#######################################################################
Please cite the following paper when using nnU-Net:
Isensee, F., Jaeger, P. F., Kohl, S. A., Petersen, J., & Maier-Hein, K. H. (2021). nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nature methods, 18(2), 203-211.
#######################################################################
 

This is the configuration used by this training:
Configuration name: 3d_fullres
 {'data_identifier': 'nnUNetPlans_3d_fullres', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 2, 'patch_size': [160, 128, 112], 'median_image_size_in_voxels': [645.0, 512.0, 512.0], 'spacing': [1.0, 1.0, 1.0], 'normalization_schemes': ['CTNormalization'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.PlainConvUNet', 'arch_kwargs': {'n_stages': 6, 'features_per_stage': [32, 64, 128, 256, 320, 320], 'conv_op': 'torch.nn.modules.conv.Conv3d', 'kernel_sizes': [[3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3]], 'strides': [[1, 1, 1], [2, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 1]], 'n_conv_per_stage': [2, 2, 2, 2, 2, 2], 'n_conv_per_stage_decoder': [2, 2, 2, 2, 2], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm3d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}, 'deep_supervision': True}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True} 
 
These are the global plan.json settings:
 {'dataset_name': 'Dataset900_JSSJ', 'plans_name': 'nnUNetPlans', 'original_median_spacing_after_transp': [1.0, 1.0, 1.0], 'original_median_shape_after_transp': [712, 512, 512], 'image_reader_writer': 'SimpleITKIO', 'transpose_forward': [0, 1, 2], 'transpose_backward': [0, 1, 2], 'experiment_planner_used': 'ExperimentPlanner', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 773.0, 'mean': -60.342926025390625, 'median': 7.0, 'min': -1148.0, 'percentile_00_5': -577.0, 'percentile_99_5': 185.0, 'std': 172.59446716308594}}} 
 
2025-05-15 10:56:33.151007: unpacking dataset... 
2025-05-15 10:57:35.034042: unpacking done... 
2025-05-15 10:57:35.044076: do_dummy_2d_data_aug: False 
2025-05-15 10:57:35.294728: Unable to plot network architecture: 
2025-05-15 10:57:35.301704: No module named 'hiddenlayer' 
2025-05-15 10:57:35.323645:  
2025-05-15 10:57:35.330626: Epoch 0 
2025-05-15 10:57:35.335613: Current learning rate: 0.01 
2025-05-15 10:59:40.773545: train_loss -0.1764 
2025-05-15 10:59:40.790212: val_loss -0.3849 
2025-05-15 10:59:40.798192: Pseudo dice [0.5847] 
2025-05-15 10:59:40.804681: Epoch time: 125.45 s 
2025-05-15 10:59:40.811667: Yayy! New best EMA pseudo Dice: 0.5847 
2025-05-15 10:59:42.031185:  
2025-05-15 10:59:42.038264: Epoch 1 
2025-05-15 10:59:42.042975: Current learning rate: 0.00999 
2025-05-15 11:01:31.299190: train_loss -0.3909 
2025-05-15 11:01:31.308670: val_loss -0.4573 
2025-05-15 11:01:31.315652: Pseudo dice [0.6245] 
2025-05-15 11:01:31.323737: Epoch time: 109.27 s 
2025-05-15 11:01:31.330719: Yayy! New best EMA pseudo Dice: 0.5886 
2025-05-15 11:01:32.643067:  
2025-05-15 11:01:32.650561: Epoch 2 
2025-05-15 11:01:32.657050: Current learning rate: 0.00998 
2025-05-15 11:03:58.159324: train_loss -0.4607 
2025-05-15 11:03:58.168301: val_loss -0.5253 
2025-05-15 11:03:58.176789: Pseudo dice [0.6725] 
2025-05-15 11:03:58.183764: Epoch time: 145.52 s 
2025-05-15 11:03:58.191743: Yayy! New best EMA pseudo Dice: 0.597 
2025-05-15 11:03:59.608382:  
2025-05-15 11:03:59.616052: Epoch 3 
2025-05-15 11:03:59.624475: Current learning rate: 0.00997 
2025-05-15 11:06:13.815822: train_loss -0.5218 
2025-05-15 11:06:13.827178: val_loss -0.4988 
2025-05-15 11:06:13.835157: Pseudo dice [0.6656] 
2025-05-15 11:06:13.842140: Epoch time: 134.21 s 
2025-05-15 11:06:13.848654: Yayy! New best EMA pseudo Dice: 0.6039 
2025-05-15 11:06:15.243291:  
2025-05-15 11:06:15.250775: Epoch 4 
2025-05-15 11:06:15.255762: Current learning rate: 0.00996 
2025-05-15 11:08:08.438738: train_loss -0.5438 
2025-05-15 11:08:08.448238: val_loss -0.591 
2025-05-15 11:08:08.457724: Pseudo dice [0.7163] 
2025-05-15 11:08:08.466278: Epoch time: 113.2 s 
2025-05-15 11:08:08.473263: Yayy! New best EMA pseudo Dice: 0.6151 
2025-05-15 11:08:09.958231:  
2025-05-15 11:08:09.966209: Epoch 5 
2025-05-15 11:08:09.971252: Current learning rate: 0.00995 
2025-05-15 11:10:03.696643: train_loss -0.5733 
2025-05-15 11:10:03.705620: val_loss -0.5735 
2025-05-15 11:10:03.715619: Pseudo dice [0.673] 
2025-05-15 11:10:03.725603: Epoch time: 113.74 s 
2025-05-15 11:10:03.732584: Yayy! New best EMA pseudo Dice: 0.6209 
2025-05-15 11:10:05.079017:  
2025-05-15 11:10:05.087014: Epoch 6 
2025-05-15 11:10:05.092999: Current learning rate: 0.00995 
2025-05-15 11:11:58.580672: train_loss -0.5943 
2025-05-15 11:11:58.591664: val_loss -0.652 
2025-05-15 11:11:58.602165: Pseudo dice [0.7698] 
2025-05-15 11:11:58.611134: Epoch time: 113.5 s 
2025-05-15 11:11:58.619112: Yayy! New best EMA pseudo Dice: 0.6358 
2025-05-15 11:11:59.978447:  
2025-05-15 11:11:59.985982: Epoch 7 
2025-05-15 11:11:59.991965: Current learning rate: 0.00994 
2025-05-15 11:13:50.317441: train_loss -0.6366 
2025-05-15 11:13:50.325420: val_loss -0.688 
2025-05-15 11:13:50.334396: Pseudo dice [0.7882] 
2025-05-15 11:13:50.343791: Epoch time: 110.34 s 
2025-05-15 11:13:50.350771: Yayy! New best EMA pseudo Dice: 0.651 
2025-05-15 11:13:51.700287:  
2025-05-15 11:13:51.708257: Epoch 8 
2025-05-15 11:13:51.714414: Current learning rate: 0.00993 
2025-05-15 11:15:41.583841: train_loss -0.6222 
2025-05-15 11:15:41.598308: val_loss -0.6979 
2025-05-15 11:15:41.607284: Pseudo dice [0.7966] 
2025-05-15 11:15:41.614772: Epoch time: 109.88 s 
2025-05-15 11:15:41.622751: Yayy! New best EMA pseudo Dice: 0.6656 
2025-05-15 11:15:43.056027:  
2025-05-15 11:15:43.064064: Epoch 9 
2025-05-15 11:15:43.071015: Current learning rate: 0.00992 
2025-05-15 11:17:34.184944: train_loss -0.6457 
2025-05-15 11:17:34.195421: val_loss -0.6859 
2025-05-15 11:17:34.202404: Pseudo dice [0.7917] 
2025-05-15 11:17:34.212670: Epoch time: 111.13 s 
2025-05-15 11:17:34.221645: Yayy! New best EMA pseudo Dice: 0.6782 
2025-05-15 11:17:35.530009:  
2025-05-15 11:17:35.537966: Epoch 10 
2025-05-15 11:17:35.543950: Current learning rate: 0.00991 
2025-05-15 11:19:29.420162: train_loss -0.6744 
2025-05-15 11:19:29.432204: val_loss -0.6925 
2025-05-15 11:19:29.444495: Pseudo dice [0.794] 
2025-05-15 11:19:29.455291: Epoch time: 113.89 s 
2025-05-15 11:19:29.464384: Yayy! New best EMA pseudo Dice: 0.6898 
2025-05-15 11:19:30.916374:  
2025-05-15 11:19:30.926347: Epoch 11 
2025-05-15 11:19:30.934843: Current learning rate: 0.0099 
2025-05-15 11:21:23.383372: train_loss -0.6678 
2025-05-15 11:21:23.402877: val_loss -0.6897 
2025-05-15 11:21:23.420342: Pseudo dice [0.7927] 
2025-05-15 11:21:23.429318: Epoch time: 112.47 s 
2025-05-15 11:21:23.439638: Yayy! New best EMA pseudo Dice: 0.7001 
2025-05-15 11:21:24.831881:  
2025-05-15 11:21:24.839576: Epoch 12 
2025-05-15 11:21:24.845560: Current learning rate: 0.00989 
2025-05-15 11:23:17.057097: train_loss -0.6804 
2025-05-15 11:23:17.066574: val_loss -0.728 
2025-05-15 11:23:17.074553: Pseudo dice [0.8103] 
2025-05-15 11:23:17.082530: Epoch time: 112.23 s 
2025-05-15 11:23:17.090019: Yayy! New best EMA pseudo Dice: 0.7111 
2025-05-15 11:23:18.575062:  
2025-05-15 11:23:18.583041: Epoch 13 
2025-05-15 11:23:18.589539: Current learning rate: 0.00988 
2025-05-15 11:25:10.749523: train_loss -0.689 
2025-05-15 11:25:10.760494: val_loss -0.7173 
2025-05-15 11:25:10.770468: Pseudo dice [0.8095] 
2025-05-15 11:25:10.777448: Epoch time: 112.18 s 
2025-05-15 11:25:10.787423: Yayy! New best EMA pseudo Dice: 0.7209 
2025-05-15 11:25:12.116093:  
2025-05-15 11:25:12.124043: Epoch 14 
2025-05-15 11:25:12.130058: Current learning rate: 0.00987 
2025-05-15 11:27:04.280175: train_loss -0.6937 
2025-05-15 11:27:04.296516: val_loss -0.7426 
2025-05-15 11:27:04.307487: Pseudo dice [0.8342] 
2025-05-15 11:27:04.319455: Epoch time: 112.17 s 
2025-05-15 11:27:04.332439: Yayy! New best EMA pseudo Dice: 0.7323 
2025-05-15 11:27:05.876898:  
2025-05-15 11:27:05.883852: Epoch 15 
2025-05-15 11:27:05.889676: Current learning rate: 0.00986 
2025-05-15 11:28:58.726149: train_loss -0.7091 
2025-05-15 11:28:58.737121: val_loss -0.7069 
2025-05-15 11:28:58.746462: Pseudo dice [0.8017] 
2025-05-15 11:28:58.754438: Epoch time: 112.85 s 
2025-05-15 11:28:58.764114: Yayy! New best EMA pseudo Dice: 0.7392 
2025-05-15 11:29:00.095935:  
2025-05-15 11:29:00.103015: Epoch 16 
2025-05-15 11:29:00.108710: Current learning rate: 0.00986 
2025-05-15 11:30:52.495654: train_loss -0.6971 
2025-05-15 11:30:52.505641: val_loss -0.7503 
2025-05-15 11:30:52.512621: Pseudo dice [0.834] 
2025-05-15 11:30:52.518605: Epoch time: 112.4 s 
2025-05-15 11:30:52.528087: Yayy! New best EMA pseudo Dice: 0.7487 
2025-05-15 11:30:54.057671:  
2025-05-15 11:30:54.064624: Epoch 17 
2025-05-15 11:30:54.069945: Current learning rate: 0.00985 
2025-05-15 11:32:45.594009: train_loss -0.7317 
2025-05-15 11:32:45.609198: val_loss -0.7804 
2025-05-15 11:32:45.618169: Pseudo dice [0.847] 
2025-05-15 11:32:45.628142: Epoch time: 111.54 s 
2025-05-15 11:32:45.638115: Yayy! New best EMA pseudo Dice: 0.7585 
2025-05-15 11:32:46.984829:  
2025-05-15 11:32:46.992837: Epoch 18 
2025-05-15 11:32:46.997823: Current learning rate: 0.00984 
2025-05-15 11:36:18.476434: train_loss -0.7468 
2025-05-15 11:36:18.487911: val_loss -0.7743 
2025-05-15 11:36:18.503382: Pseudo dice [0.8483] 
2025-05-15 11:36:18.519850: Epoch time: 211.49 s 
2025-05-15 11:36:18.539953: Yayy! New best EMA pseudo Dice: 0.7675 
2025-05-15 11:36:19.952520:  
2025-05-15 11:36:19.960472: Epoch 19 
2025-05-15 11:36:19.967007: Current learning rate: 0.00983 
2025-05-15 11:38:10.321927: train_loss -0.7271 
2025-05-15 11:38:10.333404: val_loss -0.7505 
2025-05-15 11:38:10.341382: Pseudo dice [0.8253] 
2025-05-15 11:38:10.347872: Epoch time: 110.37 s 
2025-05-15 11:38:10.356848: Yayy! New best EMA pseudo Dice: 0.7733 
2025-05-15 11:38:11.714756:  
2025-05-15 11:38:11.722321: Epoch 20 
2025-05-15 11:38:11.727336: Current learning rate: 0.00982 
2025-05-15 11:40:04.140931: train_loss -0.7363 
2025-05-15 11:40:04.149906: val_loss -0.7763 
2025-05-15 11:40:04.157407: Pseudo dice [0.8488] 
2025-05-15 11:40:04.166383: Epoch time: 112.43 s 
2025-05-15 11:40:04.174883: Yayy! New best EMA pseudo Dice: 0.7808 
2025-05-15 11:40:05.654091:  
2025-05-15 11:40:05.661103: Epoch 21 
2025-05-15 11:40:05.668125: Current learning rate: 0.00981 
2025-05-15 11:41:58.141444: train_loss -0.7374 
2025-05-15 11:41:58.152920: val_loss -0.7693 
2025-05-15 11:41:58.162907: Pseudo dice [0.8366] 
2025-05-15 11:41:58.170394: Epoch time: 112.49 s 
2025-05-15 11:41:58.179401: Yayy! New best EMA pseudo Dice: 0.7864 
2025-05-15 11:41:59.641995:  
2025-05-15 11:41:59.649973: Epoch 22 
2025-05-15 11:41:59.656983: Current learning rate: 0.0098 
2025-05-15 11:43:54.554973: train_loss -0.7373 
2025-05-15 11:43:54.563944: val_loss -0.763 
2025-05-15 11:43:54.572919: Pseudo dice [0.8372] 
2025-05-15 11:43:54.583449: Epoch time: 114.91 s 
2025-05-15 11:43:54.593423: Yayy! New best EMA pseudo Dice: 0.7915 
2025-05-15 11:43:56.002235:  
2025-05-15 11:43:56.009768: Epoch 23 
2025-05-15 11:43:56.016748: Current learning rate: 0.00979 
2025-05-15 11:45:47.362188: train_loss -0.7288 
2025-05-15 11:45:47.371169: val_loss -0.7542 
2025-05-15 11:45:47.383642: Pseudo dice [0.8349] 
2025-05-15 11:45:47.391628: Epoch time: 111.36 s 
2025-05-15 11:45:47.397611: Yayy! New best EMA pseudo Dice: 0.7958 
2025-05-15 11:45:48.703903:  
2025-05-15 11:45:48.711695: Epoch 24 
2025-05-15 11:45:48.717962: Current learning rate: 0.00978 
2025-05-15 11:47:38.144045: train_loss -0.7459 
2025-05-15 11:47:38.151055: val_loss -0.7737 
2025-05-15 11:47:38.158620: Pseudo dice [0.8372] 
2025-05-15 11:47:38.171141: Epoch time: 109.44 s 
2025-05-15 11:47:38.179211: Yayy! New best EMA pseudo Dice: 0.8 
2025-05-15 11:47:39.512760:  
2025-05-15 11:47:39.521778: Epoch 25 
2025-05-15 11:47:39.527048: Current learning rate: 0.00977 
2025-05-15 11:49:28.391229: train_loss -0.7681 
2025-05-15 11:49:28.401273: val_loss -0.7937 
2025-05-15 11:49:28.407315: Pseudo dice [0.8612] 
2025-05-15 11:49:28.411322: Epoch time: 108.87 s 
2025-05-15 11:49:28.421378: Yayy! New best EMA pseudo Dice: 0.8061 
2025-05-15 11:49:29.835007:  
2025-05-15 11:49:29.842569: Epoch 26 
2025-05-15 11:49:29.845088: Current learning rate: 0.00977 
2025-05-15 11:51:18.841382: train_loss -0.768 
2025-05-15 11:51:18.841382: val_loss -0.7582 
2025-05-15 11:51:18.861467: Pseudo dice [0.8313] 
2025-05-15 11:51:18.861467: Epoch time: 109.01 s 
2025-05-15 11:51:18.874516: Yayy! New best EMA pseudo Dice: 0.8086 
2025-05-15 11:51:20.167658:  
2025-05-15 11:51:20.167658: Epoch 27 
2025-05-15 11:51:20.167658: Current learning rate: 0.00976 
2025-05-15 11:53:08.975132: train_loss -0.7356 
2025-05-15 11:53:08.978140: val_loss -0.7734 
2025-05-15 11:53:08.991178: Pseudo dice [0.8497] 
2025-05-15 11:53:08.998213: Epoch time: 108.81 s 
2025-05-15 11:53:09.007244: Yayy! New best EMA pseudo Dice: 0.8127 
2025-05-15 11:53:10.299037:  
2025-05-15 11:53:10.307570: Epoch 28 
2025-05-15 11:53:10.312619: Current learning rate: 0.00975 
2025-05-15 11:54:59.204175: train_loss -0.7467 
2025-05-15 11:54:59.208189: val_loss -0.8022 
2025-05-15 11:54:59.224283: Pseudo dice [0.8668] 
2025-05-15 11:54:59.228297: Epoch time: 108.91 s 
2025-05-15 11:54:59.236331: Yayy! New best EMA pseudo Dice: 0.8181 
2025-05-15 11:55:00.662244:  
2025-05-15 11:55:00.668298: Epoch 29 
2025-05-15 11:55:00.668298: Current learning rate: 0.00974 
2025-05-15 11:56:49.463612: train_loss -0.7757 
2025-05-15 11:56:49.476161: val_loss -0.7955 
2025-05-15 11:56:49.483703: Pseudo dice [0.8585] 
2025-05-15 11:56:49.491245: Epoch time: 108.8 s 
2025-05-15 11:56:49.498297: Yayy! New best EMA pseudo Dice: 0.8222 
2025-05-15 11:56:50.808070:  
2025-05-15 11:56:50.816130: Epoch 30 
2025-05-15 11:56:50.821811: Current learning rate: 0.00973 
2025-05-15 11:58:39.801546: train_loss -0.7692 
2025-05-15 11:58:39.806066: val_loss -0.7895 
2025-05-15 11:58:39.818146: Pseudo dice [0.8543] 
2025-05-15 11:58:39.826190: Epoch time: 108.99 s 
2025-05-15 11:58:39.836738: Yayy! New best EMA pseudo Dice: 0.8254 
2025-05-15 11:58:41.150141:  
2025-05-15 11:58:41.159264: Epoch 31 
2025-05-15 11:58:41.165474: Current learning rate: 0.00972 
2025-05-15 12:00:29.953166: train_loss -0.7635 
2025-05-15 12:00:29.956195: val_loss -0.8039 
2025-05-15 12:00:29.963711: Pseudo dice [0.8651] 
2025-05-15 12:00:29.976291: Epoch time: 108.8 s 
2025-05-15 12:00:29.983808: Yayy! New best EMA pseudo Dice: 0.8293 
2025-05-15 12:00:31.311709:  
2025-05-15 12:00:31.321964: Epoch 32 
2025-05-15 12:00:31.327064: Current learning rate: 0.00971 
2025-05-15 12:02:20.078027: train_loss -0.7638 
2025-05-15 12:02:20.089545: val_loss -0.8144 
2025-05-15 12:02:20.098116: Pseudo dice [0.8623] 
2025-05-15 12:02:20.109635: Epoch time: 108.77 s 
2025-05-15 12:02:20.118217: Yayy! New best EMA pseudo Dice: 0.8326 
2025-05-15 12:02:21.445728:  
2025-05-15 12:02:21.448236: Epoch 33 
2025-05-15 12:02:21.460820: Current learning rate: 0.0097 
2025-05-15 12:04:10.177619: train_loss -0.7463 
2025-05-15 12:04:10.197717: val_loss -0.7939 
2025-05-15 12:04:10.206779: Pseudo dice [0.8605] 
2025-05-15 12:04:10.209297: Epoch time: 108.73 s 
2025-05-15 12:04:10.217834: Yayy! New best EMA pseudo Dice: 0.8354 
2025-05-15 12:04:11.554351:  
2025-05-15 12:04:11.574475: Epoch 34 
2025-05-15 12:04:11.574475: Current learning rate: 0.00969 
2025-05-15 12:06:00.559833: train_loss -0.7579 
2025-05-15 12:06:00.570353: val_loss -0.8059 
2025-05-15 12:06:00.581444: Pseudo dice [0.8682] 
2025-05-15 12:06:00.590456: Epoch time: 109.01 s 
2025-05-15 12:06:00.601542: Yayy! New best EMA pseudo Dice: 0.8387 
2025-05-15 12:06:02.064357:  
2025-05-15 12:06:02.065869: Epoch 35 
2025-05-15 12:06:02.073390: Current learning rate: 0.00968 
2025-05-15 12:07:50.852378: train_loss -0.787 
2025-05-15 12:07:50.859412: val_loss -0.8249 
2025-05-15 12:07:50.872025: Pseudo dice [0.878] 
2025-05-15 12:07:50.879569: Epoch time: 108.79 s 
2025-05-15 12:07:50.879569: Yayy! New best EMA pseudo Dice: 0.8426 
2025-05-15 12:07:52.228887:  
2025-05-15 12:07:52.236457: Epoch 36 
2025-05-15 12:07:52.237503: Current learning rate: 0.00968 
2025-05-15 12:09:41.087093: train_loss -0.7622 
2025-05-15 12:09:41.094655: val_loss -0.7902 
2025-05-15 12:09:41.106694: Pseudo dice [0.8534] 
2025-05-15 12:09:41.114738: Epoch time: 108.86 s 
2025-05-15 12:09:41.114738: Yayy! New best EMA pseudo Dice: 0.8437 
2025-05-15 12:09:42.452807:  
2025-05-15 12:09:42.454828: Epoch 37 
2025-05-15 12:09:42.465864: Current learning rate: 0.00967 
2025-05-15 12:11:31.011276: train_loss -0.7565 
2025-05-15 12:11:31.023394: val_loss -0.8131 
2025-05-15 12:11:31.031403: Pseudo dice [0.8657] 
2025-05-15 12:11:31.041465: Epoch time: 108.56 s 
2025-05-15 12:11:31.043488: Yayy! New best EMA pseudo Dice: 0.8459 
2025-05-15 12:11:32.360740:  
2025-05-15 12:11:32.367808: Epoch 38 
2025-05-15 12:11:32.370818: Current learning rate: 0.00966 
2025-05-15 12:13:21.183688: train_loss -0.7792 
2025-05-15 12:13:21.201765: val_loss -0.8204 
2025-05-15 12:13:21.204273: Pseudo dice [0.874] 
2025-05-15 12:13:21.220863: Epoch time: 108.82 s 
2025-05-15 12:13:21.224381: Yayy! New best EMA pseudo Dice: 0.8487 
2025-05-15 12:13:22.564116:  
2025-05-15 12:13:22.569835: Epoch 39 
2025-05-15 12:13:22.574372: Current learning rate: 0.00965 
2025-05-15 12:15:11.247579: train_loss -0.7835 
2025-05-15 12:15:11.261165: val_loss -0.8242 
2025-05-15 12:15:11.267683: Pseudo dice [0.8795] 
2025-05-15 12:15:11.269192: Epoch time: 108.68 s 
2025-05-15 12:15:11.281758: Yayy! New best EMA pseudo Dice: 0.8518 
2025-05-15 12:15:12.636592:  
2025-05-15 12:15:12.646398: Epoch 40 
2025-05-15 12:15:12.653534: Current learning rate: 0.00964 
2025-05-15 12:17:01.566985: train_loss -0.8032 
2025-05-15 12:17:01.575037: val_loss -0.8194 
2025-05-15 12:17:01.582060: Pseudo dice [0.8717] 
2025-05-15 12:17:01.587595: Epoch time: 108.93 s 
2025-05-15 12:17:01.595642: Yayy! New best EMA pseudo Dice: 0.8538 
2025-05-15 12:17:02.934760:  
2025-05-15 12:17:02.948957: Epoch 41 
2025-05-15 12:17:02.955223: Current learning rate: 0.00963 
2025-05-15 12:18:51.422706: train_loss -0.7751 
2025-05-15 12:18:51.422706: val_loss -0.8312 
2025-05-15 12:18:51.438327: Pseudo dice [0.8815] 
2025-05-15 12:18:51.438327: Epoch time: 108.49 s 
2025-05-15 12:18:51.453950: Yayy! New best EMA pseudo Dice: 0.8565 
2025-05-15 12:18:52.947353:  
2025-05-15 12:18:52.960053: Epoch 42 
2025-05-15 12:18:52.965308: Current learning rate: 0.00962 
2025-05-15 12:20:41.411080: train_loss -0.792 
2025-05-15 12:20:41.421602: val_loss -0.8259 
2025-05-15 12:20:41.429640: Pseudo dice [0.8793] 
2025-05-15 12:20:41.435692: Epoch time: 108.46 s 
2025-05-15 12:20:41.441701: Yayy! New best EMA pseudo Dice: 0.8588 
2025-05-15 12:20:42.754685:  
2025-05-15 12:20:42.757212: Epoch 43 
2025-05-15 12:20:42.769292: Current learning rate: 0.00961 
2025-05-15 12:22:31.085155: train_loss -0.792 
2025-05-15 12:22:31.100776: val_loss -0.7993 
2025-05-15 12:22:31.100776: Pseudo dice [0.8578] 
2025-05-15 12:22:31.116398: Epoch time: 108.33 s 
2025-05-15 12:22:32.054227:  
2025-05-15 12:22:32.057765: Epoch 44 
2025-05-15 12:22:32.057765: Current learning rate: 0.0096 
2025-05-15 12:24:20.756725: train_loss -0.7978 
2025-05-15 12:24:20.766281: val_loss -0.7985 
2025-05-15 12:24:20.773809: Pseudo dice [0.8583] 
2025-05-15 12:24:20.781437: Epoch time: 108.7 s 
2025-05-15 12:24:21.710296:  
2025-05-15 12:24:21.717352: Epoch 45 
2025-05-15 12:24:21.721879: Current learning rate: 0.00959 
2025-05-15 12:26:10.374130: train_loss -0.7987 
2025-05-15 12:26:10.376155: val_loss -0.8242 
2025-05-15 12:26:10.388691: Pseudo dice [0.882] 
2025-05-15 12:26:10.396735: Epoch time: 108.66 s 
2025-05-15 12:26:10.409260: Yayy! New best EMA pseudo Dice: 0.861 
2025-05-15 12:26:11.714420:  
2025-05-15 12:26:11.720930: Epoch 46 
2025-05-15 12:26:11.720930: Current learning rate: 0.00959 
2025-05-15 12:28:00.665715: train_loss -0.7587 
2025-05-15 12:28:00.672724: val_loss -0.8041 
2025-05-15 12:28:00.685814: Pseudo dice [0.8631] 
2025-05-15 12:28:00.692824: Epoch time: 108.95 s 
2025-05-15 12:28:00.705909: Yayy! New best EMA pseudo Dice: 0.8612 
2025-05-15 12:28:02.011276:  
2025-05-15 12:28:02.027513: Epoch 47 
2025-05-15 12:28:02.031547: Current learning rate: 0.00958 
2025-05-15 12:29:50.495016: train_loss -0.7924 
2025-05-15 12:29:50.509620: val_loss -0.8207 
2025-05-15 12:29:50.516643: Pseudo dice [0.8759] 
2025-05-15 12:29:50.525200: Epoch time: 108.48 s 
2025-05-15 12:29:50.529723: Yayy! New best EMA pseudo Dice: 0.8627 
2025-05-15 12:29:51.946427:  
2025-05-15 12:29:51.954007: Epoch 48 
2025-05-15 12:29:51.957026: Current learning rate: 0.00957 
2025-05-15 12:31:40.722255: train_loss -0.7914 
2025-05-15 12:31:40.733821: val_loss -0.8026 
2025-05-15 12:31:40.742342: Pseudo dice [0.8627] 
2025-05-15 12:31:40.749888: Epoch time: 108.78 s 
2025-05-15 12:31:41.687872:  
2025-05-15 12:31:41.693961: Epoch 49 
2025-05-15 12:31:41.701531: Current learning rate: 0.00956 
2025-05-15 12:33:30.290453: train_loss -0.7749 
2025-05-15 12:33:30.303513: val_loss -0.8197 
2025-05-15 12:33:30.310557: Pseudo dice [0.8744] 
2025-05-15 12:33:30.321620: Epoch time: 108.6 s 
2025-05-15 12:33:30.709256: Yayy! New best EMA pseudo Dice: 0.8639 
2025-05-15 12:33:32.023063:  
2025-05-15 12:33:32.029087: Epoch 50 
2025-05-15 12:33:32.037160: Current learning rate: 0.00955 
2025-05-15 12:35:20.785955: train_loss -0.797 
2025-05-15 12:35:20.794981: val_loss -0.8333 
2025-05-15 12:35:20.809055: Pseudo dice [0.8853] 
2025-05-15 12:35:20.815072: Epoch time: 108.76 s 
2025-05-15 12:35:20.821140: Yayy! New best EMA pseudo Dice: 0.866 
2025-05-15 12:35:22.151563:  
2025-05-15 12:35:22.163713: Epoch 51 
2025-05-15 12:35:22.166750: Current learning rate: 0.00954 
2025-05-15 12:37:10.657181: train_loss -0.8022 
2025-05-15 12:37:10.676273: val_loss -0.8288 
2025-05-15 12:37:10.688346: Pseudo dice [0.88] 
2025-05-15 12:37:10.697862: Epoch time: 108.51 s 
2025-05-15 12:37:10.708449: Yayy! New best EMA pseudo Dice: 0.8674 
2025-05-15 12:37:12.024950:  
2025-05-15 12:37:12.033172: Epoch 52 
2025-05-15 12:37:12.035755: Current learning rate: 0.00953 
2025-05-15 12:39:00.625925: train_loss -0.795 
2025-05-15 12:39:00.641546: val_loss -0.8205 
2025-05-15 12:39:00.646416: Pseudo dice [0.868] 
2025-05-15 12:39:00.666527: Epoch time: 108.6 s 
2025-05-15 12:39:00.686850: Yayy! New best EMA pseudo Dice: 0.8675 
2025-05-15 12:39:01.981626:  
2025-05-15 12:39:01.990162: Epoch 53 
2025-05-15 12:39:02.002018: Current learning rate: 0.00952 
2025-05-15 12:40:50.808160: train_loss -0.7943 
2025-05-15 12:40:50.820252: val_loss -0.8367 
2025-05-15 12:40:50.828793: Pseudo dice [0.8796] 
2025-05-15 12:40:50.836844: Epoch time: 108.83 s 
2025-05-15 12:40:50.840361: Yayy! New best EMA pseudo Dice: 0.8687 
2025-05-15 12:40:52.273834:  
2025-05-15 12:40:52.283710: Epoch 54 
2025-05-15 12:40:52.285746: Current learning rate: 0.00951 
2025-05-15 12:42:40.831670: train_loss -0.7948 
2025-05-15 12:42:40.837676: val_loss -0.8194 
2025-05-15 12:42:40.851764: Pseudo dice [0.8733] 
2025-05-15 12:42:40.857770: Epoch time: 108.56 s 
2025-05-15 12:42:40.857770: Yayy! New best EMA pseudo Dice: 0.8692 
2025-05-15 12:42:42.161146:  
2025-05-15 12:42:42.168701: Epoch 55 
2025-05-15 12:42:42.174431: Current learning rate: 0.0095 
2025-05-15 12:44:30.857935: train_loss -0.7921 
2025-05-15 12:44:30.857935: val_loss -0.8303 
2025-05-15 12:44:30.878043: Pseudo dice [0.8819] 
2025-05-15 12:44:30.889097: Epoch time: 108.7 s 
2025-05-15 12:44:30.898659: Yayy! New best EMA pseudo Dice: 0.8704 
2025-05-15 12:44:32.220338:  
2025-05-15 12:44:32.233936: Epoch 56 
2025-05-15 12:44:32.239778: Current learning rate: 0.00949 
2025-05-15 12:46:20.655593: train_loss -0.8101 
2025-05-15 12:46:20.667664: val_loss -0.8353 
2025-05-15 12:46:20.675684: Pseudo dice [0.8827] 
2025-05-15 12:46:20.683728: Epoch time: 108.44 s 
2025-05-15 12:46:20.687747: Yayy! New best EMA pseudo Dice: 0.8717 
2025-05-15 12:46:21.990685:  
2025-05-15 12:46:21.995697: Epoch 57 
2025-05-15 12:46:21.995697: Current learning rate: 0.00949 
2025-05-15 12:48:10.779069: train_loss -0.7975 
2025-05-15 12:48:10.781576: val_loss -0.8216 
2025-05-15 12:48:10.792187: Pseudo dice [0.8689] 
2025-05-15 12:48:10.801716: Epoch time: 108.79 s 
2025-05-15 12:48:11.750297:  
2025-05-15 12:48:11.757334: Epoch 58 
2025-05-15 12:48:11.757334: Current learning rate: 0.00948 
2025-05-15 12:50:00.406734: train_loss -0.7688 
2025-05-15 12:50:00.411745: val_loss -0.7999 
2025-05-15 12:50:00.411745: Pseudo dice [0.8585] 
2025-05-15 12:50:00.426822: Epoch time: 108.66 s 
2025-05-15 12:50:01.399386:  
2025-05-15 12:50:01.404918: Epoch 59 
2025-05-15 12:50:01.404918: Current learning rate: 0.00947 
2025-05-15 12:51:50.003832: train_loss -0.7875 
2025-05-15 12:51:50.018399: val_loss -0.8369 
2025-05-15 12:51:50.023910: Pseudo dice [0.8865] 
2025-05-15 12:51:50.037966: Epoch time: 108.6 s 
2025-05-15 12:51:50.043986: Yayy! New best EMA pseudo Dice: 0.8717 
2025-05-15 12:51:51.407409:  
2025-05-15 12:51:51.420934: Epoch 60 
2025-05-15 12:51:51.425464: Current learning rate: 0.00946 
2025-05-15 12:53:40.088409: train_loss -0.7949 
2025-05-15 12:53:40.098960: val_loss -0.8083 
2025-05-15 12:53:40.102990: Pseudo dice [0.863] 
2025-05-15 12:53:40.108500: Epoch time: 108.68 s 
2025-05-15 12:53:41.218654:  
2025-05-15 12:53:41.224684: Epoch 61 
2025-05-15 12:53:41.230702: Current learning rate: 0.00945 
2025-05-15 12:55:29.755990: train_loss -0.7907 
2025-05-15 12:55:29.760819: val_loss -0.8305 
2025-05-15 12:55:29.760819: Pseudo dice [0.8833] 
2025-05-15 12:55:29.781395: Epoch time: 108.55 s 
2025-05-15 12:55:29.781395: Yayy! New best EMA pseudo Dice: 0.8721 
2025-05-15 12:55:31.095125:  
2025-05-15 12:55:31.095125: Epoch 62 
2025-05-15 12:55:31.095125: Current learning rate: 0.00944 
2025-05-15 12:57:19.443759: train_loss -0.801 
2025-05-15 12:57:19.454366: val_loss -0.8331 
2025-05-15 12:57:19.463449: Pseudo dice [0.8828] 
2025-05-15 12:57:19.471016: Epoch time: 108.35 s 
2025-05-15 12:57:19.479089: Yayy! New best EMA pseudo Dice: 0.8732 
2025-05-15 12:57:20.783116:  
2025-05-15 12:57:20.797771: Epoch 63 
2025-05-15 12:57:20.803452: Current learning rate: 0.00943 
2025-05-15 12:59:09.349500: train_loss -0.8063 
2025-05-15 12:59:09.349500: val_loss -0.8287 
2025-05-15 12:59:09.365596: Pseudo dice [0.8862] 
2025-05-15 12:59:09.369603: Epoch time: 108.57 s 
2025-05-15 12:59:09.385675: Yayy! New best EMA pseudo Dice: 0.8745 
2025-05-15 12:59:10.713758:  
2025-05-15 12:59:10.723781: Epoch 64 
2025-05-15 12:59:10.729539: Current learning rate: 0.00942 
2025-05-15 13:00:59.207387: train_loss -0.7936 
2025-05-15 13:00:59.219501: val_loss -0.8413 
2025-05-15 13:00:59.227528: Pseudo dice [0.8846] 
2025-05-15 13:00:59.237597: Epoch time: 108.49 s 
2025-05-15 13:00:59.239613: Yayy! New best EMA pseudo Dice: 0.8755 
2025-05-15 13:01:00.614216:  
2025-05-15 13:01:00.619743: Epoch 65 
2025-05-15 13:01:00.627286: Current learning rate: 0.00941 
2025-05-15 13:02:49.118824: train_loss -0.8077 
2025-05-15 13:02:49.135408: val_loss -0.8217 
2025-05-15 13:02:49.138963: Pseudo dice [0.8774] 
2025-05-15 13:02:49.152011: Epoch time: 108.51 s 
2025-05-15 13:02:49.159050: Yayy! New best EMA pseudo Dice: 0.8757 
2025-05-15 13:02:50.505270:  
2025-05-15 13:02:50.519930: Epoch 66 
2025-05-15 13:02:50.525726: Current learning rate: 0.0094 
2025-05-15 13:04:39.144452: train_loss -0.8148 
2025-05-15 13:04:39.159998: val_loss -0.8441 
2025-05-15 13:04:39.165037: Pseudo dice [0.8876] 
2025-05-15 13:04:39.165037: Epoch time: 108.64 s 
2025-05-15 13:04:39.180594: Yayy! New best EMA pseudo Dice: 0.8769 
2025-05-15 13:04:40.611774:  
2025-05-15 13:04:40.615319: Epoch 67 
2025-05-15 13:04:40.615319: Current learning rate: 0.00939 
2025-05-15 13:06:29.180892: train_loss -0.8073 
2025-05-15 13:06:29.198479: val_loss -0.8319 
2025-05-15 13:06:29.200987: Pseudo dice [0.8854] 
2025-05-15 13:06:29.214579: Epoch time: 108.57 s 
2025-05-15 13:06:29.221103: Yayy! New best EMA pseudo Dice: 0.8777 
2025-05-15 13:06:30.556609:  
2025-05-15 13:06:30.564058: Epoch 68 
2025-05-15 13:06:30.564058: Current learning rate: 0.00939 
2025-05-15 13:08:19.097079: train_loss -0.7973 
2025-05-15 13:08:19.112701: val_loss -0.8105 
2025-05-15 13:08:19.117457: Pseudo dice [0.8662] 
2025-05-15 13:08:19.117457: Epoch time: 108.55 s 
2025-05-15 13:08:20.110629:  
2025-05-15 13:08:20.115355: Epoch 69 
2025-05-15 13:08:20.120895: Current learning rate: 0.00938 
2025-05-15 13:10:08.625755: train_loss -0.8007 
2025-05-15 13:10:08.635370: val_loss -0.827 
2025-05-15 13:10:08.642462: Pseudo dice [0.8766] 
2025-05-15 13:10:08.648483: Epoch time: 108.52 s 
2025-05-15 13:10:09.627547:  
2025-05-15 13:10:09.635646: Epoch 70 
2025-05-15 13:10:09.641963: Current learning rate: 0.00937 
2025-05-15 13:11:58.181064: train_loss -0.8211 
2025-05-15 13:11:58.185071: val_loss -0.8514 
2025-05-15 13:11:58.201173: Pseudo dice [0.8979] 
2025-05-15 13:11:58.205179: Epoch time: 108.55 s 
2025-05-15 13:11:58.205179: Yayy! New best EMA pseudo Dice: 0.8787 
2025-05-15 13:11:59.550285:  
2025-05-15 13:11:59.566340: Epoch 71 
2025-05-15 13:11:59.570355: Current learning rate: 0.00936 
2025-05-15 13:13:48.158135: train_loss -0.8311 
2025-05-15 13:13:48.168198: val_loss -0.8639 
2025-05-15 13:13:48.175725: Pseudo dice [0.9032] 
2025-05-15 13:13:48.182270: Epoch time: 108.61 s 
2025-05-15 13:13:48.188312: Yayy! New best EMA pseudo Dice: 0.8812 
2025-05-15 13:13:49.507310:  
2025-05-15 13:13:49.514383: Epoch 72 
2025-05-15 13:13:49.519899: Current learning rate: 0.00935 
2025-05-15 13:15:38.034704: train_loss -0.8256 
2025-05-15 13:15:38.050322: val_loss -0.8497 
2025-05-15 13:15:38.065943: Pseudo dice [0.8934] 
2025-05-15 13:15:38.065943: Epoch time: 108.53 s 
2025-05-15 13:15:38.081565: Yayy! New best EMA pseudo Dice: 0.8824 
2025-05-15 13:15:39.523207:  
2025-05-15 13:15:39.536006: Epoch 73 
2025-05-15 13:15:39.542189: Current learning rate: 0.00934 
2025-05-15 13:17:28.159042: train_loss -0.8292 
2025-05-15 13:17:28.173613: val_loss -0.8344 
2025-05-15 13:17:28.182190: Pseudo dice [0.8868] 
2025-05-15 13:17:28.193760: Epoch time: 108.64 s 
2025-05-15 13:17:28.199292: Yayy! New best EMA pseudo Dice: 0.8828 
2025-05-15 13:17:29.518190:  
2025-05-15 13:17:29.525399: Epoch 74 
2025-05-15 13:17:29.531453: Current learning rate: 0.00933 
2025-05-15 13:19:18.227941: train_loss -0.8078 
2025-05-15 13:19:18.234474: val_loss -0.8443 
2025-05-15 13:19:18.254063: Pseudo dice [0.8949] 
2025-05-15 13:19:18.254576: Epoch time: 108.71 s 
2025-05-15 13:19:18.269656: Yayy! New best EMA pseudo Dice: 0.884 
2025-05-15 13:19:19.617039:  
2025-05-15 13:19:19.633596: Epoch 75 
2025-05-15 13:19:19.637139: Current learning rate: 0.00932 
2025-05-15 13:21:07.903554: train_loss -0.8157 
2025-05-15 13:21:07.915609: val_loss -0.859 
2025-05-15 13:21:07.923657: Pseudo dice [0.9014] 
2025-05-15 13:21:07.933187: Epoch time: 108.29 s 
2025-05-15 13:21:07.940718: Yayy! New best EMA pseudo Dice: 0.8858 
2025-05-15 13:21:09.265550:  
2025-05-15 13:21:09.271123: Epoch 76 
2025-05-15 13:21:09.279343: Current learning rate: 0.00931 
2025-05-15 13:22:57.649798: train_loss -0.8275 
2025-05-15 13:22:57.653336: val_loss -0.8438 
2025-05-15 13:22:57.672446: Pseudo dice [0.8846] 
2025-05-15 13:22:57.673454: Epoch time: 108.38 s 
2025-05-15 13:22:58.688582:  
2025-05-15 13:22:58.697140: Epoch 77 
2025-05-15 13:22:58.699149: Current learning rate: 0.0093 
2025-05-15 13:24:47.276480: train_loss -0.8206 
2025-05-15 13:24:47.283525: val_loss -0.8539 
2025-05-15 13:24:47.291074: Pseudo dice [0.8952] 
2025-05-15 13:24:47.303143: Epoch time: 108.59 s 
2025-05-15 13:24:47.311200: Yayy! New best EMA pseudo Dice: 0.8866 
2025-05-15 13:24:48.652506:  
2025-05-15 13:24:48.656579: Epoch 78 
2025-05-15 13:24:48.666718: Current learning rate: 0.0093 
2025-05-15 13:26:36.924191: train_loss -0.8168 
2025-05-15 13:26:36.939269: val_loss -0.8524 
2025-05-15 13:26:36.944278: Pseudo dice [0.8942] 
2025-05-15 13:26:36.958376: Epoch time: 108.27 s 
2025-05-15 13:26:36.964408: Yayy! New best EMA pseudo Dice: 0.8874 
2025-05-15 13:26:38.482641:  
2025-05-15 13:26:38.487760: Epoch 79 
2025-05-15 13:26:38.487760: Current learning rate: 0.00929 
2025-05-15 13:28:26.925243: train_loss -0.8235 
2025-05-15 13:28:26.939316: val_loss -0.8601 
2025-05-15 13:28:26.945369: Pseudo dice [0.9017] 
2025-05-15 13:28:26.957420: Epoch time: 108.44 s 
2025-05-15 13:28:26.965449: Yayy! New best EMA pseudo Dice: 0.8888 
2025-05-15 13:28:28.336327:  
2025-05-15 13:28:28.346356: Epoch 80 
2025-05-15 13:28:28.350927: Current learning rate: 0.00928 
2025-05-15 13:30:16.939428: train_loss -0.8287 
2025-05-15 13:30:16.948525: val_loss -0.8397 
2025-05-15 13:30:16.952558: Pseudo dice [0.8854] 
2025-05-15 13:30:16.963125: Epoch time: 108.6 s 
2025-05-15 13:30:17.947969:  
2025-05-15 13:30:17.957509: Epoch 81 
2025-05-15 13:30:17.964086: Current learning rate: 0.00927 
2025-05-15 13:32:06.495672: train_loss -0.8225 
2025-05-15 13:32:06.495672: val_loss -0.8624 
2025-05-15 13:32:06.511249: Pseudo dice [0.9035] 
2025-05-15 13:32:06.515782: Epoch time: 108.55 s 
2025-05-15 13:32:06.531878: Yayy! New best EMA pseudo Dice: 0.89 
2025-05-15 13:32:07.878940:  
2025-05-15 13:32:07.883978: Epoch 82 
2025-05-15 13:32:07.891529: Current learning rate: 0.00926 
2025-05-15 13:33:56.393215: train_loss -0.8186 
2025-05-15 13:33:56.404265: val_loss -0.8645 
2025-05-15 13:33:56.413309: Pseudo dice [0.9025] 
2025-05-15 13:33:56.421351: Epoch time: 108.52 s 
2025-05-15 13:33:56.433435: Yayy! New best EMA pseudo Dice: 0.8912 
2025-05-15 13:33:57.693832:  
2025-05-15 13:33:57.702422: Epoch 83 
2025-05-15 13:33:57.710530: Current learning rate: 0.00925 
2025-05-15 13:35:46.286011: train_loss -0.8295 
2025-05-15 13:35:46.289028: val_loss -0.8398 
2025-05-15 13:35:46.301593: Pseudo dice [0.8906] 
2025-05-15 13:35:46.309613: Epoch time: 108.59 s 
2025-05-15 13:35:47.244069:  
2025-05-15 13:35:47.244069: Epoch 84 
2025-05-15 13:35:47.257762: Current learning rate: 0.00924 
2025-05-15 13:37:35.865578: train_loss -0.8273 
2025-05-15 13:37:35.877183: val_loss -0.8418 
2025-05-15 13:37:35.885705: Pseudo dice [0.8844] 
2025-05-15 13:37:35.885705: Epoch time: 108.62 s 
2025-05-15 13:37:36.953875:  
2025-05-15 13:37:36.960417: Epoch 85 
2025-05-15 13:37:36.965487: Current learning rate: 0.00923 
2025-05-15 13:39:25.354065: train_loss -0.7921 
2025-05-15 13:39:25.363095: val_loss -0.8023 
2025-05-15 13:39:25.371125: Pseudo dice [0.8601] 
2025-05-15 13:39:25.374134: Epoch time: 108.4 s 
2025-05-15 13:39:26.322046:  
2025-05-15 13:39:26.328845: Epoch 86 
2025-05-15 13:39:26.335439: Current learning rate: 0.00922 
2025-05-15 13:41:14.927382: train_loss -0.8033 
2025-05-15 13:41:14.940468: val_loss -0.8421 
2025-05-15 13:41:14.947527: Pseudo dice [0.8935] 
2025-05-15 13:41:14.956563: Epoch time: 108.61 s 
2025-05-15 13:41:15.890539:  
2025-05-15 13:41:15.898564: Epoch 87 
2025-05-15 13:41:15.903658: Current learning rate: 0.00921 
2025-05-15 13:43:04.455292: train_loss -0.8067 
2025-05-15 13:43:04.462831: val_loss -0.8558 
2025-05-15 13:43:04.471364: Pseudo dice [0.9003] 
2025-05-15 13:43:04.475373: Epoch time: 108.56 s 
2025-05-15 13:43:05.422435:  
2025-05-15 13:43:05.422435: Epoch 88 
2025-05-15 13:43:05.438541: Current learning rate: 0.0092 
2025-05-15 13:44:54.071527: train_loss -0.8076 
2025-05-15 13:44:54.077579: val_loss -0.8468 
2025-05-15 13:44:54.087126: Pseudo dice [0.8929] 
2025-05-15 13:44:54.103720: Epoch time: 108.65 s 
2025-05-15 13:44:55.067855:  
2025-05-15 13:44:55.075467: Epoch 89 
2025-05-15 13:44:55.081537: Current learning rate: 0.0092 
2025-05-15 13:46:43.505048: train_loss -0.811 
2025-05-15 13:46:43.511065: val_loss -0.8625 
2025-05-15 13:46:43.522631: Pseudo dice [0.9027] 
2025-05-15 13:46:43.531172: Epoch time: 108.44 s 
2025-05-15 13:46:44.460232:  
2025-05-15 13:46:44.460232: Epoch 90 
2025-05-15 13:46:44.476774: Current learning rate: 0.00919 
2025-05-15 13:48:33.028022: train_loss -0.8319 
2025-05-15 13:48:33.048117: val_loss -0.8528 
2025-05-15 13:48:33.048117: Pseudo dice [0.8964] 
2025-05-15 13:48:33.063179: Epoch time: 108.57 s 
2025-05-15 13:48:33.068209: Yayy! New best EMA pseudo Dice: 0.8915 
2025-05-15 13:48:34.408953:  
2025-05-15 13:48:34.426208: Epoch 91 
2025-05-15 13:48:34.429217: Current learning rate: 0.00918 
2025-05-15 13:50:22.941788: train_loss -0.8351 
2025-05-15 13:50:22.951839: val_loss -0.8598 
2025-05-15 13:50:22.959379: Pseudo dice [0.9037] 
2025-05-15 13:50:22.961892: Epoch time: 108.53 s 
2025-05-15 13:50:22.973979: Yayy! New best EMA pseudo Dice: 0.8927 
2025-05-15 13:50:24.395899:  
2025-05-15 13:50:24.415783: Epoch 92 
2025-05-15 13:50:24.416313: Current learning rate: 0.00917 
2025-05-15 13:52:13.004210: train_loss -0.8374 
2025-05-15 13:52:13.004210: val_loss -0.8612 
2025-05-15 13:52:13.019830: Pseudo dice [0.8974] 
2025-05-15 13:52:13.019830: Epoch time: 108.61 s 
2025-05-15 13:52:13.035451: Yayy! New best EMA pseudo Dice: 0.8932 
2025-05-15 13:52:14.302721:  
2025-05-15 13:52:14.309794: Epoch 93 
2025-05-15 13:52:14.318923: Current learning rate: 0.00916 
2025-05-15 13:54:03.017066: train_loss -0.8262 
2025-05-15 13:54:03.021581: val_loss -0.8494 
2025-05-15 13:54:03.037200: Pseudo dice [0.8955] 
2025-05-15 13:54:03.041722: Epoch time: 108.71 s 
2025-05-15 13:54:03.052305: Yayy! New best EMA pseudo Dice: 0.8934 
2025-05-15 13:54:04.390921:  
2025-05-15 13:54:04.396609: Epoch 94 
2025-05-15 13:54:04.403758: Current learning rate: 0.00915 
2025-05-15 13:55:52.882406: train_loss -0.8431 
2025-05-15 13:55:52.895475: val_loss -0.8746 
2025-05-15 13:55:52.902475: Pseudo dice [0.9103] 
2025-05-15 13:55:52.915901: Epoch time: 108.49 s 
2025-05-15 13:55:52.922906: Yayy! New best EMA pseudo Dice: 0.8951 
2025-05-15 13:55:54.241668:  
2025-05-15 13:55:54.250848: Epoch 95 
2025-05-15 13:55:54.256567: Current learning rate: 0.00914 
2025-05-15 13:57:42.841825: train_loss -0.8381 
2025-05-15 13:57:42.841825: val_loss -0.85 
2025-05-15 13:57:42.857446: Pseudo dice [0.8934] 
2025-05-15 13:57:42.864700: Epoch time: 108.6 s 
2025-05-15 13:57:43.799344:  
2025-05-15 13:57:43.804880: Epoch 96 
2025-05-15 13:57:43.804880: Current learning rate: 0.00913 
2025-05-15 13:59:32.380198: train_loss -0.8443 
2025-05-15 13:59:32.392253: val_loss -0.8669 
2025-05-15 13:59:32.400327: Pseudo dice [0.9102] 
2025-05-15 13:59:32.405845: Epoch time: 108.58 s 
2025-05-15 13:59:32.419422: Yayy! New best EMA pseudo Dice: 0.8965 
2025-05-15 13:59:33.763478:  
2025-05-15 13:59:33.770084: Epoch 97 
2025-05-15 13:59:33.770084: Current learning rate: 0.00912 
2025-05-15 14:01:22.434866: train_loss -0.8237 
2025-05-15 14:01:22.440919: val_loss -0.8689 
2025-05-15 14:01:22.444924: Pseudo dice [0.9044] 
2025-05-15 14:01:22.457978: Epoch time: 108.67 s 
2025-05-15 14:01:22.465015: Yayy! New best EMA pseudo Dice: 0.8973 
2025-05-15 14:01:23.915436:  
2025-05-15 14:01:23.924066: Epoch 98 
2025-05-15 14:01:23.927303: Current learning rate: 0.00911 
2025-05-15 14:03:12.403125: train_loss -0.8152 
2025-05-15 14:03:12.403125: val_loss -0.8494 
2025-05-15 14:03:12.417720: Pseudo dice [0.8934] 
2025-05-15 14:03:12.423235: Epoch time: 108.5 s 
2025-05-15 14:03:13.368785:  
2025-05-15 14:03:13.376941: Epoch 99 
2025-05-15 14:03:13.381081: Current learning rate: 0.0091 
2025-05-15 14:05:01.885978: train_loss -0.8198 
2025-05-15 14:05:01.892957: val_loss -0.8392 
2025-05-15 14:05:01.902487: Pseudo dice [0.8868] 
2025-05-15 14:05:01.915623: Epoch time: 108.52 s 
2025-05-15 14:05:03.242422:  
2025-05-15 14:05:03.246962: Epoch 100 
2025-05-15 14:05:03.262690: Current learning rate: 0.0091 
2025-05-15 14:06:51.725970: train_loss -0.8251 
2025-05-15 14:06:51.733012: val_loss -0.8428 
2025-05-15 14:06:51.733012: Pseudo dice [0.8931] 
2025-05-15 14:06:51.751583: Epoch time: 108.49 s 
2025-05-15 14:06:52.696793:  
2025-05-15 14:06:52.704367: Epoch 101 
2025-05-15 14:06:52.710712: Current learning rate: 0.00909 
2025-05-15 14:08:41.353125: train_loss -0.8372 
2025-05-15 14:08:41.368739: val_loss -0.8623 
2025-05-15 14:08:41.381196: Pseudo dice [0.9012] 
2025-05-15 14:08:41.389235: Epoch time: 108.66 s 
2025-05-15 14:08:42.343724:  
2025-05-15 14:08:42.350374: Epoch 102 
2025-05-15 14:08:42.360009: Current learning rate: 0.00908 
2025-05-15 14:10:31.038583: train_loss -0.8367 
2025-05-15 14:10:31.048667: val_loss -0.856 
2025-05-15 14:10:31.048667: Pseudo dice [0.8956] 
2025-05-15 14:10:31.064736: Epoch time: 108.69 s 
2025-05-15 14:10:32.008179:  
2025-05-15 14:10:32.015723: Epoch 103 
2025-05-15 14:10:32.022418: Current learning rate: 0.00907 
2025-05-15 14:12:20.872344: train_loss -0.8396 
2025-05-15 14:12:20.880387: val_loss -0.8619 
2025-05-15 14:12:20.885398: Pseudo dice [0.9045] 
2025-05-15 14:12:20.900479: Epoch time: 108.86 s 
2025-05-15 14:12:21.963185:  
2025-05-15 14:12:21.975774: Epoch 104 
2025-05-15 14:12:21.982011: Current learning rate: 0.00906 
2025-05-15 14:14:10.474095: train_loss -0.8389 
2025-05-15 14:14:10.474095: val_loss -0.8662 
2025-05-15 14:14:10.487665: Pseudo dice [0.906] 
2025-05-15 14:14:10.494199: Epoch time: 108.51 s 
2025-05-15 14:14:10.507785: Yayy! New best EMA pseudo Dice: 0.8978 
2025-05-15 14:14:11.867132:  
2025-05-15 14:14:11.873700: Epoch 105 
2025-05-15 14:14:11.879213: Current learning rate: 0.00905 
2025-05-15 14:16:00.440262: train_loss -0.8183 
2025-05-15 14:16:00.442766: val_loss -0.8467 
2025-05-15 14:16:00.460417: Pseudo dice [0.8956] 
2025-05-15 14:16:00.462927: Epoch time: 108.58 s 
2025-05-15 14:16:01.415250:  
2025-05-15 14:16:01.419975: Epoch 106 
2025-05-15 14:16:01.428524: Current learning rate: 0.00904 
2025-05-15 14:17:50.326845: train_loss -0.8271 
2025-05-15 14:17:50.334854: val_loss -0.8316 
2025-05-15 14:17:50.347427: Pseudo dice [0.8844] 
2025-05-15 14:17:50.354943: Epoch time: 108.91 s 
2025-05-15 14:17:51.304960:  
2025-05-15 14:17:51.309572: Epoch 107 
2025-05-15 14:17:51.309572: Current learning rate: 0.00903 
2025-05-15 14:19:40.026109: train_loss -0.8155 
2025-05-15 14:19:40.030117: val_loss -0.8386 
2025-05-15 14:19:40.046198: Pseudo dice [0.8919] 
2025-05-15 14:19:40.050206: Epoch time: 108.72 s 
2025-05-15 14:19:41.007368:  
2025-05-15 14:19:41.015932: Epoch 108 
2025-05-15 14:19:41.024100: Current learning rate: 0.00902 
2025-05-15 14:21:29.536953: train_loss -0.8308 
2025-05-15 14:21:29.539461: val_loss -0.8512 
2025-05-15 14:21:29.557049: Pseudo dice [0.8989] 
2025-05-15 14:21:29.559555: Epoch time: 108.53 s 
2025-05-15 14:21:30.535131:  
2025-05-15 14:21:30.546156: Epoch 109 
2025-05-15 14:21:30.552790: Current learning rate: 0.00901 
2025-05-15 14:23:19.231961: train_loss -0.8215 
2025-05-15 14:23:19.231961: val_loss -0.8523 
2025-05-15 14:23:19.246064: Pseudo dice [0.8974] 
2025-05-15 14:23:19.252071: Epoch time: 108.7 s 
2025-05-15 14:23:20.240311:  
2025-05-15 14:23:20.242840: Epoch 110 
2025-05-15 14:23:20.242840: Current learning rate: 0.009 
2025-05-15 14:25:08.732852: train_loss -0.7879 
2025-05-15 14:25:08.752953: val_loss -0.8351 
2025-05-15 14:25:08.763003: Pseudo dice [0.8855] 
2025-05-15 14:25:08.773024: Epoch time: 108.49 s 
2025-05-15 14:25:09.868176:  
2025-05-15 14:25:09.874434: Epoch 111 
2025-05-15 14:25:09.874434: Current learning rate: 0.009 
2025-05-15 14:26:58.400092: train_loss -0.8216 
2025-05-15 14:26:58.408119: val_loss -0.8523 
2025-05-15 14:26:58.420691: Pseudo dice [0.8986] 
2025-05-15 14:26:58.428728: Epoch time: 108.53 s 
2025-05-15 14:26:59.373814:  
2025-05-15 14:26:59.382431: Epoch 112 
2025-05-15 14:26:59.391629: Current learning rate: 0.00899 
2025-05-15 14:28:47.641155: train_loss -0.8305 
2025-05-15 14:28:47.656224: val_loss -0.8622 
2025-05-15 14:28:47.669796: Pseudo dice [0.8998] 
2025-05-15 14:28:47.676314: Epoch time: 108.27 s 
2025-05-15 14:28:48.618211:  
2025-05-15 14:28:48.631407: Epoch 113 
2025-05-15 14:28:48.638596: Current learning rate: 0.00898 
2025-05-15 14:30:37.159235: train_loss -0.7741 
2025-05-15 14:30:37.167808: val_loss -0.8223 
2025-05-15 14:30:37.167808: Pseudo dice [0.8806] 
2025-05-15 14:30:37.181426: Epoch time: 108.54 s 
2025-05-15 14:30:38.121292:  
2025-05-15 14:30:38.128830: Epoch 114 
2025-05-15 14:30:38.134372: Current learning rate: 0.00897 
2025-05-15 14:32:26.585979: train_loss -0.7991 
2025-05-15 14:32:26.596530: val_loss -0.8389 
2025-05-15 14:32:26.600040: Pseudo dice [0.8885] 
2025-05-15 14:32:26.611125: Epoch time: 108.47 s 
2025-05-15 14:32:27.559741:  
2025-05-15 14:32:27.569511: Epoch 115 
2025-05-15 14:32:27.572605: Current learning rate: 0.00896 
2025-05-15 14:34:16.054969: train_loss -0.8235 
2025-05-15 14:34:16.058481: val_loss -0.8518 
2025-05-15 14:34:16.072026: Pseudo dice [0.8999] 
2025-05-15 14:34:16.078564: Epoch time: 108.5 s 
2025-05-15 14:34:17.053079:  
2025-05-15 14:34:17.055654: Epoch 116 
2025-05-15 14:34:17.065707: Current learning rate: 0.00895 
2025-05-15 14:36:05.923841: train_loss -0.8342 
2025-05-15 14:36:05.929847: val_loss -0.8619 
2025-05-15 14:36:05.943939: Pseudo dice [0.9062] 
2025-05-15 14:36:05.949950: Epoch time: 108.87 s 
2025-05-15 14:36:07.057493:  
2025-05-15 14:36:07.065094: Epoch 117 
2025-05-15 14:36:07.070132: Current learning rate: 0.00894 
2025-05-15 14:37:55.663184: train_loss -0.8375 
2025-05-15 14:37:55.672744: val_loss -0.8609 
2025-05-15 14:37:55.677278: Pseudo dice [0.9053] 
2025-05-15 14:37:55.683285: Epoch time: 108.61 s 
2025-05-15 14:37:56.652725:  
2025-05-15 14:37:56.661870: Epoch 118 
2025-05-15 14:37:56.668940: Current learning rate: 0.00893 
2025-05-15 14:39:45.554203: train_loss -0.8234 
2025-05-15 14:39:45.562761: val_loss -0.8606 
2025-05-15 14:39:45.562761: Pseudo dice [0.9019] 
2025-05-15 14:39:45.577825: Epoch time: 108.9 s 
2025-05-15 14:39:46.541965:  
2025-05-15 14:39:46.549016: Epoch 119 
2025-05-15 14:39:46.555752: Current learning rate: 0.00892 
2025-05-15 14:41:34.958940: train_loss -0.8175 
2025-05-15 14:41:34.971503: val_loss -0.8214 
2025-05-15 14:41:34.979021: Pseudo dice [0.8683] 
2025-05-15 14:41:34.988621: Epoch time: 108.42 s 
2025-05-15 14:41:35.953728:  
2025-05-15 14:41:35.956802: Epoch 120 
2025-05-15 14:41:35.967870: Current learning rate: 0.00891 
2025-05-15 14:43:24.418117: train_loss -0.8109 
2025-05-15 14:43:24.425140: val_loss -0.8529 
2025-05-15 14:43:24.435202: Pseudo dice [0.8991] 
2025-05-15 14:43:24.441727: Epoch time: 108.46 s 
2025-05-15 14:43:25.418733:  
2025-05-15 14:43:25.428351: Epoch 121 
2025-05-15 14:43:25.433435: Current learning rate: 0.0089 
2025-05-15 14:45:14.158512: train_loss -0.8216 
2025-05-15 14:45:14.178606: val_loss -0.8575 
2025-05-15 14:45:14.178606: Pseudo dice [0.9034] 
2025-05-15 14:45:14.193171: Epoch time: 108.74 s 
2025-05-15 14:45:15.172549:  
2025-05-15 14:45:15.172549: Epoch 122 
2025-05-15 14:45:15.186107: Current learning rate: 0.00889 
2025-05-15 14:47:03.846072: train_loss -0.8335 
2025-05-15 14:47:03.859628: val_loss -0.8558 
2025-05-15 14:47:03.866162: Pseudo dice [0.899] 
2025-05-15 14:47:03.873200: Epoch time: 108.67 s 
2025-05-15 14:47:04.959579:  
2025-05-15 14:47:04.968132: Epoch 123 
2025-05-15 14:47:04.971656: Current learning rate: 0.00889 
2025-05-15 14:48:53.509684: train_loss -0.8337 
2025-05-15 14:48:53.516706: val_loss -0.8679 
2025-05-15 14:48:53.524235: Pseudo dice [0.9105] 
2025-05-15 14:48:53.532798: Epoch time: 108.55 s 
2025-05-15 14:48:54.492737:  
2025-05-15 14:48:54.497272: Epoch 124 
2025-05-15 14:48:54.509548: Current learning rate: 0.00888 
2025-05-15 14:50:42.973172: train_loss -0.8452 
2025-05-15 14:50:42.980697: val_loss -0.8701 
2025-05-15 14:50:42.991804: Pseudo dice [0.9095] 
2025-05-15 14:50:42.999341: Epoch time: 108.48 s 
2025-05-15 14:50:43.009398: Yayy! New best EMA pseudo Dice: 0.8986 
2025-05-15 14:50:44.319860:  
2025-05-15 14:50:44.327415: Epoch 125 
2025-05-15 14:50:44.333480: Current learning rate: 0.00887 
2025-05-15 14:52:32.917424: train_loss -0.8487 
2025-05-15 14:52:32.917424: val_loss -0.8669 
2025-05-15 14:52:32.937509: Pseudo dice [0.9019] 
2025-05-15 14:52:32.937509: Epoch time: 108.6 s 
2025-05-15 14:52:32.937509: Yayy! New best EMA pseudo Dice: 0.8989 
2025-05-15 14:52:34.256059:  
2025-05-15 14:52:34.256059: Epoch 126 
2025-05-15 14:52:34.273711: Current learning rate: 0.00886 
2025-05-15 14:54:22.819144: train_loss -0.842 
2025-05-15 14:54:22.835248: val_loss -0.8707 
2025-05-15 14:54:22.839254: Pseudo dice [0.9113] 
2025-05-15 14:54:22.848315: Epoch time: 108.56 s 
2025-05-15 14:54:22.859328: Yayy! New best EMA pseudo Dice: 0.9002 
2025-05-15 14:54:24.199594:  
2025-05-15 14:54:24.212098: Epoch 127 
2025-05-15 14:54:24.217702: Current learning rate: 0.00885 
2025-05-15 14:56:12.692404: train_loss -0.8354 
2025-05-15 14:56:12.694411: val_loss -0.8736 
2025-05-15 14:56:12.711488: Pseudo dice [0.9118] 
2025-05-15 14:56:12.714507: Epoch time: 108.49 s 
2025-05-15 14:56:12.728555: Yayy! New best EMA pseudo Dice: 0.9013 
2025-05-15 14:56:14.098395:  
2025-05-15 14:56:14.103432: Epoch 128 
2025-05-15 14:56:14.114643: Current learning rate: 0.00884 
2025-05-15 14:58:02.839095: train_loss -0.837 
2025-05-15 14:58:02.849623: val_loss -0.8649 
2025-05-15 14:58:02.859683: Pseudo dice [0.9083] 
2025-05-15 14:58:02.859683: Epoch time: 108.74 s 
2025-05-15 14:58:02.869726: Yayy! New best EMA pseudo Dice: 0.902 
2025-05-15 14:58:04.210192:  
2025-05-15 14:58:04.223327: Epoch 129 
2025-05-15 14:58:04.230565: Current learning rate: 0.00883 
2025-05-15 14:59:52.576360: train_loss -0.8352 
2025-05-15 14:59:52.587892: val_loss -0.8686 
2025-05-15 14:59:52.596938: Pseudo dice [0.9087] 
2025-05-15 14:59:52.596938: Epoch time: 108.37 s 
2025-05-15 14:59:52.608460: Yayy! New best EMA pseudo Dice: 0.9027 
2025-05-15 14:59:54.097326:  
2025-05-15 14:59:54.104003: Epoch 130 
2025-05-15 14:59:54.106537: Current learning rate: 0.00882 
2025-05-15 15:01:42.550133: train_loss -0.821 
2025-05-15 15:01:42.556667: val_loss -0.8236 
2025-05-15 15:01:42.564674: Pseudo dice [0.8829] 
2025-05-15 15:01:42.576736: Epoch time: 108.45 s 
2025-05-15 15:01:43.539803:  
2025-05-15 15:01:43.554342: Epoch 131 
2025-05-15 15:01:43.560360: Current learning rate: 0.00881 
2025-05-15 15:03:32.227787: train_loss -0.7972 
2025-05-15 15:03:32.247885: val_loss -0.8489 
2025-05-15 15:03:32.247885: Pseudo dice [0.8957] 
2025-05-15 15:03:32.262952: Epoch time: 108.69 s 
2025-05-15 15:03:33.239669:  
2025-05-15 15:03:33.242712: Epoch 132 
2025-05-15 15:03:33.242712: Current learning rate: 0.0088 
2025-05-15 15:05:21.842969: train_loss -0.8253 
2025-05-15 15:05:21.859023: val_loss -0.8564 
2025-05-15 15:05:21.872118: Pseudo dice [0.9034] 
2025-05-15 15:05:21.884703: Epoch time: 108.6 s 
2025-05-15 15:05:22.862734:  
2025-05-15 15:05:22.879963: Epoch 133 
2025-05-15 15:05:22.883178: Current learning rate: 0.00879 
2025-05-15 15:07:11.517892: train_loss -0.8169 
2025-05-15 15:07:11.518898: val_loss -0.8553 
2025-05-15 15:07:11.536986: Pseudo dice [0.8964] 
2025-05-15 15:07:11.539008: Epoch time: 108.66 s 
2025-05-15 15:07:12.517197:  
2025-05-15 15:07:12.522768: Epoch 134 
2025-05-15 15:07:12.524774: Current learning rate: 0.00879 
2025-05-15 15:09:01.142103: train_loss -0.842 
2025-05-15 15:09:01.155675: val_loss -0.8656 
2025-05-15 15:09:01.162213: Pseudo dice [0.9067] 
2025-05-15 15:09:01.172772: Epoch time: 108.63 s 
2025-05-15 15:09:02.158658:  
2025-05-15 15:09:02.167822: Epoch 135 
2025-05-15 15:09:02.173941: Current learning rate: 0.00878 
2025-05-15 15:10:50.618920: train_loss -0.8461 
2025-05-15 15:10:50.627966: val_loss -0.8621 
2025-05-15 15:10:50.631480: Pseudo dice [0.9045] 
2025-05-15 15:10:50.642043: Epoch time: 108.46 s 
2025-05-15 15:10:51.760899:  
2025-05-15 15:10:51.768212: Epoch 136 
2025-05-15 15:10:51.772835: Current learning rate: 0.00877 
2025-05-15 15:12:40.558631: train_loss -0.8453 
2025-05-15 15:12:40.568176: val_loss -0.8639 
2025-05-15 15:12:40.575271: Pseudo dice [0.9077] 
2025-05-15 15:12:40.582301: Epoch time: 108.8 s 
2025-05-15 15:12:41.564463:  
2025-05-15 15:12:41.571503: Epoch 137 
2025-05-15 15:12:41.571503: Current learning rate: 0.00876 
2025-05-15 15:14:29.896175: train_loss -0.8559 
2025-05-15 15:14:29.907222: val_loss -0.8865 
2025-05-15 15:14:29.916262: Pseudo dice [0.9194] 
2025-05-15 15:14:29.923293: Epoch time: 108.34 s 
2025-05-15 15:14:29.927300: Yayy! New best EMA pseudo Dice: 0.9036 
2025-05-15 15:14:31.307546:  
2025-05-15 15:14:31.315560: Epoch 138 
2025-05-15 15:14:31.323609: Current learning rate: 0.00875 
2025-05-15 15:16:19.750109: train_loss -0.8436 
2025-05-15 15:16:19.756655: val_loss -0.8595 
2025-05-15 15:16:19.756655: Pseudo dice [0.9048] 
2025-05-15 15:16:19.772729: Epoch time: 108.44 s 
2025-05-15 15:16:19.776741: Yayy! New best EMA pseudo Dice: 0.9037 
2025-05-15 15:16:21.221107:  
2025-05-15 15:16:21.228653: Epoch 139 
2025-05-15 15:16:21.234224: Current learning rate: 0.00874 
2025-05-15 15:18:09.990974: train_loss -0.828 
2025-05-15 15:18:10.005557: val_loss -0.8484 
2025-05-15 15:18:10.011068: Pseudo dice [0.8944] 
2025-05-15 15:18:10.018637: Epoch time: 108.77 s 
2025-05-15 15:18:11.000083:  
2025-05-15 15:18:11.014237: Epoch 140 
2025-05-15 15:18:11.020032: Current learning rate: 0.00873 
2025-05-15 15:19:59.684042: train_loss -0.815 
2025-05-15 15:19:59.692595: val_loss -0.8688 
2025-05-15 15:19:59.692595: Pseudo dice [0.9078] 
2025-05-15 15:19:59.708696: Epoch time: 108.68 s 
2025-05-15 15:20:00.693848:  
2025-05-15 15:20:00.693848: Epoch 141 
2025-05-15 15:20:00.708486: Current learning rate: 0.00872 
2025-05-15 15:21:49.314829: train_loss -0.8397 
2025-05-15 15:21:49.326409: val_loss -0.8692 
2025-05-15 15:21:49.333421: Pseudo dice [0.9061] 
2025-05-15 15:21:49.342007: Epoch time: 108.62 s 
2025-05-15 15:21:50.456275:  
2025-05-15 15:21:50.462829: Epoch 142 
2025-05-15 15:21:50.469359: Current learning rate: 0.00871 
2025-05-15 15:23:38.750028: train_loss -0.8483 
2025-05-15 15:23:38.758074: val_loss -0.8432 
2025-05-15 15:23:38.767127: Pseudo dice [0.8941] 
2025-05-15 15:23:38.770164: Epoch time: 108.3 s 
2025-05-15 15:23:39.769716:  
2025-05-15 15:23:39.773865: Epoch 143 
2025-05-15 15:23:39.782035: Current learning rate: 0.0087 
2025-05-15 15:25:28.559617: train_loss -0.8198 
2025-05-15 15:25:28.559617: val_loss -0.8554 
2025-05-15 15:25:28.579717: Pseudo dice [0.9019] 
2025-05-15 15:25:28.579717: Epoch time: 108.79 s 
2025-05-15 15:25:29.574367:  
2025-05-15 15:25:29.581469: Epoch 144 
2025-05-15 15:25:29.589561: Current learning rate: 0.00869 
2025-05-15 15:27:18.225004: train_loss -0.834 
2025-05-15 15:27:18.230013: val_loss -0.8537 
2025-05-15 15:27:18.243097: Pseudo dice [0.8994] 
2025-05-15 15:27:18.250126: Epoch time: 108.65 s 
2025-05-15 15:27:19.234190:  
2025-05-15 15:27:19.241530: Epoch 145 
2025-05-15 15:27:19.246138: Current learning rate: 0.00868 
2025-05-15 15:29:07.856730: train_loss -0.8411 
2025-05-15 15:29:07.872352: val_loss -0.8787 
2025-05-15 15:29:07.876968: Pseudo dice [0.9163] 
2025-05-15 15:29:07.876968: Epoch time: 108.62 s 
2025-05-15 15:29:08.867400:  
2025-05-15 15:29:08.874472: Epoch 146 
2025-05-15 15:29:08.882139: Current learning rate: 0.00868 
2025-05-15 15:30:57.451819: train_loss -0.8583 
2025-05-15 15:30:57.468914: val_loss -0.8795 
2025-05-15 15:30:57.471935: Pseudo dice [0.9171] 
2025-05-15 15:30:57.471935: Epoch time: 108.58 s 
2025-05-15 15:30:57.491011: Yayy! New best EMA pseudo Dice: 0.905 
2025-05-15 15:30:58.864913:  
2025-05-15 15:30:58.874723: Epoch 147 
2025-05-15 15:30:58.875756: Current learning rate: 0.00867 
2025-05-15 15:32:47.464827: train_loss -0.8555 
2025-05-15 15:32:47.478936: val_loss -0.866 
2025-05-15 15:32:47.484968: Pseudo dice [0.9088] 
2025-05-15 15:32:47.484968: Epoch time: 108.6 s 
2025-05-15 15:32:47.499077: Yayy! New best EMA pseudo Dice: 0.9054 
2025-05-15 15:32:48.979828:  
2025-05-15 15:32:48.987419: Epoch 148 
2025-05-15 15:32:48.987928: Current learning rate: 0.00866 
2025-05-15 15:34:37.380063: train_loss -0.8417 
2025-05-15 15:34:37.392640: val_loss -0.8649 
2025-05-15 15:34:37.400157: Pseudo dice [0.905] 
2025-05-15 15:34:37.410221: Epoch time: 108.4 s 
2025-05-15 15:34:38.409710:  
2025-05-15 15:34:38.417288: Epoch 149 
2025-05-15 15:34:38.422366: Current learning rate: 0.00865 
2025-05-15 15:36:27.087865: train_loss -0.8529 
2025-05-15 15:36:27.099252: val_loss -0.8754 
2025-05-15 15:36:27.109293: Pseudo dice [0.9161] 
2025-05-15 15:36:27.115278: Epoch time: 108.68 s 
2025-05-15 15:36:27.510392: Yayy! New best EMA pseudo Dice: 0.9064 
2025-05-15 15:36:28.966601:  
2025-05-15 15:36:28.971114: Epoch 150 
2025-05-15 15:36:28.982693: Current learning rate: 0.00864 
2025-05-15 15:38:17.819335: train_loss -0.8566 
2025-05-15 15:38:17.828882: val_loss -0.8757 
2025-05-15 15:38:17.828882: Pseudo dice [0.9108] 
2025-05-15 15:38:17.844988: Epoch time: 108.85 s 
2025-05-15 15:38:17.849010: Yayy! New best EMA pseudo Dice: 0.9068 
2025-05-15 15:38:19.254793:  
2025-05-15 15:38:19.267532: Epoch 151 
2025-05-15 15:38:19.271169: Current learning rate: 0.00863 
2025-05-15 15:40:07.687189: train_loss -0.8421 
2025-05-15 15:40:07.687189: val_loss -0.8644 
2025-05-15 15:40:07.707309: Pseudo dice [0.9072] 
2025-05-15 15:40:07.707309: Epoch time: 108.43 s 
2025-05-15 15:40:07.723894: Yayy! New best EMA pseudo Dice: 0.9069 
2025-05-15 15:40:09.048310:  
2025-05-15 15:40:09.052846: Epoch 152 
2025-05-15 15:40:09.062896: Current learning rate: 0.00862 
2025-05-15 15:41:57.859240: train_loss -0.8283 
2025-05-15 15:41:57.873813: val_loss -0.871 
2025-05-15 15:41:57.879345: Pseudo dice [0.9093] 
2025-05-15 15:41:57.885887: Epoch time: 108.81 s 
2025-05-15 15:41:57.896945: Yayy! New best EMA pseudo Dice: 0.9071 
2025-05-15 15:41:59.239415:  
2025-05-15 15:41:59.246536: Epoch 153 
2025-05-15 15:41:59.249582: Current learning rate: 0.00861 
2025-05-15 15:43:48.078418: train_loss -0.8428 
2025-05-15 15:43:48.081934: val_loss -0.8807 
2025-05-15 15:43:48.096043: Pseudo dice [0.9157] 
2025-05-15 15:43:48.102063: Epoch time: 108.84 s 
2025-05-15 15:43:48.102063: Yayy! New best EMA pseudo Dice: 0.908 
2025-05-15 15:43:49.612094:  
2025-05-15 15:43:49.620358: Epoch 154 
2025-05-15 15:43:49.620358: Current learning rate: 0.0086 
2025-05-15 15:45:38.229164: train_loss -0.852 
2025-05-15 15:45:38.240726: val_loss -0.8821 
2025-05-15 15:45:38.249240: Pseudo dice [0.9203] 
2025-05-15 15:45:38.260828: Epoch time: 108.62 s 
2025-05-15 15:45:38.269350: Yayy! New best EMA pseudo Dice: 0.9092 
2025-05-15 15:45:39.649503:  
2025-05-15 15:45:39.657633: Epoch 155 
2025-05-15 15:45:39.665664: Current learning rate: 0.00859 
2025-05-15 15:47:28.264481: train_loss -0.8557 
2025-05-15 15:47:28.269025: val_loss -0.8713 
2025-05-15 15:47:28.277042: Pseudo dice [0.9142] 
2025-05-15 15:47:28.289131: Epoch time: 108.62 s 
2025-05-15 15:47:28.297147: Yayy! New best EMA pseudo Dice: 0.9097 
2025-05-15 15:47:29.650855:  
2025-05-15 15:47:29.657422: Epoch 156 
2025-05-15 15:47:29.660958: Current learning rate: 0.00858 
2025-05-15 15:49:18.428132: train_loss -0.8262 
2025-05-15 15:49:18.428132: val_loss -0.8519 
2025-05-15 15:49:18.443733: Pseudo dice [0.9002] 
2025-05-15 15:49:18.448244: Epoch time: 108.78 s 
2025-05-15 15:49:19.481999:  
2025-05-15 15:49:19.494564: Epoch 157 
2025-05-15 15:49:19.500924: Current learning rate: 0.00858 
2025-05-15 15:51:08.176180: train_loss -0.8113 
2025-05-15 15:51:08.188765: val_loss -0.8504 
2025-05-15 15:51:08.196277: Pseudo dice [0.8935] 
2025-05-15 15:51:08.205364: Epoch time: 108.69 s 
2025-05-15 15:51:09.215594:  
2025-05-15 15:51:09.222148: Epoch 158 
2025-05-15 15:51:09.228163: Current learning rate: 0.00857 
2025-05-15 15:52:57.775561: train_loss -0.8361 
2025-05-15 15:52:57.791650: val_loss -0.8555 
2025-05-15 15:52:57.795672: Pseudo dice [0.8974] 
2025-05-15 15:52:57.807235: Epoch time: 108.57 s 
2025-05-15 15:52:58.809709:  
2025-05-15 15:52:58.814339: Epoch 159 
2025-05-15 15:52:58.821954: Current learning rate: 0.00856 
2025-05-15 15:54:47.304754: train_loss -0.8459 
2025-05-15 15:54:47.322862: val_loss -0.8781 
2025-05-15 15:54:47.324869: Pseudo dice [0.9157] 
2025-05-15 15:54:47.342986: Epoch time: 108.5 s 
2025-05-15 15:54:48.534733:  
2025-05-15 15:54:48.541440: Epoch 160 
2025-05-15 15:54:48.547998: Current learning rate: 0.00855 
2025-05-15 15:56:37.327732: train_loss -0.826 
2025-05-15 15:56:37.339285: val_loss -0.8629 
2025-05-15 15:56:37.347326: Pseudo dice [0.9088] 
2025-05-15 15:56:37.359498: Epoch time: 108.79 s 
2025-05-15 15:56:38.358110:  
2025-05-15 15:56:38.365669: Epoch 161 
2025-05-15 15:56:38.371701: Current learning rate: 0.00854 
2025-05-15 15:58:27.314173: train_loss -0.8293 
2025-05-15 15:58:27.325230: val_loss -0.8644 
2025-05-15 15:58:27.336799: Pseudo dice [0.905] 
2025-05-15 15:58:27.345349: Epoch time: 108.96 s 
2025-05-15 15:58:28.350066:  
2025-05-15 15:58:28.357128: Epoch 162 
2025-05-15 15:58:28.358640: Current learning rate: 0.00853 
2025-05-15 16:00:17.041078: train_loss -0.8382 
2025-05-15 16:00:17.049602: val_loss -0.8671 
2025-05-15 16:00:17.061190: Pseudo dice [0.9066] 
2025-05-15 16:00:17.069709: Epoch time: 108.69 s 
2025-05-15 16:00:18.081867:  
2025-05-15 16:00:18.089387: Epoch 163 
2025-05-15 16:00:18.096429: Current learning rate: 0.00852 
2025-05-15 16:02:06.812276: train_loss -0.8518 
2025-05-15 16:02:06.827901: val_loss -0.8763 
2025-05-15 16:02:06.827901: Pseudo dice [0.9152] 
2025-05-15 16:02:06.843519: Epoch time: 108.73 s 
2025-05-15 16:02:07.853974:  
2025-05-15 16:02:07.853974: Epoch 164 
2025-05-15 16:02:07.871761: Current learning rate: 0.00851 
2025-05-15 16:03:56.308780: train_loss -0.8506 
2025-05-15 16:03:56.313286: val_loss -0.8781 
2025-05-15 16:03:56.313286: Pseudo dice [0.9177] 
2025-05-15 16:03:56.333405: Epoch time: 108.45 s 
2025-05-15 16:03:57.337991:  
2025-05-15 16:03:57.341517: Epoch 165 
2025-05-15 16:03:57.351077: Current learning rate: 0.0085 
2025-05-15 16:05:45.965464: train_loss -0.8516 
2025-05-15 16:05:45.975472: val_loss -0.856 
2025-05-15 16:05:45.985540: Pseudo dice [0.8992] 
2025-05-15 16:05:45.985540: Epoch time: 108.63 s 
2025-05-15 16:05:47.092309:  
2025-05-15 16:05:47.106033: Epoch 166 
2025-05-15 16:05:47.112148: Current learning rate: 0.00849 
2025-05-15 16:07:35.710930: train_loss -0.8295 
2025-05-15 16:07:35.715955: val_loss -0.8545 
2025-05-15 16:07:35.731503: Pseudo dice [0.9015] 
2025-05-15 16:07:35.736538: Epoch time: 108.62 s 
2025-05-15 16:07:36.701726:  
2025-05-15 16:07:36.715265: Epoch 167 
2025-05-15 16:07:36.721340: Current learning rate: 0.00848 
2025-05-15 16:09:25.541959: train_loss -0.8364 
2025-05-15 16:09:25.555526: val_loss -0.8698 
2025-05-15 16:09:25.562593: Pseudo dice [0.9093] 
2025-05-15 16:09:25.574118: Epoch time: 108.84 s 
2025-05-15 16:09:26.556927:  
2025-05-15 16:09:26.564473: Epoch 168 
2025-05-15 16:09:26.567507: Current learning rate: 0.00847 
2025-05-15 16:11:14.968202: train_loss -0.8375 
2025-05-15 16:11:14.975800: val_loss -0.8698 
2025-05-15 16:11:14.988335: Pseudo dice [0.9119] 
2025-05-15 16:11:14.996387: Epoch time: 108.41 s 
2025-05-15 16:11:15.992270:  
2025-05-15 16:11:15.998992: Epoch 169 
2025-05-15 16:11:16.005604: Current learning rate: 0.00847 
2025-05-15 16:13:05.073071: train_loss -0.848 
2025-05-15 16:13:05.083611: val_loss -0.8764 
2025-05-15 16:13:05.093202: Pseudo dice [0.9097] 
2025-05-15 16:13:05.101719: Epoch time: 109.08 s 
2025-05-15 16:13:06.123667:  
2025-05-15 16:13:06.129716: Epoch 170 
2025-05-15 16:13:06.136745: Current learning rate: 0.00846 
2025-05-15 16:14:54.737561: train_loss -0.8477 
2025-05-15 16:14:54.744610: val_loss -0.8838 
2025-05-15 16:14:54.761198: Pseudo dice [0.9171] 
2025-05-15 16:14:54.764709: Epoch time: 108.61 s 
2025-05-15 16:14:55.816587:  
2025-05-15 16:14:55.817669: Epoch 171 
2025-05-15 16:14:55.827714: Current learning rate: 0.00845 
2025-05-15 16:16:44.403717: train_loss -0.8295 
2025-05-15 16:16:44.409995: val_loss -0.8415 
2025-05-15 16:16:44.409995: Pseudo dice [0.8914] 
2025-05-15 16:16:44.430554: Epoch time: 108.59 s 
2025-05-15 16:16:45.560428:  
2025-05-15 16:16:45.567196: Epoch 172 
2025-05-15 16:16:45.572342: Current learning rate: 0.00844 
2025-05-15 16:18:34.205893: train_loss -0.8067 
2025-05-15 16:18:34.208898: val_loss -0.8337 
2025-05-15 16:18:34.221976: Pseudo dice [0.8835] 
2025-05-15 16:18:34.228990: Epoch time: 108.65 s 
2025-05-15 16:18:35.221176:  
2025-05-15 16:18:35.225793: Epoch 173 
2025-05-15 16:18:35.225793: Current learning rate: 0.00843 
2025-05-15 16:20:23.793105: train_loss -0.8364 
2025-05-15 16:20:23.800173: val_loss -0.8786 
2025-05-15 16:20:23.810207: Pseudo dice [0.9151] 
2025-05-15 16:20:23.820266: Epoch time: 108.57 s 
2025-05-15 16:20:24.812560:  
2025-05-15 16:20:24.817078: Epoch 174 
2025-05-15 16:20:24.827599: Current learning rate: 0.00842 
2025-05-15 16:22:13.765562: train_loss -0.8401 
2025-05-15 16:22:13.780646: val_loss -0.8646 
2025-05-15 16:22:13.785669: Pseudo dice [0.9058] 
2025-05-15 16:22:13.797720: Epoch time: 108.95 s 
2025-05-15 16:22:14.789281:  
2025-05-15 16:22:14.797066: Epoch 175 
2025-05-15 16:22:14.799659: Current learning rate: 0.00841 
2025-05-15 16:24:03.396439: train_loss -0.8343 
2025-05-15 16:24:03.411488: val_loss -0.8579 
2025-05-15 16:24:03.417534: Pseudo dice [0.8989] 
2025-05-15 16:24:03.428074: Epoch time: 108.61 s 
2025-05-15 16:24:04.423009:  
2025-05-15 16:24:04.432060: Epoch 176 
2025-05-15 16:24:04.438111: Current learning rate: 0.0084 
2025-05-15 16:25:52.963900: train_loss -0.8526 
2025-05-15 16:25:52.976941: val_loss -0.873 
2025-05-15 16:25:52.983976: Pseudo dice [0.9096] 
2025-05-15 16:25:52.997409: Epoch time: 108.54 s 
2025-05-15 16:25:53.996449:  
2025-05-15 16:25:54.002964: Epoch 177 
2025-05-15 16:25:54.012603: Current learning rate: 0.00839 
2025-05-15 16:27:42.757394: train_loss -0.8497 
2025-05-15 16:27:42.762924: val_loss -0.8495 
2025-05-15 16:27:42.776996: Pseudo dice [0.8986] 
2025-05-15 16:27:42.783034: Epoch time: 108.76 s 
2025-05-15 16:27:43.907411:  
2025-05-15 16:27:43.914582: Epoch 178 
2025-05-15 16:27:43.923309: Current learning rate: 0.00838 
2025-05-15 16:29:32.389964: train_loss -0.8557 
2025-05-15 16:29:32.393471: val_loss -0.8802 
2025-05-15 16:29:32.408040: Pseudo dice [0.9156] 
2025-05-15 16:29:32.413572: Epoch time: 108.48 s 
2025-05-15 16:29:33.401057:  
2025-05-15 16:29:33.408916: Epoch 179 
2025-05-15 16:29:33.408916: Current learning rate: 0.00837 
2025-05-15 16:31:22.123283: train_loss -0.8581 
2025-05-15 16:31:22.125302: val_loss -0.8814 
2025-05-15 16:31:22.139395: Pseudo dice [0.9189] 
2025-05-15 16:31:22.145452: Epoch time: 108.72 s 
2025-05-15 16:31:23.137762:  
2025-05-15 16:31:23.137762: Epoch 180 
2025-05-15 16:31:23.151825: Current learning rate: 0.00836 
2025-05-15 16:33:11.831692: train_loss -0.855 
2025-05-15 16:33:11.846827: val_loss -0.8666 
2025-05-15 16:33:11.851845: Pseudo dice [0.9085] 
2025-05-15 16:33:11.860899: Epoch time: 108.69 s 
2025-05-15 16:33:12.848873:  
2025-05-15 16:33:12.864058: Epoch 181 
2025-05-15 16:33:12.869175: Current learning rate: 0.00836 
2025-05-15 16:35:01.382851: train_loss -0.8598 
2025-05-15 16:35:01.396420: val_loss -0.8913 
2025-05-15 16:35:01.403445: Pseudo dice [0.9238] 
2025-05-15 16:35:01.409489: Epoch time: 108.53 s 
2025-05-15 16:35:02.419105:  
2025-05-15 16:35:02.434472: Epoch 182 
2025-05-15 16:35:02.444224: Current learning rate: 0.00835 
2025-05-15 16:36:51.031091: train_loss -0.8641 
2025-05-15 16:36:51.037624: val_loss -0.8879 
2025-05-15 16:36:51.051684: Pseudo dice [0.9248] 
2025-05-15 16:36:51.057717: Epoch time: 108.61 s 
2025-05-15 16:36:51.057717: Yayy! New best EMA pseudo Dice: 0.9106 
2025-05-15 16:36:52.420863:  
2025-05-15 16:36:52.424937: Epoch 183 
2025-05-15 16:36:52.424937: Current learning rate: 0.00834 
2025-05-15 16:38:41.099976: train_loss -0.8673 
2025-05-15 16:38:41.110043: val_loss -0.8917 
2025-05-15 16:38:41.116580: Pseudo dice [0.9237] 
2025-05-15 16:38:41.124131: Epoch time: 108.68 s 
2025-05-15 16:38:41.130649: Yayy! New best EMA pseudo Dice: 0.9119 
2025-05-15 16:38:42.584709:  
2025-05-15 16:38:42.595784: Epoch 184 
2025-05-15 16:38:42.601847: Current learning rate: 0.00833 
2025-05-15 16:40:31.400188: train_loss -0.8531 
2025-05-15 16:40:31.413735: val_loss -0.8833 
2025-05-15 16:40:31.420249: Pseudo dice [0.9164] 
2025-05-15 16:40:31.420249: Epoch time: 108.82 s 
2025-05-15 16:40:31.433816: Yayy! New best EMA pseudo Dice: 0.9124 
2025-05-15 16:40:32.774895:  
2025-05-15 16:40:32.783785: Epoch 185 
2025-05-15 16:40:32.783785: Current learning rate: 0.00832 
2025-05-15 16:42:21.523680: train_loss -0.8597 
2025-05-15 16:42:21.532758: val_loss -0.8852 
2025-05-15 16:42:21.539850: Pseudo dice [0.9215] 
2025-05-15 16:42:21.549395: Epoch time: 108.75 s 
2025-05-15 16:42:21.558973: Yayy! New best EMA pseudo Dice: 0.9133 
2025-05-15 16:42:22.900043:  
2025-05-15 16:42:22.903558: Epoch 186 
2025-05-15 16:42:22.912083: Current learning rate: 0.00831 
2025-05-15 16:44:11.519140: train_loss -0.8703 
2025-05-15 16:44:11.527204: val_loss -0.895 
2025-05-15 16:44:11.539262: Pseudo dice [0.9259] 
2025-05-15 16:44:11.547342: Epoch time: 108.62 s 
2025-05-15 16:44:11.551849: Yayy! New best EMA pseudo Dice: 0.9145 
2025-05-15 16:44:12.917944:  
2025-05-15 16:44:12.925992: Epoch 187 
2025-05-15 16:44:12.932042: Current learning rate: 0.0083 
2025-05-15 16:46:01.407555: train_loss -0.858 
2025-05-15 16:46:01.417166: val_loss -0.8824 
2025-05-15 16:46:01.425203: Pseudo dice [0.9188] 
2025-05-15 16:46:01.432239: Epoch time: 108.49 s 
2025-05-15 16:46:01.437752: Yayy! New best EMA pseudo Dice: 0.915 
2025-05-15 16:46:02.794143:  
2025-05-15 16:46:02.802366: Epoch 188 
2025-05-15 16:46:02.808017: Current learning rate: 0.00829 
2025-05-15 16:47:51.325108: train_loss -0.8658 
2025-05-15 16:47:51.327641: val_loss -0.8936 
2025-05-15 16:47:51.338163: Pseudo dice [0.925] 
2025-05-15 16:47:51.347769: Epoch time: 108.53 s 
2025-05-15 16:47:51.358308: Yayy! New best EMA pseudo Dice: 0.916 
2025-05-15 16:47:52.705906:  
2025-05-15 16:47:52.705906: Epoch 189 
2025-05-15 16:47:52.725953: Current learning rate: 0.00828 
2025-05-15 16:49:41.820508: train_loss -0.8625 
2025-05-15 16:49:41.834621: val_loss -0.8877 
2025-05-15 16:49:41.840627: Pseudo dice [0.9217] 
2025-05-15 16:49:41.849698: Epoch time: 109.11 s 
2025-05-15 16:49:41.854748: Yayy! New best EMA pseudo Dice: 0.9165 
2025-05-15 16:49:43.328016:  
2025-05-15 16:49:43.339749: Epoch 190 
2025-05-15 16:49:43.344937: Current learning rate: 0.00827 
2025-05-15 16:51:31.995311: train_loss -0.8549 
2025-05-15 16:51:32.006854: val_loss -0.8794 
2025-05-15 16:51:32.015423: Pseudo dice [0.9192] 
2025-05-15 16:51:32.026973: Epoch time: 108.67 s 
2025-05-15 16:51:32.035515: Yayy! New best EMA pseudo Dice: 0.9168 
2025-05-15 16:51:33.378776:  
2025-05-15 16:51:33.378776: Epoch 191 
2025-05-15 16:51:33.391884: Current learning rate: 0.00826 
2025-05-15 16:53:22.172377: train_loss -0.8599 
2025-05-15 16:53:22.185945: val_loss -0.8888 
2025-05-15 16:53:22.192516: Pseudo dice [0.9221] 
2025-05-15 16:53:22.204090: Epoch time: 108.79 s 
2025-05-15 16:53:22.212138: Yayy! New best EMA pseudo Dice: 0.9173 
2025-05-15 16:53:23.568985:  
2025-05-15 16:53:23.575524: Epoch 192 
2025-05-15 16:53:23.577034: Current learning rate: 0.00825 
2025-05-15 16:55:12.287474: train_loss -0.8638 
2025-05-15 16:55:12.295020: val_loss -0.8814 
2025-05-15 16:55:12.308075: Pseudo dice [0.9161] 
2025-05-15 16:55:12.315166: Epoch time: 108.72 s 
2025-05-15 16:55:13.338030:  
2025-05-15 16:55:13.353585: Epoch 193 
2025-05-15 16:55:13.358107: Current learning rate: 0.00824 
2025-05-15 16:57:02.464959: train_loss -0.8626 
2025-05-15 16:57:02.468990: val_loss -0.8889 
2025-05-15 16:57:02.485572: Pseudo dice [0.9253] 
2025-05-15 16:57:02.489097: Epoch time: 109.13 s 
2025-05-15 16:57:02.489097: Yayy! New best EMA pseudo Dice: 0.918 
2025-05-15 16:57:03.844735:  
2025-05-15 16:57:03.849505: Epoch 194 
2025-05-15 16:57:03.849505: Current learning rate: 0.00824 
2025-05-15 16:58:52.589760: train_loss -0.8655 
2025-05-15 16:58:52.594285: val_loss -0.8837 
2025-05-15 16:58:52.608841: Pseudo dice [0.919] 
2025-05-15 16:58:52.614394: Epoch time: 108.75 s 
2025-05-15 16:58:52.614394: Yayy! New best EMA pseudo Dice: 0.9181 
2025-05-15 16:58:53.982223:  
2025-05-15 16:58:53.990843: Epoch 195 
2025-05-15 16:58:53.998008: Current learning rate: 0.00823 
2025-05-15 17:00:42.619472: train_loss -0.8602 
2025-05-15 17:00:42.623980: val_loss -0.8861 
2025-05-15 17:00:42.632034: Pseudo dice [0.9217] 
2025-05-15 17:00:42.644102: Epoch time: 108.64 s 
2025-05-15 17:00:42.650654: Yayy! New best EMA pseudo Dice: 0.9185 
2025-05-15 17:00:44.012749:  
2025-05-15 17:00:44.015271: Epoch 196 
2025-05-15 17:00:44.023335: Current learning rate: 0.00822 
2025-05-15 17:02:33.038104: train_loss -0.8492 
2025-05-15 17:02:33.045630: val_loss -0.8849 
2025-05-15 17:02:33.046641: Pseudo dice [0.9213] 
2025-05-15 17:02:33.058204: Epoch time: 109.03 s 
2025-05-15 17:02:33.066735: Yayy! New best EMA pseudo Dice: 0.9188 
2025-05-15 17:02:34.413977:  
2025-05-15 17:02:34.422063: Epoch 197 
2025-05-15 17:02:34.428080: Current learning rate: 0.00821 
2025-05-15 17:04:23.071822: train_loss -0.8562 
2025-05-15 17:04:23.082332: val_loss -0.885 
2025-05-15 17:04:23.090895: Pseudo dice [0.9187] 
2025-05-15 17:04:23.091918: Epoch time: 108.66 s 
2025-05-15 17:04:24.096328:  
2025-05-15 17:04:24.099900: Epoch 198 
2025-05-15 17:04:24.109574: Current learning rate: 0.0082 
2025-05-15 17:06:12.781558: train_loss -0.8395 
2025-05-15 17:06:12.793618: val_loss -0.8621 
2025-05-15 17:06:12.801651: Pseudo dice [0.9062] 
2025-05-15 17:06:12.810704: Epoch time: 108.69 s 
2025-05-15 17:06:13.815884:  
2025-05-15 17:06:13.820456: Epoch 199 
2025-05-15 17:06:13.820456: Current learning rate: 0.00819 
2025-05-15 17:08:02.577117: train_loss -0.8383 
2025-05-15 17:08:02.594691: val_loss -0.8823 
2025-05-15 17:08:02.599713: Pseudo dice [0.9214] 
2025-05-15 17:08:02.614283: Epoch time: 108.76 s 
2025-05-15 17:08:04.109892:  
2025-05-15 17:08:04.109892: Epoch 200 
2025-05-15 17:08:04.125789: Current learning rate: 0.00818 
2025-05-15 17:09:53.108918: train_loss -0.8489 
2025-05-15 17:09:53.108918: val_loss -0.8894 
2025-05-15 17:09:53.129496: Pseudo dice [0.9215] 
2025-05-15 17:09:53.129496: Epoch time: 109.0 s 
2025-05-15 17:09:54.134384:  
2025-05-15 17:09:54.147628: Epoch 201 
2025-05-15 17:09:54.148637: Current learning rate: 0.00817 
2025-05-15 17:11:42.829628: train_loss -0.8602 
2025-05-15 17:11:42.838149: val_loss -0.881 
2025-05-15 17:11:42.845719: Pseudo dice [0.9217] 
2025-05-15 17:11:42.853254: Epoch time: 108.7 s 
2025-05-15 17:11:43.972390:  
2025-05-15 17:11:43.978917: Epoch 202 
2025-05-15 17:11:43.988457: Current learning rate: 0.00816 
2025-05-15 17:13:32.724708: train_loss -0.8643 
2025-05-15 17:13:32.741787: val_loss -0.8908 
2025-05-15 17:13:32.744804: Pseudo dice [0.9246] 
2025-05-15 17:13:32.756343: Epoch time: 108.75 s 
2025-05-15 17:13:32.764877: Yayy! New best EMA pseudo Dice: 0.9192 
2025-05-15 17:13:34.115825:  
2025-05-15 17:13:34.124368: Epoch 203 
2025-05-15 17:13:34.130415: Current learning rate: 0.00815 
2025-05-15 17:15:22.804903: train_loss -0.8681 
2025-05-15 17:15:22.813925: val_loss -0.8924 
2025-05-15 17:15:22.817931: Pseudo dice [0.9247] 
2025-05-15 17:15:22.854153: Epoch time: 108.69 s 
2025-05-15 17:15:22.858161: Yayy! New best EMA pseudo Dice: 0.9198 
2025-05-15 17:15:24.214167:  
2025-05-15 17:15:24.214167: Epoch 204 
2025-05-15 17:15:24.214167: Current learning rate: 0.00814 
2025-05-15 17:17:13.296656: train_loss -0.8605 
2025-05-15 17:17:13.305188: val_loss -0.8777 
2025-05-15 17:17:13.314229: Pseudo dice [0.9148] 
2025-05-15 17:17:13.323755: Epoch time: 109.08 s 
2025-05-15 17:17:14.329953:  
2025-05-15 17:17:14.329953: Epoch 205 
2025-05-15 17:17:14.343596: Current learning rate: 0.00813 
2025-05-15 17:19:03.227247: train_loss -0.8397 
2025-05-15 17:19:03.240331: val_loss -0.7718 
2025-05-15 17:19:03.247359: Pseudo dice [0.833] 
2025-05-15 17:19:03.247359: Epoch time: 108.9 s 
2025-05-15 17:19:04.195796:  
2025-05-15 17:19:04.202830: Epoch 206 
2025-05-15 17:19:04.210372: Current learning rate: 0.00813 
2025-05-15 17:20:53.000340: train_loss -0.8255 
2025-05-15 17:20:53.013928: val_loss -0.8801 
2025-05-15 17:20:53.020445: Pseudo dice [0.9141] 
2025-05-15 17:20:53.034035: Epoch time: 108.8 s 
2025-05-15 17:20:54.020538:  
2025-05-15 17:20:54.027081: Epoch 207 
2025-05-15 17:20:54.040667: Current learning rate: 0.00812 
2025-05-15 17:22:42.925115: train_loss -0.8494 
2025-05-15 17:22:42.933664: val_loss -0.8856 
2025-05-15 17:22:42.940195: Pseudo dice [0.9226] 
2025-05-15 17:22:42.945704: Epoch time: 108.91 s 
2025-05-15 17:22:44.019226:  
2025-05-15 17:22:44.034783: Epoch 208 
2025-05-15 17:22:44.039342: Current learning rate: 0.00811 
2025-05-15 17:24:32.813619: train_loss -0.8337 
2025-05-15 17:24:32.830179: val_loss -0.8687 
2025-05-15 17:24:32.833713: Pseudo dice [0.906] 
2025-05-15 17:24:32.852976: Epoch time: 108.79 s 
2025-05-15 17:24:33.808845:  
2025-05-15 17:24:33.815857: Epoch 209 
2025-05-15 17:24:33.822909: Current learning rate: 0.0081 
2025-05-15 17:26:22.365602: train_loss -0.8471 
2025-05-15 17:26:22.371123: val_loss -0.8753 
2025-05-15 17:26:22.385696: Pseudo dice [0.9171] 
2025-05-15 17:26:22.391218: Epoch time: 108.56 s 
2025-05-15 17:26:23.342381:  
2025-05-15 17:26:23.343892: Epoch 210 
2025-05-15 17:26:23.359010: Current learning rate: 0.00809 
2025-05-15 17:28:12.453691: train_loss -0.8351 
2025-05-15 17:28:12.462735: val_loss -0.8501 
2025-05-15 17:28:12.471292: Pseudo dice [0.8986] 
2025-05-15 17:28:12.474802: Epoch time: 109.11 s 
2025-05-15 17:28:13.411262:  
2025-05-15 17:28:13.411262: Epoch 211 
2025-05-15 17:28:13.424913: Current learning rate: 0.00808 
2025-05-15 17:30:02.095351: train_loss -0.8234 
2025-05-15 17:30:02.098862: val_loss -0.8631 
2025-05-15 17:30:02.115962: Pseudo dice [0.9059] 
2025-05-15 17:30:02.118968: Epoch time: 108.68 s 
2025-05-15 17:30:03.061687:  
2025-05-15 17:30:03.073459: Epoch 212 
2025-05-15 17:30:03.075996: Current learning rate: 0.00807 
2025-05-15 17:31:51.911788: train_loss -0.835 
2025-05-15 17:31:51.922373: val_loss -0.8699 
2025-05-15 17:31:51.927389: Pseudo dice [0.9132] 
2025-05-15 17:31:51.931905: Epoch time: 108.85 s 
2025-05-15 17:31:52.883326:  
2025-05-15 17:31:52.886862: Epoch 213 
2025-05-15 17:31:52.896571: Current learning rate: 0.00806 
2025-05-15 17:33:41.560561: train_loss -0.8575 
2025-05-15 17:33:41.567571: val_loss -0.879 
2025-05-15 17:33:41.578629: Pseudo dice [0.9181] 
2025-05-15 17:33:41.587666: Epoch time: 108.68 s 
2025-05-15 17:33:42.530713:  
2025-05-15 17:33:42.536852: Epoch 214 
2025-05-15 17:33:42.543864: Current learning rate: 0.00805 
2025-05-15 17:35:31.201438: train_loss -0.8673 
2025-05-15 17:35:31.206462: val_loss -0.8852 
2025-05-15 17:35:31.219015: Pseudo dice [0.919] 
2025-05-15 17:35:31.226542: Epoch time: 108.68 s 
2025-05-15 17:35:32.310299:  
2025-05-15 17:35:32.313816: Epoch 215 
2025-05-15 17:35:32.324468: Current learning rate: 0.00804 
2025-05-15 17:37:21.116802: train_loss -0.8595 
2025-05-15 17:37:21.124867: val_loss -0.8863 
2025-05-15 17:37:21.135391: Pseudo dice [0.9231] 
2025-05-15 17:37:21.144454: Epoch time: 108.81 s 
2025-05-15 17:37:22.111698:  
2025-05-15 17:37:22.111698: Epoch 216 
2025-05-15 17:37:22.126473: Current learning rate: 0.00803 
2025-05-15 17:39:10.810416: train_loss -0.8653 
2025-05-15 17:39:10.817441: val_loss -0.8909 
2025-05-15 17:39:10.830505: Pseudo dice [0.9244] 
2025-05-15 17:39:10.837543: Epoch time: 108.7 s 
2025-05-15 17:39:11.815459:  
2025-05-15 17:39:11.831081: Epoch 217 
2025-05-15 17:39:11.841480: Current learning rate: 0.00802 
2025-05-15 17:41:00.583210: train_loss -0.8721 
2025-05-15 17:41:00.583210: val_loss -0.9002 
2025-05-15 17:41:00.597820: Pseudo dice [0.9284] 
2025-05-15 17:41:00.603827: Epoch time: 108.77 s 
2025-05-15 17:41:01.542603:  
2025-05-15 17:41:01.555182: Epoch 218 
2025-05-15 17:41:01.562708: Current learning rate: 0.00801 
2025-05-15 17:42:50.268573: train_loss -0.8629 
2025-05-15 17:42:50.281628: val_loss -0.8663 
2025-05-15 17:42:50.288668: Pseudo dice [0.9065] 
2025-05-15 17:42:50.298208: Epoch time: 108.73 s 
2025-05-15 17:42:51.238672:  
2025-05-15 17:42:51.239679: Epoch 219 
2025-05-15 17:42:51.251699: Current learning rate: 0.00801 
2025-05-15 17:44:39.919422: train_loss -0.8173 
2025-05-15 17:44:39.919422: val_loss -0.8571 
2025-05-15 17:44:39.932507: Pseudo dice [0.9019] 
2025-05-15 17:44:39.939521: Epoch time: 108.68 s 
2025-05-15 17:44:40.881991:  
2025-05-15 17:44:40.891316: Epoch 220 
2025-05-15 17:44:40.894861: Current learning rate: 0.008 
2025-05-15 17:46:29.876940: train_loss -0.8218 
2025-05-15 17:46:29.876940: val_loss -0.8579 
2025-05-15 17:46:29.897048: Pseudo dice [0.9066] 
2025-05-15 17:46:29.897048: Epoch time: 108.99 s 
2025-05-15 17:46:30.977112:  
2025-05-15 17:46:30.983630: Epoch 221 
2025-05-15 17:46:30.989661: Current learning rate: 0.00799 
2025-05-15 17:48:19.894228: train_loss -0.8378 
2025-05-15 17:48:19.905301: val_loss -0.8883 
2025-05-15 17:48:19.906310: Pseudo dice [0.92] 
2025-05-15 17:48:19.914355: Epoch time: 108.92 s 
2025-05-15 17:48:20.859721:  
2025-05-15 17:48:20.867013: Epoch 222 
2025-05-15 17:48:20.872048: Current learning rate: 0.00798 
2025-05-15 17:50:10.043489: train_loss -0.8521 
2025-05-15 17:50:10.051525: val_loss -0.8772 
2025-05-15 17:50:10.063073: Pseudo dice [0.9138] 
2025-05-15 17:50:10.070105: Epoch time: 109.18 s 
2025-05-15 17:50:11.021789:  
2025-05-15 17:50:11.028871: Epoch 223 
2025-05-15 17:50:11.035903: Current learning rate: 0.00797 
2025-05-15 17:51:59.829326: train_loss -0.8531 
2025-05-15 17:51:59.835334: val_loss -0.871 
2025-05-15 17:51:59.849439: Pseudo dice [0.9123] 
2025-05-15 17:51:59.855448: Epoch time: 108.81 s 
2025-05-15 17:52:00.801852:  
2025-05-15 17:52:00.810876: Epoch 224 
2025-05-15 17:52:00.818959: Current learning rate: 0.00796 
2025-05-15 17:53:49.640890: train_loss -0.8278 
2025-05-15 17:53:49.649915: val_loss -0.8438 
2025-05-15 17:53:49.649915: Pseudo dice [0.8973] 
2025-05-15 17:53:49.661472: Epoch time: 108.84 s 
2025-05-15 17:53:50.602276:  
2025-05-15 17:53:50.607789: Epoch 225 
2025-05-15 17:53:50.619381: Current learning rate: 0.00795 
2025-05-15 17:55:39.485336: train_loss -0.8376 
2025-05-15 17:55:39.496896: val_loss -0.8771 
2025-05-15 17:55:39.504926: Pseudo dice [0.9147] 
2025-05-15 17:55:39.510461: Epoch time: 108.88 s 
2025-05-15 17:55:40.443938:  
2025-05-15 17:55:40.450994: Epoch 226 
2025-05-15 17:55:40.451501: Current learning rate: 0.00794 
2025-05-15 17:57:29.211599: train_loss -0.8488 
2025-05-15 17:57:29.213607: val_loss -0.8633 
2025-05-15 17:57:29.213607: Pseudo dice [0.9049] 
2025-05-15 17:57:29.233685: Epoch time: 108.77 s 
2025-05-15 17:57:30.164674:  
2025-05-15 17:57:30.177374: Epoch 227 
2025-05-15 17:57:30.181412: Current learning rate: 0.00793 
2025-05-15 17:59:18.720975: train_loss -0.8481 
2025-05-15 17:59:18.728993: val_loss -0.8771 
2025-05-15 17:59:18.741086: Pseudo dice [0.917] 
2025-05-15 17:59:18.749104: Epoch time: 108.56 s 
2025-05-15 17:59:19.819544:  
2025-05-15 17:59:19.829575: Epoch 228 
2025-05-15 17:59:19.836114: Current learning rate: 0.00792 
2025-05-15 18:01:08.685940: train_loss -0.8584 
2025-05-15 18:01:08.728651: val_loss -0.8878 
2025-05-15 18:01:08.735165: Pseudo dice [0.9224] 
2025-05-15 18:01:08.735165: Epoch time: 108.87 s 
2025-05-15 18:01:09.666107:  
2025-05-15 18:01:09.670721: Epoch 229 
2025-05-15 18:01:09.678783: Current learning rate: 0.00791 
2025-05-15 18:02:58.647633: train_loss -0.8538 
2025-05-15 18:02:58.653156: val_loss -0.8509 
2025-05-15 18:02:58.664201: Pseudo dice [0.8963] 
2025-05-15 18:02:58.669738: Epoch time: 108.98 s 
2025-05-15 18:02:59.607723:  
2025-05-15 18:02:59.615795: Epoch 230 
2025-05-15 18:02:59.620872: Current learning rate: 0.0079 
2025-05-15 18:04:48.456512: train_loss -0.8355 
2025-05-15 18:04:48.456512: val_loss -0.87 
2025-05-15 18:04:48.471067: Pseudo dice [0.9108] 
2025-05-15 18:04:48.476615: Epoch time: 108.85 s 
2025-05-15 18:04:49.404435:  
2025-05-15 18:04:49.414218: Epoch 231 
2025-05-15 18:04:49.414218: Current learning rate: 0.00789 
2025-05-15 18:06:38.420741: train_loss -0.8479 
2025-05-15 18:06:38.440850: val_loss -0.8862 
2025-05-15 18:06:38.440850: Pseudo dice [0.9195] 
2025-05-15 18:06:38.461002: Epoch time: 109.02 s 
2025-05-15 18:06:39.391308:  
2025-05-15 18:06:39.396374: Epoch 232 
2025-05-15 18:06:39.396374: Current learning rate: 0.00789 
2025-05-15 18:08:28.257408: train_loss -0.8642 
2025-05-15 18:08:28.268989: val_loss -0.8977 
2025-05-15 18:08:28.277504: Pseudo dice [0.9272] 
2025-05-15 18:08:28.277504: Epoch time: 108.87 s 
2025-05-15 18:08:29.210430:  
2025-05-15 18:08:29.223514: Epoch 233 
2025-05-15 18:08:29.225168: Current learning rate: 0.00788 
2025-05-15 18:10:17.949164: train_loss -0.868 
2025-05-15 18:10:17.969728: val_loss -0.888 
2025-05-15 18:10:17.969728: Pseudo dice [0.9254] 
2025-05-15 18:10:17.989310: Epoch time: 108.74 s 
2025-05-15 18:10:19.039371:  
2025-05-15 18:10:19.048443: Epoch 234 
2025-05-15 18:10:19.051452: Current learning rate: 0.00787 
2025-05-15 18:12:07.981253: train_loss -0.8646 
2025-05-15 18:12:07.982769: val_loss -0.8915 
2025-05-15 18:12:07.999328: Pseudo dice [0.9278] 
2025-05-15 18:12:08.002863: Epoch time: 108.94 s 
2025-05-15 18:12:08.934623:  
2025-05-15 18:12:08.939721: Epoch 235 
2025-05-15 18:12:08.945249: Current learning rate: 0.00786 
2025-05-15 18:13:57.722235: train_loss -0.8341 
2025-05-15 18:13:57.729751: val_loss -0.8614 
2025-05-15 18:13:57.729751: Pseudo dice [0.9115] 
2025-05-15 18:13:57.749846: Epoch time: 108.79 s 
2025-05-15 18:13:58.683774:  
2025-05-15 18:13:58.688795: Epoch 236 
2025-05-15 18:13:58.688795: Current learning rate: 0.00785 
2025-05-15 18:15:47.506366: train_loss -0.8432 
2025-05-15 18:15:47.515932: val_loss -0.8878 
2025-05-15 18:15:47.520947: Pseudo dice [0.9228] 
2025-05-15 18:15:47.533578: Epoch time: 108.82 s 
2025-05-15 18:15:48.462799:  
2025-05-15 18:15:48.470876: Epoch 237 
2025-05-15 18:15:48.475894: Current learning rate: 0.00784 
2025-05-15 18:17:37.385038: train_loss -0.8612 
2025-05-15 18:17:37.396110: val_loss -0.8813 
2025-05-15 18:17:37.402642: Pseudo dice [0.9162] 
2025-05-15 18:17:37.410721: Epoch time: 108.92 s 
2025-05-15 18:17:38.341347:  
2025-05-15 18:17:38.348421: Epoch 238 
2025-05-15 18:17:38.354949: Current learning rate: 0.00783