INFO - evaluator.py - 2025-03-25 06:01:59,605 - Epoch: 144 Train acc: 100.0 Val acc: 2.48 Test acc2.31; Train loss: 0.007343860355646096 Val loss: 9.493772003173827
+INFO - evaluator.py - 2025-03-25 06:02:52,703 - Epoch: 145 Train acc: 100.0 Val acc: 2.4 Test acc2.3; Train loss: 0.007268326819061556 Val loss: 9.343068035888672
+INFO - evaluator.py - 2025-03-25 06:03:45,823 - Epoch: 146 Train acc: 100.0 Val acc: 2.46 Test acc2.36; Train loss: 0.0072413929201154545 Val loss: 8.618657052612305
+INFO - evaluator.py - 2025-03-25 06:04:38,933 - Epoch: 147 Train acc: 100.0 Val acc: 2.48 Test acc2.36; Train loss: 0.0073240059349516575 Val loss: 8.344651272583008
+INFO - evaluator.py - 2025-03-25 06:05:32,048 - Epoch: 148 Train acc: 100.0 Val acc: 2.52 Test acc2.3800000000000003; Train loss: 0.007412873916378753 Val loss: 7.694124746704102
+INFO - evaluator.py - 2025-03-25 06:06:25,152 - Epoch: 149 Train acc: 100.0 Val acc: 2.5 Test acc2.34; Train loss: 0.007387672556361014 Val loss: 6.894191917419434
+INFO - evaluator.py - 2025-03-25 06:07:18,275 - Epoch: 150 Train acc: 100.0 Val acc: 2.42 Test acc2.36; Train loss: 0.007362755641408942 Val loss: 6.92438464050293
+INFO - evaluator.py - 2025-03-25 06:08:11,366 - Epoch: 151 Train acc: 100.0 Val acc: 2.48 Test acc2.4; Train loss: 0.007341057608920064 Val loss: 6.620242181396484
+INFO - evaluator.py - 2025-03-25 06:09:04,463 - Epoch: 152 Train acc: 100.0 Val acc: 2.46 Test acc2.39; Train loss: 0.007397115812078118 Val loss: 5.848026814270019
+INFO - evaluator.py - 2025-03-25 06:09:57,572 - Epoch: 153 Train acc: 100.0 Val acc: 2.46 Test acc2.39; Train loss: 0.007418732697228816 Val loss: 5.670788461303711
+INFO - evaluator.py - 2025-03-25 06:10:50,669 - Epoch: 154 Train acc: 100.0 Val acc: 2.5 Test acc2.4699999999999998; Train loss: 0.007334714863838797 Val loss: 5.288551707458496
+INFO - evaluator.py - 2025-03-25 06:11:43,768 - Epoch: 155 Train acc: 100.0 Val acc: 2.58 Test acc2.44; Train loss: 0.007383706913990053 Val loss: 5.3981085113525396
+INFO - evaluator.py - 2025-03-25 06:12:36,868 - Epoch: 156 Train acc: 100.0 Val acc: 2.44 Test acc2.42; Train loss: 0.007443440602872182 Val loss: 4.887618653869629
+INFO - evaluator.py - 2025-03-25 06:13:29,961 - Epoch: 157 Train acc: 100.0 Val acc: 2.44 Test acc2.45; Train loss: 0.007503622105751525 Val loss: 4.486543904113769
+INFO - evaluator.py - 2025-03-25 06:14:23,109 - Epoch: 158 Train acc: 100.0 Val acc: 2.46 Test acc2.42; Train loss: 0.007455857641249895 Val loss: 4.420772273254395
+INFO - evaluator.py - 2025-03-25 06:15:16,207 - Epoch: 159 Train acc: 100.0 Val acc: 2.42 Test acc2.46; Train loss: 0.007313178038969636 Val loss: 4.266499562072753
+INFO - evaluator.py - 2025-03-25 06:16:09,334 - Epoch: 160 Train acc: 100.0 Val acc: 2.5 Test acc2.53; Train loss: 0.007483572426641529 Val loss: 4.1059328590393065
+INFO - evaluator.py - 2025-03-25 06:17:02,450 - Epoch: 161 Train acc: 100.0 Val acc: 2.46 Test acc2.48; Train loss: 0.007491115483878688 Val loss: 3.904592795562744
+INFO - evaluator.py - 2025-03-25 06:17:55,551 - Epoch: 162 Train acc: 100.0 Val acc: 2.44 Test acc2.46; Train loss: 0.007557922809283165 Val loss: 3.719959517669678
+INFO - evaluator.py - 2025-03-25 06:18:48,660 - Epoch: 163 Train acc: 100.0 Val acc: 2.5 Test acc2.4699999999999998; Train loss: 0.007535026939585805 Val loss: 3.256373879241943
+INFO - evaluator.py - 2025-03-25 06:19:41,757 - Epoch: 164 Train acc: 100.0 Val acc: 2.5 Test acc2.53; Train loss: 0.0076520148339596665 Val loss: 3.339484929656982
+INFO - evaluator.py - 2025-03-25 06:20:34,850 - Epoch: 165 Train acc: 100.0 Val acc: 2.52 Test acc2.58; Train loss: 0.0074271251809529286 Val loss: 3.160783472442627
+INFO - evaluator.py - 2025-03-25 06:21:27,958 - Epoch: 166 Train acc: 100.0 Val acc: 2.46 Test acc2.45; Train loss: 0.007305724135312167 Val loss: 3.0345650161743163
+INFO - evaluator.py - 2025-03-25 06:22:21,062 - Epoch: 167 Train acc: 100.0 Val acc: 2.46 Test acc2.54; Train loss: 0.0074258932662789115 Val loss: 2.974933905029297
+INFO - evaluator.py - 2025-03-25 06:23:14,183 - Epoch: 168 Train acc: 100.0 Val acc: 2.52 Test acc2.63; Train loss: 0.007488098001327705 Val loss: 2.7239997985839843
+INFO - evaluator.py - 2025-03-25 06:24:07,313 - Epoch: 169 Train acc: 100.0 Val acc: 2.46 Test acc2.52; Train loss: 0.007565224919722161 Val loss: 2.5901354209899905
+INFO - evaluator.py - 2025-03-25 06:25:00,618 - Epoch: 170 Train acc: 100.0 Val acc: 2.46 Test acc2.46; Train loss: 0.007525024463100867 Val loss: 2.531502575683594
+INFO - evaluator.py - 2025-03-25 06:25:53,718 - Epoch: 171 Train acc: 100.0 Val acc: 2.46 Test acc2.4899999999999998; Train loss: 0.007430705763111738 Val loss: 2.470954044342041
+INFO - evaluator.py - 2025-03-25 06:26:46,841 - Epoch: 172 Train acc: 100.0 Val acc: 2.44 Test acc2.3800000000000003; Train loss: 0.007583216659792445 Val loss: 2.3292696533203125
+INFO - evaluator.py - 2025-03-25 06:27:39,920 - Epoch: 173 Train acc: 100.0 Val acc: 2.42 Test acc2.4699999999999998; Train loss: 0.007438974546404048 Val loss: 2.143289396667481
+INFO - evaluator.py - 2025-03-25 06:28:33,047 - Epoch: 174 Train acc: 100.0 Val acc: 2.44 Test acc2.55; Train loss: 0.007572418767213822 Val loss: 2.2408967628479
+INFO - evaluator.py - 2025-03-25 06:29:26,146 - Epoch: 175 Train acc: 100.0 Val acc: 2.46 Test acc2.5100000000000002; Train loss: 0.00745402182340622 Val loss: 2.206175434112549
+INFO - evaluator.py - 2025-03-25 06:30:19,263 - Epoch: 176 Train acc: 100.0 Val acc: 2.4 Test acc2.42; Train loss: 0.007625556959144094 Val loss: 2.0136690547943115
+INFO - evaluator.py - 2025-03-25 06:31:12,374 - Epoch: 177 Train acc: 100.0 Val acc: 2.44 Test acc2.52; Train loss: 0.007492825118875638 Val loss: 1.868698374938965
+INFO - evaluator.py - 2025-03-25 06:32:05,474 - Epoch: 178 Train acc: 100.0 Val acc: 2.5 Test acc2.58; Train loss: 0.007725854376788166 Val loss: 1.9365443550109862
+INFO - evaluator.py - 2025-03-25 06:32:58,560 - Epoch: 179 Train acc: 100.0 Val acc: 2.46 Test acc2.4699999999999998; Train loss: 0.007586284935305065 Val loss: 1.9732119392395018
+INFO - evaluator.py - 2025-03-25 06:33:51,668 - Epoch: 180 Train acc: 100.0 Val acc: 2.42 Test acc2.52; Train loss: 0.006954127983647314 Val loss: 1.755237043762207
+INFO - evaluator.py - 2025-03-25 06:34:44,778 - Epoch: 181 Train acc: 100.0 Val acc: 2.54 Test acc2.56; Train loss: 0.00672560260836035 Val loss: 1.58254190826416
+INFO - evaluator.py - 2025-03-25 06:35:37,897 - Epoch: 182 Train acc: 100.0 Val acc: 2.54 Test acc2.5700000000000003; Train loss: 0.006674337022446773 Val loss: 1.5035659057617188
+INFO - evaluator.py - 2025-03-25 06:36:30,993 - Epoch: 183 Train acc: 100.0 Val acc: 2.5 Test acc2.54; Train loss: 0.0065532084429128605 Val loss: 1.5142741081237794
+INFO - evaluator.py - 2025-03-25 06:37:24,099 - Epoch: 184 Train acc: 100.0 Val acc: 2.64 Test acc2.6599999999999997; Train loss: 0.006467724368534982 Val loss: 1.3381533908843994
+INFO - evaluator.py - 2025-03-25 06:38:17,217 - Epoch: 185 Train acc: 100.0 Val acc: 2.7199999999999998 Test acc2.71; Train loss: 0.006345256493613124 Val loss: 1.3128960491180421
+INFO - evaluator.py - 2025-03-25 06:39:10,317 - Epoch: 186 Train acc: 100.0 Val acc: 2.74 Test acc2.8400000000000003; Train loss: 0.006432164044661278 Val loss: 1.2224999507904053
+INFO - evaluator.py - 2025-03-25 06:40:03,430 - Epoch: 187 Train acc: 100.0 Val acc: 2.8000000000000003 Test acc2.8899999999999997; Train loss: 0.006391867739300836 Val loss: 1.1886168788909912
+INFO - evaluator.py - 2025-03-25 06:40:56,541 - Epoch: 188 Train acc: 100.0 Val acc: 2.94 Test acc3.19; Train loss: 0.006323390448465943 Val loss: 1.0718773818969727
+INFO - evaluator.py - 2025-03-25 06:41:49,643 - Epoch: 189 Train acc: 100.0 Val acc: 2.92 Test acc3.2300000000000004; Train loss: 0.006350828498466449 Val loss: 1.0482212116241456
+INFO - evaluator.py - 2025-03-25 06:42:42,791 - Epoch: 190 Train acc: 100.0 Val acc: 3.08 Test acc3.3099999999999996; Train loss: 0.006335840892232955 Val loss: 1.0058248580932618
+INFO - evaluator.py - 2025-03-25 06:43:35,890 - Epoch: 191 Train acc: 100.0 Val acc: 3.16 Test acc3.45; Train loss: 0.006451710522157902 Val loss: 0.9511916490554809
+INFO - evaluator.py - 2025-03-25 06:44:28,990 - Epoch: 192 Train acc: 100.0 Val acc: 3.2399999999999998 Test acc3.53; Train loss: 0.006416687083718451 Val loss: 0.9181815851211548
+INFO - evaluator.py - 2025-03-25 06:45:22,095 - Epoch: 193 Train acc: 100.0 Val acc: 3.2800000000000002 Test acc3.4000000000000004; Train loss: 0.006392666968093676 Val loss: 0.9231537122726441
+INFO - evaluator.py - 2025-03-25 06:46:15,210 - Epoch: 194 Train acc: 100.0 Val acc: 3.56 Test acc3.58; Train loss: 0.006421739032779906 Val loss: 0.8605997932434082
+INFO - evaluator.py - 2025-03-25 06:47:08,304 - Epoch: 195 Train acc: 100.0 Val acc: 3.7800000000000002 Test acc3.83; Train loss: 0.00632401730783961 Val loss: 0.8219191549301147
+INFO - evaluator.py - 2025-03-25 06:48:01,397 - Epoch: 196 Train acc: 100.0 Val acc: 3.62 Test acc3.5999999999999996; Train loss: 0.006431780257126825 Val loss: 0.8072800615310669
+INFO - evaluator.py - 2025-03-25 06:48:54,488 - Epoch: 197 Train acc: 100.0 Val acc: 3.82 Test acc3.7199999999999998; Train loss: 0.0065457556967200205 Val loss: 0.8050144609451293
+INFO - evaluator.py - 2025-03-25 06:49:47,596 - Epoch: 198 Train acc: 100.0 Val acc: 3.9 Test acc3.7900000000000005; Train loss: 0.006489532539383932 Val loss: 0.7636966060638428
+INFO - evaluator.py - 2025-03-25 06:50:40,705 - Epoch: 199 Train acc: 100.0 Val acc: 3.94 Test acc3.73; Train loss: 0.006422754263674671 Val loss: 0.7683714740753174
+INFO - evaluator.py - 2025-03-25 06:50:40,716 - The best acc of synthetic images on sensitive val and the corresponding acc on test dataset from resnext is 6.4399999999999995 and 6.140000000000001
+INFO - evaluator.py - 2025-03-25 06:50:40,717 - The best acc of synthetic images on noisy sensitive val and the corresponding acc on test dataset from resnext is 6.4399999999999995 and 6.140000000000001
+INFO - evaluator.py - 2025-03-25 06:50:40,717 - The best acc test dataset from resnext is 6.140000000000001
+INFO - evaluator.py - 2025-03-25 06:50:40,717 - The best acc of accuracy (adding noise to the results on the sensitive set of validation set) of synthetic images from resnet, wrn, and resnext are [3.71, 6.35, 6.140000000000001].
+INFO - evaluator.py - 2025-03-25 06:50:40,717 - The average and std of accuracy of synthetic images are 5.40 and 1.20
+INFO - evaluator.py - 2025-03-25 07:18:47,539 - The FID of synthetic images is 130.184706241482
+INFO - evaluator.py - 2025-03-25 07:18:47,540 - The Inception Score of synthetic images is 2.7268121242523193
+INFO - evaluator.py - 2025-03-25 07:18:47,540 - The Precision and Recall of synthetic images is 0.6752833127975464 and 0.009599999524652958
+INFO - evaluator.py - 2025-03-25 07:18:47,540 - The FLD of synthetic images is 18.955469131469727
+INFO - evaluator.py - 2025-03-25 07:18:47,540 - The ImageReward of synthetic images is -2.2278927373220525
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/checkpoints/checkpoint_100000.pth b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/checkpoints/checkpoint_100000.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b77cefcfd1ea5a2d68a45a1c50e4718071c2dadf
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/checkpoints/checkpoint_100000.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:525c664485599aa5e1248ecc89c20968eae088433c351e081c5832060c0ab4bd
+size 61741705
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/checkpoints/final_checkpoint.pth b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/checkpoints/final_checkpoint.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a8e0bdbee1524391ab10ed0c226fb365e34e7020
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/checkpoints/final_checkpoint.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c4424b719b9ff76b1ba6b1505a0bb892fd8e590000b640c191a139588d21bc5
+size 61740646
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/checkpoints/snapshot_checkpoint.pth b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/checkpoints/snapshot_checkpoint.pth
new file mode 100644
index 0000000000000000000000000000000000000000..fb1a953f74cfa98144339664153609c4b2a88f9f
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/checkpoints/snapshot_checkpoint.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:540c66404c75a973e043e3d189629b399b082bdf0376959cf82498beabe40318
+size 61743823
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_10000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_10000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..3c74abeb67f95b22c1e1b713a4a0b8585cd124a5
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_10000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8cecd89bc2934b70b8e5b73cd145db46b204fc5129e736e571f8d048306d982
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_10000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_10000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..c21bf6e379bf5a224374b2bdbcdc7d3614055187
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_10000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:771922a5193e8ce3af2c2feb54d41d8087a3d406acd4d9f58099a697d838311e
+size 374451
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_100000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_100000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..cf7326a6fd118f27ecdb9ccc8bf7c4107be0e063
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_100000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b3e196857e7c466dde91ac1cdd64d2b77b76ca235d0db68f4ca5f192eeeec53
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_100000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_100000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..4890044fe4975f9cefc4508130625b03b1c4e309
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_100000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02405a933beb4ac7e08a0b7c6cb7e245d49662427d8794ca54217eb5eb2b9083
+size 335627
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_102000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_102000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..742c07185635e3c0e3f3187f59eb279cc06edbeb
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_102000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bed52a6612ee288e706b7f02f824b295e5d37b72fbebf1bb66b41350ba3a0a2d
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_102000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_102000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..193a2f64624f4e57db56b47b8f5ae11015cf17a7
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_102000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f720838718846555ed56036af8c760204f3342850fd4e051cc1baa4c7fda088
+size 336477
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_104000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_104000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..17a8e90a1e6b0d563702f28c22be31f22a60770d
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_104000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e100fab2d5b5972b94a332d0dcc3912a2d07ae52384b6bb78a9305c73c30aae1
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_104000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_104000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..8662624c19a3a36f911ad2f7fb1c4e86fdc8ab3d
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_104000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01751b9c5e8418d644f937cda64075ca60ce1210112b7f2d5ae366f343c233dd
+size 337968
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_12000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_12000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..a2505e086665ac74f49633ef6d0360d74eb8b8a4
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_12000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78bac8a4ebbfed61417ed09c1b92fcbd6528ddb9d51b1b4686fd99dc73352e32
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_12000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_12000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..434aa5396fea814a72536c1bb0783306bbc16841
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_12000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b2f27ea82e56f2a8ea97c27e81f359e4c23996810b5c85bb8daa854a66af8df
+size 368545
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_14000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_14000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..22ca2d749a21969b2772c692866125761d961bae
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_14000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07e2347d1cba8d31a5dbcf991bc6f11649edeb188daafa15f5557dde220214f5
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_14000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_14000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..ac6135bc716c6a339527ba53497f95f792335bc3
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_14000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e16f2db3f3919099600e5b46283e4243444081eca095560d8fbe1dda835c4bbb
+size 367039
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_16000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_16000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..3d6823d27509a8c60e49be428ce21520f747ae24
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_16000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14282ba2b60233b718b958500da95e37c6b5d9e17636563742c5fdc3b168ad4c
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_16000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_16000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..5c0c9566df7dfe5b823c100c6f63f3f83f5ef3e2
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_16000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b1ada00cb550a922d83a24bab5fb4986d784ef428e4143bc4f58ca3e065a434
+size 365231
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_18000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_18000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..9e6c73729780045f9ee7ef55342a80fb4f868db3
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_18000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9028096252971f4db481d991825b39df4282d1b869abf24aedd0c95566308f1
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_18000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_18000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..c5f50351e5763da24c9e7c092384ead61e95a629
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_18000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cff34f9262daef3dad075c7dc2abed026dd4e336b46a7386ea5bf425b54d4d7
+size 361208
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_2000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_2000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..bfaeccc4e709462fa7cdc5692c9a5979546f4fd1
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_2000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c89a57e8edd97a999ecbbfce6bcb5101973316160aabe3e7a2bfb8783a548eb
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_2000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_2000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..356333e7990065dc5b6ba18d7b0c9a0ec477caba
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_2000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce5c7fedc81c38e530be8c9bebb3db8274507ca02a147a34f405ecc9c62a4227
+size 476958
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_20000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_20000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..cea580b14ad4d51467d0aa93689a0ec943c66edf
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_20000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a31d588b244f07d7adbae0796e81478b6cda990e679d078dd7dd675ab60843eb
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_20000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_20000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..86e4972ce2c81ea09c9e5caf2bebbae2dfa345db
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_20000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:492501a0663ed38dc4d06182e0d2be3e8c54e5a383162f6cfd00424f813d6fa1
+size 359982
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_22000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_22000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..e943c60b254ff0881d19f014d45ba525970a0bf7
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_22000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa10598504b063ddeef992be6fd8c54719ad20fb46a6b2a36c839c74fdb10a0b
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_22000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_22000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..1d1a01f8a98e481cd35a1cd3ada3cbb6a9d4505b
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_22000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a72273bec571488c06c2d6dc3764cc25460255100f3739749afbdc3087640343
+size 356976
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_24000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_24000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..21eaaf9f3b95f1809848d573e3bb77a2571acbcd
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_24000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89700b33c820f7e59a66792a3d6be0846583b01e11170ace25545ae7e9ec1666
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_24000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_24000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..115a71bdc639d52cb8e34b07cd3721b1c20dd2ea
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_24000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f19cd702ae9b87bb59fd029087a127e77f72c80675f0dbf5bccd0f131099ad4
+size 356235
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_26000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_26000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..409985edabd8997dc52386768775e70c6726483a
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_26000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b46aee3f8a3ad686012395403852fa92871c328e0ce9c85fa83d633010676b9
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_26000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_26000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..9edb59f55a0623203e2ba4173767ab8219449600
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_26000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49620af1a5732f00d6ab9554f8d1f35ab0e2a0fb14c1f3548bb1b802bf130a39
+size 354018
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_28000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_28000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..40066840ac3fde6bc1f759c590badc448fa40629
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_28000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bba18fc1a5a2d832b582f74877dd43e725a89d75ce0f838289f5f0ebd0455c4d
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_28000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_28000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..1bcb030568ecb659f32211bd338b618a986b6533
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_28000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a254599b6b871dc819772e2a8fddd033d0bdc3b492d8100e889596d6f6eabcbf
+size 353062
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_30000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_30000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..85e8ab48b79d7638508c67b6a246ce7699dcec51
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_30000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8253525e03d629649f4d666be27098e16a1e773b4afb5ab62208f38c851ff1d6
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_30000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_30000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..d632fd9cc3ad19df3d9999657c2cb7edc6f2dbac
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_30000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2680b99cfa5e40e7a89184593b0034a50005f359831a308294896d821a9c9ea1
+size 354060
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_32000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_32000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..2fdbd02ae9b98fc05b407c1794957196d60dccb8
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_32000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bfbc3f1efd22bc940b194bf33d83878f59c9cb1ea6274801464768803b85b71
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_32000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_32000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..16cfda567281d1e0c3c4c47d76b917422994a11f
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_32000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c306eb768e404729375739f1e23e375d2b6a1964c401c68b3d353f744179edd2
+size 351105
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_34000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_34000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..164ff78a6dd1d7c938000f4479ec3416d3473746
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_34000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6f534e66a0a761c7d4352b5d9c793a4fed77a0332118cb014de3181d0b8fba9
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_34000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_34000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..325efda36d349f9a99d295c281c41d57fade96b0
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_34000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96a3dedc8fea86a93d51440db8caf880cabe5e20e61bb05f73a37f879c98166f
+size 349687
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_36000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_36000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..aa0aa7f1c732aeaabe2cce4e6adf110505e005a3
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_36000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c08fce7ca8b1b075270a5f55da139addf783c54240371f00ddae3af292b925a3
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_36000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_36000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..c174015e4162580e6ebd199c460c9360eb2fadae
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_36000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af80f30eafd5b67cbd0f67a3be9be674a103535a89f61b98dc9078261d2bd2e1
+size 350654
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_38000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_38000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..9d957205ffd5ea8a4b79023ada856991365a193f
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_38000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14b0d6ac1e735ca529c23aa8b22adb55d5681bdff5f304d8a1000791f87751ec
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_38000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_38000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..c3b7aac1de0ef8932ee77bb9ff85a46d05af06d1
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_38000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78f666675362458b155de2a6beac1926ff9e15f33a5afb9994c3a545fb0cf02b
+size 349993
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_4000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_4000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..0aed86a7d6bf71f2b6a569f8c2cda422356a0794
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_4000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ce7aa0e6bb295440172cb5b28693e447da5f01117243f222e0e23390d61eddb
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_4000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_4000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..c815458435a2f35db47574df24e8d53d84a3d6cd
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_4000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed893e070a23f6b9dbb0f3d6aab7dfd5cb00430cc24e441a106a07fc7a7762fe
+size 412103
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_40000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_40000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..0a370adfe78bb1c47719f99c5b2b3a82f7696fdb
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_40000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bac2fd3acf5edf62e3ed155a866882fa36174a47f2f7310183b55c3169d3fbd
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_40000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_40000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..bade632f0ff8e7c58b932946f8fdbdd76499579b
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_40000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c08cdb3f18ab2c171e7533508975db07218f8ba7947a0be8765797ed871ba97
+size 349540
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_42000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_42000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..ebf55e70d9454b7e47ef3ab80c8d11c2bc5957dc
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_42000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c777c87d09a04f5af2a408458ad91d77f6d0951245b539849998cc8a818f3982
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_42000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_42000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..d218bb3a5b7813506bf4847508c4bf792be2393a
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_42000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7462708b0bf2f7bcdc98eaf3edc6e6cc597349346abb6d44b4f2bfa4fb6501f1
+size 350639
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_44000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_44000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..b45f229231b006f5a087c20171c5163df19b20c7
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_44000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2055cd4addab796beb6d1c8fb8246637a2b10eb5e620ba465255e2bbf1a2d567
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_44000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_44000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..3d8ba56f10003699f86687b5f7187b035335e0b8
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_44000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa524c6f2ac5106a9df3e111dac1c085eb99e2ca273b58722876a34f3decf8f9
+size 349348
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_46000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_46000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..8b15d2710cf33a2bd2c3158301b7426cda303eb5
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_46000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7ba65d09536c0e9c9981327bbd4c25a3558cdf9c55ada9b81705d49f479d3bb
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_46000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_46000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..e2367e15bcfeb1ae18e9c8bcedf492b4986b8cf1
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_46000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0f23c8a523800f9154436cb0aebfd2504f4c980b2b9de010b260331f8781d56
+size 347224
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_48000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_48000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..ca303367f7d6bac9c4222fc51a829adfa047c00b
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_48000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fb12501b865c7d7037a06595286f53060c74c9472b60b902f2c360e8b2fd09d
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_48000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_48000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..43bb17543a75abb56dd7fb3dc4d36ce95a41622a
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_48000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d180c227e56aa75426173ac6ff4868a0a9ec4adeb66b0b3b580c020405f2a5d5
+size 346568
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_50000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_50000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..09de62028b5a2d9bd698e1270c6f4eefb4bfad89
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_50000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72f097c727997b54a476e2eae92a368cab4d2afcf98facf54b8e90d9c04d6d44
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_50000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_50000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..4c606ba85847028b909ad5287740773304903c9f
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_50000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eca00b53b8cea89fe88ec175f1fc1c7209db93ea152da28d9b41a6626b4ede10
+size 347576
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_52000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_52000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..b9b206c07fbaad7d416e2df6b438267f33c0ce7f
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_52000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfdd63553a51cab657b65102929f5a4450ad8e531486ac741043b10587f93569
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_52000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_52000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..eaeaa59368443cd0427bf7193a80844569819abd
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_52000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:547c2b115d4e0728df5258fe092b4e8acf19c880026e15667f143820a2892360
+size 349048
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_54000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_54000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..6b8609681454d42af0bbb1dff5ccf2a7ecc96449
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_54000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04a3040f583710ec8bedfb9a5d63649778c09d3a84f0441451719d7ea7bb9148
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_54000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_54000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..64f4a49403d278e777059534e696874d5ebd6fd4
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_54000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2d4ba180a499e985cd2ec22d8e6e4a560f2e91caf4b3d218e8841de3e0dca59
+size 347441
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_56000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_56000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..333a07384e8a37e92b27f478e9f065cd7c9541b9
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_56000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a837fca43729abe81976fe6e65b05426a1bfd8aae8bbc8bc6d83fd337dc76d8
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_56000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_56000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..2532e37c6cbcec82180a3f687fda71f18130387d
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_56000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74c9d7b5da83264538c042b2b67944e0cb37df4053f086788d11efe6ae1c379b
+size 348020
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_58000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_58000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..e6d19b0106c7e6c8ecbed25ff69e3ff1088317ce
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_58000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8170c2f7060dcb4528bba0dd429b19f89dbfac6f021f764fc809f5f225ff1d65
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_58000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_58000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..7bbc34bfe8f482a43cf1cfbf0256d6449b0b96a5
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_58000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d87f93184d4ad277317cfe13eea28f9640d9f62ef9f4f74353111862ff96143c
+size 344756
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_6000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_6000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..86e6769beebbf1b0e19baecefa4928a8c0f4c55a
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_6000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d84f5ebf8e5da2ae201113927dd139cdc4fe6d96aa150b2054d585a5b15d3e52
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_6000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_6000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..5ae0a596c317c51619e1e154cc028d18e77c79e8
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_6000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38af865dea28af1db25117b4581349359ea5d86975b3a70bde826ded14d07cdb
+size 385167
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_60000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_60000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..081b403a826c54095fde81b7c25d7cae46a93d75
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_60000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:765a5b1c8d06c709764d158a26f8b4cac2c4ca3c5a3246834f7d44a24267914d
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_60000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_60000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..49aa350e3c4ce902c3bc6b229abe3d14ace38508
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_60000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6403f6895f20a177d00e19daeca2351208db8be8e6bed37b738d12aff1edf100
+size 345556
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_62000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_62000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..bea528fc14b7f440924593e78cf0021869279729
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_62000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87970041f8255dca366451e80cfedfee99f19cb888d9daee0e25e03c0a872db7
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_62000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_62000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..de2633e797a5178e95bfca5bce15dda061440ba6
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_62000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5fb192af1c576b1d3f131a35080180a0b9eb31e66ad6c6b429814d3d6fb6a2f
+size 343743
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_64000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_64000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..e70c61374c9c3820dabfde32ef30497ca73dd7fe
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_64000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adc9fa15d25f2aee4893d4873a19014625eedd8a4f641653cec84f73c32ec4b0
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_64000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_64000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..ba34d9b44f39e81da13a0533aec4257d0eb1a228
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_64000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39cdaa77a2583eb8187c1d2d927958f4ec52f69e276543f1afc61a1392ea9452
+size 342125
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_66000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_66000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..13ebee1fa8f0908ff5943b791274361bf698ddbc
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_66000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b0ed30ebb5e301d675edb28f9835b9405a1931ef6595e36065e09aecdf35588
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_66000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_66000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..99ee8c0e2395efce964649fac9e1ab729b7e6a3b
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_66000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51a3ff04bc38c57e3999301435eb7b4946b83610d08cd752d110c749773aa222
+size 340329
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_68000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_68000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..d70e75577fa85454437085dd6266c83e0ec94564
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_68000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80198e1814ea32ac5a3664055d31278a1ab73705d8a8f673dfdc08ddb4705d5d
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_68000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_68000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..a906e72b91bdb3ed7c79d57ca8168321b24f3031
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_68000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fef887cd742d56a6a8bc336b9193cc21a8464e01f0d8ac93da9a0d1c472c1d61
+size 344834
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_70000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_70000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..d63409fc4de1d7cee8f56e7d55a2fccfe7d3a236
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_70000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81943b8d836beb48514cd182dfaa5db818c8a2291a5e4870d0bff9c5e91c40d9
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_70000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_70000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..9c685cd3980e4ad55045597b6ac4ceba9e763bbf
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_70000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5872745507f07ed4560a797b5298e83f077bf6328b0dc0551a0ac6fe838fa426
+size 341650
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_72000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_72000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..bc88b7ef453bb49e679242cd69483fcfdfe41da3
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_72000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca24903b0ec49de7f2eb0c3863eacd47209b9cd7b10ff37b0beb81d5e295c4cc
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_72000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_72000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..065e667c69c4391410f839d05a73606c7cd1c551
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_72000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d6ea0de1664fbd8f65aa3aa2900b5eacd034ab804810065372f5d763bf79691
+size 341185
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_74000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_74000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..2e01e1915be2d9273276fdb26dfc58217fccefd3
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_74000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29b352d65e98f9046387d8332975dec9cdc1e96987e56ca892a9be0c0c9e234b
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_74000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_74000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..bd6c424256b8dea009f385c04d0617c3dc205fc0
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_74000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87ba260716ca1bf4136733fed2cfe08f5d778f65cc56bf2f48f83587454172c5
+size 344723
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_76000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_76000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..bd22d28d8088dfe0f16f88fb97c7fe3d61761b95
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_76000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d1d5713be42beeb2f919b4d9400d3a5d8d5e22b1b63bc60b4241f5b6eec13bc
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_76000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_76000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..2dc0b715dbb145a74eb52f38cab73c323cfe50f4
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_76000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:573eebcaea346afcf53c70e7600dcb5931ae459189f858003a856d28c1e88ce2
+size 341436
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_78000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_78000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..114e20e60ec0fc4af20ec4341e0f40bb9b0b9fdc
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_78000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d44f4199082b589b1da5b5ebe7ab1f428397a39632a084b64ad9a50f9df946f1
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_78000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_78000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..aafb0c126a983af228868b5b3c1057445f6a43f8
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_78000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2bd34ef55f3e99d5ddb121761403d3c7b7f566f90aeb85ad2cc734be36a2459
+size 345987
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_8000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_8000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..6469e50fb25b751ddaf3cf50750508489465122b
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_8000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:228502aa21e2df7050a83402fb741c818db94726cd3ffc5fa9d936d2b22cf1e7
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_8000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_8000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..0a5ac92509cc84055f816ae7c101409aaf2e8b1f
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_8000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a7c3f8cb29e8f1b2ba0f918b1813fcd99db9d313fc5df1fbbf52d4b803518e0
+size 378088
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_80000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_80000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..cd4ef24518da912b689ff9d5199cf6c1b5d5fe42
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_80000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f9cbf5d00a725d2f60145a8261a779da9bc8ab8f23afb045ff3206fc52cd352
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_80000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_80000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..2930f8af81d9f7684da1492480ccc3675733f6f8
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_80000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48be7f1a7ba6e6f49faf46ce81c59855c19b1587d799207216a5d76bb48b514d
+size 340535
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_82000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_82000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..f6613d1e1359a0c5d0898bc8271387c2c4daf8e5
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_82000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe3faf4bfdd5091f31bb3866e0a859da493b87a16094da474a4e4b780e1c6500
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_82000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_82000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..4e9011f0bf872145406fcaad8235b4f33c9f1a3c
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_82000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20738596e8974b6ba57393794a7afd058ec9ecaa2fcba605d1bde032931eb4fd
+size 339093
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_84000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_84000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..5eec5560a88dfa27e4978126d1e73328319a789e
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_84000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cce7642d49c9e8962938217ef01417b6f57fce79995ecfc0a0b343d87ac60c2
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_84000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_84000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..20e9dbe08be17afcf1cf2f2cc18068225aa95393
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_84000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:438ac03dde84d05d19b5a2c848d21ba513367824145ed4c6982e5760e953a5ff
+size 342211
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_86000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_86000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..f9ad427c31ec23d3ec8ea2a73b514eeeb3574464
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_86000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12e0b4759a483b8442501723f9a3c6d806041d9f9b6bdf6b9c513c8874e3e33b
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_86000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_86000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..4e750c891d193d3775f58a0ef20c27473e80622b
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_86000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04d22aaa935e889ad8b1036b56695ec63ea6fa20d506c2d20a06af84587482ee
+size 339174
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_88000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_88000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..a01d9ed479f56e875444d9964bf870ba2a49005c
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_88000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba5c37bb75d8f1b879baf4bbff55fa3a919d90e3db2923e6db200015df10409f
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_88000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_88000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..ae7f547afb3be1e1e077eea552ec428533df9b5e
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_88000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bdeddb9b93d6a62771e26112a8872a3b1404ab1e9593c32b88c09d4f5ff9402
+size 341415
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_90000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_90000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..431f746d8fdd99232e33e80d0c1706dc1aa2de5d
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_90000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39b5b61813c1b074c8ff5dda433388aaded2e5c402f547c3bd1cbc3104c87718
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_90000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_90000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..04a15313cac5a99f3501cf6aa23f787995ce9a87
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_90000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e76c1fa9deb5e2227a723732f201f206713560da2dcd694b65d87b4cfaeca3e7
+size 337196
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_92000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_92000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..802ca47f8ed5797c8fbc2ba19124d4b19f2880f8
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_92000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edc3dfb24f4357d89f9613b995c9f1c51ebb4203e22ade97421958baebacace8
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_92000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_92000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..bd663561cc067c31a227bfd84e65316a0b4ef0d3
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_92000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6273ef95c5c7b8fd582a9dcd7a650f8ef2bc15e41371e85c7be61364d8210119
+size 338269
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_94000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_94000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..9d5fa3725430dd68f035d408bc525d06656cf59b
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_94000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c49fca159092f6f0f8af3398eda823fed40be0d43d1f13737f96d1200a42af8a
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_94000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_94000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..d660bcb8b0a33f21207ce213ca2b23c838b74783
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_94000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1c90d2895eea97f693b6c38cfd62e74aa7a405c01e5931e604d232293386fc2
+size 340017
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_96000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_96000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..16f1f08d1824e2e3abf33fb262eb226b91b8aa4c
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_96000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92dae29626f12e4b45804f9ed0e992db5d544d5366f0846e827afb4e29d6488b
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_96000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_96000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..c2a53a1dec7c006dc7e1da043220324f18f2664d
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_96000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:864acfc1615740034ae8b428c5f49541f57c6773b0a72da081d386c99e923df3
+size 339032
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_98000/sample.npy b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_98000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..d715cc3ab11b7880066ef8beff5e7ef1bcffc512
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_98000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76759e6e69af92e0d3ee8058c2e5400c8eb6f2eedb93179d0031e214b130ace0
+size 983168
diff --git a/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_98000/sample.png b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_98000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..8e973864f330e3d7e32a0bd658d92922a69e8475
--- /dev/null
+++ b/dpdm/cifar100_32_eps10.0val-2025-03-24-08-04-47/train/samples/iter_98000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66d5173795e4d7edaa51c6b18106650b41db473886dca120896d1a7d6573d6ce
+size 340780