diff --git a/.gitattributes b/.gitattributes
index 1a264862f13ef5ffe6e921b1676b75fae5082304..e8e378375c7164a8c58738ebaa17ee3631da0fd2 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -1266,3 +1266,55 @@ dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_92000/sam
 dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_94000/sample.png filter=lfs diff=lfs merge=lfs -text
 dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_96000/sample.png filter=lfs diff=lfs merge=lfs -text
 dpdm/cifar100_32_eps1.0trainval-2024-10-24-03-39-27/train/samples/iter_98000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_10000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_100000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_102000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_104000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_12000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_14000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_16000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_18000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_2000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_20000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_22000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_24000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_26000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_28000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_30000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_32000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_34000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_36000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_38000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_4000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_40000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_42000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_44000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_46000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_48000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_50000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_52000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_54000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_56000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_58000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_6000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_60000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_62000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_64000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_66000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_68000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_70000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_72000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_74000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_76000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_78000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_8000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_80000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_82000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_84000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_86000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_88000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_90000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_92000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_94000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_96000/sample.png filter=lfs diff=lfs merge=lfs -text
+dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_98000/sample.png filter=lfs diff=lfs merge=lfs -text
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/stdout.txt b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/stdout.txt
new file mode 100644
index 0000000000000000000000000000000000000000..8d58228e3c9aa1087d1bb1d8a46a24f3ae2e61c1
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/stdout.txt
@@ -0,0 +1,2124 @@
+INFO - utils.py - 2024-10-24 01:44:45,583 - {'setup': {'method': 'dpsgd-diffusion', 'run_type': 'torchmp', 'n_gpus_per_node': 3, 'n_nodes': 1, 'node_rank': 0, 'master_address': '127.0.0.1', 'master_port': 6026, 'omp_n_threads': 8, 'workdir': 'exp/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41', 'local_rank': 0, 'global_rank': 0, 'global_size': 3, 'root_folder': '.'}, 'public_data': {'name': None, 'num_channels': 3, 'resolution': 32, 'n_classes': 1000, 'train_path': 'dataset/imagenet/imagenet_32', 'selective': {'ratio': 1.0}}, 'sensitive_data': {'name': 'cifar10', 'num_channels': 3, 'resolution': 32, 'n_classes': 10, 'train_path': 'dataset/cifar10/train_32.zip', 'test_path': 'dataset/cifar10/test_32.zip', 'fid_stats': 'dataset/cifar10/fid_stats_32.npz', 'train_num': 'val'}, 'model': {'ckpt': None, 'denoiser_name': 'edm', 'denoiser_network': 'song', 'ema_rate': 0.999, 'network': {'image_size': 32, 'num_in_channels': 3, 'num_out_channels': 3, 'label_dim': 10, 'attn_resolutions': [16], 'ch_mult': [2, 4]}, 'sampler': {'type': 'ddim', 'stochastic': False, 'num_steps': 50, 'tmin': 0.002, 'tmax': 80.0, 'rho': 7.0, 'guid_scale': 0.0, 'snapshot_batch_size': 80, 'fid_batch_size': 256}, 'sampler_fid': {'type': 'ddim', 'stochastic': False, 'num_steps': 250, 'tmin': 0.002, 'tmax': 80.0, 'rho': 7.0, 'guid_scale': 0.0}, 'sampler_acc': {'type': 'ddim', 'stochastic': False, 'num_steps': 250, 'tmin': 0.002, 'tmax': 80.0, 'rho': 7.0, 'guid_scale': 0.0}, 'local_rank': 0, 'global_rank': 0, 'global_size': 3, 'fid_stats': 'dataset/cifar10/fid_stats_32.npz'}, 'pretrain': {'log_dir': 'exp/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/pretrain', 'seed': 0, 'batch_size': 64, 'n_epochs': 1, 'log_freq': 100, 'snapshot_freq': 2000, 'snapshot_threshold': 1, 'save_freq': 100000, 'save_threshold': 1, 'fid_freq': 2000, 'fid_samples': 5000, 'fid_threshold': 1, 'label_random': True, 'optim': {'optimizer': 'Adam', 'params': {'lr': 0.0003, 'weight_decay': 0.0}}, 'loss': {'version': 'edm', 'p_mean': -1.2, 'p_std': 1.2, 'n_noise_samples': 1, 'n_classes': 10}}, 'train': {'log_dir': 'exp/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train', 'seed': 0, 'batch_size': 4096, 'n_epochs': 150, 'partly_finetune': False, 'log_freq': 100, 'snapshot_freq': 2000, 'snapshot_threshold': 1, 'save_freq': 100000, 'save_threshold': 1, 'fid_freq': 2000, 'fid_samples': 5000, 'final_fid_samples': 60000, 'fid_threshold': 1, 'gen': False, 'gen_batch_size': 8192, 'optim': {'optimizer': 'Adam', 'params': {'lr': 0.0003, 'weight_decay': 0.0}}, 'loss': {'version': 'edm', 'p_mean': -1.2, 'p_std': 1.2, 'n_noise_samples': 32, 'n_classes': 10}, 'dp': {'sdq': None, 'max_grad_norm': 1.0, 'delta': 1e-05, 'epsilon': 10.0, 'max_physical_batch_size': 8192, 'n_splits': 64}}, 'gen': {'data_num': 60000, 'batch_size': 1000, 'log_dir': 'exp/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/gen'}, 'eval': {'batch_size': 1000}}
+INFO - dataset_loader.py - 2024-10-24 01:44:51,659 - delta is reset as 2.07404851125286e-06
+INFO - dpsgd_diffusion.py - 2024-10-24 01:44:53,003 - Number of trainable parameters in model: 0
+INFO - dpsgd_diffusion.py - 2024-10-24 01:44:53,003 - Number of total epochs: 150
+INFO - dpsgd_diffusion.py - 2024-10-24 01:44:53,003 - Starting training at step 0
+INFO - dpsgd_diffusion.py - 2024-10-24 01:47:12,593 - Loss: 0.9235, step: 100
+INFO - dpsgd_diffusion.py - 2024-10-24 01:48:58,623 - Loss: 0.8450, step: 200
+INFO - dpsgd_diffusion.py - 2024-10-24 01:50:38,833 - Loss: 0.8304, step: 300
+INFO - dpsgd_diffusion.py - 2024-10-24 01:52:30,454 - Loss: 0.8187, step: 400
+INFO - dpsgd_diffusion.py - 2024-10-24 01:54:12,652 - Loss: 0.8378, step: 500
+INFO - dpsgd_diffusion.py - 2024-10-24 01:55:55,914 - Loss: 0.8206, step: 600
+INFO - dpsgd_diffusion.py - 2024-10-24 01:57:38,993 - Loss: 0.8012, step: 700
+INFO - dpsgd_diffusion.py - 2024-10-24 01:57:43,121 - Eps-value after 1 epochs: 0.8449
+INFO - dpsgd_diffusion.py - 2024-10-24 01:59:20,569 - Loss: 0.8133, step: 800
+INFO - dpsgd_diffusion.py - 2024-10-24 02:01:00,618 - Loss: 0.7621, step: 900
+INFO - dpsgd_diffusion.py - 2024-10-24 02:02:43,780 - Loss: 0.7676, step: 1000
+INFO - dpsgd_diffusion.py - 2024-10-24 02:04:26,265 - Loss: 0.7471, step: 1100
+INFO - dpsgd_diffusion.py - 2024-10-24 02:06:09,684 - Loss: 0.7260, step: 1200
+INFO - dpsgd_diffusion.py - 2024-10-24 02:07:53,390 - Loss: 0.7147, step: 1300
+INFO - dpsgd_diffusion.py - 2024-10-24 02:09:32,192 - Loss: 0.7193, step: 1400
+INFO - dpsgd_diffusion.py - 2024-10-24 02:09:40,127 - Eps-value after 2 epochs: 1.1114
+INFO - dpsgd_diffusion.py - 2024-10-24 02:11:12,019 - Loss: 0.6931, step: 1500
+INFO - dpsgd_diffusion.py - 2024-10-24 02:12:54,539 - Loss: 0.6742, step: 1600
+INFO - dpsgd_diffusion.py - 2024-10-24 02:14:38,392 - Loss: 0.6606, step: 1700
+INFO - dpsgd_diffusion.py - 2024-10-24 02:16:20,195 - Loss: 0.6280, step: 1800
+INFO - dpsgd_diffusion.py - 2024-10-24 02:18:03,459 - Loss: 0.5966, step: 1900
+INFO - dpsgd_diffusion.py - 2024-10-24 02:19:45,912 - Loss: 0.6027, step: 2000
+INFO - dpsgd_diffusion.py - 2024-10-24 02:19:46,015 - Saving snapshot checkpoint and sampling single batch at iteration 2000.
+WARNING - image.py - 2024-10-24 02:19:48,306 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 02:20:22,697 - FID at iteration 2000: 346.186139
+INFO - dpsgd_diffusion.py - 2024-10-24 02:22:07,794 - Loss: 0.6065, step: 2100
+INFO - dpsgd_diffusion.py - 2024-10-24 02:22:20,254 - Eps-value after 3 epochs: 1.3227
+INFO - dpsgd_diffusion.py - 2024-10-24 02:23:54,504 - Loss: 0.6050, step: 2200
+INFO - dpsgd_diffusion.py - 2024-10-24 02:25:35,707 - Loss: 0.5918, step: 2300
+INFO - dpsgd_diffusion.py - 2024-10-24 02:27:17,537 - Loss: 0.5518, step: 2400
+INFO - dpsgd_diffusion.py - 2024-10-24 02:28:58,968 - Loss: 0.5067, step: 2500
+INFO - dpsgd_diffusion.py - 2024-10-24 02:30:38,973 - Loss: 0.5078, step: 2600
+INFO - dpsgd_diffusion.py - 2024-10-24 02:32:19,405 - Loss: 0.5262, step: 2700
+INFO - dpsgd_diffusion.py - 2024-10-24 02:34:00,443 - Loss: 0.4594, step: 2800
+INFO - dpsgd_diffusion.py - 2024-10-24 02:34:16,989 - Eps-value after 4 epochs: 1.5065
+INFO - dpsgd_diffusion.py - 2024-10-24 02:35:44,104 - Loss: 0.4749, step: 2900
+INFO - dpsgd_diffusion.py - 2024-10-24 02:37:25,422 - Loss: 0.4624, step: 3000
+INFO - dpsgd_diffusion.py - 2024-10-24 02:39:06,959 - Loss: 0.4432, step: 3100
+INFO - dpsgd_diffusion.py - 2024-10-24 02:40:48,663 - Loss: 0.4992, step: 3200
+INFO - dpsgd_diffusion.py - 2024-10-24 02:42:26,670 - Loss: 0.4223, step: 3300
+INFO - dpsgd_diffusion.py - 2024-10-24 02:44:08,401 - Loss: 0.4341, step: 3400
+INFO - dpsgd_diffusion.py - 2024-10-24 02:45:52,047 - Loss: 0.3934, step: 3500
+INFO - dpsgd_diffusion.py - 2024-10-24 02:46:11,827 - Eps-value after 5 epochs: 1.6699
+INFO - dpsgd_diffusion.py - 2024-10-24 02:47:33,088 - Loss: 0.4277, step: 3600
+INFO - dpsgd_diffusion.py - 2024-10-24 02:49:17,536 - Loss: 0.4254, step: 3700
+INFO - dpsgd_diffusion.py - 2024-10-24 02:51:00,845 - Loss: 0.3944, step: 3800
+INFO - dpsgd_diffusion.py - 2024-10-24 02:52:43,975 - Loss: 0.3949, step: 3900
+INFO - dpsgd_diffusion.py - 2024-10-24 02:54:28,116 - Loss: 0.3938, step: 4000
+INFO - dpsgd_diffusion.py - 2024-10-24 02:54:28,174 - Saving snapshot checkpoint and sampling single batch at iteration 4000.
+WARNING - image.py - 2024-10-24 02:54:29,248 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 02:54:58,962 - FID at iteration 4000: 368.724195
+INFO - dpsgd_diffusion.py - 2024-10-24 02:56:40,381 - Loss: 0.3847, step: 4100
+INFO - dpsgd_diffusion.py - 2024-10-24 02:58:24,005 - Loss: 0.3913, step: 4200
+INFO - dpsgd_diffusion.py - 2024-10-24 02:58:48,146 - Eps-value after 6 epochs: 1.8209
+INFO - dpsgd_diffusion.py - 2024-10-24 03:00:06,727 - Loss: 0.3779, step: 4300
+INFO - dpsgd_diffusion.py - 2024-10-24 03:01:50,490 - Loss: 0.3708, step: 4400
+INFO - dpsgd_diffusion.py - 2024-10-24 03:03:32,105 - Loss: 0.3679, step: 4500
+INFO - dpsgd_diffusion.py - 2024-10-24 03:05:14,099 - Loss: 0.3829, step: 4600
+INFO - dpsgd_diffusion.py - 2024-10-24 03:06:55,579 - Loss: 0.3674, step: 4700
+INFO - dpsgd_diffusion.py - 2024-10-24 03:08:37,975 - Loss: 0.3935, step: 4800
+INFO - dpsgd_diffusion.py - 2024-10-24 03:10:20,612 - Loss: 0.3799, step: 4900
+INFO - dpsgd_diffusion.py - 2024-10-24 03:10:48,700 - Eps-value after 7 epochs: 1.9592
+INFO - dpsgd_diffusion.py - 2024-10-24 03:12:02,267 - Loss: 0.3650, step: 5000
+INFO - dpsgd_diffusion.py - 2024-10-24 03:13:42,734 - Loss: 0.3299, step: 5100
+INFO - dpsgd_diffusion.py - 2024-10-24 03:15:26,816 - Loss: 0.3658, step: 5200
+INFO - dpsgd_diffusion.py - 2024-10-24 03:17:08,668 - Loss: 0.3760, step: 5300
+INFO - dpsgd_diffusion.py - 2024-10-24 03:18:52,277 - Loss: 0.3313, step: 5400
+INFO - dpsgd_diffusion.py - 2024-10-24 03:20:35,586 - Loss: 0.3415, step: 5500
+INFO - dpsgd_diffusion.py - 2024-10-24 03:22:15,457 - Loss: 0.3419, step: 5600
+INFO - dpsgd_diffusion.py - 2024-10-24 03:22:46,952 - Eps-value after 8 epochs: 2.0901
+INFO - dpsgd_diffusion.py - 2024-10-24 03:23:56,100 - Loss: 0.3261, step: 5700
+INFO - dpsgd_diffusion.py - 2024-10-24 03:25:39,793 - Loss: 0.3834, step: 5800
+INFO - dpsgd_diffusion.py - 2024-10-24 03:27:24,992 - Loss: 0.3578, step: 5900
+INFO - dpsgd_diffusion.py - 2024-10-24 03:29:09,642 - Loss: 0.3267, step: 6000
+INFO - dpsgd_diffusion.py - 2024-10-24 03:29:09,742 - Saving snapshot checkpoint and sampling single batch at iteration 6000.
+WARNING - image.py - 2024-10-24 03:29:10,815 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 03:29:40,710 - FID at iteration 6000: 309.938383
+INFO - dpsgd_diffusion.py - 2024-10-24 03:31:23,324 - Loss: 0.3553, step: 6100
+INFO - dpsgd_diffusion.py - 2024-10-24 03:33:03,268 - Loss: 0.3463, step: 6200
+INFO - dpsgd_diffusion.py - 2024-10-24 03:34:45,867 - Loss: 0.3298, step: 6300
+INFO - dpsgd_diffusion.py - 2024-10-24 03:35:22,481 - Eps-value after 9 epochs: 2.2140
+INFO - dpsgd_diffusion.py - 2024-10-24 03:36:29,955 - Loss: 0.3450, step: 6400
+INFO - dpsgd_diffusion.py - 2024-10-24 03:38:11,754 - Loss: 0.3238, step: 6500
+INFO - dpsgd_diffusion.py - 2024-10-24 03:39:53,602 - Loss: 0.3265, step: 6600
+INFO - dpsgd_diffusion.py - 2024-10-24 03:41:38,900 - Loss: 0.3212, step: 6700
+INFO - dpsgd_diffusion.py - 2024-10-24 03:43:23,184 - Loss: 0.3392, step: 6800
+INFO - dpsgd_diffusion.py - 2024-10-24 03:45:06,752 - Loss: 0.3242, step: 6900
+INFO - dpsgd_diffusion.py - 2024-10-24 03:46:50,412 - Loss: 0.2982, step: 7000
+INFO - dpsgd_diffusion.py - 2024-10-24 03:47:30,830 - Eps-value after 10 epochs: 2.3320
+INFO - dpsgd_diffusion.py - 2024-10-24 03:48:29,779 - Loss: 0.3406, step: 7100
+INFO - dpsgd_diffusion.py - 2024-10-24 03:50:11,839 - Loss: 0.3266, step: 7200
+INFO - dpsgd_diffusion.py - 2024-10-24 03:51:54,443 - Loss: 0.3018, step: 7300
+INFO - dpsgd_diffusion.py - 2024-10-24 03:53:35,882 - Loss: 0.3201, step: 7400
+INFO - dpsgd_diffusion.py - 2024-10-24 03:55:16,670 - Loss: 0.3118, step: 7500
+INFO - dpsgd_diffusion.py - 2024-10-24 03:56:57,474 - Loss: 0.3019, step: 7600
+INFO - dpsgd_diffusion.py - 2024-10-24 03:58:40,005 - Loss: 0.2964, step: 7700
+INFO - dpsgd_diffusion.py - 2024-10-24 03:59:25,459 - Eps-value after 11 epochs: 2.4450
+INFO - dpsgd_diffusion.py - 2024-10-24 04:00:23,299 - Loss: 0.3163, step: 7800
+INFO - dpsgd_diffusion.py - 2024-10-24 04:02:02,313 - Loss: 0.3071, step: 7900
+INFO - dpsgd_diffusion.py - 2024-10-24 04:03:42,120 - Loss: 0.2939, step: 8000
+INFO - dpsgd_diffusion.py - 2024-10-24 04:03:42,130 - Saving snapshot checkpoint and sampling single batch at iteration 8000.
+WARNING - image.py - 2024-10-24 04:03:43,199 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 04:04:13,046 - FID at iteration 8000: 286.701822
+INFO - dpsgd_diffusion.py - 2024-10-24 04:05:55,947 - Loss: 0.2900, step: 8100
+INFO - dpsgd_diffusion.py - 2024-10-24 04:07:37,109 - Loss: 0.3088, step: 8200
+INFO - dpsgd_diffusion.py - 2024-10-24 04:09:18,668 - Loss: 0.2930, step: 8300
+INFO - dpsgd_diffusion.py - 2024-10-24 04:11:01,829 - Loss: 0.3171, step: 8400
+INFO - dpsgd_diffusion.py - 2024-10-24 04:11:50,336 - Eps-value after 12 epochs: 2.5536
+INFO - dpsgd_diffusion.py - 2024-10-24 04:12:43,253 - Loss: 0.3202, step: 8500
+INFO - dpsgd_diffusion.py - 2024-10-24 04:14:24,537 - Loss: 0.3085, step: 8600
+INFO - dpsgd_diffusion.py - 2024-10-24 04:16:07,150 - Loss: 0.3070, step: 8700
+INFO - dpsgd_diffusion.py - 2024-10-24 04:17:49,933 - Loss: 0.3378, step: 8800
+INFO - dpsgd_diffusion.py - 2024-10-24 04:19:28,969 - Loss: 0.2950, step: 8900
+INFO - dpsgd_diffusion.py - 2024-10-24 04:21:11,669 - Loss: 0.3132, step: 9000
+INFO - dpsgd_diffusion.py - 2024-10-24 04:22:50,858 - Loss: 0.2999, step: 9100
+INFO - dpsgd_diffusion.py - 2024-10-24 04:23:42,460 - Eps-value after 13 epochs: 2.6584
+INFO - dpsgd_diffusion.py - 2024-10-24 04:24:31,707 - Loss: 0.2755, step: 9200
+INFO - dpsgd_diffusion.py - 2024-10-24 04:26:12,681 - Loss: 0.2979, step: 9300
+INFO - dpsgd_diffusion.py - 2024-10-24 04:27:54,209 - Loss: 0.2796, step: 9400
+INFO - dpsgd_diffusion.py - 2024-10-24 04:29:36,529 - Loss: 0.2959, step: 9500
+INFO - dpsgd_diffusion.py - 2024-10-24 04:31:20,775 - Loss: 0.2717, step: 9600
+INFO - dpsgd_diffusion.py - 2024-10-24 04:33:03,261 - Loss: 0.2865, step: 9700
+INFO - dpsgd_diffusion.py - 2024-10-24 04:34:45,145 - Loss: 0.3054, step: 9800
+INFO - dpsgd_diffusion.py - 2024-10-24 04:35:41,388 - Eps-value after 14 epochs: 2.7598
+INFO - dpsgd_diffusion.py - 2024-10-24 04:36:26,562 - Loss: 0.2833, step: 9900
+INFO - dpsgd_diffusion.py - 2024-10-24 04:38:09,272 - Loss: 0.3027, step: 10000
+INFO - dpsgd_diffusion.py - 2024-10-24 04:38:09,329 - Saving snapshot checkpoint and sampling single batch at iteration 10000.
+WARNING - image.py - 2024-10-24 04:38:10,401 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 04:38:40,374 - FID at iteration 10000: 273.611193
+INFO - dpsgd_diffusion.py - 2024-10-24 04:40:22,489 - Loss: 0.3048, step: 10100
+INFO - dpsgd_diffusion.py - 2024-10-24 04:42:05,346 - Loss: 0.2685, step: 10200
+INFO - dpsgd_diffusion.py - 2024-10-24 04:43:46,245 - Loss: 0.2582, step: 10300
+INFO - dpsgd_diffusion.py - 2024-10-24 04:45:27,872 - Loss: 0.2900, step: 10400
+INFO - dpsgd_diffusion.py - 2024-10-24 04:47:09,381 - Loss: 0.2994, step: 10500
+INFO - dpsgd_diffusion.py - 2024-10-24 04:48:09,143 - Eps-value after 15 epochs: 2.8581
+INFO - dpsgd_diffusion.py - 2024-10-24 04:48:50,141 - Loss: 0.2893, step: 10600
+INFO - dpsgd_diffusion.py - 2024-10-24 04:50:33,173 - Loss: 0.2779, step: 10700
+INFO - dpsgd_diffusion.py - 2024-10-24 04:52:15,800 - Loss: 0.2807, step: 10800
+INFO - dpsgd_diffusion.py - 2024-10-24 04:53:58,384 - Loss: 0.3039, step: 10900
+INFO - dpsgd_diffusion.py - 2024-10-24 04:55:42,059 - Loss: 0.2833, step: 11000
+INFO - dpsgd_diffusion.py - 2024-10-24 04:57:23,816 - Loss: 0.2597, step: 11100
+INFO - dpsgd_diffusion.py - 2024-10-24 04:59:02,295 - Loss: 0.2890, step: 11200
+INFO - dpsgd_diffusion.py - 2024-10-24 05:00:11,130 - Eps-value after 16 epochs: 2.9536
+INFO - dpsgd_diffusion.py - 2024-10-24 05:00:46,104 - Loss: 0.2665, step: 11300
+INFO - dpsgd_diffusion.py - 2024-10-24 05:02:25,757 - Loss: 0.2787, step: 11400
+INFO - dpsgd_diffusion.py - 2024-10-24 05:04:05,569 - Loss: 0.2676, step: 11500
+INFO - dpsgd_diffusion.py - 2024-10-24 05:05:46,701 - Loss: 0.2793, step: 11600
+INFO - dpsgd_diffusion.py - 2024-10-24 05:07:28,104 - Loss: 0.2889, step: 11700
+INFO - dpsgd_diffusion.py - 2024-10-24 05:09:07,912 - Loss: 0.2995, step: 11800
+INFO - dpsgd_diffusion.py - 2024-10-24 05:10:48,715 - Loss: 0.3050, step: 11900
+INFO - dpsgd_diffusion.py - 2024-10-24 05:11:56,921 - Eps-value after 17 epochs: 3.0466
+INFO - dpsgd_diffusion.py - 2024-10-24 05:12:29,870 - Loss: 0.2875, step: 12000
+INFO - dpsgd_diffusion.py - 2024-10-24 05:12:29,925 - Saving snapshot checkpoint and sampling single batch at iteration 12000.
+WARNING - image.py - 2024-10-24 05:12:30,999 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 05:13:00,905 - FID at iteration 12000: 253.368440
+INFO - dpsgd_diffusion.py - 2024-10-24 05:14:42,593 - Loss: 0.2751, step: 12100
+INFO - dpsgd_diffusion.py - 2024-10-24 05:16:26,247 - Loss: 0.2772, step: 12200
+INFO - dpsgd_diffusion.py - 2024-10-24 05:18:08,623 - Loss: 0.2769, step: 12300
+INFO - dpsgd_diffusion.py - 2024-10-24 05:19:50,926 - Loss: 0.2695, step: 12400
+INFO - dpsgd_diffusion.py - 2024-10-24 05:21:33,358 - Loss: 0.2688, step: 12500
+INFO - dpsgd_diffusion.py - 2024-10-24 05:23:14,101 - Loss: 0.2644, step: 12600
+INFO - dpsgd_diffusion.py - 2024-10-24 05:24:26,097 - Eps-value after 18 epochs: 3.1373
+INFO - dpsgd_diffusion.py - 2024-10-24 05:24:54,901 - Loss: 0.2700, step: 12700
+INFO - dpsgd_diffusion.py - 2024-10-24 05:26:35,509 - Loss: 0.2955, step: 12800
+INFO - dpsgd_diffusion.py - 2024-10-24 05:28:16,741 - Loss: 0.2875, step: 12900
+INFO - dpsgd_diffusion.py - 2024-10-24 05:29:58,499 - Loss: 0.2766, step: 13000
+INFO - dpsgd_diffusion.py - 2024-10-24 05:31:40,357 - Loss: 0.2661, step: 13100
+INFO - dpsgd_diffusion.py - 2024-10-24 05:33:21,858 - Loss: 0.2715, step: 13200
+INFO - dpsgd_diffusion.py - 2024-10-24 05:35:04,316 - Loss: 0.2558, step: 13300
+INFO - dpsgd_diffusion.py - 2024-10-24 05:36:22,712 - Eps-value after 19 epochs: 3.2258
+INFO - dpsgd_diffusion.py - 2024-10-24 05:36:47,421 - Loss: 0.2578, step: 13400
+INFO - dpsgd_diffusion.py - 2024-10-24 05:38:29,340 - Loss: 0.2914, step: 13500
+INFO - dpsgd_diffusion.py - 2024-10-24 05:40:10,491 - Loss: 0.2781, step: 13600
+INFO - dpsgd_diffusion.py - 2024-10-24 05:41:52,292 - Loss: 0.2762, step: 13700
+INFO - dpsgd_diffusion.py - 2024-10-24 05:43:36,708 - Loss: 0.2649, step: 13800
+INFO - dpsgd_diffusion.py - 2024-10-24 05:45:20,410 - Loss: 0.2908, step: 13900
+INFO - dpsgd_diffusion.py - 2024-10-24 05:47:03,199 - Loss: 0.2575, step: 14000
+INFO - dpsgd_diffusion.py - 2024-10-24 05:47:03,302 - Saving snapshot checkpoint and sampling single batch at iteration 14000.
+WARNING - image.py - 2024-10-24 05:47:04,402 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 05:47:34,262 - FID at iteration 14000: 236.401174
+INFO - dpsgd_diffusion.py - 2024-10-24 05:48:56,118 - Eps-value after 20 epochs: 3.3125
+INFO - dpsgd_diffusion.py - 2024-10-24 05:49:16,692 - Loss: 0.2617, step: 14100
+INFO - dpsgd_diffusion.py - 2024-10-24 05:50:57,495 - Loss: 0.3096, step: 14200
+INFO - dpsgd_diffusion.py - 2024-10-24 05:52:39,110 - Loss: 0.2790, step: 14300
+INFO - dpsgd_diffusion.py - 2024-10-24 05:54:21,197 - Loss: 0.2778, step: 14400
+INFO - dpsgd_diffusion.py - 2024-10-24 05:56:03,075 - Loss: 0.2601, step: 14500
+INFO - dpsgd_diffusion.py - 2024-10-24 05:57:47,141 - Loss: 0.2743, step: 14600
+INFO - dpsgd_diffusion.py - 2024-10-24 05:59:29,023 - Loss: 0.2712, step: 14700
+INFO - dpsgd_diffusion.py - 2024-10-24 06:00:55,085 - Eps-value after 21 epochs: 3.3973
+INFO - dpsgd_diffusion.py - 2024-10-24 06:01:11,766 - Loss: 0.2590, step: 14800
+INFO - dpsgd_diffusion.py - 2024-10-24 06:02:52,547 - Loss: 0.2791, step: 14900
+INFO - dpsgd_diffusion.py - 2024-10-24 06:04:35,041 - Loss: 0.2662, step: 15000
+INFO - dpsgd_diffusion.py - 2024-10-24 06:06:18,711 - Loss: 0.2766, step: 15100
+INFO - dpsgd_diffusion.py - 2024-10-24 06:08:00,653 - Loss: 0.2922, step: 15200
+INFO - dpsgd_diffusion.py - 2024-10-24 06:09:40,291 - Loss: 0.2976, step: 15300
+INFO - dpsgd_diffusion.py - 2024-10-24 06:11:22,845 - Loss: 0.2623, step: 15400
+INFO - dpsgd_diffusion.py - 2024-10-24 06:12:51,116 - Eps-value after 22 epochs: 3.4803
+INFO - dpsgd_diffusion.py - 2024-10-24 06:13:03,471 - Loss: 0.2626, step: 15500
+INFO - dpsgd_diffusion.py - 2024-10-24 06:14:44,205 - Loss: 0.2729, step: 15600
+INFO - dpsgd_diffusion.py - 2024-10-24 06:16:27,332 - Loss: 0.2499, step: 15700
+INFO - dpsgd_diffusion.py - 2024-10-24 06:18:09,227 - Loss: 0.2714, step: 15800
+INFO - dpsgd_diffusion.py - 2024-10-24 06:19:51,923 - Loss: 0.2866, step: 15900
+INFO - dpsgd_diffusion.py - 2024-10-24 06:21:32,701 - Loss: 0.2583, step: 16000
+INFO - dpsgd_diffusion.py - 2024-10-24 06:21:32,711 - Saving snapshot checkpoint and sampling single batch at iteration 16000.
+WARNING - image.py - 2024-10-24 06:21:33,830 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 06:22:03,663 - FID at iteration 16000: 221.476695
+INFO - dpsgd_diffusion.py - 2024-10-24 06:23:47,224 - Loss: 0.2571, step: 16100
+INFO - dpsgd_diffusion.py - 2024-10-24 06:25:21,429 - Eps-value after 23 epochs: 3.5619
+INFO - dpsgd_diffusion.py - 2024-10-24 06:25:29,640 - Loss: 0.2705, step: 16200
+INFO - dpsgd_diffusion.py - 2024-10-24 06:27:11,792 - Loss: 0.2870, step: 16300
+INFO - dpsgd_diffusion.py - 2024-10-24 06:28:52,223 - Loss: 0.2595, step: 16400
+INFO - dpsgd_diffusion.py - 2024-10-24 06:30:32,841 - Loss: 0.2610, step: 16500
+INFO - dpsgd_diffusion.py - 2024-10-24 06:32:17,231 - Loss: 0.2556, step: 16600
+INFO - dpsgd_diffusion.py - 2024-10-24 06:33:59,161 - Loss: 0.2589, step: 16700
+INFO - dpsgd_diffusion.py - 2024-10-24 06:35:40,835 - Loss: 0.2691, step: 16800
+INFO - dpsgd_diffusion.py - 2024-10-24 06:37:17,927 - Eps-value after 24 epochs: 3.6419
+INFO - dpsgd_diffusion.py - 2024-10-24 06:37:22,046 - Loss: 0.2647, step: 16900
+INFO - dpsgd_diffusion.py - 2024-10-24 06:39:05,373 - Loss: 0.2552, step: 17000
+INFO - dpsgd_diffusion.py - 2024-10-24 06:40:47,652 - Loss: 0.2562, step: 17100
+INFO - dpsgd_diffusion.py - 2024-10-24 06:42:30,501 - Loss: 0.2728, step: 17200
+INFO - dpsgd_diffusion.py - 2024-10-24 06:44:12,708 - Loss: 0.2748, step: 17300
+INFO - dpsgd_diffusion.py - 2024-10-24 06:45:53,961 - Loss: 0.2765, step: 17400
+INFO - dpsgd_diffusion.py - 2024-10-24 06:47:35,000 - Loss: 0.2702, step: 17500
+INFO - dpsgd_diffusion.py - 2024-10-24 06:49:15,575 - Loss: 0.2580, step: 17600
+INFO - dpsgd_diffusion.py - 2024-10-24 06:49:15,593 - Eps-value after 25 epochs: 3.7206
+INFO - dpsgd_diffusion.py - 2024-10-24 06:50:59,575 - Loss: 0.2663, step: 17700
+INFO - dpsgd_diffusion.py - 2024-10-24 06:52:39,327 - Loss: 0.2644, step: 17800
+INFO - dpsgd_diffusion.py - 2024-10-24 06:54:22,908 - Loss: 0.2850, step: 17900
+INFO - dpsgd_diffusion.py - 2024-10-24 06:56:06,035 - Loss: 0.2583, step: 18000
+INFO - dpsgd_diffusion.py - 2024-10-24 06:56:06,044 - Saving snapshot checkpoint and sampling single batch at iteration 18000.
+WARNING - image.py - 2024-10-24 06:56:07,133 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 06:56:36,968 - FID at iteration 18000: 207.602970
+INFO - dpsgd_diffusion.py - 2024-10-24 06:58:17,797 - Loss: 0.2518, step: 18100
+INFO - dpsgd_diffusion.py - 2024-10-24 07:00:02,565 - Loss: 0.2473, step: 18200
+INFO - dpsgd_diffusion.py - 2024-10-24 07:01:45,007 - Loss: 0.2316, step: 18300
+INFO - dpsgd_diffusion.py - 2024-10-24 07:01:48,964 - Eps-value after 26 epochs: 3.7979
+INFO - dpsgd_diffusion.py - 2024-10-24 07:03:26,252 - Loss: 0.2582, step: 18400
+INFO - dpsgd_diffusion.py - 2024-10-24 07:05:07,221 - Loss: 0.2302, step: 18500
+INFO - dpsgd_diffusion.py - 2024-10-24 07:06:48,838 - Loss: 0.2481, step: 18600
+INFO - dpsgd_diffusion.py - 2024-10-24 07:08:28,377 - Loss: 0.2446, step: 18700
+INFO - dpsgd_diffusion.py - 2024-10-24 07:10:09,529 - Loss: 0.2462, step: 18800
+INFO - dpsgd_diffusion.py - 2024-10-24 07:11:51,918 - Loss: 0.2456, step: 18900
+INFO - dpsgd_diffusion.py - 2024-10-24 07:13:34,512 - Loss: 0.2656, step: 19000
+INFO - dpsgd_diffusion.py - 2024-10-24 07:13:42,449 - Eps-value after 27 epochs: 3.8741
+INFO - dpsgd_diffusion.py - 2024-10-24 07:15:16,398 - Loss: 0.2725, step: 19100
+INFO - dpsgd_diffusion.py - 2024-10-24 07:16:57,682 - Loss: 0.2583, step: 19200
+INFO - dpsgd_diffusion.py - 2024-10-24 07:18:39,702 - Loss: 0.2584, step: 19300
+INFO - dpsgd_diffusion.py - 2024-10-24 07:20:20,282 - Loss: 0.2809, step: 19400
+INFO - dpsgd_diffusion.py - 2024-10-24 07:22:03,277 - Loss: 0.2350, step: 19500
+INFO - dpsgd_diffusion.py - 2024-10-24 07:23:46,231 - Loss: 0.2532, step: 19600
+INFO - dpsgd_diffusion.py - 2024-10-24 07:25:28,739 - Loss: 0.2683, step: 19700
+INFO - dpsgd_diffusion.py - 2024-10-24 07:25:41,246 - Eps-value after 28 epochs: 3.9490
+INFO - dpsgd_diffusion.py - 2024-10-24 07:27:11,555 - Loss: 0.2592, step: 19800
+INFO - dpsgd_diffusion.py - 2024-10-24 07:28:53,360 - Loss: 0.2378, step: 19900
+INFO - dpsgd_diffusion.py - 2024-10-24 07:30:35,613 - Loss: 0.2481, step: 20000
+INFO - dpsgd_diffusion.py - 2024-10-24 07:30:35,716 - Saving snapshot checkpoint and sampling single batch at iteration 20000.
+WARNING - image.py - 2024-10-24 07:30:36,809 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 07:31:06,324 - FID at iteration 20000: 197.796689
+INFO - dpsgd_diffusion.py - 2024-10-24 07:32:48,246 - Loss: 0.2635, step: 20100
+INFO - dpsgd_diffusion.py - 2024-10-24 07:34:30,594 - Loss: 0.2531, step: 20200
+INFO - dpsgd_diffusion.py - 2024-10-24 07:36:12,808 - Loss: 0.2386, step: 20300
+INFO - dpsgd_diffusion.py - 2024-10-24 07:37:56,048 - Loss: 0.2616, step: 20400
+INFO - dpsgd_diffusion.py - 2024-10-24 07:38:11,803 - Eps-value after 29 epochs: 4.0230
+INFO - dpsgd_diffusion.py - 2024-10-24 07:39:36,046 - Loss: 0.2447, step: 20500
+INFO - dpsgd_diffusion.py - 2024-10-24 07:41:18,739 - Loss: 0.2438, step: 20600
+INFO - dpsgd_diffusion.py - 2024-10-24 07:42:59,823 - Loss: 0.2612, step: 20700
+INFO - dpsgd_diffusion.py - 2024-10-24 07:44:43,778 - Loss: 0.2616, step: 20800
+INFO - dpsgd_diffusion.py - 2024-10-24 07:46:25,334 - Loss: 0.2477, step: 20900
+INFO - dpsgd_diffusion.py - 2024-10-24 07:48:05,725 - Loss: 0.2474, step: 21000
+INFO - dpsgd_diffusion.py - 2024-10-24 07:49:50,437 - Loss: 0.2676, step: 21100
+INFO - dpsgd_diffusion.py - 2024-10-24 07:50:11,138 - Eps-value after 30 epochs: 4.0958
+INFO - dpsgd_diffusion.py - 2024-10-24 07:51:30,730 - Loss: 0.2536, step: 21200
+INFO - dpsgd_diffusion.py - 2024-10-24 07:53:12,129 - Loss: 0.2585, step: 21300
+INFO - dpsgd_diffusion.py - 2024-10-24 07:54:55,248 - Loss: 0.2551, step: 21400
+INFO - dpsgd_diffusion.py - 2024-10-24 07:56:37,070 - Loss: 0.2567, step: 21500
+INFO - dpsgd_diffusion.py - 2024-10-24 07:58:18,273 - Loss: 0.2640, step: 21600
+INFO - dpsgd_diffusion.py - 2024-10-24 08:00:03,077 - Loss: 0.2538, step: 21700
+INFO - dpsgd_diffusion.py - 2024-10-24 08:01:48,452 - Loss: 0.2362, step: 21800
+INFO - dpsgd_diffusion.py - 2024-10-24 08:02:13,315 - Eps-value after 31 epochs: 4.1675
+INFO - dpsgd_diffusion.py - 2024-10-24 08:03:32,741 - Loss: 0.2771, step: 21900
+INFO - dpsgd_diffusion.py - 2024-10-24 08:05:11,547 - Loss: 0.2289, step: 22000
+INFO - dpsgd_diffusion.py - 2024-10-24 08:05:11,553 - Saving snapshot checkpoint and sampling single batch at iteration 22000.
+WARNING - image.py - 2024-10-24 08:05:12,643 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 08:05:42,529 - FID at iteration 22000: 186.396427
+INFO - dpsgd_diffusion.py - 2024-10-24 08:07:24,112 - Loss: 0.2312, step: 22100
+INFO - dpsgd_diffusion.py - 2024-10-24 08:09:05,649 - Loss: 0.2504, step: 22200
+INFO - dpsgd_diffusion.py - 2024-10-24 08:10:46,181 - Loss: 0.2601, step: 22300
+INFO - dpsgd_diffusion.py - 2024-10-24 08:12:27,372 - Loss: 0.2580, step: 22400
+INFO - dpsgd_diffusion.py - 2024-10-24 08:14:11,795 - Loss: 0.2483, step: 22500
+INFO - dpsgd_diffusion.py - 2024-10-24 08:14:39,978 - Eps-value after 32 epochs: 4.2383
+INFO - dpsgd_diffusion.py - 2024-10-24 08:15:55,504 - Loss: 0.2510, step: 22600
+INFO - dpsgd_diffusion.py - 2024-10-24 08:17:35,791 - Loss: 0.2481, step: 22700
+INFO - dpsgd_diffusion.py - 2024-10-24 08:19:16,511 - Loss: 0.2539, step: 22800
+INFO - dpsgd_diffusion.py - 2024-10-24 08:20:55,594 - Loss: 0.2376, step: 22900
+INFO - dpsgd_diffusion.py - 2024-10-24 08:22:36,927 - Loss: 0.2432, step: 23000
+INFO - dpsgd_diffusion.py - 2024-10-24 08:24:17,380 - Loss: 0.2628, step: 23100
+INFO - dpsgd_diffusion.py - 2024-10-24 08:25:57,897 - Loss: 0.2701, step: 23200
+INFO - dpsgd_diffusion.py - 2024-10-24 08:26:30,397 - Eps-value after 33 epochs: 4.3085
+INFO - dpsgd_diffusion.py - 2024-10-24 08:27:40,818 - Loss: 0.2415, step: 23300
+INFO - dpsgd_diffusion.py - 2024-10-24 08:29:24,078 - Loss: 0.2680, step: 23400
+INFO - dpsgd_diffusion.py - 2024-10-24 08:31:05,690 - Loss: 0.2555, step: 23500
+INFO - dpsgd_diffusion.py - 2024-10-24 08:32:46,876 - Loss: 0.2488, step: 23600
+INFO - dpsgd_diffusion.py - 2024-10-24 08:34:27,054 - Loss: 0.2605, step: 23700
+INFO - dpsgd_diffusion.py - 2024-10-24 08:36:09,817 - Loss: 0.2521, step: 23800
+INFO - dpsgd_diffusion.py - 2024-10-24 08:37:52,825 - Loss: 0.2440, step: 23900
+INFO - dpsgd_diffusion.py - 2024-10-24 08:38:28,651 - Eps-value after 34 epochs: 4.3774
+INFO - dpsgd_diffusion.py - 2024-10-24 08:39:32,791 - Loss: 0.2530, step: 24000
+INFO - dpsgd_diffusion.py - 2024-10-24 08:39:32,801 - Saving snapshot checkpoint and sampling single batch at iteration 24000.
+WARNING - image.py - 2024-10-24 08:39:33,889 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 08:40:03,849 - FID at iteration 24000: 178.249307
+INFO - dpsgd_diffusion.py - 2024-10-24 08:41:47,956 - Loss: 0.2502, step: 24100
+INFO - dpsgd_diffusion.py - 2024-10-24 08:43:27,835 - Loss: 0.2526, step: 24200
+INFO - dpsgd_diffusion.py - 2024-10-24 08:45:11,024 - Loss: 0.2571, step: 24300
+INFO - dpsgd_diffusion.py - 2024-10-24 08:46:53,792 - Loss: 0.2456, step: 24400
+INFO - dpsgd_diffusion.py - 2024-10-24 08:48:35,345 - Loss: 0.2398, step: 24500
+INFO - dpsgd_diffusion.py - 2024-10-24 08:50:14,150 - Loss: 0.2352, step: 24600
+INFO - dpsgd_diffusion.py - 2024-10-24 08:50:54,539 - Eps-value after 35 epochs: 4.4456
+INFO - dpsgd_diffusion.py - 2024-10-24 08:51:54,318 - Loss: 0.2545, step: 24700
+INFO - dpsgd_diffusion.py - 2024-10-24 08:53:45,609 - Loss: 0.2223, step: 24800
+INFO - dpsgd_diffusion.py - 2024-10-24 08:55:29,372 - Loss: 0.2265, step: 24900
+INFO - dpsgd_diffusion.py - 2024-10-24 08:57:11,662 - Loss: 0.2390, step: 25000
+INFO - dpsgd_diffusion.py - 2024-10-24 08:58:53,192 - Loss: 0.2223, step: 25100
+INFO - dpsgd_diffusion.py - 2024-10-24 09:00:37,095 - Loss: 0.2568, step: 25200
+INFO - dpsgd_diffusion.py - 2024-10-24 09:02:18,302 - Loss: 0.2638, step: 25300
+INFO - dpsgd_diffusion.py - 2024-10-24 09:03:03,784 - Eps-value after 36 epochs: 4.5133
+INFO - dpsgd_diffusion.py - 2024-10-24 09:04:01,205 - Loss: 0.2368, step: 25400
+INFO - dpsgd_diffusion.py - 2024-10-24 09:05:44,156 - Loss: 0.2665, step: 25500
+INFO - dpsgd_diffusion.py - 2024-10-24 09:07:23,905 - Loss: 0.2802, step: 25600
+INFO - dpsgd_diffusion.py - 2024-10-24 09:09:04,124 - Loss: 0.2381, step: 25700
+INFO - dpsgd_diffusion.py - 2024-10-24 09:10:45,095 - Loss: 0.2589, step: 25800
+INFO - dpsgd_diffusion.py - 2024-10-24 09:12:29,628 - Loss: 0.2314, step: 25900
+INFO - dpsgd_diffusion.py - 2024-10-24 09:14:12,720 - Loss: 0.2492, step: 26000
+INFO - dpsgd_diffusion.py - 2024-10-24 09:14:12,778 - Saving snapshot checkpoint and sampling single batch at iteration 26000.
+WARNING - image.py - 2024-10-24 09:14:13,856 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 09:14:43,647 - FID at iteration 26000: 170.630860
+INFO - dpsgd_diffusion.py - 2024-10-24 09:15:32,585 - Eps-value after 37 epochs: 4.5798
+INFO - dpsgd_diffusion.py - 2024-10-24 09:16:27,580 - Loss: 0.2238, step: 26100
+INFO - dpsgd_diffusion.py - 2024-10-24 09:18:10,575 - Loss: 0.2222, step: 26200
+INFO - dpsgd_diffusion.py - 2024-10-24 09:19:53,162 - Loss: 0.2536, step: 26300
+INFO - dpsgd_diffusion.py - 2024-10-24 09:21:36,778 - Loss: 0.2285, step: 26400
+INFO - dpsgd_diffusion.py - 2024-10-24 09:23:20,752 - Loss: 0.2278, step: 26500
+INFO - dpsgd_diffusion.py - 2024-10-24 09:25:03,404 - Loss: 0.2447, step: 26600
+INFO - dpsgd_diffusion.py - 2024-10-24 09:26:49,826 - Loss: 0.2349, step: 26700
+INFO - dpsgd_diffusion.py - 2024-10-24 09:27:46,051 - Eps-value after 38 epochs: 4.6459
+INFO - dpsgd_diffusion.py - 2024-10-24 09:28:35,465 - Loss: 0.2443, step: 26800
+INFO - dpsgd_diffusion.py - 2024-10-24 09:30:16,082 - Loss: 0.2363, step: 26900
+INFO - dpsgd_diffusion.py - 2024-10-24 09:31:57,745 - Loss: 0.2369, step: 27000
+INFO - dpsgd_diffusion.py - 2024-10-24 09:33:39,991 - Loss: 0.2622, step: 27100
+INFO - dpsgd_diffusion.py - 2024-10-24 09:35:21,177 - Loss: 0.2491, step: 27200
+INFO - dpsgd_diffusion.py - 2024-10-24 09:37:01,670 - Loss: 0.2258, step: 27300
+INFO - dpsgd_diffusion.py - 2024-10-24 09:38:40,872 - Loss: 0.2418, step: 27400
+INFO - dpsgd_diffusion.py - 2024-10-24 09:39:38,498 - Eps-value after 39 epochs: 4.7110
+INFO - dpsgd_diffusion.py - 2024-10-24 09:40:23,059 - Loss: 0.2662, step: 27500
+INFO - dpsgd_diffusion.py - 2024-10-24 09:42:04,784 - Loss: 0.2258, step: 27600
+INFO - dpsgd_diffusion.py - 2024-10-24 09:43:48,126 - Loss: 0.2622, step: 27700
+INFO - dpsgd_diffusion.py - 2024-10-24 09:45:29,253 - Loss: 0.2337, step: 27800
+INFO - dpsgd_diffusion.py - 2024-10-24 09:47:09,912 - Loss: 0.2260, step: 27900
+INFO - dpsgd_diffusion.py - 2024-10-24 09:48:51,848 - Loss: 0.2275, step: 28000
+INFO - dpsgd_diffusion.py - 2024-10-24 09:48:51,902 - Saving snapshot checkpoint and sampling single batch at iteration 28000.
+WARNING - image.py - 2024-10-24 09:48:52,988 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 09:49:22,847 - FID at iteration 28000: 165.001692
+INFO - dpsgd_diffusion.py - 2024-10-24 09:51:04,175 - Loss: 0.2193, step: 28100
+INFO - dpsgd_diffusion.py - 2024-10-24 09:52:04,785 - Eps-value after 40 epochs: 4.7757
+INFO - dpsgd_diffusion.py - 2024-10-24 09:52:47,144 - Loss: 0.2307, step: 28200
+INFO - dpsgd_diffusion.py - 2024-10-24 09:54:27,229 - Loss: 0.2359, step: 28300
+INFO - dpsgd_diffusion.py - 2024-10-24 09:56:09,609 - Loss: 0.2256, step: 28400
+INFO - dpsgd_diffusion.py - 2024-10-24 09:57:52,028 - Loss: 0.2386, step: 28500
+INFO - dpsgd_diffusion.py - 2024-10-24 09:59:34,142 - Loss: 0.2230, step: 28600
+INFO - dpsgd_diffusion.py - 2024-10-24 10:01:15,044 - Loss: 0.2340, step: 28700
+INFO - dpsgd_diffusion.py - 2024-10-24 10:02:53,073 - Loss: 0.2321, step: 28800
+INFO - dpsgd_diffusion.py - 2024-10-24 10:04:00,080 - Eps-value after 41 epochs: 4.8396
+INFO - dpsgd_diffusion.py - 2024-10-24 10:04:38,279 - Loss: 0.2269, step: 28900
+INFO - dpsgd_diffusion.py - 2024-10-24 10:06:21,917 - Loss: 0.2236, step: 29000
+INFO - dpsgd_diffusion.py - 2024-10-24 10:08:04,606 - Loss: 0.2500, step: 29100
+INFO - dpsgd_diffusion.py - 2024-10-24 10:09:45,487 - Loss: 0.2586, step: 29200
+INFO - dpsgd_diffusion.py - 2024-10-24 10:11:28,076 - Loss: 0.2620, step: 29300
+INFO - dpsgd_diffusion.py - 2024-10-24 10:13:12,118 - Loss: 0.2591, step: 29400
+INFO - dpsgd_diffusion.py - 2024-10-24 10:14:56,367 - Loss: 0.2547, step: 29500
+INFO - dpsgd_diffusion.py - 2024-10-24 10:16:07,646 - Eps-value after 42 epochs: 4.9030
+INFO - dpsgd_diffusion.py - 2024-10-24 10:16:39,784 - Loss: 0.2640, step: 29600
+INFO - dpsgd_diffusion.py - 2024-10-24 10:18:19,550 - Loss: 0.2331, step: 29700
+INFO - dpsgd_diffusion.py - 2024-10-24 10:20:01,458 - Loss: 0.2438, step: 29800
+INFO - dpsgd_diffusion.py - 2024-10-24 10:21:45,505 - Loss: 0.2388, step: 29900
+INFO - dpsgd_diffusion.py - 2024-10-24 10:23:26,870 - Loss: 0.2505, step: 30000
+INFO - dpsgd_diffusion.py - 2024-10-24 10:23:26,927 - Saving snapshot checkpoint and sampling single batch at iteration 30000.
+WARNING - image.py - 2024-10-24 10:23:28,015 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 10:23:57,838 - FID at iteration 30000: 160.796514
+INFO - dpsgd_diffusion.py - 2024-10-24 10:25:40,066 - Loss: 0.2271, step: 30100
+INFO - dpsgd_diffusion.py - 2024-10-24 10:27:20,010 - Loss: 0.2292, step: 30200
+INFO - dpsgd_diffusion.py - 2024-10-24 10:28:33,108 - Eps-value after 43 epochs: 4.9656
+INFO - dpsgd_diffusion.py - 2024-10-24 10:29:03,127 - Loss: 0.2353, step: 30300
+INFO - dpsgd_diffusion.py - 2024-10-24 10:30:46,545 - Loss: 0.2381, step: 30400
+INFO - dpsgd_diffusion.py - 2024-10-24 10:32:26,505 - Loss: 0.2396, step: 30500
+INFO - dpsgd_diffusion.py - 2024-10-24 10:34:09,350 - Loss: 0.2501, step: 30600
+INFO - dpsgd_diffusion.py - 2024-10-24 10:35:50,859 - Loss: 0.2370, step: 30700
+INFO - dpsgd_diffusion.py - 2024-10-24 10:37:33,481 - Loss: 0.2393, step: 30800
+INFO - dpsgd_diffusion.py - 2024-10-24 10:39:16,224 - Loss: 0.2250, step: 30900
+INFO - dpsgd_diffusion.py - 2024-10-24 10:40:35,866 - Eps-value after 44 epochs: 5.0278
+INFO - dpsgd_diffusion.py - 2024-10-24 10:41:01,403 - Loss: 0.2268, step: 31000
+INFO - dpsgd_diffusion.py - 2024-10-24 10:42:42,183 - Loss: 0.2316, step: 31100
+INFO - dpsgd_diffusion.py - 2024-10-24 10:44:27,712 - Loss: 0.2350, step: 31200
+INFO - dpsgd_diffusion.py - 2024-10-24 10:46:08,393 - Loss: 0.2446, step: 31300
+INFO - dpsgd_diffusion.py - 2024-10-24 10:47:49,242 - Loss: 0.2094, step: 31400
+INFO - dpsgd_diffusion.py - 2024-10-24 10:49:33,916 - Loss: 0.2499, step: 31500
+INFO - dpsgd_diffusion.py - 2024-10-24 10:51:18,302 - Loss: 0.2233, step: 31600
+INFO - dpsgd_diffusion.py - 2024-10-24 10:52:41,975 - Eps-value after 45 epochs: 5.0892
+INFO - dpsgd_diffusion.py - 2024-10-24 10:53:02,598 - Loss: 0.2305, step: 31700
+INFO - dpsgd_diffusion.py - 2024-10-24 10:54:45,245 - Loss: 0.2198, step: 31800
+INFO - dpsgd_diffusion.py - 2024-10-24 10:56:26,586 - Loss: 0.2540, step: 31900
+INFO - dpsgd_diffusion.py - 2024-10-24 10:58:08,110 - Loss: 0.2596, step: 32000
+INFO - dpsgd_diffusion.py - 2024-10-24 10:58:08,120 - Saving snapshot checkpoint and sampling single batch at iteration 32000.
+WARNING - image.py - 2024-10-24 10:58:09,205 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 10:58:39,079 - FID at iteration 32000: 156.687614
+INFO - dpsgd_diffusion.py - 2024-10-24 11:00:20,407 - Loss: 0.2371, step: 32100
+INFO - dpsgd_diffusion.py - 2024-10-24 11:02:01,813 - Loss: 0.2351, step: 32200
+INFO - dpsgd_diffusion.py - 2024-10-24 11:03:44,501 - Loss: 0.2275, step: 32300
+INFO - dpsgd_diffusion.py - 2024-10-24 11:05:10,599 - Eps-value after 46 epochs: 5.1505
+INFO - dpsgd_diffusion.py - 2024-10-24 11:05:27,220 - Loss: 0.2299, step: 32400
+INFO - dpsgd_diffusion.py - 2024-10-24 11:07:09,690 - Loss: 0.2367, step: 32500
+INFO - dpsgd_diffusion.py - 2024-10-24 11:08:52,493 - Loss: 0.2351, step: 32600
+INFO - dpsgd_diffusion.py - 2024-10-24 11:10:34,899 - Loss: 0.2450, step: 32700
+INFO - dpsgd_diffusion.py - 2024-10-24 11:12:15,248 - Loss: 0.2381, step: 32800
+INFO - dpsgd_diffusion.py - 2024-10-24 11:13:54,917 - Loss: 0.2319, step: 32900
+INFO - dpsgd_diffusion.py - 2024-10-24 11:15:37,402 - Loss: 0.2433, step: 33000
+INFO - dpsgd_diffusion.py - 2024-10-24 11:17:05,567 - Eps-value after 47 epochs: 5.2106
+INFO - dpsgd_diffusion.py - 2024-10-24 11:17:17,884 - Loss: 0.2427, step: 33100
+INFO - dpsgd_diffusion.py - 2024-10-24 11:18:59,854 - Loss: 0.2437, step: 33200
+INFO - dpsgd_diffusion.py - 2024-10-24 11:20:43,947 - Loss: 0.2325, step: 33300
+INFO - dpsgd_diffusion.py - 2024-10-24 11:22:29,226 - Loss: 0.2400, step: 33400
+INFO - dpsgd_diffusion.py - 2024-10-24 11:24:13,836 - Loss: 0.2401, step: 33500
+INFO - dpsgd_diffusion.py - 2024-10-24 11:25:54,982 - Loss: 0.2235, step: 33600
+INFO - dpsgd_diffusion.py - 2024-10-24 11:27:38,011 - Loss: 0.2451, step: 33700
+INFO - dpsgd_diffusion.py - 2024-10-24 11:29:10,447 - Eps-value after 48 epochs: 5.2707
+INFO - dpsgd_diffusion.py - 2024-10-24 11:29:18,692 - Loss: 0.2597, step: 33800
+INFO - dpsgd_diffusion.py - 2024-10-24 11:31:00,000 - Loss: 0.2408, step: 33900
+INFO - dpsgd_diffusion.py - 2024-10-24 11:32:42,168 - Loss: 0.2542, step: 34000
+INFO - dpsgd_diffusion.py - 2024-10-24 11:32:42,225 - Saving snapshot checkpoint and sampling single batch at iteration 34000.
+WARNING - image.py - 2024-10-24 11:32:43,315 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 11:33:13,187 - FID at iteration 34000: 153.319840
+INFO - dpsgd_diffusion.py - 2024-10-24 11:34:54,910 - Loss: 0.2670, step: 34100
+INFO - dpsgd_diffusion.py - 2024-10-24 11:36:37,863 - Loss: 0.2385, step: 34200
+INFO - dpsgd_diffusion.py - 2024-10-24 11:38:23,323 - Loss: 0.2457, step: 34300
+INFO - dpsgd_diffusion.py - 2024-10-24 11:40:04,608 - Loss: 0.2171, step: 34400
+INFO - dpsgd_diffusion.py - 2024-10-24 11:41:41,261 - Eps-value after 49 epochs: 5.3302
+INFO - dpsgd_diffusion.py - 2024-10-24 11:41:45,382 - Loss: 0.2113, step: 34500
+INFO - dpsgd_diffusion.py - 2024-10-24 11:43:28,295 - Loss: 0.2326, step: 34600
+INFO - dpsgd_diffusion.py - 2024-10-24 11:45:07,433 - Loss: 0.2318, step: 34700
+INFO - dpsgd_diffusion.py - 2024-10-24 11:46:50,812 - Loss: 0.2550, step: 34800
+INFO - dpsgd_diffusion.py - 2024-10-24 11:48:32,036 - Loss: 0.2380, step: 34900
+INFO - dpsgd_diffusion.py - 2024-10-24 11:50:12,180 - Loss: 0.2413, step: 35000
+INFO - dpsgd_diffusion.py - 2024-10-24 11:51:54,724 - Loss: 0.2395, step: 35100
+INFO - dpsgd_diffusion.py - 2024-10-24 11:53:34,770 - Loss: 0.2458, step: 35200
+INFO - dpsgd_diffusion.py - 2024-10-24 11:53:34,788 - Eps-value after 50 epochs: 5.3890
+INFO - dpsgd_diffusion.py - 2024-10-24 11:55:17,664 - Loss: 0.2139, step: 35300
+INFO - dpsgd_diffusion.py - 2024-10-24 11:56:59,920 - Loss: 0.2485, step: 35400
+INFO - dpsgd_diffusion.py - 2024-10-24 11:58:42,385 - Loss: 0.2525, step: 35500
+INFO - dpsgd_diffusion.py - 2024-10-24 12:00:21,930 - Loss: 0.2328, step: 35600
+INFO - dpsgd_diffusion.py - 2024-10-24 12:02:02,644 - Loss: 0.2181, step: 35700
+INFO - dpsgd_diffusion.py - 2024-10-24 12:03:44,840 - Loss: 0.2626, step: 35800
+INFO - dpsgd_diffusion.py - 2024-10-24 12:05:27,237 - Loss: 0.2332, step: 35900
+INFO - dpsgd_diffusion.py - 2024-10-24 12:05:31,240 - Eps-value after 51 epochs: 5.4479
+INFO - dpsgd_diffusion.py - 2024-10-24 12:07:10,160 - Loss: 0.2481, step: 36000
+INFO - dpsgd_diffusion.py - 2024-10-24 12:07:10,215 - Saving snapshot checkpoint and sampling single batch at iteration 36000.
+WARNING - image.py - 2024-10-24 12:07:11,292 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 12:07:41,395 - FID at iteration 36000: 148.911313
+INFO - dpsgd_diffusion.py - 2024-10-24 12:09:23,373 - Loss: 0.2490, step: 36100
+INFO - dpsgd_diffusion.py - 2024-10-24 12:11:05,291 - Loss: 0.2638, step: 36200
+INFO - dpsgd_diffusion.py - 2024-10-24 12:12:48,249 - Loss: 0.2210, step: 36300
+INFO - dpsgd_diffusion.py - 2024-10-24 12:14:31,702 - Loss: 0.2226, step: 36400
+INFO - dpsgd_diffusion.py - 2024-10-24 12:16:12,788 - Loss: 0.2370, step: 36500
+INFO - dpsgd_diffusion.py - 2024-10-24 12:17:55,154 - Loss: 0.2098, step: 36600
+INFO - dpsgd_diffusion.py - 2024-10-24 12:18:03,474 - Eps-value after 52 epochs: 5.5056
+INFO - dpsgd_diffusion.py - 2024-10-24 12:19:38,117 - Loss: 0.2297, step: 36700
+INFO - dpsgd_diffusion.py - 2024-10-24 12:21:21,358 - Loss: 0.2296, step: 36800
+INFO - dpsgd_diffusion.py - 2024-10-24 12:23:04,717 - Loss: 0.2284, step: 36900
+INFO - dpsgd_diffusion.py - 2024-10-24 12:24:46,281 - Loss: 0.2334, step: 37000
+INFO - dpsgd_diffusion.py - 2024-10-24 12:26:27,134 - Loss: 0.2163, step: 37100
+INFO - dpsgd_diffusion.py - 2024-10-24 12:28:10,384 - Loss: 0.2255, step: 37200
+INFO - dpsgd_diffusion.py - 2024-10-24 12:29:48,593 - Loss: 0.2532, step: 37300
+INFO - dpsgd_diffusion.py - 2024-10-24 12:29:59,980 - Eps-value after 53 epochs: 5.5632
+INFO - dpsgd_diffusion.py - 2024-10-24 12:31:28,153 - Loss: 0.2413, step: 37400
+INFO - dpsgd_diffusion.py - 2024-10-24 12:33:09,044 - Loss: 0.2271, step: 37500
+INFO - dpsgd_diffusion.py - 2024-10-24 12:34:49,209 - Loss: 0.2269, step: 37600
+INFO - dpsgd_diffusion.py - 2024-10-24 12:36:30,061 - Loss: 0.2503, step: 37700
+INFO - dpsgd_diffusion.py - 2024-10-24 12:38:11,339 - Loss: 0.2351, step: 37800
+INFO - dpsgd_diffusion.py - 2024-10-24 12:39:53,219 - Loss: 0.2160, step: 37900
+INFO - dpsgd_diffusion.py - 2024-10-24 12:41:35,674 - Loss: 0.2337, step: 38000
+INFO - dpsgd_diffusion.py - 2024-10-24 12:41:35,687 - Saving snapshot checkpoint and sampling single batch at iteration 38000.
+WARNING - image.py - 2024-10-24 12:41:36,762 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 12:42:06,611 - FID at iteration 38000: 146.967761
+INFO - dpsgd_diffusion.py - 2024-10-24 12:42:22,913 - Eps-value after 54 epochs: 5.6207
+INFO - dpsgd_diffusion.py - 2024-10-24 12:43:47,422 - Loss: 0.2319, step: 38100
+INFO - dpsgd_diffusion.py - 2024-10-24 12:45:28,105 - Loss: 0.2484, step: 38200
+INFO - dpsgd_diffusion.py - 2024-10-24 12:47:09,067 - Loss: 0.2302, step: 38300
+INFO - dpsgd_diffusion.py - 2024-10-24 12:48:49,727 - Loss: 0.2336, step: 38400
+INFO - dpsgd_diffusion.py - 2024-10-24 12:50:33,643 - Loss: 0.2198, step: 38500
+INFO - dpsgd_diffusion.py - 2024-10-24 12:52:16,205 - Loss: 0.2521, step: 38600
+INFO - dpsgd_diffusion.py - 2024-10-24 12:54:00,935 - Loss: 0.2388, step: 38700
+INFO - dpsgd_diffusion.py - 2024-10-24 12:54:20,627 - Eps-value after 55 epochs: 5.6771
+INFO - dpsgd_diffusion.py - 2024-10-24 12:55:40,989 - Loss: 0.2123, step: 38800
+INFO - dpsgd_diffusion.py - 2024-10-24 12:57:23,459 - Loss: 0.2269, step: 38900
+INFO - dpsgd_diffusion.py - 2024-10-24 12:59:05,490 - Loss: 0.2190, step: 39000
+INFO - dpsgd_diffusion.py - 2024-10-24 13:00:44,806 - Loss: 0.2412, step: 39100
+INFO - dpsgd_diffusion.py - 2024-10-24 13:02:25,134 - Loss: 0.2294, step: 39200
+INFO - dpsgd_diffusion.py - 2024-10-24 13:04:05,481 - Loss: 0.2088, step: 39300
+INFO - dpsgd_diffusion.py - 2024-10-24 13:05:46,029 - Loss: 0.2386, step: 39400
+INFO - dpsgd_diffusion.py - 2024-10-24 13:06:10,329 - Eps-value after 56 epochs: 5.7335
+INFO - dpsgd_diffusion.py - 2024-10-24 13:07:28,345 - Loss: 0.2367, step: 39500
+INFO - dpsgd_diffusion.py - 2024-10-24 13:09:09,352 - Loss: 0.2475, step: 39600
+INFO - dpsgd_diffusion.py - 2024-10-24 13:10:51,881 - Loss: 0.2073, step: 39700
+INFO - dpsgd_diffusion.py - 2024-10-24 13:12:32,850 - Loss: 0.2426, step: 39800
+INFO - dpsgd_diffusion.py - 2024-10-24 13:14:13,131 - Loss: 0.2384, step: 39900
+INFO - dpsgd_diffusion.py - 2024-10-24 13:15:56,699 - Loss: 0.2504, step: 40000
+INFO - dpsgd_diffusion.py - 2024-10-24 13:15:56,709 - Saving snapshot checkpoint and sampling single batch at iteration 40000.
+WARNING - image.py - 2024-10-24 13:15:57,777 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 13:16:27,631 - FID at iteration 40000: 143.654813
+INFO - dpsgd_diffusion.py - 2024-10-24 13:18:10,869 - Loss: 0.2677, step: 40100
+INFO - dpsgd_diffusion.py - 2024-10-24 13:18:39,617 - Eps-value after 57 epochs: 5.7898
+INFO - dpsgd_diffusion.py - 2024-10-24 13:19:52,765 - Loss: 0.2556, step: 40200
+INFO - dpsgd_diffusion.py - 2024-10-24 13:21:34,131 - Loss: 0.2236, step: 40300
+INFO - dpsgd_diffusion.py - 2024-10-24 13:23:17,130 - Loss: 0.2245, step: 40400
+INFO - dpsgd_diffusion.py - 2024-10-24 13:24:59,608 - Loss: 0.2094, step: 40500
+INFO - dpsgd_diffusion.py - 2024-10-24 13:26:43,397 - Loss: 0.2370, step: 40600
+INFO - dpsgd_diffusion.py - 2024-10-24 13:28:28,373 - Loss: 0.2307, step: 40700
+INFO - dpsgd_diffusion.py - 2024-10-24 13:30:10,951 - Loss: 0.2230, step: 40800
+INFO - dpsgd_diffusion.py - 2024-10-24 13:30:43,927 - Eps-value after 58 epochs: 5.8450
+INFO - dpsgd_diffusion.py - 2024-10-24 13:31:53,951 - Loss: 0.2273, step: 40900
+INFO - dpsgd_diffusion.py - 2024-10-24 13:33:37,199 - Loss: 0.2281, step: 41000
+INFO - dpsgd_diffusion.py - 2024-10-24 13:35:19,352 - Loss: 0.2337, step: 41100
+INFO - dpsgd_diffusion.py - 2024-10-24 13:37:02,320 - Loss: 0.2307, step: 41200
+INFO - dpsgd_diffusion.py - 2024-10-24 13:38:44,341 - Loss: 0.2218, step: 41300
+INFO - dpsgd_diffusion.py - 2024-10-24 13:40:25,949 - Loss: 0.2148, step: 41400
+INFO - dpsgd_diffusion.py - 2024-10-24 13:42:10,228 - Loss: 0.2528, step: 41500
+INFO - dpsgd_diffusion.py - 2024-10-24 13:42:47,156 - Eps-value after 59 epochs: 5.9001
+INFO - dpsgd_diffusion.py - 2024-10-24 13:43:54,375 - Loss: 0.2328, step: 41600
+INFO - dpsgd_diffusion.py - 2024-10-24 13:45:37,220 - Loss: 0.2081, step: 41700
+INFO - dpsgd_diffusion.py - 2024-10-24 13:47:18,476 - Loss: 0.2427, step: 41800
+INFO - dpsgd_diffusion.py - 2024-10-24 13:48:59,578 - Loss: 0.2249, step: 41900
+INFO - dpsgd_diffusion.py - 2024-10-24 13:50:43,124 - Loss: 0.2271, step: 42000
+INFO - dpsgd_diffusion.py - 2024-10-24 13:50:43,136 - Saving snapshot checkpoint and sampling single batch at iteration 42000.
+WARNING - image.py - 2024-10-24 13:50:44,196 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 13:51:14,105 - FID at iteration 42000: 141.881275
+INFO - dpsgd_diffusion.py - 2024-10-24 13:52:57,095 - Loss: 0.2243, step: 42100
+INFO - dpsgd_diffusion.py - 2024-10-24 13:54:37,864 - Loss: 0.2316, step: 42200
+INFO - dpsgd_diffusion.py - 2024-10-24 13:55:17,739 - Eps-value after 60 epochs: 5.9553
+INFO - dpsgd_diffusion.py - 2024-10-24 13:56:18,821 - Loss: 0.2293, step: 42300
+INFO - dpsgd_diffusion.py - 2024-10-24 13:58:01,053 - Loss: 0.2192, step: 42400
+INFO - dpsgd_diffusion.py - 2024-10-24 13:59:42,868 - Loss: 0.2053, step: 42500
+INFO - dpsgd_diffusion.py - 2024-10-24 14:01:23,564 - Loss: 0.2413, step: 42600
+INFO - dpsgd_diffusion.py - 2024-10-24 14:03:03,911 - Loss: 0.2343, step: 42700
+INFO - dpsgd_diffusion.py - 2024-10-24 14:04:42,107 - Loss: 0.2139, step: 42800
+INFO - dpsgd_diffusion.py - 2024-10-24 14:06:24,596 - Loss: 0.2220, step: 42900
+INFO - dpsgd_diffusion.py - 2024-10-24 14:07:09,987 - Eps-value after 61 epochs: 6.0095
+INFO - dpsgd_diffusion.py - 2024-10-24 14:08:08,273 - Loss: 0.2194, step: 43000
+INFO - dpsgd_diffusion.py - 2024-10-24 14:09:52,595 - Loss: 0.2187, step: 43100
+INFO - dpsgd_diffusion.py - 2024-10-24 14:11:36,816 - Loss: 0.2257, step: 43200
+INFO - dpsgd_diffusion.py - 2024-10-24 14:13:19,947 - Loss: 0.2142, step: 43300
+INFO - dpsgd_diffusion.py - 2024-10-24 14:15:00,363 - Loss: 0.2253, step: 43400
+INFO - dpsgd_diffusion.py - 2024-10-24 14:16:40,965 - Loss: 0.2359, step: 43500
+INFO - dpsgd_diffusion.py - 2024-10-24 14:18:21,266 - Loss: 0.2034, step: 43600
+INFO - dpsgd_diffusion.py - 2024-10-24 14:19:11,251 - Eps-value after 62 epochs: 6.0635
+INFO - dpsgd_diffusion.py - 2024-10-24 14:20:03,834 - Loss: 0.2346, step: 43700
+INFO - dpsgd_diffusion.py - 2024-10-24 14:21:46,588 - Loss: 0.2409, step: 43800
+INFO - dpsgd_diffusion.py - 2024-10-24 14:23:31,200 - Loss: 0.2300, step: 43900
+INFO - dpsgd_diffusion.py - 2024-10-24 14:25:14,321 - Loss: 0.2266, step: 44000
+INFO - dpsgd_diffusion.py - 2024-10-24 14:25:14,333 - Saving snapshot checkpoint and sampling single batch at iteration 44000.
+WARNING - image.py - 2024-10-24 14:25:15,448 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 14:25:45,347 - FID at iteration 44000: 139.502335
+INFO - dpsgd_diffusion.py - 2024-10-24 14:27:27,785 - Loss: 0.2232, step: 44100
+INFO - dpsgd_diffusion.py - 2024-10-24 14:29:10,196 - Loss: 0.2243, step: 44200
+INFO - dpsgd_diffusion.py - 2024-10-24 14:30:53,904 - Loss: 0.2277, step: 44300
+INFO - dpsgd_diffusion.py - 2024-10-24 14:31:47,542 - Eps-value after 63 epochs: 6.1174
+INFO - dpsgd_diffusion.py - 2024-10-24 14:32:36,913 - Loss: 0.2499, step: 44400
+INFO - dpsgd_diffusion.py - 2024-10-24 14:34:20,443 - Loss: 0.2294, step: 44500
+INFO - dpsgd_diffusion.py - 2024-10-24 14:36:02,070 - Loss: 0.2376, step: 44600
+INFO - dpsgd_diffusion.py - 2024-10-24 14:37:46,918 - Loss: 0.2252, step: 44700
+INFO - dpsgd_diffusion.py - 2024-10-24 14:39:29,119 - Loss: 0.2440, step: 44800
+INFO - dpsgd_diffusion.py - 2024-10-24 14:41:13,262 - Loss: 0.2281, step: 44900
+INFO - dpsgd_diffusion.py - 2024-10-24 14:42:55,548 - Loss: 0.2200, step: 45000
+INFO - dpsgd_diffusion.py - 2024-10-24 14:43:53,187 - Eps-value after 64 epochs: 6.1711
+INFO - dpsgd_diffusion.py - 2024-10-24 14:44:38,224 - Loss: 0.2303, step: 45100
+INFO - dpsgd_diffusion.py - 2024-10-24 14:46:19,228 - Loss: 0.2149, step: 45200
+INFO - dpsgd_diffusion.py - 2024-10-24 14:48:00,127 - Loss: 0.2382, step: 45300
+INFO - dpsgd_diffusion.py - 2024-10-24 14:49:43,905 - Loss: 0.2641, step: 45400
+INFO - dpsgd_diffusion.py - 2024-10-24 14:51:24,618 - Loss: 0.2359, step: 45500
+INFO - dpsgd_diffusion.py - 2024-10-24 14:53:08,954 - Loss: 0.2390, step: 45600
+INFO - dpsgd_diffusion.py - 2024-10-24 14:54:49,215 - Loss: 0.2402, step: 45700
+INFO - dpsgd_diffusion.py - 2024-10-24 14:55:50,103 - Eps-value after 65 epochs: 6.2238
+INFO - dpsgd_diffusion.py - 2024-10-24 14:56:31,297 - Loss: 0.2188, step: 45800
+INFO - dpsgd_diffusion.py - 2024-10-24 14:58:11,555 - Loss: 0.2214, step: 45900
+INFO - dpsgd_diffusion.py - 2024-10-24 14:59:54,152 - Loss: 0.2264, step: 46000
+INFO - dpsgd_diffusion.py - 2024-10-24 14:59:54,158 - Saving snapshot checkpoint and sampling single batch at iteration 46000.
+WARNING - image.py - 2024-10-24 14:59:55,453 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 15:00:25,334 - FID at iteration 46000: 137.862454
+INFO - dpsgd_diffusion.py - 2024-10-24 15:02:05,951 - Loss: 0.2339, step: 46100
+INFO - dpsgd_diffusion.py - 2024-10-24 15:03:46,564 - Loss: 0.2584, step: 46200
+INFO - dpsgd_diffusion.py - 2024-10-24 15:05:28,711 - Loss: 0.2318, step: 46300
+INFO - dpsgd_diffusion.py - 2024-10-24 15:07:09,899 - Loss: 0.2207, step: 46400
+INFO - dpsgd_diffusion.py - 2024-10-24 15:08:15,802 - Eps-value after 66 epochs: 6.2766
+INFO - dpsgd_diffusion.py - 2024-10-24 15:08:52,907 - Loss: 0.2269, step: 46500
+INFO - dpsgd_diffusion.py - 2024-10-24 15:10:34,445 - Loss: 0.2434, step: 46600
+INFO - dpsgd_diffusion.py - 2024-10-24 15:12:18,245 - Loss: 0.2207, step: 46700
+INFO - dpsgd_diffusion.py - 2024-10-24 15:13:59,026 - Loss: 0.2261, step: 46800
+INFO - dpsgd_diffusion.py - 2024-10-24 15:15:41,316 - Loss: 0.2308, step: 46900
+INFO - dpsgd_diffusion.py - 2024-10-24 15:17:24,944 - Loss: 0.2499, step: 47000
+INFO - dpsgd_diffusion.py - 2024-10-24 15:19:05,325 - Loss: 0.2230, step: 47100
+INFO - dpsgd_diffusion.py - 2024-10-24 15:20:14,697 - Eps-value after 67 epochs: 6.3293
+INFO - dpsgd_diffusion.py - 2024-10-24 15:20:48,964 - Loss: 0.2271, step: 47200
+INFO - dpsgd_diffusion.py - 2024-10-24 15:22:32,067 - Loss: 0.2355, step: 47300
+INFO - dpsgd_diffusion.py - 2024-10-24 15:24:16,303 - Loss: 0.2389, step: 47400
+INFO - dpsgd_diffusion.py - 2024-10-24 15:25:58,453 - Loss: 0.2252, step: 47500
+INFO - dpsgd_diffusion.py - 2024-10-24 15:27:39,164 - Loss: 0.2140, step: 47600
+INFO - dpsgd_diffusion.py - 2024-10-24 15:29:19,985 - Loss: 0.2136, step: 47700
+INFO - dpsgd_diffusion.py - 2024-10-24 15:31:01,645 - Loss: 0.2212, step: 47800
+INFO - dpsgd_diffusion.py - 2024-10-24 15:32:14,268 - Eps-value after 68 epochs: 6.3816
+INFO - dpsgd_diffusion.py - 2024-10-24 15:32:43,081 - Loss: 0.2131, step: 47900
+INFO - dpsgd_diffusion.py - 2024-10-24 15:34:26,541 - Loss: 0.2148, step: 48000
+INFO - dpsgd_diffusion.py - 2024-10-24 15:34:26,551 - Saving snapshot checkpoint and sampling single batch at iteration 48000.
+WARNING - image.py - 2024-10-24 15:34:27,644 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 15:34:57,126 - FID at iteration 48000: 135.503852
+INFO - dpsgd_diffusion.py - 2024-10-24 15:36:39,510 - Loss: 0.2271, step: 48100
+INFO - dpsgd_diffusion.py - 2024-10-24 15:38:21,530 - Loss: 0.2338, step: 48200
+INFO - dpsgd_diffusion.py - 2024-10-24 15:40:03,584 - Loss: 0.2240, step: 48300
+INFO - dpsgd_diffusion.py - 2024-10-24 15:41:45,420 - Loss: 0.2387, step: 48400
+INFO - dpsgd_diffusion.py - 2024-10-24 15:43:28,181 - Loss: 0.2231, step: 48500
+INFO - dpsgd_diffusion.py - 2024-10-24 15:44:46,882 - Eps-value after 69 epochs: 6.4332
+INFO - dpsgd_diffusion.py - 2024-10-24 15:45:12,161 - Loss: 0.2210, step: 48600
+INFO - dpsgd_diffusion.py - 2024-10-24 15:46:55,253 - Loss: 0.2236, step: 48700
+INFO - dpsgd_diffusion.py - 2024-10-24 15:48:40,184 - Loss: 0.2300, step: 48800
+INFO - dpsgd_diffusion.py - 2024-10-24 15:50:21,040 - Loss: 0.2181, step: 48900
+INFO - dpsgd_diffusion.py - 2024-10-24 15:52:01,441 - Loss: 0.2117, step: 49000
+INFO - dpsgd_diffusion.py - 2024-10-24 15:53:42,722 - Loss: 0.2254, step: 49100
+INFO - dpsgd_diffusion.py - 2024-10-24 15:55:25,615 - Loss: 0.2241, step: 49200
+INFO - dpsgd_diffusion.py - 2024-10-24 15:56:45,685 - Eps-value after 70 epochs: 6.4847
+INFO - dpsgd_diffusion.py - 2024-10-24 15:57:06,320 - Loss: 0.2133, step: 49300
+INFO - dpsgd_diffusion.py - 2024-10-24 15:58:46,302 - Loss: 0.2130, step: 49400
+INFO - dpsgd_diffusion.py - 2024-10-24 16:00:28,282 - Loss: 0.2265, step: 49500
+INFO - dpsgd_diffusion.py - 2024-10-24 16:02:11,330 - Loss: 0.2559, step: 49600
+INFO - dpsgd_diffusion.py - 2024-10-24 16:03:55,849 - Loss: 0.2333, step: 49700
+INFO - dpsgd_diffusion.py - 2024-10-24 16:05:37,345 - Loss: 0.2214, step: 49800
+INFO - dpsgd_diffusion.py - 2024-10-24 16:07:20,337 - Loss: 0.2222, step: 49900
+INFO - dpsgd_diffusion.py - 2024-10-24 16:08:47,251 - Eps-value after 71 epochs: 6.5362
+INFO - dpsgd_diffusion.py - 2024-10-24 16:09:03,730 - Loss: 0.2382, step: 50000
+INFO - dpsgd_diffusion.py - 2024-10-24 16:09:03,740 - Saving snapshot checkpoint and sampling single batch at iteration 50000.
+WARNING - image.py - 2024-10-24 16:09:04,933 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 16:09:34,802 - FID at iteration 50000: 133.870146
+INFO - dpsgd_diffusion.py - 2024-10-24 16:11:15,720 - Loss: 0.2298, step: 50100
+INFO - dpsgd_diffusion.py - 2024-10-24 16:12:56,857 - Loss: 0.2319, step: 50200
+INFO - dpsgd_diffusion.py - 2024-10-24 16:14:38,137 - Loss: 0.2197, step: 50300
+INFO - dpsgd_diffusion.py - 2024-10-24 16:16:20,186 - Loss: 0.2156, step: 50400
+INFO - dpsgd_diffusion.py - 2024-10-24 16:17:59,887 - Loss: 0.2287, step: 50500
+INFO - dpsgd_diffusion.py - 2024-10-24 16:19:43,065 - Loss: 0.2179, step: 50600
+INFO - dpsgd_diffusion.py - 2024-10-24 16:21:13,301 - Eps-value after 72 epochs: 6.5876
+INFO - dpsgd_diffusion.py - 2024-10-24 16:21:25,669 - Loss: 0.2375, step: 50700
+INFO - dpsgd_diffusion.py - 2024-10-24 16:23:08,536 - Loss: 0.2120, step: 50800
+INFO - dpsgd_diffusion.py - 2024-10-24 16:24:50,209 - Loss: 0.2263, step: 50900
+INFO - dpsgd_diffusion.py - 2024-10-24 16:26:31,993 - Loss: 0.2267, step: 51000
+INFO - dpsgd_diffusion.py - 2024-10-24 16:28:15,963 - Loss: 0.2236, step: 51100
+INFO - dpsgd_diffusion.py - 2024-10-24 16:29:57,346 - Loss: 0.2253, step: 51200
+INFO - dpsgd_diffusion.py - 2024-10-24 16:31:39,430 - Loss: 0.2155, step: 51300
+INFO - dpsgd_diffusion.py - 2024-10-24 16:33:14,950 - Eps-value after 73 epochs: 6.6379
+INFO - dpsgd_diffusion.py - 2024-10-24 16:33:23,521 - Loss: 0.2384, step: 51400
+INFO - dpsgd_diffusion.py - 2024-10-24 16:35:08,244 - Loss: 0.2161, step: 51500
+INFO - dpsgd_diffusion.py - 2024-10-24 16:36:48,243 - Loss: 0.2137, step: 51600
+INFO - dpsgd_diffusion.py - 2024-10-24 16:38:28,283 - Loss: 0.2194, step: 51700
+INFO - dpsgd_diffusion.py - 2024-10-24 16:40:11,208 - Loss: 0.2134, step: 51800
+INFO - dpsgd_diffusion.py - 2024-10-24 16:41:55,926 - Loss: 0.2210, step: 51900
+INFO - dpsgd_diffusion.py - 2024-10-24 16:43:37,165 - Loss: 0.2245, step: 52000
+INFO - dpsgd_diffusion.py - 2024-10-24 16:43:37,218 - Saving snapshot checkpoint and sampling single batch at iteration 52000.
+WARNING - image.py - 2024-10-24 16:43:38,319 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 16:44:08,179 - FID at iteration 52000: 133.328683
+INFO - dpsgd_diffusion.py - 2024-10-24 16:45:42,583 - Eps-value after 74 epochs: 6.6882
+INFO - dpsgd_diffusion.py - 2024-10-24 16:45:46,707 - Loss: 0.2135, step: 52100
+INFO - dpsgd_diffusion.py - 2024-10-24 16:47:29,407 - Loss: 0.2339, step: 52200
+INFO - dpsgd_diffusion.py - 2024-10-24 16:49:11,139 - Loss: 0.2254, step: 52300
+INFO - dpsgd_diffusion.py - 2024-10-24 16:50:54,852 - Loss: 0.2193, step: 52400
+INFO - dpsgd_diffusion.py - 2024-10-24 16:52:36,975 - Loss: 0.2556, step: 52500
+INFO - dpsgd_diffusion.py - 2024-10-24 16:54:19,170 - Loss: 0.2379, step: 52600
+INFO - dpsgd_diffusion.py - 2024-10-24 16:56:00,277 - Loss: 0.2321, step: 52700
+INFO - dpsgd_diffusion.py - 2024-10-24 16:57:44,151 - Loss: 0.2299, step: 52800
+INFO - dpsgd_diffusion.py - 2024-10-24 16:57:44,169 - Eps-value after 75 epochs: 6.7385
+INFO - dpsgd_diffusion.py - 2024-10-24 16:59:26,818 - Loss: 0.2310, step: 52900
+INFO - dpsgd_diffusion.py - 2024-10-24 17:01:12,503 - Loss: 0.2495, step: 53000
+INFO - dpsgd_diffusion.py - 2024-10-24 17:02:57,857 - Loss: 0.1984, step: 53100
+INFO - dpsgd_diffusion.py - 2024-10-24 17:04:42,002 - Loss: 0.2089, step: 53200
+INFO - dpsgd_diffusion.py - 2024-10-24 17:06:23,577 - Loss: 0.2140, step: 53300
+INFO - dpsgd_diffusion.py - 2024-10-24 17:08:07,039 - Loss: 0.2121, step: 53400
+INFO - dpsgd_diffusion.py - 2024-10-24 17:09:49,680 - Loss: 0.2364, step: 53500
+INFO - dpsgd_diffusion.py - 2024-10-24 17:09:53,643 - Eps-value after 76 epochs: 6.7888
+INFO - dpsgd_diffusion.py - 2024-10-24 17:11:28,909 - Loss: 0.2525, step: 53600
+INFO - dpsgd_diffusion.py - 2024-10-24 17:13:11,193 - Loss: 0.2114, step: 53700
+INFO - dpsgd_diffusion.py - 2024-10-24 17:14:53,873 - Loss: 0.2082, step: 53800
+INFO - dpsgd_diffusion.py - 2024-10-24 17:16:34,689 - Loss: 0.2316, step: 53900
+INFO - dpsgd_diffusion.py - 2024-10-24 17:18:15,036 - Loss: 0.2157, step: 54000
+INFO - dpsgd_diffusion.py - 2024-10-24 17:18:15,045 - Saving snapshot checkpoint and sampling single batch at iteration 54000.
+WARNING - image.py - 2024-10-24 17:18:16,140 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 17:18:45,966 - FID at iteration 54000: 132.143802
+INFO - dpsgd_diffusion.py - 2024-10-24 17:20:27,198 - Loss: 0.2282, step: 54100
+INFO - dpsgd_diffusion.py - 2024-10-24 17:22:08,544 - Loss: 0.2286, step: 54200
+INFO - dpsgd_diffusion.py - 2024-10-24 17:22:16,437 - Eps-value after 77 epochs: 6.8385
+INFO - dpsgd_diffusion.py - 2024-10-24 17:23:50,441 - Loss: 0.2202, step: 54300
+INFO - dpsgd_diffusion.py - 2024-10-24 17:25:34,616 - Loss: 0.2292, step: 54400
+INFO - dpsgd_diffusion.py - 2024-10-24 17:27:14,778 - Loss: 0.2111, step: 54500
+INFO - dpsgd_diffusion.py - 2024-10-24 17:28:56,223 - Loss: 0.2196, step: 54600
+INFO - dpsgd_diffusion.py - 2024-10-24 17:30:39,031 - Loss: 0.2398, step: 54700
+INFO - dpsgd_diffusion.py - 2024-10-24 17:32:22,430 - Loss: 0.2271, step: 54800
+INFO - dpsgd_diffusion.py - 2024-10-24 17:34:02,019 - Loss: 0.2068, step: 54900
+INFO - dpsgd_diffusion.py - 2024-10-24 17:34:13,822 - Eps-value after 78 epochs: 6.8876
+INFO - dpsgd_diffusion.py - 2024-10-24 17:35:42,603 - Loss: 0.2174, step: 55000
+INFO - dpsgd_diffusion.py - 2024-10-24 17:37:26,042 - Loss: 0.2016, step: 55100
+INFO - dpsgd_diffusion.py - 2024-10-24 17:39:08,748 - Loss: 0.2279, step: 55200
+INFO - dpsgd_diffusion.py - 2024-10-24 17:40:52,945 - Loss: 0.2053, step: 55300
+INFO - dpsgd_diffusion.py - 2024-10-24 17:42:35,479 - Loss: 0.2273, step: 55400
+INFO - dpsgd_diffusion.py - 2024-10-24 17:44:17,766 - Loss: 0.2044, step: 55500
+INFO - dpsgd_diffusion.py - 2024-10-24 17:46:00,660 - Loss: 0.2325, step: 55600
+INFO - dpsgd_diffusion.py - 2024-10-24 17:46:16,406 - Eps-value after 79 epochs: 6.9367
+INFO - dpsgd_diffusion.py - 2024-10-24 17:47:42,715 - Loss: 0.2262, step: 55700
+INFO - dpsgd_diffusion.py - 2024-10-24 17:49:25,280 - Loss: 0.2119, step: 55800
+INFO - dpsgd_diffusion.py - 2024-10-24 17:51:09,616 - Loss: 0.2290, step: 55900
+INFO - dpsgd_diffusion.py - 2024-10-24 17:52:51,670 - Loss: 0.2118, step: 56000
+INFO - dpsgd_diffusion.py - 2024-10-24 17:52:51,680 - Saving snapshot checkpoint and sampling single batch at iteration 56000.
+WARNING - image.py - 2024-10-24 17:52:52,791 - 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 - 2024-10-24 17:53:22,680 - FID at iteration 56000: 130.419367
+INFO - dpsgd_diffusion.py - 2024-10-24 17:55:06,419 - Loss: 0.2440, step: 56100
+INFO - dpsgd_diffusion.py - 2024-10-24 17:56:50,721 - Loss: 0.2329, step: 56200
+INFO - dpsgd_diffusion.py - 2024-10-24 17:58:33,742 - Loss: 0.2098, step: 56300
+INFO - dpsgd_diffusion.py - 2024-10-24 17:58:54,424 - Eps-value after 80 epochs: 6.9858
+INFO - dpsgd_diffusion.py - 2024-10-24 18:00:17,790 - Loss: 0.2273, step: 56400
+INFO - dpsgd_diffusion.py - 2024-10-24 18:02:00,444 - Loss: 0.2349, step: 56500
+INFO - dpsgd_diffusion.py - 2024-10-24 18:03:45,212 - Loss: 0.2622, step: 56600
+INFO - dpsgd_diffusion.py - 2024-10-24 18:05:25,853 - Loss: 0.2117, step: 56700
+INFO - dpsgd_diffusion.py - 2024-10-24 18:07:09,523 - Loss: 0.2274, step: 56800
+INFO - dpsgd_diffusion.py - 2024-10-24 18:08:52,971 - Loss: 0.2279, step: 56900
+INFO - dpsgd_diffusion.py - 2024-10-24 18:10:34,901 - Loss: 0.2144, step: 57000
+INFO - dpsgd_diffusion.py - 2024-10-24 18:10:59,362 - Eps-value after 81 epochs: 7.0349
+INFO - dpsgd_diffusion.py - 2024-10-24 18:12:16,831 - Loss: 0.2209, step: 57100
+INFO - dpsgd_diffusion.py - 2024-10-24 18:13:58,718 - Loss: 0.2190, step: 57200
+INFO - dpsgd_diffusion.py - 2024-10-24 18:15:41,082 - Loss: 0.2393, step: 57300
+INFO - dpsgd_diffusion.py - 2024-10-24 18:17:22,005 - Loss: 0.2088, step: 57400
+INFO - dpsgd_diffusion.py - 2024-10-24 18:18:59,244 - Loss: 0.2164, step: 57500
+INFO - dpsgd_diffusion.py - 2024-10-24 18:20:38,440 - Loss: 0.2143, step: 57600
+INFO - dpsgd_diffusion.py - 2024-10-24 18:22:21,674 - Loss: 0.2260, step: 57700
+INFO - dpsgd_diffusion.py - 2024-10-24 18:22:50,585 - Eps-value after 82 epochs: 7.0835
+INFO - dpsgd_diffusion.py - 2024-10-24 18:24:04,686 - Loss: 0.2322, step: 57800
+INFO - dpsgd_diffusion.py - 2024-10-24 18:25:47,362 - Loss: 0.2223, step: 57900
+INFO - dpsgd_diffusion.py - 2024-10-24 18:27:29,445 - Loss: 0.2230, step: 58000
+INFO - dpsgd_diffusion.py - 2024-10-24 18:27:29,454 - Saving snapshot checkpoint and sampling single batch at iteration 58000.
+WARNING - image.py - 2024-10-24 18:27:30,517 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 18:28:00,810 - FID at iteration 58000: 130.667816
+INFO - dpsgd_diffusion.py - 2024-10-24 18:29:42,107 - Loss: 0.2022, step: 58100
+INFO - dpsgd_diffusion.py - 2024-10-24 18:31:25,353 - Loss: 0.2127, step: 58200
+INFO - dpsgd_diffusion.py - 2024-10-24 18:33:07,118 - Loss: 0.2268, step: 58300
+INFO - dpsgd_diffusion.py - 2024-10-24 18:34:51,049 - Loss: 0.2194, step: 58400
+INFO - dpsgd_diffusion.py - 2024-10-24 18:35:23,445 - Eps-value after 83 epochs: 7.1314
+INFO - dpsgd_diffusion.py - 2024-10-24 18:36:34,128 - Loss: 0.2197, step: 58500
+INFO - dpsgd_diffusion.py - 2024-10-24 18:38:14,942 - Loss: 0.2257, step: 58600
+INFO - dpsgd_diffusion.py - 2024-10-24 18:39:57,527 - Loss: 0.2251, step: 58700
+INFO - dpsgd_diffusion.py - 2024-10-24 18:41:40,399 - Loss: 0.2139, step: 58800
+INFO - dpsgd_diffusion.py - 2024-10-24 18:43:23,679 - Loss: 0.2338, step: 58900
+INFO - dpsgd_diffusion.py - 2024-10-24 18:45:09,471 - Loss: 0.2301, step: 59000
+INFO - dpsgd_diffusion.py - 2024-10-24 18:46:51,577 - Loss: 0.2161, step: 59100
+INFO - dpsgd_diffusion.py - 2024-10-24 18:47:28,519 - Eps-value after 84 epochs: 7.1793
+INFO - dpsgd_diffusion.py - 2024-10-24 18:48:35,718 - Loss: 0.2089, step: 59200
+INFO - dpsgd_diffusion.py - 2024-10-24 18:50:18,706 - Loss: 0.2141, step: 59300
+INFO - dpsgd_diffusion.py - 2024-10-24 18:52:00,604 - Loss: 0.2097, step: 59400
+INFO - dpsgd_diffusion.py - 2024-10-24 18:53:40,996 - Loss: 0.2203, step: 59500
+INFO - dpsgd_diffusion.py - 2024-10-24 18:55:22,343 - Loss: 0.2218, step: 59600
+INFO - dpsgd_diffusion.py - 2024-10-24 18:57:03,973 - Loss: 0.2188, step: 59700
+INFO - dpsgd_diffusion.py - 2024-10-24 18:58:46,518 - Loss: 0.2160, step: 59800
+INFO - dpsgd_diffusion.py - 2024-10-24 18:59:25,827 - Eps-value after 85 epochs: 7.2272
+INFO - dpsgd_diffusion.py - 2024-10-24 19:00:27,272 - Loss: 0.2107, step: 59900
+INFO - dpsgd_diffusion.py - 2024-10-24 19:02:08,694 - Loss: 0.2189, step: 60000
+INFO - dpsgd_diffusion.py - 2024-10-24 19:02:08,703 - Saving snapshot checkpoint and sampling single batch at iteration 60000.
+WARNING - image.py - 2024-10-24 19:02:09,910 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 19:02:39,828 - FID at iteration 60000: 128.141214
+INFO - dpsgd_diffusion.py - 2024-10-24 19:04:21,454 - Loss: 0.2062, step: 60100
+INFO - dpsgd_diffusion.py - 2024-10-24 19:06:05,210 - Loss: 0.2214, step: 60200
+INFO - dpsgd_diffusion.py - 2024-10-24 19:07:45,345 - Loss: 0.2252, step: 60300
+INFO - dpsgd_diffusion.py - 2024-10-24 19:09:27,234 - Loss: 0.2247, step: 60400
+INFO - dpsgd_diffusion.py - 2024-10-24 19:11:08,849 - Loss: 0.2360, step: 60500
+INFO - dpsgd_diffusion.py - 2024-10-24 19:11:52,122 - Eps-value after 86 epochs: 7.2751
+INFO - dpsgd_diffusion.py - 2024-10-24 19:12:48,130 - Loss: 0.2403, step: 60600
+INFO - dpsgd_diffusion.py - 2024-10-24 19:14:31,118 - Loss: 0.2187, step: 60700
+INFO - dpsgd_diffusion.py - 2024-10-24 19:16:13,657 - Loss: 0.2294, step: 60800
+INFO - dpsgd_diffusion.py - 2024-10-24 19:17:57,456 - Loss: 0.2047, step: 60900
+INFO - dpsgd_diffusion.py - 2024-10-24 19:19:40,014 - Loss: 0.2259, step: 61000
+INFO - dpsgd_diffusion.py - 2024-10-24 19:21:21,928 - Loss: 0.2278, step: 61100
+INFO - dpsgd_diffusion.py - 2024-10-24 19:23:02,600 - Loss: 0.2166, step: 61200
+INFO - dpsgd_diffusion.py - 2024-10-24 19:23:51,704 - Eps-value after 87 epochs: 7.3230
+INFO - dpsgd_diffusion.py - 2024-10-24 19:24:45,243 - Loss: 0.2164, step: 61300
+INFO - dpsgd_diffusion.py - 2024-10-24 19:26:27,633 - Loss: 0.2373, step: 61400
+INFO - dpsgd_diffusion.py - 2024-10-24 19:28:09,246 - Loss: 0.2133, step: 61500
+INFO - dpsgd_diffusion.py - 2024-10-24 19:29:48,845 - Loss: 0.2221, step: 61600
+INFO - dpsgd_diffusion.py - 2024-10-24 19:31:31,368 - Loss: 0.2209, step: 61700
+INFO - dpsgd_diffusion.py - 2024-10-24 19:33:11,953 - Loss: 0.2124, step: 61800
+INFO - dpsgd_diffusion.py - 2024-10-24 19:34:53,752 - Loss: 0.2267, step: 61900
+INFO - dpsgd_diffusion.py - 2024-10-24 19:35:47,233 - Eps-value after 88 epochs: 7.3698
+INFO - dpsgd_diffusion.py - 2024-10-24 19:36:36,483 - Loss: 0.1927, step: 62000
+INFO - dpsgd_diffusion.py - 2024-10-24 19:36:36,493 - Saving snapshot checkpoint and sampling single batch at iteration 62000.
+WARNING - image.py - 2024-10-24 19:36:37,549 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 19:37:07,608 - FID at iteration 62000: 127.553086
+INFO - dpsgd_diffusion.py - 2024-10-24 19:38:49,528 - Loss: 0.2297, step: 62100
+INFO - dpsgd_diffusion.py - 2024-10-24 19:40:31,345 - Loss: 0.2191, step: 62200
+INFO - dpsgd_diffusion.py - 2024-10-24 19:42:11,959 - Loss: 0.2225, step: 62300
+INFO - dpsgd_diffusion.py - 2024-10-24 19:43:52,499 - Loss: 0.2281, step: 62400
+INFO - dpsgd_diffusion.py - 2024-10-24 19:45:35,046 - Loss: 0.2179, step: 62500
+INFO - dpsgd_diffusion.py - 2024-10-24 19:47:16,863 - Loss: 0.2011, step: 62600
+INFO - dpsgd_diffusion.py - 2024-10-24 19:48:13,923 - Eps-value after 89 epochs: 7.4165
+INFO - dpsgd_diffusion.py - 2024-10-24 19:48:58,917 - Loss: 0.2054, step: 62700
+INFO - dpsgd_diffusion.py - 2024-10-24 19:50:38,979 - Loss: 0.2365, step: 62800
+INFO - dpsgd_diffusion.py - 2024-10-24 19:52:20,186 - Loss: 0.2247, step: 62900
+INFO - dpsgd_diffusion.py - 2024-10-24 19:54:02,982 - Loss: 0.2228, step: 63000
+INFO - dpsgd_diffusion.py - 2024-10-24 19:55:44,694 - Loss: 0.2281, step: 63100
+INFO - dpsgd_diffusion.py - 2024-10-24 19:57:26,603 - Loss: 0.2104, step: 63200
+INFO - dpsgd_diffusion.py - 2024-10-24 19:59:08,592 - Loss: 0.2123, step: 63300
+INFO - dpsgd_diffusion.py - 2024-10-24 20:00:10,899 - Eps-value after 90 epochs: 7.4632
+INFO - dpsgd_diffusion.py - 2024-10-24 20:00:52,010 - Loss: 0.2309, step: 63400
+INFO - dpsgd_diffusion.py - 2024-10-24 20:02:34,019 - Loss: 0.2517, step: 63500
+INFO - dpsgd_diffusion.py - 2024-10-24 20:04:16,656 - Loss: 0.2088, step: 63600
+INFO - dpsgd_diffusion.py - 2024-10-24 20:06:00,004 - Loss: 0.2158, step: 63700
+INFO - dpsgd_diffusion.py - 2024-10-24 20:07:43,327 - Loss: 0.2377, step: 63800
+INFO - dpsgd_diffusion.py - 2024-10-24 20:09:26,404 - Loss: 0.2333, step: 63900
+INFO - dpsgd_diffusion.py - 2024-10-24 20:11:10,193 - Loss: 0.2333, step: 64000
+INFO - dpsgd_diffusion.py - 2024-10-24 20:11:10,203 - Saving snapshot checkpoint and sampling single batch at iteration 64000.
+WARNING - image.py - 2024-10-24 20:11:11,269 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 20:11:41,153 - FID at iteration 64000: 127.393174
+INFO - dpsgd_diffusion.py - 2024-10-24 20:12:47,645 - Eps-value after 91 epochs: 7.5100
+INFO - dpsgd_diffusion.py - 2024-10-24 20:13:25,293 - Loss: 0.2220, step: 64100
+INFO - dpsgd_diffusion.py - 2024-10-24 20:15:07,544 - Loss: 0.2173, step: 64200
+INFO - dpsgd_diffusion.py - 2024-10-24 20:16:47,448 - Loss: 0.2152, step: 64300
+INFO - dpsgd_diffusion.py - 2024-10-24 20:18:28,567 - Loss: 0.2316, step: 64400
+INFO - dpsgd_diffusion.py - 2024-10-24 20:20:11,327 - Loss: 0.2258, step: 64500
+INFO - dpsgd_diffusion.py - 2024-10-24 20:21:51,356 - Loss: 0.2326, step: 64600
+INFO - dpsgd_diffusion.py - 2024-10-24 20:23:32,875 - Loss: 0.2046, step: 64700
+INFO - dpsgd_diffusion.py - 2024-10-24 20:24:40,434 - Eps-value after 92 epochs: 7.5567
+INFO - dpsgd_diffusion.py - 2024-10-24 20:25:13,384 - Loss: 0.2131, step: 64800
+INFO - dpsgd_diffusion.py - 2024-10-24 20:26:56,525 - Loss: 0.2192, step: 64900
+INFO - dpsgd_diffusion.py - 2024-10-24 20:28:38,836 - Loss: 0.2360, step: 65000
+INFO - dpsgd_diffusion.py - 2024-10-24 20:30:19,065 - Loss: 0.2075, step: 65100
+INFO - dpsgd_diffusion.py - 2024-10-24 20:31:58,292 - Loss: 0.2135, step: 65200
+INFO - dpsgd_diffusion.py - 2024-10-24 20:33:39,866 - Loss: 0.2262, step: 65300
+INFO - dpsgd_diffusion.py - 2024-10-24 20:35:20,375 - Loss: 0.2171, step: 65400
+INFO - dpsgd_diffusion.py - 2024-10-24 20:36:33,556 - Eps-value after 93 epochs: 7.6034
+INFO - dpsgd_diffusion.py - 2024-10-24 20:37:02,387 - Loss: 0.2098, step: 65500
+INFO - dpsgd_diffusion.py - 2024-10-24 20:38:41,957 - Loss: 0.2241, step: 65600
+INFO - dpsgd_diffusion.py - 2024-10-24 20:40:24,727 - Loss: 0.2311, step: 65700
+INFO - dpsgd_diffusion.py - 2024-10-24 20:42:08,811 - Loss: 0.2358, step: 65800
+INFO - dpsgd_diffusion.py - 2024-10-24 20:43:49,515 - Loss: 0.2079, step: 65900
+INFO - dpsgd_diffusion.py - 2024-10-24 20:45:31,118 - Loss: 0.2125, step: 66000
+INFO - dpsgd_diffusion.py - 2024-10-24 20:45:31,124 - Saving snapshot checkpoint and sampling single batch at iteration 66000.
+WARNING - image.py - 2024-10-24 20:45:32,241 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 20:46:02,183 - FID at iteration 66000: 125.782415
+INFO - dpsgd_diffusion.py - 2024-10-24 20:47:42,939 - Loss: 0.2035, step: 66100
+INFO - dpsgd_diffusion.py - 2024-10-24 20:48:59,176 - Eps-value after 94 epochs: 7.6490
+INFO - dpsgd_diffusion.py - 2024-10-24 20:49:23,898 - Loss: 0.2196, step: 66200
+INFO - dpsgd_diffusion.py - 2024-10-24 20:51:05,519 - Loss: 0.2090, step: 66300
+INFO - dpsgd_diffusion.py - 2024-10-24 20:52:47,460 - Loss: 0.2107, step: 66400
+INFO - dpsgd_diffusion.py - 2024-10-24 20:54:29,053 - Loss: 0.2062, step: 66500
+INFO - dpsgd_diffusion.py - 2024-10-24 20:56:11,163 - Loss: 0.2373, step: 66600
+INFO - dpsgd_diffusion.py - 2024-10-24 20:57:52,834 - Loss: 0.2256, step: 66700
+INFO - dpsgd_diffusion.py - 2024-10-24 20:59:33,806 - Loss: 0.2103, step: 66800
+INFO - dpsgd_diffusion.py - 2024-10-24 21:00:56,132 - Eps-value after 95 epochs: 7.6946
+INFO - dpsgd_diffusion.py - 2024-10-24 21:01:16,759 - Loss: 0.2188, step: 66900
+INFO - dpsgd_diffusion.py - 2024-10-24 21:02:58,356 - Loss: 0.2253, step: 67000
+INFO - dpsgd_diffusion.py - 2024-10-24 21:04:38,976 - Loss: 0.2065, step: 67100
+INFO - dpsgd_diffusion.py - 2024-10-24 21:06:19,959 - Loss: 0.2379, step: 67200
+INFO - dpsgd_diffusion.py - 2024-10-24 21:08:02,372 - Loss: 0.2437, step: 67300
+INFO - dpsgd_diffusion.py - 2024-10-24 21:09:45,735 - Loss: 0.2014, step: 67400
+INFO - dpsgd_diffusion.py - 2024-10-24 21:11:28,487 - Loss: 0.2213, step: 67500
+INFO - dpsgd_diffusion.py - 2024-10-24 21:12:54,751 - Eps-value after 96 epochs: 7.7401
+INFO - dpsgd_diffusion.py - 2024-10-24 21:13:11,909 - Loss: 0.2342, step: 67600
+INFO - dpsgd_diffusion.py - 2024-10-24 21:14:55,232 - Loss: 0.2282, step: 67700
+INFO - dpsgd_diffusion.py - 2024-10-24 21:16:37,611 - Loss: 0.2427, step: 67800
+INFO - dpsgd_diffusion.py - 2024-10-24 21:18:18,276 - Loss: 0.2558, step: 67900
+INFO - dpsgd_diffusion.py - 2024-10-24 21:19:58,885 - Loss: 0.2009, step: 68000
+INFO - dpsgd_diffusion.py - 2024-10-24 21:19:58,943 - Saving snapshot checkpoint and sampling single batch at iteration 68000.
+WARNING - image.py - 2024-10-24 21:20:00,055 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 21:20:30,109 - FID at iteration 68000: 125.116455
+INFO - dpsgd_diffusion.py - 2024-10-24 21:22:12,548 - Loss: 0.2182, step: 68100
+INFO - dpsgd_diffusion.py - 2024-10-24 21:23:55,190 - Loss: 0.2132, step: 68200
+INFO - dpsgd_diffusion.py - 2024-10-24 21:25:26,462 - Eps-value after 97 epochs: 7.7856
+INFO - dpsgd_diffusion.py - 2024-10-24 21:25:38,827 - Loss: 0.2041, step: 68300
+INFO - dpsgd_diffusion.py - 2024-10-24 21:27:19,534 - Loss: 0.2199, step: 68400
+INFO - dpsgd_diffusion.py - 2024-10-24 21:29:00,565 - Loss: 0.2096, step: 68500
+INFO - dpsgd_diffusion.py - 2024-10-24 21:30:40,536 - Loss: 0.2171, step: 68600
+INFO - dpsgd_diffusion.py - 2024-10-24 21:32:19,412 - Loss: 0.2313, step: 68700
+INFO - dpsgd_diffusion.py - 2024-10-24 21:33:59,498 - Loss: 0.2246, step: 68800
+INFO - dpsgd_diffusion.py - 2024-10-24 21:35:40,581 - Loss: 0.2113, step: 68900
+INFO - dpsgd_diffusion.py - 2024-10-24 21:37:12,485 - Eps-value after 98 epochs: 7.8311
+INFO - dpsgd_diffusion.py - 2024-10-24 21:37:20,683 - Loss: 0.2527, step: 69000
+INFO - dpsgd_diffusion.py - 2024-10-24 21:39:02,886 - Loss: 0.2157, step: 69100
+INFO - dpsgd_diffusion.py - 2024-10-24 21:40:44,099 - Loss: 0.2148, step: 69200
+INFO - dpsgd_diffusion.py - 2024-10-24 21:42:23,585 - Loss: 0.2198, step: 69300
+INFO - dpsgd_diffusion.py - 2024-10-24 21:44:03,703 - Loss: 0.2268, step: 69400
+INFO - dpsgd_diffusion.py - 2024-10-24 21:45:43,368 - Loss: 0.2162, step: 69500
+INFO - dpsgd_diffusion.py - 2024-10-24 21:47:27,212 - Loss: 0.2144, step: 69600
+INFO - dpsgd_diffusion.py - 2024-10-24 21:49:07,334 - Eps-value after 99 epochs: 7.8767
+INFO - dpsgd_diffusion.py - 2024-10-24 21:49:11,500 - Loss: 0.2110, step: 69700
+INFO - dpsgd_diffusion.py - 2024-10-24 21:50:54,462 - Loss: 0.2077, step: 69800
+INFO - dpsgd_diffusion.py - 2024-10-24 21:52:36,532 - Loss: 0.2247, step: 69900
+INFO - dpsgd_diffusion.py - 2024-10-24 21:54:18,535 - Loss: 0.2232, step: 70000
+INFO - dpsgd_diffusion.py - 2024-10-24 21:54:18,591 - Saving snapshot checkpoint and sampling single batch at iteration 70000.
+WARNING - image.py - 2024-10-24 21:54:19,686 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 21:54:49,567 - FID at iteration 70000: 124.475222
+INFO - dpsgd_diffusion.py - 2024-10-24 21:56:32,561 - Loss: 0.2310, step: 70100
+INFO - dpsgd_diffusion.py - 2024-10-24 21:58:14,213 - Loss: 0.2232, step: 70200
+INFO - dpsgd_diffusion.py - 2024-10-24 21:59:59,176 - Loss: 0.2458, step: 70300
+INFO - dpsgd_diffusion.py - 2024-10-24 22:01:38,760 - Loss: 0.2092, step: 70400
+INFO - dpsgd_diffusion.py - 2024-10-24 22:01:38,779 - Eps-value after 100 epochs: 7.9219
+INFO - dpsgd_diffusion.py - 2024-10-24 22:03:22,970 - Loss: 0.2127, step: 70500
+INFO - dpsgd_diffusion.py - 2024-10-24 22:05:04,723 - Loss: 0.2230, step: 70600
+INFO - dpsgd_diffusion.py - 2024-10-24 22:06:47,430 - Loss: 0.2122, step: 70700
+INFO - dpsgd_diffusion.py - 2024-10-24 22:08:29,542 - Loss: 0.2031, step: 70800
+INFO - dpsgd_diffusion.py - 2024-10-24 22:10:13,448 - Loss: 0.2321, step: 70900
+INFO - dpsgd_diffusion.py - 2024-10-24 22:11:56,602 - Loss: 0.2210, step: 71000
+INFO - dpsgd_diffusion.py - 2024-10-24 22:13:37,551 - Loss: 0.2311, step: 71100
+INFO - dpsgd_diffusion.py - 2024-10-24 22:13:41,508 - Eps-value after 101 epochs: 7.9663
+INFO - dpsgd_diffusion.py - 2024-10-24 22:15:19,422 - Loss: 0.1916, step: 71200
+INFO - dpsgd_diffusion.py - 2024-10-24 22:17:01,233 - Loss: 0.2205, step: 71300
+INFO - dpsgd_diffusion.py - 2024-10-24 22:18:43,168 - Loss: 0.2098, step: 71400
+INFO - dpsgd_diffusion.py - 2024-10-24 22:20:24,077 - Loss: 0.2138, step: 71500
+INFO - dpsgd_diffusion.py - 2024-10-24 22:22:06,064 - Loss: 0.2028, step: 71600
+INFO - dpsgd_diffusion.py - 2024-10-24 22:23:49,107 - Loss: 0.1997, step: 71700
+INFO - dpsgd_diffusion.py - 2024-10-24 22:25:27,951 - Loss: 0.2067, step: 71800
+INFO - dpsgd_diffusion.py - 2024-10-24 22:25:35,838 - Eps-value after 102 epochs: 8.0106
+INFO - dpsgd_diffusion.py - 2024-10-24 22:27:10,424 - Loss: 0.2027, step: 71900
+INFO - dpsgd_diffusion.py - 2024-10-24 22:28:52,205 - Loss: 0.2475, step: 72000
+INFO - dpsgd_diffusion.py - 2024-10-24 22:28:52,214 - Saving snapshot checkpoint and sampling single batch at iteration 72000.
+WARNING - image.py - 2024-10-24 22:28:53,310 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 22:29:23,237 - FID at iteration 72000: 123.528831
+INFO - dpsgd_diffusion.py - 2024-10-24 22:31:06,246 - Loss: 0.2046, step: 72100
+INFO - dpsgd_diffusion.py - 2024-10-24 22:32:47,853 - Loss: 0.2069, step: 72200
+INFO - dpsgd_diffusion.py - 2024-10-24 22:34:29,761 - Loss: 0.2054, step: 72300
+INFO - dpsgd_diffusion.py - 2024-10-24 22:36:09,922 - Loss: 0.2145, step: 72400
+INFO - dpsgd_diffusion.py - 2024-10-24 22:37:52,828 - Loss: 0.2018, step: 72500
+INFO - dpsgd_diffusion.py - 2024-10-24 22:38:04,700 - Eps-value after 103 epochs: 8.0550
+INFO - dpsgd_diffusion.py - 2024-10-24 22:39:33,770 - Loss: 0.2266, step: 72600
+INFO - dpsgd_diffusion.py - 2024-10-24 22:41:14,737 - Loss: 0.2232, step: 72700
+INFO - dpsgd_diffusion.py - 2024-10-24 22:42:56,498 - Loss: 0.2169, step: 72800
+INFO - dpsgd_diffusion.py - 2024-10-24 22:44:38,278 - Loss: 0.2045, step: 72900
+INFO - dpsgd_diffusion.py - 2024-10-24 22:46:19,432 - Loss: 0.1974, step: 73000
+INFO - dpsgd_diffusion.py - 2024-10-24 22:48:00,251 - Loss: 0.2380, step: 73100
+INFO - dpsgd_diffusion.py - 2024-10-24 22:49:38,474 - Loss: 0.2182, step: 73200
+INFO - dpsgd_diffusion.py - 2024-10-24 22:49:53,980 - Eps-value after 104 epochs: 8.0993
+INFO - dpsgd_diffusion.py - 2024-10-24 22:51:22,737 - Loss: 0.2310, step: 73300
+INFO - dpsgd_diffusion.py - 2024-10-24 22:53:04,404 - Loss: 0.2005, step: 73400
+INFO - dpsgd_diffusion.py - 2024-10-24 22:54:49,854 - Loss: 0.2116, step: 73500
+INFO - dpsgd_diffusion.py - 2024-10-24 22:56:33,270 - Loss: 0.2115, step: 73600
+INFO - dpsgd_diffusion.py - 2024-10-24 22:58:16,862 - Loss: 0.2056, step: 73700
+INFO - dpsgd_diffusion.py - 2024-10-24 22:59:59,284 - Loss: 0.2036, step: 73800
+INFO - dpsgd_diffusion.py - 2024-10-24 23:01:40,400 - Loss: 0.1974, step: 73900
+INFO - dpsgd_diffusion.py - 2024-10-24 23:02:00,092 - Eps-value after 105 epochs: 8.1437
+INFO - dpsgd_diffusion.py - 2024-10-24 23:03:20,388 - Loss: 0.2177, step: 74000
+INFO - dpsgd_diffusion.py - 2024-10-24 23:03:20,401 - Saving snapshot checkpoint and sampling single batch at iteration 74000.
+WARNING - image.py - 2024-10-24 23:03:21,682 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 23:03:51,584 - FID at iteration 74000: 122.133632
+INFO - dpsgd_diffusion.py - 2024-10-24 23:05:34,295 - Loss: 0.2302, step: 74100
+INFO - dpsgd_diffusion.py - 2024-10-24 23:07:16,388 - Loss: 0.2048, step: 74200
+INFO - dpsgd_diffusion.py - 2024-10-24 23:08:58,305 - Loss: 0.2293, step: 74300
+INFO - dpsgd_diffusion.py - 2024-10-24 23:10:38,284 - Loss: 0.2062, step: 74400
+INFO - dpsgd_diffusion.py - 2024-10-24 23:12:19,396 - Loss: 0.2262, step: 74500
+INFO - dpsgd_diffusion.py - 2024-10-24 23:14:01,880 - Loss: 0.2121, step: 74600
+INFO - dpsgd_diffusion.py - 2024-10-24 23:14:25,450 - Eps-value after 106 epochs: 8.1880
+INFO - dpsgd_diffusion.py - 2024-10-24 23:15:42,479 - Loss: 0.1979, step: 74700
+INFO - dpsgd_diffusion.py - 2024-10-24 23:17:24,142 - Loss: 0.2096, step: 74800
+INFO - dpsgd_diffusion.py - 2024-10-24 23:19:04,442 - Loss: 0.2169, step: 74900
+INFO - dpsgd_diffusion.py - 2024-10-24 23:20:45,962 - Loss: 0.2241, step: 75000
+INFO - dpsgd_diffusion.py - 2024-10-24 23:22:28,419 - Loss: 0.2256, step: 75100
+INFO - dpsgd_diffusion.py - 2024-10-24 23:24:09,163 - Loss: 0.2239, step: 75200
+INFO - dpsgd_diffusion.py - 2024-10-24 23:25:52,103 - Loss: 0.2164, step: 75300
+INFO - dpsgd_diffusion.py - 2024-10-24 23:26:20,855 - Eps-value after 107 epochs: 8.2324
+INFO - dpsgd_diffusion.py - 2024-10-24 23:27:33,855 - Loss: 0.2529, step: 75400
+INFO - dpsgd_diffusion.py - 2024-10-24 23:29:17,207 - Loss: 0.2110, step: 75500
+INFO - dpsgd_diffusion.py - 2024-10-24 23:30:59,202 - Loss: 0.2270, step: 75600
+INFO - dpsgd_diffusion.py - 2024-10-24 23:32:39,943 - Loss: 0.2187, step: 75700
+INFO - dpsgd_diffusion.py - 2024-10-24 23:34:20,860 - Loss: 0.2154, step: 75800
+INFO - dpsgd_diffusion.py - 2024-10-24 23:36:03,589 - Loss: 0.2126, step: 75900
+INFO - dpsgd_diffusion.py - 2024-10-24 23:37:47,550 - Loss: 0.2139, step: 76000
+INFO - dpsgd_diffusion.py - 2024-10-24 23:37:47,560 - Saving snapshot checkpoint and sampling single batch at iteration 76000.
+WARNING - image.py - 2024-10-24 23:37:48,615 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-24 23:38:18,553 - FID at iteration 76000: 121.838554
+INFO - dpsgd_diffusion.py - 2024-10-24 23:38:50,751 - Eps-value after 108 epochs: 8.2756
+INFO - dpsgd_diffusion.py - 2024-10-24 23:40:01,246 - Loss: 0.2040, step: 76100
+INFO - dpsgd_diffusion.py - 2024-10-24 23:41:43,003 - Loss: 0.1869, step: 76200
+INFO - dpsgd_diffusion.py - 2024-10-24 23:43:23,802 - Loss: 0.2287, step: 76300
+INFO - dpsgd_diffusion.py - 2024-10-24 23:45:03,701 - Loss: 0.2272, step: 76400
+INFO - dpsgd_diffusion.py - 2024-10-24 23:46:44,658 - Loss: 0.2070, step: 76500
+INFO - dpsgd_diffusion.py - 2024-10-24 23:48:27,536 - Loss: 0.2236, step: 76600
+INFO - dpsgd_diffusion.py - 2024-10-24 23:50:07,360 - Loss: 0.2435, step: 76700
+INFO - dpsgd_diffusion.py - 2024-10-24 23:50:44,140 - Eps-value after 109 epochs: 8.3188
+INFO - dpsgd_diffusion.py - 2024-10-24 23:51:48,633 - Loss: 0.2251, step: 76800
+INFO - dpsgd_diffusion.py - 2024-10-24 23:53:29,039 - Loss: 0.2280, step: 76900
+INFO - dpsgd_diffusion.py - 2024-10-24 23:55:11,480 - Loss: 0.2426, step: 77000
+INFO - dpsgd_diffusion.py - 2024-10-24 23:56:50,284 - Loss: 0.1988, step: 77100
+INFO - dpsgd_diffusion.py - 2024-10-24 23:58:30,855 - Loss: 0.2157, step: 77200
+INFO - dpsgd_diffusion.py - 2024-10-25 00:00:14,189 - Loss: 0.2002, step: 77300
+INFO - dpsgd_diffusion.py - 2024-10-25 00:01:54,192 - Loss: 0.2240, step: 77400
+INFO - dpsgd_diffusion.py - 2024-10-25 00:02:34,730 - Eps-value after 110 epochs: 8.3620
+INFO - dpsgd_diffusion.py - 2024-10-25 00:03:34,796 - Loss: 0.2109, step: 77500
+INFO - dpsgd_diffusion.py - 2024-10-25 00:05:17,145 - Loss: 0.2111, step: 77600
+INFO - dpsgd_diffusion.py - 2024-10-25 00:06:59,482 - Loss: 0.2346, step: 77700
+INFO - dpsgd_diffusion.py - 2024-10-25 00:08:42,251 - Loss: 0.2226, step: 77800
+INFO - dpsgd_diffusion.py - 2024-10-25 00:10:23,437 - Loss: 0.2020, step: 77900
+INFO - dpsgd_diffusion.py - 2024-10-25 00:12:04,448 - Loss: 0.2238, step: 78000
+INFO - dpsgd_diffusion.py - 2024-10-25 00:12:04,456 - Saving snapshot checkpoint and sampling single batch at iteration 78000.
+WARNING - image.py - 2024-10-25 00:12:05,513 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-25 00:12:35,068 - FID at iteration 78000: 121.012171
+INFO - dpsgd_diffusion.py - 2024-10-25 00:14:15,452 - Loss: 0.2048, step: 78100
+INFO - dpsgd_diffusion.py - 2024-10-25 00:15:00,597 - Eps-value after 111 epochs: 8.4052
+INFO - dpsgd_diffusion.py - 2024-10-25 00:15:56,824 - Loss: 0.2247, step: 78200
+INFO - dpsgd_diffusion.py - 2024-10-25 00:17:37,644 - Loss: 0.2019, step: 78300
+INFO - dpsgd_diffusion.py - 2024-10-25 00:19:17,183 - Loss: 0.2118, step: 78400
+INFO - dpsgd_diffusion.py - 2024-10-25 00:20:59,882 - Loss: 0.2129, step: 78500
+INFO - dpsgd_diffusion.py - 2024-10-25 00:22:42,524 - Loss: 0.2206, step: 78600
+INFO - dpsgd_diffusion.py - 2024-10-25 00:24:22,943 - Loss: 0.2150, step: 78700
+INFO - dpsgd_diffusion.py - 2024-10-25 00:26:02,881 - Loss: 0.2130, step: 78800
+INFO - dpsgd_diffusion.py - 2024-10-25 00:26:51,552 - Eps-value after 112 epochs: 8.4484
+INFO - dpsgd_diffusion.py - 2024-10-25 00:27:45,096 - Loss: 0.2110, step: 78900
+INFO - dpsgd_diffusion.py - 2024-10-25 00:29:29,126 - Loss: 0.2196, step: 79000
+INFO - dpsgd_diffusion.py - 2024-10-25 00:31:12,156 - Loss: 0.2240, step: 79100
+INFO - dpsgd_diffusion.py - 2024-10-25 00:32:52,679 - Loss: 0.2130, step: 79200
+INFO - dpsgd_diffusion.py - 2024-10-25 00:34:35,288 - Loss: 0.2151, step: 79300
+INFO - dpsgd_diffusion.py - 2024-10-25 00:36:15,946 - Loss: 0.2296, step: 79400
+INFO - dpsgd_diffusion.py - 2024-10-25 00:37:57,429 - Loss: 0.2078, step: 79500
+INFO - dpsgd_diffusion.py - 2024-10-25 00:38:49,649 - Eps-value after 113 epochs: 8.4915
+INFO - dpsgd_diffusion.py - 2024-10-25 00:39:39,166 - Loss: 0.2038, step: 79600
+INFO - dpsgd_diffusion.py - 2024-10-25 00:41:21,098 - Loss: 0.2326, step: 79700
+INFO - dpsgd_diffusion.py - 2024-10-25 00:43:04,640 - Loss: 0.2003, step: 79800
+INFO - dpsgd_diffusion.py - 2024-10-25 00:44:45,232 - Loss: 0.2223, step: 79900
+INFO - dpsgd_diffusion.py - 2024-10-25 00:46:25,495 - Loss: 0.2170, step: 80000
+INFO - dpsgd_diffusion.py - 2024-10-25 00:46:25,504 - Saving snapshot checkpoint and sampling single batch at iteration 80000.
+WARNING - image.py - 2024-10-25 00:46:26,559 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-25 00:46:56,452 - FID at iteration 80000: 120.516145
+INFO - dpsgd_diffusion.py - 2024-10-25 00:48:40,492 - Loss: 0.2152, step: 80100
+INFO - dpsgd_diffusion.py - 2024-10-25 00:50:24,055 - Loss: 0.2109, step: 80200
+INFO - dpsgd_diffusion.py - 2024-10-25 00:51:19,227 - Eps-value after 114 epochs: 8.5347
+INFO - dpsgd_diffusion.py - 2024-10-25 00:52:04,439 - Loss: 0.2227, step: 80300
+INFO - dpsgd_diffusion.py - 2024-10-25 00:53:47,471 - Loss: 0.2137, step: 80400
+INFO - dpsgd_diffusion.py - 2024-10-25 00:55:28,153 - Loss: 0.2284, step: 80500
+INFO - dpsgd_diffusion.py - 2024-10-25 00:57:10,431 - Loss: 0.2420, step: 80600
+INFO - dpsgd_diffusion.py - 2024-10-25 00:58:53,816 - Loss: 0.2428, step: 80700
+INFO - dpsgd_diffusion.py - 2024-10-25 01:00:36,157 - Loss: 0.2343, step: 80800
+INFO - dpsgd_diffusion.py - 2024-10-25 01:02:16,583 - Loss: 0.2293, step: 80900
+INFO - dpsgd_diffusion.py - 2024-10-25 01:03:16,701 - Eps-value after 115 epochs: 8.5779
+INFO - dpsgd_diffusion.py - 2024-10-25 01:03:56,854 - Loss: 0.2020, step: 81000
+INFO - dpsgd_diffusion.py - 2024-10-25 01:05:38,966 - Loss: 0.2117, step: 81100
+INFO - dpsgd_diffusion.py - 2024-10-25 01:07:19,120 - Loss: 0.2126, step: 81200
+INFO - dpsgd_diffusion.py - 2024-10-25 01:09:00,138 - Loss: 0.2153, step: 81300
+INFO - dpsgd_diffusion.py - 2024-10-25 01:10:43,037 - Loss: 0.2336, step: 81400
+INFO - dpsgd_diffusion.py - 2024-10-25 01:12:25,663 - Loss: 0.2425, step: 81500
+INFO - dpsgd_diffusion.py - 2024-10-25 01:14:05,866 - Loss: 0.2057, step: 81600
+INFO - dpsgd_diffusion.py - 2024-10-25 01:15:10,152 - Eps-value after 116 epochs: 8.6202
+INFO - dpsgd_diffusion.py - 2024-10-25 01:15:47,464 - Loss: 0.2217, step: 81700
+INFO - dpsgd_diffusion.py - 2024-10-25 01:17:29,387 - Loss: 0.2271, step: 81800
+INFO - dpsgd_diffusion.py - 2024-10-25 01:19:11,928 - Loss: 0.2178, step: 81900
+INFO - dpsgd_diffusion.py - 2024-10-25 01:20:54,650 - Loss: 0.2224, step: 82000
+INFO - dpsgd_diffusion.py - 2024-10-25 01:20:54,706 - Saving snapshot checkpoint and sampling single batch at iteration 82000.
+WARNING - image.py - 2024-10-25 01:20:55,761 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-25 01:21:25,900 - FID at iteration 82000: 118.984304
+INFO - dpsgd_diffusion.py - 2024-10-25 01:23:08,275 - Loss: 0.2267, step: 82100
+INFO - dpsgd_diffusion.py - 2024-10-25 01:24:50,649 - Loss: 0.2035, step: 82200
+INFO - dpsgd_diffusion.py - 2024-10-25 01:26:29,927 - Loss: 0.2141, step: 82300
+INFO - dpsgd_diffusion.py - 2024-10-25 01:27:37,761 - Eps-value after 117 epochs: 8.6622
+INFO - dpsgd_diffusion.py - 2024-10-25 01:28:13,007 - Loss: 0.2051, step: 82400
+INFO - dpsgd_diffusion.py - 2024-10-25 01:29:55,848 - Loss: 0.2129, step: 82500
+INFO - dpsgd_diffusion.py - 2024-10-25 01:31:40,360 - Loss: 0.1886, step: 82600
+INFO - dpsgd_diffusion.py - 2024-10-25 01:33:23,078 - Loss: 0.2118, step: 82700
+INFO - dpsgd_diffusion.py - 2024-10-25 01:35:05,870 - Loss: 0.2111, step: 82800
+INFO - dpsgd_diffusion.py - 2024-10-25 01:36:47,114 - Loss: 0.2320, step: 82900
+INFO - dpsgd_diffusion.py - 2024-10-25 01:38:29,280 - Loss: 0.2165, step: 83000
+INFO - dpsgd_diffusion.py - 2024-10-25 01:39:43,436 - Eps-value after 118 epochs: 8.7042
+INFO - dpsgd_diffusion.py - 2024-10-25 01:40:11,798 - Loss: 0.2277, step: 83100
+INFO - dpsgd_diffusion.py - 2024-10-25 01:41:52,593 - Loss: 0.2185, step: 83200
+INFO - dpsgd_diffusion.py - 2024-10-25 01:43:34,449 - Loss: 0.2113, step: 83300
+INFO - dpsgd_diffusion.py - 2024-10-25 01:45:16,882 - Loss: 0.2248, step: 83400
+INFO - dpsgd_diffusion.py - 2024-10-25 01:46:58,711 - Loss: 0.1961, step: 83500
+INFO - dpsgd_diffusion.py - 2024-10-25 01:48:40,186 - Loss: 0.2146, step: 83600
+INFO - dpsgd_diffusion.py - 2024-10-25 01:50:23,216 - Loss: 0.2198, step: 83700
+INFO - dpsgd_diffusion.py - 2024-10-25 01:51:41,780 - Eps-value after 119 epochs: 8.7462
+INFO - dpsgd_diffusion.py - 2024-10-25 01:52:06,468 - Loss: 0.2055, step: 83800
+INFO - dpsgd_diffusion.py - 2024-10-25 01:53:47,412 - Loss: 0.2063, step: 83900
+INFO - dpsgd_diffusion.py - 2024-10-25 01:55:30,357 - Loss: 0.1990, step: 84000
+INFO - dpsgd_diffusion.py - 2024-10-25 01:55:30,458 - Saving snapshot checkpoint and sampling single batch at iteration 84000.
+WARNING - image.py - 2024-10-25 01:55:31,522 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-25 01:56:01,422 - FID at iteration 84000: 118.799356
+INFO - dpsgd_diffusion.py - 2024-10-25 01:57:45,344 - Loss: 0.1897, step: 84100
+INFO - dpsgd_diffusion.py - 2024-10-25 01:59:27,986 - Loss: 0.2190, step: 84200
+INFO - dpsgd_diffusion.py - 2024-10-25 02:01:12,367 - Loss: 0.2019, step: 84300
+INFO - dpsgd_diffusion.py - 2024-10-25 02:02:54,836 - Loss: 0.2114, step: 84400
+INFO - dpsgd_diffusion.py - 2024-10-25 02:04:18,332 - Eps-value after 120 epochs: 8.7882
+INFO - dpsgd_diffusion.py - 2024-10-25 02:04:38,912 - Loss: 0.2050, step: 84500
+INFO - dpsgd_diffusion.py - 2024-10-25 02:06:20,948 - Loss: 0.2282, step: 84600
+INFO - dpsgd_diffusion.py - 2024-10-25 02:08:01,203 - Loss: 0.2227, step: 84700
+INFO - dpsgd_diffusion.py - 2024-10-25 02:09:43,892 - Loss: 0.2282, step: 84800
+INFO - dpsgd_diffusion.py - 2024-10-25 02:11:27,242 - Loss: 0.2063, step: 84900
+INFO - dpsgd_diffusion.py - 2024-10-25 02:13:09,936 - Loss: 0.2342, step: 85000
+INFO - dpsgd_diffusion.py - 2024-10-25 02:14:54,597 - Loss: 0.2082, step: 85100
+INFO - dpsgd_diffusion.py - 2024-10-25 02:16:23,308 - Eps-value after 121 epochs: 8.8302
+INFO - dpsgd_diffusion.py - 2024-10-25 02:16:40,470 - Loss: 0.2012, step: 85200
+INFO - dpsgd_diffusion.py - 2024-10-25 02:18:23,254 - Loss: 0.2298, step: 85300
+INFO - dpsgd_diffusion.py - 2024-10-25 02:20:04,975 - Loss: 0.2375, step: 85400
+INFO - dpsgd_diffusion.py - 2024-10-25 02:21:47,566 - Loss: 0.2243, step: 85500
+INFO - dpsgd_diffusion.py - 2024-10-25 02:23:28,998 - Loss: 0.2019, step: 85600
+INFO - dpsgd_diffusion.py - 2024-10-25 02:25:11,648 - Loss: 0.2065, step: 85700
+INFO - dpsgd_diffusion.py - 2024-10-25 02:26:51,702 - Loss: 0.1991, step: 85800
+INFO - dpsgd_diffusion.py - 2024-10-25 02:28:20,636 - Eps-value after 122 epochs: 8.8722
+INFO - dpsgd_diffusion.py - 2024-10-25 02:28:32,964 - Loss: 0.2096, step: 85900
+INFO - dpsgd_diffusion.py - 2024-10-25 02:30:14,315 - Loss: 0.2159, step: 86000
+INFO - dpsgd_diffusion.py - 2024-10-25 02:30:14,323 - Saving snapshot checkpoint and sampling single batch at iteration 86000.
+WARNING - image.py - 2024-10-25 02:30:15,378 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-25 02:30:45,410 - FID at iteration 86000: 118.471231
+INFO - dpsgd_diffusion.py - 2024-10-25 02:32:24,752 - Loss: 0.2161, step: 86100
+INFO - dpsgd_diffusion.py - 2024-10-25 02:34:05,414 - Loss: 0.2135, step: 86200
+INFO - dpsgd_diffusion.py - 2024-10-25 02:35:46,164 - Loss: 0.2042, step: 86300
+INFO - dpsgd_diffusion.py - 2024-10-25 02:37:26,090 - Loss: 0.2271, step: 86400
+INFO - dpsgd_diffusion.py - 2024-10-25 02:39:08,785 - Loss: 0.2237, step: 86500
+INFO - dpsgd_diffusion.py - 2024-10-25 02:40:41,177 - Eps-value after 123 epochs: 8.9142
+INFO - dpsgd_diffusion.py - 2024-10-25 02:40:49,390 - Loss: 0.2072, step: 86600
+INFO - dpsgd_diffusion.py - 2024-10-25 02:42:29,080 - Loss: 0.2069, step: 86700
+INFO - dpsgd_diffusion.py - 2024-10-25 02:44:10,254 - Loss: 0.2189, step: 86800
+INFO - dpsgd_diffusion.py - 2024-10-25 02:45:50,489 - Loss: 0.2172, step: 86900
+INFO - dpsgd_diffusion.py - 2024-10-25 02:47:33,000 - Loss: 0.2149, step: 87000
+INFO - dpsgd_diffusion.py - 2024-10-25 02:49:13,772 - Loss: 0.2199, step: 87100
+INFO - dpsgd_diffusion.py - 2024-10-25 02:50:56,166 - Loss: 0.1915, step: 87200
+INFO - dpsgd_diffusion.py - 2024-10-25 02:52:33,347 - Eps-value after 124 epochs: 8.9562
+INFO - dpsgd_diffusion.py - 2024-10-25 02:52:37,467 - Loss: 0.2080, step: 87300
+INFO - dpsgd_diffusion.py - 2024-10-25 02:54:20,180 - Loss: 0.2127, step: 87400
+INFO - dpsgd_diffusion.py - 2024-10-25 02:56:02,487 - Loss: 0.2096, step: 87500
+INFO - dpsgd_diffusion.py - 2024-10-25 02:57:45,436 - Loss: 0.2071, step: 87600
+INFO - dpsgd_diffusion.py - 2024-10-25 02:59:25,789 - Loss: 0.2436, step: 87700
+INFO - dpsgd_diffusion.py - 2024-10-25 03:01:06,639 - Loss: 0.2137, step: 87800
+INFO - dpsgd_diffusion.py - 2024-10-25 03:02:47,460 - Loss: 0.2213, step: 87900
+INFO - dpsgd_diffusion.py - 2024-10-25 03:04:26,689 - Loss: 0.2194, step: 88000
+INFO - dpsgd_diffusion.py - 2024-10-25 03:04:26,707 - Eps-value after 125 epochs: 8.9974
+INFO - dpsgd_diffusion.py - 2024-10-25 03:04:26,713 - Saving snapshot checkpoint and sampling single batch at iteration 88000.
+WARNING - image.py - 2024-10-25 03:04:27,767 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-25 03:04:57,711 - FID at iteration 88000: 117.376072
+INFO - dpsgd_diffusion.py - 2024-10-25 03:06:40,673 - Loss: 0.2081, step: 88100
+INFO - dpsgd_diffusion.py - 2024-10-25 03:08:21,540 - Loss: 0.2310, step: 88200
+INFO - dpsgd_diffusion.py - 2024-10-25 03:10:03,725 - Loss: 0.2237, step: 88300
+INFO - dpsgd_diffusion.py - 2024-10-25 03:11:42,842 - Loss: 0.2346, step: 88400
+INFO - dpsgd_diffusion.py - 2024-10-25 03:13:24,811 - Loss: 0.2234, step: 88500
+INFO - dpsgd_diffusion.py - 2024-10-25 03:15:05,963 - Loss: 0.2272, step: 88600
+INFO - dpsgd_diffusion.py - 2024-10-25 03:16:48,417 - Loss: 0.1959, step: 88700
+INFO - dpsgd_diffusion.py - 2024-10-25 03:16:52,373 - Eps-value after 126 epochs: 9.0382
+INFO - dpsgd_diffusion.py - 2024-10-25 03:18:29,566 - Loss: 0.2340, step: 88800
+INFO - dpsgd_diffusion.py - 2024-10-25 03:20:11,029 - Loss: 0.2120, step: 88900
+INFO - dpsgd_diffusion.py - 2024-10-25 03:21:53,672 - Loss: 0.2068, step: 89000
+INFO - dpsgd_diffusion.py - 2024-10-25 03:23:37,034 - Loss: 0.2179, step: 89100
+INFO - dpsgd_diffusion.py - 2024-10-25 03:25:18,320 - Loss: 0.2166, step: 89200
+INFO - dpsgd_diffusion.py - 2024-10-25 03:27:00,029 - Loss: 0.2241, step: 89300
+INFO - dpsgd_diffusion.py - 2024-10-25 03:28:40,631 - Loss: 0.2087, step: 89400
+INFO - dpsgd_diffusion.py - 2024-10-25 03:28:48,565 - Eps-value after 127 epochs: 9.0791
+INFO - dpsgd_diffusion.py - 2024-10-25 03:30:21,343 - Loss: 0.2144, step: 89500
+INFO - dpsgd_diffusion.py - 2024-10-25 03:31:58,704 - Loss: 0.2157, step: 89600
+INFO - dpsgd_diffusion.py - 2024-10-25 03:33:41,767 - Loss: 0.2198, step: 89700
+INFO - dpsgd_diffusion.py - 2024-10-25 03:35:23,202 - Loss: 0.2240, step: 89800
+INFO - dpsgd_diffusion.py - 2024-10-25 03:37:07,023 - Loss: 0.2205, step: 89900
+INFO - dpsgd_diffusion.py - 2024-10-25 03:38:49,100 - Loss: 0.2051, step: 90000
+INFO - dpsgd_diffusion.py - 2024-10-25 03:38:49,156 - Saving snapshot checkpoint and sampling single batch at iteration 90000.
+WARNING - image.py - 2024-10-25 03:38:50,212 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-25 03:39:20,090 - FID at iteration 90000: 118.191038
+INFO - dpsgd_diffusion.py - 2024-10-25 03:41:01,268 - Loss: 0.2224, step: 90100
+INFO - dpsgd_diffusion.py - 2024-10-25 03:41:13,071 - Eps-value after 128 epochs: 9.1199
+INFO - dpsgd_diffusion.py - 2024-10-25 03:42:43,450 - Loss: 0.2075, step: 90200
+INFO - dpsgd_diffusion.py - 2024-10-25 03:44:23,147 - Loss: 0.1977, step: 90300
+INFO - dpsgd_diffusion.py - 2024-10-25 03:46:04,335 - Loss: 0.2059, step: 90400
+INFO - dpsgd_diffusion.py - 2024-10-25 03:47:44,239 - Loss: 0.1998, step: 90500
+INFO - dpsgd_diffusion.py - 2024-10-25 03:49:25,792 - Loss: 0.2161, step: 90600
+INFO - dpsgd_diffusion.py - 2024-10-25 03:51:07,783 - Loss: 0.2388, step: 90700
+INFO - dpsgd_diffusion.py - 2024-10-25 03:52:50,513 - Loss: 0.1983, step: 90800
+INFO - dpsgd_diffusion.py - 2024-10-25 03:53:06,260 - Eps-value after 129 epochs: 9.1608
+INFO - dpsgd_diffusion.py - 2024-10-25 03:54:31,913 - Loss: 0.2053, step: 90900
+INFO - dpsgd_diffusion.py - 2024-10-25 03:56:12,623 - Loss: 0.2047, step: 91000
+INFO - dpsgd_diffusion.py - 2024-10-25 03:57:54,926 - Loss: 0.2511, step: 91100
+INFO - dpsgd_diffusion.py - 2024-10-25 03:59:35,050 - Loss: 0.2194, step: 91200
+INFO - dpsgd_diffusion.py - 2024-10-25 04:01:19,114 - Loss: 0.2021, step: 91300
+INFO - dpsgd_diffusion.py - 2024-10-25 04:02:59,384 - Loss: 0.2107, step: 91400
+INFO - dpsgd_diffusion.py - 2024-10-25 04:04:42,676 - Loss: 0.2146, step: 91500
+INFO - dpsgd_diffusion.py - 2024-10-25 04:05:03,342 - Eps-value after 130 epochs: 9.2016
+INFO - dpsgd_diffusion.py - 2024-10-25 04:06:26,831 - Loss: 0.2000, step: 91600
+INFO - dpsgd_diffusion.py - 2024-10-25 04:08:09,238 - Loss: 0.2105, step: 91700
+INFO - dpsgd_diffusion.py - 2024-10-25 04:09:51,913 - Loss: 0.2048, step: 91800
+INFO - dpsgd_diffusion.py - 2024-10-25 04:11:32,074 - Loss: 0.2104, step: 91900
+INFO - dpsgd_diffusion.py - 2024-10-25 04:13:15,872 - Loss: 0.2138, step: 92000
+INFO - dpsgd_diffusion.py - 2024-10-25 04:13:15,881 - Saving snapshot checkpoint and sampling single batch at iteration 92000.
+WARNING - image.py - 2024-10-25 04:13:16,936 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-25 04:13:46,488 - FID at iteration 92000: 117.157083
+INFO - dpsgd_diffusion.py - 2024-10-25 04:15:29,782 - Loss: 0.1992, step: 92100
+INFO - dpsgd_diffusion.py - 2024-10-25 04:17:10,994 - Loss: 0.2046, step: 92200
+INFO - dpsgd_diffusion.py - 2024-10-25 04:17:35,108 - Eps-value after 131 epochs: 9.2425
+INFO - dpsgd_diffusion.py - 2024-10-25 04:18:51,135 - Loss: 0.2248, step: 92300
+INFO - dpsgd_diffusion.py - 2024-10-25 04:20:35,534 - Loss: 0.2044, step: 92400
+INFO - dpsgd_diffusion.py - 2024-10-25 04:22:19,558 - Loss: 0.2400, step: 92500
+INFO - dpsgd_diffusion.py - 2024-10-25 04:24:01,291 - Loss: 0.1984, step: 92600
+INFO - dpsgd_diffusion.py - 2024-10-25 04:25:40,635 - Loss: 0.2224, step: 92700
+INFO - dpsgd_diffusion.py - 2024-10-25 04:27:23,413 - Loss: 0.2166, step: 92800
+INFO - dpsgd_diffusion.py - 2024-10-25 04:29:05,192 - Loss: 0.2082, step: 92900
+INFO - dpsgd_diffusion.py - 2024-10-25 04:29:32,699 - Eps-value after 132 epochs: 9.2833
+INFO - dpsgd_diffusion.py - 2024-10-25 04:30:47,718 - Loss: 0.2186, step: 93000
+INFO - dpsgd_diffusion.py - 2024-10-25 04:32:28,493 - Loss: 0.2167, step: 93100
+INFO - dpsgd_diffusion.py - 2024-10-25 04:34:10,813 - Loss: 0.2074, step: 93200
+INFO - dpsgd_diffusion.py - 2024-10-25 04:35:50,003 - Loss: 0.2276, step: 93300
+INFO - dpsgd_diffusion.py - 2024-10-25 04:37:30,688 - Loss: 0.2099, step: 93400
+INFO - dpsgd_diffusion.py - 2024-10-25 04:39:14,000 - Loss: 0.2019, step: 93500
+INFO - dpsgd_diffusion.py - 2024-10-25 04:40:57,949 - Loss: 0.1997, step: 93600
+INFO - dpsgd_diffusion.py - 2024-10-25 04:41:31,034 - Eps-value after 133 epochs: 9.3242
+INFO - dpsgd_diffusion.py - 2024-10-25 04:42:41,475 - Loss: 0.2206, step: 93700
+INFO - dpsgd_diffusion.py - 2024-10-25 04:44:22,112 - Loss: 0.2026, step: 93800
+INFO - dpsgd_diffusion.py - 2024-10-25 04:46:06,041 - Loss: 0.2119, step: 93900
+INFO - dpsgd_diffusion.py - 2024-10-25 04:47:46,961 - Loss: 0.2271, step: 94000
+INFO - dpsgd_diffusion.py - 2024-10-25 04:47:46,970 - Saving snapshot checkpoint and sampling single batch at iteration 94000.
+WARNING - image.py - 2024-10-25 04:47:48,216 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-25 04:48:18,091 - FID at iteration 94000: 117.278868
+INFO - dpsgd_diffusion.py - 2024-10-25 04:49:58,984 - Loss: 0.1983, step: 94100
+INFO - dpsgd_diffusion.py - 2024-10-25 04:51:41,369 - Loss: 0.2174, step: 94200
+INFO - dpsgd_diffusion.py - 2024-10-25 04:53:23,901 - Loss: 0.2085, step: 94300
+INFO - dpsgd_diffusion.py - 2024-10-25 04:53:59,865 - Eps-value after 134 epochs: 9.3650
+INFO - dpsgd_diffusion.py - 2024-10-25 04:55:06,659 - Loss: 0.2292, step: 94400
+INFO - dpsgd_diffusion.py - 2024-10-25 04:56:49,431 - Loss: 0.1975, step: 94500
+INFO - dpsgd_diffusion.py - 2024-10-25 04:58:30,885 - Loss: 0.2018, step: 94600
+INFO - dpsgd_diffusion.py - 2024-10-25 05:00:10,954 - Loss: 0.2041, step: 94700
+INFO - dpsgd_diffusion.py - 2024-10-25 05:01:51,563 - Loss: 0.2052, step: 94800
+INFO - dpsgd_diffusion.py - 2024-10-25 05:03:30,815 - Loss: 0.2106, step: 94900
+INFO - dpsgd_diffusion.py - 2024-10-25 05:05:15,662 - Loss: 0.2220, step: 95000
+INFO - dpsgd_diffusion.py - 2024-10-25 05:05:57,681 - Eps-value after 135 epochs: 9.4051
+INFO - dpsgd_diffusion.py - 2024-10-25 05:06:56,725 - Loss: 0.2465, step: 95100
+INFO - dpsgd_diffusion.py - 2024-10-25 05:08:38,821 - Loss: 0.2313, step: 95200
+INFO - dpsgd_diffusion.py - 2024-10-25 05:10:18,938 - Loss: 0.2019, step: 95300
+INFO - dpsgd_diffusion.py - 2024-10-25 05:12:03,023 - Loss: 0.2111, step: 95400
+INFO - dpsgd_diffusion.py - 2024-10-25 05:13:46,496 - Loss: 0.2114, step: 95500
+INFO - dpsgd_diffusion.py - 2024-10-25 05:15:29,621 - Loss: 0.2066, step: 95600
+INFO - dpsgd_diffusion.py - 2024-10-25 05:17:11,591 - Loss: 0.1992, step: 95700
+INFO - dpsgd_diffusion.py - 2024-10-25 05:17:55,915 - Eps-value after 136 epochs: 9.4448
+INFO - dpsgd_diffusion.py - 2024-10-25 05:18:54,482 - Loss: 0.2178, step: 95800
+INFO - dpsgd_diffusion.py - 2024-10-25 05:20:35,785 - Loss: 0.2080, step: 95900
+INFO - dpsgd_diffusion.py - 2024-10-25 05:22:17,451 - Loss: 0.2282, step: 96000
+INFO - dpsgd_diffusion.py - 2024-10-25 05:22:17,461 - Saving snapshot checkpoint and sampling single batch at iteration 96000.
+WARNING - image.py - 2024-10-25 05:22:18,517 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-25 05:22:48,411 - FID at iteration 96000: 116.508435
+INFO - dpsgd_diffusion.py - 2024-10-25 05:24:32,784 - Loss: 0.2152, step: 96100
+INFO - dpsgd_diffusion.py - 2024-10-25 05:26:16,975 - Loss: 0.2124, step: 96200
+INFO - dpsgd_diffusion.py - 2024-10-25 05:28:01,895 - Loss: 0.2404, step: 96300
+INFO - dpsgd_diffusion.py - 2024-10-25 05:29:44,119 - Loss: 0.2081, step: 96400
+INFO - dpsgd_diffusion.py - 2024-10-25 05:30:34,176 - Eps-value after 137 epochs: 9.4844
+INFO - dpsgd_diffusion.py - 2024-10-25 05:31:26,085 - Loss: 0.1816, step: 96500
+INFO - dpsgd_diffusion.py - 2024-10-25 05:33:09,464 - Loss: 0.2215, step: 96600
+INFO - dpsgd_diffusion.py - 2024-10-25 05:34:49,539 - Loss: 0.2324, step: 96700
+INFO - dpsgd_diffusion.py - 2024-10-25 05:36:31,536 - Loss: 0.2137, step: 96800
+INFO - dpsgd_diffusion.py - 2024-10-25 05:38:15,316 - Loss: 0.2092, step: 96900
+INFO - dpsgd_diffusion.py - 2024-10-25 05:39:55,686 - Loss: 0.1830, step: 97000
+INFO - dpsgd_diffusion.py - 2024-10-25 05:41:34,770 - Loss: 0.1890, step: 97100
+INFO - dpsgd_diffusion.py - 2024-10-25 05:42:27,495 - Eps-value after 138 epochs: 9.5241
+INFO - dpsgd_diffusion.py - 2024-10-25 05:43:15,983 - Loss: 0.2141, step: 97200
+INFO - dpsgd_diffusion.py - 2024-10-25 05:44:58,774 - Loss: 0.2135, step: 97300
+INFO - dpsgd_diffusion.py - 2024-10-25 05:46:41,785 - Loss: 0.2052, step: 97400
+INFO - dpsgd_diffusion.py - 2024-10-25 05:48:22,330 - Loss: 0.2151, step: 97500
+INFO - dpsgd_diffusion.py - 2024-10-25 05:50:04,010 - Loss: 0.2253, step: 97600
+INFO - dpsgd_diffusion.py - 2024-10-25 05:51:47,945 - Loss: 0.2115, step: 97700
+INFO - dpsgd_diffusion.py - 2024-10-25 05:53:29,136 - Loss: 0.2310, step: 97800
+INFO - dpsgd_diffusion.py - 2024-10-25 05:54:26,690 - Eps-value after 139 epochs: 9.5638
+INFO - dpsgd_diffusion.py - 2024-10-25 05:55:12,317 - Loss: 0.1945, step: 97900
+INFO - dpsgd_diffusion.py - 2024-10-25 05:56:55,722 - Loss: 0.2189, step: 98000
+INFO - dpsgd_diffusion.py - 2024-10-25 05:56:55,730 - Saving snapshot checkpoint and sampling single batch at iteration 98000.
+WARNING - image.py - 2024-10-25 05:56:56,786 - 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 - 2024-10-25 05:57:26,854 - FID at iteration 98000: 114.870242
+INFO - dpsgd_diffusion.py - 2024-10-25 05:59:07,780 - Loss: 0.2239, step: 98100
+INFO - dpsgd_diffusion.py - 2024-10-25 06:00:50,180 - Loss: 0.2408, step: 98200
+INFO - dpsgd_diffusion.py - 2024-10-25 06:02:30,629 - Loss: 0.2184, step: 98300
+INFO - dpsgd_diffusion.py - 2024-10-25 06:04:12,142 - Loss: 0.2089, step: 98400
+INFO - dpsgd_diffusion.py - 2024-10-25 06:05:52,720 - Loss: 0.2234, step: 98500
+INFO - dpsgd_diffusion.py - 2024-10-25 06:06:54,688 - Eps-value after 140 epochs: 9.6035
+INFO - dpsgd_diffusion.py - 2024-10-25 06:07:35,687 - Loss: 0.2143, step: 98600
+INFO - dpsgd_diffusion.py - 2024-10-25 06:09:20,934 - Loss: 0.2183, step: 98700
+INFO - dpsgd_diffusion.py - 2024-10-25 06:11:04,648 - Loss: 0.2108, step: 98800
+INFO - dpsgd_diffusion.py - 2024-10-25 06:12:45,951 - Loss: 0.2322, step: 98900
+INFO - dpsgd_diffusion.py - 2024-10-25 06:14:27,374 - Loss: 0.2064, step: 99000
+INFO - dpsgd_diffusion.py - 2024-10-25 06:16:10,248 - Loss: 0.2184, step: 99100
+INFO - dpsgd_diffusion.py - 2024-10-25 06:17:49,211 - Loss: 0.2042, step: 99200
+INFO - dpsgd_diffusion.py - 2024-10-25 06:18:52,787 - Eps-value after 141 epochs: 9.6432
+INFO - dpsgd_diffusion.py - 2024-10-25 06:19:29,649 - Loss: 0.1774, step: 99300
+INFO - dpsgd_diffusion.py - 2024-10-25 06:21:10,636 - Loss: 0.2046, step: 99400
+INFO - dpsgd_diffusion.py - 2024-10-25 06:22:52,671 - Loss: 0.2008, step: 99500
+INFO - dpsgd_diffusion.py - 2024-10-25 06:24:36,862 - Loss: 0.2125, step: 99600
+INFO - dpsgd_diffusion.py - 2024-10-25 06:26:19,458 - Loss: 0.2262, step: 99700
+INFO - dpsgd_diffusion.py - 2024-10-25 06:28:02,346 - Loss: 0.2074, step: 99800
+INFO - dpsgd_diffusion.py - 2024-10-25 06:29:44,351 - Loss: 0.2237, step: 99900
+INFO - dpsgd_diffusion.py - 2024-10-25 06:30:54,573 - Eps-value after 142 epochs: 9.6829
+INFO - dpsgd_diffusion.py - 2024-10-25 06:31:27,531 - Loss: 0.2154, step: 100000
+INFO - dpsgd_diffusion.py - 2024-10-25 06:31:27,543 - Saving snapshot checkpoint and sampling single batch at iteration 100000.
+WARNING - image.py - 2024-10-25 06:31:28,599 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-25 06:31:58,449 - FID at iteration 100000: 114.459113
+INFO - dpsgd_diffusion.py - 2024-10-25 06:31:59,157 - Saving  checkpoint at iteration 100000
+INFO - dpsgd_diffusion.py - 2024-10-25 06:33:40,629 - Loss: 0.2136, step: 100100
+INFO - dpsgd_diffusion.py - 2024-10-25 06:35:21,650 - Loss: 0.1928, step: 100200
+INFO - dpsgd_diffusion.py - 2024-10-25 06:37:02,238 - Loss: 0.2004, step: 100300
+INFO - dpsgd_diffusion.py - 2024-10-25 06:38:41,947 - Loss: 0.2141, step: 100400
+INFO - dpsgd_diffusion.py - 2024-10-25 06:40:24,775 - Loss: 0.1849, step: 100500
+INFO - dpsgd_diffusion.py - 2024-10-25 06:42:07,923 - Loss: 0.2026, step: 100600
+INFO - dpsgd_diffusion.py - 2024-10-25 06:43:20,292 - Eps-value after 143 epochs: 9.7226
+INFO - dpsgd_diffusion.py - 2024-10-25 06:43:48,484 - Loss: 0.2144, step: 100700
+INFO - dpsgd_diffusion.py - 2024-10-25 06:45:29,322 - Loss: 0.2063, step: 100800
+INFO - dpsgd_diffusion.py - 2024-10-25 06:47:11,715 - Loss: 0.2126, step: 100900
+INFO - dpsgd_diffusion.py - 2024-10-25 06:48:56,622 - Loss: 0.2216, step: 101000
+INFO - dpsgd_diffusion.py - 2024-10-25 06:50:38,755 - Loss: 0.2109, step: 101100
+INFO - dpsgd_diffusion.py - 2024-10-25 06:52:21,320 - Loss: 0.1975, step: 101200
+INFO - dpsgd_diffusion.py - 2024-10-25 06:54:03,399 - Loss: 0.2257, step: 101300
+INFO - dpsgd_diffusion.py - 2024-10-25 06:55:20,514 - Eps-value after 144 epochs: 9.7623
+INFO - dpsgd_diffusion.py - 2024-10-25 06:55:44,862 - Loss: 0.2063, step: 101400
+INFO - dpsgd_diffusion.py - 2024-10-25 06:57:25,924 - Loss: 0.1914, step: 101500
+INFO - dpsgd_diffusion.py - 2024-10-25 06:59:10,248 - Loss: 0.2075, step: 101600
+INFO - dpsgd_diffusion.py - 2024-10-25 07:00:54,474 - Loss: 0.2150, step: 101700
+INFO - dpsgd_diffusion.py - 2024-10-25 07:02:34,481 - Loss: 0.2084, step: 101800
+INFO - dpsgd_diffusion.py - 2024-10-25 07:04:14,652 - Loss: 0.1980, step: 101900
+INFO - dpsgd_diffusion.py - 2024-10-25 07:05:58,672 - Loss: 0.2189, step: 102000
+INFO - dpsgd_diffusion.py - 2024-10-25 07:05:58,678 - Saving snapshot checkpoint and sampling single batch at iteration 102000.
+WARNING - image.py - 2024-10-25 07:05:59,737 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-25 07:06:29,463 - FID at iteration 102000: 114.106304
+INFO - dpsgd_diffusion.py - 2024-10-25 07:07:51,806 - Eps-value after 145 epochs: 9.8020
+INFO - dpsgd_diffusion.py - 2024-10-25 07:08:12,397 - Loss: 0.2290, step: 102100
+INFO - dpsgd_diffusion.py - 2024-10-25 07:09:53,098 - Loss: 0.2220, step: 102200
+INFO - dpsgd_diffusion.py - 2024-10-25 07:11:33,819 - Loss: 0.2021, step: 102300
+INFO - dpsgd_diffusion.py - 2024-10-25 07:13:15,600 - Loss: 0.2379, step: 102400
+INFO - dpsgd_diffusion.py - 2024-10-25 07:14:58,871 - Loss: 0.2232, step: 102500
+INFO - dpsgd_diffusion.py - 2024-10-25 07:16:42,322 - Loss: 0.2154, step: 102600
+INFO - dpsgd_diffusion.py - 2024-10-25 07:18:27,208 - Loss: 0.2098, step: 102700
+INFO - dpsgd_diffusion.py - 2024-10-25 07:19:51,430 - Eps-value after 146 epochs: 9.8412
+INFO - dpsgd_diffusion.py - 2024-10-25 07:20:07,880 - Loss: 0.2347, step: 102800
+INFO - dpsgd_diffusion.py - 2024-10-25 07:21:49,696 - Loss: 0.2127, step: 102900
+INFO - dpsgd_diffusion.py - 2024-10-25 07:23:32,263 - Loss: 0.2140, step: 103000
+INFO - dpsgd_diffusion.py - 2024-10-25 07:25:13,203 - Loss: 0.2179, step: 103100
+INFO - dpsgd_diffusion.py - 2024-10-25 07:26:54,839 - Loss: 0.2113, step: 103200
+INFO - dpsgd_diffusion.py - 2024-10-25 07:28:35,149 - Loss: 0.1832, step: 103300
+INFO - dpsgd_diffusion.py - 2024-10-25 07:30:16,925 - Loss: 0.1956, step: 103400
+INFO - dpsgd_diffusion.py - 2024-10-25 07:31:46,260 - Eps-value after 147 epochs: 9.8797
+INFO - dpsgd_diffusion.py - 2024-10-25 07:31:58,584 - Loss: 0.2129, step: 103500
+INFO - dpsgd_diffusion.py - 2024-10-25 07:33:39,927 - Loss: 0.2051, step: 103600
+INFO - dpsgd_diffusion.py - 2024-10-25 07:35:21,753 - Loss: 0.2084, step: 103700
+INFO - dpsgd_diffusion.py - 2024-10-25 07:37:01,799 - Loss: 0.1913, step: 103800
+INFO - dpsgd_diffusion.py - 2024-10-25 07:38:41,175 - Loss: 0.2062, step: 103900
+INFO - dpsgd_diffusion.py - 2024-10-25 07:40:21,981 - Loss: 0.1948, step: 104000
+INFO - dpsgd_diffusion.py - 2024-10-25 07:40:21,990 - Saving snapshot checkpoint and sampling single batch at iteration 104000.
+WARNING - image.py - 2024-10-25 07:40:23,045 - Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
+INFO - dpsgd_diffusion.py - 2024-10-25 07:40:52,978 - FID at iteration 104000: 113.768921
+INFO - dpsgd_diffusion.py - 2024-10-25 07:42:35,206 - Loss: 0.1961, step: 104100
+INFO - dpsgd_diffusion.py - 2024-10-25 07:44:08,756 - Eps-value after 148 epochs: 9.9183
+INFO - dpsgd_diffusion.py - 2024-10-25 07:44:16,973 - Loss: 0.2154, step: 104200
+INFO - dpsgd_diffusion.py - 2024-10-25 07:45:55,767 - Loss: 0.2164, step: 104300
+INFO - dpsgd_diffusion.py - 2024-10-25 07:47:36,308 - Loss: 0.1986, step: 104400
+INFO - dpsgd_diffusion.py - 2024-10-25 07:49:16,629 - Loss: 0.1926, step: 104500
+INFO - dpsgd_diffusion.py - 2024-10-25 07:50:58,296 - Loss: 0.2220, step: 104600
+INFO - dpsgd_diffusion.py - 2024-10-25 07:52:38,233 - Loss: 0.2155, step: 104700
+INFO - dpsgd_diffusion.py - 2024-10-25 07:54:18,270 - Loss: 0.2093, step: 104800
+INFO - dpsgd_diffusion.py - 2024-10-25 07:55:54,248 - Eps-value after 149 epochs: 9.9568
+INFO - dpsgd_diffusion.py - 2024-10-25 07:55:58,369 - Loss: 0.1819, step: 104900
+INFO - dpsgd_diffusion.py - 2024-10-25 07:57:39,087 - Loss: 0.2193, step: 105000
+INFO - dpsgd_diffusion.py - 2024-10-25 07:59:19,829 - Loss: 0.1959, step: 105100
+INFO - dpsgd_diffusion.py - 2024-10-25 08:01:00,764 - Loss: 0.1988, step: 105200
+INFO - dpsgd_diffusion.py - 2024-10-25 08:02:41,936 - Loss: 0.1901, step: 105300
+INFO - dpsgd_diffusion.py - 2024-10-25 08:04:24,306 - Loss: 0.2140, step: 105400
+INFO - dpsgd_diffusion.py - 2024-10-25 08:06:03,999 - Loss: 0.2116, step: 105500
+INFO - dpsgd_diffusion.py - 2024-10-25 08:07:47,663 - Loss: 0.2253, step: 105600
+INFO - dpsgd_diffusion.py - 2024-10-25 08:07:47,685 - Eps-value after 150 epochs: 9.9953
+INFO - dpsgd_diffusion.py - 2024-10-25 08:07:48,476 - Saving final checkpoint.
+INFO - dpsgd_diffusion.py - 2024-10-25 08:07:48,478 - start to generate 60000 samples
+INFO - dpsgd_diffusion.py - 2024-10-25 08:28:54,675 - Generation Finished!
+INFO - dataset_loader.py - 2024-10-26 14:09:43,492 - delta is reset as 2.07404851125286e-06
+INFO - evaluator.py - 2024-10-26 14:10:22,187 - Epoch: 0 Train acc: 15.014545454545456 Val acc: 18.86 Test acc18.93; Train loss: 0.01861388004693118 Val loss: 0.002283462905883789
+INFO - evaluator.py - 2024-10-26 14:10:40,894 - Epoch: 1 Train acc: 22.874545454545455 Val acc: 21.8 Test acc21.7; Train loss: 0.0159178026155992 Val loss: 0.0020491133213043212
+INFO - evaluator.py - 2024-10-26 14:10:58,808 - Epoch: 2 Train acc: 33.75090909090909 Val acc: 17.02 Test acc16.27; Train loss: 0.013397879524664445 Val loss: 0.003458361864089966
+INFO - evaluator.py - 2024-10-26 14:11:17,319 - Epoch: 3 Train acc: 42.696363636363635 Val acc: 12.839999999999998 Test acc12.889999999999999; Train loss: 0.011304961293393916 Val loss: 0.04186669540405273
+INFO - evaluator.py - 2024-10-26 14:11:35,225 - Epoch: 4 Train acc: 48.04727272727273 Val acc: 9.84 Test acc9.99; Train loss: 0.010339483406326988 Val loss: 0.09598612670898438
+INFO - evaluator.py - 2024-10-26 14:11:53,058 - Epoch: 5 Train acc: 52.85818181818181 Val acc: 11.16 Test acc10.549999999999999; Train loss: 0.009550223903222518 Val loss: 1.282722509765625
+INFO - evaluator.py - 2024-10-26 14:12:11,675 - Epoch: 6 Train acc: 57.46181818181818 Val acc: 13.639999999999999 Test acc13.819999999999999; Train loss: 0.008771907676349987 Val loss: 0.08684271850585938
+INFO - evaluator.py - 2024-10-26 14:12:30,325 - Epoch: 7 Train acc: 59.80545454545455 Val acc: 33.239999999999995 Test acc32.800000000000004; Train loss: 0.00826530499458313 Val loss: 0.0073063543319702145
+INFO - evaluator.py - 2024-10-26 14:12:48,559 - Epoch: 8 Train acc: 63.53636363636363 Val acc: 17.380000000000003 Test acc16.8; Train loss: 0.007538490879535675 Val loss: 0.013976483917236328
+INFO - evaluator.py - 2024-10-26 14:13:07,048 - Epoch: 9 Train acc: 67.72181818181818 Val acc: 21.0 Test acc21.45; Train loss: 0.006830102132667194 Val loss: 0.032285881042480466
+INFO - evaluator.py - 2024-10-26 14:13:25,551 - Epoch: 10 Train acc: 71.27636363636364 Val acc: 10.66 Test acc10.03; Train loss: 0.006186395661397414 Val loss: 1.703451708984375
+INFO - evaluator.py - 2024-10-26 14:13:43,970 - Epoch: 11 Train acc: 75.53636363636363 Val acc: 15.06 Test acc15.120000000000001; Train loss: 0.005355050039291382 Val loss: 0.05855643463134766
+INFO - evaluator.py - 2024-10-26 14:14:02,546 - Epoch: 12 Train acc: 78.52 Val acc: 16.68 Test acc16.93; Train loss: 0.004835751440308311 Val loss: 0.013958157920837402
+INFO - evaluator.py - 2024-10-26 14:14:20,813 - Epoch: 13 Train acc: 80.73818181818181 Val acc: 29.84 Test acc29.68; Train loss: 0.004313509670712731 Val loss: 0.008164561462402345
+INFO - evaluator.py - 2024-10-26 14:14:39,469 - Epoch: 14 Train acc: 82.48363636363636 Val acc: 28.96 Test acc29.849999999999998; Train loss: 0.003916169941425324 Val loss: 0.006304430294036865
+INFO - evaluator.py - 2024-10-26 14:14:57,830 - Epoch: 15 Train acc: 83.78545454545454 Val acc: 25.56 Test acc25.66; Train loss: 0.003669068292054263 Val loss: 0.009189882850646973
+INFO - evaluator.py - 2024-10-26 14:15:16,037 - Epoch: 16 Train acc: 84.91090909090909 Val acc: 33.44 Test acc34.13; Train loss: 0.003465553998405283 Val loss: 0.005557067108154297
+INFO - evaluator.py - 2024-10-26 14:15:34,231 - Epoch: 17 Train acc: 85.66 Val acc: 33.2 Test acc33.21; Train loss: 0.0032478335367007688 Val loss: 0.00497376184463501
+INFO - evaluator.py - 2024-10-26 14:15:52,798 - Epoch: 18 Train acc: 85.77636363636364 Val acc: 24.98 Test acc25.2; Train loss: 0.003235261418331753 Val loss: 0.007944511890411376
+INFO - evaluator.py - 2024-10-26 14:16:11,215 - Epoch: 19 Train acc: 86.39454545454545 Val acc: 30.080000000000002 Test acc31.14; Train loss: 0.0030967684721404857 Val loss: 0.005569573783874512
+INFO - evaluator.py - 2024-10-26 14:16:29,725 - Epoch: 20 Train acc: 87.08545454545454 Val acc: 28.08 Test acc29.18; Train loss: 0.002940645830468698 Val loss: 0.007337588500976562
+INFO - evaluator.py - 2024-10-26 14:16:48,080 - Epoch: 21 Train acc: 87.53636363636363 Val acc: 22.439999999999998 Test acc23.46; Train loss: 0.0028550562712279233 Val loss: 0.010127158546447754
+INFO - evaluator.py - 2024-10-26 14:17:06,461 - Epoch: 22 Train acc: 87.47818181818182 Val acc: 27.3 Test acc26.810000000000002; Train loss: 0.002852259696071798 Val loss: 0.006854809665679931
+INFO - evaluator.py - 2024-10-26 14:17:24,975 - Epoch: 23 Train acc: 87.88181818181819 Val acc: 25.919999999999998 Test acc26.1; Train loss: 0.0027248669637875123 Val loss: 0.010249069404602051
+INFO - evaluator.py - 2024-10-26 14:17:43,370 - Epoch: 24 Train acc: 88.11636363636364 Val acc: 18.96 Test acc20.119999999999997; Train loss: 0.0026982152061028916 Val loss: 0.01617881374359131
+INFO - evaluator.py - 2024-10-26 14:18:02,022 - Epoch: 25 Train acc: 88.44545454545455 Val acc: 26.96 Test acc27.48; Train loss: 0.0026297103732824327 Val loss: 0.010487296867370606
+INFO - evaluator.py - 2024-10-26 14:18:20,442 - Epoch: 26 Train acc: 88.66363636363637 Val acc: 20.119999999999997 Test acc20.86; Train loss: 0.0025864665416153996 Val loss: 0.011761844253540038
+INFO - evaluator.py - 2024-10-26 14:18:38,492 - Epoch: 27 Train acc: 88.80363636363636 Val acc: 31.080000000000002 Test acc31.65; Train loss: 0.002561759263547984 Val loss: 0.007416973686218261
+INFO - evaluator.py - 2024-10-26 14:18:56,506 - Epoch: 28 Train acc: 88.89272727272727 Val acc: 17.96 Test acc18.310000000000002; Train loss: 0.002523355151306499 Val loss: 0.008916540145874024
+INFO - evaluator.py - 2024-10-26 14:19:14,947 - Epoch: 29 Train acc: 88.95818181818181 Val acc: 17.9 Test acc18.240000000000002; Train loss: 0.0025298599779605864 Val loss: 0.018185325241088866
+INFO - evaluator.py - 2024-10-26 14:19:33,327 - Epoch: 30 Train acc: 89.12181818181818 Val acc: 21.44 Test acc21.490000000000002; Train loss: 0.002466095954721624 Val loss: 0.008612784576416016
+INFO - evaluator.py - 2024-10-26 14:19:51,961 - Epoch: 31 Train acc: 89.39636363636365 Val acc: 12.879999999999999 Test acc12.620000000000001; Train loss: 0.0024319001974029975 Val loss: 0.029300729751586915
+INFO - evaluator.py - 2024-10-26 14:20:10,541 - Epoch: 32 Train acc: 89.52909090909091 Val acc: 16.46 Test acc16.99; Train loss: 0.002372847965359688 Val loss: 0.019331645584106445
+INFO - evaluator.py - 2024-10-26 14:20:29,140 - Epoch: 33 Train acc: 89.64727272727274 Val acc: 21.02 Test acc21.01; Train loss: 0.0023538839677518064 Val loss: 0.01277662410736084
+INFO - evaluator.py - 2024-10-26 14:20:47,784 - Epoch: 34 Train acc: 89.64727272727274 Val acc: 25.56 Test acc25.31; Train loss: 0.002387020493637432 Val loss: 0.007917161083221436
+INFO - evaluator.py - 2024-10-26 14:21:06,396 - Epoch: 35 Train acc: 89.9 Val acc: 22.74 Test acc23.0; Train loss: 0.002321677076952024 Val loss: 0.012597501182556153
+INFO - evaluator.py - 2024-10-26 14:21:25,183 - Epoch: 36 Train acc: 89.89272727272727 Val acc: 28.92 Test acc29.14; Train loss: 0.0023023515500805595 Val loss: 0.01014600601196289
+INFO - evaluator.py - 2024-10-26 14:21:43,615 - Epoch: 37 Train acc: 89.91090909090909 Val acc: 17.119999999999997 Test acc17.43; Train loss: 0.002307438108866865 Val loss: 0.01384342269897461
+INFO - evaluator.py - 2024-10-26 14:22:02,155 - Epoch: 38 Train acc: 90.18545454545455 Val acc: 20.62 Test acc20.380000000000003; Train loss: 0.002274379942769354 Val loss: 0.007482813835144043
+INFO - evaluator.py - 2024-10-26 14:22:20,435 - Epoch: 39 Train acc: 90.1509090909091 Val acc: 18.82 Test acc19.07; Train loss: 0.002297822770069946 Val loss: 0.009632501029968262
+INFO - evaluator.py - 2024-10-26 14:22:39,013 - Epoch: 40 Train acc: 90.47454545454545 Val acc: 15.78 Test acc16.49; Train loss: 0.002210790512643077 Val loss: 0.016812101364135742
+INFO - evaluator.py - 2024-10-26 14:22:57,434 - Epoch: 41 Train acc: 90.02363636363636 Val acc: 19.18 Test acc19.72; Train loss: 0.0022839875516566365 Val loss: 0.01028322467803955
+INFO - evaluator.py - 2024-10-26 14:23:15,999 - Epoch: 42 Train acc: 90.27090909090909 Val acc: 26.44 Test acc26.44; Train loss: 0.0022270340152762153 Val loss: 0.006566728019714355
+INFO - evaluator.py - 2024-10-26 14:23:34,363 - Epoch: 43 Train acc: 90.76727272727273 Val acc: 16.56 Test acc16.150000000000002; Train loss: 0.002135362379930236 Val loss: 0.023481878280639648
+INFO - evaluator.py - 2024-10-26 14:23:52,901 - Epoch: 44 Train acc: 90.67272727272727 Val acc: 27.939999999999998 Test acc28.26; Train loss: 0.0021108948200941084 Val loss: 0.00584222993850708
+INFO - evaluator.py - 2024-10-26 14:24:10,973 - Epoch: 45 Train acc: 90.43272727272728 Val acc: 23.28 Test acc23.95; Train loss: 0.002222662628645247 Val loss: 0.0118391939163208
+INFO - evaluator.py - 2024-10-26 14:24:30,152 - Epoch: 46 Train acc: 91.25090909090909 Val acc: 23.84 Test acc23.830000000000002; Train loss: 0.0020344845442609354 Val loss: 0.01225621223449707
+INFO - evaluator.py - 2024-10-26 14:24:48,373 - Epoch: 47 Train acc: 90.68727272727273 Val acc: 18.22 Test acc17.77; Train loss: 0.0021709006943485955 Val loss: 0.013316797065734864
+INFO - evaluator.py - 2024-10-26 14:25:08,158 - Epoch: 48 Train acc: 91.36181818181818 Val acc: 25.040000000000003 Test acc25.119999999999997; Train loss: 0.00203737325722521 Val loss: 0.008970665740966798
+INFO - evaluator.py - 2024-10-26 14:25:27,218 - Epoch: 49 Train acc: 90.87636363636364 Val acc: 19.24 Test acc19.08; Train loss: 0.002112580169737339 Val loss: 0.011067705154418945
+INFO - evaluator.py - 2024-10-26 14:25:46,168 - Epoch: 50 Train acc: 90.81636363636363 Val acc: 19.439999999999998 Test acc19.830000000000002; Train loss: 0.0021027242052284153 Val loss: 0.011338262557983399
+INFO - evaluator.py - 2024-10-26 14:26:04,035 - Epoch: 51 Train acc: 91.55272727272728 Val acc: 14.46 Test acc14.78; Train loss: 0.0019564501935785466 Val loss: 0.01721540412902832
+INFO - evaluator.py - 2024-10-26 14:26:22,434 - Epoch: 52 Train acc: 91.51272727272726 Val acc: 29.74 Test acc30.44; Train loss: 0.001965766278586604 Val loss: 0.007548541069030762
+INFO - evaluator.py - 2024-10-26 14:26:41,005 - Epoch: 53 Train acc: 91.52 Val acc: 22.24 Test acc22.6; Train loss: 0.001948077308589762 Val loss: 0.014299720764160155
+INFO - evaluator.py - 2024-10-26 14:26:59,985 - Epoch: 54 Train acc: 91.24181818181818 Val acc: 15.920000000000002 Test acc15.36; Train loss: 0.002013479431650855 Val loss: 0.022196928024291993
+INFO - evaluator.py - 2024-10-26 14:27:18,780 - Epoch: 55 Train acc: 91.15454545454546 Val acc: 23.98 Test acc24.310000000000002; Train loss: 0.002032834431258115 Val loss: 0.015054377365112304
+INFO - evaluator.py - 2024-10-26 14:27:37,430 - Epoch: 56 Train acc: 91.55636363636364 Val acc: 15.160000000000002 Test acc15.310000000000002; Train loss: 0.001947996732863513 Val loss: 0.020683409881591796
+INFO - evaluator.py - 2024-10-26 14:27:55,710 - Epoch: 57 Train acc: 91.37454545454545 Val acc: 17.34 Test acc18.57; Train loss: 0.0019990380869670346 Val loss: 0.010516492462158203
+INFO - evaluator.py - 2024-10-26 14:28:14,159 - Epoch: 58 Train acc: 91.69636363636363 Val acc: 21.12 Test acc20.61; Train loss: 0.0019140617068518291 Val loss: 0.012984418487548829
+INFO - evaluator.py - 2024-10-26 14:28:32,505 - Epoch: 59 Train acc: 91.79272727272728 Val acc: 17.4 Test acc17.54; Train loss: 0.001874005055156621 Val loss: 0.010135948944091797
+INFO - evaluator.py - 2024-10-26 14:28:50,872 - Epoch: 60 Train acc: 97.9509090909091 Val acc: 26.68 Test acc26.14; Train loss: 0.0004980025662363253 Val loss: 0.00929108943939209
+INFO - evaluator.py - 2024-10-26 14:29:09,297 - Epoch: 61 Train acc: 98.99272727272728 Val acc: 19.36 Test acc19.07; Train loss: 0.0002518633887510408 Val loss: 0.013696688842773438
+INFO - evaluator.py - 2024-10-26 14:29:27,616 - Epoch: 62 Train acc: 99.33454545454545 Val acc: 19.24 Test acc19.54; Train loss: 0.00017709162583447654 Val loss: 0.0184653564453125
+INFO - evaluator.py - 2024-10-26 14:29:46,006 - Epoch: 63 Train acc: 99.57636363636364 Val acc: 19.8 Test acc19.29; Train loss: 0.00012854714487382972 Val loss: 0.018137005996704102
+INFO - evaluator.py - 2024-10-26 14:30:04,282 - Epoch: 64 Train acc: 99.57454545454546 Val acc: 18.78 Test acc19.139999999999997; Train loss: 0.00011881137793164023 Val loss: 0.024677830505371093
+INFO - evaluator.py - 2024-10-26 14:30:22,602 - Epoch: 65 Train acc: 99.67272727272727 Val acc: 16.1 Test acc15.790000000000001; Train loss: 9.703429847193713e-05 Val loss: 0.04245401077270508
+INFO - evaluator.py - 2024-10-26 14:30:41,020 - Epoch: 66 Train acc: 99.63636363636364 Val acc: 15.939999999999998 Test acc15.47; Train loss: 0.00010281096408037807 Val loss: 0.036763818359375
+INFO - evaluator.py - 2024-10-26 14:30:59,496 - Epoch: 67 Train acc: 99.4890909090909 Val acc: 10.280000000000001 Test acc9.67; Train loss: 0.00013565727304878897 Val loss: 0.06931924285888671
+INFO - evaluator.py - 2024-10-26 14:31:17,903 - Epoch: 68 Train acc: 99.62545454545455 Val acc: 9.520000000000001 Test acc9.5; Train loss: 0.00011150056136645038 Val loss: 0.11341277465820312
+INFO - evaluator.py - 2024-10-26 14:31:36,718 - Epoch: 69 Train acc: 99.24909090909091 Val acc: 10.8 Test acc10.93; Train loss: 0.00019014127613045274 Val loss: 0.10500220031738282
+INFO - evaluator.py - 2024-10-26 14:31:55,137 - Epoch: 70 Train acc: 98.66727272727273 Val acc: 10.52 Test acc11.020000000000001; Train loss: 0.0003058623705863614 Val loss: 0.10203723754882812
+INFO - evaluator.py - 2024-10-26 14:32:13,578 - Epoch: 71 Train acc: 98.79454545454546 Val acc: 10.280000000000001 Test acc10.01; Train loss: 0.00028539931361817503 Val loss: 0.15015975036621093
+INFO - evaluator.py - 2024-10-26 14:32:32,284 - Epoch: 72 Train acc: 98.70181818181818 Val acc: 9.58 Test acc9.28; Train loss: 0.0003122298176400363 Val loss: 0.08637455139160156
+INFO - evaluator.py - 2024-10-26 14:32:51,095 - Epoch: 73 Train acc: 98.56 Val acc: 10.32 Test acc10.68; Train loss: 0.0003368938317564739 Val loss: 0.11634847717285156
+INFO - evaluator.py - 2024-10-26 14:33:10,313 - Epoch: 74 Train acc: 98.42181818181818 Val acc: 8.88 Test acc8.94; Train loss: 0.00036645841525274924 Val loss: 0.08424293365478516
+INFO - evaluator.py - 2024-10-26 14:33:29,445 - Epoch: 75 Train acc: 98.39090909090909 Val acc: 12.520000000000001 Test acc12.520000000000001; Train loss: 0.0003775243629108776 Val loss: 0.05344164199829102
+INFO - evaluator.py - 2024-10-26 14:33:48,063 - Epoch: 76 Train acc: 98.22 Val acc: 11.62 Test acc11.899999999999999; Train loss: 0.0004207794872027907 Val loss: 0.055840123748779294
+INFO - evaluator.py - 2024-10-26 14:34:05,782 - Epoch: 77 Train acc: 98.39272727272727 Val acc: 14.04 Test acc14.42; Train loss: 0.0003854381132193587 Val loss: 0.0528526725769043
+INFO - evaluator.py - 2024-10-26 14:34:23,459 - Epoch: 78 Train acc: 98.18909090909091 Val acc: 17.04 Test acc17.07; Train loss: 0.0004173509213311428 Val loss: 0.03255628280639648
+INFO - evaluator.py - 2024-10-26 14:34:41,429 - Epoch: 79 Train acc: 98.21636363636364 Val acc: 16.5 Test acc16.509999999999998; Train loss: 0.0004163417454046959 Val loss: 0.030619656753540038
+INFO - evaluator.py - 2024-10-26 14:34:59,310 - Epoch: 80 Train acc: 98.07818181818182 Val acc: 13.4 Test acc13.950000000000001; Train loss: 0.0004508997590281069 Val loss: 0.03897881774902344
+INFO - evaluator.py - 2024-10-26 14:35:17,301 - Epoch: 81 Train acc: 97.81454545454545 Val acc: 10.299999999999999 Test acc10.27; Train loss: 0.0004968601640737192 Val loss: 0.07161763305664062
+INFO - evaluator.py - 2024-10-26 14:35:35,852 - Epoch: 82 Train acc: 98.15272727272728 Val acc: 11.1 Test acc11.200000000000001; Train loss: 0.0004352867738936435 Val loss: 0.05427826690673828
+INFO - evaluator.py - 2024-10-26 14:35:54,092 - Epoch: 83 Train acc: 97.88909090909091 Val acc: 10.26 Test acc10.73; Train loss: 0.00048020741522142833 Val loss: 0.04855219039916992
+INFO - evaluator.py - 2024-10-26 14:36:12,391 - Epoch: 84 Train acc: 98.13636363636363 Val acc: 16.32 Test acc15.939999999999998; Train loss: 0.00044637393551793966 Val loss: 0.025809529876708984
+INFO - evaluator.py - 2024-10-26 14:36:31,275 - Epoch: 85 Train acc: 98.32363636363637 Val acc: 13.52 Test acc13.63; Train loss: 0.0003960447892969982 Val loss: 0.04406749496459961
+INFO - evaluator.py - 2024-10-26 14:36:49,369 - Epoch: 86 Train acc: 97.99636363636364 Val acc: 16.48 Test acc17.2; Train loss: 0.00046659223836931316 Val loss: 0.032016099166870114
+INFO - evaluator.py - 2024-10-26 14:37:07,465 - Epoch: 87 Train acc: 98.22363636363637 Val acc: 12.34 Test acc12.22; Train loss: 0.00041511393946341493 Val loss: 0.04488995819091797
+INFO - evaluator.py - 2024-10-26 14:37:25,636 - Epoch: 88 Train acc: 98.2 Val acc: 15.160000000000002 Test acc15.39; Train loss: 0.00043023970721458844 Val loss: 0.026630177688598634
+INFO - evaluator.py - 2024-10-26 14:37:43,557 - Epoch: 89 Train acc: 98.21454545454546 Val acc: 22.32 Test acc22.17; Train loss: 0.0004174852940423245 Val loss: 0.012784780502319336
+INFO - evaluator.py - 2024-10-26 14:38:01,468 - Epoch: 90 Train acc: 97.87818181818182 Val acc: 17.14 Test acc17.150000000000002; Train loss: 0.0004780877170830288 Val loss: 0.01665402946472168
+INFO - evaluator.py - 2024-10-26 14:38:19,551 - Epoch: 91 Train acc: 98.39272727272727 Val acc: 24.32 Test acc24.33; Train loss: 0.0003840247913263738 Val loss: 0.01282232437133789
+INFO - evaluator.py - 2024-10-26 14:38:37,837 - Epoch: 92 Train acc: 98.02545454545455 Val acc: 16.16 Test acc15.8; Train loss: 0.00044400061264803463 Val loss: 0.020559578323364257
+INFO - evaluator.py - 2024-10-26 14:38:56,124 - Epoch: 93 Train acc: 98.16545454545455 Val acc: 21.52 Test acc20.95; Train loss: 0.0004369782712987878 Val loss: 0.012922397041320801
+INFO - evaluator.py - 2024-10-26 14:39:14,378 - Epoch: 94 Train acc: 98.1509090909091 Val acc: 19.86 Test acc19.71; Train loss: 0.0004249850021929226 Val loss: 0.02328617820739746
+INFO - evaluator.py - 2024-10-26 14:39:32,320 - Epoch: 95 Train acc: 98.33454545454545 Val acc: 14.64 Test acc14.46; Train loss: 0.00039265058720484375 Val loss: 0.027183742904663084
+INFO - evaluator.py - 2024-10-26 14:39:50,466 - Epoch: 96 Train acc: 98.38545454545454 Val acc: 9.9 Test acc10.059999999999999; Train loss: 0.00038957687274298887 Val loss: 0.033608868408203124
+INFO - evaluator.py - 2024-10-26 14:40:08,686 - Epoch: 97 Train acc: 98.32363636363637 Val acc: 24.959999999999997 Test acc24.7; Train loss: 0.00039205889256501737 Val loss: 0.008849457359313966
+INFO - evaluator.py - 2024-10-26 14:40:26,935 - Epoch: 98 Train acc: 98.15818181818182 Val acc: 20.22 Test acc19.45; Train loss: 0.00044032543228769846 Val loss: 0.01049863109588623
+INFO - evaluator.py - 2024-10-26 14:40:45,296 - Epoch: 99 Train acc: 98.02909090909091 Val acc: 23.98 Test acc24.15; Train loss: 0.0004468670566396957 Val loss: 0.008638600730895996
+INFO - evaluator.py - 2024-10-26 14:41:03,319 - Epoch: 100 Train acc: 98.27454545454546 Val acc: 12.1 Test acc12.43; Train loss: 0.00041942707345905627 Val loss: 0.023299740600585938
+INFO - evaluator.py - 2024-10-26 14:41:20,814 - Epoch: 101 Train acc: 98.1490909090909 Val acc: 23.200000000000003 Test acc23.07; Train loss: 0.0004365564987063408 Val loss: 0.01177143268585205
+INFO - evaluator.py - 2024-10-26 14:41:38,299 - Epoch: 102 Train acc: 98.16363636363636 Val acc: 15.299999999999999 Test acc15.07; Train loss: 0.0004332751477052542 Val loss: 0.03150205841064453
+INFO - evaluator.py - 2024-10-26 14:41:56,167 - Epoch: 103 Train acc: 98.52181818181818 Val acc: 21.279999999999998 Test acc21.51; Train loss: 0.00035227511481974614 Val loss: 0.013189926147460937
+INFO - evaluator.py - 2024-10-26 14:42:14,165 - Epoch: 104 Train acc: 97.82363636363637 Val acc: 21.44 Test acc21.51; Train loss: 0.00049976628144187 Val loss: 0.01443074722290039
+INFO - evaluator.py - 2024-10-26 14:42:32,361 - Epoch: 105 Train acc: 98.48727272727272 Val acc: 13.98 Test acc14.49; Train loss: 0.0003620731575414538 Val loss: 0.028453032302856444
+INFO - evaluator.py - 2024-10-26 14:42:50,281 - Epoch: 106 Train acc: 97.59272727272727 Val acc: 16.98 Test acc16.93; Train loss: 0.0005415140788324855 Val loss: 0.019940346145629884
+INFO - evaluator.py - 2024-10-26 14:43:08,173 - Epoch: 107 Train acc: 98.68545454545455 Val acc: 22.64 Test acc23.549999999999997; Train loss: 0.00031219620407050983 Val loss: 0.01696130485534668
+INFO - evaluator.py - 2024-10-26 14:43:26,318 - Epoch: 108 Train acc: 98.30909090909091 Val acc: 17.96 Test acc17.73; Train loss: 0.00041141715394333006 Val loss: 0.024880505752563477
+INFO - evaluator.py - 2024-10-26 14:43:45,206 - Epoch: 109 Train acc: 98.21454545454546 Val acc: 17.84 Test acc17.25; Train loss: 0.00042420452461493284 Val loss: 0.01465998592376709
+INFO - evaluator.py - 2024-10-26 14:44:03,515 - Epoch: 110 Train acc: 98.2909090909091 Val acc: 22.0 Test acc21.57; Train loss: 0.00037285954084416683 Val loss: 0.015225676155090332
+INFO - evaluator.py - 2024-10-26 14:44:21,663 - Epoch: 111 Train acc: 98.44181818181819 Val acc: 25.840000000000003 Test acc25.4; Train loss: 0.0003804812608921731 Val loss: 0.011067831611633301
+INFO - evaluator.py - 2024-10-26 14:44:40,133 - Epoch: 112 Train acc: 98.24363636363637 Val acc: 26.939999999999998 Test acc27.389999999999997; Train loss: 0.0004246496107175269 Val loss: 0.00941518783569336
+INFO - evaluator.py - 2024-10-26 14:44:58,640 - Epoch: 113 Train acc: 98.11454545454545 Val acc: 22.58 Test acc22.46; Train loss: 0.0004261750762435523 Val loss: 0.012943670654296874
+INFO - evaluator.py - 2024-10-26 14:45:17,377 - Epoch: 114 Train acc: 98.1509090909091 Val acc: 16.919999999999998 Test acc17.150000000000002; Train loss: 0.00042759072023697877 Val loss: 0.019598682022094728
+INFO - evaluator.py - 2024-10-26 14:45:36,386 - Epoch: 115 Train acc: 98.21272727272728 Val acc: 14.099999999999998 Test acc13.780000000000001; Train loss: 0.0004062625692522323 Val loss: 0.025625044631958006
+INFO - evaluator.py - 2024-10-26 14:45:55,341 - Epoch: 116 Train acc: 98.4 Val acc: 18.459999999999997 Test acc19.38; Train loss: 0.00039445598552172834 Val loss: 0.02261109619140625
+INFO - evaluator.py - 2024-10-26 14:46:13,867 - Epoch: 117 Train acc: 98.33636363636363 Val acc: 22.42 Test acc21.97; Train loss: 0.00039264477224258535 Val loss: 0.010643023681640626
+INFO - evaluator.py - 2024-10-26 14:46:32,477 - Epoch: 118 Train acc: 98.26 Val acc: 18.62 Test acc18.55; Train loss: 0.00040697715421291917 Val loss: 0.015838291549682616
+INFO - evaluator.py - 2024-10-26 14:46:51,062 - Epoch: 119 Train acc: 98.2309090909091 Val acc: 19.759999999999998 Test acc19.23; Train loss: 0.0004168117141224105 Val loss: 0.02009123229980469
+INFO - evaluator.py - 2024-10-26 14:47:09,763 - Epoch: 120 Train acc: 99.79818181818182 Val acc: 27.0 Test acc26.8; Train loss: 7.110022038369524e-05 Val loss: 0.011166125297546388
+INFO - evaluator.py - 2024-10-26 14:47:28,754 - Epoch: 121 Train acc: 99.97636363636364 Val acc: 25.94 Test acc25.430000000000003; Train loss: 2.7488987454192034e-05 Val loss: 0.012900094985961914
+INFO - evaluator.py - 2024-10-26 14:47:46,898 - Epoch: 122 Train acc: 99.98181818181818 Val acc: 27.200000000000003 Test acc26.51; Train loss: 2.1906148919052528e-05 Val loss: 0.012731936836242675
+INFO - evaluator.py - 2024-10-26 14:48:05,509 - Epoch: 123 Train acc: 99.99090909090908 Val acc: 26.479999999999997 Test acc25.919999999999998; Train loss: 1.7299848922464827e-05 Val loss: 0.014121161270141602
+INFO - evaluator.py - 2024-10-26 14:48:23,797 - Epoch: 124 Train acc: 99.99818181818182 Val acc: 26.240000000000002 Test acc25.52; Train loss: 1.3972865211227061e-05 Val loss: 0.014364031219482421
+INFO - evaluator.py - 2024-10-26 14:48:41,962 - Epoch: 125 Train acc: 99.99272727272728 Val acc: 25.5 Test acc24.990000000000002; Train loss: 1.391865781201473e-05 Val loss: 0.014253604888916015
+INFO - evaluator.py - 2024-10-26 14:49:00,103 - Epoch: 126 Train acc: 99.99272727272728 Val acc: 26.6 Test acc25.97; Train loss: 1.189059035228142e-05 Val loss: 0.013416957473754883
+INFO - evaluator.py - 2024-10-26 14:49:19,174 - Epoch: 127 Train acc: 99.99454545454546 Val acc: 25.66 Test acc25.15; Train loss: 1.2436718007930639e-05 Val loss: 0.014511369132995606
+INFO - evaluator.py - 2024-10-26 14:49:38,142 - Epoch: 128 Train acc: 99.99636363636364 Val acc: 26.22 Test acc25.509999999999998; Train loss: 1.0860486223034308e-05 Val loss: 0.014410819053649902
+INFO - evaluator.py - 2024-10-26 14:49:56,437 - Epoch: 129 Train acc: 99.99818181818182 Val acc: 26.06 Test acc25.169999999999998; Train loss: 9.786324341125278e-06 Val loss: 0.014771768760681153
+INFO - evaluator.py - 2024-10-26 14:50:14,445 - Epoch: 130 Train acc: 100.0 Val acc: 26.179999999999996 Test acc25.369999999999997; Train loss: 1.0098258487149988e-05 Val loss: 0.014562413597106933
+INFO - evaluator.py - 2024-10-26 14:50:32,973 - Epoch: 131 Train acc: 99.99818181818182 Val acc: 26.16 Test acc25.119999999999997; Train loss: 9.469917438797314e-06 Val loss: 0.014665761756896973
+INFO - evaluator.py - 2024-10-26 14:50:51,920 - Epoch: 132 Train acc: 99.99818181818182 Val acc: 25.94 Test acc24.95; Train loss: 9.631628656908023e-06 Val loss: 0.015330132102966309
+INFO - evaluator.py - 2024-10-26 14:51:09,894 - Epoch: 133 Train acc: 99.99454545454546 Val acc: 24.6 Test acc23.849999999999998; Train loss: 9.926151727135716e-06 Val loss: 0.016641716766357423
+INFO - evaluator.py - 2024-10-26 14:51:27,760 - Epoch: 134 Train acc: 100.0 Val acc: 24.32 Test acc23.48; Train loss: 9.37564947922841e-06 Val loss: 0.01702614974975586
+INFO - evaluator.py - 2024-10-26 14:51:46,265 - Epoch: 135 Train acc: 100.0 Val acc: 24.44 Test acc23.53; Train loss: 8.923669125016948e-06 Val loss: 0.017022778701782225
+INFO - evaluator.py - 2024-10-26 14:52:04,408 - Epoch: 136 Train acc: 100.0 Val acc: 24.84 Test acc23.89; Train loss: 8.973157514066604e-06 Val loss: 0.016679617881774904
+INFO - evaluator.py - 2024-10-26 14:52:23,359 - Epoch: 137 Train acc: 100.0 Val acc: 26.200000000000003 Test acc24.86; Train loss: 8.746829901462082e-06 Val loss: 0.01596671371459961
+INFO - evaluator.py - 2024-10-26 14:52:41,420 - Epoch: 138 Train acc: 100.0 Val acc: 27.279999999999998 Test acc26.32; Train loss: 8.449005383722991e-06 Val loss: 0.014623344421386719
+INFO - evaluator.py - 2024-10-26 14:52:59,405 - Epoch: 139 Train acc: 100.0 Val acc: 27.02 Test acc26.029999999999998; Train loss: 8.643735172650354e-06 Val loss: 0.014881966781616211
+INFO - evaluator.py - 2024-10-26 14:53:17,238 - Epoch: 140 Train acc: 99.99818181818182 Val acc: 26.76 Test acc25.540000000000003; Train loss: 8.881145937431773e-06 Val loss: 0.015517813110351563
+INFO - evaluator.py - 2024-10-26 14:53:35,122 - Epoch: 141 Train acc: 100.0 Val acc: 27.12 Test acc25.929999999999996; Train loss: 8.433865642556073e-06 Val loss: 0.0156919885635376
+INFO - evaluator.py - 2024-10-26 14:53:53,452 - Epoch: 142 Train acc: 100.0 Val acc: 25.36 Test acc24.48; Train loss: 8.677237812662497e-06 Val loss: 0.016678572845458983
+INFO - evaluator.py - 2024-10-26 14:54:11,774 - Epoch: 143 Train acc: 100.0 Val acc: 24.7 Test acc24.0; Train loss: 8.345725347647782e-06 Val loss: 0.0176328800201416
+INFO - evaluator.py - 2024-10-26 14:54:30,236 - Epoch: 144 Train acc: 100.0 Val acc: 25.040000000000003 Test acc23.95; Train loss: 8.36892875535837e-06 Val loss: 0.017848648071289063
+INFO - evaluator.py - 2024-10-26 14:54:48,635 - Epoch: 145 Train acc: 100.0 Val acc: 25.34 Test acc24.58; Train loss: 7.945060532603582e-06 Val loss: 0.016631811714172363
+INFO - evaluator.py - 2024-10-26 14:55:07,230 - Epoch: 146 Train acc: 100.0 Val acc: 25.580000000000002 Test acc24.68; Train loss: 8.445899399124424e-06 Val loss: 0.016439819526672363
+INFO - evaluator.py - 2024-10-26 14:55:25,730 - Epoch: 147 Train acc: 100.0 Val acc: 25.2 Test acc24.54; Train loss: 7.885077195665375e-06 Val loss: 0.016912090301513673
+INFO - evaluator.py - 2024-10-26 14:55:44,562 - Epoch: 148 Train acc: 99.99636363636364 Val acc: 25.740000000000002 Test acc24.95; Train loss: 8.6671952100005e-06 Val loss: 0.01679018154144287
+INFO - evaluator.py - 2024-10-26 14:56:03,209 - Epoch: 149 Train acc: 99.99454545454546 Val acc: 26.419999999999998 Test acc25.5; Train loss: 9.552434914142148e-06 Val loss: 0.016388087272644042
+INFO - evaluator.py - 2024-10-26 14:56:21,279 - Epoch: 150 Train acc: 100.0 Val acc: 25.919999999999998 Test acc25.34; Train loss: 8.024529178775001e-06 Val loss: 0.016571682167053223
+INFO - evaluator.py - 2024-10-26 14:56:39,391 - Epoch: 151 Train acc: 100.0 Val acc: 25.16 Test acc23.98; Train loss: 7.836665796772153e-06 Val loss: 0.017551452255249022
+INFO - evaluator.py - 2024-10-26 14:56:57,982 - Epoch: 152 Train acc: 99.99636363636364 Val acc: 24.779999999999998 Test acc24.48; Train loss: 8.274591204032979e-06 Val loss: 0.017040314865112306
+INFO - evaluator.py - 2024-10-26 14:57:16,662 - Epoch: 153 Train acc: 100.0 Val acc: 25.1 Test acc24.54; Train loss: 8.323963798730718e-06 Val loss: 0.01688908405303955
+INFO - evaluator.py - 2024-10-26 14:57:35,545 - Epoch: 154 Train acc: 99.99818181818182 Val acc: 25.16 Test acc24.43; Train loss: 8.18412988499569e-06 Val loss: 0.017221704483032226
+INFO - evaluator.py - 2024-10-26 14:57:54,448 - Epoch: 155 Train acc: 100.0 Val acc: 24.98 Test acc24.14; Train loss: 8.150304829045621e-06 Val loss: 0.01715276737213135
+INFO - evaluator.py - 2024-10-26 14:58:13,254 - Epoch: 156 Train acc: 100.0 Val acc: 24.72 Test acc24.18; Train loss: 7.910340315588242e-06 Val loss: 0.017658948135375975
+INFO - evaluator.py - 2024-10-26 14:58:31,429 - Epoch: 157 Train acc: 99.99818181818182 Val acc: 24.240000000000002 Test acc23.91; Train loss: 8.118920860579238e-06 Val loss: 0.01795279884338379
+INFO - evaluator.py - 2024-10-26 14:58:49,963 - Epoch: 158 Train acc: 100.0 Val acc: 24.759999999999998 Test acc24.169999999999998; Train loss: 7.773087957916273e-06 Val loss: 0.01737662010192871
+INFO - evaluator.py - 2024-10-26 14:59:07,914 - Epoch: 159 Train acc: 100.0 Val acc: 23.18 Test acc23.06; Train loss: 7.747676322469488e-06 Val loss: 0.01928547782897949
+INFO - evaluator.py - 2024-10-26 14:59:26,246 - Epoch: 160 Train acc: 100.0 Val acc: 23.34 Test acc23.22; Train loss: 7.627144866009158e-06 Val loss: 0.019271855163574218
+INFO - evaluator.py - 2024-10-26 14:59:44,717 - Epoch: 161 Train acc: 100.0 Val acc: 22.16 Test acc22.35; Train loss: 8.001403827537697e-06 Val loss: 0.0206006103515625
+INFO - evaluator.py - 2024-10-26 15:00:02,871 - Epoch: 162 Train acc: 100.0 Val acc: 22.400000000000002 Test acc22.03; Train loss: 7.310007702538066e-06 Val loss: 0.02117897834777832
+INFO - evaluator.py - 2024-10-26 15:00:21,270 - Epoch: 163 Train acc: 100.0 Val acc: 22.86 Test acc22.71; Train loss: 7.408409141300416e-06 Val loss: 0.020351069259643556
+INFO - evaluator.py - 2024-10-26 15:00:39,829 - Epoch: 164 Train acc: 100.0 Val acc: 22.62 Test acc22.32; Train loss: 7.702329461145299e-06 Val loss: 0.021039422988891603
+INFO - evaluator.py - 2024-10-26 15:00:58,531 - Epoch: 165 Train acc: 100.0 Val acc: 20.4 Test acc19.98; Train loss: 7.801026894859123e-06 Val loss: 0.023230735778808593
+INFO - evaluator.py - 2024-10-26 15:01:17,090 - Epoch: 166 Train acc: 100.0 Val acc: 21.5 Test acc20.87; Train loss: 7.65197345013307e-06 Val loss: 0.02241242904663086
+INFO - evaluator.py - 2024-10-26 15:01:35,489 - Epoch: 167 Train acc: 100.0 Val acc: 20.48 Test acc20.25; Train loss: 7.66035778162239e-06 Val loss: 0.024392227935791017
+INFO - evaluator.py - 2024-10-26 15:01:53,875 - Epoch: 168 Train acc: 100.0 Val acc: 20.4 Test acc20.44; Train loss: 7.849989239846103e-06 Val loss: 0.023871527862548828
+INFO - evaluator.py - 2024-10-26 15:02:12,491 - Epoch: 169 Train acc: 100.0 Val acc: 19.939999999999998 Test acc19.59; Train loss: 7.777920776491307e-06 Val loss: 0.026291888427734375
+INFO - evaluator.py - 2024-10-26 15:02:30,761 - Epoch: 170 Train acc: 100.0 Val acc: 18.3 Test acc18.08; Train loss: 7.404035394640893e-06 Val loss: 0.029384850311279298
+INFO - evaluator.py - 2024-10-26 15:02:49,489 - Epoch: 171 Train acc: 100.0 Val acc: 18.9 Test acc18.990000000000002; Train loss: 8.140746138683013e-06 Val loss: 0.027875106048583984
+INFO - evaluator.py - 2024-10-26 15:03:08,265 - Epoch: 172 Train acc: 100.0 Val acc: 17.0 Test acc16.75; Train loss: 8.133455701913177e-06 Val loss: 0.031158147048950195
+INFO - evaluator.py - 2024-10-26 15:03:26,814 - Epoch: 173 Train acc: 100.0 Val acc: 18.740000000000002 Test acc18.759999999999998; Train loss: 7.897637436822565e-06 Val loss: 0.028501552963256835
+INFO - evaluator.py - 2024-10-26 15:03:45,299 - Epoch: 174 Train acc: 100.0 Val acc: 18.4 Test acc18.6; Train loss: 8.053081328133968e-06 Val loss: 0.029383534240722656
+INFO - evaluator.py - 2024-10-26 15:04:04,068 - Epoch: 175 Train acc: 100.0 Val acc: 17.54 Test acc17.37; Train loss: 7.19177613818002e-06 Val loss: 0.030298345184326173
+INFO - evaluator.py - 2024-10-26 15:04:21,729 - Epoch: 176 Train acc: 100.0 Val acc: 18.04 Test acc18.12; Train loss: 7.406830904867754e-06 Val loss: 0.028712429428100587
+INFO - evaluator.py - 2024-10-26 15:04:39,700 - Epoch: 177 Train acc: 100.0 Val acc: 19.139999999999997 Test acc19.759999999999998; Train loss: 7.949763111008162e-06 Val loss: 0.027311498260498047
+INFO - evaluator.py - 2024-10-26 15:04:58,159 - Epoch: 178 Train acc: 100.0 Val acc: 18.52 Test acc19.09; Train loss: 7.894815179117194e-06 Val loss: 0.029857119369506836
+INFO - evaluator.py - 2024-10-26 15:05:16,079 - Epoch: 179 Train acc: 100.0 Val acc: 18.96 Test acc19.03; Train loss: 7.214773391817951e-06 Val loss: 0.030468549346923827
+INFO - evaluator.py - 2024-10-26 15:05:34,274 - Epoch: 180 Train acc: 100.0 Val acc: 19.36 Test acc19.62; Train loss: 6.606247394599698e-06 Val loss: 0.028483975982666016
+INFO - evaluator.py - 2024-10-26 15:05:52,698 - Epoch: 181 Train acc: 100.0 Val acc: 19.46 Test acc20.02; Train loss: 6.501733729171313e-06 Val loss: 0.026490637969970702
+INFO - evaluator.py - 2024-10-26 15:06:11,347 - Epoch: 182 Train acc: 100.0 Val acc: 19.86 Test acc20.04; Train loss: 6.761426884490489e-06 Val loss: 0.024758222198486328
+INFO - evaluator.py - 2024-10-26 15:06:29,710 - Epoch: 183 Train acc: 100.0 Val acc: 20.599999999999998 Test acc21.07; Train loss: 6.651985372776505e-06 Val loss: 0.02189318504333496
+INFO - evaluator.py - 2024-10-26 15:06:48,301 - Epoch: 184 Train acc: 100.0 Val acc: 21.279999999999998 Test acc21.63; Train loss: 6.7418980338102715e-06 Val loss: 0.020664613342285157
+INFO - evaluator.py - 2024-10-26 15:07:06,999 - Epoch: 185 Train acc: 99.99818181818182 Val acc: 21.68 Test acc21.98; Train loss: 7.106452731584961e-06 Val loss: 0.01930730743408203
+INFO - evaluator.py - 2024-10-26 15:07:26,006 - Epoch: 186 Train acc: 100.0 Val acc: 22.34 Test acc22.689999999999998; Train loss: 6.42441619314592e-06 Val loss: 0.01776782646179199
+INFO - evaluator.py - 2024-10-26 15:07:44,693 - Epoch: 187 Train acc: 100.0 Val acc: 22.56 Test acc22.98; Train loss: 6.745050951774994e-06 Val loss: 0.016851174545288086
+INFO - evaluator.py - 2024-10-26 15:08:03,670 - Epoch: 188 Train acc: 100.0 Val acc: 23.22 Test acc23.66; Train loss: 6.809069484006613e-06 Val loss: 0.015677213287353515
+INFO - evaluator.py - 2024-10-26 15:08:22,105 - Epoch: 189 Train acc: 100.0 Val acc: 23.1 Test acc23.599999999999998; Train loss: 6.760097246892242e-06 Val loss: 0.015451734733581543
+INFO - evaluator.py - 2024-10-26 15:08:40,620 - Epoch: 190 Train acc: 100.0 Val acc: 23.46 Test acc23.74; Train loss: 6.951839131281965e-06 Val loss: 0.014721269607543946
+INFO - evaluator.py - 2024-10-26 15:08:59,031 - Epoch: 191 Train acc: 100.0 Val acc: 23.94 Test acc24.16; Train loss: 6.7839527039640495e-06 Val loss: 0.013949800491333007
+INFO - evaluator.py - 2024-10-26 15:09:17,381 - Epoch: 192 Train acc: 100.0 Val acc: 24.740000000000002 Test acc24.779999999999998; Train loss: 6.886235542531887e-06 Val loss: 0.013019420623779298
+INFO - evaluator.py - 2024-10-26 15:09:35,889 - Epoch: 193 Train acc: 100.0 Val acc: 24.84 Test acc24.89; Train loss: 6.984389102911915e-06 Val loss: 0.012789339828491212
+INFO - evaluator.py - 2024-10-26 15:09:54,463 - Epoch: 194 Train acc: 100.0 Val acc: 25.259999999999998 Test acc25.130000000000003; Train loss: 6.4152406409530985e-06 Val loss: 0.012094090843200683
+INFO - evaluator.py - 2024-10-26 15:10:13,265 - Epoch: 195 Train acc: 100.0 Val acc: 25.2 Test acc25.22; Train loss: 6.5649708772649646e-06 Val loss: 0.011902593612670898
+INFO - evaluator.py - 2024-10-26 15:10:31,576 - Epoch: 196 Train acc: 100.0 Val acc: 25.66 Test acc25.759999999999998; Train loss: 6.643009330516427e-06 Val loss: 0.011405685234069825
+INFO - evaluator.py - 2024-10-26 15:10:49,712 - Epoch: 197 Train acc: 100.0 Val acc: 26.16 Test acc25.619999999999997; Train loss: 6.790730549519966e-06 Val loss: 0.01119742488861084
+INFO - evaluator.py - 2024-10-26 15:11:08,156 - Epoch: 198 Train acc: 100.0 Val acc: 25.66 Test acc25.590000000000003; Train loss: 6.937551012643698e-06 Val loss: 0.011296120834350587
+INFO - evaluator.py - 2024-10-26 15:11:26,110 - Epoch: 199 Train acc: 100.0 Val acc: 26.44 Test acc26.19; Train loss: 6.518545851577073e-06 Val loss: 0.0105855318069458
+INFO - evaluator.py - 2024-10-26 15:11:26,117 - The best acc of synthetic images on sensitive val and the corresponding acc on test dataset from resnet is 33.44 and 34.13
+INFO - evaluator.py - 2024-10-26 15:11:26,117 - The best acc of synthetic images on noisy sensitive val and the corresponding acc on test dataset from resnet is 33.44 and 34.13
+INFO - evaluator.py - 2024-10-26 15:11:26,117 - The best acc test dataset from resnet is 34.13
+INFO - evaluator.py - 2024-10-26 15:12:17,882 - Epoch: 0 Train acc: 36.55272727272727 Val acc: 34.260000000000005 Test acc34.55; Train loss: 0.013123908656293695 Val loss: 0.0029300785541534423
+INFO - evaluator.py - 2024-10-26 15:13:09,539 - Epoch: 1 Train acc: 53.34181818181818 Val acc: 32.26 Test acc32.35; Train loss: 0.009556598157232457 Val loss: 0.004487674808502197
+INFO - evaluator.py - 2024-10-26 15:14:00,972 - Epoch: 2 Train acc: 61.46727272727273 Val acc: 34.5 Test acc35.44; Train loss: 0.00802914181839336 Val loss: 0.004406402063369751
+INFO - evaluator.py - 2024-10-26 15:14:52,349 - Epoch: 3 Train acc: 66.74181818181818 Val acc: 35.4 Test acc35.96; Train loss: 0.006997075852480801 Val loss: 0.004906195545196533
+INFO - evaluator.py - 2024-10-26 15:15:43,686 - Epoch: 4 Train acc: 72.58181818181818 Val acc: 28.000000000000004 Test acc28.53; Train loss: 0.0058767668214711275 Val loss: 0.00863521671295166
+INFO - evaluator.py - 2024-10-26 15:16:34,945 - Epoch: 5 Train acc: 78.01272727272728 Val acc: 31.14 Test acc31.25; Train loss: 0.004782077292420648 Val loss: 0.008599441528320312
+INFO - evaluator.py - 2024-10-26 15:17:26,189 - Epoch: 6 Train acc: 81.62 Val acc: 30.36 Test acc30.81; Train loss: 0.004018979261680083 Val loss: 0.009425230598449706
+INFO - evaluator.py - 2024-10-26 15:18:17,263 - Epoch: 7 Train acc: 84.74545454545455 Val acc: 25.1 Test acc26.13; Train loss: 0.003404462738741528 Val loss: 0.009826947212219238
+INFO - evaluator.py - 2024-10-26 15:19:08,143 - Epoch: 8 Train acc: 87.06363636363636 Val acc: 32.879999999999995 Test acc32.92; Train loss: 0.002914035188068043 Val loss: 0.00840416898727417
+INFO - evaluator.py - 2024-10-26 15:19:58,889 - Epoch: 9 Train acc: 88.74727272727273 Val acc: 31.759999999999998 Test acc31.619999999999997; Train loss: 0.0025668549031019213 Val loss: 0.00990259780883789
+INFO - evaluator.py - 2024-10-26 15:20:49,631 - Epoch: 10 Train acc: 89.97454545454545 Val acc: 27.08 Test acc27.560000000000002; Train loss: 0.0022696418622677977 Val loss: 0.009238011741638184
+INFO - evaluator.py - 2024-10-26 15:21:40,399 - Epoch: 11 Train acc: 91.11272727272727 Val acc: 22.98 Test acc23.62; Train loss: 0.0020309462143616244 Val loss: 0.01334038257598877
+INFO - evaluator.py - 2024-10-26 15:22:31,283 - Epoch: 12 Train acc: 91.2890909090909 Val acc: 32.4 Test acc32.629999999999995; Train loss: 0.00197862371775237 Val loss: 0.006700242519378662
+INFO - evaluator.py - 2024-10-26 15:23:22,291 - Epoch: 13 Train acc: 91.96 Val acc: 30.520000000000003 Test acc30.54; Train loss: 0.0018483483016490936 Val loss: 0.008969761085510253
+INFO - evaluator.py - 2024-10-26 15:24:13,051 - Epoch: 14 Train acc: 92.21454545454544 Val acc: 27.0 Test acc27.51; Train loss: 0.0017769501775503158 Val loss: 0.009342995071411132
+INFO - evaluator.py - 2024-10-26 15:25:03,916 - Epoch: 15 Train acc: 92.81454545454545 Val acc: 30.28 Test acc30.09; Train loss: 0.0016318465292453766 Val loss: 0.0077633040428161625
+INFO - evaluator.py - 2024-10-26 15:25:54,782 - Epoch: 16 Train acc: 92.61272727272727 Val acc: 21.44 Test acc22.85; Train loss: 0.0016671608857133171 Val loss: 0.015430038070678711
+INFO - evaluator.py - 2024-10-26 15:26:45,674 - Epoch: 17 Train acc: 93.36363636363636 Val acc: 32.72 Test acc32.6; Train loss: 0.0015617980228229003 Val loss: 0.005799475383758545
+INFO - evaluator.py - 2024-10-26 15:27:36,604 - Epoch: 18 Train acc: 93.24181818181818 Val acc: 27.639999999999997 Test acc28.139999999999997; Train loss: 0.0015455170993100512 Val loss: 0.006555839061737061
+INFO - evaluator.py - 2024-10-26 15:28:27,606 - Epoch: 19 Train acc: 93.41272727272727 Val acc: 26.56 Test acc27.200000000000003; Train loss: 0.0015055524106730115 Val loss: 0.00850142765045166
+INFO - evaluator.py - 2024-10-26 15:29:18,620 - Epoch: 20 Train acc: 93.2 Val acc: 27.439999999999998 Test acc27.029999999999998; Train loss: 0.001561993907392025 Val loss: 0.00665921573638916
+INFO - evaluator.py - 2024-10-26 15:30:09,771 - Epoch: 21 Train acc: 93.68909090909091 Val acc: 36.16 Test acc35.93; Train loss: 0.001418156154995615 Val loss: 0.004980039119720459
+INFO - evaluator.py - 2024-10-26 15:31:00,834 - Epoch: 22 Train acc: 93.70181818181818 Val acc: 36.24 Test acc36.059999999999995; Train loss: 0.001445527866008607 Val loss: 0.004872051429748535
+INFO - evaluator.py - 2024-10-26 15:31:51,859 - Epoch: 23 Train acc: 93.76363636363637 Val acc: 24.959999999999997 Test acc25.21; Train loss: 0.0014523434084247459 Val loss: 0.00958940658569336
+INFO - evaluator.py - 2024-10-26 15:32:42,870 - Epoch: 24 Train acc: 93.8709090909091 Val acc: 36.1 Test acc36.480000000000004; Train loss: 0.0014054964018816298 Val loss: 0.0044866566658020015
+INFO - evaluator.py - 2024-10-26 15:33:33,876 - Epoch: 25 Train acc: 94.58545454545455 Val acc: 22.8 Test acc23.24; Train loss: 0.0012713357080112804 Val loss: 0.008921937751770019
+INFO - evaluator.py - 2024-10-26 15:34:24,846 - Epoch: 26 Train acc: 93.99090909090908 Val acc: 30.919999999999998 Test acc30.98; Train loss: 0.0013955783425406976 Val loss: 0.006870752429962158
+INFO - evaluator.py - 2024-10-26 15:35:15,740 - Epoch: 27 Train acc: 93.93454545454546 Val acc: 25.1 Test acc24.7; Train loss: 0.001412432667680762 Val loss: 0.007419277858734131
+INFO - evaluator.py - 2024-10-26 15:36:06,566 - Epoch: 28 Train acc: 94.46181818181817 Val acc: 30.580000000000002 Test acc30.86; Train loss: 0.0012959062723612244 Val loss: 0.006544166278839111
+INFO - evaluator.py - 2024-10-26 15:36:57,304 - Epoch: 29 Train acc: 94.27272727272728 Val acc: 29.080000000000002 Test acc28.88; Train loss: 0.0013476043204692276 Val loss: 0.0074164569854736325
+INFO - evaluator.py - 2024-10-26 15:37:47,976 - Epoch: 30 Train acc: 94.40181818181819 Val acc: 27.700000000000003 Test acc27.750000000000004; Train loss: 0.001314130054007877 Val loss: 0.008459710884094238
+INFO - evaluator.py - 2024-10-26 15:38:38,681 - Epoch: 31 Train acc: 94.81090909090909 Val acc: 34.22 Test acc34.29; Train loss: 0.001214514851028269 Val loss: 0.0043726951122283935
+INFO - evaluator.py - 2024-10-26 15:39:29,419 - Epoch: 32 Train acc: 94.32363636363637 Val acc: 29.9 Test acc29.64; Train loss: 0.0013288762723857707 Val loss: 0.006015873146057129
+INFO - evaluator.py - 2024-10-26 15:40:20,076 - Epoch: 33 Train acc: 94.34181818181818 Val acc: 25.480000000000004 Test acc25.03; Train loss: 0.0013304329905997623 Val loss: 0.007918413162231446
+INFO - evaluator.py - 2024-10-26 15:41:10,743 - Epoch: 34 Train acc: 94.62 Val acc: 21.36 Test acc20.76; Train loss: 0.001253686371852051 Val loss: 0.009732664680480957
+INFO - evaluator.py - 2024-10-26 15:42:01,391 - Epoch: 35 Train acc: 94.78 Val acc: 16.84 Test acc16.98; Train loss: 0.0012106677701527423 Val loss: 0.01487175407409668
+INFO - evaluator.py - 2024-10-26 15:42:52,064 - Epoch: 36 Train acc: 94.64545454545454 Val acc: 26.040000000000003 Test acc25.91; Train loss: 0.001245889095894315 Val loss: 0.009290895652770996
+INFO - evaluator.py - 2024-10-26 15:43:42,755 - Epoch: 37 Train acc: 94.42545454545454 Val acc: 26.44 Test acc26.19; Train loss: 0.0013037913273681295 Val loss: 0.006721109962463379
+INFO - evaluator.py - 2024-10-26 15:44:33,590 - Epoch: 38 Train acc: 95.33272727272727 Val acc: 24.279999999999998 Test acc23.78; Train loss: 0.001095580841228366 Val loss: 0.010745677375793457
+INFO - evaluator.py - 2024-10-26 15:45:24,392 - Epoch: 39 Train acc: 94.61454545454545 Val acc: 29.299999999999997 Test acc30.009999999999998; Train loss: 0.0012450906051830813 Val loss: 0.006010369682312011
+INFO - evaluator.py - 2024-10-26 15:46:15,105 - Epoch: 40 Train acc: 95.13636363636364 Val acc: 29.48 Test acc30.43; Train loss: 0.001155898692458868 Val loss: 0.0071183389663696285
+INFO - evaluator.py - 2024-10-26 15:47:05,918 - Epoch: 41 Train acc: 94.77454545454546 Val acc: 23.7 Test acc24.610000000000003; Train loss: 0.001227396579764106 Val loss: 0.011572813224792481
+INFO - evaluator.py - 2024-10-26 15:47:56,661 - Epoch: 42 Train acc: 94.80181818181819 Val acc: 30.380000000000003 Test acc30.9; Train loss: 0.0012239303013140506 Val loss: 0.0060768367767333985
+INFO - evaluator.py - 2024-10-26 15:48:47,389 - Epoch: 43 Train acc: 95.06545454545454 Val acc: 17.24 Test acc17.54; Train loss: 0.0011831554647196423 Val loss: 0.01207618865966797
+INFO - evaluator.py - 2024-10-26 15:49:37,948 - Epoch: 44 Train acc: 94.93272727272726 Val acc: 30.5 Test acc30.59; Train loss: 0.00118266458125277 Val loss: 0.007056664085388183
+INFO - evaluator.py - 2024-10-26 15:50:28,554 - Epoch: 45 Train acc: 95.2309090909091 Val acc: 21.560000000000002 Test acc22.6; Train loss: 0.001119212650202892 Val loss: 0.01031412124633789
+INFO - evaluator.py - 2024-10-26 15:51:19,140 - Epoch: 46 Train acc: 94.55272727272728 Val acc: 33.52 Test acc33.61; Train loss: 0.0012714561520652337 Val loss: 0.0038618993759155272
+INFO - evaluator.py - 2024-10-26 15:52:09,756 - Epoch: 47 Train acc: 95.02909090909091 Val acc: 21.14 Test acc21.95; Train loss: 0.001151642292263833 Val loss: 0.008898631286621094
+INFO - evaluator.py - 2024-10-26 15:53:00,340 - Epoch: 48 Train acc: 94.99818181818182 Val acc: 25.1 Test acc24.48; Train loss: 0.0011545073283666914 Val loss: 0.009362647819519043
+INFO - evaluator.py - 2024-10-26 15:53:50,969 - Epoch: 49 Train acc: 95.11272727272727 Val acc: 28.000000000000004 Test acc28.43; Train loss: 0.0011731207657944072 Val loss: 0.005419194412231446
+INFO - evaluator.py - 2024-10-26 15:54:41,635 - Epoch: 50 Train acc: 95.16 Val acc: 31.16 Test acc31.16; Train loss: 0.0011385420208288866 Val loss: 0.005557328796386719
+INFO - evaluator.py - 2024-10-26 15:55:32,242 - Epoch: 51 Train acc: 94.56181818181818 Val acc: 16.919999999999998 Test acc16.98; Train loss: 0.0012665438367223199 Val loss: 0.010032894897460938
+INFO - evaluator.py - 2024-10-26 15:56:22,850 - Epoch: 52 Train acc: 95.39090909090909 Val acc: 17.78 Test acc17.080000000000002; Train loss: 0.0010948191993615844 Val loss: 0.009535698890686036
+INFO - evaluator.py - 2024-10-26 15:57:13,425 - Epoch: 53 Train acc: 95.07272727272728 Val acc: 23.86 Test acc22.61; Train loss: 0.001171851496398449 Val loss: 0.007062309455871582
+INFO - evaluator.py - 2024-10-26 15:58:04,069 - Epoch: 54 Train acc: 95.09454545454545 Val acc: 30.18 Test acc30.130000000000003; Train loss: 0.0011573057242415168 Val loss: 0.004656458187103272
+INFO - evaluator.py - 2024-10-26 15:58:54,705 - Epoch: 55 Train acc: 95.00181818181818 Val acc: 24.68 Test acc24.88; Train loss: 0.0011695287165316669 Val loss: 0.007353320693969726
+INFO - evaluator.py - 2024-10-26 15:59:45,236 - Epoch: 56 Train acc: 94.90727272727273 Val acc: 26.340000000000003 Test acc26.179999999999996; Train loss: 0.0011777196613902395 Val loss: 0.006897083759307861
+INFO - evaluator.py - 2024-10-26 16:00:35,779 - Epoch: 57 Train acc: 95.27272727272728 Val acc: 16.82 Test acc17.25; Train loss: 0.0011333107153800401 Val loss: 0.010286527442932129
+INFO - evaluator.py - 2024-10-26 16:01:26,467 - Epoch: 58 Train acc: 95.37272727272727 Val acc: 17.46 Test acc18.279999999999998; Train loss: 0.0010937179399484937 Val loss: 0.011967911911010742
+INFO - evaluator.py - 2024-10-26 16:02:17,099 - Epoch: 59 Train acc: 94.8709090909091 Val acc: 15.260000000000002 Test acc15.110000000000001; Train loss: 0.0012168568970127539 Val loss: 0.01392981414794922
+INFO - evaluator.py - 2024-10-26 16:03:07,691 - Epoch: 60 Train acc: 99.22727272727273 Val acc: 33.76 Test acc32.910000000000004; Train loss: 0.0002500270206396553 Val loss: 0.00548208703994751
+INFO - evaluator.py - 2024-10-26 16:03:58,253 - Epoch: 61 Train acc: 99.72909090909091 Val acc: 36.0 Test acc35.85; Train loss: 0.00011735907684249634 Val loss: 0.0069892755508422855
+INFO - evaluator.py - 2024-10-26 16:04:48,784 - Epoch: 62 Train acc: 99.86 Val acc: 32.519999999999996 Test acc32.300000000000004; Train loss: 8.303171528757296e-05 Val loss: 0.010980266189575195
+INFO - evaluator.py - 2024-10-26 16:05:39,318 - Epoch: 63 Train acc: 99.92545454545456 Val acc: 23.080000000000002 Test acc23.48; Train loss: 6.461766100996597e-05 Val loss: 0.020882066345214844
+INFO - evaluator.py - 2024-10-26 16:06:29,914 - Epoch: 64 Train acc: 99.94181818181819 Val acc: 18.5 Test acc18.96; Train loss: 5.9011113620363174e-05 Val loss: 0.033345329666137694
+INFO - evaluator.py - 2024-10-26 16:07:20,473 - Epoch: 65 Train acc: 99.96000000000001 Val acc: 16.56 Test acc16.650000000000002; Train loss: 5.1459674509665505e-05 Val loss: 0.04892270965576172
+INFO - evaluator.py - 2024-10-26 16:08:11,035 - Epoch: 66 Train acc: 99.96181818181819 Val acc: 13.459999999999999 Test acc13.87; Train loss: 4.846338914199309e-05 Val loss: 0.07335139770507812
+INFO - evaluator.py - 2024-10-26 16:09:01,605 - Epoch: 67 Train acc: 99.95818181818181 Val acc: 12.620000000000001 Test acc12.83; Train loss: 4.701541674704376e-05 Val loss: 0.09971581726074219
+INFO - evaluator.py - 2024-10-26 16:09:52,325 - Epoch: 68 Train acc: 99.96545454545455 Val acc: 12.24 Test acc12.44; Train loss: 4.442778841211376e-05 Val loss: 0.12890780944824218
+INFO - evaluator.py - 2024-10-26 16:10:43,071 - Epoch: 69 Train acc: 99.97090909090909 Val acc: 13.26 Test acc13.48; Train loss: 4.429116672201251e-05 Val loss: 0.14441159057617187
+INFO - evaluator.py - 2024-10-26 16:11:33,744 - Epoch: 70 Train acc: 99.96181818181819 Val acc: 12.3 Test acc12.49; Train loss: 4.2085068207234146e-05 Val loss: 0.18625611572265624
+INFO - evaluator.py - 2024-10-26 16:12:24,326 - Epoch: 71 Train acc: 99.94545454545455 Val acc: 12.740000000000002 Test acc13.020000000000001; Train loss: 4.2780364757742396e-05 Val loss: 0.2229930938720703
+INFO - evaluator.py - 2024-10-26 16:13:14,863 - Epoch: 72 Train acc: 99.94363636363637 Val acc: 11.32 Test acc11.26; Train loss: 4.870026095939631e-05 Val loss: 0.2916725524902344
+INFO - evaluator.py - 2024-10-26 16:14:05,476 - Epoch: 73 Train acc: 99.87272727272727 Val acc: 12.0 Test acc12.29; Train loss: 6.758558524730193e-05 Val loss: 0.2953462951660156
+INFO - evaluator.py - 2024-10-26 16:14:56,135 - Epoch: 74 Train acc: 99.69272727272728 Val acc: 11.48 Test acc11.600000000000001; Train loss: 0.00011143827368928628 Val loss: 0.282371923828125
+INFO - evaluator.py - 2024-10-26 16:15:46,684 - Epoch: 75 Train acc: 99.77818181818182 Val acc: 11.76 Test acc11.97; Train loss: 0.00010137957737950439 Val loss: 0.2825890380859375
+INFO - evaluator.py - 2024-10-26 16:16:37,397 - Epoch: 76 Train acc: 99.3709090909091 Val acc: 11.58 Test acc11.68; Train loss: 0.00019780352748083798 Val loss: 0.17834095458984375
+INFO - evaluator.py - 2024-10-26 16:17:28,025 - Epoch: 77 Train acc: 99.11090909090909 Val acc: 11.34 Test acc11.35; Train loss: 0.00026430536933581936 Val loss: 0.12249473876953125
+INFO - evaluator.py - 2024-10-26 16:18:18,584 - Epoch: 78 Train acc: 98.91272727272728 Val acc: 11.16 Test acc11.23; Train loss: 0.00029603640476072375 Val loss: 0.06935583953857422
+INFO - evaluator.py - 2024-10-26 16:19:09,214 - Epoch: 79 Train acc: 99.03454545454545 Val acc: 11.799999999999999 Test acc11.88; Train loss: 0.000268862507509237 Val loss: 0.05560423965454102
+INFO - evaluator.py - 2024-10-26 16:19:59,887 - Epoch: 80 Train acc: 99.07090909090908 Val acc: 12.559999999999999 Test acc12.280000000000001; Train loss: 0.0002590955093587664 Val loss: 0.04450334243774414
+INFO - evaluator.py - 2024-10-26 16:20:50,595 - Epoch: 81 Train acc: 99.06727272727272 Val acc: 11.48 Test acc11.200000000000001; Train loss: 0.0002600594564256343 Val loss: 0.04281368026733398
+INFO - evaluator.py - 2024-10-26 16:21:41,201 - Epoch: 82 Train acc: 98.98727272727272 Val acc: 15.8 Test acc15.870000000000001; Train loss: 0.0002727550000714307 Val loss: 0.025719215774536133
+INFO - evaluator.py - 2024-10-26 16:22:31,784 - Epoch: 83 Train acc: 98.88727272727273 Val acc: 13.639999999999999 Test acc13.38; Train loss: 0.00030329488196664236 Val loss: 0.021414855575561522
+INFO - evaluator.py - 2024-10-26 16:23:22,386 - Epoch: 84 Train acc: 99.06545454545454 Val acc: 17.580000000000002 Test acc18.04; Train loss: 0.00025646510267714884 Val loss: 0.014459253120422363
+INFO - evaluator.py - 2024-10-26 16:24:12,912 - Epoch: 85 Train acc: 98.91454545454546 Val acc: 23.76 Test acc23.91; Train loss: 0.0002854612370233305 Val loss: 0.010589285469055175
+INFO - evaluator.py - 2024-10-26 16:25:03,424 - Epoch: 86 Train acc: 99.0909090909091 Val acc: 15.52 Test acc16.220000000000002; Train loss: 0.00024880941739644516 Val loss: 0.01681924476623535
+INFO - evaluator.py - 2024-10-26 16:25:53,990 - Epoch: 87 Train acc: 99.10545454545453 Val acc: 28.16 Test acc28.860000000000003; Train loss: 0.0002438898767217655 Val loss: 0.0077309345245361325
+INFO - evaluator.py - 2024-10-26 16:26:44,519 - Epoch: 88 Train acc: 99.03090909090909 Val acc: 25.779999999999998 Test acc26.119999999999997; Train loss: 0.0002606544582935219 Val loss: 0.008835150146484375
+INFO - evaluator.py - 2024-10-26 16:27:35,371 - Epoch: 89 Train acc: 98.79454545454546 Val acc: 24.3 Test acc24.560000000000002; Train loss: 0.0003117483911781826 Val loss: 0.009343779754638673
+INFO - evaluator.py - 2024-10-26 16:28:25,861 - Epoch: 90 Train acc: 99.06 Val acc: 32.2 Test acc31.240000000000002; Train loss: 0.00025524296758865767 Val loss: 0.006590220642089844
+INFO - evaluator.py - 2024-10-26 16:29:16,304 - Epoch: 91 Train acc: 99.09454545454545 Val acc: 29.5 Test acc29.14; Train loss: 0.00024347093893553723 Val loss: 0.007281247520446777
+INFO - evaluator.py - 2024-10-26 16:30:06,833 - Epoch: 92 Train acc: 99.22909090909091 Val acc: 31.28 Test acc31.2; Train loss: 0.00020640412468293852 Val loss: 0.006527221393585205
+INFO - evaluator.py - 2024-10-26 16:30:57,407 - Epoch: 93 Train acc: 99.16727272727273 Val acc: 23.52 Test acc23.53; Train loss: 0.0002263736970553344 Val loss: 0.010003889083862304
+INFO - evaluator.py - 2024-10-26 16:31:47,972 - Epoch: 94 Train acc: 99.06727272727272 Val acc: 32.42 Test acc32.36; Train loss: 0.0002453067874959247 Val loss: 0.005832240390777588
+INFO - evaluator.py - 2024-10-26 16:32:38,665 - Epoch: 95 Train acc: 99.16545454545455 Val acc: 28.12 Test acc28.060000000000002; Train loss: 0.00023255026346834546 Val loss: 0.00675056791305542
+INFO - evaluator.py - 2024-10-26 16:33:29,280 - Epoch: 96 Train acc: 98.79272727272728 Val acc: 25.64 Test acc24.88; Train loss: 0.00030512499842284753 Val loss: 0.007898650455474854
+INFO - evaluator.py - 2024-10-26 16:34:19,907 - Epoch: 97 Train acc: 98.77636363636364 Val acc: 21.22 Test acc22.07; Train loss: 0.0003085871664553203 Val loss: 0.008498397254943847
+INFO - evaluator.py - 2024-10-26 16:35:10,432 - Epoch: 98 Train acc: 99.04181818181819 Val acc: 33.08 Test acc33.739999999999995; Train loss: 0.0002535332431297072 Val loss: 0.005549691390991211
+INFO - evaluator.py - 2024-10-26 16:36:00,974 - Epoch: 99 Train acc: 98.92909090909092 Val acc: 26.3 Test acc26.14; Train loss: 0.0002818536460484293 Val loss: 0.007584347152709961
+INFO - evaluator.py - 2024-10-26 16:36:51,449 - Epoch: 100 Train acc: 99.17272727272727 Val acc: 28.54 Test acc28.249999999999996; Train loss: 0.00022892796272327276 Val loss: 0.00657747392654419
+INFO - evaluator.py - 2024-10-26 16:37:41,941 - Epoch: 101 Train acc: 99.19454545454546 Val acc: 32.86 Test acc33.339999999999996; Train loss: 0.0002230973354329101 Val loss: 0.0057966518402099605
+INFO - evaluator.py - 2024-10-26 16:38:32,415 - Epoch: 102 Train acc: 99.08 Val acc: 29.360000000000003 Test acc29.659999999999997; Train loss: 0.00024777948811057616 Val loss: 0.006102237415313721
+INFO - evaluator.py - 2024-10-26 16:39:22,996 - Epoch: 103 Train acc: 99.2 Val acc: 27.96 Test acc27.689999999999998; Train loss: 0.00021426015221937136 Val loss: 0.007813517093658448
+INFO - evaluator.py - 2024-10-26 16:40:13,526 - Epoch: 104 Train acc: 99.28 Val acc: 29.82 Test acc30.48; Train loss: 0.00020329919248734686 Val loss: 0.007335807800292969
+INFO - evaluator.py - 2024-10-26 16:41:04,039 - Epoch: 105 Train acc: 98.82909090909091 Val acc: 28.860000000000003 Test acc28.310000000000002; Train loss: 0.00030495279742066156 Val loss: 0.006716108512878418
+INFO - evaluator.py - 2024-10-26 16:41:54,534 - Epoch: 106 Train acc: 98.95636363636363 Val acc: 31.119999999999997 Test acc30.48; Train loss: 0.00027119867256842554 Val loss: 0.005566715335845947
+INFO - evaluator.py - 2024-10-26 16:42:45,140 - Epoch: 107 Train acc: 99.0890909090909 Val acc: 26.06 Test acc25.979999999999997; Train loss: 0.00024785463074222206 Val loss: 0.006580077266693116
+INFO - evaluator.py - 2024-10-26 16:43:35,672 - Epoch: 108 Train acc: 99.1909090909091 Val acc: 27.800000000000004 Test acc27.439999999999998; Train loss: 0.00023178932215087115 Val loss: 0.0062398612976074215
+INFO - evaluator.py - 2024-10-26 16:44:26,168 - Epoch: 109 Train acc: 98.88 Val acc: 26.02 Test acc25.75; Train loss: 0.00029607402230189607 Val loss: 0.006688001346588135
+INFO - evaluator.py - 2024-10-26 16:45:16,701 - Epoch: 110 Train acc: 98.82 Val acc: 31.979999999999997 Test acc31.240000000000002; Train loss: 0.00029980173727328126 Val loss: 0.004968024063110352
+INFO - evaluator.py - 2024-10-26 16:46:07,223 - Epoch: 111 Train acc: 99.21636363636364 Val acc: 29.5 Test acc29.37; Train loss: 0.00020467081005177038 Val loss: 0.006138758182525635
+INFO - evaluator.py - 2024-10-26 16:46:57,724 - Epoch: 112 Train acc: 99.28181818181818 Val acc: 26.979999999999997 Test acc25.31; Train loss: 0.00019820631227286702 Val loss: 0.006105050849914551
+INFO - evaluator.py - 2024-10-26 16:47:48,302 - Epoch: 113 Train acc: 99.03454545454545 Val acc: 27.060000000000002 Test acc25.740000000000002; Train loss: 0.0002635363010583784 Val loss: 0.006091359901428223
+INFO - evaluator.py - 2024-10-26 16:48:38,827 - Epoch: 114 Train acc: 99.06 Val acc: 32.72 Test acc33.69; Train loss: 0.0002511418158273128 Val loss: 0.005006053638458252
+INFO - evaluator.py - 2024-10-26 16:49:29,325 - Epoch: 115 Train acc: 99.03999999999999 Val acc: 32.46 Test acc33.1; Train loss: 0.00025951240867037666 Val loss: 0.004596235942840576
+INFO - evaluator.py - 2024-10-26 16:50:19,820 - Epoch: 116 Train acc: 98.82363636363637 Val acc: 35.82 Test acc35.370000000000005; Train loss: 0.00030211808358488433 Val loss: 0.003729775905609131
+INFO - evaluator.py - 2024-10-26 16:51:10,345 - Epoch: 117 Train acc: 99.01454545454546 Val acc: 34.52 Test acc33.92; Train loss: 0.0002688965028913861 Val loss: 0.004017335510253906
+INFO - evaluator.py - 2024-10-26 16:52:00,957 - Epoch: 118 Train acc: 99.17090909090909 Val acc: 30.599999999999998 Test acc29.93; Train loss: 0.00022652660614641554 Val loss: 0.004511868572235107
+INFO - evaluator.py - 2024-10-26 16:52:51,591 - Epoch: 119 Train acc: 99.18 Val acc: 23.44 Test acc24.09; Train loss: 0.00023406697915951636 Val loss: 0.007245740604400635
+INFO - evaluator.py - 2024-10-26 16:53:42,138 - Epoch: 120 Train acc: 99.82909090909091 Val acc: 29.04 Test acc29.65; Train loss: 6.601332578786903e-05 Val loss: 0.005940197563171387
+INFO - evaluator.py - 2024-10-26 16:54:32,959 - Epoch: 121 Train acc: 99.94909090909091 Val acc: 30.64 Test acc30.73; Train loss: 3.281517587284642e-05 Val loss: 0.006114741706848144
+INFO - evaluator.py - 2024-10-26 16:55:23,504 - Epoch: 122 Train acc: 99.96545454545455 Val acc: 32.78 Test acc32.72; Train loss: 2.520115701534616e-05 Val loss: 0.00596361722946167
+INFO - evaluator.py - 2024-10-26 16:56:13,952 - Epoch: 123 Train acc: 99.98181818181818 Val acc: 32.96 Test acc32.62; Train loss: 2.2840273938014764e-05 Val loss: 0.006315069961547851
+INFO - evaluator.py - 2024-10-26 16:57:04,509 - Epoch: 124 Train acc: 99.97090909090909 Val acc: 34.36 Test acc34.27; Train loss: 2.1197405409343032e-05 Val loss: 0.005975437927246093
+INFO - evaluator.py - 2024-10-26 16:57:55,019 - Epoch: 125 Train acc: 99.98181818181818 Val acc: 33.660000000000004 Test acc33.410000000000004; Train loss: 1.915944472685541e-05 Val loss: 0.0065743334770202635
+INFO - evaluator.py - 2024-10-26 16:58:45,560 - Epoch: 126 Train acc: 99.97818181818182 Val acc: 33.96 Test acc34.1; Train loss: 1.7890796034110034e-05 Val loss: 0.006579244995117187
+INFO - evaluator.py - 2024-10-26 16:59:36,068 - Epoch: 127 Train acc: 99.97454545454545 Val acc: 34.04 Test acc34.449999999999996; Train loss: 1.781953306847506e-05 Val loss: 0.006764878559112549
+INFO - evaluator.py - 2024-10-26 17:00:26,610 - Epoch: 128 Train acc: 99.99090909090908 Val acc: 35.88 Test acc34.839999999999996; Train loss: 1.4225854059490798e-05 Val loss: 0.006554048633575439
+INFO - evaluator.py - 2024-10-26 17:01:17,123 - Epoch: 129 Train acc: 99.9890909090909 Val acc: 34.5 Test acc34.050000000000004; Train loss: 1.4923938528359444e-05 Val loss: 0.007106407642364502
+INFO - evaluator.py - 2024-10-26 17:02:07,667 - Epoch: 130 Train acc: 99.98545454545454 Val acc: 33.76 Test acc33.47; Train loss: 1.5936947099610487e-05 Val loss: 0.007641277503967286
+INFO - evaluator.py - 2024-10-26 17:02:58,241 - Epoch: 131 Train acc: 99.99090909090908 Val acc: 33.96 Test acc33.26; Train loss: 1.3930196966975928e-05 Val loss: 0.007697111701965332
+INFO - evaluator.py - 2024-10-26 17:03:48,726 - Epoch: 132 Train acc: 99.98727272727272 Val acc: 33.26 Test acc32.769999999999996; Train loss: 1.5491056234300644e-05 Val loss: 0.007951477813720704
+INFO - evaluator.py - 2024-10-26 17:04:39,206 - Epoch: 133 Train acc: 99.9890909090909 Val acc: 32.32 Test acc32.300000000000004; Train loss: 1.4300958685238252e-05 Val loss: 0.00853227825164795
+INFO - evaluator.py - 2024-10-26 17:05:29,713 - Epoch: 134 Train acc: 99.99090909090908 Val acc: 30.259999999999998 Test acc30.43; Train loss: 1.3642550508004868e-05 Val loss: 0.009536850547790528
+INFO - evaluator.py - 2024-10-26 17:06:20,219 - Epoch: 135 Train acc: 99.99272727272728 Val acc: 30.080000000000002 Test acc30.44; Train loss: 1.4770901419053024e-05 Val loss: 0.009677509117126466
+INFO - evaluator.py - 2024-10-26 17:07:10,695 - Epoch: 136 Train acc: 99.99636363636364 Val acc: 29.099999999999998 Test acc29.57; Train loss: 1.2769786606606265e-05 Val loss: 0.010350312042236328
+INFO - evaluator.py - 2024-10-26 17:08:01,128 - Epoch: 137 Train acc: 99.99272727272728 Val acc: 27.779999999999998 Test acc28.49; Train loss: 1.4704894804162905e-05 Val loss: 0.01075681095123291
+INFO - evaluator.py - 2024-10-26 17:08:51,693 - Epoch: 138 Train acc: 99.99454545454546 Val acc: 26.5 Test acc26.77; Train loss: 1.4158514916727489e-05 Val loss: 0.012109954452514648
+INFO - evaluator.py - 2024-10-26 17:09:42,189 - Epoch: 139 Train acc: 99.99636363636364 Val acc: 26.32 Test acc27.02; Train loss: 1.3429549284046515e-05 Val loss: 0.01209088191986084
+INFO - evaluator.py - 2024-10-26 17:10:32,791 - Epoch: 140 Train acc: 99.99818181818182 Val acc: 25.3 Test acc26.240000000000002; Train loss: 1.3214750836645676e-05 Val loss: 0.012812716484069824
+INFO - evaluator.py - 2024-10-26 17:11:23,298 - Epoch: 141 Train acc: 99.99818181818182 Val acc: 23.04 Test acc24.169999999999998; Train loss: 1.32887127708686e-05 Val loss: 0.014039980506896973
+INFO - evaluator.py - 2024-10-26 17:12:13,829 - Epoch: 142 Train acc: 99.99454545454546 Val acc: 24.72 Test acc25.7; Train loss: 1.3612017101100222e-05 Val loss: 0.013055280113220215
+INFO - evaluator.py - 2024-10-26 17:13:04,394 - Epoch: 143 Train acc: 99.99454545454546 Val acc: 22.720000000000002 Test acc23.76; Train loss: 1.3725555065849966e-05 Val loss: 0.014427368354797363
+INFO - evaluator.py - 2024-10-26 17:13:55,101 - Epoch: 144 Train acc: 100.0 Val acc: 21.7 Test acc22.759999999999998; Train loss: 1.3780242357593538e-05 Val loss: 0.015299131774902344
+INFO - evaluator.py - 2024-10-26 17:14:45,662 - Epoch: 145 Train acc: 99.99272727272728 Val acc: 21.279999999999998 Test acc22.05; Train loss: 1.4244095876347273e-05 Val loss: 0.015979934120178223
+INFO - evaluator.py - 2024-10-26 17:15:36,119 - Epoch: 146 Train acc: 99.99454545454546 Val acc: 21.66 Test acc22.43; Train loss: 1.4485108902656727e-05 Val loss: 0.015575557708740235
+INFO - evaluator.py - 2024-10-26 17:16:26,605 - Epoch: 147 Train acc: 99.99636363636364 Val acc: 20.94 Test acc21.19; Train loss: 1.4848665841749276e-05 Val loss: 0.017155717849731446
+INFO - evaluator.py - 2024-10-26 17:17:17,112 - Epoch: 148 Train acc: 99.99818181818182 Val acc: 19.919999999999998 Test acc20.29; Train loss: 1.389687130629847e-05 Val loss: 0.017767800521850587
+INFO - evaluator.py - 2024-10-26 17:18:07,600 - Epoch: 149 Train acc: 99.99636363636364 Val acc: 19.96 Test acc20.23; Train loss: 1.4283472955734893e-05 Val loss: 0.017998973846435548
+INFO - evaluator.py - 2024-10-26 17:18:58,064 - Epoch: 150 Train acc: 99.99454545454546 Val acc: 19.98 Test acc19.93; Train loss: 1.441589863282967e-05 Val loss: 0.01776936912536621
+INFO - evaluator.py - 2024-10-26 17:19:48,545 - Epoch: 151 Train acc: 99.99636363636364 Val acc: 20.66 Test acc20.82; Train loss: 1.4268313136629083e-05 Val loss: 0.016600268173217775
+INFO - evaluator.py - 2024-10-26 17:20:38,973 - Epoch: 152 Train acc: 99.9890909090909 Val acc: 20.84 Test acc20.89; Train loss: 1.5842132414267822e-05 Val loss: 0.016857764434814453
+INFO - evaluator.py - 2024-10-26 17:21:29,456 - Epoch: 153 Train acc: 100.0 Val acc: 19.38 Test acc19.13; Train loss: 1.3338792898734524e-05 Val loss: 0.018610631942749024
+INFO - evaluator.py - 2024-10-26 17:22:19,842 - Epoch: 154 Train acc: 99.99272727272728 Val acc: 17.1 Test acc17.29; Train loss: 1.4353753440082073e-05 Val loss: 0.0209723575592041
+INFO - evaluator.py - 2024-10-26 17:23:10,194 - Epoch: 155 Train acc: 99.99454545454546 Val acc: 17.7 Test acc18.08; Train loss: 1.4272692214316604e-05 Val loss: 0.019980126571655273
+INFO - evaluator.py - 2024-10-26 17:24:00,509 - Epoch: 156 Train acc: 99.99636363636364 Val acc: 17.32 Test acc17.64; Train loss: 1.4928680811797016e-05 Val loss: 0.020292036056518553
+INFO - evaluator.py - 2024-10-26 17:24:50,851 - Epoch: 157 Train acc: 99.98727272727272 Val acc: 16.06 Test acc16.11; Train loss: 1.7277588478331878e-05 Val loss: 0.022726391983032227
+INFO - evaluator.py - 2024-10-26 17:25:41,348 - Epoch: 158 Train acc: 99.99636363636364 Val acc: 16.619999999999997 Test acc16.48; Train loss: 1.4862444979900664e-05 Val loss: 0.02234571762084961
+INFO - evaluator.py - 2024-10-26 17:26:31,782 - Epoch: 159 Train acc: 99.99636363636364 Val acc: 15.879999999999999 Test acc15.840000000000002; Train loss: 1.4988951206164942e-05 Val loss: 0.02444505615234375
+INFO - evaluator.py - 2024-10-26 17:27:22,176 - Epoch: 160 Train acc: 99.99272727272728 Val acc: 15.479999999999999 Test acc15.52; Train loss: 1.553034502377903e-05 Val loss: 0.023891995620727538
+INFO - evaluator.py - 2024-10-26 17:28:12,421 - Epoch: 161 Train acc: 99.98363636363636 Val acc: 15.78 Test acc15.9; Train loss: 1.8571280028713358e-05 Val loss: 0.02332359733581543
+INFO - evaluator.py - 2024-10-26 17:29:02,648 - Epoch: 162 Train acc: 99.97636363636364 Val acc: 16.0 Test acc16.17; Train loss: 2.0061962322374297e-05 Val loss: 0.0233349910736084
+INFO - evaluator.py - 2024-10-26 17:29:52,974 - Epoch: 163 Train acc: 99.99090909090908 Val acc: 15.540000000000001 Test acc15.98; Train loss: 1.6546700359322132e-05 Val loss: 0.023792610931396483
+INFO - evaluator.py - 2024-10-26 17:30:43,340 - Epoch: 164 Train acc: 99.99272727272728 Val acc: 16.76 Test acc17.0; Train loss: 1.5548654351468112e-05 Val loss: 0.021245218658447265
+INFO - evaluator.py - 2024-10-26 17:31:33,808 - Epoch: 165 Train acc: 99.99636363636364 Val acc: 16.72 Test acc16.72; Train loss: 1.6860703290016815e-05 Val loss: 0.022062104797363282
+INFO - evaluator.py - 2024-10-26 17:32:24,345 - Epoch: 166 Train acc: 99.99454545454546 Val acc: 16.580000000000002 Test acc16.36; Train loss: 1.588375553467565e-05 Val loss: 0.021957312393188478
+INFO - evaluator.py - 2024-10-26 17:33:14,778 - Epoch: 167 Train acc: 99.9890909090909 Val acc: 15.959999999999999 Test acc16.1; Train loss: 1.716183035274629e-05 Val loss: 0.022682608795166016
+INFO - evaluator.py - 2024-10-26 17:34:05,143 - Epoch: 168 Train acc: 99.99818181818182 Val acc: 15.22 Test acc14.85; Train loss: 1.5226825899232857e-05 Val loss: 0.023923876190185548
+INFO - evaluator.py - 2024-10-26 17:34:55,665 - Epoch: 169 Train acc: 99.98181818181818 Val acc: 15.440000000000001 Test acc15.459999999999999; Train loss: 1.823461141585457e-05 Val loss: 0.02331506805419922
+INFO - evaluator.py - 2024-10-26 17:35:46,089 - Epoch: 170 Train acc: 99.98 Val acc: 14.84 Test acc14.64; Train loss: 2.070601513947953e-05 Val loss: 0.025035325622558592
+INFO - evaluator.py - 2024-10-26 17:36:36,376 - Epoch: 171 Train acc: 99.98 Val acc: 15.68 Test acc15.45; Train loss: 1.9856152312025765e-05 Val loss: 0.022927854919433593
+INFO - evaluator.py - 2024-10-26 17:37:26,680 - Epoch: 172 Train acc: 99.98 Val acc: 15.14 Test acc14.879999999999999; Train loss: 2.0863544401204723e-05 Val loss: 0.024359799575805665
+INFO - evaluator.py - 2024-10-26 17:38:17,008 - Epoch: 173 Train acc: 99.98545454545454 Val acc: 14.12 Test acc13.63; Train loss: 1.9855328515933995e-05 Val loss: 0.02614980239868164
+INFO - evaluator.py - 2024-10-26 17:39:07,349 - Epoch: 174 Train acc: 99.99272727272728 Val acc: 14.899999999999999 Test acc14.610000000000001; Train loss: 1.6825105533511802e-05 Val loss: 0.02565791473388672
+INFO - evaluator.py - 2024-10-26 17:39:57,722 - Epoch: 175 Train acc: 99.99090909090908 Val acc: 14.180000000000001 Test acc13.83; Train loss: 1.745867509902878e-05 Val loss: 0.027272574615478516
+INFO - evaluator.py - 2024-10-26 17:40:48,094 - Epoch: 176 Train acc: 99.99272727272728 Val acc: 13.56 Test acc13.15; Train loss: 1.499244640792974e-05 Val loss: 0.02813837585449219
+INFO - evaluator.py - 2024-10-26 17:41:38,542 - Epoch: 177 Train acc: 99.99454545454546 Val acc: 13.44 Test acc13.13; Train loss: 1.57861315169033e-05 Val loss: 0.029637402725219728
+INFO - evaluator.py - 2024-10-26 17:42:28,979 - Epoch: 178 Train acc: 99.96909090909091 Val acc: 12.42 Test acc12.23; Train loss: 2.5167828599329698e-05 Val loss: 0.030904379653930666
+INFO - evaluator.py - 2024-10-26 17:43:19,271 - Epoch: 179 Train acc: 99.98363636363636 Val acc: 14.879999999999999 Test acc14.680000000000001; Train loss: 2.189570466500961e-05 Val loss: 0.024548701095581056
+INFO - evaluator.py - 2024-10-26 17:44:09,606 - Epoch: 180 Train acc: 99.98545454545454 Val acc: 15.98 Test acc15.78; Train loss: 1.852393298812041e-05 Val loss: 0.021091204833984373
+INFO - evaluator.py - 2024-10-26 17:44:59,956 - Epoch: 181 Train acc: 99.99636363636364 Val acc: 15.459999999999999 Test acc15.39; Train loss: 1.5727720060385765e-05 Val loss: 0.021143123626708983
+INFO - evaluator.py - 2024-10-26 17:45:50,391 - Epoch: 182 Train acc: 99.99454545454546 Val acc: 16.16 Test acc15.909999999999998; Train loss: 1.4359449060760778e-05 Val loss: 0.019241054534912108
+INFO - evaluator.py - 2024-10-26 17:46:40,829 - Epoch: 183 Train acc: 99.99090909090908 Val acc: 16.64 Test acc16.259999999999998; Train loss: 1.5800300752744077e-05 Val loss: 0.017591254806518554
+INFO - evaluator.py - 2024-10-26 17:47:31,255 - Epoch: 184 Train acc: 99.99454545454546 Val acc: 16.400000000000002 Test acc16.470000000000002; Train loss: 1.5876684480727735e-05 Val loss: 0.017337144470214845
+INFO - evaluator.py - 2024-10-26 17:48:21,720 - Epoch: 185 Train acc: 99.99818181818182 Val acc: 17.46 Test acc17.39; Train loss: 1.2865111147138205e-05 Val loss: 0.015695285034179687
+INFO - evaluator.py - 2024-10-26 17:49:12,062 - Epoch: 186 Train acc: 99.99636363636364 Val acc: 17.740000000000002 Test acc17.990000000000002; Train loss: 1.3218555434352972e-05 Val loss: 0.015148291015625
+INFO - evaluator.py - 2024-10-26 17:50:02,522 - Epoch: 187 Train acc: 99.99636363636364 Val acc: 18.740000000000002 Test acc18.95; Train loss: 1.3407030900601636e-05 Val loss: 0.01361093292236328
+INFO - evaluator.py - 2024-10-26 17:50:53,043 - Epoch: 188 Train acc: 99.99636363636364 Val acc: 18.64 Test acc18.77; Train loss: 1.296085333663293e-05 Val loss: 0.013370147895812989
+INFO - evaluator.py - 2024-10-26 17:51:43,413 - Epoch: 189 Train acc: 99.99636363636364 Val acc: 18.740000000000002 Test acc18.85; Train loss: 1.324031634721905e-05 Val loss: 0.013199214935302734
+INFO - evaluator.py - 2024-10-26 17:52:33,740 - Epoch: 190 Train acc: 99.99272727272728 Val acc: 19.82 Test acc20.14; Train loss: 1.3440479247153482e-05 Val loss: 0.011615233421325684
+INFO - evaluator.py - 2024-10-26 17:53:24,025 - Epoch: 191 Train acc: 99.99454545454546 Val acc: 19.54 Test acc19.81; Train loss: 1.2900116180323742e-05 Val loss: 0.011755660820007324
+INFO - evaluator.py - 2024-10-26 17:54:14,246 - Epoch: 192 Train acc: 99.99454545454546 Val acc: 19.939999999999998 Test acc20.03; Train loss: 1.375823243076659e-05 Val loss: 0.011609267616271972
+INFO - evaluator.py - 2024-10-26 17:55:04,453 - Epoch: 193 Train acc: 99.99454545454546 Val acc: 20.68 Test acc20.849999999999998; Train loss: 1.3118539940015498e-05 Val loss: 0.010514107513427734
+INFO - evaluator.py - 2024-10-26 17:55:54,702 - Epoch: 194 Train acc: 99.99454545454546 Val acc: 22.16 Test acc22.21; Train loss: 1.2609506625978446e-05 Val loss: 0.009577838897705079
+INFO - evaluator.py - 2024-10-26 17:56:45,029 - Epoch: 195 Train acc: 99.99454545454546 Val acc: 22.06 Test acc22.439999999999998; Train loss: 1.3030999823769724e-05 Val loss: 0.009601345825195312
+INFO - evaluator.py - 2024-10-26 17:57:35,514 - Epoch: 196 Train acc: 99.99818181818182 Val acc: 23.02 Test acc23.169999999999998; Train loss: 1.278044121784412e-05 Val loss: 0.009141358375549316
+INFO - evaluator.py - 2024-10-26 17:58:26,111 - Epoch: 197 Train acc: 99.99818181818182 Val acc: 22.939999999999998 Test acc23.26; Train loss: 1.2664915479465642e-05 Val loss: 0.009031304359436035
+INFO - evaluator.py - 2024-10-26 17:59:16,648 - Epoch: 198 Train acc: 99.99818181818182 Val acc: 24.14 Test acc24.03; Train loss: 1.2507944356184452e-05 Val loss: 0.008744723510742188
+INFO - evaluator.py - 2024-10-26 18:00:07,197 - Epoch: 199 Train acc: 99.99454545454546 Val acc: 25.0 Test acc25.319999999999997; Train loss: 1.279307079649615e-05 Val loss: 0.007837607669830323
+INFO - evaluator.py - 2024-10-26 18:00:07,200 - The best acc of synthetic images on sensitive val and the corresponding acc on test dataset from wrn is 36.24 and 36.059999999999995
+INFO - evaluator.py - 2024-10-26 18:00:07,200 - The best acc of synthetic images on noisy sensitive val and the corresponding acc on test dataset from wrn is 36.24 and 36.059999999999995
+INFO - evaluator.py - 2024-10-26 18:00:07,200 - The best acc test dataset from wrn is 36.480000000000004
+INFO - evaluator.py - 2024-10-26 18:01:26,171 - Epoch: 0 Train acc: 19.78 Val acc: 20.36 Test acc21.11; Train loss: 0.02464460810097781 Val loss: 0.004033523845672607
+INFO - evaluator.py - 2024-10-26 18:02:44,797 - Epoch: 1 Train acc: 29.063636363636363 Val acc: 17.4 Test acc17.68; Train loss: 0.014776307561180809 Val loss: 0.02141273956298828
+INFO - evaluator.py - 2024-10-26 18:04:03,556 - Epoch: 2 Train acc: 35.63454545454545 Val acc: 11.52 Test acc11.97; Train loss: 0.013293595305356112 Val loss: 0.08415137329101563
+INFO - evaluator.py - 2024-10-26 18:05:22,266 - Epoch: 3 Train acc: 42.44363636363636 Val acc: 8.32 Test acc7.23; Train loss: 0.011698830476674166 Val loss: 0.798629052734375
+INFO - evaluator.py - 2024-10-26 18:06:40,826 - Epoch: 4 Train acc: 47.07818181818182 Val acc: 7.6 Test acc7.9799999999999995; Train loss: 0.010782895783944563 Val loss: 1.5482238037109375
+INFO - evaluator.py - 2024-10-26 18:07:59,487 - Epoch: 5 Train acc: 52.22545454545454 Val acc: 9.86 Test acc9.78; Train loss: 0.009734722137451171 Val loss: 1.9028749267578124
+INFO - evaluator.py - 2024-10-26 18:09:18,027 - Epoch: 6 Train acc: 56.38363636363637 Val acc: 10.040000000000001 Test acc10.0; Train loss: 0.008911452586000616 Val loss: 5.36386494140625
+INFO - evaluator.py - 2024-10-26 18:10:36,625 - Epoch: 7 Train acc: 61.62 Val acc: 10.040000000000001 Test acc10.0; Train loss: 0.007923544164137406 Val loss: 1.6180460205078124
+INFO - evaluator.py - 2024-10-26 18:11:55,340 - Epoch: 8 Train acc: 66.58 Val acc: 10.040000000000001 Test acc10.0; Train loss: 0.007001848915490237 Val loss: 14.8214583984375
+INFO - evaluator.py - 2024-10-26 18:13:14,287 - Epoch: 9 Train acc: 71.63454545454545 Val acc: 10.040000000000001 Test acc10.0; Train loss: 0.006047715803709897 Val loss: 74.8114859375
+INFO - evaluator.py - 2024-10-26 18:14:33,184 - Epoch: 10 Train acc: 76.60181818181819 Val acc: 10.040000000000001 Test acc10.0; Train loss: 0.0050927333577112715 Val loss: 28.259444921875
+INFO - evaluator.py - 2024-10-26 18:15:51,965 - Epoch: 11 Train acc: 80.46909090909091 Val acc: 10.040000000000001 Test acc10.0; Train loss: 0.004297154442288659 Val loss: 4.44864755859375
+INFO - evaluator.py - 2024-10-26 18:17:10,645 - Epoch: 12 Train acc: 83.38909090909091 Val acc: 10.040000000000001 Test acc10.0; Train loss: 0.003722793546589938 Val loss: 1.6454032958984375
+INFO - evaluator.py - 2024-10-26 18:18:29,385 - Epoch: 13 Train acc: 85.66 Val acc: 17.2 Test acc16.33; Train loss: 0.0032402908463369717 Val loss: 0.02103288459777832
+INFO - evaluator.py - 2024-10-26 18:19:48,045 - Epoch: 14 Train acc: 87.42363636363636 Val acc: 25.14 Test acc26.5; Train loss: 0.0028503332105549897 Val loss: 0.009258658790588379
+INFO - evaluator.py - 2024-10-26 18:21:06,665 - Epoch: 15 Train acc: 88.79090909090908 Val acc: 29.5 Test acc30.61; Train loss: 0.002558373436602679 Val loss: 0.008284649372100831
+INFO - evaluator.py - 2024-10-26 18:22:25,327 - Epoch: 16 Train acc: 89.75636363636363 Val acc: 26.840000000000003 Test acc27.82; Train loss: 0.002356540416858413 Val loss: 0.007855852603912354
+INFO - evaluator.py - 2024-10-26 18:23:43,993 - Epoch: 17 Train acc: 90.42 Val acc: 29.38 Test acc30.259999999999998; Train loss: 0.0021692978914488446 Val loss: 0.006415073013305664
+INFO - evaluator.py - 2024-10-26 18:25:02,650 - Epoch: 18 Train acc: 90.76545454545455 Val acc: 26.900000000000002 Test acc26.8; Train loss: 0.002129890721359036 Val loss: 0.007799664402008057
+INFO - evaluator.py - 2024-10-26 18:26:21,297 - Epoch: 19 Train acc: 91.33636363636364 Val acc: 28.12 Test acc28.48; Train loss: 0.0020039721921086312 Val loss: 0.007980160427093506
+INFO - evaluator.py - 2024-10-26 18:27:40,028 - Epoch: 20 Train acc: 92.08 Val acc: 23.72 Test acc24.67; Train loss: 0.0018406105279922486 Val loss: 0.012854755973815917
+INFO - evaluator.py - 2024-10-26 18:28:58,946 - Epoch: 21 Train acc: 92.24363636363636 Val acc: 27.3 Test acc27.27; Train loss: 0.0018010352416472002 Val loss: 0.009121622657775878
+INFO - evaluator.py - 2024-10-26 18:30:18,067 - Epoch: 22 Train acc: 92.21818181818182 Val acc: 24.9 Test acc25.669999999999998; Train loss: 0.001774021921239116 Val loss: 0.00863111686706543
+INFO - evaluator.py - 2024-10-26 18:31:36,937 - Epoch: 23 Train acc: 92.78727272727274 Val acc: 29.160000000000004 Test acc29.23; Train loss: 0.0016672592658210884 Val loss: 0.007217916774749756
+INFO - evaluator.py - 2024-10-26 18:32:55,721 - Epoch: 24 Train acc: 93.22727272727272 Val acc: 35.86 Test acc35.93; Train loss: 0.001572035270116546 Val loss: 0.0059157381057739255
+INFO - evaluator.py - 2024-10-26 18:34:14,342 - Epoch: 25 Train acc: 93.34363636363636 Val acc: 27.72 Test acc27.229999999999997; Train loss: 0.0015426110778342594 Val loss: 0.009143341064453124
+INFO - evaluator.py - 2024-10-26 18:35:32,958 - Epoch: 26 Train acc: 93.30727272727273 Val acc: 29.439999999999998 Test acc29.549999999999997; Train loss: 0.0015531480325893922 Val loss: 0.006235687828063965
+INFO - evaluator.py - 2024-10-26 18:36:51,676 - Epoch: 27 Train acc: 93.41454545454545 Val acc: 29.48 Test acc28.720000000000002; Train loss: 0.0014838733501055025 Val loss: 0.00606185417175293
+INFO - evaluator.py - 2024-10-26 18:38:10,313 - Epoch: 28 Train acc: 93.87454545454545 Val acc: 33.72 Test acc33.58; Train loss: 0.0014148837866430934 Val loss: 0.007801075458526611
+INFO - evaluator.py - 2024-10-26 18:39:28,923 - Epoch: 29 Train acc: 93.70363636363636 Val acc: 29.94 Test acc30.0; Train loss: 0.0014495136800814759 Val loss: 0.007115932464599609
+INFO - evaluator.py - 2024-10-26 18:40:47,466 - Epoch: 30 Train acc: 93.74545454545455 Val acc: 32.06 Test acc31.72; Train loss: 0.0014394351371309973 Val loss: 0.006030428695678711
+INFO - evaluator.py - 2024-10-26 18:42:06,022 - Epoch: 31 Train acc: 93.75818181818182 Val acc: 23.380000000000003 Test acc23.46; Train loss: 0.001421016365289688 Val loss: 0.0082602388381958
+INFO - evaluator.py - 2024-10-26 18:43:24,577 - Epoch: 32 Train acc: 94.2909090909091 Val acc: 27.66 Test acc27.67; Train loss: 0.0013073149164291946 Val loss: 0.008069457149505615
+INFO - evaluator.py - 2024-10-26 18:44:43,147 - Epoch: 33 Train acc: 93.65272727272728 Val acc: 24.94 Test acc25.080000000000002; Train loss: 0.0014856356464326382 Val loss: 0.009371804428100585
+INFO - evaluator.py - 2024-10-26 18:46:01,586 - Epoch: 34 Train acc: 94.53636363636365 Val acc: 26.200000000000003 Test acc25.2; Train loss: 0.0012705434990200129 Val loss: 0.00861025447845459
+INFO - evaluator.py - 2024-10-26 18:47:20,104 - Epoch: 35 Train acc: 94.5109090909091 Val acc: 25.840000000000003 Test acc27.150000000000002; Train loss: 0.0013188927972858603 Val loss: 0.009297309303283692
+INFO - evaluator.py - 2024-10-26 18:48:38,629 - Epoch: 36 Train acc: 94.39090909090909 Val acc: 33.900000000000006 Test acc33.75; Train loss: 0.0013114567693322896 Val loss: 0.0038650826454162597
+INFO - evaluator.py - 2024-10-26 18:49:57,195 - Epoch: 37 Train acc: 94.22545454545454 Val acc: 24.740000000000002 Test acc24.26; Train loss: 0.0013390840673988516 Val loss: 0.010360249519348145
+INFO - evaluator.py - 2024-10-26 18:51:15,777 - Epoch: 38 Train acc: 95.31636363636363 Val acc: 27.58 Test acc28.07; Train loss: 0.0011299743623896079 Val loss: 0.00850582675933838
+INFO - evaluator.py - 2024-10-26 18:52:34,549 - Epoch: 39 Train acc: 93.91272727272727 Val acc: 29.62 Test acc28.26; Train loss: 0.0014074704779820008 Val loss: 0.005291779518127441
+INFO - evaluator.py - 2024-10-26 18:53:53,189 - Epoch: 40 Train acc: 94.89999999999999 Val acc: 30.0 Test acc29.880000000000003; Train loss: 0.0011887280424887484 Val loss: 0.00577341947555542
+INFO - evaluator.py - 2024-10-26 18:55:12,080 - Epoch: 41 Train acc: 95.15636363636364 Val acc: 28.18 Test acc27.68; Train loss: 0.0011437587282535704 Val loss: 0.009304792404174804
+INFO - evaluator.py - 2024-10-26 18:56:31,078 - Epoch: 42 Train acc: 94.56909090909092 Val acc: 26.919999999999998 Test acc27.16; Train loss: 0.0012831766679883003 Val loss: 0.006058498859405518
+INFO - evaluator.py - 2024-10-26 18:57:49,783 - Epoch: 43 Train acc: 94.81818181818183 Val acc: 24.12 Test acc24.72; Train loss: 0.0012252492577514865 Val loss: 0.008616259574890137
+INFO - evaluator.py - 2024-10-26 18:59:08,826 - Epoch: 44 Train acc: 95.08727272727273 Val acc: 22.2 Test acc22.08; Train loss: 0.0011544318265535615 Val loss: 0.015601495170593262
+INFO - evaluator.py - 2024-10-26 19:00:27,361 - Epoch: 45 Train acc: 95.13090909090909 Val acc: 28.32 Test acc29.020000000000003; Train loss: 0.0011302568069235844 Val loss: 0.007202647781372071
+INFO - evaluator.py - 2024-10-26 19:01:45,904 - Epoch: 46 Train acc: 95.29272727272728 Val acc: 35.839999999999996 Test acc34.33; Train loss: 0.0011303902381523089 Val loss: 0.004665080642700195
+INFO - evaluator.py - 2024-10-26 19:03:04,479 - Epoch: 47 Train acc: 94.75090909090909 Val acc: 30.12 Test acc30.28; Train loss: 0.0012247949867085976 Val loss: 0.0038960087776184083
+INFO - evaluator.py - 2024-10-26 19:04:23,032 - Epoch: 48 Train acc: 95.4490909090909 Val acc: 23.56 Test acc24.22; Train loss: 0.0010904533484442668 Val loss: 0.00717347297668457
+INFO - evaluator.py - 2024-10-26 19:05:41,765 - Epoch: 49 Train acc: 95.03818181818183 Val acc: 19.48 Test acc18.93; Train loss: 0.0011609040668742222 Val loss: 0.007610122489929199
+INFO - evaluator.py - 2024-10-26 19:07:00,649 - Epoch: 50 Train acc: 95.66181818181818 Val acc: 20.66 Test acc20.5; Train loss: 0.0010401645071465861 Val loss: 0.015031559562683105
+INFO - evaluator.py - 2024-10-26 19:08:19,623 - Epoch: 51 Train acc: 94.70727272727272 Val acc: 29.42 Test acc28.89; Train loss: 0.001233462303165685 Val loss: 0.005355513286590576
+INFO - evaluator.py - 2024-10-26 19:09:38,385 - Epoch: 52 Train acc: 95.11090909090909 Val acc: 24.04 Test acc22.759999999999998; Train loss: 0.0011418163752013987 Val loss: 0.009239851379394532
+INFO - evaluator.py - 2024-10-26 19:10:57,012 - Epoch: 53 Train acc: 95.46 Val acc: 25.96 Test acc27.21; Train loss: 0.0010957914349369027 Val loss: 0.00749125452041626
+INFO - evaluator.py - 2024-10-26 19:12:15,509 - Epoch: 54 Train acc: 95.18363636363635 Val acc: 22.32 Test acc21.93; Train loss: 0.00113161163831299 Val loss: 0.008088311195373536
+INFO - evaluator.py - 2024-10-26 19:13:34,005 - Epoch: 55 Train acc: 95.67454545454545 Val acc: 24.16 Test acc24.05; Train loss: 0.0010187283522364767 Val loss: 0.007141452503204346
+INFO - evaluator.py - 2024-10-26 19:14:52,351 - Epoch: 56 Train acc: 95.02000000000001 Val acc: 27.16 Test acc27.150000000000002; Train loss: 0.001181158398701386 Val loss: 0.005391407012939453
+INFO - evaluator.py - 2024-10-26 19:16:10,759 - Epoch: 57 Train acc: 96.05272727272727 Val acc: 24.48 Test acc25.22; Train loss: 0.0009427385675974867 Val loss: 0.00807127227783203
+INFO - evaluator.py - 2024-10-26 19:17:29,420 - Epoch: 58 Train acc: 95.55272727272728 Val acc: 27.139999999999997 Test acc27.68; Train loss: 0.001073226746442643 Val loss: 0.0073936355590820315
+INFO - evaluator.py - 2024-10-26 19:18:48,181 - Epoch: 59 Train acc: 95.4909090909091 Val acc: 28.84 Test acc29.21; Train loss: 0.0010588486212898384 Val loss: 0.007687525367736816
+INFO - evaluator.py - 2024-10-26 19:20:07,034 - Epoch: 60 Train acc: 99.53818181818181 Val acc: 28.64 Test acc28.62; Train loss: 0.00016934765394015068 Val loss: 0.012042772293090821
+INFO - evaluator.py - 2024-10-26 19:21:25,836 - Epoch: 61 Train acc: 99.96909090909091 Val acc: 20.82 Test acc21.48; Train loss: 4.88931306108663e-05 Val loss: 0.0291370792388916
+INFO - evaluator.py - 2024-10-26 19:22:44,667 - Epoch: 62 Train acc: 99.99090909090908 Val acc: 16.42 Test acc16.84; Train loss: 3.4044140323319216e-05 Val loss: 0.06335307693481446
+INFO - evaluator.py - 2024-10-26 19:24:03,548 - Epoch: 63 Train acc: 100.0 Val acc: 14.04 Test acc13.309999999999999; Train loss: 2.885320741492747e-05 Val loss: 0.12412516632080078
+INFO - evaluator.py - 2024-10-26 19:25:22,223 - Epoch: 64 Train acc: 100.0 Val acc: 11.86 Test acc11.08; Train loss: 2.7640115495093845e-05 Val loss: 0.26132578735351564
+INFO - evaluator.py - 2024-10-26 19:26:40,838 - Epoch: 65 Train acc: 99.99818181818182 Val acc: 10.66 Test acc10.31; Train loss: 2.631873656275936e-05 Val loss: 0.49177244262695313
+INFO - evaluator.py - 2024-10-26 19:27:59,404 - Epoch: 66 Train acc: 100.0 Val acc: 10.34 Test acc10.040000000000001; Train loss: 2.6303042369810018e-05 Val loss: 0.919958349609375
+INFO - evaluator.py - 2024-10-26 19:29:18,164 - Epoch: 67 Train acc: 100.0 Val acc: 10.22 Test acc10.01; Train loss: 2.6340424260971222e-05 Val loss: 1.60318525390625
+INFO - evaluator.py - 2024-10-26 19:30:36,839 - Epoch: 68 Train acc: 100.0 Val acc: 10.16 Test acc10.0; Train loss: 2.673503967340697e-05 Val loss: 2.586512109375
+INFO - evaluator.py - 2024-10-26 19:31:55,535 - Epoch: 69 Train acc: 100.0 Val acc: 10.18 Test acc10.02; Train loss: 2.6245704595930873e-05 Val loss: 3.996236181640625
+INFO - evaluator.py - 2024-10-26 19:33:14,300 - Epoch: 70 Train acc: 100.0 Val acc: 10.2 Test acc10.040000000000001; Train loss: 2.6928928577002478e-05 Val loss: 5.795536328125
+INFO - evaluator.py - 2024-10-26 19:34:33,169 - Epoch: 71 Train acc: 100.0 Val acc: 10.26 Test acc10.08; Train loss: 2.572882263921201e-05 Val loss: 8.5081388671875
+INFO - evaluator.py - 2024-10-26 19:35:51,981 - Epoch: 72 Train acc: 100.0 Val acc: 10.48 Test acc10.25; Train loss: 2.3591289586726237e-05 Val loss: 11.80328515625
+INFO - evaluator.py - 2024-10-26 19:37:10,820 - Epoch: 73 Train acc: 100.0 Val acc: 10.780000000000001 Test acc10.549999999999999; Train loss: 2.4482802451926878e-05 Val loss: 16.93960234375
+INFO - evaluator.py - 2024-10-26 19:38:29,502 - Epoch: 74 Train acc: 100.0 Val acc: 11.44 Test acc11.559999999999999; Train loss: 2.4321202182380314e-05 Val loss: 21.383091796875
+INFO - evaluator.py - 2024-10-26 19:39:48,181 - Epoch: 75 Train acc: 100.0 Val acc: 12.58 Test acc12.53; Train loss: 2.3198775299401444e-05 Val loss: 29.81000234375
+INFO - evaluator.py - 2024-10-26 19:41:06,955 - Epoch: 76 Train acc: 100.0 Val acc: 13.26 Test acc12.85; Train loss: 2.3620289252986286e-05 Val loss: 38.0079578125
+INFO - evaluator.py - 2024-10-26 19:42:25,701 - Epoch: 77 Train acc: 100.0 Val acc: 13.200000000000001 Test acc12.78; Train loss: 2.1477784506383946e-05 Val loss: 50.595109375
+INFO - evaluator.py - 2024-10-26 19:43:44,379 - Epoch: 78 Train acc: 100.0 Val acc: 12.0 Test acc12.3; Train loss: 2.0980674775571308e-05 Val loss: 69.697671875
+INFO - evaluator.py - 2024-10-26 19:45:03,173 - Epoch: 79 Train acc: 100.0 Val acc: 11.84 Test acc12.11; Train loss: 2.291591156020083e-05 Val loss: 89.4914953125
+INFO - evaluator.py - 2024-10-26 19:46:21,670 - Epoch: 80 Train acc: 100.0 Val acc: 11.64 Test acc11.97; Train loss: 2.1375271650454536e-05 Val loss: 116.4732875
+INFO - evaluator.py - 2024-10-26 19:47:40,164 - Epoch: 81 Train acc: 99.98727272727272 Val acc: 11.600000000000001 Test acc11.98; Train loss: 3.34553355181759e-05 Val loss: 127.9683203125
+INFO - evaluator.py - 2024-10-26 19:48:58,568 - Epoch: 82 Train acc: 99.82545454545455 Val acc: 10.440000000000001 Test acc11.06; Train loss: 9.775151285681534e-05 Val loss: 37.8889296875
+INFO - evaluator.py - 2024-10-26 19:50:17,229 - Epoch: 83 Train acc: 98.11454545454545 Val acc: 10.16 Test acc10.0; Train loss: 0.0005728710173205896 Val loss: 0.725707666015625
+INFO - evaluator.py - 2024-10-26 19:51:35,992 - Epoch: 84 Train acc: 98.49454545454546 Val acc: 10.76 Test acc10.459999999999999; Train loss: 0.00043762034584175454 Val loss: 0.11947062225341797
+INFO - evaluator.py - 2024-10-26 19:52:54,784 - Epoch: 85 Train acc: 99.55818181818182 Val acc: 11.92 Test acc11.83; Train loss: 0.000163070027212697 Val loss: 0.12081173400878906
+INFO - evaluator.py - 2024-10-26 19:54:13,531 - Epoch: 86 Train acc: 99.83090909090909 Val acc: 11.58 Test acc11.5; Train loss: 8.088048264934597e-05 Val loss: 0.189152490234375
+INFO - evaluator.py - 2024-10-26 19:55:32,280 - Epoch: 87 Train acc: 99.89272727272727 Val acc: 11.540000000000001 Test acc11.29; Train loss: 6.151085877579383e-05 Val loss: 0.24022737731933594
+INFO - evaluator.py - 2024-10-26 19:56:51,041 - Epoch: 88 Train acc: 99.9890909090909 Val acc: 10.7 Test acc10.66; Train loss: 2.1771387695546516e-05 Val loss: 0.5490681396484375
+INFO - evaluator.py - 2024-10-26 19:58:09,820 - Epoch: 89 Train acc: 100.0 Val acc: 11.52 Test acc11.67; Train loss: 1.158775454598733e-05 Val loss: 1.001979150390625
+INFO - evaluator.py - 2024-10-26 19:59:28,590 - Epoch: 90 Train acc: 100.0 Val acc: 13.200000000000001 Test acc13.11; Train loss: 1.0366373267871412e-05 Val loss: 1.8811920654296874
+INFO - evaluator.py - 2024-10-26 20:00:47,691 - Epoch: 91 Train acc: 100.0 Val acc: 13.86 Test acc13.29; Train loss: 1.0767081005244769e-05 Val loss: 3.58446171875
+INFO - evaluator.py - 2024-10-26 20:02:06,424 - Epoch: 92 Train acc: 100.0 Val acc: 13.54 Test acc13.18; Train loss: 1.2645004711918195e-05 Val loss: 6.308230078125
+INFO - evaluator.py - 2024-10-26 20:03:25,093 - Epoch: 93 Train acc: 100.0 Val acc: 13.120000000000001 Test acc12.86; Train loss: 1.4897521845573052e-05 Val loss: 10.16358046875
+INFO - evaluator.py - 2024-10-26 20:04:43,569 - Epoch: 94 Train acc: 100.0 Val acc: 11.06 Test acc11.72; Train loss: 1.6207763645797966e-05 Val loss: 16.609115234375
+INFO - evaluator.py - 2024-10-26 20:06:02,132 - Epoch: 95 Train acc: 96.67999999999999 Val acc: 15.340000000000002 Test acc13.91; Train loss: 0.000858693802841431 Val loss: 0.007588305282592773
+INFO - evaluator.py - 2024-10-26 20:07:20,794 - Epoch: 96 Train acc: 96.74363636363637 Val acc: 10.08 Test acc10.05; Train loss: 0.0008663004944947632 Val loss: 0.0067049445152282715
+INFO - evaluator.py - 2024-10-26 20:08:39,396 - Epoch: 97 Train acc: 99.14727272727274 Val acc: 15.76 Test acc15.2; Train loss: 0.00026265583669936115 Val loss: 0.003677298831939697
+INFO - evaluator.py - 2024-10-26 20:09:58,074 - Epoch: 98 Train acc: 99.84181818181818 Val acc: 24.34 Test acc24.14; Train loss: 8.367861657064746e-05 Val loss: 0.0036042426109313963
+INFO - evaluator.py - 2024-10-26 20:11:17,008 - Epoch: 99 Train acc: 99.97454545454545 Val acc: 30.12 Test acc29.37; Train loss: 2.81184941498478e-05 Val loss: 0.004915830993652344
+INFO - evaluator.py - 2024-10-26 20:12:35,989 - Epoch: 100 Train acc: 99.99454545454546 Val acc: 28.74 Test acc28.389999999999997; Train loss: 1.3473355948967351e-05 Val loss: 0.009399392318725585
+INFO - evaluator.py - 2024-10-26 20:13:55,017 - Epoch: 101 Train acc: 100.0 Val acc: 21.4 Test acc21.4; Train loss: 1.2674618484875696e-05 Val loss: 0.026947535705566406
+INFO - evaluator.py - 2024-10-26 20:15:14,020 - Epoch: 102 Train acc: 100.0 Val acc: 15.28 Test acc15.559999999999999; Train loss: 1.1487631948495453e-05 Val loss: 0.07747395629882813
+INFO - evaluator.py - 2024-10-26 20:16:32,907 - Epoch: 103 Train acc: 100.0 Val acc: 12.18 Test acc12.139999999999999; Train loss: 1.2336052851539783e-05 Val loss: 0.22342206420898436
+INFO - evaluator.py - 2024-10-26 20:17:52,145 - Epoch: 104 Train acc: 100.0 Val acc: 11.559999999999999 Test acc11.450000000000001; Train loss: 1.2789106591265988e-05 Val loss: 0.5213739379882812
+INFO - evaluator.py - 2024-10-26 20:19:10,838 - Epoch: 105 Train acc: 100.0 Val acc: 10.94 Test acc11.15; Train loss: 1.7066932094960727e-05 Val loss: 1.0764477783203126
+INFO - evaluator.py - 2024-10-26 20:20:29,455 - Epoch: 106 Train acc: 100.0 Val acc: 12.479999999999999 Test acc12.45; Train loss: 1.4977712786375461e-05 Val loss: 1.9375822998046874
+INFO - evaluator.py - 2024-10-26 20:21:48,071 - Epoch: 107 Train acc: 100.0 Val acc: 12.2 Test acc11.93; Train loss: 1.574593135684898e-05 Val loss: 3.427979443359375
+INFO - evaluator.py - 2024-10-26 20:23:06,621 - Epoch: 108 Train acc: 100.0 Val acc: 11.42 Test acc11.459999999999999; Train loss: 1.699644408019429e-05 Val loss: 5.4577302734375
+INFO - evaluator.py - 2024-10-26 20:24:25,317 - Epoch: 109 Train acc: 100.0 Val acc: 11.28 Test acc11.360000000000001; Train loss: 1.7500787159554998e-05 Val loss: 8.10769140625
+INFO - evaluator.py - 2024-10-26 20:25:44,188 - Epoch: 110 Train acc: 94.53818181818183 Val acc: 12.139999999999999 Test acc12.19; Train loss: 0.0013633087484240108 Val loss: 0.002897948503494263
+INFO - evaluator.py - 2024-10-26 20:27:03,212 - Epoch: 111 Train acc: 95.98909090909092 Val acc: 9.879999999999999 Test acc10.0; Train loss: 0.0010411158507520502 Val loss: 0.0031035478115081787
+INFO - evaluator.py - 2024-10-26 20:28:22,071 - Epoch: 112 Train acc: 98.80181818181818 Val acc: 11.0 Test acc10.36; Train loss: 0.0003456011405214667 Val loss: 0.003027235746383667
+INFO - evaluator.py - 2024-10-26 20:29:41,047 - Epoch: 113 Train acc: 99.26 Val acc: 9.879999999999999 Test acc10.0; Train loss: 0.0002334033620501445 Val loss: 0.0039351463317871095
+INFO - evaluator.py - 2024-10-26 20:31:00,042 - Epoch: 114 Train acc: 99.71454545454546 Val acc: 15.1 Test acc14.879999999999999; Train loss: 0.00011445445466405627 Val loss: 0.0036463857173919677
+INFO - evaluator.py - 2024-10-26 20:32:19,332 - Epoch: 115 Train acc: 99.87454545454545 Val acc: 17.68 Test acc17.49; Train loss: 6.66703887728297e-05 Val loss: 0.003661229991912842
+INFO - evaluator.py - 2024-10-26 20:33:38,475 - Epoch: 116 Train acc: 99.97454545454545 Val acc: 25.779999999999998 Test acc25.19; Train loss: 2.7063513624439524e-05 Val loss: 0.0026948994636535645
+INFO - evaluator.py - 2024-10-26 20:34:57,690 - Epoch: 117 Train acc: 99.9890909090909 Val acc: 37.68 Test acc36.8; Train loss: 1.648848142993467e-05 Val loss: 0.0032455411434173585
+INFO - evaluator.py - 2024-10-26 20:36:16,780 - Epoch: 118 Train acc: 100.0 Val acc: 28.38 Test acc28.12; Train loss: 1.2519860814262012e-05 Val loss: 0.009263991737365723
+INFO - evaluator.py - 2024-10-26 20:37:35,886 - Epoch: 119 Train acc: 100.0 Val acc: 18.12 Test acc18.48; Train loss: 1.0513868037907576e-05 Val loss: 0.030361394119262697
+INFO - evaluator.py - 2024-10-26 20:38:54,795 - Epoch: 120 Train acc: 100.0 Val acc: 19.0 Test acc19.36; Train loss: 9.858152590988374e-06 Val loss: 0.031490067672729494
+INFO - evaluator.py - 2024-10-26 20:40:13,510 - Epoch: 121 Train acc: 100.0 Val acc: 17.419999999999998 Test acc17.599999999999998; Train loss: 1.0513983070003715e-05 Val loss: 0.036959583282470704
+INFO - evaluator.py - 2024-10-26 20:41:32,170 - Epoch: 122 Train acc: 100.0 Val acc: 17.24 Test acc17.36; Train loss: 1.0468727445483884e-05 Val loss: 0.03959898529052734
+INFO - evaluator.py - 2024-10-26 20:42:50,736 - Epoch: 123 Train acc: 100.0 Val acc: 18.02 Test acc18.09; Train loss: 1.0905614638150754e-05 Val loss: 0.03995451049804687
+INFO - evaluator.py - 2024-10-26 20:44:09,178 - Epoch: 124 Train acc: 100.0 Val acc: 17.32 Test acc17.419999999999998; Train loss: 1.0343367356637662e-05 Val loss: 0.044219947052001954
+INFO - evaluator.py - 2024-10-26 20:45:27,741 - Epoch: 125 Train acc: 100.0 Val acc: 17.14 Test acc17.19; Train loss: 1.1241883098740469e-05 Val loss: 0.04628953323364258
+INFO - evaluator.py - 2024-10-26 20:46:46,522 - Epoch: 126 Train acc: 100.0 Val acc: 16.32 Test acc16.24; Train loss: 1.088807111267339e-05 Val loss: 0.05232998962402344
+INFO - evaluator.py - 2024-10-26 20:48:05,357 - Epoch: 127 Train acc: 100.0 Val acc: 16.38 Test acc16.32; Train loss: 1.1300842155998742e-05 Val loss: 0.053121054077148434
+INFO - evaluator.py - 2024-10-26 20:49:24,190 - Epoch: 128 Train acc: 100.0 Val acc: 16.54 Test acc16.619999999999997; Train loss: 1.1831445940135215e-05 Val loss: 0.05621515731811524
+INFO - evaluator.py - 2024-10-26 20:50:42,950 - Epoch: 129 Train acc: 100.0 Val acc: 15.9 Test acc15.790000000000001; Train loss: 1.1749917259228161e-05 Val loss: 0.059573983001708984
+INFO - evaluator.py - 2024-10-26 20:52:01,712 - Epoch: 130 Train acc: 100.0 Val acc: 15.620000000000001 Test acc15.459999999999999; Train loss: 1.1870699271094054e-05 Val loss: 0.06497544326782227
+INFO - evaluator.py - 2024-10-26 20:53:20,668 - Epoch: 131 Train acc: 100.0 Val acc: 15.299999999999999 Test acc15.25; Train loss: 1.2252605049235915e-05 Val loss: 0.06811334381103516
+INFO - evaluator.py - 2024-10-26 20:54:39,630 - Epoch: 132 Train acc: 100.0 Val acc: 14.92 Test acc14.7; Train loss: 1.1973257688805461e-05 Val loss: 0.07237617950439452
+INFO - evaluator.py - 2024-10-26 20:55:58,575 - Epoch: 133 Train acc: 100.0 Val acc: 15.06 Test acc14.77; Train loss: 1.2513635111761026e-05 Val loss: 0.07368907012939453
+INFO - evaluator.py - 2024-10-26 20:57:17,488 - Epoch: 134 Train acc: 100.0 Val acc: 15.0 Test acc14.81; Train loss: 1.2951785887972536e-05 Val loss: 0.07592268676757813
+INFO - evaluator.py - 2024-10-26 20:58:36,452 - Epoch: 135 Train acc: 100.0 Val acc: 15.02 Test acc14.69; Train loss: 1.256663264410401e-05 Val loss: 0.07891687774658203
+INFO - evaluator.py - 2024-10-26 20:59:55,214 - Epoch: 136 Train acc: 100.0 Val acc: 14.62 Test acc14.37; Train loss: 1.3010387676133013e-05 Val loss: 0.08139472045898437
+INFO - evaluator.py - 2024-10-26 21:01:13,828 - Epoch: 137 Train acc: 100.0 Val acc: 15.2 Test acc14.87; Train loss: 1.2909800434400413e-05 Val loss: 0.07920527496337891
+INFO - evaluator.py - 2024-10-26 21:02:32,566 - Epoch: 138 Train acc: 100.0 Val acc: 14.38 Test acc14.219999999999999; Train loss: 1.3396342787679962e-05 Val loss: 0.08589370880126954
+INFO - evaluator.py - 2024-10-26 21:03:51,382 - Epoch: 139 Train acc: 100.0 Val acc: 14.7 Test acc14.38; Train loss: 1.3359556136525829e-05 Val loss: 0.08754972229003906
+INFO - evaluator.py - 2024-10-26 21:05:10,335 - Epoch: 140 Train acc: 100.0 Val acc: 14.48 Test acc14.299999999999999; Train loss: 1.365163623757491e-05 Val loss: 0.08867274169921875
+INFO - evaluator.py - 2024-10-26 21:06:28,955 - Epoch: 141 Train acc: 100.0 Val acc: 14.7 Test acc14.399999999999999; Train loss: 1.3815744499548932e-05 Val loss: 0.08960809478759765
+INFO - evaluator.py - 2024-10-26 21:07:47,729 - Epoch: 142 Train acc: 100.0 Val acc: 14.62 Test acc14.32; Train loss: 1.3364696021149444e-05 Val loss: 0.092016455078125
+INFO - evaluator.py - 2024-10-26 21:09:06,702 - Epoch: 143 Train acc: 100.0 Val acc: 14.04 Test acc13.87; Train loss: 1.3367281739854e-05 Val loss: 0.0972457260131836
+INFO - evaluator.py - 2024-10-26 21:10:25,658 - Epoch: 144 Train acc: 100.0 Val acc: 13.919999999999998 Test acc13.8; Train loss: 1.3373114476615394e-05 Val loss: 0.09645409545898438
+INFO - evaluator.py - 2024-10-26 21:11:44,665 - Epoch: 145 Train acc: 100.0 Val acc: 14.360000000000001 Test acc14.180000000000001; Train loss: 1.416841002117673e-05 Val loss: 0.09567544860839844
+INFO - evaluator.py - 2024-10-26 21:13:03,609 - Epoch: 146 Train acc: 100.0 Val acc: 13.819999999999999 Test acc13.58; Train loss: 1.3627994929397986e-05 Val loss: 0.09852180023193359
+INFO - evaluator.py - 2024-10-26 21:14:22,524 - Epoch: 147 Train acc: 100.0 Val acc: 13.52 Test acc13.33; Train loss: 1.3387986092658884e-05 Val loss: 0.10280430297851563
+INFO - evaluator.py - 2024-10-26 21:15:41,265 - Epoch: 148 Train acc: 100.0 Val acc: 13.719999999999999 Test acc13.669999999999998; Train loss: 1.4007104918445376e-05 Val loss: 0.10246100463867187
+INFO - evaluator.py - 2024-10-26 21:16:59,962 - Epoch: 149 Train acc: 100.0 Val acc: 13.38 Test acc13.03; Train loss: 1.3737279233861376e-05 Val loss: 0.10830574340820312
+INFO - evaluator.py - 2024-10-26 21:18:18,497 - Epoch: 150 Train acc: 100.0 Val acc: 13.600000000000001 Test acc13.5; Train loss: 1.3877581918231127e-05 Val loss: 0.10196796112060547
+INFO - evaluator.py - 2024-10-26 21:19:37,122 - Epoch: 151 Train acc: 100.0 Val acc: 13.459999999999999 Test acc13.309999999999999; Train loss: 1.3379304829603908e-05 Val loss: 0.10358463134765625
+INFO - evaluator.py - 2024-10-26 21:20:55,806 - Epoch: 152 Train acc: 100.0 Val acc: 13.44 Test acc13.059999999999999; Train loss: 1.3956040410663593e-05 Val loss: 0.1039241439819336
+INFO - evaluator.py - 2024-10-26 21:22:14,539 - Epoch: 153 Train acc: 100.0 Val acc: 13.52 Test acc13.309999999999999; Train loss: 1.3743541826790368e-05 Val loss: 0.09774365386962891
+INFO - evaluator.py - 2024-10-26 21:23:33,328 - Epoch: 154 Train acc: 100.0 Val acc: 13.56 Test acc13.22; Train loss: 1.4131237736860799e-05 Val loss: 0.09774871520996094
+INFO - evaluator.py - 2024-10-26 21:24:52,323 - Epoch: 155 Train acc: 100.0 Val acc: 13.459999999999999 Test acc13.08; Train loss: 1.4031652198173106e-05 Val loss: 0.10012387084960937
+INFO - evaluator.py - 2024-10-26 21:26:11,395 - Epoch: 156 Train acc: 100.0 Val acc: 13.320000000000002 Test acc12.959999999999999; Train loss: 1.374093705301427e-05 Val loss: 0.09760721282958984
+INFO - evaluator.py - 2024-10-26 21:27:30,632 - Epoch: 157 Train acc: 100.0 Val acc: 13.200000000000001 Test acc12.8; Train loss: 1.3258946062573655e-05 Val loss: 0.09770384063720704
+INFO - evaluator.py - 2024-10-26 21:28:49,464 - Epoch: 158 Train acc: 100.0 Val acc: 13.4 Test acc13.03; Train loss: 1.3639482282186774e-05 Val loss: 0.09589189910888672
+INFO - evaluator.py - 2024-10-26 21:30:08,313 - Epoch: 159 Train acc: 100.0 Val acc: 13.76 Test acc13.450000000000001; Train loss: 1.351048861079934e-05 Val loss: 0.08880516052246094
+INFO - evaluator.py - 2024-10-26 21:31:27,194 - Epoch: 160 Train acc: 100.0 Val acc: 13.74 Test acc13.420000000000002; Train loss: 1.3755314303985373e-05 Val loss: 0.08837624664306641
+INFO - evaluator.py - 2024-10-26 21:32:46,204 - Epoch: 161 Train acc: 100.0 Val acc: 13.96 Test acc13.51; Train loss: 1.3110312433193691e-05 Val loss: 0.08582529602050781
+INFO - evaluator.py - 2024-10-26 21:34:04,789 - Epoch: 162 Train acc: 100.0 Val acc: 13.84 Test acc13.420000000000002; Train loss: 1.3250021274540235e-05 Val loss: 0.08189734649658204
+INFO - evaluator.py - 2024-10-26 21:35:23,479 - Epoch: 163 Train acc: 100.0 Val acc: 14.12 Test acc13.66; Train loss: 1.328970621847971e-05 Val loss: 0.07953425903320313
+INFO - evaluator.py - 2024-10-26 21:36:42,156 - Epoch: 164 Train acc: 100.0 Val acc: 13.900000000000002 Test acc13.450000000000001; Train loss: 1.3420369363897903e-05 Val loss: 0.08040586700439453
+INFO - evaluator.py - 2024-10-26 21:38:00,779 - Epoch: 165 Train acc: 100.0 Val acc: 13.239999999999998 Test acc12.870000000000001; Train loss: 1.3295004178177226e-05 Val loss: 0.08377252502441407
+INFO - evaluator.py - 2024-10-26 21:39:19,385 - Epoch: 166 Train acc: 100.0 Val acc: 13.62 Test acc13.08; Train loss: 1.2719060237180781e-05 Val loss: 0.07675940704345703
+INFO - evaluator.py - 2024-10-26 21:40:37,933 - Epoch: 167 Train acc: 100.0 Val acc: 13.4 Test acc12.97; Train loss: 1.3139035276518288e-05 Val loss: 0.0752447250366211
+INFO - evaluator.py - 2024-10-26 21:41:56,508 - Epoch: 168 Train acc: 100.0 Val acc: 13.200000000000001 Test acc12.740000000000002; Train loss: 1.3383993466215378e-05 Val loss: 0.07506266632080077
+INFO - evaluator.py - 2024-10-26 21:43:15,172 - Epoch: 169 Train acc: 100.0 Val acc: 13.059999999999999 Test acc12.590000000000002; Train loss: 1.3350968634371054e-05 Val loss: 0.0745497299194336
+INFO - evaluator.py - 2024-10-26 21:44:33,809 - Epoch: 170 Train acc: 100.0 Val acc: 13.459999999999999 Test acc12.950000000000001; Train loss: 1.2949147169605237e-05 Val loss: 0.06699364318847656
+INFO - evaluator.py - 2024-10-26 21:45:52,433 - Epoch: 171 Train acc: 100.0 Val acc: 13.100000000000001 Test acc12.620000000000001; Train loss: 1.395135902249339e-05 Val loss: 0.06769280395507812
+INFO - evaluator.py - 2024-10-26 21:47:11,009 - Epoch: 172 Train acc: 100.0 Val acc: 12.520000000000001 Test acc12.11; Train loss: 1.2910406866153194e-05 Val loss: 0.07122139282226563
+INFO - evaluator.py - 2024-10-26 21:48:29,591 - Epoch: 173 Train acc: 100.0 Val acc: 12.8 Test acc12.41; Train loss: 1.3053798823702065e-05 Val loss: 0.06663780212402344
+INFO - evaluator.py - 2024-10-26 21:49:48,236 - Epoch: 174 Train acc: 100.0 Val acc: 13.08 Test acc12.629999999999999; Train loss: 1.2976074240974743e-05 Val loss: 0.06222069625854492
+INFO - evaluator.py - 2024-10-26 21:51:07,109 - Epoch: 175 Train acc: 100.0 Val acc: 12.68 Test acc12.280000000000001; Train loss: 1.3015596493443643e-05 Val loss: 0.06281260604858399
+INFO - evaluator.py - 2024-10-26 21:52:26,032 - Epoch: 176 Train acc: 100.0 Val acc: 13.18 Test acc12.68; Train loss: 1.270610181487758e-05 Val loss: 0.05840375289916992
+INFO - evaluator.py - 2024-10-26 21:53:44,997 - Epoch: 177 Train acc: 100.0 Val acc: 12.82 Test acc12.43; Train loss: 1.3228525339879773e-05 Val loss: 0.0586435546875
+INFO - evaluator.py - 2024-10-26 21:55:03,962 - Epoch: 178 Train acc: 100.0 Val acc: 12.94 Test acc12.49; Train loss: 1.2617527976081791e-05 Val loss: 0.054038347625732425
+INFO - evaluator.py - 2024-10-26 21:56:22,768 - Epoch: 179 Train acc: 100.0 Val acc: 12.9 Test acc12.5; Train loss: 1.2457171717489308e-05 Val loss: 0.05307389144897461
+INFO - evaluator.py - 2024-10-26 21:57:41,548 - Epoch: 180 Train acc: 100.0 Val acc: 13.8 Test acc13.29; Train loss: 1.2266850486313078e-05 Val loss: 0.045393663024902345
+INFO - evaluator.py - 2024-10-26 21:59:00,371 - Epoch: 181 Train acc: 100.0 Val acc: 13.700000000000001 Test acc13.139999999999999; Train loss: 1.1809650502717969e-05 Val loss: 0.042661957550048826
+INFO - evaluator.py - 2024-10-26 22:00:19,302 - Epoch: 182 Train acc: 100.0 Val acc: 14.299999999999999 Test acc13.71; Train loss: 1.1954657623375004e-05 Val loss: 0.03743687744140625
+INFO - evaluator.py - 2024-10-26 22:01:37,981 - Epoch: 183 Train acc: 100.0 Val acc: 14.7 Test acc14.069999999999999; Train loss: 1.1645671460692855e-05 Val loss: 0.034681957244873045
+INFO - evaluator.py - 2024-10-26 22:02:56,851 - Epoch: 184 Train acc: 100.0 Val acc: 15.079999999999998 Test acc14.29; Train loss: 1.2028066876386716e-05 Val loss: 0.0313770637512207
+INFO - evaluator.py - 2024-10-26 22:04:15,828 - Epoch: 185 Train acc: 100.0 Val acc: 16.02 Test acc15.21; Train loss: 1.2066266938663003e-05 Val loss: 0.02749907569885254
+INFO - evaluator.py - 2024-10-26 22:05:34,847 - Epoch: 186 Train acc: 100.0 Val acc: 16.220000000000002 Test acc15.47; Train loss: 1.2085250987332653e-05 Val loss: 0.02512684555053711
+INFO - evaluator.py - 2024-10-26 22:06:53,855 - Epoch: 187 Train acc: 100.0 Val acc: 16.400000000000002 Test acc15.920000000000002; Train loss: 1.2063611138993027e-05 Val loss: 0.023525184631347656
+INFO - evaluator.py - 2024-10-26 22:08:12,714 - Epoch: 188 Train acc: 100.0 Val acc: 16.939999999999998 Test acc16.49; Train loss: 1.2056489079259336e-05 Val loss: 0.02160581703186035
+INFO - evaluator.py - 2024-10-26 22:09:31,494 - Epoch: 189 Train acc: 100.0 Val acc: 17.599999999999998 Test acc17.39; Train loss: 1.1648742731829936e-05 Val loss: 0.01924864387512207
+INFO - evaluator.py - 2024-10-26 22:10:50,195 - Epoch: 190 Train acc: 100.0 Val acc: 17.78 Test acc17.47; Train loss: 1.1686260273299095e-05 Val loss: 0.018937464141845703
+INFO - evaluator.py - 2024-10-26 22:12:08,773 - Epoch: 191 Train acc: 100.0 Val acc: 18.759999999999998 Test acc18.65; Train loss: 1.1866004118399525e-05 Val loss: 0.016066427612304687
+INFO - evaluator.py - 2024-10-26 22:13:27,569 - Epoch: 192 Train acc: 100.0 Val acc: 18.9 Test acc18.93; Train loss: 1.1772388365881687e-05 Val loss: 0.015545502662658691
+INFO - evaluator.py - 2024-10-26 22:14:46,238 - Epoch: 193 Train acc: 100.0 Val acc: 19.78 Test acc19.71; Train loss: 1.2344137474428862e-05 Val loss: 0.014079130363464356
+INFO - evaluator.py - 2024-10-26 22:16:05,071 - Epoch: 194 Train acc: 100.0 Val acc: 20.18 Test acc20.07; Train loss: 1.2022080339110372e-05 Val loss: 0.013299431419372558
+INFO - evaluator.py - 2024-10-26 22:17:23,681 - Epoch: 195 Train acc: 100.0 Val acc: 20.4 Test acc20.330000000000002; Train loss: 1.1352157526099208e-05 Val loss: 0.01246220760345459
+INFO - evaluator.py - 2024-10-26 22:18:42,512 - Epoch: 196 Train acc: 100.0 Val acc: 20.599999999999998 Test acc20.65; Train loss: 1.1998691705097867e-05 Val loss: 0.012127499198913575
+INFO - evaluator.py - 2024-10-26 22:20:01,129 - Epoch: 197 Train acc: 100.0 Val acc: 21.52 Test acc21.37; Train loss: 1.2096692332786254e-05 Val loss: 0.01093718662261963
+INFO - evaluator.py - 2024-10-26 22:21:19,736 - Epoch: 198 Train acc: 100.0 Val acc: 21.0 Test acc21.08; Train loss: 1.2115579494275152e-05 Val loss: 0.01130635108947754
+INFO - evaluator.py - 2024-10-26 22:22:38,408 - Epoch: 199 Train acc: 100.0 Val acc: 22.42 Test acc22.040000000000003; Train loss: 1.1386211260899224e-05 Val loss: 0.009963677978515625
+INFO - evaluator.py - 2024-10-26 22:22:38,410 - The best acc of synthetic images on sensitive val and the corresponding acc on test dataset from resnext is 37.68 and 36.8
+INFO - evaluator.py - 2024-10-26 22:22:38,410 - The best acc of synthetic images on noisy sensitive val and the corresponding acc on test dataset from resnext is 37.68 and 36.8
+INFO - evaluator.py - 2024-10-26 22:22:38,410 - The best acc test dataset from resnext is 36.8
+INFO - evaluator.py - 2024-10-26 22:22:38,411 - The best acc of accuracy (using synthetic images as the validation set) of synthetic images from resnet, wrn, and resnext are [34.13, 36.059999999999995, 36.8].
+INFO - evaluator.py - 2024-10-26 22:22:38,411 - The average and std of accuracy of synthetic images are 35.66 and 1.13
+INFO - dataset_loader.py - 2024-10-28 16:30:06,730 - delta is reset as 2.07404851125286e-06
+INFO - evaluator.py - 2024-10-28 17:37:14,035 - The FID of synthetic images is 110.1077091760867
+INFO - evaluator.py - 2024-10-28 17:37:14,037 - The Inception Score of synthetic images is 3.1288182735443115
+INFO - evaluator.py - 2024-10-28 17:37:14,037 - The Precision and Recall of synthetic images is 0.5966984033584595 and 0.036159999668598175
+INFO - evaluator.py - 2024-10-28 17:37:14,037 - The FLD of synthetic images is 19.009149074554443
+INFO - evaluator.py - 2024-10-28 17:37:14,037 - The ImageReward of synthetic images is -2.214698282242767
+INFO - dataset_loader.py - 2024-10-28 19:02:37,446 - delta is reset as 2.07404851125286e-06
+INFO - evaluator.py - 2024-10-28 19:04:33,427 - Epoch: 0 Train acc: 9.972727272727273 Val acc: 8.799999999999999 Test acc9.120000000000001; Train loss: 0.019373420533266933 Val loss: 0.0023052162647247314
+INFO - evaluator.py - 2024-10-28 19:05:46,458 - Epoch: 1 Train acc: 10.018181818181818 Val acc: 10.48 Test acc10.57; Train loss: 0.01830985530939969 Val loss: 0.0023106085777282715
+INFO - evaluator.py - 2024-10-28 19:06:59,152 - Epoch: 2 Train acc: 13.741818181818182 Val acc: 14.08 Test acc14.540000000000001; Train loss: 0.017884794317592274 Val loss: 0.035334281539916995
+INFO - evaluator.py - 2024-10-28 19:08:10,719 - Epoch: 3 Train acc: 21.254545454545454 Val acc: 11.540000000000001 Test acc11.39; Train loss: 0.016041422980481928 Val loss: 235.611884375
+INFO - evaluator.py - 2024-10-28 19:09:23,232 - Epoch: 4 Train acc: 30.209090909090907 Val acc: 10.2 Test acc10.040000000000001; Train loss: 0.013987511255524375 Val loss: 331.7216375
+INFO - evaluator.py - 2024-10-28 19:10:35,495 - Epoch: 5 Train acc: 39.525454545454544 Val acc: 10.16 Test acc10.0; Train loss: 0.012140994121811606 Val loss: 3846.2529
+INFO - evaluator.py - 2024-10-28 19:11:47,298 - Epoch: 6 Train acc: 45.092727272727274 Val acc: 10.16 Test acc10.0; Train loss: 0.010891232607581399 Val loss: 2787.69555
+INFO - evaluator.py - 2024-10-28 19:12:58,915 - Epoch: 7 Train acc: 48.20181818181818 Val acc: 10.16 Test acc10.0; Train loss: 0.010312528334964405 Val loss: 174211.9968
+INFO - evaluator.py - 2024-10-28 19:14:10,772 - Epoch: 8 Train acc: 51.06363636363637 Val acc: 10.16 Test acc10.0; Train loss: 0.00981518687768416 Val loss: 9571.7916
+INFO - evaluator.py - 2024-10-28 19:15:21,714 - Epoch: 9 Train acc: 54.843636363636364 Val acc: 10.040000000000001 Test acc10.0; Train loss: 0.009227424560893666 Val loss: 2214.8079
+INFO - evaluator.py - 2024-10-28 19:16:33,155 - Epoch: 10 Train acc: 57.947272727272725 Val acc: 9.9 Test acc9.8; Train loss: 0.008661381801691922 Val loss: 4687.3977
+INFO - evaluator.py - 2024-10-28 19:17:46,937 - Epoch: 11 Train acc: 61.75090909090909 Val acc: 10.26 Test acc10.100000000000001; Train loss: 0.007905393460663882 Val loss: 1662.93625
+INFO - evaluator.py - 2024-10-28 19:18:59,287 - Epoch: 12 Train acc: 66.2890909090909 Val acc: 10.040000000000001 Test acc10.0; Train loss: 0.007074990799210288 Val loss: 1192.7683375
+INFO - evaluator.py - 2024-10-28 19:20:12,187 - Epoch: 13 Train acc: 69.38 Val acc: 16.3 Test acc16.21; Train loss: 0.006509326010400599 Val loss: 0.29429794921875
+INFO - evaluator.py - 2024-10-28 19:21:23,694 - Epoch: 14 Train acc: 73.39636363636363 Val acc: 26.740000000000002 Test acc27.08; Train loss: 0.005755381668697704 Val loss: 0.0038077638626098633
+INFO - evaluator.py - 2024-10-28 19:22:33,985 - Epoch: 15 Train acc: 75.9309090909091 Val acc: 17.419999999999998 Test acc17.130000000000003; Train loss: 0.005253951759771868 Val loss: 0.09967994995117188
+INFO - dataset_loader.py - 2024-10-28 19:23:03,824 - delta is reset as 2.07404851125286e-06
+INFO - evaluator.py - 2024-10-28 22:06:33,597 - The FID of synthetic images is 110.00590226186807
+INFO - evaluator.py - 2024-10-28 22:06:33,602 - The Inception Score of synthetic images is 3.1287941932678223
+INFO - evaluator.py - 2024-10-28 22:06:33,602 - The Precision and Recall of synthetic images is 0.5965238213539124 and 0.03596000000834465
+INFO - evaluator.py - 2024-10-28 22:06:33,602 - The FLD of synthetic images is 19.469380378723145
+INFO - evaluator.py - 2024-10-28 22:06:33,602 - The ImageReward of synthetic images is -2.214698274219793
+INFO - dataset_loader.py - 2024-10-28 22:46:40,177 - delta is reset as 2.07404851125286e-06
+INFO - dataset_loader.py - 2024-10-29 01:42:25,242 - delta is reset as 1.8484667129285888e-06
+INFO - evaluator.py - 2024-10-29 02:35:25,718 - The FID of synthetic images is 109.95839653086716
+INFO - evaluator.py - 2024-10-29 02:35:25,751 - The Inception Score of synthetic images is 3.1288182735443115
+INFO - evaluator.py - 2024-10-29 02:35:25,751 - The Precision and Recall of synthetic images is 0.5966984033584595 and 0.036159999668598175
+INFO - evaluator.py - 2024-10-29 02:35:25,751 - The FLD of synthetic images is 19.213759899139404
+INFO - evaluator.py - 2024-10-29 02:35:25,751 - The ImageReward of synthetic images is -2.214698282242767
+INFO - dataset_loader.py - 2024-10-29 02:35:26,383 - delta is reset as 1.8484667129285888e-06
+INFO - evaluator.py - 2024-10-29 03:27:02,083 - The FID of synthetic images is 219.54836766661845
+INFO - evaluator.py - 2024-10-29 03:27:02,086 - The Inception Score of synthetic images is 1.7984269857406616
+INFO - evaluator.py - 2024-10-29 03:27:02,086 - The Precision and Recall of synthetic images is 0.6327812671661377 and 0.0003600000054575503
+INFO - evaluator.py - 2024-10-29 03:27:02,086 - The FLD of synthetic images is 27.920222282409668
+INFO - evaluator.py - 2024-10-29 03:27:02,086 - The ImageReward of synthetic images is -2.2739594591539354
+INFO - dataset_loader.py - 2024-10-29 03:27:02,840 - delta is reset as 1.8484667129285888e-06
+INFO - evaluator.py - 2024-10-29 04:18:40,193 - The FID of synthetic images is 201.61100378723972
+INFO - evaluator.py - 2024-10-29 04:18:40,221 - The Inception Score of synthetic images is 1.9011380672454834
+INFO - evaluator.py - 2024-10-29 04:18:40,221 - The Precision and Recall of synthetic images is 0.6231746077537537 and 0.0005200000014156103
+INFO - evaluator.py - 2024-10-29 04:18:40,221 - The FLD of synthetic images is 27.509820461273193
+INFO - evaluator.py - 2024-10-29 04:18:40,221 - The ImageReward of synthetic images is -2.2687564725081124
+INFO - dataset_loader.py - 2024-10-29 04:18:42,924 - delta is reset as 2.6201132658294697e-07
+INFO - evaluator.py - 2024-10-29 05:19:05,639 - The FID of synthetic images is 22.085653876120773
+INFO - evaluator.py - 2024-10-29 05:19:05,642 - The Inception Score of synthetic images is 1.7683465480804443
+INFO - evaluator.py - 2024-10-29 05:19:05,642 - The Precision and Recall of synthetic images is 0.7516825795173645 and 0.3393147587776184
+INFO - evaluator.py - 2024-10-29 05:19:05,642 - The FLD of synthetic images is -6.095540523529053
+INFO - evaluator.py - 2024-10-29 05:19:05,642 - The ImageReward of synthetic images is -1.793093251128755
+INFO - dataset_loader.py - 2024-10-29 05:19:06,164 - delta is reset as 1.5148623360286113e-06
+INFO - evaluator.py - 2024-10-29 06:19:12,182 - The FID of synthetic images is 36.55868340206811
+INFO - evaluator.py - 2024-10-29 06:19:12,189 - The Inception Score of synthetic images is 1.9821124076843262
+INFO - evaluator.py - 2024-10-29 06:19:12,189 - The Precision and Recall of synthetic images is 0.19395314157009125 and 0.42188334465026855
+INFO - evaluator.py - 2024-10-29 06:19:12,189 - The FLD of synthetic images is 16.948330402374268
+INFO - evaluator.py - 2024-10-29 06:19:12,189 - The ImageReward of synthetic images is -2.130454104746692
+INFO - dataset_loader.py - 2024-10-29 06:19:12,548 - delta is reset as 1.8484667129285888e-06
+INFO - evaluator.py - 2024-10-29 07:17:08,735 - The FID of synthetic images is 103.17130225064335
+INFO - evaluator.py - 2024-10-29 07:17:08,757 - The Inception Score of synthetic images is 3.3248043060302734
+INFO - evaluator.py - 2024-10-29 07:17:08,757 - The Precision and Recall of synthetic images is 0.5925872921943665 and 0.05226000025868416
+INFO - evaluator.py - 2024-10-29 07:17:08,757 - The FLD of synthetic images is 18.80326271057129
+INFO - evaluator.py - 2024-10-29 07:17:08,757 - The ImageReward of synthetic images is -2.2046342791773026
+INFO - dataset_loader.py - 2024-10-29 07:17:09,384 - delta is reset as 1.5148623360286113e-06
+INFO - evaluator.py - 2024-10-29 08:12:19,400 - The FID of synthetic images is 36.16871462142183
+INFO - evaluator.py - 2024-10-29 08:12:19,442 - The Inception Score of synthetic images is 1.9785420894622803
+INFO - evaluator.py - 2024-10-29 08:12:19,442 - The Precision and Recall of synthetic images is 0.2151111215353012 and 0.38750001788139343
+INFO - evaluator.py - 2024-10-29 08:12:19,442 - The FLD of synthetic images is 16.76713228225708
+INFO - evaluator.py - 2024-10-29 08:12:19,442 - The ImageReward of synthetic images is -2.120978381105832
+INFO - dataset_loader.py - 2024-10-29 08:12:21,784 - delta is reset as 2.6201132658294697e-07
+INFO - evaluator.py - 2024-10-29 09:12:37,637 - The FID of synthetic images is 57.79238987775261
+INFO - evaluator.py - 2024-10-29 09:12:37,646 - The Inception Score of synthetic images is 1.4734785556793213
+INFO - evaluator.py - 2024-10-29 09:12:37,647 - The Precision and Recall of synthetic images is 0.6569206714630127 and 0.13006387650966644
+INFO - evaluator.py - 2024-10-29 09:12:37,647 - The FLD of synthetic images is -1.181638240814209
+INFO - evaluator.py - 2024-10-29 09:12:37,647 - The ImageReward of synthetic images is -2.0049813007896855
+INFO - dataset_loader.py - 2024-10-29 09:12:39,948 - delta is reset as 2.6201132658294697e-07
+INFO - evaluator.py - 2024-10-29 10:14:57,218 - The FID of synthetic images is 29.3289837710725
+INFO - evaluator.py - 2024-10-29 10:14:57,224 - The Inception Score of synthetic images is 1.652750849723816
+INFO - evaluator.py - 2024-10-29 10:14:57,224 - The Precision and Recall of synthetic images is 0.7476875185966492 and 0.285733163356781
+INFO - evaluator.py - 2024-10-29 10:14:57,224 - The FLD of synthetic images is -4.951715469360352
+INFO - evaluator.py - 2024-10-29 10:14:57,224 - The ImageReward of synthetic images is -1.871033944573719
+INFO - dataset_loader.py - 2024-10-29 10:14:57,630 - delta is reset as 1.5148623360286113e-06
+INFO - evaluator.py - 2024-10-29 11:06:17,358 - The FID of synthetic images is 5.286480673016143
+INFO - evaluator.py - 2024-10-29 11:06:17,363 - The Inception Score of synthetic images is 2.071159601211548
+INFO - evaluator.py - 2024-10-29 11:06:17,363 - The Precision and Recall of synthetic images is 0.6194375157356262 and 0.7204999923706055
+INFO - evaluator.py - 2024-10-29 11:06:17,364 - The FLD of synthetic images is 3.7299275398254395
+INFO - evaluator.py - 2024-10-29 11:06:17,364 - The ImageReward of synthetic images is -2.0137405606759713
+INFO - dataset_loader.py - 2024-10-29 11:06:17,775 - delta is reset as 4.329102935418938e-06
+INFO - evaluator.py - 2024-10-29 11:39:57,591 - The FID of synthetic images is 168.59217462930627
+INFO - evaluator.py - 2024-10-29 11:39:57,596 - The Inception Score of synthetic images is 1.6652277708053589
+INFO - evaluator.py - 2024-10-29 11:39:57,596 - The Precision and Recall of synthetic images is 0.6194375157356262 and 0.00952173862606287
+INFO - evaluator.py - 2024-10-29 11:39:57,596 - The FLD of synthetic images is 20.778346061706543
+INFO - evaluator.py - 2024-10-29 11:39:57,596 - The ImageReward of synthetic images is -1.5740511079076678
+INFO - dataset_loader.py - 2024-10-29 11:39:58,114 - delta is reset as 1.8484667129285888e-06
+INFO - evaluator.py - 2024-10-29 12:12:19,140 - The FID of synthetic images is 231.37436795903784
+INFO - evaluator.py - 2024-10-29 12:12:19,145 - The Inception Score of synthetic images is 1.7306236028671265
+INFO - evaluator.py - 2024-10-29 12:12:19,145 - The Precision and Recall of synthetic images is 0.7602222561836243 and 0.00043999997433274984
+INFO - evaluator.py - 2024-10-29 12:12:19,145 - The FLD of synthetic images is 23.48649501800537
+INFO - evaluator.py - 2024-10-29 12:12:19,146 - The ImageReward of synthetic images is -2.2615407764571054
+INFO - dataset_loader.py - 2024-10-29 12:12:19,367 - delta is reset as 4.329102935418938e-06
+INFO - evaluator.py - 2024-10-29 12:45:16,662 - The FID of synthetic images is 237.36948091544997
+INFO - evaluator.py - 2024-10-29 12:45:16,666 - The Inception Score of synthetic images is 1.2807329893112183
+INFO - evaluator.py - 2024-10-29 12:45:16,667 - The Precision and Recall of synthetic images is 0.5577656626701355 and 4.347825961303897e-05
+INFO - evaluator.py - 2024-10-29 12:45:16,667 - The FLD of synthetic images is 30.49933910369873
+INFO - evaluator.py - 2024-10-29 12:45:16,667 - The ImageReward of synthetic images is -1.8509714604625478
+INFO - dataset_loader.py - 2024-10-29 12:45:17,305 - delta is reset as 1.5148623360286113e-06
+INFO - evaluator.py - 2024-10-29 13:18:11,048 - The FID of synthetic images is 53.50594213505724
+INFO - evaluator.py - 2024-10-29 13:18:11,054 - The Inception Score of synthetic images is 3.4386539459228516
+INFO - evaluator.py - 2024-10-29 13:18:11,055 - The Precision and Recall of synthetic images is 0.26606249809265137 and 0.12056666612625122
+INFO - evaluator.py - 2024-10-29 13:18:11,055 - The FLD of synthetic images is 20.395588874816895
+INFO - evaluator.py - 2024-10-29 13:18:11,055 - The ImageReward of synthetic images is -1.8617446345779531
+INFO - dataset_loader.py - 2024-10-29 13:18:11,648 - delta is reset as 1.5148623360286113e-06
+INFO - evaluator.py - 2024-10-29 13:50:35,681 - The FID of synthetic images is 4.446889068230405
+INFO - evaluator.py - 2024-10-29 13:50:35,832 - The Inception Score of synthetic images is 2.0761497020721436
+INFO - evaluator.py - 2024-10-29 13:50:35,832 - The Precision and Recall of synthetic images is 0.6322698593139648 and 0.7390333414077759
+INFO - evaluator.py - 2024-10-29 13:50:35,833 - The FLD of synthetic images is 3.283095359802246
+INFO - evaluator.py - 2024-10-29 13:50:35,833 - The ImageReward of synthetic images is -2.0057078354216755
+INFO - dataset_loader.py - 2024-10-29 13:50:37,371 - delta is reset as 5.11965868690912e-07
+INFO - evaluator.py - 2024-10-29 14:31:49,267 - The FID of synthetic images is 28.848900967099837
+INFO - evaluator.py - 2024-10-29 14:31:49,353 - The Inception Score of synthetic images is 2.238304853439331
+INFO - evaluator.py - 2024-10-29 14:31:49,353 - The Precision and Recall of synthetic images is 0.6088594198226929 and 0.1520366072654724
+INFO - evaluator.py - 2024-10-29 14:31:49,354 - The FLD of synthetic images is nan
+INFO - evaluator.py - 2024-10-29 14:31:49,354 - The ImageReward of synthetic images is -1.3833920579410202
+INFO - dataset_loader.py - 2024-10-29 14:31:49,986 - delta is reset as 1.8484667129285888e-06
+INFO - dataset_loader.py - 2024-10-29 16:22:04,259 - delta is reset as 2.07404851125286e-06
+INFO - evaluator.py - 2024-10-29 16:58:22,362 - The FID of synthetic images is 110.1117061771098
+INFO - evaluator.py - 2024-10-29 16:58:22,377 - The Inception Score of synthetic images is 3.1287941932678223
+INFO - evaluator.py - 2024-10-29 16:58:22,377 - The Precision and Recall of synthetic images is 0.5965238213539124 and 0.03596000000834465
+INFO - evaluator.py - 2024-10-29 16:58:22,377 - The FLD of synthetic images is 19.336581230163574
+INFO - evaluator.py - 2024-10-29 16:58:22,377 - The ImageReward of synthetic images is -2.214698274219793
+INFO - dataset_loader.py - 2025-06-11 02:08:27,224 - train size: 145064 val size: 17706
+INFO - dataset_loader.py - 2025-06-11 02:08:27,225 - delta is reset as 5.800209926283058e-07
+INFO - evaluator.py - 2025-06-11 02:09:21,489 - The Precision and Recall of synthetic images is 0.0 and 0.0 at k = 2
+INFO - evaluator.py - 2025-06-11 02:09:32,950 - The Precision and Recall of synthetic images is 0.002111111069098115 and 0.0 at k = 7
+INFO - dataset_loader.py - 2025-06-11 04:16:30,241 - train size: 45000 val size: 5000
+INFO - dataset_loader.py - 2025-06-11 04:16:30,241 - delta is reset as 2.07404851125286e-06
+INFO - evaluator.py - 2025-06-11 04:17:09,350 - The Precision and Recall of synthetic images is 0.36769843101501465 and 0.01119999960064888 at k = 2
+INFO - evaluator.py - 2025-06-11 04:17:12,658 - The Precision and Recall of synthetic images is 0.7365079522132874 and 0.05077999830245972 at k = 7
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/checkpoints/checkpoint_100000.pth b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/checkpoints/checkpoint_100000.pth
new file mode 100644
index 0000000000000000000000000000000000000000..8674230aadfe083e58846b529024d69525cc914e
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/checkpoints/checkpoint_100000.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51bc8c40fb082d7fa5cf772ce75f55421519fb763d8a880d2ffa99aca8f6577e
+size 61695625
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/checkpoints/final_checkpoint.pth b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/checkpoints/final_checkpoint.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c32c9e396a0c121f92869fdc2451823caf239742
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/checkpoints/final_checkpoint.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69df4a03da5ff02bb5fd8ca00aa7648523f637a8f6449f29f5ae92520b620d07
+size 61694566
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/checkpoints/snapshot_checkpoint.pth b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/checkpoints/snapshot_checkpoint.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c33d5ba95fc5c4864d75a63f416d96f367830498
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/checkpoints/snapshot_checkpoint.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:907c6806afde9dee598d60ac442ee5e9d4a7ff630893c39e2131138e308f15e0
+size 61697743
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_10000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_10000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..be27f5f483c845aa554f7d5663e159c2a71ce587
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_10000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:448b7e761e2e15f6c2e854ffe7fba19ae81b76eacd7b8c32c4802e48ce99fb94
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_10000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_10000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..9cc1ccf9736979b37d849534691b2d0355b155ed
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_10000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34a7a69c48a653ade599102f15766a1f59c179eb034659ae51fc3092da3e7eb0
+size 370365
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_100000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_100000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..7952d1446a670e3cbaae2a827f97bcbe205b76e6
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_100000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c0c6616e7c0a87618359731e7d62b61d16a7b17a1a046157186fef33a3baba4
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_100000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_100000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..72f928d21d5fe291716c22d25dd729218316f291
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_100000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8058e19aa3665aea6e8c28f1f6182ca35da725c111dd65742ea600299e63910
+size 330783
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_102000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_102000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..3403666d8368e577ab6c5af99d97fc869a3d2a28
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_102000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbbbfa3d5e0ce13e1617b8be7bf94fcebcc12b78767315f021c0c6d5986664fe
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_102000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_102000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..5375721b44b9e9b05c6935c1082d1adc5d016b8e
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_102000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b16beec914dfe524fbba4ae8d467e702707a1adf48b103370eba4840ea00151
+size 332319
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_104000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_104000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..e427118058709ec234c3a07367465a8b2c9a74f8
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_104000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5727a15aeb97265a8e962fcc36534de4fc350d1152a8da992ca95bc94a748519
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_104000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_104000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..d19f60c12065151007874369a239c520fad4bcfc
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_104000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3aae41abc07bf4ef2f285c861ba00e6a5e60bd3463f125f773a1a1677cd8af9
+size 331298
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_12000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_12000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..f99fb0a69cab2b55b3053c7829789422535a6537
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_12000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c8ed7255872480ef2bd2eb6886a7ad910eaa6ea8ff98627786d93fd3db9bbc4
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_12000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_12000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..539da73b6f57438df76903720fbc5b3936208bc5
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_12000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae707eaf418eb685c1b7b9bde7e8b06684f966a524bd2df13e01be4d7d940238
+size 366621
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_14000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_14000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..9c76d1358d05c2de5046935e3cc09f2504a87949
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_14000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d431229f92ccd6005932df8068f675e2fcc5c614179083d84b78926cb44491ef
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_14000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_14000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..d0894e0721da6dfcd600c8c9e522587a3ac4c4ed
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_14000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed9149ea9866cc3f050d617e2c83d188fa3344600f0fe1568c037648aa0dac1b
+size 362687
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_16000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_16000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..62ec742a1d08962a9a79f215275e902e2060c8a8
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_16000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc1f9d356d193df7b6c4b06a74bf68a15bc135df16a1e2a369d74d8e331cc603
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_16000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_16000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..a2428ab12db1ab0d9beef95dd661db165ce9511b
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_16000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:722a61b4dfe40dfa24315c18fd6190e0fee1bfa98ef9637a58f711db47879c33
+size 357719
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_18000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_18000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..0d17273ed0e72681a6cdafdf5cfc3a82183d80ef
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_18000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:610cc9268d96c3099fc7b9c2f95978c8f57da29930b1dafae173383eac5abb95
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_18000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_18000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..cb0c3222784314b3629334d5ed85139d6483ec95
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_18000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:858f56cb19a53d0b809187b9ebe58d393c5e3d2ca4d421f25e8d9b9dd96a17b7
+size 355913
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_2000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_2000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..710bc719ded2223008d8673b31fb31a5b96a2e16
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_2000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e87a5da617e06dfae507c75d7c2564aa44362ecb4be1c1c00ec45da0d6ebecc
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_2000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_2000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..715ac86c8f252c2d5e39cdc9323dad16811ccd1d
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_2000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3e38b906a28a753df8211ff8dcfa1e4e1df4c758a7035afd383c606aa52de11
+size 482840
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_20000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_20000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..11c700d6d5318f9eb5cfceaed04312bc75921937
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_20000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f7bc034ec13a1bc5086833d89db5100b346503b517191b9aa1f5d900d32b79d
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_20000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_20000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..6bd91c6f1bf0cb6d791616e0b3b7f09d98b6453a
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_20000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2081a83d5e06ef2f80587094af1d224f6107d2a73e464406bc91c278c141eca3
+size 353505
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_22000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_22000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..0984661d4db95b01e6aa66343ee69c8a8187d972
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_22000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0418e7a9b9dac07cbd7458b78ab5872c662664e4f906af8b5e24bbc87e6f2516
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_22000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_22000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..08fbabd156c6c6b3002b8b08c59f93ec2027f8f5
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_22000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a4225f3e96117396aa8866318a6503f1d97369abced2d31c9ac25037673d402
+size 351751
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_24000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_24000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..03436df2708a4c0156db584aac5fe404f224cbb3
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_24000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2240ce998f18d20411592de880c4619bc2c632c7621bcec14166de4abb683ff
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_24000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_24000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..7441b5919e4791a48750acfeee3836f65926ffa5
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_24000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bf40e81b4c35889fc3869c2d2a340f5d2391e1efba48c6dbae582380dee3e42
+size 351608
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_26000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_26000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..d289a5c4b062bf74fc091d96fc8540b074d559f3
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_26000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c1649c3a400b887780d2287f59dfa3cf2873b56d88b6a7a31229a009b93dc8d
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_26000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_26000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..06c904951c996a690f7bb9f7d09d22437ff84a22
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_26000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec4d4079bb19c74338c879b8e22855e144eb8f3a4776100e2760ad79aabbba2d
+size 349163
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_28000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_28000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..aa52a83c46e7083fc22c58500767afef9e777bcd
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_28000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c1964b5f45220c593b679e8c84652d766917836d2d5a33844df8cb049762a91
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_28000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_28000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..6b24a9906b0a64b6c64274ac4b7748d964ef893c
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_28000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f085169dfa40f228bdb84862ab6cd07bb739ba023e1f5e9b77f768ba51a54461
+size 347399
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_30000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_30000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..df8c4799badddb9e183d182682bf6f11da27983e
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_30000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e35de47c0c275886c8a791860fc60b97d2b2ca37b68078114865593c2e74f298
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_30000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_30000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..bb811a5a99f5033057443f921c9da951d0147594
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_30000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f5689a28f8222e688ac5bf7544779946c58fe6b3c1c8cd0e83f782144835e3d
+size 346313
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_32000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_32000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..3475b17c6708928cb9c4c679d62dd8b813a4d65e
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_32000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4fc757d04b32d12053ef75846a43b72f6843c8fb0f80925a96502eb2504d38c
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_32000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_32000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..b3d6fad999a8fdb7941e767aef76313f06d49f3a
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_32000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56df352d954411771d5757af9847edbe6df27922aa8c8de573e55df1c9b69878
+size 346550
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_34000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_34000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..ddc453f4f0bc14a55a3c1793fc01e0418b611d96
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_34000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b13925c5aaf60a16c581da2b7929254cf0cefa5f67a9f36afc9bcdedf5462a5d
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_34000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_34000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..404e2563ee4f31ac175d52bd68fc1b66ea1e572d
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_34000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92092cfe9f56ad2c4ff963c7cf5125f3ddbfcc3c41e97a8a2a66e60858a7b477
+size 346176
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_36000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_36000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..faf39088350df15ae215c8de93595f192dbf866c
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_36000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82fedb37e49b67bd17bf50a8667d1dcea16b4b814041e98ec82723cd051f0df5
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_36000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_36000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..4d3bcf168ec9656c4faf69c891434dac604e3c3c
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_36000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f63b427b11e58bb8f558088173bb4d0f46eb82b1c34981bb20989696fab84096
+size 346764
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_38000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_38000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..eaea651582ea9e5ff345ce493013eda594de0dff
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_38000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87817a16c87361e8af1553384749352a74959115559bf736bb81bb8ffd1ed5dc
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_38000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_38000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..bc2f46ee91f9234e44d234599c26057b75e5ba89
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_38000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d0ce7116d10312209316efb6b47defacc0e49fdcbdc8692aac78639d82e889a
+size 345303
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_4000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_4000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..e8a3dfc018c05c081e7a7a149bff62dc92a135d5
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_4000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f1d5af34381cfc951709d4b63954e4c8f1adec428193d5fcdd9c55e4eb63fbf
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_4000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_4000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..4b969409f91112ff83a7c897e924969c22ad7404
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_4000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b65982128056a24241c9235257980e4b2f7fd5d753fcab76ed17f9ac89124027
+size 420649
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_40000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_40000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..17648de56694427eb729e06af4f525b535e6deaa
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_40000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:564b91e54358276b5906951a5a17eac5301ac8d910b3a298b4539ae3180a680e
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_40000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_40000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..35681e11afbbd7f6bc553f0b0a3ea587091af088
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_40000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b81d53af7f48f9ce0555a35355eae68b475bb8ddc36b545481d96671b95942c
+size 344668
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_42000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_42000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..8dfce76bed1fc8f32e5c254ef6766c7124ca1e77
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_42000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:701cc116b3ed4e1140dbdac70a9c55e10b2d08ccf7190c697d12169042511b96
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_42000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_42000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..7f9720bce830c84c8964d7bed57b2c144294274a
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_42000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f1a551e67660f1e3a76cc6034d56712481603f429982eb8450c56a4260738af
+size 344228
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_44000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_44000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..20d635a1aa25e32fb7a9d559a5551aac7c66a063
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_44000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c33f9e77c36bc7cf3e54e186b1620546619152a6fdd1a4b3306e1069e2e8a01
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_44000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_44000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..ba8b21751e704cf70be320aab4057deb7891f8f7
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_44000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d10ecb131dc61160abaeaab75a42a82e2d2236ccad0bab733d7bbc29706b071
+size 343265
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_46000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_46000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..e43c13369554c05a4e6afb85b8c9b70c60662f25
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_46000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20097c065c8905a6a3034293c403e722ba503ad35f11e99c0479944b18569c10
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_46000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_46000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..ee313cbf53017333c43753719705c1cfbebf10ab
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_46000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9931fd0c41a18f5e7efee823bb0e2a459da742ecd4bb39f80403f366d8926a6c
+size 341193
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_48000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_48000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..b6b2b903e4137ac122eb30cd1ed383ef8c9d6c85
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_48000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01da2087d4f8e70feb3f582835bfeca7e1caa4592b663eb5ff17f5ad8a9838ba
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_48000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_48000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..a4c49c78c1d704bf9b7af8a181cfd2f4e62709d4
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_48000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8119284dcbe941ebd4feda20a5250a4efdf74db497b3be7d1300a1c41bd31037
+size 343469
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_50000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_50000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..4b7e70bcfb08a82d863f19be9e5457d4df8e7d77
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_50000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2347a0b83ae9379c1aef12e8ea7faedee604b52009e23ec7423a666a329ec67c
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_50000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_50000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..e30f5ef31b0493e002762e5e7f1c0c971f4de054
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_50000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b8c56da94f9cff2478e2f66758b5a38bebb60dea5f21136f277d62953f56e4d
+size 341525
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_52000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_52000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..afccfa52b951f65cf773fccf2117651cc3ad6796
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_52000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a3a2f1679cfe32e3cef9146570ebd2ddfff0cc2a6767e4571939446018a9774
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_52000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_52000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..d0a823515e5c37c186381bc6fac140483d2f4b58
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_52000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a2eba9629869649da5d626c0d289c9990b5d6e8fd4c0ca0898380341fdffcf1
+size 338999
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_54000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_54000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..93760e57877ee4b408ee1c3ac141985fe7ff5a1d
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_54000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3742ee1d8f33c9aea6c1f703e8fb9d6eed8aab3c1033451732d84ca71349725a
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_54000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_54000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..7c9695eddf68ffb1999757c179d58b6d3828280e
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_54000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a99d66403953a4c3549bbdaa1282dfeedec06a1245f9d909375b9711a4f2b32
+size 341209
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_56000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_56000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..8f926aee3e5e0e2d71c015e9d83b24efe08f447a
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_56000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09e0a9cdc43382c966c021a83728b92f2f7a33e86b66e2975ea97932e429f251
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_56000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_56000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..e7d35c857eb2d52a0f23232df153d58f752bac82
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_56000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceb349a59d468e8d8f1fe175c1dd8097e08ae9487505c181210dbb3020ab0039
+size 337061
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_58000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_58000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..c354ed6ac9ff243eb720894dd1012582df6d97e7
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_58000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc5476b6106c5beea4c4197d4dd208061d5c985ad738b9e2f6c307e3f03cf10f
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_58000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_58000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..8d34fdda4e0d660eb913bbff6ed1f5e2f2a94030
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_58000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:175c1cc85dc3fe29f645c16d7dd035e1a1391ecfaa1b4cd258a245f3bcc03347
+size 339769
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_6000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_6000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..eae7fe88e8cf0c2eb97383e2ba75fa045d2ab036
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_6000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86220c9b6fc39a246de7eec664f72545b1cc2b35e95adb44c876f0addc900c96
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_6000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_6000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..8ac8805530b485a225b07783e741aee6e433c8f3
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_6000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94d97b5e145a2ea5390b77761e4ce14a05a040bf70cf254b0cebb0b2fad45e23
+size 383728
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_60000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_60000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..67d3b5422397850358730cf9a3d566501e3c3d43
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_60000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88d6c0fa0bbb559dad0ce57a34d84f6bf3ed6a816b50dda51c51cedf58fc3045
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_60000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_60000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..93dfbe848cac42712ea29dc6a52736d1e7fd5bc5
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_60000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4e501cce6c1a7e5775f2480afea9ca158fab1558a0e6390b419fea55950802e
+size 335478
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_62000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_62000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..fee43250be16d80161ce64e894297fb1c8133c05
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_62000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7d1514d8827bedf19ac9c59055c6da1857bc06156726849526b054c70eead0
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_62000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_62000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..6ee541830c018774b9be46f820b9fbb4e02a19ed
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_62000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80b6009faa5c51cfd2e11bf6c29dd72948d3b939068a204a21e3d97a51ca7cad
+size 337249
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_64000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_64000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..3cad9a390300358d66da51827fbab5951215bf5d
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_64000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6cae54b7f897f5b117673fb5aa16ab3ca28fcb9b074b2a5ff46f195018ebea1
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_64000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_64000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..afc4e2c6e1c4d43d0c32ff4e901a5628cc394f6b
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_64000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73186b469c176c90175b4724dbef00b007af643270ffff159f7074f3b04d7cf5
+size 337372
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_66000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_66000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..7af503a1c06cd4eec577c3b8302f0cbe983e0c87
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_66000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b1b1fe1c9bbfc38137f39227ae1bbb2d2d42168023232ac9fe7ada67b8bb2fa
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_66000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_66000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..605150efafeea4696b9b70475c8059949653f0ba
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_66000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d9968c0f047a0422527ceb5437835514daef6988b48ed93055289fb4455c922
+size 340632
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_68000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_68000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..d09bb001ac5a2be2ba9466f9a774ac78fe4dce94
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_68000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7f1feb9cbd54a212ce0b4544bc9ff0a97e25d527eaa025a8608a408f8ead71c
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_68000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_68000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..fc3ae6073c60b33fceb6006721e5c719b0f681b5
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_68000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9971019f720ad399730cd9d7d7d44274eb152b8a970da047898e72b14603e10
+size 338027
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_70000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_70000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..d41f03cfa7ea0871925d751a93e3e95e60256b6a
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_70000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93d18bd9b4897608b6bf1d009e5972bcf6c0e8a2c471df0ee49a5ee5e1af3b43
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_70000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_70000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..8ecd97dc24760d74c54ada5859f57712706cfbca
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_70000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7361c1161b2759c04dc94af4967a9a038052bfaaa182f1c83c45cde3996ea79f
+size 334491
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_72000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_72000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..ec06298ebb9fb3ae71b5111c41c70380cc14945f
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_72000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90df6311e907f26b79eb6af0a4a54b0c8cce215f86646744c84e35663138d508
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_72000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_72000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..2cd4b05e23f80d60ae688b95193d64bff82eff39
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_72000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dd7a9ca5a8f8877eea4241854913cc0e4308cb4e26b03b1e4a65c85c5622bdb
+size 339141
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_74000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_74000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..9399ef472139e21c96d54316b84b2776605813e4
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_74000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6112ee2f5bb96d4d7e94b41f29aa6cee94f9a1d8c040b22aca605bfc0757811
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_74000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_74000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..2cd22817589b2dee56da5df3a76f6be609f58df1
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_74000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0f4af41335e281bdd4f1f771d7083646236575d13f1bd616421201aaa72c77e
+size 332895
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_76000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_76000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..679e3dccad3f61cfef71c44a6cfbdd5a18a155b0
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_76000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e81f62945635f0ac630264cf69544cfe08254e07b0bf2d74218060ee5b2d8c5
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_76000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_76000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..8fa515a7987d6617d984a4f7311befa3ea605428
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_76000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a22f92f5c5c276de682adff1bb9fc61c64a22ff71d4579f40e2b05b0f04bcfa
+size 335810
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_78000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_78000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..49fb37e56aa644af8903216e3b419844985acf6c
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_78000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c78c432437e181e52b62049e778bb44d000b3c6cf4f8ae9065d55146f8109556
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_78000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_78000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..128150d76d6f3bfe38b716689e3eae6e1fd0297f
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_78000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b1fcc29b3de8099e677cabe334da21114f18c7603fa905026b0c949d58a55fd
+size 334291
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_8000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_8000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..f04d6d734801041e57a823b6d722d1df9bb259a7
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_8000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebb9562360297d049adf97790c4e26352a9e315bbeb54f5af84e0fb298d2dd2e
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_8000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_8000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..e6fcb2983383b1423e990c14202e10fcf44f01f2
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_8000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37572bdf7d32186e6abfc88eb52da9e4b9bc48cb66988326fdde2dd6c4e47197
+size 374600
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_80000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_80000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..974ba179f2f9d9786facaba0c26d6c87a4d20c4f
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_80000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6ef57ac04374db3a9b93bcebdb4bdbff6a60aeabdb02c1e2b8b857bd06783c3
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_80000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_80000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..cb89baced1f72f6b6158f8b9bf359fa62eb9e31a
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_80000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf2b1ded9a2a7e74ec0cbb3ae71d426ffe91ee4992a731f11ee82d62c044282e
+size 335728
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_82000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_82000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..40b0805b13d549b285866a6736b092d4ac330867
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_82000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7cdba59756df5c3e9d6f264658abff56eca42b19fe331cae37cc8305155a0d0
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_82000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_82000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..84a5d78a9888b161a8b991f77688c49dc9d1e1fc
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_82000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df22d42a991a9b259912c4b04429b1bb49b51d31bd2ace8b27c5053075b79da5
+size 333558
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_84000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_84000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..cf8f7fc0af32928f2f7da6eba11eaf502a0ea3f7
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_84000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb848992f0d649661c7c62e824475499ec97c3973fa5311f8766306dd90cb96c
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_84000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_84000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..4a93ee917301327556b3f97b2d24494d59e885c9
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_84000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0364f0fff02098e984d4d096638c50b98c7b732c5809f4648d4f0f6cf00b892f
+size 335221
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_86000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_86000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..f5dcaaaf1b0ddf6c5e98e75846ff4504fe47058d
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_86000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00447ca03fc0690b7421c1a5f08a9a9d21793d7f37e649ba9db3bbedd8b510be
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_86000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_86000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..c1748a0016d9182f4b642c23ce8a3ec84b1b3c51
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_86000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:572a0d3f9d35e646c6248b24ef394030b94360ac04f8baea81dbf6b8c4a0a3aa
+size 333986
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_88000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_88000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..95bfa1c0423c62fa4886759b76263c6d984b53cd
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_88000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6aa1ea6610f5f1ac7bdcca63acd4a0e9aec570a62da1a56b7b3a09e162bc556
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_88000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_88000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..5b29c4935e15350148a9ebe216053481544947e9
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_88000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e746514b22e46701e143113ddfb1fe17b528219ddd931ab0b95854b042484dea
+size 336384
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_90000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_90000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..719126d3702b14fe49a75dedfa515a466524d14e
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_90000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:206d5fe1ceb9fb2e600d07ac8ab73c5c1beaf13c8c2cfbeb154df08172580263
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_90000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_90000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..e549402648f6066571f14d859830342b4e6a565a
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_90000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:812e4fdc1949ab9cb1e75d3905a055bea6474c059d84d05ad86039ece6bb27ad
+size 335799
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_92000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_92000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..1981d5777f6c70b865d621636754a5f7b7f669cb
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_92000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d07fb0d69042f9813a94705e67082aeabfc110974c8fff35f5c55b2327810ba7
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_92000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_92000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..c5a432f8f71a03ba2bd93bce350ec5a3584535ad
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_92000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b796e0d56750e3076af41d40a00ee11aca5807e14b90090a0e58a6e97a716aa8
+size 333601
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_94000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_94000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..a8e95636c2086327b0bbccaf3f89225173d945c2
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_94000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5622ec4b7292e1f925618b8515f119999036e0f2f7236c4f8f9bf8c2d0bbe24e
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_94000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_94000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..e8be7f1a49a26a776c997745ff3ab1fb27a8ff33
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_94000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2113d124ded83862686f41f501f13adb351e5a0fe1c48478196db88f57f9b6ce
+size 328779
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_96000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_96000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..0a38587180cbd8ece2d59ee4adbd06806396ae07
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_96000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e0c29481c62edd87fa365480255ca9e9ef149f5210d086dd676e53b69cfc31a
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_96000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_96000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..9ffea0d5f3dcc3bf25ed1d3d793196048577437e
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_96000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa6c7fabfdf468ffbfa88377f8644334837c15b81144f7916c4e8f3e473c04d2
+size 330505
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_98000/sample.npy b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_98000/sample.npy
new file mode 100644
index 0000000000000000000000000000000000000000..4974ce6534c73e5cc6b60a8518a00ddbffa6fff1
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_98000/sample.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2b2c5bce6e6fb42846c841fec0ced5a6c7fd4e48f17cd788b93cfe820770485
+size 983168
diff --git a/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_98000/sample.png b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_98000/sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..d5e761f4ac0ec4bcaea272a3527e8a3e99724c52
--- /dev/null
+++ b/dpdm/cifar10_32_eps10.0trainval-2024-10-24-01-44-41/train/samples/iter_98000/sample.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46257ba0c874b6b93783dfaa61c4b39c88cc62ca8dbf2ab03de39e995867a23b
+size 331534