diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..c4dd81d8a0c57295fd1907e756f92bca3c5885a0 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/progress.png filter=lfs diff=lfs merge=lfs -text +Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/progress.png filter=lfs diff=lfs merge=lfs -text +Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/progress.png filter=lfs diff=lfs merge=lfs -text +Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/progress.png filter=lfs diff=lfs merge=lfs -text +Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/progress.png filter=lfs diff=lfs merge=lfs -text diff --git a/Dataset002_zebrafish/.DS_Store b/Dataset002_zebrafish/.DS_Store new file mode 100644 index 0000000000000000000000000000000000000000..4db6197538106c2537e3d9252dfe1b67e8061deb Binary files /dev/null and b/Dataset002_zebrafish/.DS_Store differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/.DS_Store b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/.DS_Store new file mode 100644 index 0000000000000000000000000000000000000000..d9666c29d7a3681cf027203acb0a95b03e52f40f Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/.DS_Store differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/dataset.json b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/dataset.json new file mode 100644 index 0000000000000000000000000000000000000000..ef894f450f2b26f27430d9b748912216f05082ca --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/dataset.json @@ -0,0 +1,14 @@ +{ + "channel_names": { + "0": "\u00b5OCT" + }, + "labels": { + "background": 0, + "Retina": 1, + "VCD": 2, + "lens": 3, + "cornea": 4 + }, + "numTraining": 108, + "file_ending": ".png" +} \ No newline at end of file diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/dataset_fingerprint.json b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/dataset_fingerprint.json new file mode 100644 index 0000000000000000000000000000000000000000..be8fe86c9b9d4d583aa3bac5844a6b9887746d97 --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/dataset_fingerprint.json @@ -0,0 +1,1098 @@ +{ + "foreground_intensity_properties_per_channel": { + "0": { + "max": 255.0, + "mean": 49.659568786621094, + "median": 45.0, + "min": 0.0, + "percentile_00_5": 10.0, + "percentile_99_5": 163.0, + "std": 24.689043045043945 + } + }, + "median_relative_size_after_cropping": 1.0, + "shapes_after_crop": [ + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ], + [ + 1, + 1024, + 102 + ] + ], + "spacings": [ + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ], + [ + 999, + 1, + 1 + ] + ] +} \ No newline at end of file diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/checkpoint_best.pth b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/checkpoint_best.pth new file mode 100644 index 0000000000000000000000000000000000000000..1ecd0335a12b7bd11da78bb4dc38fc211c40ade2 --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/checkpoint_best.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c85bc96f2ed20c7a56bf57156f9b351e4ae16ebc903b697d3135e26b93b4d02a +size 358248962 diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/checkpoint_final.pth b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/checkpoint_final.pth new file mode 100644 index 0000000000000000000000000000000000000000..a7b2080ac2c0ace26fe3b61bb5b5eb1f2f283327 --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/checkpoint_final.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1775baebd76cdfb8fd659bb14964bfadb041781f0b332b342b99c69fdf5daae9 +size 358731182 diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/debug.json b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/debug.json new file mode 100644 index 0000000000000000000000000000000000000000..a4e636ae18eeada7e1c11ebdf0704cb62e7fcc84 --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/debug.json @@ -0,0 +1,53 @@ +{ + "_best_ema": "None", + "batch_size": "5", + "configuration_manager": "{'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 5, 'patch_size': [1024, 112], 'median_image_size_in_voxels': [1024.0, 102.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['ZScoreNormalization'], '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': 8, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 1], [2, 1], [2, 1]], 'n_conv_per_stage': [2, 2, 2, 2, 2, 2, 2, 2], 'n_conv_per_stage_decoder': [2, 2, 2, 2, 2, 2, 2], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}", + "configuration_name": "2d", + "cudnn_version": 90100, + "current_epoch": "0", + "dataloader_train": "", + "dataloader_train.generator": "", + "dataloader_train.num_processes": "12", + "dataloader_train.transform": "None", + "dataloader_val": "", + "dataloader_val.generator": "", + "dataloader_val.num_processes": "6", + "dataloader_val.transform": "None", + "dataset_json": "{'channel_names': {'0': '\u00b5OCT'}, 'labels': {'background': 0, 'Retina': 1, 'VCD': 2, 'lens': 3, 'cornea': 4}, 'numTraining': 108, 'file_ending': '.png'}", + "device": "cuda:0", + "disable_checkpointing": "False", + "enable_deep_supervision": "True", + "fold": "0", + "folder_with_segs_from_previous_stage": "None", + "gpu_name": "NVIDIA A100 80GB PCIe", + "grad_scaler": "", + "hostname": "hpc5", + "inference_allowed_mirroring_axes": "(0, 1)", + "initial_lr": "0.01", + "is_cascaded": "False", + "is_ddp": "False", + "label_manager": "", + "local_rank": "0", + "log_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/training_log_2025_10_30_08_33_14.txt", + "logger": "", + "loss": "DeepSupervisionWrapper(\n (loss): DC_and_CE_loss(\n (ce): RobustCrossEntropyLoss()\n (dc): OptimizedModule(\n (_orig_mod): MemoryEfficientSoftDiceLoss()\n )\n )\n)", + "lr_scheduler": "", + "my_init_kwargs": "{'plans': {'dataset_name': 'Dataset001_zebrafish', 'plans_name': 'nnUNetPlans', 'original_median_spacing_after_transp': [999.0, 1.0, 1.0], 'original_median_shape_after_transp': [1, 1024, 102], 'image_reader_writer': 'NaturalImage2DIO', 'transpose_forward': [0, 1, 2], 'transpose_backward': [0, 1, 2], 'configurations': {'2d': {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 5, 'patch_size': [1024, 112], 'median_image_size_in_voxels': [1024.0, 102.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['ZScoreNormalization'], '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': 8, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 1], [2, 1], [2, 1]], 'n_conv_per_stage': [2, 2, 2, 2, 2, 2, 2, 2], 'n_conv_per_stage_decoder': [2, 2, 2, 2, 2, 2, 2], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}}, 'experiment_planner_used': 'ExperimentPlanner', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 255.0, 'mean': 49.659568786621094, 'median': 45.0, 'min': 0.0, 'percentile_00_5': 10.0, 'percentile_99_5': 163.0, 'std': 24.689043045043945}}}, 'configuration': '2d', 'fold': 0, 'dataset_json': {'channel_names': {'0': '\u00b5OCT'}, 'labels': {'background': 0, 'Retina': 1, 'VCD': 2, 'lens': 3, 'cornea': 4}, 'numTraining': 108, 'file_ending': '.png'}, 'device': device(type='cuda')}", + "network": "OptimizedModule", + "num_epochs": "1000", + "num_input_channels": "1", + "num_iterations_per_epoch": "250", + "num_val_iterations_per_epoch": "50", + "optimizer": "SGD (\nParameter Group 0\n dampening: 0\n differentiable: False\n foreach: None\n fused: None\n initial_lr: 0.01\n lr: 0.01\n maximize: False\n momentum: 0.99\n nesterov: True\n weight_decay: 3e-05\n)", + "output_folder": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0", + "output_folder_base": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d", + "oversample_foreground_percent": "0.33", + "plans_manager": "{'dataset_name': 'Dataset001_zebrafish', 'plans_name': 'nnUNetPlans', 'original_median_spacing_after_transp': [999.0, 1.0, 1.0], 'original_median_shape_after_transp': [1, 1024, 102], 'image_reader_writer': 'NaturalImage2DIO', 'transpose_forward': [0, 1, 2], 'transpose_backward': [0, 1, 2], 'configurations': {'2d': {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 5, 'patch_size': [1024, 112], 'median_image_size_in_voxels': [1024.0, 102.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['ZScoreNormalization'], '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': 8, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 1], [2, 1], [2, 1]], 'n_conv_per_stage': [2, 2, 2, 2, 2, 2, 2, 2], 'n_conv_per_stage_decoder': [2, 2, 2, 2, 2, 2, 2], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}}, 'experiment_planner_used': 'ExperimentPlanner', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 255.0, 'mean': 49.659568786621094, 'median': 45.0, 'min': 0.0, 'percentile_00_5': 10.0, 'percentile_99_5': 163.0, 'std': 24.689043045043945}}}", + "preprocessed_dataset_folder": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/nnUNetPlans_2d", + "preprocessed_dataset_folder_base": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish", + "probabilistic_oversampling": "False", + "save_every": "50", + "torch_version": "2.5.1+cu121", + "was_initialized": "True", + "weight_decay": "3e-05" +} \ No newline at end of file diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/progress.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/progress.png new file mode 100644 index 0000000000000000000000000000000000000000..eb91fbf4e2ed5184d743279838dcca3611fd3231 --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/progress.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a35e6373d4ff846b9a8339189a5ab0c69579c72f1a8b1171b8a2c197ec5287de +size 1113377 diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/training_log_2025_10_30_08_30_37.txt b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/training_log_2025_10_30_08_30_37.txt new file mode 100644 index 0000000000000000000000000000000000000000..4fd3e16844b0e378eed0b69efbbac9ae116124eb --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/training_log_2025_10_30_08_30_37.txt @@ -0,0 +1,23 @@ + +####################################################################### +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. +####################################################################### + +2025-10-30 08:30:39.758686: Using torch.compile... +2025-10-30 08:30:40.806764: do_dummy_2d_data_aug: False +2025-10-30 08:30:40.812904: Creating new 5-fold cross-validation split... +2025-10-30 08:30:40.818653: Desired fold for training: 0 +2025-10-30 08:30:40.820158: This split has 86 training and 22 validation cases. + +This is the configuration used by this training: +Configuration name: 2d + {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 5, 'patch_size': [1024, 112], 'median_image_size_in_voxels': [1024.0, 102.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['ZScoreNormalization'], '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': 8, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 1], [2, 1], [2, 1]], 'n_conv_per_stage': [2, 2, 2, 2, 2, 2, 2, 2], 'n_conv_per_stage_decoder': [2, 2, 2, 2, 2, 2, 2], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True} + +These are the global plan.json settings: + {'dataset_name': 'Dataset001_zebrafish', 'plans_name': 'nnUNetPlans', 'original_median_spacing_after_transp': [999.0, 1.0, 1.0], 'original_median_shape_after_transp': [1, 1024, 102], 'image_reader_writer': 'NaturalImage2DIO', 'transpose_forward': [0, 1, 2], 'transpose_backward': [0, 1, 2], 'experiment_planner_used': 'ExperimentPlanner', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 255.0, 'mean': 49.659568786621094, 'median': 45.0, 'min': 0.0, 'percentile_00_5': 10.0, 'percentile_99_5': 163.0, 'std': 24.689043045043945}}} + +2025-10-30 08:30:42.544917: Unable to plot network architecture: nnUNet_compile is enabled! +2025-10-30 08:30:42.566393: +2025-10-30 08:30:42.568064: Epoch 0 +2025-10-30 08:30:42.569908: Current learning rate: 0.01 diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/training_log_2025_10_30_08_31_30.txt b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/training_log_2025_10_30_08_31_30.txt new file mode 100644 index 0000000000000000000000000000000000000000..04cc7a0aa1a2a8150e7c705e6e92c0094d26f2d3 --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/training_log_2025_10_30_08_31_30.txt @@ -0,0 +1,24 @@ + +####################################################################### +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. +####################################################################### + +2025-10-30 08:31:32.228938: Using torch.compile... +2025-10-30 08:31:33.240147: do_dummy_2d_data_aug: False +2025-10-30 08:31:33.242795: Using splits from existing split file: /hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/splits_final.json +2025-10-30 08:31:33.244770: The split file contains 5 splits. +2025-10-30 08:31:33.246291: Desired fold for training: 0 +2025-10-30 08:31:33.247709: This split has 86 training and 22 validation cases. + +This is the configuration used by this training: +Configuration name: 2d + {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 5, 'patch_size': [1024, 112], 'median_image_size_in_voxels': [1024.0, 102.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['ZScoreNormalization'], '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': 8, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 1], [2, 1], [2, 1]], 'n_conv_per_stage': [2, 2, 2, 2, 2, 2, 2, 2], 'n_conv_per_stage_decoder': [2, 2, 2, 2, 2, 2, 2], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True} + +These are the global plan.json settings: + {'dataset_name': 'Dataset001_zebrafish', 'plans_name': 'nnUNetPlans', 'original_median_spacing_after_transp': [999.0, 1.0, 1.0], 'original_median_shape_after_transp': [1, 1024, 102], 'image_reader_writer': 'NaturalImage2DIO', 'transpose_forward': [0, 1, 2], 'transpose_backward': [0, 1, 2], 'experiment_planner_used': 'ExperimentPlanner', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 255.0, 'mean': 49.659568786621094, 'median': 45.0, 'min': 0.0, 'percentile_00_5': 10.0, 'percentile_99_5': 163.0, 'std': 24.689043045043945}}} + +2025-10-30 08:31:35.049255: Unable to plot network architecture: nnUNet_compile is enabled! +2025-10-30 08:31:35.064852: +2025-10-30 08:31:35.066397: Epoch 0 +2025-10-30 08:31:35.067992: Current learning rate: 0.01 diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/training_log_2025_10_30_08_33_14.txt b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/training_log_2025_10_30_08_33_14.txt new file mode 100644 index 0000000000000000000000000000000000000000..cfa69fd5290b92be224fde0c0d3aa6ca970f8b66 --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/training_log_2025_10_30_08_33_14.txt @@ -0,0 +1,7102 @@ + +####################################################################### +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. +####################################################################### + +2025-10-30 08:33:16.281551: Using torch.compile... +2025-10-30 08:33:17.593666: do_dummy_2d_data_aug: False +2025-10-30 08:33:17.596357: Using splits from existing split file: /hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/splits_final.json +2025-10-30 08:33:17.597936: The split file contains 5 splits. +2025-10-30 08:33:17.599164: Desired fold for training: 0 +2025-10-30 08:33:17.600339: This split has 86 training and 22 validation cases. + +This is the configuration used by this training: +Configuration name: 2d + {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 5, 'patch_size': [1024, 112], 'median_image_size_in_voxels': [1024.0, 102.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['ZScoreNormalization'], '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': 8, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 1], [2, 1], [2, 1]], 'n_conv_per_stage': [2, 2, 2, 2, 2, 2, 2, 2], 'n_conv_per_stage_decoder': [2, 2, 2, 2, 2, 2, 2], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True} + +These are the global plan.json settings: + {'dataset_name': 'Dataset001_zebrafish', 'plans_name': 'nnUNetPlans', 'original_median_spacing_after_transp': [999.0, 1.0, 1.0], 'original_median_shape_after_transp': [1, 1024, 102], 'image_reader_writer': 'NaturalImage2DIO', 'transpose_forward': [0, 1, 2], 'transpose_backward': [0, 1, 2], 'experiment_planner_used': 'ExperimentPlanner', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 255.0, 'mean': 49.659568786621094, 'median': 45.0, 'min': 0.0, 'percentile_00_5': 10.0, 'percentile_99_5': 163.0, 'std': 24.689043045043945}}} + +2025-10-30 08:33:19.437288: Unable to plot network architecture: nnUNet_compile is enabled! +2025-10-30 08:33:19.457871: +2025-10-30 08:33:19.459705: Epoch 0 +2025-10-30 08:33:19.461525: Current learning rate: 0.01 +2025-10-30 08:35:55.300356: train_loss -0.2011 +2025-10-30 08:35:55.304906: val_loss -0.8298 +2025-10-30 08:35:55.307080: Pseudo dice [np.float32(0.9565), np.float32(0.967), np.float32(0.9819), np.float32(0.711)] +2025-10-30 08:35:55.309041: Epoch time: 155.84 s +2025-10-30 08:35:55.310800: Yayy! New best EMA pseudo Dice: 0.9041000008583069 +2025-10-30 08:35:57.996264: +2025-10-30 08:35:57.998470: Epoch 1 +2025-10-30 08:35:58.000053: Current learning rate: 0.00999 +2025-10-30 08:36:19.523322: train_loss -0.8436 +2025-10-30 08:36:19.525536: val_loss -0.8621 +2025-10-30 08:36:19.527546: Pseudo dice [np.float32(0.9723), np.float32(0.9816), np.float32(0.9876), np.float32(0.7133)] +2025-10-30 08:36:19.529307: Epoch time: 21.53 s +2025-10-30 08:36:19.531449: Yayy! New best EMA pseudo Dice: 0.9050999879837036 +2025-10-30 08:36:21.757197: +2025-10-30 08:36:21.759477: Epoch 2 +2025-10-30 08:36:21.761945: Current learning rate: 0.00998 +2025-10-30 08:36:43.945111: train_loss -0.8599 +2025-10-30 08:36:43.948063: val_loss -0.8849 +2025-10-30 08:36:43.949866: Pseudo dice [np.float32(0.9736), np.float32(0.9771), np.float32(0.991), np.float32(0.786)] +2025-10-30 08:36:43.951645: Epoch time: 22.19 s +2025-10-30 08:36:43.953467: Yayy! New best EMA pseudo Dice: 0.907800018787384 +2025-10-30 08:36:46.193052: +2025-10-30 08:36:46.195275: Epoch 3 +2025-10-30 08:36:46.197120: Current learning rate: 0.00997 +2025-10-30 08:37:07.069169: train_loss -0.8917 +2025-10-30 08:37:07.072623: val_loss -0.8931 +2025-10-30 08:37:07.074981: Pseudo dice [np.float32(0.9782), np.float32(0.9843), np.float32(0.9896), np.float32(0.7875)] +2025-10-30 08:37:07.076745: Epoch time: 20.88 s +2025-10-30 08:37:07.078381: Yayy! New best EMA pseudo Dice: 0.9104999899864197 +2025-10-30 08:37:09.713239: +2025-10-30 08:37:09.715621: Epoch 4 +2025-10-30 08:37:09.717515: Current learning rate: 0.00996 +2025-10-30 08:37:31.065458: train_loss -0.907 +2025-10-30 08:37:31.068059: val_loss -0.9106 +2025-10-30 08:37:31.069803: Pseudo dice [np.float32(0.9807), np.float32(0.9864), np.float32(0.9926), np.float32(0.8156)] +2025-10-30 08:37:31.071594: Epoch time: 21.35 s +2025-10-30 08:37:31.073309: Yayy! New best EMA pseudo Dice: 0.9138000011444092 +2025-10-30 08:37:33.194563: +2025-10-30 08:37:33.196444: Epoch 5 +2025-10-30 08:37:33.198329: Current learning rate: 0.00995 +2025-10-30 08:37:53.950495: train_loss -0.918 +2025-10-30 08:37:53.954231: val_loss -0.9097 +2025-10-30 08:37:53.956407: Pseudo dice [np.float32(0.9828), np.float32(0.9875), np.float32(0.9936), np.float32(0.7887)] +2025-10-30 08:37:53.958459: Epoch time: 20.76 s +2025-10-30 08:37:53.960705: Yayy! New best EMA pseudo Dice: 0.9161999821662903 +2025-10-30 08:37:56.276218: +2025-10-30 08:37:56.279190: Epoch 6 +2025-10-30 08:37:56.282395: Current learning rate: 0.00995 +2025-10-30 08:38:16.157264: train_loss -0.9212 +2025-10-30 08:38:16.160696: val_loss -0.9043 +2025-10-30 08:38:16.162944: Pseudo dice [np.float32(0.9816), np.float32(0.9836), np.float32(0.989), np.float32(0.8034)] +2025-10-30 08:38:16.165004: Epoch time: 19.88 s +2025-10-30 08:38:16.166912: Yayy! New best EMA pseudo Dice: 0.9186000227928162 +2025-10-30 08:38:18.593900: +2025-10-30 08:38:18.596569: Epoch 7 +2025-10-30 08:38:18.598631: Current learning rate: 0.00994 +2025-10-30 08:38:39.223606: train_loss -0.9218 +2025-10-30 08:38:39.226637: val_loss -0.8896 +2025-10-30 08:38:39.228139: Pseudo dice [np.float32(0.9815), np.float32(0.9875), np.float32(0.9864), np.float32(0.7744)] +2025-10-30 08:38:39.229788: Epoch time: 20.63 s +2025-10-30 08:38:39.231450: Yayy! New best EMA pseudo Dice: 0.9200000166893005 +2025-10-30 08:38:41.704346: +2025-10-30 08:38:41.706640: Epoch 8 +2025-10-30 08:38:41.709222: Current learning rate: 0.00993 +2025-10-30 08:39:02.370332: train_loss -0.9202 +2025-10-30 08:39:02.377281: val_loss -0.893 +2025-10-30 08:39:02.379483: Pseudo dice [np.float32(0.9817), np.float32(0.9873), np.float32(0.9814), np.float32(0.7903)] +2025-10-30 08:39:02.381657: Epoch time: 20.67 s +2025-10-30 08:39:02.383466: Yayy! New best EMA pseudo Dice: 0.921500027179718 +2025-10-30 08:39:04.596991: +2025-10-30 08:39:04.598815: Epoch 9 +2025-10-30 08:39:04.600480: Current learning rate: 0.00992 +2025-10-30 08:39:25.475000: train_loss -0.9288 +2025-10-30 08:39:25.477386: val_loss -0.916 +2025-10-30 08:39:25.479833: Pseudo dice [np.float32(0.9806), np.float32(0.9868), np.float32(0.9938), np.float32(0.8076)] +2025-10-30 08:39:25.481551: Epoch time: 20.88 s +2025-10-30 08:39:25.483315: Yayy! New best EMA pseudo Dice: 0.9236000180244446 +2025-10-30 08:39:27.944439: +2025-10-30 08:39:27.946432: Epoch 10 +2025-10-30 08:39:27.948279: Current learning rate: 0.00991 +2025-10-30 08:39:49.333472: train_loss -0.9166 +2025-10-30 08:39:49.336682: val_loss -0.908 +2025-10-30 08:39:49.338593: Pseudo dice [np.float32(0.9807), np.float32(0.9869), np.float32(0.9908), np.float32(0.8012)] +2025-10-30 08:39:49.340612: Epoch time: 21.39 s +2025-10-30 08:39:49.345459: Yayy! New best EMA pseudo Dice: 0.9251999855041504 +2025-10-30 08:39:51.644448: +2025-10-30 08:39:51.647420: Epoch 11 +2025-10-30 08:39:51.649571: Current learning rate: 0.0099 +2025-10-30 08:40:13.562881: train_loss -0.9235 +2025-10-30 08:40:13.565609: val_loss -0.9173 +2025-10-30 08:40:13.567231: Pseudo dice [np.float32(0.9818), np.float32(0.9873), np.float32(0.9939), np.float32(0.8125)] +2025-10-30 08:40:13.568761: Epoch time: 21.92 s +2025-10-30 08:40:13.570499: Yayy! New best EMA pseudo Dice: 0.9271000027656555 +2025-10-30 08:40:15.729130: +2025-10-30 08:40:15.732464: Epoch 12 +2025-10-30 08:40:15.734186: Current learning rate: 0.00989 +2025-10-30 08:40:36.968980: train_loss -0.934 +2025-10-30 08:40:36.972244: val_loss -0.9168 +2025-10-30 08:40:36.974940: Pseudo dice [np.float32(0.9812), np.float32(0.9865), np.float32(0.994), np.float32(0.8094)] +2025-10-30 08:40:36.977720: Epoch time: 21.24 s +2025-10-30 08:40:36.979926: Yayy! New best EMA pseudo Dice: 0.928600013256073 +2025-10-30 08:40:39.485619: +2025-10-30 08:40:39.487905: Epoch 13 +2025-10-30 08:40:39.490260: Current learning rate: 0.00988 +2025-10-30 08:41:00.413558: train_loss -0.9398 +2025-10-30 08:41:00.416636: val_loss -0.9178 +2025-10-30 08:41:00.418781: Pseudo dice [np.float32(0.981), np.float32(0.9855), np.float32(0.9937), np.float32(0.8221)] +2025-10-30 08:41:00.420910: Epoch time: 20.93 s +2025-10-30 08:41:00.422961: Yayy! New best EMA pseudo Dice: 0.9302999973297119 +2025-10-30 08:41:02.779487: +2025-10-30 08:41:02.784781: Epoch 14 +2025-10-30 08:41:02.786869: Current learning rate: 0.00987 +2025-10-30 08:41:23.639882: train_loss -0.9393 +2025-10-30 08:41:23.642632: val_loss -0.906 +2025-10-30 08:41:23.644096: Pseudo dice [np.float32(0.982), np.float32(0.9878), np.float32(0.9931), np.float32(0.7842)] +2025-10-30 08:41:23.646136: Epoch time: 20.86 s +2025-10-30 08:41:23.647461: Yayy! New best EMA pseudo Dice: 0.9309999942779541 +2025-10-30 08:41:26.037601: +2025-10-30 08:41:26.039889: Epoch 15 +2025-10-30 08:41:26.041870: Current learning rate: 0.00986 +2025-10-30 08:41:46.050131: train_loss -0.9415 +2025-10-30 08:41:46.052989: val_loss -0.9029 +2025-10-30 08:41:46.054736: Pseudo dice [np.float32(0.9801), np.float32(0.9876), np.float32(0.9931), np.float32(0.7733)] +2025-10-30 08:41:46.056403: Epoch time: 20.01 s +2025-10-30 08:41:46.058074: Yayy! New best EMA pseudo Dice: 0.9312000274658203 +2025-10-30 08:41:48.514375: +2025-10-30 08:41:48.516583: Epoch 16 +2025-10-30 08:41:48.518580: Current learning rate: 0.00986 +2025-10-30 08:42:09.216008: train_loss -0.9458 +2025-10-30 08:42:09.218492: val_loss -0.9072 +2025-10-30 08:42:09.220031: Pseudo dice [np.float32(0.982), np.float32(0.9875), np.float32(0.9943), np.float32(0.7809)] +2025-10-30 08:42:09.221545: Epoch time: 20.7 s +2025-10-30 08:42:09.223107: Yayy! New best EMA pseudo Dice: 0.9316999912261963 +2025-10-30 08:42:12.561053: +2025-10-30 08:42:12.563340: Epoch 17 +2025-10-30 08:42:12.565351: Current learning rate: 0.00985 +2025-10-30 08:42:34.513654: train_loss -0.9474 +2025-10-30 08:42:34.517978: val_loss -0.9189 +2025-10-30 08:42:34.519558: Pseudo dice [np.float32(0.9829), np.float32(0.9881), np.float32(0.9944), np.float32(0.8052)] +2025-10-30 08:42:34.521192: Epoch time: 21.95 s +2025-10-30 08:42:34.522718: Yayy! New best EMA pseudo Dice: 0.9327999949455261 +2025-10-30 08:42:36.880483: +2025-10-30 08:42:36.882839: Epoch 18 +2025-10-30 08:42:36.885396: Current learning rate: 0.00984 +2025-10-30 08:42:58.086959: train_loss -0.9486 +2025-10-30 08:42:58.090233: val_loss -0.9191 +2025-10-30 08:42:58.092290: Pseudo dice [np.float32(0.9814), np.float32(0.987), np.float32(0.995), np.float32(0.8201)] +2025-10-30 08:42:58.097975: Epoch time: 21.21 s +2025-10-30 08:42:58.100075: Yayy! New best EMA pseudo Dice: 0.9340999722480774 +2025-10-30 08:43:00.358150: +2025-10-30 08:43:00.360431: Epoch 19 +2025-10-30 08:43:00.362532: Current learning rate: 0.00983 +2025-10-30 08:43:21.418591: train_loss -0.9513 +2025-10-30 08:43:21.421437: val_loss -0.9145 +2025-10-30 08:43:21.423297: Pseudo dice [np.float32(0.9806), np.float32(0.9885), np.float32(0.9947), np.float32(0.8047)] +2025-10-30 08:43:21.425089: Epoch time: 21.06 s +2025-10-30 08:43:21.427110: Yayy! New best EMA pseudo Dice: 0.9348999857902527 +2025-10-30 08:43:23.775558: +2025-10-30 08:43:23.777860: Epoch 20 +2025-10-30 08:43:23.779832: Current learning rate: 0.00982 +2025-10-30 08:43:45.162298: train_loss -0.9507 +2025-10-30 08:43:45.165411: val_loss -0.9213 +2025-10-30 08:43:45.167510: Pseudo dice [np.float32(0.9819), np.float32(0.9869), np.float32(0.9945), np.float32(0.8252)] +2025-10-30 08:43:45.169469: Epoch time: 21.39 s +2025-10-30 08:43:45.171194: Yayy! New best EMA pseudo Dice: 0.9361000061035156 +2025-10-30 08:43:47.620883: +2025-10-30 08:43:47.623063: Epoch 21 +2025-10-30 08:43:47.625075: Current learning rate: 0.00981 +2025-10-30 08:44:08.971025: train_loss -0.9548 +2025-10-30 08:44:08.973208: val_loss -0.9114 +2025-10-30 08:44:08.974689: Pseudo dice [np.float32(0.981), np.float32(0.9876), np.float32(0.9945), np.float32(0.7897)] +2025-10-30 08:44:08.977766: Epoch time: 21.35 s +2025-10-30 08:44:08.979161: Yayy! New best EMA pseudo Dice: 0.9362999796867371 +2025-10-30 08:44:11.369570: +2025-10-30 08:44:11.371942: Epoch 22 +2025-10-30 08:44:11.374269: Current learning rate: 0.0098 +2025-10-30 08:44:32.917626: train_loss -0.9581 +2025-10-30 08:44:32.920060: val_loss -0.9071 +2025-10-30 08:44:32.925249: Pseudo dice [np.float32(0.9812), np.float32(0.9879), np.float32(0.9945), np.float32(0.7815)] +2025-10-30 08:44:32.926892: Epoch time: 21.55 s +2025-10-30 08:44:34.121065: +2025-10-30 08:44:34.123188: Epoch 23 +2025-10-30 08:44:34.125051: Current learning rate: 0.00979 +2025-10-30 08:44:56.065155: train_loss -0.953 +2025-10-30 08:44:56.068643: val_loss -0.9083 +2025-10-30 08:44:56.070493: Pseudo dice [np.float32(0.9771), np.float32(0.9858), np.float32(0.9944), np.float32(0.8061)] +2025-10-30 08:44:56.072261: Epoch time: 21.95 s +2025-10-30 08:44:56.074056: Yayy! New best EMA pseudo Dice: 0.9368000030517578 +2025-10-30 08:44:58.441863: +2025-10-30 08:44:58.444610: Epoch 24 +2025-10-30 08:44:58.446513: Current learning rate: 0.00978 +2025-10-30 08:45:20.599854: train_loss -0.957 +2025-10-30 08:45:20.602332: val_loss -0.9127 +2025-10-30 08:45:20.603988: Pseudo dice [np.float32(0.9791), np.float32(0.9867), np.float32(0.9945), np.float32(0.8063)] +2025-10-30 08:45:20.605580: Epoch time: 22.16 s +2025-10-30 08:45:20.607219: Yayy! New best EMA pseudo Dice: 0.9373000264167786 +2025-10-30 08:45:22.741931: +2025-10-30 08:45:22.744240: Epoch 25 +2025-10-30 08:45:22.745867: Current learning rate: 0.00977 +2025-10-30 08:45:42.746531: train_loss -0.9598 +2025-10-30 08:45:42.748814: val_loss -0.909 +2025-10-30 08:45:42.750877: Pseudo dice [np.float32(0.9791), np.float32(0.9872), np.float32(0.9945), np.float32(0.7981)] +2025-10-30 08:45:42.752674: Epoch time: 20.01 s +2025-10-30 08:45:42.757385: Yayy! New best EMA pseudo Dice: 0.9375 +2025-10-30 08:45:45.006826: +2025-10-30 08:45:45.008967: Epoch 26 +2025-10-30 08:45:45.011026: Current learning rate: 0.00977 +2025-10-30 08:46:07.304061: train_loss -0.9584 +2025-10-30 08:46:07.307296: val_loss -0.8942 +2025-10-30 08:46:07.309001: Pseudo dice [np.float32(0.9776), np.float32(0.9861), np.float32(0.9935), np.float32(0.7629)] +2025-10-30 08:46:07.310941: Epoch time: 22.3 s +2025-10-30 08:46:08.332757: +2025-10-30 08:46:08.334986: Epoch 27 +2025-10-30 08:46:08.336945: Current learning rate: 0.00976 +2025-10-30 08:46:29.230905: train_loss -0.9552 +2025-10-30 08:46:29.234669: val_loss -0.9124 +2025-10-30 08:46:29.236854: Pseudo dice [np.float32(0.9821), np.float32(0.987), np.float32(0.9945), np.float32(0.8089)] +2025-10-30 08:46:29.238691: Epoch time: 20.9 s +2025-10-30 08:46:30.554417: +2025-10-30 08:46:30.556092: Epoch 28 +2025-10-30 08:46:30.557630: Current learning rate: 0.00975 +2025-10-30 08:46:52.764468: train_loss -0.958 +2025-10-30 08:46:52.767355: val_loss -0.9107 +2025-10-30 08:46:52.769493: Pseudo dice [np.float32(0.9805), np.float32(0.9878), np.float32(0.9946), np.float32(0.7988)] +2025-10-30 08:46:52.771173: Epoch time: 22.21 s +2025-10-30 08:46:52.773326: Yayy! New best EMA pseudo Dice: 0.9376999735832214 +2025-10-30 08:46:55.058839: +2025-10-30 08:46:55.061374: Epoch 29 +2025-10-30 08:46:55.063326: Current learning rate: 0.00974 +2025-10-30 08:47:17.361234: train_loss -0.9603 +2025-10-30 08:47:17.367910: val_loss -0.9053 +2025-10-30 08:47:17.370121: Pseudo dice [np.float32(0.979), np.float32(0.9867), np.float32(0.9943), np.float32(0.7914)] +2025-10-30 08:47:17.372103: Epoch time: 22.3 s +2025-10-30 08:47:17.373808: Yayy! New best EMA pseudo Dice: 0.9376999735832214 +2025-10-30 08:47:19.907679: +2025-10-30 08:47:19.910181: Epoch 30 +2025-10-30 08:47:19.911862: Current learning rate: 0.00973 +2025-10-30 08:47:41.983291: train_loss -0.9607 +2025-10-30 08:47:41.986503: val_loss -0.9012 +2025-10-30 08:47:41.988186: Pseudo dice [np.float32(0.9818), np.float32(0.9877), np.float32(0.994), np.float32(0.7737)] +2025-10-30 08:47:41.989763: Epoch time: 22.08 s +2025-10-30 08:47:43.012625: +2025-10-30 08:47:43.014509: Epoch 31 +2025-10-30 08:47:43.016515: Current learning rate: 0.00972 +2025-10-30 08:48:03.703418: train_loss -0.9623 +2025-10-30 08:48:03.705708: val_loss -0.9118 +2025-10-30 08:48:03.707327: Pseudo dice [np.float32(0.982), np.float32(0.9875), np.float32(0.9944), np.float32(0.8011)] +2025-10-30 08:48:03.709036: Epoch time: 20.69 s +2025-10-30 08:48:03.710825: Yayy! New best EMA pseudo Dice: 0.9377999901771545 +2025-10-30 08:48:06.165358: +2025-10-30 08:48:06.166985: Epoch 32 +2025-10-30 08:48:06.168739: Current learning rate: 0.00971 +2025-10-30 08:48:28.362567: train_loss -0.9658 +2025-10-30 08:48:28.395439: val_loss -0.9047 +2025-10-30 08:48:28.411853: Pseudo dice [np.float32(0.9816), np.float32(0.9882), np.float32(0.9949), np.float32(0.7757)] +2025-10-30 08:48:28.425341: Epoch time: 22.2 s +2025-10-30 08:48:29.659690: +2025-10-30 08:48:29.669864: Epoch 33 +2025-10-30 08:48:29.671584: Current learning rate: 0.0097 +2025-10-30 08:48:51.124115: train_loss -0.9649 +2025-10-30 08:48:51.126994: val_loss -0.9004 +2025-10-30 08:48:51.129056: Pseudo dice [np.float32(0.9793), np.float32(0.9872), np.float32(0.9941), np.float32(0.7844)] +2025-10-30 08:48:51.130882: Epoch time: 21.47 s +2025-10-30 08:48:52.903190: +2025-10-30 08:48:52.905361: Epoch 34 +2025-10-30 08:48:52.908080: Current learning rate: 0.00969 +2025-10-30 08:49:14.752511: train_loss -0.9603 +2025-10-30 08:49:14.754912: val_loss -0.8957 +2025-10-30 08:49:14.756814: Pseudo dice [np.float32(0.9796), np.float32(0.9862), np.float32(0.9944), np.float32(0.7589)] +2025-10-30 08:49:14.758360: Epoch time: 21.85 s +2025-10-30 08:49:15.945115: +2025-10-30 08:49:15.947486: Epoch 35 +2025-10-30 08:49:15.949412: Current learning rate: 0.00968 +2025-10-30 08:49:37.770817: train_loss -0.9548 +2025-10-30 08:49:37.779455: val_loss -0.9 +2025-10-30 08:49:37.781353: Pseudo dice [np.float32(0.9801), np.float32(0.9856), np.float32(0.9944), np.float32(0.778)] +2025-10-30 08:49:37.783180: Epoch time: 21.83 s +2025-10-30 08:49:38.860848: +2025-10-30 08:49:38.862586: Epoch 36 +2025-10-30 08:49:38.864267: Current learning rate: 0.00968 +2025-10-30 08:50:00.603733: train_loss -0.9615 +2025-10-30 08:50:00.606511: val_loss -0.9054 +2025-10-30 08:50:00.609301: Pseudo dice [np.float32(0.9814), np.float32(0.9876), np.float32(0.9943), np.float32(0.793)] +2025-10-30 08:50:00.611132: Epoch time: 21.74 s +2025-10-30 08:50:01.852064: +2025-10-30 08:50:01.854163: Epoch 37 +2025-10-30 08:50:01.856088: Current learning rate: 0.00967 +2025-10-30 08:50:22.438915: train_loss -0.9621 +2025-10-30 08:50:22.441326: val_loss -0.9124 +2025-10-30 08:50:22.443060: Pseudo dice [np.float32(0.9811), np.float32(0.9878), np.float32(0.9948), np.float32(0.8105)] +2025-10-30 08:50:22.444862: Epoch time: 20.59 s +2025-10-30 08:50:23.482108: +2025-10-30 08:50:23.485343: Epoch 38 +2025-10-30 08:50:23.487066: Current learning rate: 0.00966 +2025-10-30 08:50:45.259076: train_loss -0.965 +2025-10-30 08:50:45.262047: val_loss -0.9104 +2025-10-30 08:50:45.264047: Pseudo dice [np.float32(0.9821), np.float32(0.9878), np.float32(0.9946), np.float32(0.7996)] +2025-10-30 08:50:45.265754: Epoch time: 21.78 s +2025-10-30 08:50:46.297735: +2025-10-30 08:50:46.299974: Epoch 39 +2025-10-30 08:50:46.302047: Current learning rate: 0.00965 +2025-10-30 08:51:07.161331: train_loss -0.9652 +2025-10-30 08:51:07.164161: val_loss -0.897 +2025-10-30 08:51:07.166356: Pseudo dice [np.float32(0.9814), np.float32(0.989), np.float32(0.9944), np.float32(0.7622)] +2025-10-30 08:51:07.168663: Epoch time: 20.87 s +2025-10-30 08:51:08.347872: +2025-10-30 08:51:08.349958: Epoch 40 +2025-10-30 08:51:08.351703: Current learning rate: 0.00964 +2025-10-30 08:51:30.607479: train_loss -0.9664 +2025-10-30 08:51:30.610272: val_loss -0.8986 +2025-10-30 08:51:30.612052: Pseudo dice [np.float32(0.9805), np.float32(0.9867), np.float32(0.9941), np.float32(0.7767)] +2025-10-30 08:51:30.613659: Epoch time: 22.26 s +2025-10-30 08:51:31.852441: +2025-10-30 08:51:31.854234: Epoch 41 +2025-10-30 08:51:31.855779: Current learning rate: 0.00963 +2025-10-30 08:51:53.965712: train_loss -0.9678 +2025-10-30 08:51:53.971611: val_loss -0.9011 +2025-10-30 08:51:53.973475: Pseudo dice [np.float32(0.9805), np.float32(0.9873), np.float32(0.9946), np.float32(0.7867)] +2025-10-30 08:51:53.975267: Epoch time: 22.11 s +2025-10-30 08:51:54.978088: +2025-10-30 08:51:54.979949: Epoch 42 +2025-10-30 08:51:54.981644: Current learning rate: 0.00962 +2025-10-30 08:52:17.038369: train_loss -0.9706 +2025-10-30 08:52:17.040895: val_loss -0.9102 +2025-10-30 08:52:17.042759: Pseudo dice [np.float32(0.9822), np.float32(0.9882), np.float32(0.9945), np.float32(0.8065)] +2025-10-30 08:52:17.044847: Epoch time: 22.06 s +2025-10-30 08:52:18.238014: +2025-10-30 08:52:18.240060: Epoch 43 +2025-10-30 08:52:18.242201: Current learning rate: 0.00961 +2025-10-30 08:52:39.938845: train_loss -0.9704 +2025-10-30 08:52:39.941702: val_loss -0.9153 +2025-10-30 08:52:39.943333: Pseudo dice [np.float32(0.9794), np.float32(0.9875), np.float32(0.9951), np.float32(0.823)] +2025-10-30 08:52:39.944907: Epoch time: 21.7 s +2025-10-30 08:52:39.946378: Yayy! New best EMA pseudo Dice: 0.9383999705314636 +2025-10-30 08:52:42.122947: +2025-10-30 08:52:42.124889: Epoch 44 +2025-10-30 08:52:42.126895: Current learning rate: 0.0096 +2025-10-30 08:53:03.851173: train_loss -0.97 +2025-10-30 08:53:03.854522: val_loss -0.8902 +2025-10-30 08:53:03.856349: Pseudo dice [np.float32(0.9801), np.float32(0.9868), np.float32(0.994), np.float32(0.7563)] +2025-10-30 08:53:03.858004: Epoch time: 21.73 s +2025-10-30 08:53:04.857606: +2025-10-30 08:53:04.859472: Epoch 45 +2025-10-30 08:53:04.861154: Current learning rate: 0.00959 +2025-10-30 08:53:25.870989: train_loss -0.9704 +2025-10-30 08:53:25.874279: val_loss -0.9004 +2025-10-30 08:53:25.876283: Pseudo dice [np.float32(0.9813), np.float32(0.9871), np.float32(0.9942), np.float32(0.7811)] +2025-10-30 08:53:25.878430: Epoch time: 21.01 s +2025-10-30 08:53:27.052322: +2025-10-30 08:53:27.054282: Epoch 46 +2025-10-30 08:53:27.059118: Current learning rate: 0.00959 +2025-10-30 08:53:48.879659: train_loss -0.9707 +2025-10-30 08:53:48.882112: val_loss -0.9053 +2025-10-30 08:53:48.884441: Pseudo dice [np.float32(0.9799), np.float32(0.9869), np.float32(0.995), np.float32(0.8007)] +2025-10-30 08:53:48.886060: Epoch time: 21.83 s +2025-10-30 08:53:49.928051: +2025-10-30 08:53:49.930115: Epoch 47 +2025-10-30 08:53:49.932194: Current learning rate: 0.00958 +2025-10-30 08:54:11.520876: train_loss -0.9698 +2025-10-30 08:54:11.523755: val_loss -0.8987 +2025-10-30 08:54:11.526686: Pseudo dice [np.float32(0.9807), np.float32(0.9869), np.float32(0.9944), np.float32(0.7801)] +2025-10-30 08:54:11.529415: Epoch time: 21.59 s +2025-10-30 08:54:12.506930: +2025-10-30 08:54:12.508834: Epoch 48 +2025-10-30 08:54:12.510604: Current learning rate: 0.00957 +2025-10-30 08:54:34.772946: train_loss -0.9706 +2025-10-30 08:54:34.775542: val_loss -0.8997 +2025-10-30 08:54:34.777243: Pseudo dice [np.float32(0.9822), np.float32(0.9876), np.float32(0.9945), np.float32(0.7824)] +2025-10-30 08:54:34.779267: Epoch time: 22.27 s +2025-10-30 08:54:35.973134: +2025-10-30 08:54:35.975143: Epoch 49 +2025-10-30 08:54:35.976925: Current learning rate: 0.00956 +2025-10-30 08:54:58.004041: train_loss -0.9739 +2025-10-30 08:54:58.007984: val_loss -0.9024 +2025-10-30 08:54:58.009793: Pseudo dice [np.float32(0.9815), np.float32(0.988), np.float32(0.9949), np.float32(0.8008)] +2025-10-30 08:54:58.011763: Epoch time: 22.03 s +2025-10-30 08:55:00.416945: +2025-10-30 08:55:00.419187: Epoch 50 +2025-10-30 08:55:00.422023: Current learning rate: 0.00955 +2025-10-30 08:55:21.291556: train_loss -0.9722 +2025-10-30 08:55:21.294713: val_loss -0.9043 +2025-10-30 08:55:21.296591: Pseudo dice [np.float32(0.9803), np.float32(0.9878), np.float32(0.9946), np.float32(0.7977)] +2025-10-30 08:55:21.298179: Epoch time: 20.88 s +2025-10-30 08:55:22.459219: +2025-10-30 08:55:22.461168: Epoch 51 +2025-10-30 08:55:22.462986: Current learning rate: 0.00954 +2025-10-30 08:55:43.228825: train_loss -0.97 +2025-10-30 08:55:43.231367: val_loss -0.9048 +2025-10-30 08:55:43.233319: Pseudo dice [np.float32(0.9805), np.float32(0.9873), np.float32(0.9946), np.float32(0.8024)] +2025-10-30 08:55:43.235220: Epoch time: 20.77 s +2025-10-30 08:55:45.280247: +2025-10-30 08:55:45.282010: Epoch 52 +2025-10-30 08:55:45.283634: Current learning rate: 0.00953 +2025-10-30 08:56:07.449952: train_loss -0.9685 +2025-10-30 08:56:07.453387: val_loss -0.9086 +2025-10-30 08:56:07.455345: Pseudo dice [np.float32(0.9812), np.float32(0.9875), np.float32(0.9943), np.float32(0.8092)] +2025-10-30 08:56:07.457145: Epoch time: 22.17 s +2025-10-30 08:56:07.459066: Yayy! New best EMA pseudo Dice: 0.9387999773025513 +2025-10-30 08:56:09.920966: +2025-10-30 08:56:09.923677: Epoch 53 +2025-10-30 08:56:09.925627: Current learning rate: 0.00952 +2025-10-30 08:56:31.872032: train_loss -0.9691 +2025-10-30 08:56:31.874894: val_loss -0.9001 +2025-10-30 08:56:31.876499: Pseudo dice [np.float32(0.9805), np.float32(0.9877), np.float32(0.9943), np.float32(0.7876)] +2025-10-30 08:56:31.878205: Epoch time: 21.95 s +2025-10-30 08:56:32.939283: +2025-10-30 08:56:32.941011: Epoch 54 +2025-10-30 08:56:32.942632: Current learning rate: 0.00951 +2025-10-30 08:56:54.848933: train_loss -0.9729 +2025-10-30 08:56:54.854592: val_loss -0.8808 +2025-10-30 08:56:54.859356: Pseudo dice [np.float32(0.9801), np.float32(0.9865), np.float32(0.9936), np.float32(0.7429)] +2025-10-30 08:56:54.863848: Epoch time: 21.91 s +2025-10-30 08:56:56.049353: +2025-10-30 08:56:56.051375: Epoch 55 +2025-10-30 08:56:56.053163: Current learning rate: 0.0095 +2025-10-30 08:57:18.261899: train_loss -0.9739 +2025-10-30 08:57:18.264419: val_loss -0.8965 +2025-10-30 08:57:18.266063: Pseudo dice [np.float32(0.9809), np.float32(0.9876), np.float32(0.9941), np.float32(0.7799)] +2025-10-30 08:57:18.289239: Epoch time: 22.21 s +2025-10-30 08:57:19.476799: +2025-10-30 08:57:19.478572: Epoch 56 +2025-10-30 08:57:19.480234: Current learning rate: 0.00949 +2025-10-30 08:57:39.654124: train_loss -0.9741 +2025-10-30 08:57:39.657093: val_loss -0.8911 +2025-10-30 08:57:39.658975: Pseudo dice [np.float32(0.9811), np.float32(0.9866), np.float32(0.994), np.float32(0.7608)] +2025-10-30 08:57:39.660654: Epoch time: 20.18 s +2025-10-30 08:57:40.852574: +2025-10-30 08:57:40.854693: Epoch 57 +2025-10-30 08:57:40.856277: Current learning rate: 0.00949 +2025-10-30 08:58:01.694230: train_loss -0.9757 +2025-10-30 08:58:01.701717: val_loss -0.8884 +2025-10-30 08:58:01.703475: Pseudo dice [np.float32(0.9817), np.float32(0.9876), np.float32(0.994), np.float32(0.7641)] +2025-10-30 08:58:01.705111: Epoch time: 20.84 s +2025-10-30 08:58:02.920941: +2025-10-30 08:58:02.923042: Epoch 58 +2025-10-30 08:58:02.924773: Current learning rate: 0.00948 +2025-10-30 08:58:24.421878: train_loss -0.9749 +2025-10-30 08:58:24.424394: val_loss -0.8883 +2025-10-30 08:58:24.426224: Pseudo dice [np.float32(0.9829), np.float32(0.9888), np.float32(0.9947), np.float32(0.7576)] +2025-10-30 08:58:24.428834: Epoch time: 21.5 s +2025-10-30 08:58:25.405049: +2025-10-30 08:58:25.407164: Epoch 59 +2025-10-30 08:58:25.408743: Current learning rate: 0.00947 +2025-10-30 08:58:47.135118: train_loss -0.9612 +2025-10-30 08:58:47.141999: val_loss -0.9064 +2025-10-30 08:58:47.147416: Pseudo dice [np.float32(0.9788), np.float32(0.9864), np.float32(0.9939), np.float32(0.8047)] +2025-10-30 08:58:47.149145: Epoch time: 21.73 s +2025-10-30 08:58:48.154527: +2025-10-30 08:58:48.156393: Epoch 60 +2025-10-30 08:58:48.158281: Current learning rate: 0.00946 +2025-10-30 08:59:09.947980: train_loss -0.9617 +2025-10-30 08:59:09.954781: val_loss -0.9006 +2025-10-30 08:59:09.956285: Pseudo dice [np.float32(0.9804), np.float32(0.9877), np.float32(0.9943), np.float32(0.7864)] +2025-10-30 08:59:09.958122: Epoch time: 21.8 s +2025-10-30 08:59:10.829092: +2025-10-30 08:59:10.831201: Epoch 61 +2025-10-30 08:59:10.832899: Current learning rate: 0.00945 +2025-10-30 08:59:32.589073: train_loss -0.9664 +2025-10-30 08:59:32.591513: val_loss -0.8968 +2025-10-30 08:59:32.593259: Pseudo dice [np.float32(0.9748), np.float32(0.9865), np.float32(0.9939), np.float32(0.7872)] +2025-10-30 08:59:32.594801: Epoch time: 21.76 s +2025-10-30 08:59:33.657211: +2025-10-30 08:59:33.659045: Epoch 62 +2025-10-30 08:59:33.660697: Current learning rate: 0.00944 +2025-10-30 08:59:55.308846: train_loss -0.9703 +2025-10-30 08:59:55.311622: val_loss -0.908 +2025-10-30 08:59:55.313229: Pseudo dice [np.float32(0.9806), np.float32(0.9877), np.float32(0.9943), np.float32(0.8131)] +2025-10-30 08:59:55.314751: Epoch time: 21.65 s +2025-10-30 08:59:56.330168: +2025-10-30 08:59:56.331939: Epoch 63 +2025-10-30 08:59:56.333475: Current learning rate: 0.00943 +2025-10-30 09:00:15.090567: train_loss -0.9741 +2025-10-30 09:00:15.092738: val_loss -0.8874 +2025-10-30 09:00:15.094303: Pseudo dice [np.float32(0.981), np.float32(0.9882), np.float32(0.9944), np.float32(0.7473)] +2025-10-30 09:00:15.095867: Epoch time: 18.76 s +2025-10-30 09:00:16.301816: +2025-10-30 09:00:16.303540: Epoch 64 +2025-10-30 09:00:16.305159: Current learning rate: 0.00942 +2025-10-30 09:00:38.134668: train_loss -0.9746 +2025-10-30 09:00:38.136659: val_loss -0.9048 +2025-10-30 09:00:38.138347: Pseudo dice [np.float32(0.9812), np.float32(0.9881), np.float32(0.9947), np.float32(0.8001)] +2025-10-30 09:00:38.139935: Epoch time: 21.83 s +2025-10-30 09:00:39.406224: +2025-10-30 09:00:39.408060: Epoch 65 +2025-10-30 09:00:39.409744: Current learning rate: 0.00941 +2025-10-30 09:01:01.106789: train_loss -0.974 +2025-10-30 09:01:01.109986: val_loss -0.8888 +2025-10-30 09:01:01.111660: Pseudo dice [np.float32(0.9802), np.float32(0.987), np.float32(0.9934), np.float32(0.7679)] +2025-10-30 09:01:01.113205: Epoch time: 21.7 s +2025-10-30 09:01:02.195633: +2025-10-30 09:01:02.197505: Epoch 66 +2025-10-30 09:01:02.198983: Current learning rate: 0.0094 +2025-10-30 09:01:23.120765: train_loss -0.9743 +2025-10-30 09:01:23.123042: val_loss -0.8951 +2025-10-30 09:01:23.124869: Pseudo dice [np.float32(0.9819), np.float32(0.9869), np.float32(0.9935), np.float32(0.7815)] +2025-10-30 09:01:23.126690: Epoch time: 20.93 s +2025-10-30 09:01:24.264400: +2025-10-30 09:01:24.267541: Epoch 67 +2025-10-30 09:01:24.269297: Current learning rate: 0.00939 +2025-10-30 09:01:45.122434: train_loss -0.9713 +2025-10-30 09:01:45.127495: val_loss -0.8892 +2025-10-30 09:01:45.129171: Pseudo dice [np.float32(0.9778), np.float32(0.9872), np.float32(0.9939), np.float32(0.7648)] +2025-10-30 09:01:45.130543: Epoch time: 20.86 s +2025-10-30 09:01:46.375320: +2025-10-30 09:01:46.390799: Epoch 68 +2025-10-30 09:01:46.392822: Current learning rate: 0.00939 +2025-10-30 09:02:08.197695: train_loss -0.9755 +2025-10-30 09:02:08.200922: val_loss -0.8973 +2025-10-30 09:02:08.202610: Pseudo dice [np.float32(0.9823), np.float32(0.9874), np.float32(0.9942), np.float32(0.7846)] +2025-10-30 09:02:08.204247: Epoch time: 21.82 s +2025-10-30 09:02:10.630676: +2025-10-30 09:02:10.632620: Epoch 69 +2025-10-30 09:02:10.634237: Current learning rate: 0.00938 +2025-10-30 09:02:30.105489: train_loss -0.9765 +2025-10-30 09:02:30.108038: val_loss -0.8855 +2025-10-30 09:02:30.109835: Pseudo dice [np.float32(0.9811), np.float32(0.9876), np.float32(0.9936), np.float32(0.7588)] +2025-10-30 09:02:30.111594: Epoch time: 19.48 s +2025-10-30 09:02:31.310171: +2025-10-30 09:02:31.312043: Epoch 70 +2025-10-30 09:02:31.313887: Current learning rate: 0.00937 +2025-10-30 09:02:53.161034: train_loss -0.9772 +2025-10-30 09:02:53.163270: val_loss -0.8694 +2025-10-30 09:02:53.164909: Pseudo dice [np.float32(0.981), np.float32(0.9807), np.float32(0.9932), np.float32(0.7563)] +2025-10-30 09:02:53.166509: Epoch time: 21.85 s +2025-10-30 09:02:54.174504: +2025-10-30 09:02:54.176182: Epoch 71 +2025-10-30 09:02:54.177733: Current learning rate: 0.00936 +2025-10-30 09:03:16.040440: train_loss -0.9597 +2025-10-30 09:03:16.044097: val_loss -0.9026 +2025-10-30 09:03:16.045775: Pseudo dice [np.float32(0.9799), np.float32(0.9872), np.float32(0.9941), np.float32(0.7913)] +2025-10-30 09:03:16.047365: Epoch time: 21.87 s +2025-10-30 09:03:17.244345: +2025-10-30 09:03:17.246427: Epoch 72 +2025-10-30 09:03:17.248137: Current learning rate: 0.00935 +2025-10-30 09:03:39.315027: train_loss -0.9643 +2025-10-30 09:03:39.319644: val_loss -0.9043 +2025-10-30 09:03:39.321326: Pseudo dice [np.float32(0.9789), np.float32(0.9864), np.float32(0.994), np.float32(0.809)] +2025-10-30 09:03:39.323105: Epoch time: 22.07 s +2025-10-30 09:03:40.401546: +2025-10-30 09:03:40.403872: Epoch 73 +2025-10-30 09:03:40.406504: Current learning rate: 0.00934 +2025-10-30 09:04:02.298549: train_loss -0.9682 +2025-10-30 09:04:02.303842: val_loss -0.8791 +2025-10-30 09:04:02.305824: Pseudo dice [np.float32(0.9801), np.float32(0.9863), np.float32(0.9927), np.float32(0.7298)] +2025-10-30 09:04:02.307496: Epoch time: 21.9 s +2025-10-30 09:04:03.492108: +2025-10-30 09:04:03.494033: Epoch 74 +2025-10-30 09:04:03.496884: Current learning rate: 0.00933 +2025-10-30 09:04:25.473927: train_loss -0.9705 +2025-10-30 09:04:25.476865: val_loss -0.9006 +2025-10-30 09:04:25.478553: Pseudo dice [np.float32(0.9827), np.float32(0.988), np.float32(0.9939), np.float32(0.7805)] +2025-10-30 09:04:25.480029: Epoch time: 21.98 s +2025-10-30 09:04:26.628458: +2025-10-30 09:04:26.630946: Epoch 75 +2025-10-30 09:04:26.632700: Current learning rate: 0.00932 +2025-10-30 09:04:47.843752: train_loss -0.9712 +2025-10-30 09:04:47.846334: val_loss -0.9025 +2025-10-30 09:04:47.848094: Pseudo dice [np.float32(0.9813), np.float32(0.9896), np.float32(0.9944), np.float32(0.7835)] +2025-10-30 09:04:47.849971: Epoch time: 21.22 s +2025-10-30 09:04:48.735271: +2025-10-30 09:04:48.737785: Epoch 76 +2025-10-30 09:04:48.740030: Current learning rate: 0.00931 +2025-10-30 09:05:09.420686: train_loss -0.9741 +2025-10-30 09:05:09.422757: val_loss -0.8974 +2025-10-30 09:05:09.424220: Pseudo dice [np.float32(0.982), np.float32(0.9886), np.float32(0.9942), np.float32(0.7778)] +2025-10-30 09:05:09.425695: Epoch time: 20.69 s +2025-10-30 09:05:10.575158: +2025-10-30 09:05:10.577393: Epoch 77 +2025-10-30 09:05:10.579386: Current learning rate: 0.0093 +2025-10-30 09:05:32.686395: train_loss -0.9755 +2025-10-30 09:05:32.690018: val_loss -0.8882 +2025-10-30 09:05:32.691893: Pseudo dice [np.float32(0.9813), np.float32(0.9879), np.float32(0.9941), np.float32(0.7632)] +2025-10-30 09:05:32.693661: Epoch time: 22.11 s +2025-10-30 09:05:33.905499: +2025-10-30 09:05:33.907815: Epoch 78 +2025-10-30 09:05:33.909759: Current learning rate: 0.0093 +2025-10-30 09:05:55.399594: train_loss -0.9771 +2025-10-30 09:05:55.401782: val_loss -0.8896 +2025-10-30 09:05:55.403484: Pseudo dice [np.float32(0.9812), np.float32(0.9879), np.float32(0.9938), np.float32(0.7642)] +2025-10-30 09:05:55.405078: Epoch time: 21.5 s +2025-10-30 09:05:56.455774: +2025-10-30 09:05:56.457738: Epoch 79 +2025-10-30 09:05:56.459319: Current learning rate: 0.00929 +2025-10-30 09:06:18.475486: train_loss -0.9766 +2025-10-30 09:06:18.478575: val_loss -0.8954 +2025-10-30 09:06:18.480628: Pseudo dice [np.float32(0.982), np.float32(0.988), np.float32(0.9941), np.float32(0.7757)] +2025-10-30 09:06:18.482472: Epoch time: 22.02 s +2025-10-30 09:06:19.646287: +2025-10-30 09:06:19.648955: Epoch 80 +2025-10-30 09:06:19.651138: Current learning rate: 0.00928 +2025-10-30 09:06:41.605078: train_loss -0.9751 +2025-10-30 09:06:41.608368: val_loss -0.8845 +2025-10-30 09:06:41.609797: Pseudo dice [np.float32(0.9811), np.float32(0.9871), np.float32(0.9934), np.float32(0.7578)] +2025-10-30 09:06:41.611485: Epoch time: 21.96 s +2025-10-30 09:06:42.875668: +2025-10-30 09:06:42.877838: Epoch 81 +2025-10-30 09:06:42.879533: Current learning rate: 0.00927 +2025-10-30 09:07:04.428539: train_loss -0.9767 +2025-10-30 09:07:04.430472: val_loss -0.8873 +2025-10-30 09:07:04.432141: Pseudo dice [np.float32(0.9819), np.float32(0.9884), np.float32(0.9932), np.float32(0.7541)] +2025-10-30 09:07:04.433772: Epoch time: 21.55 s +2025-10-30 09:07:05.513972: +2025-10-30 09:07:05.516807: Epoch 82 +2025-10-30 09:07:05.518435: Current learning rate: 0.00926 +2025-10-30 09:07:25.178500: train_loss -0.9789 +2025-10-30 09:07:25.180894: val_loss -0.8942 +2025-10-30 09:07:25.182647: Pseudo dice [np.float32(0.9823), np.float32(0.988), np.float32(0.9943), np.float32(0.7776)] +2025-10-30 09:07:25.184256: Epoch time: 19.67 s +2025-10-30 09:07:26.176965: +2025-10-30 09:07:26.179245: Epoch 83 +2025-10-30 09:07:26.181210: Current learning rate: 0.00925 +2025-10-30 09:07:47.805746: train_loss -0.9774 +2025-10-30 09:07:47.808147: val_loss -0.8907 +2025-10-30 09:07:47.809885: Pseudo dice [np.float32(0.9812), np.float32(0.9872), np.float32(0.994), np.float32(0.764)] +2025-10-30 09:07:47.811708: Epoch time: 21.63 s +2025-10-30 09:07:48.809066: +2025-10-30 09:07:48.811439: Epoch 84 +2025-10-30 09:07:48.813690: Current learning rate: 0.00924 +2025-10-30 09:08:10.883475: train_loss -0.9797 +2025-10-30 09:08:10.885175: val_loss -0.8946 +2025-10-30 09:08:10.887572: Pseudo dice [np.float32(0.9823), np.float32(0.988), np.float32(0.9943), np.float32(0.7812)] +2025-10-30 09:08:10.889298: Epoch time: 22.08 s +2025-10-30 09:08:12.610318: +2025-10-30 09:08:12.612642: Epoch 85 +2025-10-30 09:08:12.614736: Current learning rate: 0.00923 +2025-10-30 09:08:34.437582: train_loss -0.9768 +2025-10-30 09:08:34.440428: val_loss -0.8084 +2025-10-30 09:08:34.441900: Pseudo dice [np.float32(0.9818), np.float32(0.9668), np.float32(0.9733), np.float32(0.7429)] +2025-10-30 09:08:34.443338: Epoch time: 21.83 s +2025-10-30 09:08:35.574976: +2025-10-30 09:08:35.576816: Epoch 86 +2025-10-30 09:08:35.578328: Current learning rate: 0.00922 +2025-10-30 09:08:57.506665: train_loss -0.9713 +2025-10-30 09:08:57.509400: val_loss -0.8909 +2025-10-30 09:08:57.510945: Pseudo dice [np.float32(0.9786), np.float32(0.9868), np.float32(0.9945), np.float32(0.7762)] +2025-10-30 09:08:57.512262: Epoch time: 21.93 s +2025-10-30 09:08:58.740959: +2025-10-30 09:08:58.745776: Epoch 87 +2025-10-30 09:08:58.748028: Current learning rate: 0.00921 +2025-10-30 09:09:20.538333: train_loss -0.9723 +2025-10-30 09:09:20.540920: val_loss -0.8886 +2025-10-30 09:09:20.542690: Pseudo dice [np.float32(0.9808), np.float32(0.9871), np.float32(0.994), np.float32(0.7703)] +2025-10-30 09:09:20.544418: Epoch time: 21.8 s +2025-10-30 09:09:21.602692: +2025-10-30 09:09:21.604583: Epoch 88 +2025-10-30 09:09:21.606112: Current learning rate: 0.0092 +2025-10-30 09:09:42.950567: train_loss -0.976 +2025-10-30 09:09:42.953341: val_loss -0.8988 +2025-10-30 09:09:42.955122: Pseudo dice [np.float32(0.9814), np.float32(0.9881), np.float32(0.9949), np.float32(0.7885)] +2025-10-30 09:09:42.956960: Epoch time: 21.35 s +2025-10-30 09:09:44.155625: +2025-10-30 09:09:44.157828: Epoch 89 +2025-10-30 09:09:44.160086: Current learning rate: 0.0092 +2025-10-30 09:10:05.050035: train_loss -0.9788 +2025-10-30 09:10:05.053517: val_loss -0.8923 +2025-10-30 09:10:05.055316: Pseudo dice [np.float32(0.9803), np.float32(0.9867), np.float32(0.9942), np.float32(0.7805)] +2025-10-30 09:10:05.057652: Epoch time: 20.9 s +2025-10-30 09:10:06.145365: +2025-10-30 09:10:06.147509: Epoch 90 +2025-10-30 09:10:06.149489: Current learning rate: 0.00919 +2025-10-30 09:10:27.747802: train_loss -0.9794 +2025-10-30 09:10:27.750329: val_loss -0.8905 +2025-10-30 09:10:27.752194: Pseudo dice [np.float32(0.9808), np.float32(0.988), np.float32(0.9941), np.float32(0.7618)] +2025-10-30 09:10:27.753887: Epoch time: 21.6 s +2025-10-30 09:10:28.751307: +2025-10-30 09:10:28.754019: Epoch 91 +2025-10-30 09:10:28.758464: Current learning rate: 0.00918 +2025-10-30 09:10:50.526835: train_loss -0.9777 +2025-10-30 09:10:50.529355: val_loss -0.8882 +2025-10-30 09:10:50.531090: Pseudo dice [np.float32(0.9826), np.float32(0.9882), np.float32(0.9939), np.float32(0.7555)] +2025-10-30 09:10:50.532553: Epoch time: 21.78 s +2025-10-30 09:10:51.526329: +2025-10-30 09:10:51.528198: Epoch 92 +2025-10-30 09:10:51.530035: Current learning rate: 0.00917 +2025-10-30 09:11:13.306863: train_loss -0.9789 +2025-10-30 09:11:13.309664: val_loss -0.8914 +2025-10-30 09:11:13.311206: Pseudo dice [np.float32(0.9825), np.float32(0.9883), np.float32(0.9938), np.float32(0.7667)] +2025-10-30 09:11:13.312701: Epoch time: 21.78 s +2025-10-30 09:11:14.478403: +2025-10-30 09:11:14.480328: Epoch 93 +2025-10-30 09:11:14.481935: Current learning rate: 0.00916 +2025-10-30 09:11:36.052255: train_loss -0.9793 +2025-10-30 09:11:36.054950: val_loss -0.8893 +2025-10-30 09:11:36.057192: Pseudo dice [np.float32(0.9813), np.float32(0.9884), np.float32(0.9936), np.float32(0.7777)] +2025-10-30 09:11:36.059487: Epoch time: 21.58 s +2025-10-30 09:11:37.124365: +2025-10-30 09:11:37.126372: Epoch 94 +2025-10-30 09:11:37.128063: Current learning rate: 0.00915 +2025-10-30 09:11:58.223155: train_loss -0.9762 +2025-10-30 09:11:58.225720: val_loss -0.899 +2025-10-30 09:11:58.227543: Pseudo dice [np.float32(0.9809), np.float32(0.9884), np.float32(0.9945), np.float32(0.7919)] +2025-10-30 09:11:58.229281: Epoch time: 21.1 s +2025-10-30 09:11:59.222088: +2025-10-30 09:11:59.223857: Epoch 95 +2025-10-30 09:11:59.225427: Current learning rate: 0.00914 +2025-10-30 09:12:19.963271: train_loss -0.9765 +2025-10-30 09:12:19.969607: val_loss -0.8951 +2025-10-30 09:12:19.971317: Pseudo dice [np.float32(0.9804), np.float32(0.9877), np.float32(0.9943), np.float32(0.7847)] +2025-10-30 09:12:19.973516: Epoch time: 20.74 s +2025-10-30 09:12:21.165658: +2025-10-30 09:12:21.168887: Epoch 96 +2025-10-30 09:12:21.173542: Current learning rate: 0.00913 +2025-10-30 09:12:42.990985: train_loss -0.9792 +2025-10-30 09:12:42.994904: val_loss -0.8913 +2025-10-30 09:12:42.996442: Pseudo dice [np.float32(0.9831), np.float32(0.9891), np.float32(0.9941), np.float32(0.7668)] +2025-10-30 09:12:42.998148: Epoch time: 21.83 s +2025-10-30 09:12:44.106930: +2025-10-30 09:12:44.109056: Epoch 97 +2025-10-30 09:12:44.111067: Current learning rate: 0.00912 +2025-10-30 09:13:05.893137: train_loss -0.9802 +2025-10-30 09:13:05.896134: val_loss -0.8779 +2025-10-30 09:13:05.898042: Pseudo dice [np.float32(0.9818), np.float32(0.9882), np.float32(0.9934), np.float32(0.7486)] +2025-10-30 09:13:05.899993: Epoch time: 21.79 s +2025-10-30 09:13:07.059984: +2025-10-30 09:13:07.062033: Epoch 98 +2025-10-30 09:13:07.064012: Current learning rate: 0.00911 +2025-10-30 09:13:29.082569: train_loss -0.9793 +2025-10-30 09:13:29.086491: val_loss -0.8874 +2025-10-30 09:13:29.088126: Pseudo dice [np.float32(0.9817), np.float32(0.989), np.float32(0.9944), np.float32(0.7561)] +2025-10-30 09:13:29.089805: Epoch time: 22.02 s +2025-10-30 09:13:30.215770: +2025-10-30 09:13:30.217724: Epoch 99 +2025-10-30 09:13:30.219559: Current learning rate: 0.0091 +2025-10-30 09:13:52.149354: train_loss -0.9809 +2025-10-30 09:13:52.152330: val_loss -0.8952 +2025-10-30 09:13:52.154604: Pseudo dice [np.float32(0.9829), np.float32(0.9887), np.float32(0.9945), np.float32(0.7816)] +2025-10-30 09:13:52.156539: Epoch time: 21.94 s +2025-10-30 09:13:54.533752: +2025-10-30 09:13:54.535613: Epoch 100 +2025-10-30 09:13:54.537216: Current learning rate: 0.0091 +2025-10-30 09:14:15.734361: train_loss -0.9812 +2025-10-30 09:14:15.737917: val_loss -0.8916 +2025-10-30 09:14:15.741685: Pseudo dice [np.float32(0.9813), np.float32(0.9874), np.float32(0.994), np.float32(0.785)] +2025-10-30 09:14:15.744849: Epoch time: 21.2 s +2025-10-30 09:14:16.940822: +2025-10-30 09:14:16.943433: Epoch 101 +2025-10-30 09:14:16.945584: Current learning rate: 0.00909 +2025-10-30 09:14:38.664647: train_loss -0.9799 +2025-10-30 09:14:38.667634: val_loss -0.8944 +2025-10-30 09:14:38.669540: Pseudo dice [np.float32(0.983), np.float32(0.989), np.float32(0.9943), np.float32(0.7804)] +2025-10-30 09:14:38.671089: Epoch time: 21.73 s +2025-10-30 09:14:39.880462: +2025-10-30 09:14:39.885022: Epoch 102 +2025-10-30 09:14:39.888294: Current learning rate: 0.00908 +2025-10-30 09:15:00.890722: train_loss -0.9793 +2025-10-30 09:15:00.893934: val_loss -0.8918 +2025-10-30 09:15:00.895766: Pseudo dice [np.float32(0.9808), np.float32(0.9883), np.float32(0.9943), np.float32(0.7685)] +2025-10-30 09:15:00.897412: Epoch time: 21.01 s +2025-10-30 09:15:02.672871: +2025-10-30 09:15:02.674949: Epoch 103 +2025-10-30 09:15:02.677439: Current learning rate: 0.00907 +2025-10-30 09:15:24.496261: train_loss -0.9796 +2025-10-30 09:15:24.498258: val_loss -0.8803 +2025-10-30 09:15:24.499897: Pseudo dice [np.float32(0.9813), np.float32(0.9879), np.float32(0.9939), np.float32(0.747)] +2025-10-30 09:15:24.501675: Epoch time: 21.82 s +2025-10-30 09:15:25.520141: +2025-10-30 09:15:25.522462: Epoch 104 +2025-10-30 09:15:25.524447: Current learning rate: 0.00906 +2025-10-30 09:15:47.573608: train_loss -0.9794 +2025-10-30 09:15:47.576924: val_loss -0.8795 +2025-10-30 09:15:47.578707: Pseudo dice [np.float32(0.9826), np.float32(0.988), np.float32(0.9933), np.float32(0.7418)] +2025-10-30 09:15:47.582091: Epoch time: 22.06 s +2025-10-30 09:15:48.778795: +2025-10-30 09:15:48.780931: Epoch 105 +2025-10-30 09:15:48.782931: Current learning rate: 0.00905 +2025-10-30 09:16:10.841282: train_loss -0.9814 +2025-10-30 09:16:10.844217: val_loss -0.889 +2025-10-30 09:16:10.846126: Pseudo dice [np.float32(0.9807), np.float32(0.9882), np.float32(0.9939), np.float32(0.7654)] +2025-10-30 09:16:10.847983: Epoch time: 22.06 s +2025-10-30 09:16:11.983259: +2025-10-30 09:16:11.985322: Epoch 106 +2025-10-30 09:16:11.986865: Current learning rate: 0.00904 +2025-10-30 09:16:32.622756: train_loss -0.9795 +2025-10-30 09:16:32.625102: val_loss -0.8927 +2025-10-30 09:16:32.626785: Pseudo dice [np.float32(0.9801), np.float32(0.9882), np.float32(0.9942), np.float32(0.7755)] +2025-10-30 09:16:32.628359: Epoch time: 20.64 s +2025-10-30 09:16:33.683654: +2025-10-30 09:16:33.686131: Epoch 107 +2025-10-30 09:16:33.688092: Current learning rate: 0.00903 +2025-10-30 09:16:55.791827: train_loss -0.9809 +2025-10-30 09:16:55.795347: val_loss -0.8818 +2025-10-30 09:16:55.797292: Pseudo dice [np.float32(0.9811), np.float32(0.9884), np.float32(0.9937), np.float32(0.746)] +2025-10-30 09:16:55.799078: Epoch time: 22.11 s +2025-10-30 09:16:56.920255: +2025-10-30 09:16:56.922085: Epoch 108 +2025-10-30 09:16:56.924124: Current learning rate: 0.00902 +2025-10-30 09:17:16.898966: train_loss -0.9801 +2025-10-30 09:17:16.900785: val_loss -0.8926 +2025-10-30 09:17:16.902865: Pseudo dice [np.float32(0.9788), np.float32(0.9867), np.float32(0.994), np.float32(0.7939)] +2025-10-30 09:17:16.904455: Epoch time: 19.98 s +2025-10-30 09:17:17.932947: +2025-10-30 09:17:17.935658: Epoch 109 +2025-10-30 09:17:17.937985: Current learning rate: 0.00901 +2025-10-30 09:17:39.808760: train_loss -0.977 +2025-10-30 09:17:39.816121: val_loss -0.894 +2025-10-30 09:17:39.823373: Pseudo dice [np.float32(0.9809), np.float32(0.9871), np.float32(0.9937), np.float32(0.7823)] +2025-10-30 09:17:39.831900: Epoch time: 21.88 s +2025-10-30 09:17:41.028940: +2025-10-30 09:17:41.031085: Epoch 110 +2025-10-30 09:17:41.032718: Current learning rate: 0.009 +2025-10-30 09:18:03.112227: train_loss -0.9794 +2025-10-30 09:18:03.116092: val_loss -0.8779 +2025-10-30 09:18:03.118236: Pseudo dice [np.float32(0.9814), np.float32(0.9883), np.float32(0.9933), np.float32(0.7402)] +2025-10-30 09:18:03.119981: Epoch time: 22.09 s +2025-10-30 09:18:04.139968: +2025-10-30 09:18:04.143845: Epoch 111 +2025-10-30 09:18:04.147190: Current learning rate: 0.009 +2025-10-30 09:18:25.921799: train_loss -0.9809 +2025-10-30 09:18:25.924201: val_loss -0.8943 +2025-10-30 09:18:25.925743: Pseudo dice [np.float32(0.9818), np.float32(0.988), np.float32(0.9944), np.float32(0.7887)] +2025-10-30 09:18:25.927410: Epoch time: 21.78 s +2025-10-30 09:18:26.981581: +2025-10-30 09:18:26.983430: Epoch 112 +2025-10-30 09:18:26.985097: Current learning rate: 0.00899 +2025-10-30 09:18:47.764665: train_loss -0.981 +2025-10-30 09:18:47.767205: val_loss -0.895 +2025-10-30 09:18:47.769081: Pseudo dice [np.float32(0.9828), np.float32(0.9883), np.float32(0.9942), np.float32(0.7881)] +2025-10-30 09:18:47.770876: Epoch time: 20.78 s +2025-10-30 09:18:48.944306: +2025-10-30 09:18:48.946576: Epoch 113 +2025-10-30 09:18:48.948602: Current learning rate: 0.00898 +2025-10-30 09:19:10.915298: train_loss -0.983 +2025-10-30 09:19:10.919014: val_loss -0.8888 +2025-10-30 09:19:10.924330: Pseudo dice [np.float32(0.9829), np.float32(0.9885), np.float32(0.994), np.float32(0.7716)] +2025-10-30 09:19:10.928257: Epoch time: 21.97 s +2025-10-30 09:19:12.158959: +2025-10-30 09:19:12.162118: Epoch 114 +2025-10-30 09:19:12.164204: Current learning rate: 0.00897 +2025-10-30 09:19:33.749207: train_loss -0.9825 +2025-10-30 09:19:33.751662: val_loss -0.8862 +2025-10-30 09:19:33.757194: Pseudo dice [np.float32(0.9832), np.float32(0.9881), np.float32(0.9937), np.float32(0.766)] +2025-10-30 09:19:33.762135: Epoch time: 21.59 s +2025-10-30 09:19:34.807242: +2025-10-30 09:19:34.809821: Epoch 115 +2025-10-30 09:19:34.812042: Current learning rate: 0.00896 +2025-10-30 09:19:54.947425: train_loss -0.9829 +2025-10-30 09:19:54.956040: val_loss -0.8869 +2025-10-30 09:19:54.957606: Pseudo dice [np.float32(0.9817), np.float32(0.9874), np.float32(0.9937), np.float32(0.7678)] +2025-10-30 09:19:54.959179: Epoch time: 20.14 s +2025-10-30 09:19:56.058940: +2025-10-30 09:19:56.063037: Epoch 116 +2025-10-30 09:19:56.064744: Current learning rate: 0.00895 +2025-10-30 09:20:17.593153: train_loss -0.9816 +2025-10-30 09:20:17.596668: val_loss -0.8797 +2025-10-30 09:20:17.598997: Pseudo dice [np.float32(0.9814), np.float32(0.9876), np.float32(0.9931), np.float32(0.7521)] +2025-10-30 09:20:17.601081: Epoch time: 21.54 s +2025-10-30 09:20:18.832065: +2025-10-30 09:20:18.838998: Epoch 117 +2025-10-30 09:20:18.848089: Current learning rate: 0.00894 +2025-10-30 09:20:40.527355: train_loss -0.982 +2025-10-30 09:20:40.529915: val_loss -0.8768 +2025-10-30 09:20:40.531744: Pseudo dice [np.float32(0.9805), np.float32(0.9868), np.float32(0.9934), np.float32(0.7469)] +2025-10-30 09:20:40.533458: Epoch time: 21.7 s +2025-10-30 09:20:41.819869: +2025-10-30 09:20:41.821805: Epoch 118 +2025-10-30 09:20:41.823911: Current learning rate: 0.00893 +2025-10-30 09:21:02.686812: train_loss -0.9822 +2025-10-30 09:21:02.693258: val_loss -0.8686 +2025-10-30 09:21:02.695827: Pseudo dice [np.float32(0.9805), np.float32(0.987), np.float32(0.993), np.float32(0.7221)] +2025-10-30 09:21:02.700163: Epoch time: 20.87 s +2025-10-30 09:21:03.805630: +2025-10-30 09:21:03.807476: Epoch 119 +2025-10-30 09:21:03.809107: Current learning rate: 0.00892 +2025-10-30 09:21:25.360895: train_loss -0.9819 +2025-10-30 09:21:25.363733: val_loss -0.8849 +2025-10-30 09:21:25.366193: Pseudo dice [np.float32(0.9829), np.float32(0.9881), np.float32(0.9938), np.float32(0.7577)] +2025-10-30 09:21:25.369573: Epoch time: 21.56 s +2025-10-30 09:21:26.412715: +2025-10-30 09:21:26.417444: Epoch 120 +2025-10-30 09:21:26.419418: Current learning rate: 0.00891 +2025-10-30 09:21:48.180319: train_loss -0.9815 +2025-10-30 09:21:48.184426: val_loss -0.8841 +2025-10-30 09:21:48.189058: Pseudo dice [np.float32(0.9819), np.float32(0.9882), np.float32(0.994), np.float32(0.7636)] +2025-10-30 09:21:48.191218: Epoch time: 21.77 s +2025-10-30 09:21:50.158446: +2025-10-30 09:21:50.161057: Epoch 121 +2025-10-30 09:21:50.162671: Current learning rate: 0.0089 +2025-10-30 09:22:11.811761: train_loss -0.9825 +2025-10-30 09:22:11.819022: val_loss -0.8819 +2025-10-30 09:22:11.821147: Pseudo dice [np.float32(0.9807), np.float32(0.9872), np.float32(0.9941), np.float32(0.7612)] +2025-10-30 09:22:11.823208: Epoch time: 21.66 s +2025-10-30 09:22:13.101777: +2025-10-30 09:22:13.103831: Epoch 122 +2025-10-30 09:22:13.105653: Current learning rate: 0.00889 +2025-10-30 09:22:33.881286: train_loss -0.9827 +2025-10-30 09:22:33.886135: val_loss -0.8897 +2025-10-30 09:22:33.887973: Pseudo dice [np.float32(0.9825), np.float32(0.9889), np.float32(0.994), np.float32(0.7761)] +2025-10-30 09:22:33.889775: Epoch time: 20.78 s +2025-10-30 09:22:34.958503: +2025-10-30 09:22:34.963769: Epoch 123 +2025-10-30 09:22:34.966031: Current learning rate: 0.00889 +2025-10-30 09:22:56.792928: train_loss -0.9828 +2025-10-30 09:22:56.795708: val_loss -0.8919 +2025-10-30 09:22:56.797868: Pseudo dice [np.float32(0.9815), np.float32(0.9878), np.float32(0.9946), np.float32(0.7894)] +2025-10-30 09:22:56.799987: Epoch time: 21.84 s +2025-10-30 09:22:57.816383: +2025-10-30 09:22:57.818723: Epoch 124 +2025-10-30 09:22:57.820567: Current learning rate: 0.00888 +2025-10-30 09:23:18.341061: train_loss -0.9816 +2025-10-30 09:23:18.345544: val_loss -0.872 +2025-10-30 09:23:18.349057: Pseudo dice [np.float32(0.9833), np.float32(0.9885), np.float32(0.9931), np.float32(0.7271)] +2025-10-30 09:23:18.355018: Epoch time: 20.53 s +2025-10-30 09:23:19.434927: +2025-10-30 09:23:19.437498: Epoch 125 +2025-10-30 09:23:19.439514: Current learning rate: 0.00887 +2025-10-30 09:23:41.209981: train_loss -0.9827 +2025-10-30 09:23:41.213380: val_loss -0.8839 +2025-10-30 09:23:41.215048: Pseudo dice [np.float32(0.983), np.float32(0.988), np.float32(0.9936), np.float32(0.7658)] +2025-10-30 09:23:41.216778: Epoch time: 21.78 s +2025-10-30 09:23:42.499696: +2025-10-30 09:23:42.511016: Epoch 126 +2025-10-30 09:23:42.512985: Current learning rate: 0.00886 +2025-10-30 09:24:04.415224: train_loss -0.9836 +2025-10-30 09:24:04.418196: val_loss -0.8829 +2025-10-30 09:24:04.421938: Pseudo dice [np.float32(0.9809), np.float32(0.9879), np.float32(0.9938), np.float32(0.7662)] +2025-10-30 09:24:04.424199: Epoch time: 21.92 s +2025-10-30 09:24:05.620022: +2025-10-30 09:24:05.623111: Epoch 127 +2025-10-30 09:24:05.625823: Current learning rate: 0.00885 +2025-10-30 09:24:27.412328: train_loss -0.981 +2025-10-30 09:24:27.415356: val_loss -0.897 +2025-10-30 09:24:27.417161: Pseudo dice [np.float32(0.9822), np.float32(0.9882), np.float32(0.9946), np.float32(0.794)] +2025-10-30 09:24:27.418867: Epoch time: 21.79 s +2025-10-30 09:24:28.681676: +2025-10-30 09:24:28.683751: Epoch 128 +2025-10-30 09:24:28.685518: Current learning rate: 0.00884 +2025-10-30 09:24:48.686609: train_loss -0.9799 +2025-10-30 09:24:48.691228: val_loss -0.8908 +2025-10-30 09:24:48.693600: Pseudo dice [np.float32(0.982), np.float32(0.9883), np.float32(0.9937), np.float32(0.7812)] +2025-10-30 09:24:48.695858: Epoch time: 20.01 s +2025-10-30 09:24:49.850837: +2025-10-30 09:24:49.855182: Epoch 129 +2025-10-30 09:24:49.860367: Current learning rate: 0.00883 +2025-10-30 09:25:11.364673: train_loss -0.9813 +2025-10-30 09:25:11.368000: val_loss -0.8893 +2025-10-30 09:25:11.369849: Pseudo dice [np.float32(0.9805), np.float32(0.9883), np.float32(0.9942), np.float32(0.7724)] +2025-10-30 09:25:11.372215: Epoch time: 21.52 s +2025-10-30 09:25:12.559253: +2025-10-30 09:25:12.562611: Epoch 130 +2025-10-30 09:25:12.567987: Current learning rate: 0.00882 +2025-10-30 09:25:33.411275: train_loss -0.9813 +2025-10-30 09:25:33.414869: val_loss -0.8883 +2025-10-30 09:25:33.417008: Pseudo dice [np.float32(0.9806), np.float32(0.9879), np.float32(0.9941), np.float32(0.774)] +2025-10-30 09:25:33.419490: Epoch time: 20.85 s +2025-10-30 09:25:34.684874: +2025-10-30 09:25:34.687179: Epoch 131 +2025-10-30 09:25:34.689101: Current learning rate: 0.00881 +2025-10-30 09:25:56.469235: train_loss -0.9808 +2025-10-30 09:25:56.472388: val_loss -0.879 +2025-10-30 09:25:56.474618: Pseudo dice [np.float32(0.9813), np.float32(0.987), np.float32(0.9933), np.float32(0.7534)] +2025-10-30 09:25:56.476446: Epoch time: 21.79 s +2025-10-30 09:25:57.500883: +2025-10-30 09:25:57.502972: Epoch 132 +2025-10-30 09:25:57.505352: Current learning rate: 0.0088 +2025-10-30 09:26:19.636890: train_loss -0.9822 +2025-10-30 09:26:19.638879: val_loss -0.8691 +2025-10-30 09:26:19.641094: Pseudo dice [np.float32(0.9799), np.float32(0.9868), np.float32(0.9938), np.float32(0.741)] +2025-10-30 09:26:19.647739: Epoch time: 22.14 s +2025-10-30 09:26:20.832822: +2025-10-30 09:26:20.835378: Epoch 133 +2025-10-30 09:26:20.837288: Current learning rate: 0.00879 +2025-10-30 09:26:42.637488: train_loss -0.9844 +2025-10-30 09:26:42.640570: val_loss -0.8873 +2025-10-30 09:26:42.642366: Pseudo dice [np.float32(0.9817), np.float32(0.9872), np.float32(0.994), np.float32(0.7793)] +2025-10-30 09:26:42.645194: Epoch time: 21.81 s +2025-10-30 09:26:43.833529: +2025-10-30 09:26:43.835412: Epoch 134 +2025-10-30 09:26:43.837160: Current learning rate: 0.00879 +2025-10-30 09:27:06.038281: train_loss -0.9839 +2025-10-30 09:27:06.041121: val_loss -0.8855 +2025-10-30 09:27:06.043077: Pseudo dice [np.float32(0.9826), np.float32(0.9878), np.float32(0.9935), np.float32(0.7691)] +2025-10-30 09:27:06.045074: Epoch time: 22.21 s +2025-10-30 09:27:07.311084: +2025-10-30 09:27:07.313033: Epoch 135 +2025-10-30 09:27:07.315106: Current learning rate: 0.00878 +2025-10-30 09:27:28.008126: train_loss -0.9843 +2025-10-30 09:27:28.010571: val_loss -0.8944 +2025-10-30 09:27:28.013144: Pseudo dice [np.float32(0.9831), np.float32(0.989), np.float32(0.9945), np.float32(0.7811)] +2025-10-30 09:27:28.015286: Epoch time: 20.7 s +2025-10-30 09:27:29.114128: +2025-10-30 09:27:29.116988: Epoch 136 +2025-10-30 09:27:29.118671: Current learning rate: 0.00877 +2025-10-30 09:27:50.546057: train_loss -0.9839 +2025-10-30 09:27:50.548790: val_loss -0.8858 +2025-10-30 09:27:50.553624: Pseudo dice [np.float32(0.9829), np.float32(0.989), np.float32(0.9942), np.float32(0.7683)] +2025-10-30 09:27:50.556676: Epoch time: 21.43 s +2025-10-30 09:27:51.573976: +2025-10-30 09:27:51.577950: Epoch 137 +2025-10-30 09:27:51.580712: Current learning rate: 0.00876 +2025-10-30 09:28:11.836488: train_loss -0.9827 +2025-10-30 09:28:11.840662: val_loss -0.8808 +2025-10-30 09:28:11.843580: Pseudo dice [np.float32(0.9811), np.float32(0.9873), np.float32(0.9932), np.float32(0.7487)] +2025-10-30 09:28:11.846080: Epoch time: 20.26 s +2025-10-30 09:28:13.712754: +2025-10-30 09:28:13.715046: Epoch 138 +2025-10-30 09:28:13.720869: Current learning rate: 0.00875 +2025-10-30 09:28:35.087603: train_loss -0.9815 +2025-10-30 09:28:35.090153: val_loss -0.8966 +2025-10-30 09:28:35.092177: Pseudo dice [np.float32(0.9817), np.float32(0.9888), np.float32(0.9946), np.float32(0.7967)] +2025-10-30 09:28:35.093903: Epoch time: 21.38 s +2025-10-30 09:28:36.113057: +2025-10-30 09:28:36.114990: Epoch 139 +2025-10-30 09:28:36.117306: Current learning rate: 0.00874 +2025-10-30 09:28:57.840393: train_loss -0.9833 +2025-10-30 09:28:57.842917: val_loss -0.8796 +2025-10-30 09:28:57.889028: Pseudo dice [np.float32(0.9824), np.float32(0.988), np.float32(0.9936), np.float32(0.7536)] +2025-10-30 09:28:57.892049: Epoch time: 21.73 s +2025-10-30 09:28:59.144361: +2025-10-30 09:28:59.146460: Epoch 140 +2025-10-30 09:28:59.148926: Current learning rate: 0.00873 +2025-10-30 09:29:20.711784: train_loss -0.9852 +2025-10-30 09:29:20.715555: val_loss -0.8846 +2025-10-30 09:29:20.721703: Pseudo dice [np.float32(0.9818), np.float32(0.9888), np.float32(0.994), np.float32(0.7672)] +2025-10-30 09:29:20.724150: Epoch time: 21.57 s +2025-10-30 09:29:21.908896: +2025-10-30 09:29:21.911597: Epoch 141 +2025-10-30 09:29:21.915368: Current learning rate: 0.00872 +2025-10-30 09:29:42.570634: train_loss -0.9829 +2025-10-30 09:29:42.573139: val_loss -0.8775 +2025-10-30 09:29:42.574850: Pseudo dice [np.float32(0.9802), np.float32(0.9874), np.float32(0.9932), np.float32(0.7504)] +2025-10-30 09:29:42.576381: Epoch time: 20.66 s +2025-10-30 09:29:43.725837: +2025-10-30 09:29:43.727986: Epoch 142 +2025-10-30 09:29:43.729608: Current learning rate: 0.00871 +2025-10-30 09:30:05.270612: train_loss -0.9824 +2025-10-30 09:30:05.272907: val_loss -0.8825 +2025-10-30 09:30:05.274619: Pseudo dice [np.float32(0.9832), np.float32(0.9885), np.float32(0.9938), np.float32(0.7605)] +2025-10-30 09:30:05.276294: Epoch time: 21.55 s +2025-10-30 09:30:06.369471: +2025-10-30 09:30:06.371136: Epoch 143 +2025-10-30 09:30:06.372737: Current learning rate: 0.0087 +2025-10-30 09:30:26.852696: train_loss -0.9831 +2025-10-30 09:30:26.859073: val_loss -0.8867 +2025-10-30 09:30:26.861148: Pseudo dice [np.float32(0.982), np.float32(0.9888), np.float32(0.9942), np.float32(0.7656)] +2025-10-30 09:30:26.863086: Epoch time: 20.48 s +2025-10-30 09:30:28.071225: +2025-10-30 09:30:28.073785: Epoch 144 +2025-10-30 09:30:28.075711: Current learning rate: 0.00869 +2025-10-30 09:30:49.907574: train_loss -0.9847 +2025-10-30 09:30:49.923742: val_loss -0.886 +2025-10-30 09:30:49.931208: Pseudo dice [np.float32(0.983), np.float32(0.9891), np.float32(0.9938), np.float32(0.7695)] +2025-10-30 09:30:49.938482: Epoch time: 21.84 s +2025-10-30 09:30:51.003817: +2025-10-30 09:30:51.006397: Epoch 145 +2025-10-30 09:30:51.009307: Current learning rate: 0.00868 +2025-10-30 09:31:12.721825: train_loss -0.982 +2025-10-30 09:31:12.724589: val_loss -0.8857 +2025-10-30 09:31:12.726800: Pseudo dice [np.float32(0.981), np.float32(0.9886), np.float32(0.9942), np.float32(0.766)] +2025-10-30 09:31:12.728591: Epoch time: 21.72 s +2025-10-30 09:31:14.042338: +2025-10-30 09:31:14.045545: Epoch 146 +2025-10-30 09:31:14.050095: Current learning rate: 0.00868 +2025-10-30 09:31:36.093684: train_loss -0.9832 +2025-10-30 09:31:36.098382: val_loss -0.8843 +2025-10-30 09:31:36.100077: Pseudo dice [np.float32(0.9831), np.float32(0.9885), np.float32(0.9939), np.float32(0.7595)] +2025-10-30 09:31:36.102268: Epoch time: 22.05 s +2025-10-30 09:31:37.316686: +2025-10-30 09:31:37.318878: Epoch 147 +2025-10-30 09:31:37.320672: Current learning rate: 0.00867 +2025-10-30 09:31:58.630866: train_loss -0.9828 +2025-10-30 09:31:58.633384: val_loss -0.8786 +2025-10-30 09:31:58.635118: Pseudo dice [np.float32(0.9804), np.float32(0.9882), np.float32(0.9941), np.float32(0.7553)] +2025-10-30 09:31:58.636589: Epoch time: 21.32 s +2025-10-30 09:31:59.743323: +2025-10-30 09:31:59.745507: Epoch 148 +2025-10-30 09:31:59.747219: Current learning rate: 0.00866 +2025-10-30 09:32:19.862283: train_loss -0.9843 +2025-10-30 09:32:19.865429: val_loss -0.8911 +2025-10-30 09:32:19.867091: Pseudo dice [np.float32(0.9836), np.float32(0.9893), np.float32(0.9942), np.float32(0.7773)] +2025-10-30 09:32:19.868706: Epoch time: 20.12 s +2025-10-30 09:32:21.140806: +2025-10-30 09:32:21.143742: Epoch 149 +2025-10-30 09:32:21.146801: Current learning rate: 0.00865 +2025-10-30 09:32:41.072592: train_loss -0.985 +2025-10-30 09:32:41.079057: val_loss -0.8815 +2025-10-30 09:32:41.081342: Pseudo dice [np.float32(0.9819), np.float32(0.9874), np.float32(0.9943), np.float32(0.7644)] +2025-10-30 09:32:41.083061: Epoch time: 19.93 s +2025-10-30 09:32:43.833452: +2025-10-30 09:32:43.835899: Epoch 150 +2025-10-30 09:32:43.838218: Current learning rate: 0.00864 +2025-10-30 09:33:05.590202: train_loss -0.9841 +2025-10-30 09:33:05.593009: val_loss -0.8853 +2025-10-30 09:33:05.601790: Pseudo dice [np.float32(0.9822), np.float32(0.99), np.float32(0.9942), np.float32(0.7555)] +2025-10-30 09:33:05.604425: Epoch time: 21.76 s +2025-10-30 09:33:06.699053: +2025-10-30 09:33:06.701319: Epoch 151 +2025-10-30 09:33:06.703048: Current learning rate: 0.00863 +2025-10-30 09:33:28.444548: train_loss -0.9831 +2025-10-30 09:33:28.448169: val_loss -0.8806 +2025-10-30 09:33:28.449953: Pseudo dice [np.float32(0.984), np.float32(0.9894), np.float32(0.994), np.float32(0.7377)] +2025-10-30 09:33:28.451639: Epoch time: 21.75 s +2025-10-30 09:33:29.765431: +2025-10-30 09:33:29.767752: Epoch 152 +2025-10-30 09:33:29.769380: Current learning rate: 0.00862 +2025-10-30 09:33:51.444011: train_loss -0.9839 +2025-10-30 09:33:51.447465: val_loss -0.8779 +2025-10-30 09:33:51.449326: Pseudo dice [np.float32(0.9816), np.float32(0.9871), np.float32(0.9937), np.float32(0.757)] +2025-10-30 09:33:51.451769: Epoch time: 21.68 s +2025-10-30 09:33:52.490326: +2025-10-30 09:33:52.492311: Epoch 153 +2025-10-30 09:33:52.494665: Current learning rate: 0.00861 +2025-10-30 09:34:14.049802: train_loss -0.9795 +2025-10-30 09:34:14.052467: val_loss -0.8907 +2025-10-30 09:34:14.054093: Pseudo dice [np.float32(0.9803), np.float32(0.9873), np.float32(0.9945), np.float32(0.7915)] +2025-10-30 09:34:14.055674: Epoch time: 21.56 s +2025-10-30 09:34:15.095156: +2025-10-30 09:34:15.097555: Epoch 154 +2025-10-30 09:34:15.099581: Current learning rate: 0.0086 +2025-10-30 09:34:34.657429: train_loss -0.9804 +2025-10-30 09:34:34.660069: val_loss -0.8758 +2025-10-30 09:34:34.661998: Pseudo dice [np.float32(0.9807), np.float32(0.9876), np.float32(0.9932), np.float32(0.747)] +2025-10-30 09:34:34.663760: Epoch time: 19.56 s +2025-10-30 09:34:36.634958: +2025-10-30 09:34:36.636974: Epoch 155 +2025-10-30 09:34:36.638760: Current learning rate: 0.00859 +2025-10-30 09:34:57.229156: train_loss -0.9842 +2025-10-30 09:34:57.232690: val_loss -0.8799 +2025-10-30 09:34:57.234170: Pseudo dice [np.float32(0.9831), np.float32(0.9889), np.float32(0.9941), np.float32(0.7561)] +2025-10-30 09:34:57.235703: Epoch time: 20.6 s +2025-10-30 09:34:58.495992: +2025-10-30 09:34:58.498610: Epoch 156 +2025-10-30 09:34:58.501039: Current learning rate: 0.00858 +2025-10-30 09:35:20.289324: train_loss -0.9846 +2025-10-30 09:35:20.292742: val_loss -0.8813 +2025-10-30 09:35:20.295081: Pseudo dice [np.float32(0.9829), np.float32(0.9891), np.float32(0.9942), np.float32(0.7697)] +2025-10-30 09:35:20.297190: Epoch time: 21.8 s +2025-10-30 09:35:21.536813: +2025-10-30 09:35:21.539200: Epoch 157 +2025-10-30 09:35:21.541019: Current learning rate: 0.00858 +2025-10-30 09:35:43.742266: train_loss -0.9839 +2025-10-30 09:35:43.744577: val_loss -0.8871 +2025-10-30 09:35:43.747221: Pseudo dice [np.float32(0.983), np.float32(0.989), np.float32(0.9937), np.float32(0.7602)] +2025-10-30 09:35:43.749788: Epoch time: 22.21 s +2025-10-30 09:35:44.964416: +2025-10-30 09:35:44.966179: Epoch 158 +2025-10-30 09:35:44.967671: Current learning rate: 0.00857 +2025-10-30 09:36:07.724443: train_loss -0.9779 +2025-10-30 09:36:07.727709: val_loss -0.8744 +2025-10-30 09:36:07.729476: Pseudo dice [np.float32(0.9806), np.float32(0.9862), np.float32(0.993), np.float32(0.7429)] +2025-10-30 09:36:07.731209: Epoch time: 22.76 s +2025-10-30 09:36:08.957174: +2025-10-30 09:36:08.959214: Epoch 159 +2025-10-30 09:36:08.961004: Current learning rate: 0.00856 +2025-10-30 09:36:31.525472: train_loss -0.9676 +2025-10-30 09:36:31.528199: val_loss -0.8703 +2025-10-30 09:36:31.530535: Pseudo dice [np.float32(0.9807), np.float32(0.9869), np.float32(0.9804), np.float32(0.7897)] +2025-10-30 09:36:31.533618: Epoch time: 22.57 s +2025-10-30 09:36:32.841262: +2025-10-30 09:36:32.844030: Epoch 160 +2025-10-30 09:36:32.846283: Current learning rate: 0.00855 +2025-10-30 09:36:55.591518: train_loss -0.954 +2025-10-30 09:36:55.596100: val_loss -0.9116 +2025-10-30 09:36:55.597896: Pseudo dice [np.float32(0.9803), np.float32(0.9879), np.float32(0.9941), np.float32(0.8026)] +2025-10-30 09:36:55.599642: Epoch time: 22.75 s +2025-10-30 09:36:56.823866: +2025-10-30 09:36:56.826241: Epoch 161 +2025-10-30 09:36:56.828635: Current learning rate: 0.00854 +2025-10-30 09:37:16.594162: train_loss -0.9571 +2025-10-30 09:37:16.602353: val_loss -0.8963 +2025-10-30 09:37:16.605419: Pseudo dice [np.float32(0.9822), np.float32(0.9873), np.float32(0.9935), np.float32(0.7724)] +2025-10-30 09:37:16.608269: Epoch time: 19.77 s +2025-10-30 09:37:17.703385: +2025-10-30 09:37:17.705712: Epoch 162 +2025-10-30 09:37:17.707541: Current learning rate: 0.00853 +2025-10-30 09:37:40.534383: train_loss -0.9701 +2025-10-30 09:37:40.536976: val_loss -0.8927 +2025-10-30 09:37:40.538705: Pseudo dice [np.float32(0.9818), np.float32(0.9877), np.float32(0.9941), np.float32(0.7567)] +2025-10-30 09:37:40.540363: Epoch time: 22.83 s +2025-10-30 09:37:41.590307: +2025-10-30 09:37:41.592511: Epoch 163 +2025-10-30 09:37:41.594030: Current learning rate: 0.00852 +2025-10-30 09:38:03.343186: train_loss -0.975 +2025-10-30 09:38:03.346547: val_loss -0.9018 +2025-10-30 09:38:03.348562: Pseudo dice [np.float32(0.9818), np.float32(0.9876), np.float32(0.9942), np.float32(0.7884)] +2025-10-30 09:38:03.350164: Epoch time: 21.75 s +2025-10-30 09:38:04.576854: +2025-10-30 09:38:04.579393: Epoch 164 +2025-10-30 09:38:04.643475: Current learning rate: 0.00851 +2025-10-30 09:38:26.576540: train_loss -0.9762 +2025-10-30 09:38:26.579487: val_loss -0.896 +2025-10-30 09:38:26.581170: Pseudo dice [np.float32(0.9821), np.float32(0.9885), np.float32(0.9943), np.float32(0.7713)] +2025-10-30 09:38:26.582763: Epoch time: 22.0 s +2025-10-30 09:38:27.724241: +2025-10-30 09:38:27.732493: Epoch 165 +2025-10-30 09:38:27.740581: Current learning rate: 0.0085 +2025-10-30 09:38:49.917552: train_loss -0.981 +2025-10-30 09:38:49.919965: val_loss -0.8982 +2025-10-30 09:38:49.922212: Pseudo dice [np.float32(0.9819), np.float32(0.9869), np.float32(0.994), np.float32(0.7918)] +2025-10-30 09:38:49.924517: Epoch time: 22.19 s +2025-10-30 09:38:51.140612: +2025-10-30 09:38:51.143530: Epoch 166 +2025-10-30 09:38:51.150324: Current learning rate: 0.00849 +2025-10-30 09:39:13.728204: train_loss -0.9822 +2025-10-30 09:39:13.730474: val_loss -0.8762 +2025-10-30 09:39:13.732023: Pseudo dice [np.float32(0.9813), np.float32(0.9877), np.float32(0.9931), np.float32(0.7384)] +2025-10-30 09:39:13.734495: Epoch time: 22.59 s +2025-10-30 09:39:15.008643: +2025-10-30 09:39:15.012019: Epoch 167 +2025-10-30 09:39:15.013463: Current learning rate: 0.00848 +2025-10-30 09:39:33.616614: train_loss -0.9829 +2025-10-30 09:39:33.623853: val_loss -0.8843 +2025-10-30 09:39:33.633833: Pseudo dice [np.float32(0.9805), np.float32(0.9872), np.float32(0.9936), np.float32(0.7629)] +2025-10-30 09:39:33.642950: Epoch time: 18.61 s +2025-10-30 09:39:34.976195: +2025-10-30 09:39:34.978802: Epoch 168 +2025-10-30 09:39:34.980531: Current learning rate: 0.00847 +2025-10-30 09:39:56.900536: train_loss -0.9825 +2025-10-30 09:39:56.903799: val_loss -0.8975 +2025-10-30 09:39:56.908806: Pseudo dice [np.float32(0.9813), np.float32(0.9877), np.float32(0.9942), np.float32(0.7961)] +2025-10-30 09:39:56.910706: Epoch time: 21.93 s +2025-10-30 09:39:57.962379: +2025-10-30 09:39:57.964246: Epoch 169 +2025-10-30 09:39:57.965977: Current learning rate: 0.00847 +2025-10-30 09:40:20.063374: train_loss -0.983 +2025-10-30 09:40:20.069326: val_loss -0.8985 +2025-10-30 09:40:20.072416: Pseudo dice [np.float32(0.9837), np.float32(0.9886), np.float32(0.9945), np.float32(0.7829)] +2025-10-30 09:40:20.074940: Epoch time: 22.1 s +2025-10-30 09:40:21.233844: +2025-10-30 09:40:21.236386: Epoch 170 +2025-10-30 09:40:21.238248: Current learning rate: 0.00846 +2025-10-30 09:40:43.626295: train_loss -0.9842 +2025-10-30 09:40:43.632184: val_loss -0.8934 +2025-10-30 09:40:43.634033: Pseudo dice [np.float32(0.982), np.float32(0.9888), np.float32(0.9945), np.float32(0.7868)] +2025-10-30 09:40:43.635504: Epoch time: 22.39 s +2025-10-30 09:40:44.920087: +2025-10-30 09:40:44.921780: Epoch 171 +2025-10-30 09:40:44.923373: Current learning rate: 0.00845 +2025-10-30 09:41:07.413151: train_loss -0.9852 +2025-10-30 09:41:07.416087: val_loss -0.8896 +2025-10-30 09:41:07.419205: Pseudo dice [np.float32(0.9797), np.float32(0.9872), np.float32(0.9945), np.float32(0.7791)] +2025-10-30 09:41:07.421278: Epoch time: 22.49 s +2025-10-30 09:41:09.510485: +2025-10-30 09:41:09.515307: Epoch 172 +2025-10-30 09:41:09.517014: Current learning rate: 0.00844 +2025-10-30 09:41:31.374603: train_loss -0.9853 +2025-10-30 09:41:31.377689: val_loss -0.8798 +2025-10-30 09:41:31.379650: Pseudo dice [np.float32(0.9803), np.float32(0.9884), np.float32(0.9942), np.float32(0.7609)] +2025-10-30 09:41:31.381246: Epoch time: 21.87 s +2025-10-30 09:41:32.554271: +2025-10-30 09:41:32.556479: Epoch 173 +2025-10-30 09:41:32.558223: Current learning rate: 0.00843 +2025-10-30 09:41:52.706924: train_loss -0.985 +2025-10-30 09:41:52.709455: val_loss -0.8941 +2025-10-30 09:41:52.711483: Pseudo dice [np.float32(0.9808), np.float32(0.9875), np.float32(0.9947), np.float32(0.7878)] +2025-10-30 09:41:52.713044: Epoch time: 20.15 s +2025-10-30 09:41:53.988284: +2025-10-30 09:41:53.990365: Epoch 174 +2025-10-30 09:41:53.991921: Current learning rate: 0.00842 +2025-10-30 09:42:14.531817: train_loss -0.9852 +2025-10-30 09:42:14.539165: val_loss -0.8853 +2025-10-30 09:42:14.541989: Pseudo dice [np.float32(0.9808), np.float32(0.9878), np.float32(0.9942), np.float32(0.7676)] +2025-10-30 09:42:14.543612: Epoch time: 20.55 s +2025-10-30 09:42:15.892560: +2025-10-30 09:42:15.894795: Epoch 175 +2025-10-30 09:42:15.896388: Current learning rate: 0.00841 +2025-10-30 09:42:38.416169: train_loss -0.9849 +2025-10-30 09:42:38.428613: val_loss -0.8747 +2025-10-30 09:42:38.435815: Pseudo dice [np.float32(0.9817), np.float32(0.9888), np.float32(0.9938), np.float32(0.7383)] +2025-10-30 09:42:38.439582: Epoch time: 22.53 s +2025-10-30 09:42:39.729530: +2025-10-30 09:42:39.738048: Epoch 176 +2025-10-30 09:42:39.747291: Current learning rate: 0.0084 +2025-10-30 09:43:01.696353: train_loss -0.984 +2025-10-30 09:43:01.701939: val_loss -0.8701 +2025-10-30 09:43:01.704341: Pseudo dice [np.float32(0.9809), np.float32(0.9882), np.float32(0.9933), np.float32(0.7385)] +2025-10-30 09:43:01.707015: Epoch time: 21.97 s +2025-10-30 09:43:02.940737: +2025-10-30 09:43:02.942846: Epoch 177 +2025-10-30 09:43:02.944589: Current learning rate: 0.00839 +2025-10-30 09:43:25.015603: train_loss -0.9832 +2025-10-30 09:43:25.018232: val_loss -0.8953 +2025-10-30 09:43:25.020080: Pseudo dice [np.float32(0.984), np.float32(0.9896), np.float32(0.9941), np.float32(0.7836)] +2025-10-30 09:43:25.023278: Epoch time: 22.08 s +2025-10-30 09:43:26.240466: +2025-10-30 09:43:26.242813: Epoch 178 +2025-10-30 09:43:26.246865: Current learning rate: 0.00838 +2025-10-30 09:43:49.081044: train_loss -0.9847 +2025-10-30 09:43:49.084912: val_loss -0.8798 +2025-10-30 09:43:49.086641: Pseudo dice [np.float32(0.9805), np.float32(0.9874), np.float32(0.9934), np.float32(0.7674)] +2025-10-30 09:43:49.088781: Epoch time: 22.84 s +2025-10-30 09:43:50.179040: +2025-10-30 09:43:50.180778: Epoch 179 +2025-10-30 09:43:50.182317: Current learning rate: 0.00837 +2025-10-30 09:44:11.618089: train_loss -0.985 +2025-10-30 09:44:11.624280: val_loss -0.8816 +2025-10-30 09:44:11.628793: Pseudo dice [np.float32(0.9808), np.float32(0.9878), np.float32(0.9938), np.float32(0.7654)] +2025-10-30 09:44:11.630347: Epoch time: 21.44 s +2025-10-30 09:44:12.674109: +2025-10-30 09:44:12.676479: Epoch 180 +2025-10-30 09:44:12.678591: Current learning rate: 0.00836 +2025-10-30 09:44:32.828844: train_loss -0.9856 +2025-10-30 09:44:32.830879: val_loss -0.8828 +2025-10-30 09:44:32.833814: Pseudo dice [np.float32(0.9814), np.float32(0.9882), np.float32(0.9939), np.float32(0.7709)] +2025-10-30 09:44:32.835276: Epoch time: 20.16 s +2025-10-30 09:44:34.020323: +2025-10-30 09:44:34.022111: Epoch 181 +2025-10-30 09:44:34.023866: Current learning rate: 0.00836 +2025-10-30 09:44:56.266217: train_loss -0.9844 +2025-10-30 09:44:56.270519: val_loss -0.8831 +2025-10-30 09:44:56.273004: Pseudo dice [np.float32(0.9818), np.float32(0.9884), np.float32(0.9938), np.float32(0.7643)] +2025-10-30 09:44:56.276754: Epoch time: 22.25 s +2025-10-30 09:44:57.348302: +2025-10-30 09:44:57.359406: Epoch 182 +2025-10-30 09:44:57.373468: Current learning rate: 0.00835 +2025-10-30 09:45:19.572467: train_loss -0.9856 +2025-10-30 09:45:19.579736: val_loss -0.8797 +2025-10-30 09:45:19.582286: Pseudo dice [np.float32(0.9808), np.float32(0.9881), np.float32(0.9942), np.float32(0.7657)] +2025-10-30 09:45:19.584008: Epoch time: 22.23 s +2025-10-30 09:45:20.850138: +2025-10-30 09:45:20.852273: Epoch 183 +2025-10-30 09:45:20.854688: Current learning rate: 0.00834 +2025-10-30 09:45:43.142958: train_loss -0.9851 +2025-10-30 09:45:43.145661: val_loss -0.8895 +2025-10-30 09:45:43.147437: Pseudo dice [np.float32(0.9817), np.float32(0.9884), np.float32(0.9945), np.float32(0.7773)] +2025-10-30 09:45:43.149785: Epoch time: 22.29 s +2025-10-30 09:45:44.376901: +2025-10-30 09:45:44.379101: Epoch 184 +2025-10-30 09:45:44.380545: Current learning rate: 0.00833 +2025-10-30 09:46:06.207056: train_loss -0.9831 +2025-10-30 09:46:06.209721: val_loss -0.8877 +2025-10-30 09:46:06.211989: Pseudo dice [np.float32(0.9808), np.float32(0.9881), np.float32(0.9941), np.float32(0.7738)] +2025-10-30 09:46:06.213669: Epoch time: 21.83 s +2025-10-30 09:46:07.388403: +2025-10-30 09:46:07.390178: Epoch 185 +2025-10-30 09:46:07.391508: Current learning rate: 0.00832 +2025-10-30 09:46:28.751821: train_loss -0.9844 +2025-10-30 09:46:28.754687: val_loss -0.8894 +2025-10-30 09:46:28.756122: Pseudo dice [np.float32(0.9805), np.float32(0.987), np.float32(0.9942), np.float32(0.7786)] +2025-10-30 09:46:28.757664: Epoch time: 21.36 s +2025-10-30 09:46:29.901343: +2025-10-30 09:46:29.906844: Epoch 186 +2025-10-30 09:46:29.908739: Current learning rate: 0.00831 +2025-10-30 09:46:52.025440: train_loss -0.9857 +2025-10-30 09:46:52.028026: val_loss -0.8853 +2025-10-30 09:46:52.029831: Pseudo dice [np.float32(0.983), np.float32(0.9887), np.float32(0.9938), np.float32(0.7659)] +2025-10-30 09:46:52.031709: Epoch time: 22.13 s +2025-10-30 09:46:53.243098: +2025-10-30 09:46:53.244853: Epoch 187 +2025-10-30 09:46:53.246393: Current learning rate: 0.0083 +2025-10-30 09:47:13.692680: train_loss -0.9849 +2025-10-30 09:47:13.695535: val_loss -0.892 +2025-10-30 09:47:13.697355: Pseudo dice [np.float32(0.9826), np.float32(0.9887), np.float32(0.9948), np.float32(0.7989)] +2025-10-30 09:47:13.700129: Epoch time: 20.45 s +2025-10-30 09:47:14.924098: +2025-10-30 09:47:14.925999: Epoch 188 +2025-10-30 09:47:14.927674: Current learning rate: 0.00829 +2025-10-30 09:47:37.094955: train_loss -0.9856 +2025-10-30 09:47:37.097722: val_loss -0.8904 +2025-10-30 09:47:37.101054: Pseudo dice [np.float32(0.983), np.float32(0.9888), np.float32(0.9945), np.float32(0.7838)] +2025-10-30 09:47:37.104193: Epoch time: 22.17 s +2025-10-30 09:47:39.184818: +2025-10-30 09:47:39.187249: Epoch 189 +2025-10-30 09:47:39.192374: Current learning rate: 0.00828 +2025-10-30 09:48:00.675032: train_loss -0.9853 +2025-10-30 09:48:00.678238: val_loss -0.8685 +2025-10-30 09:48:00.680212: Pseudo dice [np.float32(0.9788), np.float32(0.9869), np.float32(0.9934), np.float32(0.7478)] +2025-10-30 09:48:00.682095: Epoch time: 21.49 s +2025-10-30 09:48:01.897533: +2025-10-30 09:48:01.902479: Epoch 190 +2025-10-30 09:48:01.905435: Current learning rate: 0.00827 +2025-10-30 09:48:23.796170: train_loss -0.9869 +2025-10-30 09:48:23.799215: val_loss -0.8843 +2025-10-30 09:48:23.801602: Pseudo dice [np.float32(0.9816), np.float32(0.988), np.float32(0.9943), np.float32(0.773)] +2025-10-30 09:48:23.803415: Epoch time: 21.9 s +2025-10-30 09:48:25.090469: +2025-10-30 09:48:25.093261: Epoch 191 +2025-10-30 09:48:25.095570: Current learning rate: 0.00826 +2025-10-30 09:48:46.561494: train_loss -0.9851 +2025-10-30 09:48:46.567434: val_loss -0.8853 +2025-10-30 09:48:46.569325: Pseudo dice [np.float32(0.9818), np.float32(0.9878), np.float32(0.994), np.float32(0.774)] +2025-10-30 09:48:46.571082: Epoch time: 21.47 s +2025-10-30 09:48:47.842079: +2025-10-30 09:48:47.844803: Epoch 192 +2025-10-30 09:48:47.846792: Current learning rate: 0.00825 +2025-10-30 09:49:10.093501: train_loss -0.9857 +2025-10-30 09:49:10.095614: val_loss -0.8849 +2025-10-30 09:49:10.097210: Pseudo dice [np.float32(0.9828), np.float32(0.9891), np.float32(0.9943), np.float32(0.7662)] +2025-10-30 09:49:10.099695: Epoch time: 22.25 s +2025-10-30 09:49:11.286082: +2025-10-30 09:49:11.288202: Epoch 193 +2025-10-30 09:49:11.290236: Current learning rate: 0.00824 +2025-10-30 09:49:31.853037: train_loss -0.9861 +2025-10-30 09:49:31.857944: val_loss -0.8893 +2025-10-30 09:49:31.861182: Pseudo dice [np.float32(0.9825), np.float32(0.989), np.float32(0.9942), np.float32(0.7745)] +2025-10-30 09:49:31.863875: Epoch time: 20.57 s +2025-10-30 09:49:33.008802: +2025-10-30 09:49:33.010559: Epoch 194 +2025-10-30 09:49:33.011971: Current learning rate: 0.00824 +2025-10-30 09:49:55.180717: train_loss -0.9853 +2025-10-30 09:49:55.183851: val_loss -0.8954 +2025-10-30 09:49:55.185379: Pseudo dice [np.float32(0.9823), np.float32(0.9883), np.float32(0.9948), np.float32(0.8008)] +2025-10-30 09:49:55.189458: Epoch time: 22.17 s +2025-10-30 09:49:56.505221: +2025-10-30 09:49:56.508219: Epoch 195 +2025-10-30 09:49:56.512510: Current learning rate: 0.00823 +2025-10-30 09:50:18.300724: train_loss -0.9857 +2025-10-30 09:50:18.304127: val_loss -0.8863 +2025-10-30 09:50:18.306503: Pseudo dice [np.float32(0.9823), np.float32(0.9879), np.float32(0.9942), np.float32(0.7764)] +2025-10-30 09:50:18.310248: Epoch time: 21.8 s +2025-10-30 09:50:19.496460: +2025-10-30 09:50:19.498818: Epoch 196 +2025-10-30 09:50:19.500580: Current learning rate: 0.00822 +2025-10-30 09:50:41.726478: train_loss -0.9843 +2025-10-30 09:50:41.729788: val_loss -0.8834 +2025-10-30 09:50:41.731852: Pseudo dice [np.float32(0.9825), np.float32(0.9882), np.float32(0.9936), np.float32(0.7595)] +2025-10-30 09:50:41.733554: Epoch time: 22.23 s +2025-10-30 09:50:42.797894: +2025-10-30 09:50:42.802489: Epoch 197 +2025-10-30 09:50:42.806070: Current learning rate: 0.00821 +2025-10-30 09:51:04.447818: train_loss -0.9847 +2025-10-30 09:51:04.451120: val_loss -0.8859 +2025-10-30 09:51:04.452909: Pseudo dice [np.float32(0.9803), np.float32(0.9881), np.float32(0.9943), np.float32(0.7717)] +2025-10-30 09:51:04.455097: Epoch time: 21.65 s +2025-10-30 09:51:05.719013: +2025-10-30 09:51:05.720752: Epoch 198 +2025-10-30 09:51:05.722249: Current learning rate: 0.0082 +2025-10-30 09:51:28.042977: train_loss -0.9843 +2025-10-30 09:51:28.047311: val_loss -0.8917 +2025-10-30 09:51:28.049121: Pseudo dice [np.float32(0.9837), np.float32(0.9895), np.float32(0.9944), np.float32(0.7838)] +2025-10-30 09:51:28.050872: Epoch time: 22.33 s +2025-10-30 09:51:29.325722: +2025-10-30 09:51:29.328049: Epoch 199 +2025-10-30 09:51:29.329789: Current learning rate: 0.00819 +2025-10-30 09:51:51.123513: train_loss -0.9849 +2025-10-30 09:51:51.130480: val_loss -0.8906 +2025-10-30 09:51:51.132272: Pseudo dice [np.float32(0.9821), np.float32(0.9885), np.float32(0.9945), np.float32(0.7758)] +2025-10-30 09:51:51.134268: Epoch time: 21.8 s +2025-10-30 09:51:53.759603: +2025-10-30 09:51:53.762520: Epoch 200 +2025-10-30 09:51:53.764923: Current learning rate: 0.00818 +2025-10-30 09:52:15.278696: train_loss -0.9856 +2025-10-30 09:52:15.283632: val_loss -0.8889 +2025-10-30 09:52:15.285479: Pseudo dice [np.float32(0.9819), np.float32(0.9875), np.float32(0.9944), np.float32(0.7877)] +2025-10-30 09:52:15.287128: Epoch time: 21.52 s +2025-10-30 09:52:16.469214: +2025-10-30 09:52:16.472959: Epoch 201 +2025-10-30 09:52:16.476349: Current learning rate: 0.00817 +2025-10-30 09:52:38.847506: train_loss -0.9846 +2025-10-30 09:52:38.852772: val_loss -0.896 +2025-10-30 09:52:38.854639: Pseudo dice [np.float32(0.983), np.float32(0.9895), np.float32(0.9946), np.float32(0.7915)] +2025-10-30 09:52:38.856276: Epoch time: 22.38 s +2025-10-30 09:52:40.123830: +2025-10-30 09:52:40.126101: Epoch 202 +2025-10-30 09:52:40.127878: Current learning rate: 0.00816 +2025-10-30 09:53:02.872040: train_loss -0.9854 +2025-10-30 09:53:02.880907: val_loss -0.8788 +2025-10-30 09:53:02.888009: Pseudo dice [np.float32(0.9807), np.float32(0.9886), np.float32(0.994), np.float32(0.7586)] +2025-10-30 09:53:02.895519: Epoch time: 22.75 s +2025-10-30 09:53:04.156548: +2025-10-30 09:53:04.158334: Epoch 203 +2025-10-30 09:53:04.160115: Current learning rate: 0.00815 +2025-10-30 09:53:25.433675: train_loss -0.9861 +2025-10-30 09:53:25.436608: val_loss -0.8884 +2025-10-30 09:53:25.438473: Pseudo dice [np.float32(0.9824), np.float32(0.9883), np.float32(0.994), np.float32(0.7805)] +2025-10-30 09:53:25.440422: Epoch time: 21.28 s +2025-10-30 09:53:26.601623: +2025-10-30 09:53:26.603632: Epoch 204 +2025-10-30 09:53:26.605261: Current learning rate: 0.00814 +2025-10-30 09:53:48.400724: train_loss -0.9856 +2025-10-30 09:53:48.404319: val_loss -0.8805 +2025-10-30 09:53:48.406440: Pseudo dice [np.float32(0.9825), np.float32(0.9886), np.float32(0.9935), np.float32(0.7593)] +2025-10-30 09:53:48.408647: Epoch time: 21.8 s +2025-10-30 09:53:50.571852: +2025-10-30 09:53:50.573639: Epoch 205 +2025-10-30 09:53:50.575030: Current learning rate: 0.00813 +2025-10-30 09:54:12.525427: train_loss -0.9855 +2025-10-30 09:54:12.528634: val_loss -0.8715 +2025-10-30 09:54:12.531465: Pseudo dice [np.float32(0.9801), np.float32(0.9866), np.float32(0.9935), np.float32(0.7527)] +2025-10-30 09:54:12.533780: Epoch time: 21.96 s +2025-10-30 09:54:13.758022: +2025-10-30 09:54:13.772511: Epoch 206 +2025-10-30 09:54:13.778964: Current learning rate: 0.00813 +2025-10-30 09:54:35.318716: train_loss -0.9792 +2025-10-30 09:54:35.324446: val_loss -0.8802 +2025-10-30 09:54:35.326942: Pseudo dice [np.float32(0.9798), np.float32(0.9865), np.float32(0.9939), np.float32(0.7611)] +2025-10-30 09:54:35.328666: Epoch time: 21.56 s +2025-10-30 09:54:36.429347: +2025-10-30 09:54:36.435416: Epoch 207 +2025-10-30 09:54:36.440892: Current learning rate: 0.00812 +2025-10-30 09:54:58.544055: train_loss -0.9817 +2025-10-30 09:54:58.547157: val_loss -0.8919 +2025-10-30 09:54:58.549265: Pseudo dice [np.float32(0.9805), np.float32(0.987), np.float32(0.9942), np.float32(0.7924)] +2025-10-30 09:54:58.551779: Epoch time: 22.12 s +2025-10-30 09:54:59.747501: +2025-10-30 09:54:59.750133: Epoch 208 +2025-10-30 09:54:59.753053: Current learning rate: 0.00811 +2025-10-30 09:55:22.096330: train_loss -0.9841 +2025-10-30 09:55:22.103857: val_loss -0.8839 +2025-10-30 09:55:22.106677: Pseudo dice [np.float32(0.9811), np.float32(0.9878), np.float32(0.9939), np.float32(0.7603)] +2025-10-30 09:55:22.109083: Epoch time: 22.35 s +2025-10-30 09:55:23.394704: +2025-10-30 09:55:23.396881: Epoch 209 +2025-10-30 09:55:23.398928: Current learning rate: 0.0081 +2025-10-30 09:55:44.508605: train_loss -0.9818 +2025-10-30 09:55:44.519782: val_loss -0.8826 +2025-10-30 09:55:44.522775: Pseudo dice [np.float32(0.9822), np.float32(0.9881), np.float32(0.9939), np.float32(0.7664)] +2025-10-30 09:55:44.525495: Epoch time: 21.12 s +2025-10-30 09:55:45.727147: +2025-10-30 09:55:45.731314: Epoch 210 +2025-10-30 09:55:45.735956: Current learning rate: 0.00809 +2025-10-30 09:56:07.518462: train_loss -0.984 +2025-10-30 09:56:07.521122: val_loss -0.8855 +2025-10-30 09:56:07.523396: Pseudo dice [np.float32(0.9821), np.float32(0.988), np.float32(0.9943), np.float32(0.7743)] +2025-10-30 09:56:07.525678: Epoch time: 21.79 s +2025-10-30 09:56:08.807414: +2025-10-30 09:56:08.809766: Epoch 211 +2025-10-30 09:56:08.811919: Current learning rate: 0.00808 +2025-10-30 09:56:31.006593: train_loss -0.9855 +2025-10-30 09:56:31.011711: val_loss -0.8837 +2025-10-30 09:56:31.014537: Pseudo dice [np.float32(0.9813), np.float32(0.9868), np.float32(0.9942), np.float32(0.7795)] +2025-10-30 09:56:31.017538: Epoch time: 22.2 s +2025-10-30 09:56:32.203812: +2025-10-30 09:56:32.207952: Epoch 212 +2025-10-30 09:56:32.210690: Current learning rate: 0.00807 +2025-10-30 09:56:53.453051: train_loss -0.9853 +2025-10-30 09:56:53.458830: val_loss -0.8917 +2025-10-30 09:56:53.460821: Pseudo dice [np.float32(0.9823), np.float32(0.9881), np.float32(0.9942), np.float32(0.7889)] +2025-10-30 09:56:53.462329: Epoch time: 21.25 s +2025-10-30 09:56:54.690000: +2025-10-30 09:56:54.692938: Epoch 213 +2025-10-30 09:56:54.695515: Current learning rate: 0.00806 +2025-10-30 09:57:17.078894: train_loss -0.9859 +2025-10-30 09:57:17.082426: val_loss -0.901 +2025-10-30 09:57:17.086055: Pseudo dice [np.float32(0.982), np.float32(0.9888), np.float32(0.995), np.float32(0.8093)] +2025-10-30 09:57:17.090595: Epoch time: 22.39 s +2025-10-30 09:57:18.339243: +2025-10-30 09:57:18.341449: Epoch 214 +2025-10-30 09:57:18.344328: Current learning rate: 0.00805 +2025-10-30 09:57:40.362938: train_loss -0.9836 +2025-10-30 09:57:40.369057: val_loss -0.8846 +2025-10-30 09:57:40.370850: Pseudo dice [np.float32(0.9829), np.float32(0.9892), np.float32(0.9939), np.float32(0.7673)] +2025-10-30 09:57:40.372438: Epoch time: 22.03 s +2025-10-30 09:57:41.553283: +2025-10-30 09:57:41.556123: Epoch 215 +2025-10-30 09:57:41.557927: Current learning rate: 0.00804 +2025-10-30 09:58:02.771746: train_loss -0.9815 +2025-10-30 09:58:02.779589: val_loss -0.8893 +2025-10-30 09:58:02.782268: Pseudo dice [np.float32(0.9829), np.float32(0.9888), np.float32(0.994), np.float32(0.7715)] +2025-10-30 09:58:02.783921: Epoch time: 21.22 s +2025-10-30 09:58:04.032115: +2025-10-30 09:58:04.037769: Epoch 216 +2025-10-30 09:58:04.041576: Current learning rate: 0.00803 +2025-10-30 09:58:26.548864: train_loss -0.9837 +2025-10-30 09:58:26.551328: val_loss -0.8884 +2025-10-30 09:58:26.552946: Pseudo dice [np.float32(0.9821), np.float32(0.9881), np.float32(0.9939), np.float32(0.7901)] +2025-10-30 09:58:26.554645: Epoch time: 22.52 s +2025-10-30 09:58:27.761258: +2025-10-30 09:58:27.763795: Epoch 217 +2025-10-30 09:58:27.765623: Current learning rate: 0.00802 +2025-10-30 09:58:50.250159: train_loss -0.9845 +2025-10-30 09:58:50.253399: val_loss -0.8849 +2025-10-30 09:58:50.256214: Pseudo dice [np.float32(0.9831), np.float32(0.9885), np.float32(0.9936), np.float32(0.7575)] +2025-10-30 09:58:50.257903: Epoch time: 22.49 s +2025-10-30 09:58:51.484448: +2025-10-30 09:58:51.486825: Epoch 218 +2025-10-30 09:58:51.488978: Current learning rate: 0.00801 +2025-10-30 09:59:13.558687: train_loss -0.9856 +2025-10-30 09:59:13.561875: val_loss -0.8928 +2025-10-30 09:59:13.563642: Pseudo dice [np.float32(0.9825), np.float32(0.9882), np.float32(0.9943), np.float32(0.7862)] +2025-10-30 09:59:13.565137: Epoch time: 22.08 s +2025-10-30 09:59:14.848745: +2025-10-30 09:59:14.851020: Epoch 219 +2025-10-30 09:59:14.854922: Current learning rate: 0.00801 +2025-10-30 09:59:36.106021: train_loss -0.9852 +2025-10-30 09:59:36.111443: val_loss -0.8843 +2025-10-30 09:59:36.113341: Pseudo dice [np.float32(0.9827), np.float32(0.9883), np.float32(0.9941), np.float32(0.7607)] +2025-10-30 09:59:36.114837: Epoch time: 21.26 s +2025-10-30 09:59:37.363593: +2025-10-30 09:59:37.365337: Epoch 220 +2025-10-30 09:59:37.366877: Current learning rate: 0.008 +2025-10-30 09:59:59.668159: train_loss -0.9868 +2025-10-30 09:59:59.670870: val_loss -0.8897 +2025-10-30 09:59:59.672456: Pseudo dice [np.float32(0.9842), np.float32(0.9894), np.float32(0.9944), np.float32(0.7737)] +2025-10-30 09:59:59.673843: Epoch time: 22.31 s +2025-10-30 10:00:00.779952: +2025-10-30 10:00:00.782529: Epoch 221 +2025-10-30 10:00:00.784458: Current learning rate: 0.00799 +2025-10-30 10:00:21.957602: train_loss -0.9875 +2025-10-30 10:00:21.960974: val_loss -0.8842 +2025-10-30 10:00:21.962842: Pseudo dice [np.float32(0.9817), np.float32(0.9881), np.float32(0.9942), np.float32(0.7603)] +2025-10-30 10:00:21.965756: Epoch time: 21.18 s +2025-10-30 10:00:23.974032: +2025-10-30 10:00:23.978173: Epoch 222 +2025-10-30 10:00:23.981517: Current learning rate: 0.00798 +2025-10-30 10:00:46.354049: train_loss -0.987 +2025-10-30 10:00:46.357110: val_loss -0.8914 +2025-10-30 10:00:46.359328: Pseudo dice [np.float32(0.9822), np.float32(0.9878), np.float32(0.9943), np.float32(0.7915)] +2025-10-30 10:00:46.361098: Epoch time: 22.38 s +2025-10-30 10:00:47.588477: +2025-10-30 10:00:47.590799: Epoch 223 +2025-10-30 10:00:47.592710: Current learning rate: 0.00797 +2025-10-30 10:01:09.708175: train_loss -0.9887 +2025-10-30 10:01:09.710750: val_loss -0.888 +2025-10-30 10:01:09.712328: Pseudo dice [np.float32(0.9817), np.float32(0.9881), np.float32(0.9942), np.float32(0.7853)] +2025-10-30 10:01:09.714126: Epoch time: 22.12 s +2025-10-30 10:01:10.915839: +2025-10-30 10:01:10.919761: Epoch 224 +2025-10-30 10:01:10.922071: Current learning rate: 0.00796 +2025-10-30 10:01:33.437886: train_loss -0.9835 +2025-10-30 10:01:33.441293: val_loss -0.8942 +2025-10-30 10:01:33.442884: Pseudo dice [np.float32(0.9816), np.float32(0.9872), np.float32(0.9936), np.float32(0.7953)] +2025-10-30 10:01:33.444752: Epoch time: 22.52 s +2025-10-30 10:01:34.753094: +2025-10-30 10:01:34.755517: Epoch 225 +2025-10-30 10:01:34.757845: Current learning rate: 0.00795 +2025-10-30 10:01:56.176673: train_loss -0.9854 +2025-10-30 10:01:56.179459: val_loss -0.8776 +2025-10-30 10:01:56.181444: Pseudo dice [np.float32(0.9808), np.float32(0.9865), np.float32(0.9941), np.float32(0.7684)] +2025-10-30 10:01:56.183444: Epoch time: 21.43 s +2025-10-30 10:01:57.417813: +2025-10-30 10:01:57.420300: Epoch 226 +2025-10-30 10:01:57.422307: Current learning rate: 0.00794 +2025-10-30 10:02:19.017776: train_loss -0.9857 +2025-10-30 10:02:19.020506: val_loss -0.8755 +2025-10-30 10:02:19.023082: Pseudo dice [np.float32(0.9818), np.float32(0.9885), np.float32(0.993), np.float32(0.7455)] +2025-10-30 10:02:19.024997: Epoch time: 21.6 s +2025-10-30 10:02:20.208539: +2025-10-30 10:02:20.215634: Epoch 227 +2025-10-30 10:02:20.235383: Current learning rate: 0.00793 +2025-10-30 10:02:41.833180: train_loss -0.9877 +2025-10-30 10:02:41.835607: val_loss -0.8837 +2025-10-30 10:02:41.836994: Pseudo dice [np.float32(0.9805), np.float32(0.9883), np.float32(0.9942), np.float32(0.7754)] +2025-10-30 10:02:41.838951: Epoch time: 21.63 s +2025-10-30 10:02:43.067497: +2025-10-30 10:02:43.070106: Epoch 228 +2025-10-30 10:02:43.072115: Current learning rate: 0.00792 +2025-10-30 10:03:05.282144: train_loss -0.9867 +2025-10-30 10:03:05.286755: val_loss -0.8877 +2025-10-30 10:03:05.289662: Pseudo dice [np.float32(0.9805), np.float32(0.9868), np.float32(0.9939), np.float32(0.7875)] +2025-10-30 10:03:05.291643: Epoch time: 22.22 s +2025-10-30 10:03:06.367587: +2025-10-30 10:03:06.369686: Epoch 229 +2025-10-30 10:03:06.371958: Current learning rate: 0.00791 +2025-10-30 10:03:28.421348: train_loss -0.9858 +2025-10-30 10:03:28.424910: val_loss -0.8852 +2025-10-30 10:03:28.426710: Pseudo dice [np.float32(0.9813), np.float32(0.9862), np.float32(0.9935), np.float32(0.7796)] +2025-10-30 10:03:28.428638: Epoch time: 22.06 s +2025-10-30 10:03:29.678561: +2025-10-30 10:03:29.681151: Epoch 230 +2025-10-30 10:03:29.683284: Current learning rate: 0.0079 +2025-10-30 10:03:51.488783: train_loss -0.9865 +2025-10-30 10:03:51.494877: val_loss -0.8913 +2025-10-30 10:03:51.496950: Pseudo dice [np.float32(0.9835), np.float32(0.989), np.float32(0.9941), np.float32(0.7793)] +2025-10-30 10:03:51.498876: Epoch time: 21.81 s +2025-10-30 10:03:52.696813: +2025-10-30 10:03:52.700035: Epoch 231 +2025-10-30 10:03:52.703250: Current learning rate: 0.00789 +2025-10-30 10:04:14.290556: train_loss -0.9868 +2025-10-30 10:04:14.293720: val_loss -0.891 +2025-10-30 10:04:14.295584: Pseudo dice [np.float32(0.9804), np.float32(0.9873), np.float32(0.9944), np.float32(0.7914)] +2025-10-30 10:04:14.297602: Epoch time: 21.6 s +2025-10-30 10:04:15.496185: +2025-10-30 10:04:15.498031: Epoch 232 +2025-10-30 10:04:15.502844: Current learning rate: 0.00789 +2025-10-30 10:04:37.538871: train_loss -0.9883 +2025-10-30 10:04:37.545840: val_loss -0.8893 +2025-10-30 10:04:37.547609: Pseudo dice [np.float32(0.9819), np.float32(0.9885), np.float32(0.9945), np.float32(0.7841)] +2025-10-30 10:04:37.549287: Epoch time: 22.04 s +2025-10-30 10:04:38.661583: +2025-10-30 10:04:38.664335: Epoch 233 +2025-10-30 10:04:38.667089: Current learning rate: 0.00788 +2025-10-30 10:05:00.102332: train_loss -0.9825 +2025-10-30 10:05:00.105251: val_loss -0.8827 +2025-10-30 10:05:00.106736: Pseudo dice [np.float32(0.9821), np.float32(0.9873), np.float32(0.9944), np.float32(0.7691)] +2025-10-30 10:05:00.108260: Epoch time: 21.44 s +2025-10-30 10:05:01.267796: +2025-10-30 10:05:01.270084: Epoch 234 +2025-10-30 10:05:01.272325: Current learning rate: 0.00787 +2025-10-30 10:05:23.571524: train_loss -0.9758 +2025-10-30 10:05:23.575231: val_loss -0.8901 +2025-10-30 10:05:23.577580: Pseudo dice [np.float32(0.979), np.float32(0.9864), np.float32(0.9935), np.float32(0.7787)] +2025-10-30 10:05:23.579190: Epoch time: 22.31 s +2025-10-30 10:05:24.745334: +2025-10-30 10:05:24.747587: Epoch 235 +2025-10-30 10:05:24.749767: Current learning rate: 0.00786 +2025-10-30 10:05:47.128581: train_loss -0.9817 +2025-10-30 10:05:47.140272: val_loss -0.8925 +2025-10-30 10:05:47.142794: Pseudo dice [np.float32(0.9824), np.float32(0.9879), np.float32(0.994), np.float32(0.7723)] +2025-10-30 10:05:47.144481: Epoch time: 22.38 s +2025-10-30 10:05:48.239180: +2025-10-30 10:05:48.241134: Epoch 236 +2025-10-30 10:05:48.243026: Current learning rate: 0.00785 +2025-10-30 10:06:10.177928: train_loss -0.982 +2025-10-30 10:06:10.185400: val_loss -0.8839 +2025-10-30 10:06:10.186900: Pseudo dice [np.float32(0.9832), np.float32(0.989), np.float32(0.9933), np.float32(0.7495)] +2025-10-30 10:06:10.188402: Epoch time: 21.94 s +2025-10-30 10:06:11.440622: +2025-10-30 10:06:11.442806: Epoch 237 +2025-10-30 10:06:11.446005: Current learning rate: 0.00784 +2025-10-30 10:06:33.312218: train_loss -0.9639 +2025-10-30 10:06:33.316149: val_loss -0.8829 +2025-10-30 10:06:33.319731: Pseudo dice [np.float32(0.9805), np.float32(0.9764), np.float32(0.9894), np.float32(0.7531)] +2025-10-30 10:06:33.322905: Epoch time: 21.87 s +2025-10-30 10:06:34.465567: +2025-10-30 10:06:34.467430: Epoch 238 +2025-10-30 10:06:34.469236: Current learning rate: 0.00783 +2025-10-30 10:06:55.986562: train_loss -0.9549 +2025-10-30 10:06:55.991343: val_loss -0.8988 +2025-10-30 10:06:55.993935: Pseudo dice [np.float32(0.9817), np.float32(0.9867), np.float32(0.9938), np.float32(0.7764)] +2025-10-30 10:06:55.996129: Epoch time: 21.52 s +2025-10-30 10:06:57.157684: +2025-10-30 10:06:57.159872: Epoch 239 +2025-10-30 10:06:57.161712: Current learning rate: 0.00782 +2025-10-30 10:07:18.848593: train_loss -0.9626 +2025-10-30 10:07:18.854612: val_loss -0.9094 +2025-10-30 10:07:18.856571: Pseudo dice [np.float32(0.9814), np.float32(0.9867), np.float32(0.9945), np.float32(0.8043)] +2025-10-30 10:07:18.858214: Epoch time: 21.69 s +2025-10-30 10:07:20.100203: +2025-10-30 10:07:20.102579: Epoch 240 +2025-10-30 10:07:20.105900: Current learning rate: 0.00781 +2025-10-30 10:07:43.815663: train_loss -0.9732 +2025-10-30 10:07:43.817856: val_loss -0.8988 +2025-10-30 10:07:43.819303: Pseudo dice [np.float32(0.9781), np.float32(0.9885), np.float32(0.9942), np.float32(0.7845)] +2025-10-30 10:07:43.820705: Epoch time: 23.72 s +2025-10-30 10:07:45.149899: +2025-10-30 10:07:45.152320: Epoch 241 +2025-10-30 10:07:45.154248: Current learning rate: 0.0078 +2025-10-30 10:08:07.004350: train_loss -0.9799 +2025-10-30 10:08:07.006930: val_loss -0.8948 +2025-10-30 10:08:07.008614: Pseudo dice [np.float32(0.9766), np.float32(0.9867), np.float32(0.9934), np.float32(0.7928)] +2025-10-30 10:08:07.010488: Epoch time: 21.86 s +2025-10-30 10:08:08.116212: +2025-10-30 10:08:08.118408: Epoch 242 +2025-10-30 10:08:08.120255: Current learning rate: 0.00779 +2025-10-30 10:08:30.051960: train_loss -0.9814 +2025-10-30 10:08:30.056284: val_loss -0.8964 +2025-10-30 10:08:30.058416: Pseudo dice [np.float32(0.9815), np.float32(0.9888), np.float32(0.9953), np.float32(0.7901)] +2025-10-30 10:08:30.060133: Epoch time: 21.94 s +2025-10-30 10:08:31.081200: +2025-10-30 10:08:31.083110: Epoch 243 +2025-10-30 10:08:31.084858: Current learning rate: 0.00778 +2025-10-30 10:08:53.650107: train_loss -0.984 +2025-10-30 10:08:53.652837: val_loss -0.8908 +2025-10-30 10:08:53.656241: Pseudo dice [np.float32(0.9821), np.float32(0.988), np.float32(0.9946), np.float32(0.7741)] +2025-10-30 10:08:53.658578: Epoch time: 22.57 s +2025-10-30 10:08:54.673034: +2025-10-30 10:08:54.675887: Epoch 244 +2025-10-30 10:08:54.677888: Current learning rate: 0.00777 +2025-10-30 10:09:15.285322: train_loss -0.9832 +2025-10-30 10:09:15.287942: val_loss -0.8903 +2025-10-30 10:09:15.289855: Pseudo dice [np.float32(0.9816), np.float32(0.9879), np.float32(0.9943), np.float32(0.7774)] +2025-10-30 10:09:15.291608: Epoch time: 20.61 s +2025-10-30 10:09:16.494630: +2025-10-30 10:09:16.496744: Epoch 245 +2025-10-30 10:09:16.498996: Current learning rate: 0.00777 +2025-10-30 10:09:37.506581: train_loss -0.9815 +2025-10-30 10:09:37.510129: val_loss -0.8813 +2025-10-30 10:09:37.512104: Pseudo dice [np.float32(0.979), np.float32(0.9891), np.float32(0.9925), np.float32(0.7505)] +2025-10-30 10:09:37.513998: Epoch time: 21.01 s +2025-10-30 10:09:38.816070: +2025-10-30 10:09:38.818321: Epoch 246 +2025-10-30 10:09:38.820423: Current learning rate: 0.00776 +2025-10-30 10:10:00.401490: train_loss -0.9824 +2025-10-30 10:10:00.407849: val_loss -0.8799 +2025-10-30 10:10:00.409636: Pseudo dice [np.float32(0.9786), np.float32(0.9867), np.float32(0.9932), np.float32(0.7622)] +2025-10-30 10:10:00.411383: Epoch time: 21.59 s +2025-10-30 10:10:01.446720: +2025-10-30 10:10:01.448666: Epoch 247 +2025-10-30 10:10:01.450343: Current learning rate: 0.00775 +2025-10-30 10:10:23.087927: train_loss -0.9841 +2025-10-30 10:10:23.090439: val_loss -0.8913 +2025-10-30 10:10:23.092454: Pseudo dice [np.float32(0.9824), np.float32(0.9878), np.float32(0.9941), np.float32(0.785)] +2025-10-30 10:10:23.094190: Epoch time: 21.64 s +2025-10-30 10:10:24.211319: +2025-10-30 10:10:24.213230: Epoch 248 +2025-10-30 10:10:24.215206: Current learning rate: 0.00774 +2025-10-30 10:10:46.245654: train_loss -0.9854 +2025-10-30 10:10:46.248814: val_loss -0.89 +2025-10-30 10:10:46.250568: Pseudo dice [np.float32(0.9814), np.float32(0.9886), np.float32(0.994), np.float32(0.7739)] +2025-10-30 10:10:46.252119: Epoch time: 22.04 s +2025-10-30 10:10:47.351480: +2025-10-30 10:10:47.355236: Epoch 249 +2025-10-30 10:10:47.357128: Current learning rate: 0.00773 +2025-10-30 10:11:09.113007: train_loss -0.9842 +2025-10-30 10:11:09.115796: val_loss -0.8906 +2025-10-30 10:11:09.117607: Pseudo dice [np.float32(0.9826), np.float32(0.9874), np.float32(0.9941), np.float32(0.7745)] +2025-10-30 10:11:09.119494: Epoch time: 21.76 s +2025-10-30 10:11:11.658631: +2025-10-30 10:11:11.661070: Epoch 250 +2025-10-30 10:11:11.664841: Current learning rate: 0.00772 +2025-10-30 10:11:32.025062: train_loss -0.9845 +2025-10-30 10:11:32.027749: val_loss -0.8847 +2025-10-30 10:11:32.029544: Pseudo dice [np.float32(0.982), np.float32(0.9875), np.float32(0.9937), np.float32(0.7553)] +2025-10-30 10:11:32.031659: Epoch time: 20.37 s +2025-10-30 10:11:33.079632: +2025-10-30 10:11:33.081484: Epoch 251 +2025-10-30 10:11:33.083111: Current learning rate: 0.00771 +2025-10-30 10:11:54.018057: train_loss -0.9845 +2025-10-30 10:11:54.021097: val_loss -0.8838 +2025-10-30 10:11:54.022678: Pseudo dice [np.float32(0.9811), np.float32(0.9873), np.float32(0.9937), np.float32(0.7688)] +2025-10-30 10:11:54.024487: Epoch time: 20.94 s +2025-10-30 10:11:55.052117: +2025-10-30 10:11:55.054093: Epoch 252 +2025-10-30 10:11:55.056042: Current learning rate: 0.0077 +2025-10-30 10:12:16.872101: train_loss -0.9865 +2025-10-30 10:12:16.874579: val_loss -0.8813 +2025-10-30 10:12:16.876246: Pseudo dice [np.float32(0.9764), np.float32(0.9876), np.float32(0.9924), np.float32(0.7779)] +2025-10-30 10:12:16.877892: Epoch time: 21.82 s +2025-10-30 10:12:18.109416: +2025-10-30 10:12:18.113283: Epoch 253 +2025-10-30 10:12:18.115333: Current learning rate: 0.00769 +2025-10-30 10:12:39.839602: train_loss -0.986 +2025-10-30 10:12:39.842194: val_loss -0.8855 +2025-10-30 10:12:39.844150: Pseudo dice [np.float32(0.9824), np.float32(0.9884), np.float32(0.9938), np.float32(0.7684)] +2025-10-30 10:12:39.846537: Epoch time: 21.73 s +2025-10-30 10:12:40.996320: +2025-10-30 10:12:40.998370: Epoch 254 +2025-10-30 10:12:41.000005: Current learning rate: 0.00768 +2025-10-30 10:13:02.592717: train_loss -0.9856 +2025-10-30 10:13:02.595983: val_loss -0.8858 +2025-10-30 10:13:02.598418: Pseudo dice [np.float32(0.9813), np.float32(0.9876), np.float32(0.9941), np.float32(0.7765)] +2025-10-30 10:13:02.600485: Epoch time: 21.6 s +2025-10-30 10:13:03.808599: +2025-10-30 10:13:03.810703: Epoch 255 +2025-10-30 10:13:03.812477: Current learning rate: 0.00767 +2025-10-30 10:13:25.771481: train_loss -0.9805 +2025-10-30 10:13:25.773684: val_loss -0.8815 +2025-10-30 10:13:25.775885: Pseudo dice [np.float32(0.9818), np.float32(0.9869), np.float32(0.9904), np.float32(0.7726)] +2025-10-30 10:13:25.777694: Epoch time: 21.96 s +2025-10-30 10:13:26.840667: +2025-10-30 10:13:26.844139: Epoch 256 +2025-10-30 10:13:26.846525: Current learning rate: 0.00766 +2025-10-30 10:13:48.671295: train_loss -0.9813 +2025-10-30 10:13:48.673696: val_loss -0.8908 +2025-10-30 10:13:48.675659: Pseudo dice [np.float32(0.9828), np.float32(0.9876), np.float32(0.9937), np.float32(0.7698)] +2025-10-30 10:13:48.677210: Epoch time: 21.83 s +2025-10-30 10:13:49.762182: +2025-10-30 10:13:49.764369: Epoch 257 +2025-10-30 10:13:49.766100: Current learning rate: 0.00765 +2025-10-30 10:14:08.630604: train_loss -0.9855 +2025-10-30 10:14:08.634028: val_loss -0.8752 +2025-10-30 10:14:08.636541: Pseudo dice [np.float32(0.9821), np.float32(0.9872), np.float32(0.9931), np.float32(0.7439)] +2025-10-30 10:14:08.638638: Epoch time: 18.87 s +2025-10-30 10:14:10.739867: +2025-10-30 10:14:10.741940: Epoch 258 +2025-10-30 10:14:10.744051: Current learning rate: 0.00764 +2025-10-30 10:14:32.425242: train_loss -0.9863 +2025-10-30 10:14:32.429506: val_loss -0.8859 +2025-10-30 10:14:32.431329: Pseudo dice [np.float32(0.9815), np.float32(0.9864), np.float32(0.9942), np.float32(0.785)] +2025-10-30 10:14:32.432856: Epoch time: 21.69 s +2025-10-30 10:14:33.567987: +2025-10-30 10:14:33.570143: Epoch 259 +2025-10-30 10:14:33.572337: Current learning rate: 0.00764 +2025-10-30 10:14:55.103700: train_loss -0.9862 +2025-10-30 10:14:55.107909: val_loss -0.8882 +2025-10-30 10:14:55.109616: Pseudo dice [np.float32(0.98), np.float32(0.9864), np.float32(0.9939), np.float32(0.7882)] +2025-10-30 10:14:55.112463: Epoch time: 21.54 s +2025-10-30 10:14:56.316588: +2025-10-30 10:14:56.319536: Epoch 260 +2025-10-30 10:14:56.321996: Current learning rate: 0.00763 +2025-10-30 10:15:17.923516: train_loss -0.9853 +2025-10-30 10:15:17.927464: val_loss -0.89 +2025-10-30 10:15:17.929176: Pseudo dice [np.float32(0.9823), np.float32(0.9871), np.float32(0.9942), np.float32(0.7813)] +2025-10-30 10:15:17.930922: Epoch time: 21.61 s +2025-10-30 10:15:19.064512: +2025-10-30 10:15:19.066778: Epoch 261 +2025-10-30 10:15:19.068789: Current learning rate: 0.00762 +2025-10-30 10:15:41.310471: train_loss -0.9863 +2025-10-30 10:15:41.312613: val_loss -0.8934 +2025-10-30 10:15:41.314462: Pseudo dice [np.float32(0.9825), np.float32(0.9884), np.float32(0.9944), np.float32(0.7841)] +2025-10-30 10:15:41.317009: Epoch time: 22.25 s +2025-10-30 10:15:42.350114: +2025-10-30 10:15:42.352384: Epoch 262 +2025-10-30 10:15:42.354382: Current learning rate: 0.00761 +2025-10-30 10:16:03.735116: train_loss -0.9866 +2025-10-30 10:16:03.737644: val_loss -0.8895 +2025-10-30 10:16:03.739577: Pseudo dice [np.float32(0.9823), np.float32(0.9882), np.float32(0.9945), np.float32(0.7788)] +2025-10-30 10:16:03.741545: Epoch time: 21.39 s +2025-10-30 10:16:04.637794: +2025-10-30 10:16:04.640637: Epoch 263 +2025-10-30 10:16:04.642880: Current learning rate: 0.0076 +2025-10-30 10:16:24.912174: train_loss -0.9876 +2025-10-30 10:16:24.955717: val_loss -0.8874 +2025-10-30 10:16:24.979164: Pseudo dice [np.float32(0.9822), np.float32(0.9879), np.float32(0.994), np.float32(0.7742)] +2025-10-30 10:16:25.003075: Epoch time: 20.28 s +2025-10-30 10:16:26.166032: +2025-10-30 10:16:26.168118: Epoch 264 +2025-10-30 10:16:26.174333: Current learning rate: 0.00759 +2025-10-30 10:16:47.540584: train_loss -0.9866 +2025-10-30 10:16:47.543302: val_loss -0.8824 +2025-10-30 10:16:47.545295: Pseudo dice [np.float32(0.9821), np.float32(0.9882), np.float32(0.9941), np.float32(0.7671)] +2025-10-30 10:16:47.547021: Epoch time: 21.38 s +2025-10-30 10:16:48.771925: +2025-10-30 10:16:48.775552: Epoch 265 +2025-10-30 10:16:48.777347: Current learning rate: 0.00758 +2025-10-30 10:17:10.383524: train_loss -0.9885 +2025-10-30 10:17:10.385794: val_loss -0.8798 +2025-10-30 10:17:10.388255: Pseudo dice [np.float32(0.9826), np.float32(0.9884), np.float32(0.9938), np.float32(0.7634)] +2025-10-30 10:17:10.390486: Epoch time: 21.61 s +2025-10-30 10:17:11.432298: +2025-10-30 10:17:11.434253: Epoch 266 +2025-10-30 10:17:11.435935: Current learning rate: 0.00757 +2025-10-30 10:17:33.337000: train_loss -0.9874 +2025-10-30 10:17:33.344320: val_loss -0.8828 +2025-10-30 10:17:33.345870: Pseudo dice [np.float32(0.9821), np.float32(0.987), np.float32(0.9943), np.float32(0.7798)] +2025-10-30 10:17:33.347500: Epoch time: 21.91 s +2025-10-30 10:17:34.501698: +2025-10-30 10:17:34.503663: Epoch 267 +2025-10-30 10:17:34.505611: Current learning rate: 0.00756 +2025-10-30 10:17:56.522200: train_loss -0.9875 +2025-10-30 10:17:56.526801: val_loss -0.8838 +2025-10-30 10:17:56.529089: Pseudo dice [np.float32(0.9828), np.float32(0.9887), np.float32(0.9942), np.float32(0.7676)] +2025-10-30 10:17:56.530783: Epoch time: 22.02 s +2025-10-30 10:17:57.733426: +2025-10-30 10:17:57.735303: Epoch 268 +2025-10-30 10:17:57.737462: Current learning rate: 0.00755 +2025-10-30 10:18:19.685202: train_loss -0.988 +2025-10-30 10:18:19.688361: val_loss -0.8817 +2025-10-30 10:18:19.690410: Pseudo dice [np.float32(0.9836), np.float32(0.9884), np.float32(0.9937), np.float32(0.7666)] +2025-10-30 10:18:19.692791: Epoch time: 21.95 s +2025-10-30 10:18:20.789925: +2025-10-30 10:18:20.792622: Epoch 269 +2025-10-30 10:18:20.794429: Current learning rate: 0.00754 +2025-10-30 10:18:42.211744: train_loss -0.9872 +2025-10-30 10:18:42.217901: val_loss -0.8881 +2025-10-30 10:18:42.219630: Pseudo dice [np.float32(0.982), np.float32(0.9878), np.float32(0.9944), np.float32(0.7864)] +2025-10-30 10:18:42.221558: Epoch time: 21.42 s +2025-10-30 10:18:43.268901: +2025-10-30 10:18:43.270829: Epoch 270 +2025-10-30 10:18:43.272436: Current learning rate: 0.00753 +2025-10-30 10:19:03.762735: train_loss -0.9876 +2025-10-30 10:19:03.765705: val_loss -0.8937 +2025-10-30 10:19:03.768557: Pseudo dice [np.float32(0.9828), np.float32(0.9883), np.float32(0.9947), np.float32(0.8011)] +2025-10-30 10:19:03.771425: Epoch time: 20.5 s +2025-10-30 10:19:05.033941: +2025-10-30 10:19:05.036088: Epoch 271 +2025-10-30 10:19:05.040405: Current learning rate: 0.00752 +2025-10-30 10:19:27.296249: train_loss -0.9874 +2025-10-30 10:19:27.299138: val_loss -0.8827 +2025-10-30 10:19:27.300888: Pseudo dice [np.float32(0.9827), np.float32(0.9887), np.float32(0.9938), np.float32(0.7573)] +2025-10-30 10:19:27.302440: Epoch time: 22.26 s +2025-10-30 10:19:28.337505: +2025-10-30 10:19:28.339663: Epoch 272 +2025-10-30 10:19:28.342520: Current learning rate: 0.00751 +2025-10-30 10:19:49.860711: train_loss -0.9881 +2025-10-30 10:19:49.863434: val_loss -0.8861 +2025-10-30 10:19:49.864960: Pseudo dice [np.float32(0.982), np.float32(0.9879), np.float32(0.9946), np.float32(0.7714)] +2025-10-30 10:19:49.866445: Epoch time: 21.52 s +2025-10-30 10:19:50.993190: +2025-10-30 10:19:50.995285: Epoch 273 +2025-10-30 10:19:50.997549: Current learning rate: 0.00751 +2025-10-30 10:20:12.839970: train_loss -0.988 +2025-10-30 10:20:12.842935: val_loss -0.8831 +2025-10-30 10:20:12.844866: Pseudo dice [np.float32(0.9835), np.float32(0.9888), np.float32(0.9942), np.float32(0.7724)] +2025-10-30 10:20:12.846461: Epoch time: 21.85 s +2025-10-30 10:20:13.876686: +2025-10-30 10:20:13.879359: Epoch 274 +2025-10-30 10:20:13.882305: Current learning rate: 0.0075 +2025-10-30 10:20:35.465019: train_loss -0.9884 +2025-10-30 10:20:35.467626: val_loss -0.8879 +2025-10-30 10:20:35.469443: Pseudo dice [np.float32(0.9815), np.float32(0.9884), np.float32(0.9944), np.float32(0.7833)] +2025-10-30 10:20:35.471142: Epoch time: 21.59 s +2025-10-30 10:20:36.732981: +2025-10-30 10:20:36.735428: Epoch 275 +2025-10-30 10:20:36.737267: Current learning rate: 0.00749 +2025-10-30 10:20:57.614048: train_loss -0.9882 +2025-10-30 10:20:57.617198: val_loss -0.8803 +2025-10-30 10:20:57.618904: Pseudo dice [np.float32(0.9811), np.float32(0.988), np.float32(0.9938), np.float32(0.7746)] +2025-10-30 10:20:57.620758: Epoch time: 20.88 s +2025-10-30 10:20:59.627849: +2025-10-30 10:20:59.629708: Epoch 276 +2025-10-30 10:20:59.631351: Current learning rate: 0.00748 +2025-10-30 10:21:21.464294: train_loss -0.9871 +2025-10-30 10:21:21.467201: val_loss -0.8965 +2025-10-30 10:21:21.468893: Pseudo dice [np.float32(0.9818), np.float32(0.9875), np.float32(0.9945), np.float32(0.8035)] +2025-10-30 10:21:21.470629: Epoch time: 21.84 s +2025-10-30 10:21:22.503033: +2025-10-30 10:21:22.505300: Epoch 277 +2025-10-30 10:21:22.507375: Current learning rate: 0.00747 +2025-10-30 10:21:42.566860: train_loss -0.9878 +2025-10-30 10:21:42.568928: val_loss -0.8974 +2025-10-30 10:21:42.570699: Pseudo dice [np.float32(0.9838), np.float32(0.9885), np.float32(0.9944), np.float32(0.8014)] +2025-10-30 10:21:42.572369: Epoch time: 20.07 s +2025-10-30 10:21:43.599607: +2025-10-30 10:21:43.602179: Epoch 278 +2025-10-30 10:21:43.604164: Current learning rate: 0.00746 +2025-10-30 10:22:05.454088: train_loss -0.987 +2025-10-30 10:22:05.458122: val_loss -0.8846 +2025-10-30 10:22:05.460195: Pseudo dice [np.float32(0.9818), np.float32(0.9873), np.float32(0.9939), np.float32(0.7805)] +2025-10-30 10:22:05.462742: Epoch time: 21.86 s +2025-10-30 10:22:06.681899: +2025-10-30 10:22:06.687846: Epoch 279 +2025-10-30 10:22:06.689774: Current learning rate: 0.00745 +2025-10-30 10:22:28.429247: train_loss -0.9873 +2025-10-30 10:22:28.432702: val_loss -0.8863 +2025-10-30 10:22:28.434841: Pseudo dice [np.float32(0.9819), np.float32(0.9876), np.float32(0.9941), np.float32(0.776)] +2025-10-30 10:22:28.436282: Epoch time: 21.75 s +2025-10-30 10:22:29.490909: +2025-10-30 10:22:29.492988: Epoch 280 +2025-10-30 10:22:29.495394: Current learning rate: 0.00744 +2025-10-30 10:22:51.168579: train_loss -0.9879 +2025-10-30 10:22:51.172270: val_loss -0.8891 +2025-10-30 10:22:51.174999: Pseudo dice [np.float32(0.9822), np.float32(0.9881), np.float32(0.994), np.float32(0.7791)] +2025-10-30 10:22:51.177031: Epoch time: 21.68 s +2025-10-30 10:22:52.306674: +2025-10-30 10:22:52.309446: Epoch 281 +2025-10-30 10:22:52.311443: Current learning rate: 0.00743 +2025-10-30 10:23:13.366777: train_loss -0.9878 +2025-10-30 10:23:13.371396: val_loss -0.8799 +2025-10-30 10:23:13.373766: Pseudo dice [np.float32(0.9805), np.float32(0.9873), np.float32(0.9942), np.float32(0.7675)] +2025-10-30 10:23:13.376981: Epoch time: 21.06 s +2025-10-30 10:23:14.593911: +2025-10-30 10:23:14.596317: Epoch 282 +2025-10-30 10:23:14.598391: Current learning rate: 0.00742 +2025-10-30 10:23:36.510133: train_loss -0.9875 +2025-10-30 10:23:36.513475: val_loss -0.8926 +2025-10-30 10:23:36.515800: Pseudo dice [np.float32(0.9818), np.float32(0.9888), np.float32(0.9951), np.float32(0.7881)] +2025-10-30 10:23:36.517778: Epoch time: 21.92 s +2025-10-30 10:23:37.662640: +2025-10-30 10:23:37.668002: Epoch 283 +2025-10-30 10:23:37.672513: Current learning rate: 0.00741 +2025-10-30 10:23:58.585215: train_loss -0.9882 +2025-10-30 10:23:58.588112: val_loss -0.886 +2025-10-30 10:23:58.590620: Pseudo dice [np.float32(0.9805), np.float32(0.9871), np.float32(0.9943), np.float32(0.7891)] +2025-10-30 10:23:58.592267: Epoch time: 20.92 s +2025-10-30 10:23:59.622337: +2025-10-30 10:23:59.626848: Epoch 284 +2025-10-30 10:23:59.633250: Current learning rate: 0.0074 +2025-10-30 10:24:21.346934: train_loss -0.9892 +2025-10-30 10:24:21.354152: val_loss -0.8887 +2025-10-30 10:24:21.358073: Pseudo dice [np.float32(0.9827), np.float32(0.9875), np.float32(0.9943), np.float32(0.7861)] +2025-10-30 10:24:21.362879: Epoch time: 21.73 s +2025-10-30 10:24:22.405407: +2025-10-30 10:24:22.407444: Epoch 285 +2025-10-30 10:24:22.409774: Current learning rate: 0.00739 +2025-10-30 10:24:44.614090: train_loss -0.988 +2025-10-30 10:24:44.616552: val_loss -0.8772 +2025-10-30 10:24:44.618189: Pseudo dice [np.float32(0.9815), np.float32(0.9872), np.float32(0.994), np.float32(0.766)] +2025-10-30 10:24:44.619832: Epoch time: 22.21 s +2025-10-30 10:24:45.816978: +2025-10-30 10:24:45.819080: Epoch 286 +2025-10-30 10:24:45.820946: Current learning rate: 0.00738 +2025-10-30 10:25:07.728660: train_loss -0.9891 +2025-10-30 10:25:07.730947: val_loss -0.8784 +2025-10-30 10:25:07.733459: Pseudo dice [np.float32(0.9819), np.float32(0.9879), np.float32(0.9941), np.float32(0.7672)] +2025-10-30 10:25:07.736226: Epoch time: 21.91 s +2025-10-30 10:25:08.838585: +2025-10-30 10:25:08.840721: Epoch 287 +2025-10-30 10:25:08.842531: Current learning rate: 0.00738 +2025-10-30 10:25:29.522953: train_loss -0.9884 +2025-10-30 10:25:29.525543: val_loss -0.8832 +2025-10-30 10:25:29.527058: Pseudo dice [np.float32(0.9805), np.float32(0.9882), np.float32(0.9943), np.float32(0.7781)] +2025-10-30 10:25:29.528559: Epoch time: 20.69 s +2025-10-30 10:25:30.562782: +2025-10-30 10:25:30.564772: Epoch 288 +2025-10-30 10:25:30.566824: Current learning rate: 0.00737 +2025-10-30 10:25:52.473801: train_loss -0.9882 +2025-10-30 10:25:52.488366: val_loss -0.8819 +2025-10-30 10:25:52.490342: Pseudo dice [np.float32(0.9823), np.float32(0.9878), np.float32(0.9944), np.float32(0.763)] +2025-10-30 10:25:52.491969: Epoch time: 21.91 s +2025-10-30 10:25:53.658687: +2025-10-30 10:25:53.661988: Epoch 289 +2025-10-30 10:25:53.664090: Current learning rate: 0.00736 +2025-10-30 10:26:15.741198: train_loss -0.9892 +2025-10-30 10:26:15.744213: val_loss -0.886 +2025-10-30 10:26:15.745882: Pseudo dice [np.float32(0.9828), np.float32(0.9888), np.float32(0.9943), np.float32(0.7778)] +2025-10-30 10:26:15.748047: Epoch time: 22.08 s +2025-10-30 10:26:16.880478: +2025-10-30 10:26:16.882498: Epoch 290 +2025-10-30 10:26:16.884179: Current learning rate: 0.00735 +2025-10-30 10:26:37.866431: train_loss -0.9884 +2025-10-30 10:26:37.870247: val_loss -0.8734 +2025-10-30 10:26:37.874181: Pseudo dice [np.float32(0.982), np.float32(0.9888), np.float32(0.9937), np.float32(0.7556)] +2025-10-30 10:26:37.876434: Epoch time: 20.99 s +2025-10-30 10:26:39.003868: +2025-10-30 10:26:39.006286: Epoch 291 +2025-10-30 10:26:39.008485: Current learning rate: 0.00734 +2025-10-30 10:27:01.078289: train_loss -0.9884 +2025-10-30 10:27:01.080792: val_loss -0.8716 +2025-10-30 10:27:01.085331: Pseudo dice [np.float32(0.9831), np.float32(0.9878), np.float32(0.9939), np.float32(0.7411)] +2025-10-30 10:27:01.088294: Epoch time: 22.08 s +2025-10-30 10:27:02.129472: +2025-10-30 10:27:02.131929: Epoch 292 +2025-10-30 10:27:02.133731: Current learning rate: 0.00733 +2025-10-30 10:27:24.468520: train_loss -0.9884 +2025-10-30 10:27:24.471577: val_loss -0.8833 +2025-10-30 10:27:24.474403: Pseudo dice [np.float32(0.9816), np.float32(0.9877), np.float32(0.9948), np.float32(0.7796)] +2025-10-30 10:27:24.479628: Epoch time: 22.34 s +2025-10-30 10:27:26.333593: +2025-10-30 10:27:26.335842: Epoch 293 +2025-10-30 10:27:26.337827: Current learning rate: 0.00732 +2025-10-30 10:27:47.434564: train_loss -0.9884 +2025-10-30 10:27:47.437396: val_loss -0.885 +2025-10-30 10:27:47.438939: Pseudo dice [np.float32(0.9826), np.float32(0.9882), np.float32(0.9943), np.float32(0.7681)] +2025-10-30 10:27:47.441424: Epoch time: 21.1 s +2025-10-30 10:27:48.708693: +2025-10-30 10:27:48.710572: Epoch 294 +2025-10-30 10:27:48.712430: Current learning rate: 0.00731 +2025-10-30 10:28:10.334805: train_loss -0.9887 +2025-10-30 10:28:10.337072: val_loss -0.8848 +2025-10-30 10:28:10.338676: Pseudo dice [np.float32(0.9831), np.float32(0.9882), np.float32(0.9947), np.float32(0.7801)] +2025-10-30 10:28:10.340106: Epoch time: 21.63 s +2025-10-30 10:28:11.487787: +2025-10-30 10:28:11.490595: Epoch 295 +2025-10-30 10:28:11.492577: Current learning rate: 0.0073 +2025-10-30 10:28:33.353289: train_loss -0.989 +2025-10-30 10:28:33.355854: val_loss -0.8819 +2025-10-30 10:28:33.357547: Pseudo dice [np.float32(0.9818), np.float32(0.9877), np.float32(0.9938), np.float32(0.769)] +2025-10-30 10:28:33.359131: Epoch time: 21.87 s +2025-10-30 10:28:34.378766: +2025-10-30 10:28:34.381539: Epoch 296 +2025-10-30 10:28:34.383327: Current learning rate: 0.00729 +2025-10-30 10:28:55.151753: train_loss -0.9881 +2025-10-30 10:28:55.154630: val_loss -0.8749 +2025-10-30 10:28:55.156585: Pseudo dice [np.float32(0.9819), np.float32(0.9881), np.float32(0.9937), np.float32(0.7597)] +2025-10-30 10:28:55.158679: Epoch time: 20.77 s +2025-10-30 10:28:56.305738: +2025-10-30 10:28:56.307674: Epoch 297 +2025-10-30 10:28:56.309391: Current learning rate: 0.00728 +2025-10-30 10:29:18.160947: train_loss -0.9873 +2025-10-30 10:29:18.179181: val_loss -0.8798 +2025-10-30 10:29:18.181084: Pseudo dice [np.float32(0.9822), np.float32(0.9881), np.float32(0.9941), np.float32(0.7609)] +2025-10-30 10:29:18.182723: Epoch time: 21.86 s +2025-10-30 10:29:19.416155: +2025-10-30 10:29:19.418067: Epoch 298 +2025-10-30 10:29:19.419711: Current learning rate: 0.00727 +2025-10-30 10:29:41.447750: train_loss -0.9885 +2025-10-30 10:29:41.450651: val_loss -0.8761 +2025-10-30 10:29:41.452470: Pseudo dice [np.float32(0.9831), np.float32(0.9878), np.float32(0.9934), np.float32(0.7512)] +2025-10-30 10:29:41.454484: Epoch time: 22.03 s +2025-10-30 10:29:42.719739: +2025-10-30 10:29:42.722489: Epoch 299 +2025-10-30 10:29:42.724310: Current learning rate: 0.00726 +2025-10-30 10:30:03.649689: train_loss -0.9896 +2025-10-30 10:30:03.652971: val_loss -0.8776 +2025-10-30 10:30:03.655595: Pseudo dice [np.float32(0.9807), np.float32(0.9863), np.float32(0.9933), np.float32(0.7693)] +2025-10-30 10:30:03.657838: Epoch time: 20.93 s +2025-10-30 10:30:06.220234: +2025-10-30 10:30:06.224700: Epoch 300 +2025-10-30 10:30:06.228663: Current learning rate: 0.00725 +2025-10-30 10:30:28.428554: train_loss -0.9882 +2025-10-30 10:30:28.430845: val_loss -0.8838 +2025-10-30 10:30:28.432674: Pseudo dice [np.float32(0.9829), np.float32(0.9887), np.float32(0.9942), np.float32(0.7693)] +2025-10-30 10:30:28.434275: Epoch time: 22.21 s +2025-10-30 10:30:29.520332: +2025-10-30 10:30:29.522256: Epoch 301 +2025-10-30 10:30:29.524127: Current learning rate: 0.00724 +2025-10-30 10:30:51.352958: train_loss -0.9884 +2025-10-30 10:30:51.355751: val_loss -0.8868 +2025-10-30 10:30:51.357421: Pseudo dice [np.float32(0.9824), np.float32(0.9879), np.float32(0.994), np.float32(0.7786)] +2025-10-30 10:30:51.359061: Epoch time: 21.83 s +2025-10-30 10:30:52.614806: +2025-10-30 10:30:52.617283: Epoch 302 +2025-10-30 10:30:52.619111: Current learning rate: 0.00724 +2025-10-30 10:31:14.205799: train_loss -0.9896 +2025-10-30 10:31:14.208948: val_loss -0.8896 +2025-10-30 10:31:14.211239: Pseudo dice [np.float32(0.9815), np.float32(0.9878), np.float32(0.9942), np.float32(0.797)] +2025-10-30 10:31:14.213661: Epoch time: 21.59 s +2025-10-30 10:31:15.375478: +2025-10-30 10:31:15.378365: Epoch 303 +2025-10-30 10:31:15.380700: Current learning rate: 0.00723 +2025-10-30 10:31:36.131625: train_loss -0.9896 +2025-10-30 10:31:36.138784: val_loss -0.8748 +2025-10-30 10:31:36.141894: Pseudo dice [np.float32(0.9818), np.float32(0.9881), np.float32(0.9939), np.float32(0.7507)] +2025-10-30 10:31:36.146087: Epoch time: 20.76 s +2025-10-30 10:31:37.289470: +2025-10-30 10:31:37.293901: Epoch 304 +2025-10-30 10:31:37.298243: Current learning rate: 0.00722 +2025-10-30 10:31:59.179363: train_loss -0.9893 +2025-10-30 10:31:59.181998: val_loss -0.8826 +2025-10-30 10:31:59.183858: Pseudo dice [np.float32(0.9817), np.float32(0.9877), np.float32(0.9941), np.float32(0.7736)] +2025-10-30 10:31:59.185586: Epoch time: 21.89 s +2025-10-30 10:32:00.226968: +2025-10-30 10:32:00.229142: Epoch 305 +2025-10-30 10:32:00.231264: Current learning rate: 0.00721 +2025-10-30 10:32:20.847851: train_loss -0.9894 +2025-10-30 10:32:20.850789: val_loss -0.8742 +2025-10-30 10:32:20.852867: Pseudo dice [np.float32(0.982), np.float32(0.9894), np.float32(0.9939), np.float32(0.745)] +2025-10-30 10:32:20.855286: Epoch time: 20.62 s +2025-10-30 10:32:21.928822: +2025-10-30 10:32:21.931219: Epoch 306 +2025-10-30 10:32:21.933026: Current learning rate: 0.0072 +2025-10-30 10:32:43.988395: train_loss -0.9877 +2025-10-30 10:32:43.990752: val_loss -0.8751 +2025-10-30 10:32:43.992255: Pseudo dice [np.float32(0.9817), np.float32(0.9885), np.float32(0.9945), np.float32(0.7598)] +2025-10-30 10:32:43.994100: Epoch time: 22.06 s +2025-10-30 10:32:45.258355: +2025-10-30 10:32:45.260184: Epoch 307 +2025-10-30 10:32:45.262450: Current learning rate: 0.00719 +2025-10-30 10:33:06.774501: train_loss -0.9877 +2025-10-30 10:33:06.777480: val_loss -0.8888 +2025-10-30 10:33:06.779828: Pseudo dice [np.float32(0.9824), np.float32(0.9877), np.float32(0.9947), np.float32(0.7904)] +2025-10-30 10:33:06.781741: Epoch time: 21.52 s +2025-10-30 10:33:08.008590: +2025-10-30 10:33:08.011374: Epoch 308 +2025-10-30 10:33:08.013260: Current learning rate: 0.00718 +2025-10-30 10:33:29.722509: train_loss -0.9892 +2025-10-30 10:33:29.726159: val_loss -0.8729 +2025-10-30 10:33:29.728990: Pseudo dice [np.float32(0.9795), np.float32(0.987), np.float32(0.9932), np.float32(0.7466)] +2025-10-30 10:33:29.730959: Epoch time: 21.72 s +2025-10-30 10:33:30.760513: +2025-10-30 10:33:30.766340: Epoch 309 +2025-10-30 10:33:30.767964: Current learning rate: 0.00717 +2025-10-30 10:33:51.257324: train_loss -0.9879 +2025-10-30 10:33:51.259777: val_loss -0.8779 +2025-10-30 10:33:51.262025: Pseudo dice [np.float32(0.9778), np.float32(0.9854), np.float32(0.9938), np.float32(0.7779)] +2025-10-30 10:33:51.263960: Epoch time: 20.5 s +2025-10-30 10:33:52.465373: +2025-10-30 10:33:52.467274: Epoch 310 +2025-10-30 10:33:52.469296: Current learning rate: 0.00716 +2025-10-30 10:34:14.051941: train_loss -0.9884 +2025-10-30 10:34:14.054518: val_loss -0.869 +2025-10-30 10:34:14.056302: Pseudo dice [np.float32(0.982), np.float32(0.9883), np.float32(0.9929), np.float32(0.728)] +2025-10-30 10:34:14.058143: Epoch time: 21.59 s +2025-10-30 10:34:16.590610: +2025-10-30 10:34:16.595292: Epoch 311 +2025-10-30 10:34:16.597738: Current learning rate: 0.00715 +2025-10-30 10:34:37.121158: train_loss -0.9653 +2025-10-30 10:34:37.139695: val_loss -0.8299 +2025-10-30 10:34:37.147160: Pseudo dice [np.float32(0.9813), np.float32(0.9745), np.float32(0.961), np.float32(0.7815)] +2025-10-30 10:34:37.155376: Epoch time: 20.53 s +2025-10-30 10:34:38.430305: +2025-10-30 10:34:38.441452: Epoch 312 +2025-10-30 10:34:38.447153: Current learning rate: 0.00714 +2025-10-30 10:34:57.991006: train_loss -0.9123 +2025-10-30 10:34:57.993422: val_loss -0.8984 +2025-10-30 10:34:57.994978: Pseudo dice [np.float32(0.9806), np.float32(0.9844), np.float32(0.9921), np.float32(0.7922)] +2025-10-30 10:34:57.996547: Epoch time: 19.56 s +2025-10-30 10:34:59.021266: +2025-10-30 10:34:59.023669: Epoch 313 +2025-10-30 10:34:59.026061: Current learning rate: 0.00713 +2025-10-30 10:35:21.243795: train_loss -0.9281 +2025-10-30 10:35:21.246651: val_loss -0.8942 +2025-10-30 10:35:21.248413: Pseudo dice [np.float32(0.9814), np.float32(0.986), np.float32(0.9912), np.float32(0.7619)] +2025-10-30 10:35:21.250198: Epoch time: 22.22 s +2025-10-30 10:35:22.599787: +2025-10-30 10:35:22.601909: Epoch 314 +2025-10-30 10:35:22.604363: Current learning rate: 0.00712 +2025-10-30 10:35:44.593461: train_loss -0.946 +2025-10-30 10:35:44.599451: val_loss -0.9081 +2025-10-30 10:35:44.600975: Pseudo dice [np.float32(0.9836), np.float32(0.9892), np.float32(0.9942), np.float32(0.7824)] +2025-10-30 10:35:44.603025: Epoch time: 22.0 s +2025-10-30 10:35:45.704184: +2025-10-30 10:35:45.710241: Epoch 315 +2025-10-30 10:35:45.714555: Current learning rate: 0.00711 +2025-10-30 10:36:07.219243: train_loss -0.9599 +2025-10-30 10:36:07.221692: val_loss -0.9051 +2025-10-30 10:36:07.223941: Pseudo dice [np.float32(0.9818), np.float32(0.9874), np.float32(0.9944), np.float32(0.7882)] +2025-10-30 10:36:07.225829: Epoch time: 21.52 s +2025-10-30 10:36:08.368928: +2025-10-30 10:36:08.371135: Epoch 316 +2025-10-30 10:36:08.373266: Current learning rate: 0.0071 +2025-10-30 10:36:29.574276: train_loss -0.9684 +2025-10-30 10:36:29.584506: val_loss -0.8895 +2025-10-30 10:36:29.590285: Pseudo dice [np.float32(0.9803), np.float32(0.987), np.float32(0.994), np.float32(0.7602)] +2025-10-30 10:36:29.593503: Epoch time: 21.21 s +2025-10-30 10:36:30.846068: +2025-10-30 10:36:30.847902: Epoch 317 +2025-10-30 10:36:30.849463: Current learning rate: 0.0071 +2025-10-30 10:36:52.568090: train_loss -0.9753 +2025-10-30 10:36:52.570869: val_loss -0.8933 +2025-10-30 10:36:52.572621: Pseudo dice [np.float32(0.9815), np.float32(0.9862), np.float32(0.9938), np.float32(0.7689)] +2025-10-30 10:36:52.574201: Epoch time: 21.72 s +2025-10-30 10:36:53.791632: +2025-10-30 10:36:53.793751: Epoch 318 +2025-10-30 10:36:53.795550: Current learning rate: 0.00709 +2025-10-30 10:37:14.044415: train_loss -0.9788 +2025-10-30 10:37:14.046651: val_loss -0.8984 +2025-10-30 10:37:14.048349: Pseudo dice [np.float32(0.9815), np.float32(0.9868), np.float32(0.9938), np.float32(0.7969)] +2025-10-30 10:37:14.050683: Epoch time: 20.25 s +2025-10-30 10:37:15.272406: +2025-10-30 10:37:15.274776: Epoch 319 +2025-10-30 10:37:15.277406: Current learning rate: 0.00708 +2025-10-30 10:37:37.335575: train_loss -0.9799 +2025-10-30 10:37:37.338284: val_loss -0.9006 +2025-10-30 10:37:37.340133: Pseudo dice [np.float32(0.9834), np.float32(0.9876), np.float32(0.994), np.float32(0.7873)] +2025-10-30 10:37:37.341949: Epoch time: 22.06 s +2025-10-30 10:37:38.619864: +2025-10-30 10:37:38.621609: Epoch 320 +2025-10-30 10:37:38.624018: Current learning rate: 0.00707 +2025-10-30 10:38:00.338809: train_loss -0.9736 +2025-10-30 10:38:00.341384: val_loss -0.8807 +2025-10-30 10:38:00.344995: Pseudo dice [np.float32(0.9828), np.float32(0.9859), np.float32(0.9895), np.float32(0.7576)] +2025-10-30 10:38:00.348309: Epoch time: 21.72 s +2025-10-30 10:38:01.485893: +2025-10-30 10:38:01.488268: Epoch 321 +2025-10-30 10:38:01.489974: Current learning rate: 0.00706 +2025-10-30 10:38:23.278609: train_loss -0.9795 +2025-10-30 10:38:23.280861: val_loss -0.893 +2025-10-30 10:38:23.283035: Pseudo dice [np.float32(0.9824), np.float32(0.9876), np.float32(0.9942), np.float32(0.7728)] +2025-10-30 10:38:23.285685: Epoch time: 21.79 s +2025-10-30 10:38:24.308908: +2025-10-30 10:38:24.310642: Epoch 322 +2025-10-30 10:38:24.312301: Current learning rate: 0.00705 +2025-10-30 10:38:45.228593: train_loss -0.9815 +2025-10-30 10:38:45.231074: val_loss -0.8988 +2025-10-30 10:38:45.232768: Pseudo dice [np.float32(0.9815), np.float32(0.9876), np.float32(0.9944), np.float32(0.8011)] +2025-10-30 10:38:45.234514: Epoch time: 20.92 s +2025-10-30 10:38:46.419431: +2025-10-30 10:38:46.423826: Epoch 323 +2025-10-30 10:38:46.429546: Current learning rate: 0.00704 +2025-10-30 10:39:08.503330: train_loss -0.9822 +2025-10-30 10:39:08.507528: val_loss -0.895 +2025-10-30 10:39:08.510190: Pseudo dice [np.float32(0.9843), np.float32(0.9885), np.float32(0.994), np.float32(0.7786)] +2025-10-30 10:39:08.512665: Epoch time: 22.09 s +2025-10-30 10:39:09.622637: +2025-10-30 10:39:09.624609: Epoch 324 +2025-10-30 10:39:09.626551: Current learning rate: 0.00703 +2025-10-30 10:39:29.798885: train_loss -0.9837 +2025-10-30 10:39:29.801039: val_loss -0.8898 +2025-10-30 10:39:29.802586: Pseudo dice [np.float32(0.981), np.float32(0.9868), np.float32(0.9942), np.float32(0.7844)] +2025-10-30 10:39:29.804159: Epoch time: 20.18 s +2025-10-30 10:39:31.034253: +2025-10-30 10:39:31.036177: Epoch 325 +2025-10-30 10:39:31.037972: Current learning rate: 0.00702 +2025-10-30 10:39:52.901922: train_loss -0.9808 +2025-10-30 10:39:52.904876: val_loss -0.8855 +2025-10-30 10:39:52.906863: Pseudo dice [np.float32(0.9795), np.float32(0.9869), np.float32(0.9941), np.float32(0.7691)] +2025-10-30 10:39:52.908577: Epoch time: 21.87 s +2025-10-30 10:39:54.230411: +2025-10-30 10:39:54.233551: Epoch 326 +2025-10-30 10:39:54.235934: Current learning rate: 0.00701 +2025-10-30 10:40:15.958431: train_loss -0.9804 +2025-10-30 10:40:15.963999: val_loss -0.8855 +2025-10-30 10:40:15.965771: Pseudo dice [np.float32(0.9815), np.float32(0.9869), np.float32(0.9942), np.float32(0.7678)] +2025-10-30 10:40:15.967572: Epoch time: 21.73 s +2025-10-30 10:40:17.239393: +2025-10-30 10:40:17.241829: Epoch 327 +2025-10-30 10:40:17.247108: Current learning rate: 0.007 +2025-10-30 10:40:39.625906: train_loss -0.9831 +2025-10-30 10:40:39.628948: val_loss -0.8818 +2025-10-30 10:40:39.630791: Pseudo dice [np.float32(0.9802), np.float32(0.9882), np.float32(0.9941), np.float32(0.7504)] +2025-10-30 10:40:39.632678: Epoch time: 22.39 s +2025-10-30 10:40:41.740788: +2025-10-30 10:40:41.742710: Epoch 328 +2025-10-30 10:40:41.744950: Current learning rate: 0.00699 +2025-10-30 10:41:04.047081: train_loss -0.9841 +2025-10-30 10:41:04.050830: val_loss -0.8724 +2025-10-30 10:41:04.053402: Pseudo dice [np.float32(0.9803), np.float32(0.9879), np.float32(0.9936), np.float32(0.7418)] +2025-10-30 10:41:04.055223: Epoch time: 22.31 s +2025-10-30 10:41:05.160311: +2025-10-30 10:41:05.165180: Epoch 329 +2025-10-30 10:41:05.170351: Current learning rate: 0.00698 +2025-10-30 10:41:26.519469: train_loss -0.9848 +2025-10-30 10:41:26.522802: val_loss -0.8879 +2025-10-30 10:41:26.524980: Pseudo dice [np.float32(0.9809), np.float32(0.9868), np.float32(0.9937), np.float32(0.7739)] +2025-10-30 10:41:26.526836: Epoch time: 21.36 s +2025-10-30 10:41:27.609111: +2025-10-30 10:41:27.610872: Epoch 330 +2025-10-30 10:41:27.612441: Current learning rate: 0.00697 +2025-10-30 10:41:47.618894: train_loss -0.9854 +2025-10-30 10:41:47.621359: val_loss -0.8807 +2025-10-30 10:41:47.623366: Pseudo dice [np.float32(0.9825), np.float32(0.9877), np.float32(0.9941), np.float32(0.7564)] +2025-10-30 10:41:47.625184: Epoch time: 20.01 s +2025-10-30 10:41:48.690682: +2025-10-30 10:41:48.692712: Epoch 331 +2025-10-30 10:41:48.694415: Current learning rate: 0.00696 +2025-10-30 10:42:11.120222: train_loss -0.9856 +2025-10-30 10:42:11.123287: val_loss -0.8861 +2025-10-30 10:42:11.124925: Pseudo dice [np.float32(0.979), np.float32(0.9866), np.float32(0.9944), np.float32(0.78)] +2025-10-30 10:42:11.126637: Epoch time: 22.43 s +2025-10-30 10:42:12.355279: +2025-10-30 10:42:12.357240: Epoch 332 +2025-10-30 10:42:12.358771: Current learning rate: 0.00696 +2025-10-30 10:42:34.177954: train_loss -0.9852 +2025-10-30 10:42:34.181473: val_loss -0.8924 +2025-10-30 10:42:34.183802: Pseudo dice [np.float32(0.9808), np.float32(0.9881), np.float32(0.9948), np.float32(0.7909)] +2025-10-30 10:42:34.185611: Epoch time: 21.82 s +2025-10-30 10:42:35.456304: +2025-10-30 10:42:35.459134: Epoch 333 +2025-10-30 10:42:35.463725: Current learning rate: 0.00695 +2025-10-30 10:42:57.850548: train_loss -0.9869 +2025-10-30 10:42:57.852477: val_loss -0.884 +2025-10-30 10:42:57.853863: Pseudo dice [np.float32(0.9817), np.float32(0.9879), np.float32(0.9943), np.float32(0.7681)] +2025-10-30 10:42:57.855907: Epoch time: 22.4 s +2025-10-30 10:42:59.112181: +2025-10-30 10:42:59.114090: Epoch 334 +2025-10-30 10:42:59.115696: Current learning rate: 0.00694 +2025-10-30 10:43:21.241136: train_loss -0.9865 +2025-10-30 10:43:21.244644: val_loss -0.8901 +2025-10-30 10:43:21.246401: Pseudo dice [np.float32(0.9812), np.float32(0.9879), np.float32(0.9947), np.float32(0.7889)] +2025-10-30 10:43:21.247942: Epoch time: 22.13 s +2025-10-30 10:43:22.373122: +2025-10-30 10:43:22.375349: Epoch 335 +2025-10-30 10:43:22.377217: Current learning rate: 0.00693 +2025-10-30 10:43:44.039068: train_loss -0.9849 +2025-10-30 10:43:44.043323: val_loss -0.8939 +2025-10-30 10:43:44.044944: Pseudo dice [np.float32(0.9816), np.float32(0.9885), np.float32(0.9948), np.float32(0.7922)] +2025-10-30 10:43:44.047482: Epoch time: 21.67 s +2025-10-30 10:43:45.117352: +2025-10-30 10:43:45.119230: Epoch 336 +2025-10-30 10:43:45.120978: Current learning rate: 0.00692 +2025-10-30 10:44:06.103761: train_loss -0.9865 +2025-10-30 10:44:06.106555: val_loss -0.8849 +2025-10-30 10:44:06.108490: Pseudo dice [np.float32(0.9813), np.float32(0.9877), np.float32(0.9944), np.float32(0.7759)] +2025-10-30 10:44:06.110762: Epoch time: 20.99 s +2025-10-30 10:44:07.377097: +2025-10-30 10:44:07.379398: Epoch 337 +2025-10-30 10:44:07.381834: Current learning rate: 0.00691 +2025-10-30 10:44:29.552821: train_loss -0.9876 +2025-10-30 10:44:29.556808: val_loss -0.8778 +2025-10-30 10:44:29.559943: Pseudo dice [np.float32(0.9813), np.float32(0.9886), np.float32(0.9942), np.float32(0.7472)] +2025-10-30 10:44:29.563039: Epoch time: 22.18 s +2025-10-30 10:44:30.658789: +2025-10-30 10:44:30.662472: Epoch 338 +2025-10-30 10:44:30.665278: Current learning rate: 0.0069 +2025-10-30 10:44:52.794115: train_loss -0.9869 +2025-10-30 10:44:52.797739: val_loss -0.8839 +2025-10-30 10:44:52.800231: Pseudo dice [np.float32(0.9797), np.float32(0.9868), np.float32(0.9944), np.float32(0.7666)] +2025-10-30 10:44:52.802469: Epoch time: 22.14 s +2025-10-30 10:44:53.875623: +2025-10-30 10:44:53.877882: Epoch 339 +2025-10-30 10:44:53.880624: Current learning rate: 0.00689 +2025-10-30 10:45:15.838873: train_loss -0.9888 +2025-10-30 10:45:15.841398: val_loss -0.8853 +2025-10-30 10:45:15.843180: Pseudo dice [np.float32(0.981), np.float32(0.9875), np.float32(0.9947), np.float32(0.7757)] +2025-10-30 10:45:15.845026: Epoch time: 21.96 s +2025-10-30 10:45:17.125167: +2025-10-30 10:45:17.134059: Epoch 340 +2025-10-30 10:45:17.139849: Current learning rate: 0.00688 +2025-10-30 10:45:38.902379: train_loss -0.9876 +2025-10-30 10:45:38.905262: val_loss -0.8775 +2025-10-30 10:45:38.907382: Pseudo dice [np.float32(0.9813), np.float32(0.9876), np.float32(0.9935), np.float32(0.7437)] +2025-10-30 10:45:38.909308: Epoch time: 21.78 s +2025-10-30 10:45:40.109194: +2025-10-30 10:45:40.111649: Epoch 341 +2025-10-30 10:45:40.113497: Current learning rate: 0.00687 +2025-10-30 10:46:00.978959: train_loss -0.9876 +2025-10-30 10:46:00.986599: val_loss -0.8921 +2025-10-30 10:46:00.988529: Pseudo dice [np.float32(0.9838), np.float32(0.9891), np.float32(0.9942), np.float32(0.7752)] +2025-10-30 10:46:00.991359: Epoch time: 20.87 s +2025-10-30 10:46:02.247641: +2025-10-30 10:46:02.249781: Epoch 342 +2025-10-30 10:46:02.251416: Current learning rate: 0.00686 +2025-10-30 10:46:23.298506: train_loss -0.9881 +2025-10-30 10:46:23.301389: val_loss -0.8795 +2025-10-30 10:46:23.304703: Pseudo dice [np.float32(0.9798), np.float32(0.9872), np.float32(0.9939), np.float32(0.7606)] +2025-10-30 10:46:23.307262: Epoch time: 21.05 s +2025-10-30 10:46:24.316302: +2025-10-30 10:46:24.319430: Epoch 343 +2025-10-30 10:46:24.322290: Current learning rate: 0.00685 +2025-10-30 10:46:46.171860: train_loss -0.988 +2025-10-30 10:46:46.174308: val_loss -0.8921 +2025-10-30 10:46:46.176116: Pseudo dice [np.float32(0.9821), np.float32(0.9881), np.float32(0.9946), np.float32(0.792)] +2025-10-30 10:46:46.177609: Epoch time: 21.86 s +2025-10-30 10:46:47.450553: +2025-10-30 10:46:47.456138: Epoch 344 +2025-10-30 10:46:47.457617: Current learning rate: 0.00684 +2025-10-30 10:47:09.259462: train_loss -0.988 +2025-10-30 10:47:09.262747: val_loss -0.8936 +2025-10-30 10:47:09.264561: Pseudo dice [np.float32(0.982), np.float32(0.9877), np.float32(0.9946), np.float32(0.7888)] +2025-10-30 10:47:09.266280: Epoch time: 21.81 s +2025-10-30 10:47:11.438303: +2025-10-30 10:47:11.440370: Epoch 345 +2025-10-30 10:47:11.441965: Current learning rate: 0.00683 +2025-10-30 10:47:33.441818: train_loss -0.9876 +2025-10-30 10:47:33.444338: val_loss -0.8861 +2025-10-30 10:47:33.446031: Pseudo dice [np.float32(0.9801), np.float32(0.9867), np.float32(0.9944), np.float32(0.7797)] +2025-10-30 10:47:33.447555: Epoch time: 22.01 s +2025-10-30 10:47:34.681320: +2025-10-30 10:47:34.683005: Epoch 346 +2025-10-30 10:47:34.684430: Current learning rate: 0.00682 +2025-10-30 10:47:56.377088: train_loss -0.9881 +2025-10-30 10:47:56.380154: val_loss -0.8841 +2025-10-30 10:47:56.382123: Pseudo dice [np.float32(0.9839), np.float32(0.9882), np.float32(0.9942), np.float32(0.7662)] +2025-10-30 10:47:56.383876: Epoch time: 21.7 s +2025-10-30 10:47:57.567212: +2025-10-30 10:47:57.569558: Epoch 347 +2025-10-30 10:47:57.572246: Current learning rate: 0.00681 +2025-10-30 10:48:19.007158: train_loss -0.9883 +2025-10-30 10:48:19.010303: val_loss -0.8729 +2025-10-30 10:48:19.012755: Pseudo dice [np.float32(0.9824), np.float32(0.9879), np.float32(0.9935), np.float32(0.7375)] +2025-10-30 10:48:19.014449: Epoch time: 21.44 s +2025-10-30 10:48:20.348599: +2025-10-30 10:48:20.350436: Epoch 348 +2025-10-30 10:48:20.352438: Current learning rate: 0.0068 +2025-10-30 10:48:38.624202: train_loss -0.9887 +2025-10-30 10:48:38.628522: val_loss -0.882 +2025-10-30 10:48:38.630218: Pseudo dice [np.float32(0.983), np.float32(0.988), np.float32(0.9938), np.float32(0.765)] +2025-10-30 10:48:38.631909: Epoch time: 18.28 s +2025-10-30 10:48:39.860272: +2025-10-30 10:48:39.862317: Epoch 349 +2025-10-30 10:48:39.863966: Current learning rate: 0.0068 +2025-10-30 10:49:01.780198: train_loss -0.988 +2025-10-30 10:49:01.782573: val_loss -0.8901 +2025-10-30 10:49:01.784377: Pseudo dice [np.float32(0.9825), np.float32(0.9884), np.float32(0.9941), np.float32(0.7858)] +2025-10-30 10:49:01.786122: Epoch time: 21.92 s +2025-10-30 10:49:04.264869: +2025-10-30 10:49:04.266785: Epoch 350 +2025-10-30 10:49:04.269023: Current learning rate: 0.00679 +2025-10-30 10:49:26.094539: train_loss -0.9883 +2025-10-30 10:49:26.099513: val_loss -0.8809 +2025-10-30 10:49:26.105283: Pseudo dice [np.float32(0.9816), np.float32(0.9875), np.float32(0.9939), np.float32(0.7669)] +2025-10-30 10:49:26.107248: Epoch time: 21.83 s +2025-10-30 10:49:27.293031: +2025-10-30 10:49:27.295090: Epoch 351 +2025-10-30 10:49:27.296707: Current learning rate: 0.00678 +2025-10-30 10:49:49.368941: train_loss -0.9887 +2025-10-30 10:49:49.371598: val_loss -0.8833 +2025-10-30 10:49:49.373051: Pseudo dice [np.float32(0.9827), np.float32(0.989), np.float32(0.9945), np.float32(0.7638)] +2025-10-30 10:49:49.374639: Epoch time: 22.08 s +2025-10-30 10:49:50.658918: +2025-10-30 10:49:50.660934: Epoch 352 +2025-10-30 10:49:50.662890: Current learning rate: 0.00677 +2025-10-30 10:50:12.818332: train_loss -0.9879 +2025-10-30 10:50:12.820812: val_loss -0.8788 +2025-10-30 10:50:12.822359: Pseudo dice [np.float32(0.9818), np.float32(0.9867), np.float32(0.9939), np.float32(0.7639)] +2025-10-30 10:50:12.823987: Epoch time: 22.16 s +2025-10-30 10:50:13.932613: +2025-10-30 10:50:13.934695: Epoch 353 +2025-10-30 10:50:13.936775: Current learning rate: 0.00676 +2025-10-30 10:50:36.491844: train_loss -0.9878 +2025-10-30 10:50:36.498308: val_loss -0.8815 +2025-10-30 10:50:36.499907: Pseudo dice [np.float32(0.9807), np.float32(0.9879), np.float32(0.9944), np.float32(0.7685)] +2025-10-30 10:50:36.501461: Epoch time: 22.56 s +2025-10-30 10:50:37.728061: +2025-10-30 10:50:37.730505: Epoch 354 +2025-10-30 10:50:37.733554: Current learning rate: 0.00675 +2025-10-30 10:50:57.851043: train_loss -0.9878 +2025-10-30 10:50:57.853513: val_loss -0.8841 +2025-10-30 10:50:57.855132: Pseudo dice [np.float32(0.9816), np.float32(0.9882), np.float32(0.9946), np.float32(0.7693)] +2025-10-30 10:50:57.856911: Epoch time: 20.12 s +2025-10-30 10:50:59.173515: +2025-10-30 10:50:59.176530: Epoch 355 +2025-10-30 10:50:59.178159: Current learning rate: 0.00674 +2025-10-30 10:51:20.871756: train_loss -0.9891 +2025-10-30 10:51:20.874415: val_loss -0.8783 +2025-10-30 10:51:20.876101: Pseudo dice [np.float32(0.9801), np.float32(0.9872), np.float32(0.9944), np.float32(0.7639)] +2025-10-30 10:51:20.877606: Epoch time: 21.7 s +2025-10-30 10:51:22.170436: +2025-10-30 10:51:22.172362: Epoch 356 +2025-10-30 10:51:22.174004: Current learning rate: 0.00673 +2025-10-30 10:51:44.411287: train_loss -0.9882 +2025-10-30 10:51:44.414003: val_loss -0.8815 +2025-10-30 10:51:44.415653: Pseudo dice [np.float32(0.9823), np.float32(0.9887), np.float32(0.9942), np.float32(0.7584)] +2025-10-30 10:51:44.417218: Epoch time: 22.24 s +2025-10-30 10:51:45.676972: +2025-10-30 10:51:45.679937: Epoch 357 +2025-10-30 10:51:45.681717: Current learning rate: 0.00672 +2025-10-30 10:52:08.019437: train_loss -0.9872 +2025-10-30 10:52:08.022149: val_loss -0.8767 +2025-10-30 10:52:08.023764: Pseudo dice [np.float32(0.9786), np.float32(0.9864), np.float32(0.9938), np.float32(0.7564)] +2025-10-30 10:52:08.025266: Epoch time: 22.34 s +2025-10-30 10:52:09.261136: +2025-10-30 10:52:09.262882: Epoch 358 +2025-10-30 10:52:09.264362: Current learning rate: 0.00671 +2025-10-30 10:52:31.134288: train_loss -0.9873 +2025-10-30 10:52:31.140234: val_loss -0.879 +2025-10-30 10:52:31.142119: Pseudo dice [np.float32(0.9806), np.float32(0.9873), np.float32(0.9943), np.float32(0.758)] +2025-10-30 10:52:31.143913: Epoch time: 21.87 s +2025-10-30 10:52:32.416698: +2025-10-30 10:52:32.418817: Epoch 359 +2025-10-30 10:52:32.420605: Current learning rate: 0.0067 +2025-10-30 10:52:54.307522: train_loss -0.9874 +2025-10-30 10:52:54.310201: val_loss -0.8756 +2025-10-30 10:52:54.311840: Pseudo dice [np.float32(0.9807), np.float32(0.9873), np.float32(0.9941), np.float32(0.7451)] +2025-10-30 10:52:54.313408: Epoch time: 21.89 s +2025-10-30 10:52:55.510699: +2025-10-30 10:52:55.512591: Epoch 360 +2025-10-30 10:52:55.514520: Current learning rate: 0.00669 +2025-10-30 10:53:16.480330: train_loss -0.9879 +2025-10-30 10:53:16.483224: val_loss -0.8805 +2025-10-30 10:53:16.484864: Pseudo dice [np.float32(0.9815), np.float32(0.987), np.float32(0.9939), np.float32(0.7722)] +2025-10-30 10:53:16.486610: Epoch time: 20.97 s +2025-10-30 10:53:17.616368: +2025-10-30 10:53:17.618285: Epoch 361 +2025-10-30 10:53:17.619777: Current learning rate: 0.00668 +2025-10-30 10:53:39.659878: train_loss -0.9856 +2025-10-30 10:53:39.661941: val_loss -0.8859 +2025-10-30 10:53:39.664168: Pseudo dice [np.float32(0.98), np.float32(0.9869), np.float32(0.9943), np.float32(0.7762)] +2025-10-30 10:53:39.665799: Epoch time: 22.05 s +2025-10-30 10:53:41.642831: +2025-10-30 10:53:41.644452: Epoch 362 +2025-10-30 10:53:41.645923: Current learning rate: 0.00667 +2025-10-30 10:54:03.634710: train_loss -0.9871 +2025-10-30 10:54:03.638032: val_loss -0.8783 +2025-10-30 10:54:03.639688: Pseudo dice [np.float32(0.9812), np.float32(0.9885), np.float32(0.9935), np.float32(0.757)] +2025-10-30 10:54:03.641991: Epoch time: 21.99 s +2025-10-30 10:54:04.799419: +2025-10-30 10:54:04.801368: Epoch 363 +2025-10-30 10:54:04.803103: Current learning rate: 0.00666 +2025-10-30 10:54:26.507078: train_loss -0.9884 +2025-10-30 10:54:26.509800: val_loss -0.8982 +2025-10-30 10:54:26.511559: Pseudo dice [np.float32(0.9833), np.float32(0.9891), np.float32(0.9948), np.float32(0.799)] +2025-10-30 10:54:26.513239: Epoch time: 21.71 s +2025-10-30 10:54:27.736495: +2025-10-30 10:54:27.738402: Epoch 364 +2025-10-30 10:54:27.739917: Current learning rate: 0.00665 +2025-10-30 10:54:49.901922: train_loss -0.9889 +2025-10-30 10:54:49.904428: val_loss -0.8877 +2025-10-30 10:54:49.906340: Pseudo dice [np.float32(0.9822), np.float32(0.9879), np.float32(0.9941), np.float32(0.7775)] +2025-10-30 10:54:49.907916: Epoch time: 22.17 s +2025-10-30 10:54:51.160161: +2025-10-30 10:54:51.162093: Epoch 365 +2025-10-30 10:54:51.163814: Current learning rate: 0.00665 +2025-10-30 10:55:12.842964: train_loss -0.9886 +2025-10-30 10:55:12.847472: val_loss -0.8825 +2025-10-30 10:55:12.849290: Pseudo dice [np.float32(0.981), np.float32(0.9875), np.float32(0.9947), np.float32(0.7798)] +2025-10-30 10:55:12.851033: Epoch time: 21.68 s +2025-10-30 10:55:14.132998: +2025-10-30 10:55:14.134816: Epoch 366 +2025-10-30 10:55:14.136342: Current learning rate: 0.00664 +2025-10-30 10:55:34.777484: train_loss -0.9887 +2025-10-30 10:55:34.782387: val_loss -0.8841 +2025-10-30 10:55:34.784512: Pseudo dice [np.float32(0.9832), np.float32(0.9886), np.float32(0.9942), np.float32(0.7718)] +2025-10-30 10:55:34.790146: Epoch time: 20.65 s +2025-10-30 10:55:36.154398: +2025-10-30 10:55:36.156940: Epoch 367 +2025-10-30 10:55:36.159426: Current learning rate: 0.00663 +2025-10-30 10:55:57.609277: train_loss -0.9893 +2025-10-30 10:55:57.611968: val_loss -0.8787 +2025-10-30 10:55:57.613839: Pseudo dice [np.float32(0.9794), np.float32(0.9872), np.float32(0.995), np.float32(0.7785)] +2025-10-30 10:55:57.615508: Epoch time: 21.46 s +2025-10-30 10:55:58.888150: +2025-10-30 10:55:58.890382: Epoch 368 +2025-10-30 10:55:58.892155: Current learning rate: 0.00662 +2025-10-30 10:56:21.254572: train_loss -0.9891 +2025-10-30 10:56:21.261719: val_loss -0.8859 +2025-10-30 10:56:21.264560: Pseudo dice [np.float32(0.9838), np.float32(0.9894), np.float32(0.9945), np.float32(0.765)] +2025-10-30 10:56:21.266667: Epoch time: 22.37 s +2025-10-30 10:56:22.541046: +2025-10-30 10:56:22.544389: Epoch 369 +2025-10-30 10:56:22.546672: Current learning rate: 0.00661 +2025-10-30 10:56:45.017698: train_loss -0.9883 +2025-10-30 10:56:45.020336: val_loss -0.8846 +2025-10-30 10:56:45.022004: Pseudo dice [np.float32(0.982), np.float32(0.9875), np.float32(0.9941), np.float32(0.7784)] +2025-10-30 10:56:45.023613: Epoch time: 22.48 s +2025-10-30 10:56:46.180342: +2025-10-30 10:56:46.182143: Epoch 370 +2025-10-30 10:56:46.183963: Current learning rate: 0.0066 +2025-10-30 10:57:08.690201: train_loss -0.9881 +2025-10-30 10:57:08.692908: val_loss -0.8819 +2025-10-30 10:57:08.706243: Pseudo dice [np.float32(0.9809), np.float32(0.9875), np.float32(0.9943), np.float32(0.7665)] +2025-10-30 10:57:08.708672: Epoch time: 22.51 s +2025-10-30 10:57:10.301476: +2025-10-30 10:57:10.303210: Epoch 371 +2025-10-30 10:57:10.304715: Current learning rate: 0.00659 +2025-10-30 10:57:32.341640: train_loss -0.9882 +2025-10-30 10:57:32.345446: val_loss -0.8838 +2025-10-30 10:57:32.348945: Pseudo dice [np.float32(0.9831), np.float32(0.9884), np.float32(0.9939), np.float32(0.7653)] +2025-10-30 10:57:32.351093: Epoch time: 22.04 s +2025-10-30 10:57:33.645364: +2025-10-30 10:57:33.647744: Epoch 372 +2025-10-30 10:57:33.650208: Current learning rate: 0.00658 +2025-10-30 10:57:55.212943: train_loss -0.9892 +2025-10-30 10:57:55.215370: val_loss -0.891 +2025-10-30 10:57:55.216982: Pseudo dice [np.float32(0.9839), np.float32(0.9895), np.float32(0.9944), np.float32(0.7806)] +2025-10-30 10:57:55.218444: Epoch time: 21.57 s +2025-10-30 10:57:56.541426: +2025-10-30 10:57:56.543897: Epoch 373 +2025-10-30 10:57:56.545926: Current learning rate: 0.00657 +2025-10-30 10:58:17.885904: train_loss -0.9888 +2025-10-30 10:58:17.888415: val_loss -0.8864 +2025-10-30 10:58:17.889874: Pseudo dice [np.float32(0.9811), np.float32(0.9878), np.float32(0.9943), np.float32(0.7761)] +2025-10-30 10:58:17.891458: Epoch time: 21.35 s +2025-10-30 10:58:19.182623: +2025-10-30 10:58:19.184596: Epoch 374 +2025-10-30 10:58:19.186316: Current learning rate: 0.00656 +2025-10-30 10:58:41.538242: train_loss -0.9889 +2025-10-30 10:58:41.546914: val_loss -0.8919 +2025-10-30 10:58:41.549163: Pseudo dice [np.float32(0.9826), np.float32(0.9888), np.float32(0.9944), np.float32(0.7879)] +2025-10-30 10:58:41.551512: Epoch time: 22.36 s +2025-10-30 10:58:42.673148: +2025-10-30 10:58:42.675853: Epoch 375 +2025-10-30 10:58:42.677754: Current learning rate: 0.00655 +2025-10-30 10:59:04.811361: train_loss -0.9884 +2025-10-30 10:59:04.814520: val_loss -0.8807 +2025-10-30 10:59:04.816216: Pseudo dice [np.float32(0.9821), np.float32(0.9884), np.float32(0.9937), np.float32(0.7643)] +2025-10-30 10:59:04.817936: Epoch time: 22.14 s +2025-10-30 10:59:05.843352: +2025-10-30 10:59:05.846256: Epoch 376 +2025-10-30 10:59:05.849026: Current learning rate: 0.00654 +2025-10-30 10:59:27.807635: train_loss -0.9892 +2025-10-30 10:59:27.811946: val_loss -0.8844 +2025-10-30 10:59:27.814421: Pseudo dice [np.float32(0.9813), np.float32(0.9879), np.float32(0.9942), np.float32(0.7764)] +2025-10-30 10:59:27.816828: Epoch time: 21.97 s +2025-10-30 10:59:28.969359: +2025-10-30 10:59:28.971423: Epoch 377 +2025-10-30 10:59:28.973101: Current learning rate: 0.00653 +2025-10-30 10:59:50.752010: train_loss -0.9894 +2025-10-30 10:59:50.755841: val_loss -0.8781 +2025-10-30 10:59:50.757944: Pseudo dice [np.float32(0.9823), np.float32(0.9887), np.float32(0.9938), np.float32(0.7617)] +2025-10-30 10:59:50.760089: Epoch time: 21.78 s +2025-10-30 10:59:52.056698: +2025-10-30 10:59:52.058783: Epoch 378 +2025-10-30 10:59:52.060230: Current learning rate: 0.00652 +2025-10-30 11:00:14.157843: train_loss -0.9901 +2025-10-30 11:00:14.160490: val_loss -0.8868 +2025-10-30 11:00:14.162400: Pseudo dice [np.float32(0.9803), np.float32(0.9883), np.float32(0.9945), np.float32(0.786)] +2025-10-30 11:00:14.164326: Epoch time: 22.1 s +2025-10-30 11:00:15.382990: +2025-10-30 11:00:15.384923: Epoch 379 +2025-10-30 11:00:15.386894: Current learning rate: 0.00651 +2025-10-30 11:00:36.210499: train_loss -0.9887 +2025-10-30 11:00:36.212849: val_loss -0.8808 +2025-10-30 11:00:36.214449: Pseudo dice [np.float32(0.9801), np.float32(0.9867), np.float32(0.994), np.float32(0.7783)] +2025-10-30 11:00:36.216003: Epoch time: 20.83 s +2025-10-30 11:00:37.414211: +2025-10-30 11:00:37.416554: Epoch 380 +2025-10-30 11:00:37.419034: Current learning rate: 0.0065 +2025-10-30 11:00:59.522740: train_loss -0.9872 +2025-10-30 11:00:59.525429: val_loss -0.8847 +2025-10-30 11:00:59.527112: Pseudo dice [np.float32(0.9808), np.float32(0.9885), np.float32(0.9934), np.float32(0.7771)] +2025-10-30 11:00:59.528703: Epoch time: 22.11 s +2025-10-30 11:01:00.784316: +2025-10-30 11:01:00.786226: Epoch 381 +2025-10-30 11:01:00.787845: Current learning rate: 0.00649 +2025-10-30 11:01:23.107115: train_loss -0.9869 +2025-10-30 11:01:23.109058: val_loss -0.8763 +2025-10-30 11:01:23.110615: Pseudo dice [np.float32(0.9811), np.float32(0.9872), np.float32(0.9934), np.float32(0.7601)] +2025-10-30 11:01:23.112205: Epoch time: 22.32 s +2025-10-30 11:01:24.246979: +2025-10-30 11:01:24.249285: Epoch 382 +2025-10-30 11:01:24.251039: Current learning rate: 0.00648 +2025-10-30 11:01:45.960906: train_loss -0.9876 +2025-10-30 11:01:45.963092: val_loss -0.8908 +2025-10-30 11:01:45.964565: Pseudo dice [np.float32(0.9831), np.float32(0.9879), np.float32(0.9946), np.float32(0.7845)] +2025-10-30 11:01:45.966089: Epoch time: 21.72 s +2025-10-30 11:01:47.223782: +2025-10-30 11:01:47.226780: Epoch 383 +2025-10-30 11:01:47.228505: Current learning rate: 0.00648 +2025-10-30 11:02:08.933795: train_loss -0.988 +2025-10-30 11:02:08.940477: val_loss -0.8872 +2025-10-30 11:02:08.942262: Pseudo dice [np.float32(0.9793), np.float32(0.987), np.float32(0.9944), np.float32(0.789)] +2025-10-30 11:02:08.944037: Epoch time: 21.71 s +2025-10-30 11:02:10.199584: +2025-10-30 11:02:10.201694: Epoch 384 +2025-10-30 11:02:10.203616: Current learning rate: 0.00647 +2025-10-30 11:02:32.028616: train_loss -0.9886 +2025-10-30 11:02:32.031429: val_loss -0.8845 +2025-10-30 11:02:32.033841: Pseudo dice [np.float32(0.982), np.float32(0.9888), np.float32(0.9945), np.float32(0.771)] +2025-10-30 11:02:32.036261: Epoch time: 21.83 s +2025-10-30 11:02:33.235532: +2025-10-30 11:02:33.251626: Epoch 385 +2025-10-30 11:02:33.266401: Current learning rate: 0.00646 +2025-10-30 11:02:54.117427: train_loss -0.9892 +2025-10-30 11:02:54.119867: val_loss -0.8881 +2025-10-30 11:02:54.122203: Pseudo dice [np.float32(0.9803), np.float32(0.9881), np.float32(0.9941), np.float32(0.7825)] +2025-10-30 11:02:54.123833: Epoch time: 20.88 s +2025-10-30 11:02:55.178160: +2025-10-30 11:02:55.179824: Epoch 386 +2025-10-30 11:02:55.181774: Current learning rate: 0.00645 +2025-10-30 11:03:14.802633: train_loss -0.9891 +2025-10-30 11:03:14.806170: val_loss -0.8875 +2025-10-30 11:03:14.808570: Pseudo dice [np.float32(0.9825), np.float32(0.9881), np.float32(0.9944), np.float32(0.777)] +2025-10-30 11:03:14.810587: Epoch time: 19.63 s +2025-10-30 11:03:15.736561: +2025-10-30 11:03:15.738457: Epoch 387 +2025-10-30 11:03:15.740060: Current learning rate: 0.00644 +2025-10-30 11:03:37.552920: train_loss -0.9896 +2025-10-30 11:03:37.555011: val_loss -0.8831 +2025-10-30 11:03:37.556398: Pseudo dice [np.float32(0.9794), np.float32(0.9866), np.float32(0.9942), np.float32(0.7772)] +2025-10-30 11:03:37.557884: Epoch time: 21.82 s +2025-10-30 11:03:38.681556: +2025-10-30 11:03:38.683242: Epoch 388 +2025-10-30 11:03:38.684678: Current learning rate: 0.00643 +2025-10-30 11:04:00.395939: train_loss -0.9903 +2025-10-30 11:04:00.398337: val_loss -0.8816 +2025-10-30 11:04:00.400677: Pseudo dice [np.float32(0.9799), np.float32(0.9873), np.float32(0.9945), np.float32(0.7749)] +2025-10-30 11:04:00.402298: Epoch time: 21.72 s +2025-10-30 11:04:01.456820: +2025-10-30 11:04:01.459288: Epoch 389 +2025-10-30 11:04:01.460944: Current learning rate: 0.00642 +2025-10-30 11:04:23.454070: train_loss -0.9898 +2025-10-30 11:04:23.456868: val_loss -0.876 +2025-10-30 11:04:23.458636: Pseudo dice [np.float32(0.9806), np.float32(0.9874), np.float32(0.9939), np.float32(0.7677)] +2025-10-30 11:04:23.460225: Epoch time: 22.0 s +2025-10-30 11:04:24.524386: +2025-10-30 11:04:24.526320: Epoch 390 +2025-10-30 11:04:24.528208: Current learning rate: 0.00641 +2025-10-30 11:04:46.675068: train_loss -0.9893 +2025-10-30 11:04:46.679297: val_loss -0.8652 +2025-10-30 11:04:46.681523: Pseudo dice [np.float32(0.982), np.float32(0.988), np.float32(0.9935), np.float32(0.732)] +2025-10-30 11:04:46.684213: Epoch time: 22.15 s +2025-10-30 11:04:47.929905: +2025-10-30 11:04:47.932934: Epoch 391 +2025-10-30 11:04:47.936104: Current learning rate: 0.0064 +2025-10-30 11:05:07.895263: train_loss -0.9885 +2025-10-30 11:05:07.898661: val_loss -0.8878 +2025-10-30 11:05:07.901829: Pseudo dice [np.float32(0.9823), np.float32(0.9879), np.float32(0.9941), np.float32(0.7779)] +2025-10-30 11:05:07.904812: Epoch time: 19.97 s +2025-10-30 11:05:09.090336: +2025-10-30 11:05:09.092892: Epoch 392 +2025-10-30 11:05:09.095045: Current learning rate: 0.00639 +2025-10-30 11:05:30.299839: train_loss -0.9894 +2025-10-30 11:05:30.339926: val_loss -0.8715 +2025-10-30 11:05:30.358927: Pseudo dice [np.float32(0.98), np.float32(0.987), np.float32(0.9942), np.float32(0.7459)] +2025-10-30 11:05:30.378032: Epoch time: 21.21 s +2025-10-30 11:05:31.604856: +2025-10-30 11:05:31.606848: Epoch 393 +2025-10-30 11:05:31.608802: Current learning rate: 0.00638 +2025-10-30 11:05:52.790428: train_loss -0.9892 +2025-10-30 11:05:52.792982: val_loss -0.8881 +2025-10-30 11:05:52.794872: Pseudo dice [np.float32(0.9822), np.float32(0.9871), np.float32(0.9943), np.float32(0.7831)] +2025-10-30 11:05:52.796646: Epoch time: 21.19 s +2025-10-30 11:05:54.157230: +2025-10-30 11:05:54.159279: Epoch 394 +2025-10-30 11:05:54.160771: Current learning rate: 0.00637 +2025-10-30 11:06:16.475485: train_loss -0.9884 +2025-10-30 11:06:16.478150: val_loss -0.8882 +2025-10-30 11:06:16.479948: Pseudo dice [np.float32(0.9804), np.float32(0.9873), np.float32(0.9945), np.float32(0.7908)] +2025-10-30 11:06:16.481690: Epoch time: 22.32 s +2025-10-30 11:06:18.942696: +2025-10-30 11:06:18.945964: Epoch 395 +2025-10-30 11:06:18.948020: Current learning rate: 0.00636 +2025-10-30 11:06:41.111492: train_loss -0.9895 +2025-10-30 11:06:41.114196: val_loss -0.8884 +2025-10-30 11:06:41.115930: Pseudo dice [np.float32(0.981), np.float32(0.9866), np.float32(0.9945), np.float32(0.7907)] +2025-10-30 11:06:41.117538: Epoch time: 22.17 s +2025-10-30 11:06:42.402647: +2025-10-30 11:06:42.404781: Epoch 396 +2025-10-30 11:06:42.406499: Current learning rate: 0.00635 +2025-10-30 11:07:03.945795: train_loss -0.9891 +2025-10-30 11:07:03.947780: val_loss -0.8804 +2025-10-30 11:07:03.949372: Pseudo dice [np.float32(0.9824), np.float32(0.9894), np.float32(0.9939), np.float32(0.7579)] +2025-10-30 11:07:03.951103: Epoch time: 21.55 s +2025-10-30 11:07:05.238688: +2025-10-30 11:07:05.240435: Epoch 397 +2025-10-30 11:07:05.242257: Current learning rate: 0.00634 +2025-10-30 11:07:25.633820: train_loss -0.9899 +2025-10-30 11:07:25.636186: val_loss -0.8777 +2025-10-30 11:07:25.637987: Pseudo dice [np.float32(0.9807), np.float32(0.9879), np.float32(0.9941), np.float32(0.7638)] +2025-10-30 11:07:25.639632: Epoch time: 20.4 s +2025-10-30 11:07:26.872928: +2025-10-30 11:07:26.874958: Epoch 398 +2025-10-30 11:07:26.876688: Current learning rate: 0.00633 +2025-10-30 11:07:48.875690: train_loss -0.9854 +2025-10-30 11:07:48.878562: val_loss -0.8808 +2025-10-30 11:07:48.880080: Pseudo dice [np.float32(0.981), np.float32(0.9881), np.float32(0.9942), np.float32(0.7699)] +2025-10-30 11:07:48.881601: Epoch time: 22.0 s +2025-10-30 11:07:50.130052: +2025-10-30 11:07:50.132118: Epoch 399 +2025-10-30 11:07:50.133795: Current learning rate: 0.00632 +2025-10-30 11:08:11.152828: train_loss -0.9887 +2025-10-30 11:08:11.155431: val_loss -0.8743 +2025-10-30 11:08:11.157528: Pseudo dice [np.float32(0.9818), np.float32(0.9883), np.float32(0.9936), np.float32(0.7412)] +2025-10-30 11:08:11.159073: Epoch time: 21.02 s +2025-10-30 11:08:13.310453: +2025-10-30 11:08:13.312901: Epoch 400 +2025-10-30 11:08:13.315021: Current learning rate: 0.00631 +2025-10-30 11:08:35.445563: train_loss -0.9883 +2025-10-30 11:08:35.448052: val_loss -0.8756 +2025-10-30 11:08:35.449624: Pseudo dice [np.float32(0.9803), np.float32(0.987), np.float32(0.9936), np.float32(0.7644)] +2025-10-30 11:08:35.451160: Epoch time: 22.14 s +2025-10-30 11:08:36.585404: +2025-10-30 11:08:36.587709: Epoch 401 +2025-10-30 11:08:36.589805: Current learning rate: 0.0063 +2025-10-30 11:08:58.240615: train_loss -0.9895 +2025-10-30 11:08:58.243193: val_loss -0.886 +2025-10-30 11:08:58.245315: Pseudo dice [np.float32(0.9813), np.float32(0.987), np.float32(0.9943), np.float32(0.7815)] +2025-10-30 11:08:58.246984: Epoch time: 21.66 s +2025-10-30 11:08:59.493993: +2025-10-30 11:08:59.496054: Epoch 402 +2025-10-30 11:08:59.498153: Current learning rate: 0.0063 +2025-10-30 11:09:21.790634: train_loss -0.9885 +2025-10-30 11:09:21.792639: val_loss -0.8758 +2025-10-30 11:09:21.794289: Pseudo dice [np.float32(0.9818), np.float32(0.9872), np.float32(0.9938), np.float32(0.7602)] +2025-10-30 11:09:21.796060: Epoch time: 22.3 s +2025-10-30 11:09:22.856530: +2025-10-30 11:09:22.858436: Epoch 403 +2025-10-30 11:09:22.860312: Current learning rate: 0.00629 +2025-10-30 11:09:43.656167: train_loss -0.989 +2025-10-30 11:09:43.658452: val_loss -0.8796 +2025-10-30 11:09:43.660014: Pseudo dice [np.float32(0.9791), np.float32(0.9865), np.float32(0.9939), np.float32(0.7727)] +2025-10-30 11:09:43.661513: Epoch time: 20.8 s +2025-10-30 11:09:44.712452: +2025-10-30 11:09:44.714293: Epoch 404 +2025-10-30 11:09:44.716013: Current learning rate: 0.00628 +2025-10-30 11:10:06.794385: train_loss -0.9889 +2025-10-30 11:10:06.800238: val_loss -0.8846 +2025-10-30 11:10:06.801830: Pseudo dice [np.float32(0.9816), np.float32(0.9882), np.float32(0.9944), np.float32(0.7754)] +2025-10-30 11:10:06.803561: Epoch time: 22.08 s +2025-10-30 11:10:08.067287: +2025-10-30 11:10:08.069133: Epoch 405 +2025-10-30 11:10:08.071756: Current learning rate: 0.00627 +2025-10-30 11:10:28.943356: train_loss -0.9888 +2025-10-30 11:10:28.945267: val_loss -0.8815 +2025-10-30 11:10:28.946786: Pseudo dice [np.float32(0.9811), np.float32(0.9891), np.float32(0.994), np.float32(0.7633)] +2025-10-30 11:10:28.948510: Epoch time: 20.88 s +2025-10-30 11:10:30.210496: +2025-10-30 11:10:30.216079: Epoch 406 +2025-10-30 11:10:30.218572: Current learning rate: 0.00626 +2025-10-30 11:10:52.631948: train_loss -0.9892 +2025-10-30 11:10:52.634080: val_loss -0.8852 +2025-10-30 11:10:52.636070: Pseudo dice [np.float32(0.9813), np.float32(0.9868), np.float32(0.9945), np.float32(0.7777)] +2025-10-30 11:10:52.637666: Epoch time: 22.42 s +2025-10-30 11:10:53.895757: +2025-10-30 11:10:53.897666: Epoch 407 +2025-10-30 11:10:53.899505: Current learning rate: 0.00625 +2025-10-30 11:11:15.768211: train_loss -0.9891 +2025-10-30 11:11:15.770869: val_loss -0.8891 +2025-10-30 11:11:15.772433: Pseudo dice [np.float32(0.9818), np.float32(0.9886), np.float32(0.9946), np.float32(0.7884)] +2025-10-30 11:11:15.773982: Epoch time: 21.87 s +2025-10-30 11:11:16.920695: +2025-10-30 11:11:16.925412: Epoch 408 +2025-10-30 11:11:16.927103: Current learning rate: 0.00624 +2025-10-30 11:11:38.464620: train_loss -0.9889 +2025-10-30 11:11:38.466970: val_loss -0.8847 +2025-10-30 11:11:38.468511: Pseudo dice [np.float32(0.9812), np.float32(0.9878), np.float32(0.9947), np.float32(0.7793)] +2025-10-30 11:11:38.470192: Epoch time: 21.55 s +2025-10-30 11:11:39.617013: +2025-10-30 11:11:39.619027: Epoch 409 +2025-10-30 11:11:39.620699: Current learning rate: 0.00623 +2025-10-30 11:12:01.006691: train_loss -0.9889 +2025-10-30 11:12:01.009801: val_loss -0.8886 +2025-10-30 11:12:01.012218: Pseudo dice [np.float32(0.9816), np.float32(0.9881), np.float32(0.9947), np.float32(0.7889)] +2025-10-30 11:12:01.014233: Epoch time: 21.39 s +2025-10-30 11:12:02.137785: +2025-10-30 11:12:02.139811: Epoch 410 +2025-10-30 11:12:02.141608: Current learning rate: 0.00622 +2025-10-30 11:12:24.026579: train_loss -0.9893 +2025-10-30 11:12:24.028974: val_loss -0.8755 +2025-10-30 11:12:24.030437: Pseudo dice [np.float32(0.9804), np.float32(0.987), np.float32(0.9933), np.float32(0.7603)] +2025-10-30 11:12:24.032576: Epoch time: 21.89 s +2025-10-30 11:12:24.976405: +2025-10-30 11:12:24.978180: Epoch 411 +2025-10-30 11:12:24.979946: Current learning rate: 0.00621 +2025-10-30 11:12:46.478408: train_loss -0.9885 +2025-10-30 11:12:46.483819: val_loss -0.8944 +2025-10-30 11:12:46.485530: Pseudo dice [np.float32(0.9831), np.float32(0.9889), np.float32(0.9946), np.float32(0.7965)] +2025-10-30 11:12:46.487240: Epoch time: 21.5 s +2025-10-30 11:12:48.755243: +2025-10-30 11:12:48.757282: Epoch 412 +2025-10-30 11:12:48.758943: Current learning rate: 0.0062 +2025-10-30 11:13:09.744289: train_loss -0.9895 +2025-10-30 11:13:09.746903: val_loss -0.8899 +2025-10-30 11:13:09.748436: Pseudo dice [np.float32(0.9813), np.float32(0.9876), np.float32(0.9943), np.float32(0.793)] +2025-10-30 11:13:09.749951: Epoch time: 20.99 s +2025-10-30 11:13:10.790990: +2025-10-30 11:13:10.793478: Epoch 413 +2025-10-30 11:13:10.795335: Current learning rate: 0.00619 +2025-10-30 11:13:32.825414: train_loss -0.9901 +2025-10-30 11:13:32.828289: val_loss -0.8722 +2025-10-30 11:13:32.830116: Pseudo dice [np.float32(0.9792), np.float32(0.9863), np.float32(0.9937), np.float32(0.7517)] +2025-10-30 11:13:32.831726: Epoch time: 22.04 s +2025-10-30 11:13:33.950482: +2025-10-30 11:13:33.952449: Epoch 414 +2025-10-30 11:13:33.953955: Current learning rate: 0.00618 +2025-10-30 11:13:55.686024: train_loss -0.9898 +2025-10-30 11:13:55.687871: val_loss -0.8819 +2025-10-30 11:13:55.689356: Pseudo dice [np.float32(0.9814), np.float32(0.987), np.float32(0.9934), np.float32(0.7721)] +2025-10-30 11:13:55.690808: Epoch time: 21.74 s +2025-10-30 11:13:56.947548: +2025-10-30 11:13:56.949470: Epoch 415 +2025-10-30 11:13:56.951038: Current learning rate: 0.00617 +2025-10-30 11:14:18.112567: train_loss -0.9887 +2025-10-30 11:14:18.132633: val_loss -0.8788 +2025-10-30 11:14:18.139149: Pseudo dice [np.float32(0.9818), np.float32(0.9876), np.float32(0.9935), np.float32(0.7572)] +2025-10-30 11:14:18.143913: Epoch time: 21.17 s +2025-10-30 11:14:19.400686: +2025-10-30 11:14:19.402686: Epoch 416 +2025-10-30 11:14:19.404363: Current learning rate: 0.00616 +2025-10-30 11:14:40.492213: train_loss -0.9879 +2025-10-30 11:14:40.502283: val_loss -0.8846 +2025-10-30 11:14:40.507650: Pseudo dice [np.float32(0.9808), np.float32(0.9872), np.float32(0.994), np.float32(0.777)] +2025-10-30 11:14:40.512788: Epoch time: 21.09 s +2025-10-30 11:14:41.778261: +2025-10-30 11:14:41.779763: Epoch 417 +2025-10-30 11:14:41.781115: Current learning rate: 0.00615 +2025-10-30 11:15:03.952306: train_loss -0.9899 +2025-10-30 11:15:03.954137: val_loss -0.8753 +2025-10-30 11:15:03.955606: Pseudo dice [np.float32(0.981), np.float32(0.9878), np.float32(0.9943), np.float32(0.7683)] +2025-10-30 11:15:03.957225: Epoch time: 22.18 s +2025-10-30 11:15:04.992200: +2025-10-30 11:15:04.993895: Epoch 418 +2025-10-30 11:15:04.995342: Current learning rate: 0.00614 +2025-10-30 11:15:25.576996: train_loss -0.9886 +2025-10-30 11:15:25.579650: val_loss -0.8928 +2025-10-30 11:15:25.581177: Pseudo dice [np.float32(0.9811), np.float32(0.9877), np.float32(0.9948), np.float32(0.7941)] +2025-10-30 11:15:25.582779: Epoch time: 20.59 s +2025-10-30 11:15:26.590410: +2025-10-30 11:15:26.592414: Epoch 419 +2025-10-30 11:15:26.594486: Current learning rate: 0.00613 +2025-10-30 11:15:48.440818: train_loss -0.9888 +2025-10-30 11:15:48.444643: val_loss -0.8848 +2025-10-30 11:15:48.446890: Pseudo dice [np.float32(0.9822), np.float32(0.9885), np.float32(0.9943), np.float32(0.773)] +2025-10-30 11:15:48.448994: Epoch time: 21.85 s +2025-10-30 11:15:49.788921: +2025-10-30 11:15:49.791036: Epoch 420 +2025-10-30 11:15:49.792631: Current learning rate: 0.00612 +2025-10-30 11:16:11.801645: train_loss -0.9892 +2025-10-30 11:16:11.804027: val_loss -0.8998 +2025-10-30 11:16:11.805765: Pseudo dice [np.float32(0.9827), np.float32(0.9887), np.float32(0.995), np.float32(0.8121)] +2025-10-30 11:16:11.807391: Epoch time: 22.01 s +2025-10-30 11:16:12.883119: +2025-10-30 11:16:12.884943: Epoch 421 +2025-10-30 11:16:12.886496: Current learning rate: 0.00612 +2025-10-30 11:16:33.815376: train_loss -0.9893 +2025-10-30 11:16:33.817830: val_loss -0.8884 +2025-10-30 11:16:33.819587: Pseudo dice [np.float32(0.9802), np.float32(0.9875), np.float32(0.9948), np.float32(0.789)] +2025-10-30 11:16:33.821214: Epoch time: 20.93 s +2025-10-30 11:16:34.982680: +2025-10-30 11:16:34.985241: Epoch 422 +2025-10-30 11:16:34.986827: Current learning rate: 0.00611 +2025-10-30 11:16:56.929684: train_loss -0.9902 +2025-10-30 11:16:56.933545: val_loss -0.885 +2025-10-30 11:16:56.935547: Pseudo dice [np.float32(0.9819), np.float32(0.988), np.float32(0.9945), np.float32(0.7779)] +2025-10-30 11:16:56.937056: Epoch time: 21.95 s +2025-10-30 11:16:58.090074: +2025-10-30 11:16:58.092088: Epoch 423 +2025-10-30 11:16:58.093917: Current learning rate: 0.0061 +2025-10-30 11:17:19.779021: train_loss -0.9899 +2025-10-30 11:17:19.781554: val_loss -0.8818 +2025-10-30 11:17:19.783465: Pseudo dice [np.float32(0.9774), np.float32(0.9861), np.float32(0.9942), np.float32(0.7954)] +2025-10-30 11:17:19.785498: Epoch time: 21.69 s +2025-10-30 11:17:20.823475: +2025-10-30 11:17:20.825503: Epoch 424 +2025-10-30 11:17:20.827487: Current learning rate: 0.00609 +2025-10-30 11:17:42.576151: train_loss -0.9888 +2025-10-30 11:17:42.578878: val_loss -0.886 +2025-10-30 11:17:42.580537: Pseudo dice [np.float32(0.9808), np.float32(0.9887), np.float32(0.995), np.float32(0.7778)] +2025-10-30 11:17:42.582166: Epoch time: 21.75 s +2025-10-30 11:17:43.627574: +2025-10-30 11:17:43.629667: Epoch 425 +2025-10-30 11:17:43.631450: Current learning rate: 0.00608 +2025-10-30 11:18:04.958599: train_loss -0.9895 +2025-10-30 11:18:04.962110: val_loss -0.8857 +2025-10-30 11:18:04.963786: Pseudo dice [np.float32(0.981), np.float32(0.9878), np.float32(0.9941), np.float32(0.7766)] +2025-10-30 11:18:04.965343: Epoch time: 21.33 s +2025-10-30 11:18:06.187937: +2025-10-30 11:18:06.189753: Epoch 426 +2025-10-30 11:18:06.191280: Current learning rate: 0.00607 +2025-10-30 11:18:28.404963: train_loss -0.9895 +2025-10-30 11:18:28.407187: val_loss -0.8855 +2025-10-30 11:18:28.408696: Pseudo dice [np.float32(0.9801), np.float32(0.9877), np.float32(0.9948), np.float32(0.7884)] +2025-10-30 11:18:28.410220: Epoch time: 22.22 s +2025-10-30 11:18:29.638219: +2025-10-30 11:18:29.640539: Epoch 427 +2025-10-30 11:18:29.642705: Current learning rate: 0.00606 +2025-10-30 11:18:50.458499: train_loss -0.9898 +2025-10-30 11:18:50.461392: val_loss -0.882 +2025-10-30 11:18:50.463332: Pseudo dice [np.float32(0.9807), np.float32(0.9879), np.float32(0.994), np.float32(0.7768)] +2025-10-30 11:18:50.465455: Epoch time: 20.82 s +2025-10-30 11:18:51.514289: +2025-10-30 11:18:51.516398: Epoch 428 +2025-10-30 11:18:51.518096: Current learning rate: 0.00605 +2025-10-30 11:19:13.373390: train_loss -0.9899 +2025-10-30 11:19:13.375654: val_loss -0.8822 +2025-10-30 11:19:13.377499: Pseudo dice [np.float32(0.9803), np.float32(0.9877), np.float32(0.994), np.float32(0.7779)] +2025-10-30 11:19:13.378855: Epoch time: 21.86 s +2025-10-30 11:19:15.459254: +2025-10-30 11:19:15.461299: Epoch 429 +2025-10-30 11:19:15.462837: Current learning rate: 0.00604 +2025-10-30 11:19:37.309695: train_loss -0.99 +2025-10-30 11:19:37.311579: val_loss -0.88 +2025-10-30 11:19:37.313049: Pseudo dice [np.float32(0.9815), np.float32(0.9891), np.float32(0.994), np.float32(0.7644)] +2025-10-30 11:19:37.314474: Epoch time: 21.85 s +2025-10-30 11:19:38.537396: +2025-10-30 11:19:38.539140: Epoch 430 +2025-10-30 11:19:38.540701: Current learning rate: 0.00603 +2025-10-30 11:20:00.568931: train_loss -0.9896 +2025-10-30 11:20:00.572298: val_loss -0.8882 +2025-10-30 11:20:00.574078: Pseudo dice [np.float32(0.9829), np.float32(0.9889), np.float32(0.9942), np.float32(0.7814)] +2025-10-30 11:20:00.575733: Epoch time: 22.03 s +2025-10-30 11:20:01.773343: +2025-10-30 11:20:01.775559: Epoch 431 +2025-10-30 11:20:01.777506: Current learning rate: 0.00602 +2025-10-30 11:20:22.947377: train_loss -0.989 +2025-10-30 11:20:22.949941: val_loss -0.8795 +2025-10-30 11:20:22.951458: Pseudo dice [np.float32(0.9817), np.float32(0.9867), np.float32(0.9938), np.float32(0.7683)] +2025-10-30 11:20:22.952894: Epoch time: 21.18 s +2025-10-30 11:20:24.259918: +2025-10-30 11:20:24.261732: Epoch 432 +2025-10-30 11:20:24.264590: Current learning rate: 0.00601 +2025-10-30 11:20:45.986512: train_loss -0.9896 +2025-10-30 11:20:45.989051: val_loss -0.8816 +2025-10-30 11:20:45.991507: Pseudo dice [np.float32(0.9823), np.float32(0.9889), np.float32(0.9945), np.float32(0.7676)] +2025-10-30 11:20:45.993856: Epoch time: 21.73 s +2025-10-30 11:20:47.056273: +2025-10-30 11:20:47.058253: Epoch 433 +2025-10-30 11:20:47.059938: Current learning rate: 0.006 +2025-10-30 11:21:08.163774: train_loss -0.9881 +2025-10-30 11:21:08.166039: val_loss -0.8894 +2025-10-30 11:21:08.168030: Pseudo dice [np.float32(0.9806), np.float32(0.9876), np.float32(0.9948), np.float32(0.7946)] +2025-10-30 11:21:08.170322: Epoch time: 21.11 s +2025-10-30 11:21:09.364276: +2025-10-30 11:21:09.366289: Epoch 434 +2025-10-30 11:21:09.367769: Current learning rate: 0.00599 +2025-10-30 11:21:30.920347: train_loss -0.9876 +2025-10-30 11:21:30.923696: val_loss -0.8738 +2025-10-30 11:21:30.925418: Pseudo dice [np.float32(0.9792), np.float32(0.9863), np.float32(0.9935), np.float32(0.754)] +2025-10-30 11:21:30.927252: Epoch time: 21.56 s +2025-10-30 11:21:32.147254: +2025-10-30 11:21:32.148985: Epoch 435 +2025-10-30 11:21:32.154037: Current learning rate: 0.00598 +2025-10-30 11:21:53.829315: train_loss -0.9887 +2025-10-30 11:21:53.831749: val_loss -0.8768 +2025-10-30 11:21:53.833688: Pseudo dice [np.float32(0.9808), np.float32(0.9871), np.float32(0.9936), np.float32(0.7563)] +2025-10-30 11:21:53.835403: Epoch time: 21.68 s +2025-10-30 11:21:55.090927: +2025-10-30 11:21:55.092741: Epoch 436 +2025-10-30 11:21:55.094445: Current learning rate: 0.00597 +2025-10-30 11:22:16.602110: train_loss -0.9893 +2025-10-30 11:22:16.604506: val_loss -0.8847 +2025-10-30 11:22:16.606029: Pseudo dice [np.float32(0.9815), np.float32(0.9885), np.float32(0.9946), np.float32(0.7743)] +2025-10-30 11:22:16.607590: Epoch time: 21.51 s +2025-10-30 11:22:17.903736: +2025-10-30 11:22:17.905742: Epoch 437 +2025-10-30 11:22:17.908007: Current learning rate: 0.00596 +2025-10-30 11:22:39.366515: train_loss -0.9895 +2025-10-30 11:22:39.369442: val_loss -0.8803 +2025-10-30 11:22:39.371905: Pseudo dice [np.float32(0.9806), np.float32(0.9874), np.float32(0.9942), np.float32(0.7779)] +2025-10-30 11:22:39.374165: Epoch time: 21.46 s +2025-10-30 11:22:40.398562: +2025-10-30 11:22:40.400314: Epoch 438 +2025-10-30 11:22:40.402233: Current learning rate: 0.00595 +2025-10-30 11:23:00.818535: train_loss -0.9901 +2025-10-30 11:23:00.821422: val_loss -0.8926 +2025-10-30 11:23:00.823278: Pseudo dice [np.float32(0.9807), np.float32(0.9876), np.float32(0.9949), np.float32(0.804)] +2025-10-30 11:23:00.824950: Epoch time: 20.42 s +2025-10-30 11:23:02.104839: +2025-10-30 11:23:02.106922: Epoch 439 +2025-10-30 11:23:02.108629: Current learning rate: 0.00594 +2025-10-30 11:23:22.771134: train_loss -0.9899 +2025-10-30 11:23:22.773620: val_loss -0.8883 +2025-10-30 11:23:22.775143: Pseudo dice [np.float32(0.9816), np.float32(0.9881), np.float32(0.9947), np.float32(0.7857)] +2025-10-30 11:23:22.777200: Epoch time: 20.67 s +2025-10-30 11:23:24.074722: +2025-10-30 11:23:24.076932: Epoch 440 +2025-10-30 11:23:24.078840: Current learning rate: 0.00593 +2025-10-30 11:23:45.599487: train_loss -0.9908 +2025-10-30 11:23:45.601894: val_loss -0.8807 +2025-10-30 11:23:45.603631: Pseudo dice [np.float32(0.9834), np.float32(0.9895), np.float32(0.9941), np.float32(0.7652)] +2025-10-30 11:23:45.605434: Epoch time: 21.53 s +2025-10-30 11:23:46.709429: +2025-10-30 11:23:46.711528: Epoch 441 +2025-10-30 11:23:46.713223: Current learning rate: 0.00592 +2025-10-30 11:24:08.273245: train_loss -0.9891 +2025-10-30 11:24:08.276907: val_loss -0.8854 +2025-10-30 11:24:08.278487: Pseudo dice [np.float32(0.9799), np.float32(0.9866), np.float32(0.9942), np.float32(0.7948)] +2025-10-30 11:24:08.280087: Epoch time: 21.57 s +2025-10-30 11:24:09.476276: +2025-10-30 11:24:09.478019: Epoch 442 +2025-10-30 11:24:09.479404: Current learning rate: 0.00592 +2025-10-30 11:24:32.093609: train_loss -0.9899 +2025-10-30 11:24:32.095996: val_loss -0.8831 +2025-10-30 11:24:32.098590: Pseudo dice [np.float32(0.9818), np.float32(0.9886), np.float32(0.9942), np.float32(0.7735)] +2025-10-30 11:24:32.100295: Epoch time: 22.62 s +2025-10-30 11:24:33.210748: +2025-10-30 11:24:33.212582: Epoch 443 +2025-10-30 11:24:33.214254: Current learning rate: 0.00591 +2025-10-30 11:24:55.379364: train_loss -0.9892 +2025-10-30 11:24:55.381808: val_loss -0.8703 +2025-10-30 11:24:55.383464: Pseudo dice [np.float32(0.9811), np.float32(0.9878), np.float32(0.9936), np.float32(0.7398)] +2025-10-30 11:24:55.385231: Epoch time: 22.17 s +2025-10-30 11:24:56.566161: +2025-10-30 11:24:56.568036: Epoch 444 +2025-10-30 11:24:56.569856: Current learning rate: 0.0059 +2025-10-30 11:25:17.486445: train_loss -0.989 +2025-10-30 11:25:17.488772: val_loss -0.8827 +2025-10-30 11:25:17.490448: Pseudo dice [np.float32(0.9809), np.float32(0.9884), np.float32(0.994), np.float32(0.7652)] +2025-10-30 11:25:17.492111: Epoch time: 20.92 s +2025-10-30 11:25:18.780781: +2025-10-30 11:25:18.782859: Epoch 445 +2025-10-30 11:25:18.784449: Current learning rate: 0.00589 +2025-10-30 11:25:39.375022: train_loss -0.9898 +2025-10-30 11:25:39.377747: val_loss -0.8803 +2025-10-30 11:25:39.379870: Pseudo dice [np.float32(0.9784), np.float32(0.9871), np.float32(0.9945), np.float32(0.771)] +2025-10-30 11:25:39.382016: Epoch time: 20.6 s +2025-10-30 11:25:40.587151: +2025-10-30 11:25:40.589187: Epoch 446 +2025-10-30 11:25:40.591091: Current learning rate: 0.00588 +2025-10-30 11:26:02.797770: train_loss -0.9894 +2025-10-30 11:26:02.801199: val_loss -0.8783 +2025-10-30 11:26:02.804581: Pseudo dice [np.float32(0.9793), np.float32(0.9876), np.float32(0.9934), np.float32(0.7627)] +2025-10-30 11:26:02.806280: Epoch time: 22.21 s +2025-10-30 11:26:05.375557: +2025-10-30 11:26:05.377668: Epoch 447 +2025-10-30 11:26:05.379511: Current learning rate: 0.00587 +2025-10-30 11:26:27.752358: train_loss -0.9892 +2025-10-30 11:26:27.757567: val_loss -0.8826 +2025-10-30 11:26:27.759776: Pseudo dice [np.float32(0.9816), np.float32(0.9875), np.float32(0.9938), np.float32(0.7745)] +2025-10-30 11:26:27.762015: Epoch time: 22.38 s +2025-10-30 11:26:28.902529: +2025-10-30 11:26:28.904352: Epoch 448 +2025-10-30 11:26:28.905889: Current learning rate: 0.00586 +2025-10-30 11:26:51.086637: train_loss -0.9901 +2025-10-30 11:26:51.089048: val_loss -0.8794 +2025-10-30 11:26:51.090719: Pseudo dice [np.float32(0.9782), np.float32(0.9868), np.float32(0.994), np.float32(0.7751)] +2025-10-30 11:26:51.092253: Epoch time: 22.19 s +2025-10-30 11:26:52.253112: +2025-10-30 11:26:52.254865: Epoch 449 +2025-10-30 11:26:52.256357: Current learning rate: 0.00585 +2025-10-30 11:27:14.248536: train_loss -0.9901 +2025-10-30 11:27:14.251760: val_loss -0.8815 +2025-10-30 11:27:14.253670: Pseudo dice [np.float32(0.9799), np.float32(0.9871), np.float32(0.9941), np.float32(0.7755)] +2025-10-30 11:27:14.255401: Epoch time: 22.0 s +2025-10-30 11:27:16.572821: +2025-10-30 11:27:16.575267: Epoch 450 +2025-10-30 11:27:16.577676: Current learning rate: 0.00584 +2025-10-30 11:27:38.355173: train_loss -0.9891 +2025-10-30 11:27:38.357246: val_loss -0.8806 +2025-10-30 11:27:38.359007: Pseudo dice [np.float32(0.9819), np.float32(0.9888), np.float32(0.9942), np.float32(0.7657)] +2025-10-30 11:27:38.360508: Epoch time: 21.78 s +2025-10-30 11:27:39.412846: +2025-10-30 11:27:39.414853: Epoch 451 +2025-10-30 11:27:39.416679: Current learning rate: 0.00583 +2025-10-30 11:27:58.705830: train_loss -0.9905 +2025-10-30 11:27:58.708137: val_loss -0.8836 +2025-10-30 11:27:58.710282: Pseudo dice [np.float32(0.9823), np.float32(0.988), np.float32(0.9944), np.float32(0.7745)] +2025-10-30 11:27:58.711988: Epoch time: 19.29 s +2025-10-30 11:27:59.887485: +2025-10-30 11:27:59.889503: Epoch 452 +2025-10-30 11:27:59.891331: Current learning rate: 0.00582 +2025-10-30 11:28:21.627236: train_loss -0.9899 +2025-10-30 11:28:21.629716: val_loss -0.8858 +2025-10-30 11:28:21.631456: Pseudo dice [np.float32(0.9831), np.float32(0.9889), np.float32(0.994), np.float32(0.7727)] +2025-10-30 11:28:21.632993: Epoch time: 21.74 s +2025-10-30 11:28:22.804913: +2025-10-30 11:28:22.806972: Epoch 453 +2025-10-30 11:28:22.808737: Current learning rate: 0.00581 +2025-10-30 11:28:44.474427: train_loss -0.9899 +2025-10-30 11:28:44.476803: val_loss -0.8847 +2025-10-30 11:28:44.479099: Pseudo dice [np.float32(0.9823), np.float32(0.9879), np.float32(0.9939), np.float32(0.7733)] +2025-10-30 11:28:44.481369: Epoch time: 21.67 s +2025-10-30 11:28:45.645603: +2025-10-30 11:28:45.648407: Epoch 454 +2025-10-30 11:28:45.650540: Current learning rate: 0.0058 +2025-10-30 11:29:07.409431: train_loss -0.9899 +2025-10-30 11:29:07.411866: val_loss -0.8742 +2025-10-30 11:29:07.414214: Pseudo dice [np.float32(0.9805), np.float32(0.9869), np.float32(0.9937), np.float32(0.7611)] +2025-10-30 11:29:07.416318: Epoch time: 21.77 s +2025-10-30 11:29:08.638754: +2025-10-30 11:29:08.641541: Epoch 455 +2025-10-30 11:29:08.643597: Current learning rate: 0.00579 +2025-10-30 11:29:29.947789: train_loss -0.9904 +2025-10-30 11:29:29.950928: val_loss -0.8768 +2025-10-30 11:29:29.952815: Pseudo dice [np.float32(0.9809), np.float32(0.9879), np.float32(0.9936), np.float32(0.7648)] +2025-10-30 11:29:29.954738: Epoch time: 21.31 s +2025-10-30 11:29:31.037024: +2025-10-30 11:29:31.041252: Epoch 456 +2025-10-30 11:29:31.044258: Current learning rate: 0.00578 +2025-10-30 11:29:52.414697: train_loss -0.9903 +2025-10-30 11:29:52.416700: val_loss -0.8872 +2025-10-30 11:29:52.418477: Pseudo dice [np.float32(0.9812), np.float32(0.9877), np.float32(0.9945), np.float32(0.787)] +2025-10-30 11:29:52.419999: Epoch time: 21.38 s +2025-10-30 11:29:53.463806: +2025-10-30 11:29:53.466126: Epoch 457 +2025-10-30 11:29:53.468021: Current learning rate: 0.00577 +2025-10-30 11:30:12.177089: train_loss -0.9898 +2025-10-30 11:30:12.179346: val_loss -0.8794 +2025-10-30 11:30:12.180890: Pseudo dice [np.float32(0.9811), np.float32(0.9881), np.float32(0.9941), np.float32(0.7686)] +2025-10-30 11:30:12.182334: Epoch time: 18.72 s +2025-10-30 11:30:13.385397: +2025-10-30 11:30:13.387289: Epoch 458 +2025-10-30 11:30:13.389180: Current learning rate: 0.00576 +2025-10-30 11:30:34.411643: train_loss -0.9899 +2025-10-30 11:30:34.415034: val_loss -0.8806 +2025-10-30 11:30:34.417228: Pseudo dice [np.float32(0.9816), np.float32(0.9874), np.float32(0.9936), np.float32(0.7743)] +2025-10-30 11:30:34.418837: Epoch time: 21.03 s +2025-10-30 11:30:35.615603: +2025-10-30 11:30:35.617531: Epoch 459 +2025-10-30 11:30:35.619118: Current learning rate: 0.00575 +2025-10-30 11:30:57.034598: train_loss -0.9902 +2025-10-30 11:30:57.036932: val_loss -0.8741 +2025-10-30 11:30:57.039480: Pseudo dice [np.float32(0.9829), np.float32(0.9885), np.float32(0.9933), np.float32(0.7473)] +2025-10-30 11:30:57.041240: Epoch time: 21.42 s +2025-10-30 11:30:58.214359: +2025-10-30 11:30:58.217063: Epoch 460 +2025-10-30 11:30:58.218754: Current learning rate: 0.00574 +2025-10-30 11:31:20.080010: train_loss -0.9902 +2025-10-30 11:31:20.084769: val_loss -0.8748 +2025-10-30 11:31:20.086442: Pseudo dice [np.float32(0.9815), np.float32(0.9887), np.float32(0.9944), np.float32(0.7557)] +2025-10-30 11:31:20.087905: Epoch time: 21.87 s +2025-10-30 11:31:21.353412: +2025-10-30 11:31:21.355445: Epoch 461 +2025-10-30 11:31:21.357147: Current learning rate: 0.00573 +2025-10-30 11:31:42.973610: train_loss -0.99 +2025-10-30 11:31:42.980010: val_loss -0.8792 +2025-10-30 11:31:42.981712: Pseudo dice [np.float32(0.9816), np.float32(0.9885), np.float32(0.9939), np.float32(0.7639)] +2025-10-30 11:31:42.983326: Epoch time: 21.62 s +2025-10-30 11:31:44.066306: +2025-10-30 11:31:44.068480: Epoch 462 +2025-10-30 11:31:44.071474: Current learning rate: 0.00572 +2025-10-30 11:32:05.699366: train_loss -0.9896 +2025-10-30 11:32:05.701832: val_loss -0.8849 +2025-10-30 11:32:05.703490: Pseudo dice [np.float32(0.9814), np.float32(0.9881), np.float32(0.9948), np.float32(0.7769)] +2025-10-30 11:32:05.705026: Epoch time: 21.63 s +2025-10-30 11:32:06.917644: +2025-10-30 11:32:06.919451: Epoch 463 +2025-10-30 11:32:06.920976: Current learning rate: 0.00571 +2025-10-30 11:32:28.357048: train_loss -0.9891 +2025-10-30 11:32:28.359586: val_loss -0.8736 +2025-10-30 11:32:28.361611: Pseudo dice [np.float32(0.9807), np.float32(0.9869), np.float32(0.9938), np.float32(0.753)] +2025-10-30 11:32:28.363300: Epoch time: 21.44 s +2025-10-30 11:32:29.394418: +2025-10-30 11:32:29.396221: Epoch 464 +2025-10-30 11:32:29.397987: Current learning rate: 0.0057 +2025-10-30 11:32:49.180257: train_loss -0.9896 +2025-10-30 11:32:49.184301: val_loss -0.8884 +2025-10-30 11:32:49.185896: Pseudo dice [np.float32(0.9828), np.float32(0.9885), np.float32(0.9944), np.float32(0.7736)] +2025-10-30 11:32:49.187230: Epoch time: 19.79 s +2025-10-30 11:32:51.360073: +2025-10-30 11:32:51.361922: Epoch 465 +2025-10-30 11:32:51.363481: Current learning rate: 0.0057 +2025-10-30 11:33:13.099958: train_loss -0.9902 +2025-10-30 11:33:13.102507: val_loss -0.8883 +2025-10-30 11:33:13.104072: Pseudo dice [np.float32(0.9812), np.float32(0.9872), np.float32(0.9943), np.float32(0.7923)] +2025-10-30 11:33:13.105793: Epoch time: 21.74 s +2025-10-30 11:33:14.274501: +2025-10-30 11:33:14.276404: Epoch 466 +2025-10-30 11:33:14.278423: Current learning rate: 0.00569 +2025-10-30 11:33:35.827660: train_loss -0.9897 +2025-10-30 11:33:35.830087: val_loss -0.8873 +2025-10-30 11:33:35.831653: Pseudo dice [np.float32(0.9803), np.float32(0.9876), np.float32(0.9946), np.float32(0.785)] +2025-10-30 11:33:35.833186: Epoch time: 21.56 s +2025-10-30 11:33:36.931968: +2025-10-30 11:33:36.933908: Epoch 467 +2025-10-30 11:33:36.935504: Current learning rate: 0.00568 +2025-10-30 11:33:58.456285: train_loss -0.99 +2025-10-30 11:33:58.460521: val_loss -0.8779 +2025-10-30 11:33:58.462355: Pseudo dice [np.float32(0.9814), np.float32(0.9878), np.float32(0.9942), np.float32(0.7629)] +2025-10-30 11:33:58.464024: Epoch time: 21.53 s +2025-10-30 11:33:59.518698: +2025-10-30 11:33:59.520520: Epoch 468 +2025-10-30 11:33:59.521962: Current learning rate: 0.00567 +2025-10-30 11:34:21.189858: train_loss -0.9901 +2025-10-30 11:34:21.192690: val_loss -0.8855 +2025-10-30 11:34:21.194872: Pseudo dice [np.float32(0.9812), np.float32(0.9874), np.float32(0.9937), np.float32(0.7737)] +2025-10-30 11:34:21.196501: Epoch time: 21.67 s +2025-10-30 11:34:22.455870: +2025-10-30 11:34:22.457775: Epoch 469 +2025-10-30 11:34:22.459590: Current learning rate: 0.00566 +2025-10-30 11:34:44.316032: train_loss -0.9896 +2025-10-30 11:34:44.318192: val_loss -0.9009 +2025-10-30 11:34:44.319902: Pseudo dice [np.float32(0.9824), np.float32(0.9888), np.float32(0.9947), np.float32(0.8103)] +2025-10-30 11:34:44.321779: Epoch time: 21.86 s +2025-10-30 11:34:45.348125: +2025-10-30 11:34:45.350143: Epoch 470 +2025-10-30 11:34:45.351702: Current learning rate: 0.00565 +2025-10-30 11:35:06.041654: train_loss -0.9905 +2025-10-30 11:35:06.044346: val_loss -0.8772 +2025-10-30 11:35:06.046015: Pseudo dice [np.float32(0.9788), np.float32(0.9874), np.float32(0.9941), np.float32(0.7671)] +2025-10-30 11:35:06.047536: Epoch time: 20.69 s +2025-10-30 11:35:07.427746: +2025-10-30 11:35:07.432170: Epoch 471 +2025-10-30 11:35:07.433980: Current learning rate: 0.00564 +2025-10-30 11:35:29.241323: train_loss -0.9896 +2025-10-30 11:35:29.244158: val_loss -0.8808 +2025-10-30 11:35:29.245749: Pseudo dice [np.float32(0.9802), np.float32(0.9879), np.float32(0.9942), np.float32(0.7677)] +2025-10-30 11:35:29.247149: Epoch time: 21.82 s +2025-10-30 11:35:30.362554: +2025-10-30 11:35:30.364809: Epoch 472 +2025-10-30 11:35:30.366398: Current learning rate: 0.00563 +2025-10-30 11:35:52.394464: train_loss -0.9888 +2025-10-30 11:35:52.397948: val_loss -0.887 +2025-10-30 11:35:52.399631: Pseudo dice [np.float32(0.9806), np.float32(0.9883), np.float32(0.9943), np.float32(0.7818)] +2025-10-30 11:35:52.401277: Epoch time: 22.03 s +2025-10-30 11:35:53.610556: +2025-10-30 11:35:53.612545: Epoch 473 +2025-10-30 11:35:53.614166: Current learning rate: 0.00562 +2025-10-30 11:36:16.073342: train_loss -0.9891 +2025-10-30 11:36:16.075930: val_loss -0.8854 +2025-10-30 11:36:16.077527: Pseudo dice [np.float32(0.9802), np.float32(0.9877), np.float32(0.9938), np.float32(0.7803)] +2025-10-30 11:36:16.079093: Epoch time: 22.46 s +2025-10-30 11:36:17.085591: +2025-10-30 11:36:17.087920: Epoch 474 +2025-10-30 11:36:17.090204: Current learning rate: 0.00561 +2025-10-30 11:36:39.379286: train_loss -0.9901 +2025-10-30 11:36:39.381701: val_loss -0.8774 +2025-10-30 11:36:39.383645: Pseudo dice [np.float32(0.9802), np.float32(0.9873), np.float32(0.994), np.float32(0.7571)] +2025-10-30 11:36:39.385625: Epoch time: 22.3 s +2025-10-30 11:36:40.372580: +2025-10-30 11:36:40.374634: Epoch 475 +2025-10-30 11:36:40.376517: Current learning rate: 0.0056 +2025-10-30 11:37:02.573326: train_loss -0.9904 +2025-10-30 11:37:02.575735: val_loss -0.8853 +2025-10-30 11:37:02.577225: Pseudo dice [np.float32(0.983), np.float32(0.9889), np.float32(0.9941), np.float32(0.7641)] +2025-10-30 11:37:02.578907: Epoch time: 22.2 s +2025-10-30 11:37:03.741579: +2025-10-30 11:37:03.743423: Epoch 476 +2025-10-30 11:37:03.745325: Current learning rate: 0.00559 +2025-10-30 11:37:25.202192: train_loss -0.9899 +2025-10-30 11:37:25.205519: val_loss -0.8898 +2025-10-30 11:37:25.208044: Pseudo dice [np.float32(0.9806), np.float32(0.9873), np.float32(0.9941), np.float32(0.7926)] +2025-10-30 11:37:25.211859: Epoch time: 21.46 s +2025-10-30 11:37:26.374838: +2025-10-30 11:37:26.379024: Epoch 477 +2025-10-30 11:37:26.383780: Current learning rate: 0.00558 +2025-10-30 11:37:47.480216: train_loss -0.9898 +2025-10-30 11:37:47.482412: val_loss -0.8898 +2025-10-30 11:37:47.484395: Pseudo dice [np.float32(0.9816), np.float32(0.9886), np.float32(0.9943), np.float32(0.7904)] +2025-10-30 11:37:47.486102: Epoch time: 21.11 s +2025-10-30 11:37:48.548576: +2025-10-30 11:37:48.550336: Epoch 478 +2025-10-30 11:37:48.552279: Current learning rate: 0.00557 +2025-10-30 11:38:10.198139: train_loss -0.9911 +2025-10-30 11:38:10.200548: val_loss -0.8834 +2025-10-30 11:38:10.202295: Pseudo dice [np.float32(0.9832), np.float32(0.9889), np.float32(0.9945), np.float32(0.7657)] +2025-10-30 11:38:10.203995: Epoch time: 21.65 s +2025-10-30 11:38:11.208691: +2025-10-30 11:38:11.212667: Epoch 479 +2025-10-30 11:38:11.214605: Current learning rate: 0.00556 +2025-10-30 11:38:33.042352: train_loss -0.9906 +2025-10-30 11:38:33.045336: val_loss -0.8739 +2025-10-30 11:38:33.046882: Pseudo dice [np.float32(0.98), np.float32(0.987), np.float32(0.9933), np.float32(0.7573)] +2025-10-30 11:38:33.048487: Epoch time: 21.83 s +2025-10-30 11:38:34.254335: +2025-10-30 11:38:34.256217: Epoch 480 +2025-10-30 11:38:34.257753: Current learning rate: 0.00555 +2025-10-30 11:38:56.172843: train_loss -0.9903 +2025-10-30 11:38:56.174896: val_loss -0.8786 +2025-10-30 11:38:56.176426: Pseudo dice [np.float32(0.9808), np.float32(0.988), np.float32(0.9936), np.float32(0.7644)] +2025-10-30 11:38:56.177883: Epoch time: 21.92 s +2025-10-30 11:38:57.363222: +2025-10-30 11:38:57.365053: Epoch 481 +2025-10-30 11:38:57.366519: Current learning rate: 0.00554 +2025-10-30 11:39:19.638240: train_loss -0.991 +2025-10-30 11:39:19.640516: val_loss -0.8833 +2025-10-30 11:39:19.642222: Pseudo dice [np.float32(0.9807), np.float32(0.988), np.float32(0.9939), np.float32(0.77)] +2025-10-30 11:39:19.643875: Epoch time: 22.28 s +2025-10-30 11:39:20.701061: +2025-10-30 11:39:20.702946: Epoch 482 +2025-10-30 11:39:20.704424: Current learning rate: 0.00553 +2025-10-30 11:39:41.674507: train_loss -0.9903 +2025-10-30 11:39:41.677224: val_loss -0.8865 +2025-10-30 11:39:41.678832: Pseudo dice [np.float32(0.9799), np.float32(0.9872), np.float32(0.9941), np.float32(0.7856)] +2025-10-30 11:39:41.680392: Epoch time: 20.97 s +2025-10-30 11:39:43.491785: +2025-10-30 11:39:43.493777: Epoch 483 +2025-10-30 11:39:43.495427: Current learning rate: 0.00552 +2025-10-30 11:40:04.456178: train_loss -0.9902 +2025-10-30 11:40:04.458473: val_loss -0.8743 +2025-10-30 11:40:04.460925: Pseudo dice [np.float32(0.9809), np.float32(0.9882), np.float32(0.9936), np.float32(0.7474)] +2025-10-30 11:40:04.462695: Epoch time: 20.97 s +2025-10-30 11:40:05.668670: +2025-10-30 11:40:05.670554: Epoch 484 +2025-10-30 11:40:05.672136: Current learning rate: 0.00551 +2025-10-30 11:40:27.515582: train_loss -0.9905 +2025-10-30 11:40:27.517973: val_loss -0.8779 +2025-10-30 11:40:27.519572: Pseudo dice [np.float32(0.9824), np.float32(0.9877), np.float32(0.9933), np.float32(0.7653)] +2025-10-30 11:40:27.521238: Epoch time: 21.85 s +2025-10-30 11:40:28.628652: +2025-10-30 11:40:28.630713: Epoch 485 +2025-10-30 11:40:28.632533: Current learning rate: 0.0055 +2025-10-30 11:40:51.379040: train_loss -0.9887 +2025-10-30 11:40:51.382119: val_loss -0.88 +2025-10-30 11:40:51.383943: Pseudo dice [np.float32(0.9834), np.float32(0.988), np.float32(0.9933), np.float32(0.7625)] +2025-10-30 11:40:51.385850: Epoch time: 22.75 s +2025-10-30 11:40:52.581873: +2025-10-30 11:40:52.583833: Epoch 486 +2025-10-30 11:40:52.585598: Current learning rate: 0.00549 +2025-10-30 11:41:15.207339: train_loss -0.9904 +2025-10-30 11:41:15.209693: val_loss -0.8825 +2025-10-30 11:41:15.211949: Pseudo dice [np.float32(0.9806), np.float32(0.9878), np.float32(0.9942), np.float32(0.7777)] +2025-10-30 11:41:15.214085: Epoch time: 22.63 s +2025-10-30 11:41:16.556998: +2025-10-30 11:41:16.558855: Epoch 487 +2025-10-30 11:41:16.560526: Current learning rate: 0.00548 +2025-10-30 11:41:38.260221: train_loss -0.9899 +2025-10-30 11:41:38.269172: val_loss -0.8871 +2025-10-30 11:41:38.273280: Pseudo dice [np.float32(0.9817), np.float32(0.9879), np.float32(0.9938), np.float32(0.7894)] +2025-10-30 11:41:38.274863: Epoch time: 21.71 s +2025-10-30 11:41:39.515884: +2025-10-30 11:41:39.517837: Epoch 488 +2025-10-30 11:41:39.519467: Current learning rate: 0.00547 +2025-10-30 11:42:01.464622: train_loss -0.9904 +2025-10-30 11:42:01.468919: val_loss -0.8866 +2025-10-30 11:42:01.470554: Pseudo dice [np.float32(0.9819), np.float32(0.9891), np.float32(0.9943), np.float32(0.7783)] +2025-10-30 11:42:01.472179: Epoch time: 21.95 s +2025-10-30 11:42:02.606366: +2025-10-30 11:42:02.608371: Epoch 489 +2025-10-30 11:42:02.609780: Current learning rate: 0.00546 +2025-10-30 11:42:24.626581: train_loss -0.9899 +2025-10-30 11:42:24.631305: val_loss -0.8788 +2025-10-30 11:42:24.632891: Pseudo dice [np.float32(0.9819), np.float32(0.9878), np.float32(0.9937), np.float32(0.7646)] +2025-10-30 11:42:24.634344: Epoch time: 22.02 s +2025-10-30 11:42:25.900537: +2025-10-30 11:42:25.902461: Epoch 490 +2025-10-30 11:42:25.904047: Current learning rate: 0.00546 +2025-10-30 11:42:47.659209: train_loss -0.9899 +2025-10-30 11:42:47.663087: val_loss -0.8883 +2025-10-30 11:42:47.664979: Pseudo dice [np.float32(0.9818), np.float32(0.9883), np.float32(0.9946), np.float32(0.7906)] +2025-10-30 11:42:47.666811: Epoch time: 21.76 s +2025-10-30 11:42:48.842344: +2025-10-30 11:42:48.844380: Epoch 491 +2025-10-30 11:42:48.846216: Current learning rate: 0.00545 +2025-10-30 11:43:11.381966: train_loss -0.9901 +2025-10-30 11:43:11.386809: val_loss -0.8903 +2025-10-30 11:43:11.388589: Pseudo dice [np.float32(0.9823), np.float32(0.9883), np.float32(0.9947), np.float32(0.7942)] +2025-10-30 11:43:11.390380: Epoch time: 22.54 s +2025-10-30 11:43:12.494257: +2025-10-30 11:43:12.496015: Epoch 492 +2025-10-30 11:43:12.500537: Current learning rate: 0.00544 +2025-10-30 11:43:35.188943: train_loss -0.9903 +2025-10-30 11:43:35.191596: val_loss -0.8743 +2025-10-30 11:43:35.193343: Pseudo dice [np.float32(0.9803), np.float32(0.9875), np.float32(0.9938), np.float32(0.7543)] +2025-10-30 11:43:35.195010: Epoch time: 22.7 s +2025-10-30 11:43:36.260555: +2025-10-30 11:43:36.262641: Epoch 493 +2025-10-30 11:43:36.264246: Current learning rate: 0.00543 +2025-10-30 11:43:58.649326: train_loss -0.9907 +2025-10-30 11:43:58.655173: val_loss -0.8725 +2025-10-30 11:43:58.657327: Pseudo dice [np.float32(0.9808), np.float32(0.9876), np.float32(0.9936), np.float32(0.7554)] +2025-10-30 11:43:58.658998: Epoch time: 22.39 s +2025-10-30 11:43:59.932546: +2025-10-30 11:43:59.934534: Epoch 494 +2025-10-30 11:43:59.936125: Current learning rate: 0.00542 +2025-10-30 11:44:21.672222: train_loss -0.9899 +2025-10-30 11:44:21.674850: val_loss -0.8795 +2025-10-30 11:44:21.676587: Pseudo dice [np.float32(0.982), np.float32(0.988), np.float32(0.9938), np.float32(0.7722)] +2025-10-30 11:44:21.677998: Epoch time: 21.74 s +2025-10-30 11:44:22.847786: +2025-10-30 11:44:22.849629: Epoch 495 +2025-10-30 11:44:22.851203: Current learning rate: 0.00541 +2025-10-30 11:44:45.663541: train_loss -0.9901 +2025-10-30 11:44:45.666027: val_loss -0.8786 +2025-10-30 11:44:45.667697: Pseudo dice [np.float32(0.9801), np.float32(0.9874), np.float32(0.9941), np.float32(0.7643)] +2025-10-30 11:44:45.669772: Epoch time: 22.82 s +2025-10-30 11:44:47.046277: +2025-10-30 11:44:47.048156: Epoch 496 +2025-10-30 11:44:47.049578: Current learning rate: 0.0054 +2025-10-30 11:45:08.532054: train_loss -0.9904 +2025-10-30 11:45:08.535315: val_loss -0.8739 +2025-10-30 11:45:08.537779: Pseudo dice [np.float32(0.9797), np.float32(0.987), np.float32(0.9937), np.float32(0.7588)] +2025-10-30 11:45:08.540088: Epoch time: 21.49 s +2025-10-30 11:45:09.812596: +2025-10-30 11:45:09.814936: Epoch 497 +2025-10-30 11:45:09.816555: Current learning rate: 0.00539 +2025-10-30 11:45:32.082242: train_loss -0.9906 +2025-10-30 11:45:32.085011: val_loss -0.8779 +2025-10-30 11:45:32.086584: Pseudo dice [np.float32(0.9812), np.float32(0.988), np.float32(0.994), np.float32(0.7649)] +2025-10-30 11:45:32.088073: Epoch time: 22.27 s +2025-10-30 11:45:33.400143: +2025-10-30 11:45:33.401983: Epoch 498 +2025-10-30 11:45:33.403657: Current learning rate: 0.00538 +2025-10-30 11:45:55.935518: train_loss -0.9908 +2025-10-30 11:45:55.937550: val_loss -0.8676 +2025-10-30 11:45:55.938957: Pseudo dice [np.float32(0.9806), np.float32(0.9807), np.float32(0.991), np.float32(0.7627)] +2025-10-30 11:45:55.940385: Epoch time: 22.54 s +2025-10-30 11:45:57.220286: +2025-10-30 11:45:57.223130: Epoch 499 +2025-10-30 11:45:57.225095: Current learning rate: 0.00537 +2025-10-30 11:46:19.754598: train_loss -0.9905 +2025-10-30 11:46:19.758419: val_loss -0.873 +2025-10-30 11:46:19.759905: Pseudo dice [np.float32(0.9801), np.float32(0.987), np.float32(0.9936), np.float32(0.7635)] +2025-10-30 11:46:19.761357: Epoch time: 22.54 s +2025-10-30 11:46:23.185771: +2025-10-30 11:46:23.187703: Epoch 500 +2025-10-30 11:46:23.189443: Current learning rate: 0.00536 +2025-10-30 11:46:45.459020: train_loss -0.9907 +2025-10-30 11:46:45.461823: val_loss -0.8908 +2025-10-30 11:46:45.463378: Pseudo dice [np.float32(0.9808), np.float32(0.9878), np.float32(0.9947), np.float32(0.7869)] +2025-10-30 11:46:45.464973: Epoch time: 22.27 s +2025-10-30 11:46:46.736687: +2025-10-30 11:46:46.738999: Epoch 501 +2025-10-30 11:46:46.740880: Current learning rate: 0.00535 +2025-10-30 11:47:08.806791: train_loss -0.9904 +2025-10-30 11:47:08.810036: val_loss -0.8799 +2025-10-30 11:47:08.811551: Pseudo dice [np.float32(0.9806), np.float32(0.9873), np.float32(0.994), np.float32(0.7649)] +2025-10-30 11:47:08.813009: Epoch time: 22.07 s +2025-10-30 11:47:10.056522: +2025-10-30 11:47:10.058535: Epoch 502 +2025-10-30 11:47:10.060314: Current learning rate: 0.00534 +2025-10-30 11:47:31.243852: train_loss -0.9905 +2025-10-30 11:47:31.246887: val_loss -0.876 +2025-10-30 11:47:31.248935: Pseudo dice [np.float32(0.9797), np.float32(0.9873), np.float32(0.9942), np.float32(0.7653)] +2025-10-30 11:47:31.250517: Epoch time: 21.19 s +2025-10-30 11:47:32.449157: +2025-10-30 11:47:32.451254: Epoch 503 +2025-10-30 11:47:32.453241: Current learning rate: 0.00533 +2025-10-30 11:47:55.012046: train_loss -0.99 +2025-10-30 11:47:55.016479: val_loss -0.8842 +2025-10-30 11:47:55.018858: Pseudo dice [np.float32(0.9829), np.float32(0.9893), np.float32(0.9941), np.float32(0.7758)] +2025-10-30 11:47:55.020854: Epoch time: 22.57 s +2025-10-30 11:47:56.201048: +2025-10-30 11:47:56.203049: Epoch 504 +2025-10-30 11:47:56.205075: Current learning rate: 0.00532 +2025-10-30 11:48:18.772333: train_loss -0.9897 +2025-10-30 11:48:18.775015: val_loss -0.8868 +2025-10-30 11:48:18.776553: Pseudo dice [np.float32(0.9818), np.float32(0.9887), np.float32(0.9943), np.float32(0.7775)] +2025-10-30 11:48:18.778188: Epoch time: 22.57 s +2025-10-30 11:48:19.889358: +2025-10-30 11:48:19.891356: Epoch 505 +2025-10-30 11:48:19.893202: Current learning rate: 0.00531 +2025-10-30 11:48:41.696698: train_loss -0.9908 +2025-10-30 11:48:41.699231: val_loss -0.8751 +2025-10-30 11:48:41.700735: Pseudo dice [np.float32(0.9794), np.float32(0.9877), np.float32(0.9941), np.float32(0.7563)] +2025-10-30 11:48:41.702286: Epoch time: 21.81 s +2025-10-30 11:48:42.877347: +2025-10-30 11:48:42.878997: Epoch 506 +2025-10-30 11:48:42.880541: Current learning rate: 0.0053 +2025-10-30 11:49:04.734624: train_loss -0.9904 +2025-10-30 11:49:04.741302: val_loss -0.8757 +2025-10-30 11:49:04.743435: Pseudo dice [np.float32(0.9819), np.float32(0.9881), np.float32(0.9936), np.float32(0.761)] +2025-10-30 11:49:04.745926: Epoch time: 21.86 s +2025-10-30 11:49:05.951313: +2025-10-30 11:49:05.953349: Epoch 507 +2025-10-30 11:49:05.954846: Current learning rate: 0.00529 +2025-10-30 11:49:28.315902: train_loss -0.9907 +2025-10-30 11:49:28.318387: val_loss -0.8825 +2025-10-30 11:49:28.321075: Pseudo dice [np.float32(0.9827), np.float32(0.9888), np.float32(0.9937), np.float32(0.7732)] +2025-10-30 11:49:28.322806: Epoch time: 22.37 s +2025-10-30 11:49:29.448623: +2025-10-30 11:49:29.450670: Epoch 508 +2025-10-30 11:49:29.452070: Current learning rate: 0.00528 +2025-10-30 11:49:50.794062: train_loss -0.9899 +2025-10-30 11:49:50.797645: val_loss -0.872 +2025-10-30 11:49:50.799505: Pseudo dice [np.float32(0.9819), np.float32(0.9884), np.float32(0.9935), np.float32(0.7513)] +2025-10-30 11:49:50.801001: Epoch time: 21.35 s +2025-10-30 11:49:52.315961: +2025-10-30 11:49:52.318240: Epoch 509 +2025-10-30 11:49:52.320056: Current learning rate: 0.00527 +2025-10-30 11:50:14.566472: train_loss -0.9902 +2025-10-30 11:50:14.572275: val_loss -0.8863 +2025-10-30 11:50:14.573832: Pseudo dice [np.float32(0.9815), np.float32(0.9886), np.float32(0.9945), np.float32(0.7777)] +2025-10-30 11:50:14.575266: Epoch time: 22.25 s +2025-10-30 11:50:15.810890: +2025-10-30 11:50:15.812912: Epoch 510 +2025-10-30 11:50:15.814621: Current learning rate: 0.00526 +2025-10-30 11:50:37.684919: train_loss -0.9903 +2025-10-30 11:50:37.687013: val_loss -0.8932 +2025-10-30 11:50:37.688611: Pseudo dice [np.float32(0.9808), np.float32(0.9882), np.float32(0.9952), np.float32(0.8018)] +2025-10-30 11:50:37.690655: Epoch time: 21.88 s +2025-10-30 11:50:38.895903: +2025-10-30 11:50:38.897666: Epoch 511 +2025-10-30 11:50:38.899260: Current learning rate: 0.00525 +2025-10-30 11:51:00.008367: train_loss -0.9906 +2025-10-30 11:51:00.011250: val_loss -0.8771 +2025-10-30 11:51:00.012887: Pseudo dice [np.float32(0.9793), np.float32(0.9878), np.float32(0.9944), np.float32(0.7725)] +2025-10-30 11:51:00.014444: Epoch time: 21.11 s +2025-10-30 11:51:01.259958: +2025-10-30 11:51:01.261834: Epoch 512 +2025-10-30 11:51:01.264261: Current learning rate: 0.00524 +2025-10-30 11:51:23.775965: train_loss -0.99 +2025-10-30 11:51:23.779477: val_loss -0.8858 +2025-10-30 11:51:23.781246: Pseudo dice [np.float32(0.9817), np.float32(0.9891), np.float32(0.9943), np.float32(0.7735)] +2025-10-30 11:51:23.783419: Epoch time: 22.52 s +2025-10-30 11:51:24.996998: +2025-10-30 11:51:24.999110: Epoch 513 +2025-10-30 11:51:25.000951: Current learning rate: 0.00523 +2025-10-30 11:51:47.709515: train_loss -0.99 +2025-10-30 11:51:47.715809: val_loss -0.8682 +2025-10-30 11:51:47.717626: Pseudo dice [np.float32(0.9798), np.float32(0.9875), np.float32(0.9933), np.float32(0.7467)] +2025-10-30 11:51:47.719356: Epoch time: 22.71 s +2025-10-30 11:51:48.966015: +2025-10-30 11:51:48.968274: Epoch 514 +2025-10-30 11:51:48.970531: Current learning rate: 0.00522 +2025-10-30 11:52:11.253150: train_loss -0.9893 +2025-10-30 11:52:11.255673: val_loss -0.8805 +2025-10-30 11:52:11.257288: Pseudo dice [np.float32(0.9827), np.float32(0.9892), np.float32(0.9936), np.float32(0.76)] +2025-10-30 11:52:11.258962: Epoch time: 22.29 s +2025-10-30 11:52:12.447346: +2025-10-30 11:52:12.449467: Epoch 515 +2025-10-30 11:52:12.451233: Current learning rate: 0.00521 +2025-10-30 11:52:33.413249: train_loss -0.9817 +2025-10-30 11:52:33.416473: val_loss -0.8804 +2025-10-30 11:52:33.418191: Pseudo dice [np.float32(0.9816), np.float32(0.9873), np.float32(0.993), np.float32(0.7453)] +2025-10-30 11:52:33.420331: Epoch time: 20.97 s +2025-10-30 11:52:34.665811: +2025-10-30 11:52:34.667519: Epoch 516 +2025-10-30 11:52:34.668974: Current learning rate: 0.0052 +2025-10-30 11:52:56.846324: train_loss -0.963 +2025-10-30 11:52:56.849261: val_loss -0.8879 +2025-10-30 11:52:56.850761: Pseudo dice [np.float32(0.9817), np.float32(0.9879), np.float32(0.9894), np.float32(0.7617)] +2025-10-30 11:52:56.852278: Epoch time: 22.18 s +2025-10-30 11:52:58.076483: +2025-10-30 11:52:58.078719: Epoch 517 +2025-10-30 11:52:58.080429: Current learning rate: 0.00519 +2025-10-30 11:53:19.685695: train_loss -0.9532 +2025-10-30 11:53:19.688922: val_loss -0.9017 +2025-10-30 11:53:19.690518: Pseudo dice [np.float32(0.9806), np.float32(0.9878), np.float32(0.9918), np.float32(0.801)] +2025-10-30 11:53:19.692895: Epoch time: 21.61 s +2025-10-30 11:53:22.461171: +2025-10-30 11:53:22.463250: Epoch 518 +2025-10-30 11:53:22.464957: Current learning rate: 0.00518 +2025-10-30 11:53:44.806564: train_loss -0.9626 +2025-10-30 11:53:44.809505: val_loss -0.8976 +2025-10-30 11:53:44.811366: Pseudo dice [np.float32(0.9822), np.float32(0.9879), np.float32(0.994), np.float32(0.7718)] +2025-10-30 11:53:44.812916: Epoch time: 22.35 s +2025-10-30 11:53:46.077946: +2025-10-30 11:53:46.079929: Epoch 519 +2025-10-30 11:53:46.081839: Current learning rate: 0.00518 +2025-10-30 11:54:08.599388: train_loss -0.974 +2025-10-30 11:54:08.601692: val_loss -0.8886 +2025-10-30 11:54:08.603197: Pseudo dice [np.float32(0.9817), np.float32(0.9871), np.float32(0.9929), np.float32(0.762)] +2025-10-30 11:54:08.604670: Epoch time: 22.52 s +2025-10-30 11:54:09.915012: +2025-10-30 11:54:09.916685: Epoch 520 +2025-10-30 11:54:09.918079: Current learning rate: 0.00517 +2025-10-30 11:54:31.932624: train_loss -0.9826 +2025-10-30 11:54:31.935005: val_loss -0.8904 +2025-10-30 11:54:31.936560: Pseudo dice [np.float32(0.98), np.float32(0.9869), np.float32(0.9945), np.float32(0.7829)] +2025-10-30 11:54:31.938123: Epoch time: 22.02 s +2025-10-30 11:54:33.223336: +2025-10-30 11:54:33.225629: Epoch 521 +2025-10-30 11:54:33.227905: Current learning rate: 0.00516 +2025-10-30 11:54:54.869171: train_loss -0.9844 +2025-10-30 11:54:54.872403: val_loss -0.8925 +2025-10-30 11:54:54.874844: Pseudo dice [np.float32(0.9801), np.float32(0.9881), np.float32(0.9945), np.float32(0.7833)] +2025-10-30 11:54:54.876609: Epoch time: 21.65 s +2025-10-30 11:54:56.176680: +2025-10-30 11:54:56.179066: Epoch 522 +2025-10-30 11:54:56.180765: Current learning rate: 0.00515 +2025-10-30 11:55:18.576816: train_loss -0.9866 +2025-10-30 11:55:18.579262: val_loss -0.8916 +2025-10-30 11:55:18.580999: Pseudo dice [np.float32(0.9826), np.float32(0.9882), np.float32(0.9942), np.float32(0.7797)] +2025-10-30 11:55:18.582697: Epoch time: 22.4 s +2025-10-30 11:55:19.890029: +2025-10-30 11:55:19.892170: Epoch 523 +2025-10-30 11:55:19.894269: Current learning rate: 0.00514 +2025-10-30 11:55:41.055386: train_loss -0.9857 +2025-10-30 11:55:41.059352: val_loss -0.8859 +2025-10-30 11:55:41.061032: Pseudo dice [np.float32(0.9819), np.float32(0.9885), np.float32(0.9944), np.float32(0.7649)] +2025-10-30 11:55:41.062778: Epoch time: 21.17 s +2025-10-30 11:55:42.398389: +2025-10-30 11:55:42.400804: Epoch 524 +2025-10-30 11:55:42.402710: Current learning rate: 0.00513 +2025-10-30 11:56:04.495152: train_loss -0.983 +2025-10-30 11:56:04.498405: val_loss -0.8714 +2025-10-30 11:56:04.500143: Pseudo dice [np.float32(0.9795), np.float32(0.9865), np.float32(0.9924), np.float32(0.7455)] +2025-10-30 11:56:04.502153: Epoch time: 22.1 s +2025-10-30 11:56:05.885207: +2025-10-30 11:56:05.887858: Epoch 525 +2025-10-30 11:56:05.889745: Current learning rate: 0.00512 +2025-10-30 11:56:28.326967: train_loss -0.9823 +2025-10-30 11:56:28.330528: val_loss -0.8813 +2025-10-30 11:56:28.333541: Pseudo dice [np.float32(0.9788), np.float32(0.9872), np.float32(0.9947), np.float32(0.7626)] +2025-10-30 11:56:28.335909: Epoch time: 22.44 s +2025-10-30 11:56:29.389086: +2025-10-30 11:56:29.391360: Epoch 526 +2025-10-30 11:56:29.393281: Current learning rate: 0.00511 +2025-10-30 11:56:51.665202: train_loss -0.9849 +2025-10-30 11:56:51.668006: val_loss -0.8924 +2025-10-30 11:56:51.669680: Pseudo dice [np.float32(0.9818), np.float32(0.9889), np.float32(0.9946), np.float32(0.778)] +2025-10-30 11:56:51.671211: Epoch time: 22.28 s +2025-10-30 11:56:52.843865: +2025-10-30 11:56:52.845633: Epoch 527 +2025-10-30 11:56:52.847098: Current learning rate: 0.0051 +2025-10-30 11:57:13.800107: train_loss -0.9872 +2025-10-30 11:57:13.803783: val_loss -0.8785 +2025-10-30 11:57:13.805953: Pseudo dice [np.float32(0.9801), np.float32(0.9874), np.float32(0.9947), np.float32(0.7639)] +2025-10-30 11:57:13.808132: Epoch time: 20.96 s +2025-10-30 11:57:14.880386: +2025-10-30 11:57:14.883241: Epoch 528 +2025-10-30 11:57:14.885105: Current learning rate: 0.00509 +2025-10-30 11:57:36.916292: train_loss -0.9878 +2025-10-30 11:57:36.918724: val_loss -0.8794 +2025-10-30 11:57:36.921049: Pseudo dice [np.float32(0.9808), np.float32(0.9871), np.float32(0.9939), np.float32(0.763)] +2025-10-30 11:57:36.922644: Epoch time: 22.04 s +2025-10-30 11:57:38.180288: +2025-10-30 11:57:38.181995: Epoch 529 +2025-10-30 11:57:38.183497: Current learning rate: 0.00508 +2025-10-30 11:57:59.156050: train_loss -0.9891 +2025-10-30 11:57:59.158404: val_loss -0.8849 +2025-10-30 11:57:59.160525: Pseudo dice [np.float32(0.9834), np.float32(0.9893), np.float32(0.9944), np.float32(0.7633)] +2025-10-30 11:57:59.162081: Epoch time: 20.98 s +2025-10-30 11:58:00.297706: +2025-10-30 11:58:00.299513: Epoch 530 +2025-10-30 11:58:00.301022: Current learning rate: 0.00507 +2025-10-30 11:58:22.098593: train_loss -0.9895 +2025-10-30 11:58:22.103799: val_loss -0.8855 +2025-10-30 11:58:22.105963: Pseudo dice [np.float32(0.9824), np.float32(0.9878), np.float32(0.9938), np.float32(0.7763)] +2025-10-30 11:58:22.107974: Epoch time: 21.8 s +2025-10-30 11:58:23.263476: +2025-10-30 11:58:23.265340: Epoch 531 +2025-10-30 11:58:23.266926: Current learning rate: 0.00506 +2025-10-30 11:58:45.411075: train_loss -0.9889 +2025-10-30 11:58:45.413931: val_loss -0.8858 +2025-10-30 11:58:45.415997: Pseudo dice [np.float32(0.9828), np.float32(0.9879), np.float32(0.9939), np.float32(0.7768)] +2025-10-30 11:58:45.417670: Epoch time: 22.15 s +2025-10-30 11:58:46.729044: +2025-10-30 11:58:46.731556: Epoch 532 +2025-10-30 11:58:46.734681: Current learning rate: 0.00505 +2025-10-30 11:59:08.404271: train_loss -0.9892 +2025-10-30 11:59:08.407171: val_loss -0.888 +2025-10-30 11:59:08.409184: Pseudo dice [np.float32(0.9828), np.float32(0.9881), np.float32(0.9945), np.float32(0.7776)] +2025-10-30 11:59:08.411051: Epoch time: 21.68 s +2025-10-30 11:59:09.511951: +2025-10-30 11:59:09.513587: Epoch 533 +2025-10-30 11:59:09.514976: Current learning rate: 0.00504 +2025-10-30 11:59:31.505195: train_loss -0.9885 +2025-10-30 11:59:31.508030: val_loss -0.8863 +2025-10-30 11:59:31.509466: Pseudo dice [np.float32(0.9802), np.float32(0.9875), np.float32(0.9944), np.float32(0.7802)] +2025-10-30 11:59:31.510909: Epoch time: 21.99 s +2025-10-30 11:59:32.696521: +2025-10-30 11:59:32.698391: Epoch 534 +2025-10-30 11:59:32.700032: Current learning rate: 0.00503 +2025-10-30 11:59:53.847116: train_loss -0.9831 +2025-10-30 11:59:53.849305: val_loss -0.8882 +2025-10-30 11:59:53.850969: Pseudo dice [np.float32(0.981), np.float32(0.9867), np.float32(0.9941), np.float32(0.7784)] +2025-10-30 11:59:53.852520: Epoch time: 21.15 s +2025-10-30 11:59:55.099582: +2025-10-30 11:59:55.101521: Epoch 535 +2025-10-30 11:59:55.103995: Current learning rate: 0.00502 +2025-10-30 12:00:16.247443: train_loss -0.9825 +2025-10-30 12:00:16.249619: val_loss -0.8794 +2025-10-30 12:00:16.251831: Pseudo dice [np.float32(0.9786), np.float32(0.9856), np.float32(0.9936), np.float32(0.7603)] +2025-10-30 12:00:16.253271: Epoch time: 21.15 s +2025-10-30 12:00:18.333803: +2025-10-30 12:00:18.335520: Epoch 536 +2025-10-30 12:00:18.337500: Current learning rate: 0.00501 +2025-10-30 12:00:39.989877: train_loss -0.9869 +2025-10-30 12:00:39.992672: val_loss -0.8813 +2025-10-30 12:00:39.994233: Pseudo dice [np.float32(0.9779), np.float32(0.9861), np.float32(0.9935), np.float32(0.7753)] +2025-10-30 12:00:39.995852: Epoch time: 21.66 s +2025-10-30 12:00:41.191749: +2025-10-30 12:00:41.193578: Epoch 537 +2025-10-30 12:00:41.195254: Current learning rate: 0.005 +2025-10-30 12:01:03.121031: train_loss -0.9886 +2025-10-30 12:01:03.123164: val_loss -0.8942 +2025-10-30 12:01:03.124838: Pseudo dice [np.float32(0.9807), np.float32(0.9877), np.float32(0.9947), np.float32(0.7965)] +2025-10-30 12:01:03.126404: Epoch time: 21.93 s +2025-10-30 12:01:04.362511: +2025-10-30 12:01:04.364531: Epoch 538 +2025-10-30 12:01:04.366246: Current learning rate: 0.00499 +2025-10-30 12:01:26.088993: train_loss -0.9889 +2025-10-30 12:01:26.091589: val_loss -0.8867 +2025-10-30 12:01:26.093194: Pseudo dice [np.float32(0.9819), np.float32(0.9885), np.float32(0.9945), np.float32(0.7761)] +2025-10-30 12:01:26.094799: Epoch time: 21.73 s +2025-10-30 12:01:27.224243: +2025-10-30 12:01:27.226132: Epoch 539 +2025-10-30 12:01:27.227894: Current learning rate: 0.00498 +2025-10-30 12:01:49.910197: train_loss -0.9889 +2025-10-30 12:01:49.913738: val_loss -0.8738 +2025-10-30 12:01:49.916035: Pseudo dice [np.float32(0.9803), np.float32(0.9868), np.float32(0.9933), np.float32(0.761)] +2025-10-30 12:01:49.918279: Epoch time: 22.69 s +2025-10-30 12:01:51.244937: +2025-10-30 12:01:51.246901: Epoch 540 +2025-10-30 12:01:51.248706: Current learning rate: 0.00497 +2025-10-30 12:02:11.971802: train_loss -0.9895 +2025-10-30 12:02:11.973878: val_loss -0.8858 +2025-10-30 12:02:11.975432: Pseudo dice [np.float32(0.9817), np.float32(0.9871), np.float32(0.9944), np.float32(0.7914)] +2025-10-30 12:02:11.976944: Epoch time: 20.73 s +2025-10-30 12:02:13.137698: +2025-10-30 12:02:13.139461: Epoch 541 +2025-10-30 12:02:13.140970: Current learning rate: 0.00496 +2025-10-30 12:02:34.218143: train_loss -0.9896 +2025-10-30 12:02:34.221833: val_loss -0.881 +2025-10-30 12:02:34.224145: Pseudo dice [np.float32(0.9809), np.float32(0.9876), np.float32(0.994), np.float32(0.7676)] +2025-10-30 12:02:34.226061: Epoch time: 21.08 s +2025-10-30 12:02:35.460862: +2025-10-30 12:02:35.462773: Epoch 542 +2025-10-30 12:02:35.465029: Current learning rate: 0.00495 +2025-10-30 12:02:57.667657: train_loss -0.9776 +2025-10-30 12:02:57.670079: val_loss -0.8844 +2025-10-30 12:02:57.671627: Pseudo dice [np.float32(0.9795), np.float32(0.986), np.float32(0.991), np.float32(0.7697)] +2025-10-30 12:02:57.673058: Epoch time: 22.21 s +2025-10-30 12:02:58.728933: +2025-10-30 12:02:58.730747: Epoch 543 +2025-10-30 12:02:58.732521: Current learning rate: 0.00494 +2025-10-30 12:03:20.521977: train_loss -0.9776 +2025-10-30 12:03:20.525993: val_loss -0.8891 +2025-10-30 12:03:20.527672: Pseudo dice [np.float32(0.9804), np.float32(0.9879), np.float32(0.9941), np.float32(0.7768)] +2025-10-30 12:03:20.529211: Epoch time: 21.79 s +2025-10-30 12:03:21.796807: +2025-10-30 12:03:21.798689: Epoch 544 +2025-10-30 12:03:21.800441: Current learning rate: 0.00493 +2025-10-30 12:03:44.241873: train_loss -0.9684 +2025-10-30 12:03:44.244609: val_loss -0.8992 +2025-10-30 12:03:44.246684: Pseudo dice [np.float32(0.9831), np.float32(0.9882), np.float32(0.9942), np.float32(0.7847)] +2025-10-30 12:03:44.248235: Epoch time: 22.45 s +2025-10-30 12:03:45.483930: +2025-10-30 12:03:45.490871: Epoch 545 +2025-10-30 12:03:45.492793: Current learning rate: 0.00492 +2025-10-30 12:04:07.158446: train_loss -0.9822 +2025-10-30 12:04:07.161250: val_loss -0.8875 +2025-10-30 12:04:07.162790: Pseudo dice [np.float32(0.9802), np.float32(0.9876), np.float32(0.9946), np.float32(0.7653)] +2025-10-30 12:04:07.164258: Epoch time: 21.68 s +2025-10-30 12:04:08.386551: +2025-10-30 12:04:08.388450: Epoch 546 +2025-10-30 12:04:08.390125: Current learning rate: 0.00491 +2025-10-30 12:04:30.231123: train_loss -0.9866 +2025-10-30 12:04:30.233545: val_loss -0.879 +2025-10-30 12:04:30.235059: Pseudo dice [np.float32(0.9796), np.float32(0.9865), np.float32(0.9935), np.float32(0.7521)] +2025-10-30 12:04:30.236479: Epoch time: 21.85 s +2025-10-30 12:04:31.275784: +2025-10-30 12:04:31.277692: Epoch 547 +2025-10-30 12:04:31.279227: Current learning rate: 0.0049 +2025-10-30 12:04:51.111948: train_loss -0.9851 +2025-10-30 12:04:51.114259: val_loss -0.882 +2025-10-30 12:04:51.116681: Pseudo dice [np.float32(0.9814), np.float32(0.988), np.float32(0.9938), np.float32(0.7535)] +2025-10-30 12:04:51.118317: Epoch time: 19.84 s +2025-10-30 12:04:52.151240: +2025-10-30 12:04:52.153077: Epoch 548 +2025-10-30 12:04:52.156146: Current learning rate: 0.00489 +2025-10-30 12:05:14.448960: train_loss -0.9872 +2025-10-30 12:05:14.451424: val_loss -0.8821 +2025-10-30 12:05:14.453076: Pseudo dice [np.float32(0.9809), np.float32(0.9881), np.float32(0.9944), np.float32(0.7633)] +2025-10-30 12:05:14.454674: Epoch time: 22.3 s +2025-10-30 12:05:15.469720: +2025-10-30 12:05:15.471808: Epoch 549 +2025-10-30 12:05:15.473488: Current learning rate: 0.00488 +2025-10-30 12:05:37.433496: train_loss -0.9883 +2025-10-30 12:05:37.435979: val_loss -0.8834 +2025-10-30 12:05:37.437678: Pseudo dice [np.float32(0.9801), np.float32(0.9875), np.float32(0.9946), np.float32(0.7751)] +2025-10-30 12:05:37.439151: Epoch time: 21.97 s +2025-10-30 12:05:39.841203: +2025-10-30 12:05:39.843191: Epoch 550 +2025-10-30 12:05:39.844916: Current learning rate: 0.00487 +2025-10-30 12:06:01.713436: train_loss -0.989 +2025-10-30 12:06:01.720080: val_loss -0.8854 +2025-10-30 12:06:01.723335: Pseudo dice [np.float32(0.9802), np.float32(0.9868), np.float32(0.9939), np.float32(0.78)] +2025-10-30 12:06:01.725117: Epoch time: 21.87 s +2025-10-30 12:06:02.782740: +2025-10-30 12:06:02.785096: Epoch 551 +2025-10-30 12:06:02.786736: Current learning rate: 0.00486 +2025-10-30 12:06:24.880002: train_loss -0.9887 +2025-10-30 12:06:24.882528: val_loss -0.8826 +2025-10-30 12:06:24.884046: Pseudo dice [np.float32(0.983), np.float32(0.9884), np.float32(0.9941), np.float32(0.7668)] +2025-10-30 12:06:24.885523: Epoch time: 22.1 s +2025-10-30 12:06:26.171278: +2025-10-30 12:06:26.173081: Epoch 552 +2025-10-30 12:06:26.174620: Current learning rate: 0.00485 +2025-10-30 12:06:48.204121: train_loss -0.9893 +2025-10-30 12:06:48.206983: val_loss -0.8851 +2025-10-30 12:06:48.209230: Pseudo dice [np.float32(0.9784), np.float32(0.9873), np.float32(0.9946), np.float32(0.7958)] +2025-10-30 12:06:48.211064: Epoch time: 22.03 s +2025-10-30 12:06:50.333402: +2025-10-30 12:06:50.336105: Epoch 553 +2025-10-30 12:06:50.338040: Current learning rate: 0.00484 +2025-10-30 12:07:10.626927: train_loss -0.989 +2025-10-30 12:07:10.629770: val_loss -0.8845 +2025-10-30 12:07:10.632054: Pseudo dice [np.float32(0.9793), np.float32(0.9875), np.float32(0.9941), np.float32(0.7739)] +2025-10-30 12:07:10.634151: Epoch time: 20.3 s +2025-10-30 12:07:11.752829: +2025-10-30 12:07:11.754939: Epoch 554 +2025-10-30 12:07:11.756776: Current learning rate: 0.00484 +2025-10-30 12:07:33.769186: train_loss -0.9888 +2025-10-30 12:07:33.773701: val_loss -0.8806 +2025-10-30 12:07:33.775444: Pseudo dice [np.float32(0.9817), np.float32(0.9879), np.float32(0.994), np.float32(0.7658)] +2025-10-30 12:07:33.777103: Epoch time: 22.02 s +2025-10-30 12:07:35.007075: +2025-10-30 12:07:35.009585: Epoch 555 +2025-10-30 12:07:35.011896: Current learning rate: 0.00483 +2025-10-30 12:07:57.204765: train_loss -0.9894 +2025-10-30 12:07:57.207241: val_loss -0.8708 +2025-10-30 12:07:57.208924: Pseudo dice [np.float32(0.9805), np.float32(0.9879), np.float32(0.9941), np.float32(0.7426)] +2025-10-30 12:07:57.210508: Epoch time: 22.2 s +2025-10-30 12:07:58.254335: +2025-10-30 12:07:58.257671: Epoch 556 +2025-10-30 12:07:58.261091: Current learning rate: 0.00482 +2025-10-30 12:08:19.713625: train_loss -0.99 +2025-10-30 12:08:19.717526: val_loss -0.8786 +2025-10-30 12:08:19.719425: Pseudo dice [np.float32(0.9798), np.float32(0.988), np.float32(0.9943), np.float32(0.7685)] +2025-10-30 12:08:19.721539: Epoch time: 21.46 s +2025-10-30 12:08:20.955097: +2025-10-30 12:08:20.957441: Epoch 557 +2025-10-30 12:08:20.959266: Current learning rate: 0.00481 +2025-10-30 12:08:42.996153: train_loss -0.9903 +2025-10-30 12:08:43.001804: val_loss -0.8848 +2025-10-30 12:08:43.003460: Pseudo dice [np.float32(0.9802), np.float32(0.9882), np.float32(0.9944), np.float32(0.7856)] +2025-10-30 12:08:43.004818: Epoch time: 22.04 s +2025-10-30 12:08:44.059877: +2025-10-30 12:08:44.061626: Epoch 558 +2025-10-30 12:08:44.063016: Current learning rate: 0.0048 +2025-10-30 12:09:06.027270: train_loss -0.9897 +2025-10-30 12:09:06.029582: val_loss -0.8807 +2025-10-30 12:09:06.031724: Pseudo dice [np.float32(0.9802), np.float32(0.9866), np.float32(0.9943), np.float32(0.7687)] +2025-10-30 12:09:06.033957: Epoch time: 21.97 s +2025-10-30 12:09:07.019115: +2025-10-30 12:09:07.021103: Epoch 559 +2025-10-30 12:09:07.022663: Current learning rate: 0.00479 +2025-10-30 12:09:28.160125: train_loss -0.99 +2025-10-30 12:09:28.164014: val_loss -0.8792 +2025-10-30 12:09:28.167223: Pseudo dice [np.float32(0.9801), np.float32(0.9881), np.float32(0.9942), np.float32(0.7583)] +2025-10-30 12:09:28.170554: Epoch time: 21.14 s +2025-10-30 12:09:29.278413: +2025-10-30 12:09:29.281206: Epoch 560 +2025-10-30 12:09:29.282762: Current learning rate: 0.00478 +2025-10-30 12:09:50.083643: train_loss -0.9902 +2025-10-30 12:09:50.086118: val_loss -0.8778 +2025-10-30 12:09:50.087879: Pseudo dice [np.float32(0.9807), np.float32(0.988), np.float32(0.9944), np.float32(0.765)] +2025-10-30 12:09:50.089401: Epoch time: 20.81 s +2025-10-30 12:09:51.313429: +2025-10-30 12:09:51.315829: Epoch 561 +2025-10-30 12:09:51.317889: Current learning rate: 0.00477 +2025-10-30 12:10:13.728602: train_loss -0.9903 +2025-10-30 12:10:13.731695: val_loss -0.8796 +2025-10-30 12:10:13.733591: Pseudo dice [np.float32(0.9824), np.float32(0.989), np.float32(0.9943), np.float32(0.7655)] +2025-10-30 12:10:13.735269: Epoch time: 22.42 s +2025-10-30 12:10:14.773937: +2025-10-30 12:10:14.775856: Epoch 562 +2025-10-30 12:10:14.777573: Current learning rate: 0.00476 +2025-10-30 12:10:36.834607: train_loss -0.9904 +2025-10-30 12:10:36.838041: val_loss -0.8888 +2025-10-30 12:10:36.839617: Pseudo dice [np.float32(0.9818), np.float32(0.9891), np.float32(0.9947), np.float32(0.7849)] +2025-10-30 12:10:36.841237: Epoch time: 22.06 s +2025-10-30 12:10:37.924389: +2025-10-30 12:10:37.926376: Epoch 563 +2025-10-30 12:10:37.928086: Current learning rate: 0.00475 +2025-10-30 12:10:59.651334: train_loss -0.9906 +2025-10-30 12:10:59.658298: val_loss -0.8766 +2025-10-30 12:10:59.660703: Pseudo dice [np.float32(0.9817), np.float32(0.9888), np.float32(0.9941), np.float32(0.7556)] +2025-10-30 12:10:59.663038: Epoch time: 21.73 s +2025-10-30 12:11:00.990325: +2025-10-30 12:11:00.992193: Epoch 564 +2025-10-30 12:11:00.993782: Current learning rate: 0.00474 +2025-10-30 12:11:22.813968: train_loss -0.9905 +2025-10-30 12:11:22.816011: val_loss -0.883 +2025-10-30 12:11:22.818043: Pseudo dice [np.float32(0.9805), np.float32(0.9885), np.float32(0.9941), np.float32(0.7727)] +2025-10-30 12:11:22.819857: Epoch time: 21.83 s +2025-10-30 12:11:23.948136: +2025-10-30 12:11:23.950025: Epoch 565 +2025-10-30 12:11:23.951622: Current learning rate: 0.00473 +2025-10-30 12:11:45.710156: train_loss -0.99 +2025-10-30 12:11:45.712098: val_loss -0.8742 +2025-10-30 12:11:45.713548: Pseudo dice [np.float32(0.9798), np.float32(0.9879), np.float32(0.994), np.float32(0.7566)] +2025-10-30 12:11:45.714902: Epoch time: 21.76 s +2025-10-30 12:11:46.721361: +2025-10-30 12:11:46.723171: Epoch 566 +2025-10-30 12:11:46.724746: Current learning rate: 0.00472 +2025-10-30 12:12:07.525671: train_loss -0.9902 +2025-10-30 12:12:07.528706: val_loss -0.8876 +2025-10-30 12:12:07.530352: Pseudo dice [np.float32(0.9819), np.float32(0.9887), np.float32(0.9945), np.float32(0.7837)] +2025-10-30 12:12:07.532065: Epoch time: 20.81 s +2025-10-30 12:12:08.849080: +2025-10-30 12:12:08.850989: Epoch 567 +2025-10-30 12:12:08.852598: Current learning rate: 0.00471 +2025-10-30 12:12:30.789398: train_loss -0.9903 +2025-10-30 12:12:30.791543: val_loss -0.8818 +2025-10-30 12:12:30.793011: Pseudo dice [np.float32(0.98), np.float32(0.9878), np.float32(0.9943), np.float32(0.7748)] +2025-10-30 12:12:30.794528: Epoch time: 21.94 s +2025-10-30 12:12:32.037162: +2025-10-30 12:12:32.039336: Epoch 568 +2025-10-30 12:12:32.041044: Current learning rate: 0.0047 +2025-10-30 12:12:53.864752: train_loss -0.9908 +2025-10-30 12:12:53.866948: val_loss -0.8819 +2025-10-30 12:12:53.869040: Pseudo dice [np.float32(0.9827), np.float32(0.9892), np.float32(0.9943), np.float32(0.76)] +2025-10-30 12:12:53.871261: Epoch time: 21.83 s +2025-10-30 12:12:54.935352: +2025-10-30 12:12:54.937164: Epoch 569 +2025-10-30 12:12:54.938856: Current learning rate: 0.00469 +2025-10-30 12:13:16.436309: train_loss -0.9911 +2025-10-30 12:13:16.442822: val_loss -0.8833 +2025-10-30 12:13:16.445429: Pseudo dice [np.float32(0.9799), np.float32(0.9877), np.float32(0.9941), np.float32(0.7803)] +2025-10-30 12:13:16.447885: Epoch time: 21.5 s +2025-10-30 12:13:17.671240: +2025-10-30 12:13:17.673607: Epoch 570 +2025-10-30 12:13:17.675561: Current learning rate: 0.00468 +2025-10-30 12:13:40.076986: train_loss -0.9915 +2025-10-30 12:13:40.079326: val_loss -0.8848 +2025-10-30 12:13:40.080905: Pseudo dice [np.float32(0.9818), np.float32(0.9884), np.float32(0.9945), np.float32(0.7753)] +2025-10-30 12:13:40.082419: Epoch time: 22.41 s +2025-10-30 12:13:42.188902: +2025-10-30 12:13:42.190887: Epoch 571 +2025-10-30 12:13:42.192683: Current learning rate: 0.00467 +2025-10-30 12:14:04.483273: train_loss -0.9913 +2025-10-30 12:14:04.486367: val_loss -0.8845 +2025-10-30 12:14:04.488794: Pseudo dice [np.float32(0.9799), np.float32(0.9883), np.float32(0.9941), np.float32(0.7759)] +2025-10-30 12:14:04.490562: Epoch time: 22.3 s +2025-10-30 12:14:05.987299: +2025-10-30 12:14:05.989230: Epoch 572 +2025-10-30 12:14:05.990914: Current learning rate: 0.00466 +2025-10-30 12:14:26.859354: train_loss -0.9908 +2025-10-30 12:14:26.865757: val_loss -0.8795 +2025-10-30 12:14:26.867858: Pseudo dice [np.float32(0.9832), np.float32(0.989), np.float32(0.9941), np.float32(0.765)] +2025-10-30 12:14:26.869412: Epoch time: 20.87 s +2025-10-30 12:14:27.923312: +2025-10-30 12:14:27.926001: Epoch 573 +2025-10-30 12:14:27.928447: Current learning rate: 0.00465 +2025-10-30 12:14:49.183574: train_loss -0.9891 +2025-10-30 12:14:49.188324: val_loss -0.8827 +2025-10-30 12:14:49.191292: Pseudo dice [np.float32(0.982), np.float32(0.9889), np.float32(0.9937), np.float32(0.7649)] +2025-10-30 12:14:49.194440: Epoch time: 21.26 s +2025-10-30 12:14:50.484030: +2025-10-30 12:14:50.485977: Epoch 574 +2025-10-30 12:14:50.487591: Current learning rate: 0.00464 +2025-10-30 12:15:11.562189: train_loss -0.9903 +2025-10-30 12:15:11.565407: val_loss -0.8777 +2025-10-30 12:15:11.567140: Pseudo dice [np.float32(0.9825), np.float32(0.9884), np.float32(0.9939), np.float32(0.7659)] +2025-10-30 12:15:11.568887: Epoch time: 21.08 s +2025-10-30 12:15:12.630414: +2025-10-30 12:15:12.632825: Epoch 575 +2025-10-30 12:15:12.634654: Current learning rate: 0.00463 +2025-10-30 12:15:34.745240: train_loss -0.9904 +2025-10-30 12:15:34.747596: val_loss -0.8824 +2025-10-30 12:15:34.755188: Pseudo dice [np.float32(0.9824), np.float32(0.9891), np.float32(0.994), np.float32(0.7694)] +2025-10-30 12:15:34.757455: Epoch time: 22.12 s +2025-10-30 12:15:35.998597: +2025-10-30 12:15:36.000844: Epoch 576 +2025-10-30 12:15:36.002972: Current learning rate: 0.00462 +2025-10-30 12:15:58.137683: train_loss -0.9902 +2025-10-30 12:15:58.140209: val_loss -0.885 +2025-10-30 12:15:58.142103: Pseudo dice [np.float32(0.9804), np.float32(0.9881), np.float32(0.9942), np.float32(0.7825)] +2025-10-30 12:15:58.144195: Epoch time: 22.14 s +2025-10-30 12:15:59.306015: +2025-10-30 12:15:59.308282: Epoch 577 +2025-10-30 12:15:59.310524: Current learning rate: 0.00461 +2025-10-30 12:16:21.520615: train_loss -0.9909 +2025-10-30 12:16:21.522780: val_loss -0.8824 +2025-10-30 12:16:21.524324: Pseudo dice [np.float32(0.9811), np.float32(0.9881), np.float32(0.9945), np.float32(0.7755)] +2025-10-30 12:16:21.525672: Epoch time: 22.22 s +2025-10-30 12:16:22.834022: +2025-10-30 12:16:22.835688: Epoch 578 +2025-10-30 12:16:22.837103: Current learning rate: 0.0046 +2025-10-30 12:16:43.978710: train_loss -0.9911 +2025-10-30 12:16:43.981376: val_loss -0.8771 +2025-10-30 12:16:43.982980: Pseudo dice [np.float32(0.9818), np.float32(0.9886), np.float32(0.9941), np.float32(0.7596)] +2025-10-30 12:16:43.984629: Epoch time: 21.15 s +2025-10-30 12:16:45.262107: +2025-10-30 12:16:45.264213: Epoch 579 +2025-10-30 12:16:45.266058: Current learning rate: 0.00459 +2025-10-30 12:17:06.733423: train_loss -0.9904 +2025-10-30 12:17:06.735800: val_loss -0.8779 +2025-10-30 12:17:06.737319: Pseudo dice [np.float32(0.9823), np.float32(0.9887), np.float32(0.994), np.float32(0.7552)] +2025-10-30 12:17:06.739083: Epoch time: 21.47 s +2025-10-30 12:17:07.936662: +2025-10-30 12:17:07.938704: Epoch 580 +2025-10-30 12:17:07.940390: Current learning rate: 0.00458 +2025-10-30 12:17:30.381056: train_loss -0.9912 +2025-10-30 12:17:30.384818: val_loss -0.8844 +2025-10-30 12:17:30.386689: Pseudo dice [np.float32(0.9821), np.float32(0.9884), np.float32(0.9941), np.float32(0.7735)] +2025-10-30 12:17:30.388644: Epoch time: 22.45 s +2025-10-30 12:17:31.777783: +2025-10-30 12:17:31.779923: Epoch 581 +2025-10-30 12:17:31.781635: Current learning rate: 0.00457 +2025-10-30 12:17:54.095234: train_loss -0.9923 +2025-10-30 12:17:54.099333: val_loss -0.8784 +2025-10-30 12:17:54.101352: Pseudo dice [np.float32(0.9807), np.float32(0.9885), np.float32(0.994), np.float32(0.7608)] +2025-10-30 12:17:54.103633: Epoch time: 22.32 s +2025-10-30 12:17:55.273682: +2025-10-30 12:17:55.275716: Epoch 582 +2025-10-30 12:17:55.278258: Current learning rate: 0.00456 +2025-10-30 12:18:17.446889: train_loss -0.9916 +2025-10-30 12:18:17.449162: val_loss -0.8777 +2025-10-30 12:18:17.450974: Pseudo dice [np.float32(0.9812), np.float32(0.9888), np.float32(0.9939), np.float32(0.7602)] +2025-10-30 12:18:17.452441: Epoch time: 22.18 s +2025-10-30 12:18:18.724977: +2025-10-30 12:18:18.727378: Epoch 583 +2025-10-30 12:18:18.729572: Current learning rate: 0.00455 +2025-10-30 12:18:40.611735: train_loss -0.9904 +2025-10-30 12:18:40.614434: val_loss -0.8783 +2025-10-30 12:18:40.616267: Pseudo dice [np.float32(0.9813), np.float32(0.989), np.float32(0.9941), np.float32(0.7676)] +2025-10-30 12:18:40.617893: Epoch time: 21.89 s +2025-10-30 12:18:41.774453: +2025-10-30 12:18:41.776268: Epoch 584 +2025-10-30 12:18:41.777913: Current learning rate: 0.00454 +2025-10-30 12:19:02.490160: train_loss -0.988 +2025-10-30 12:19:02.493568: val_loss -0.8883 +2025-10-30 12:19:02.495403: Pseudo dice [np.float32(0.9799), np.float32(0.9887), np.float32(0.9949), np.float32(0.7833)] +2025-10-30 12:19:02.497015: Epoch time: 20.72 s +2025-10-30 12:19:03.533883: +2025-10-30 12:19:03.537979: Epoch 585 +2025-10-30 12:19:03.539610: Current learning rate: 0.00453 +2025-10-30 12:19:24.819139: train_loss -0.9898 +2025-10-30 12:19:24.821261: val_loss -0.8839 +2025-10-30 12:19:24.822978: Pseudo dice [np.float32(0.9825), np.float32(0.9894), np.float32(0.9941), np.float32(0.7622)] +2025-10-30 12:19:24.824928: Epoch time: 21.29 s +2025-10-30 12:19:25.912734: +2025-10-30 12:19:25.914656: Epoch 586 +2025-10-30 12:19:25.916610: Current learning rate: 0.00452 +2025-10-30 12:19:47.583107: train_loss -0.9887 +2025-10-30 12:19:47.586009: val_loss -0.8919 +2025-10-30 12:19:47.590797: Pseudo dice [np.float32(0.9814), np.float32(0.9885), np.float32(0.9932), np.float32(0.7969)] +2025-10-30 12:19:47.595801: Epoch time: 21.67 s +2025-10-30 12:19:48.665836: +2025-10-30 12:19:48.667654: Epoch 587 +2025-10-30 12:19:48.669537: Current learning rate: 0.00451 +2025-10-30 12:20:10.180182: train_loss -0.9862 +2025-10-30 12:20:10.183001: val_loss -0.8877 +2025-10-30 12:20:10.184561: Pseudo dice [np.float32(0.9832), np.float32(0.9903), np.float32(0.9945), np.float32(0.7717)] +2025-10-30 12:20:10.186144: Epoch time: 21.52 s +2025-10-30 12:20:11.238894: +2025-10-30 12:20:11.240845: Epoch 588 +2025-10-30 12:20:11.242532: Current learning rate: 0.0045 +2025-10-30 12:20:33.869017: train_loss -0.9875 +2025-10-30 12:20:33.881968: val_loss -0.8885 +2025-10-30 12:20:33.883850: Pseudo dice [np.float32(0.9798), np.float32(0.9884), np.float32(0.9943), np.float32(0.7783)] +2025-10-30 12:20:33.885540: Epoch time: 22.63 s +2025-10-30 12:20:35.066592: +2025-10-30 12:20:35.069268: Epoch 589 +2025-10-30 12:20:35.071466: Current learning rate: 0.00449 +2025-10-30 12:20:56.744947: train_loss -0.9879 +2025-10-30 12:20:56.747369: val_loss -0.8828 +2025-10-30 12:20:56.749009: Pseudo dice [np.float32(0.9803), np.float32(0.988), np.float32(0.9938), np.float32(0.7677)] +2025-10-30 12:20:56.750880: Epoch time: 21.68 s +2025-10-30 12:20:57.933676: +2025-10-30 12:20:57.935580: Epoch 590 +2025-10-30 12:20:57.937227: Current learning rate: 0.00448 +2025-10-30 12:21:18.645033: train_loss -0.9899 +2025-10-30 12:21:18.647774: val_loss -0.8808 +2025-10-30 12:21:18.649621: Pseudo dice [np.float32(0.9812), np.float32(0.9873), np.float32(0.9938), np.float32(0.7723)] +2025-10-30 12:21:18.651384: Epoch time: 20.71 s +2025-10-30 12:21:19.954034: +2025-10-30 12:21:19.955981: Epoch 591 +2025-10-30 12:21:19.957798: Current learning rate: 0.00447 +2025-10-30 12:21:41.830313: train_loss -0.9898 +2025-10-30 12:21:41.832470: val_loss -0.8933 +2025-10-30 12:21:41.834146: Pseudo dice [np.float32(0.983), np.float32(0.9891), np.float32(0.9948), np.float32(0.7904)] +2025-10-30 12:21:41.835668: Epoch time: 21.88 s +2025-10-30 12:21:43.066123: +2025-10-30 12:21:43.067652: Epoch 592 +2025-10-30 12:21:43.069175: Current learning rate: 0.00446 +2025-10-30 12:22:04.137666: train_loss -0.9898 +2025-10-30 12:22:04.143844: val_loss -0.8821 +2025-10-30 12:22:04.145593: Pseudo dice [np.float32(0.9819), np.float32(0.9885), np.float32(0.9943), np.float32(0.7779)] +2025-10-30 12:22:04.147357: Epoch time: 21.07 s +2025-10-30 12:22:05.387765: +2025-10-30 12:22:05.389844: Epoch 593 +2025-10-30 12:22:05.391648: Current learning rate: 0.00445 +2025-10-30 12:22:26.708711: train_loss -0.9896 +2025-10-30 12:22:26.711939: val_loss -0.8909 +2025-10-30 12:22:26.713766: Pseudo dice [np.float32(0.9819), np.float32(0.9882), np.float32(0.9944), np.float32(0.7931)] +2025-10-30 12:22:26.715467: Epoch time: 21.32 s +2025-10-30 12:22:27.817961: +2025-10-30 12:22:27.819962: Epoch 594 +2025-10-30 12:22:27.822047: Current learning rate: 0.00444 +2025-10-30 12:22:49.407099: train_loss -0.9907 +2025-10-30 12:22:49.409548: val_loss -0.8889 +2025-10-30 12:22:49.411371: Pseudo dice [np.float32(0.9807), np.float32(0.9877), np.float32(0.9943), np.float32(0.791)] +2025-10-30 12:22:49.413380: Epoch time: 21.59 s +2025-10-30 12:22:50.615983: +2025-10-30 12:22:50.617986: Epoch 595 +2025-10-30 12:22:50.619950: Current learning rate: 0.00443 +2025-10-30 12:23:12.197135: train_loss -0.9905 +2025-10-30 12:23:12.201522: val_loss -0.8852 +2025-10-30 12:23:12.203596: Pseudo dice [np.float32(0.9816), np.float32(0.9897), np.float32(0.9942), np.float32(0.774)] +2025-10-30 12:23:12.205502: Epoch time: 21.58 s +2025-10-30 12:23:13.340189: +2025-10-30 12:23:13.342034: Epoch 596 +2025-10-30 12:23:13.343805: Current learning rate: 0.00442 +2025-10-30 12:23:33.442239: train_loss -0.9909 +2025-10-30 12:23:33.448100: val_loss -0.8878 +2025-10-30 12:23:33.450095: Pseudo dice [np.float32(0.9804), np.float32(0.9883), np.float32(0.995), np.float32(0.7829)] +2025-10-30 12:23:33.451666: Epoch time: 20.1 s +2025-10-30 12:23:34.520600: +2025-10-30 12:23:34.528428: Epoch 597 +2025-10-30 12:23:34.533830: Current learning rate: 0.00441 +2025-10-30 12:23:56.461039: train_loss -0.9908 +2025-10-30 12:23:56.463602: val_loss -0.8947 +2025-10-30 12:23:56.465439: Pseudo dice [np.float32(0.9829), np.float32(0.9893), np.float32(0.9945), np.float32(0.79)] +2025-10-30 12:23:56.467196: Epoch time: 21.94 s +2025-10-30 12:23:57.683121: +2025-10-30 12:23:57.687049: Epoch 598 +2025-10-30 12:23:57.688647: Current learning rate: 0.0044 +2025-10-30 12:24:18.385053: train_loss -0.9914 +2025-10-30 12:24:18.387623: val_loss -0.8714 +2025-10-30 12:24:18.389235: Pseudo dice [np.float32(0.9799), np.float32(0.9889), np.float32(0.9943), np.float32(0.7481)] +2025-10-30 12:24:18.391052: Epoch time: 20.7 s +2025-10-30 12:24:19.595680: +2025-10-30 12:24:19.597725: Epoch 599 +2025-10-30 12:24:19.599838: Current learning rate: 0.00439 +2025-10-30 12:24:41.347288: train_loss -0.9907 +2025-10-30 12:24:41.350348: val_loss -0.8875 +2025-10-30 12:24:41.351852: Pseudo dice [np.float32(0.9802), np.float32(0.9883), np.float32(0.9947), np.float32(0.784)] +2025-10-30 12:24:41.353430: Epoch time: 21.75 s +2025-10-30 12:24:43.861761: +2025-10-30 12:24:43.864030: Epoch 600 +2025-10-30 12:24:43.866368: Current learning rate: 0.00438 +2025-10-30 12:25:05.314492: train_loss -0.991 +2025-10-30 12:25:05.318272: val_loss -0.8838 +2025-10-30 12:25:05.319825: Pseudo dice [np.float32(0.9801), np.float32(0.9883), np.float32(0.9948), np.float32(0.782)] +2025-10-30 12:25:05.321671: Epoch time: 21.45 s +2025-10-30 12:25:06.448203: +2025-10-30 12:25:06.450607: Epoch 601 +2025-10-30 12:25:06.452342: Current learning rate: 0.00437 +2025-10-30 12:25:28.406353: train_loss -0.9915 +2025-10-30 12:25:28.409086: val_loss -0.8854 +2025-10-30 12:25:28.411068: Pseudo dice [np.float32(0.9818), np.float32(0.9888), np.float32(0.9946), np.float32(0.7835)] +2025-10-30 12:25:28.413089: Epoch time: 21.96 s +2025-10-30 12:25:29.458546: +2025-10-30 12:25:29.460687: Epoch 602 +2025-10-30 12:25:29.462288: Current learning rate: 0.00436 +2025-10-30 12:25:50.297952: train_loss -0.9905 +2025-10-30 12:25:50.301944: val_loss -0.8753 +2025-10-30 12:25:50.305082: Pseudo dice [np.float32(0.9822), np.float32(0.9889), np.float32(0.9943), np.float32(0.7541)] +2025-10-30 12:25:50.306834: Epoch time: 20.84 s +2025-10-30 12:25:51.723010: +2025-10-30 12:25:51.724905: Epoch 603 +2025-10-30 12:25:51.726597: Current learning rate: 0.00435 +2025-10-30 12:26:13.364772: train_loss -0.9903 +2025-10-30 12:26:13.367261: val_loss -0.8784 +2025-10-30 12:26:13.368912: Pseudo dice [np.float32(0.981), np.float32(0.9876), np.float32(0.9941), np.float32(0.7591)] +2025-10-30 12:26:13.370495: Epoch time: 21.64 s +2025-10-30 12:26:14.500967: +2025-10-30 12:26:14.503042: Epoch 604 +2025-10-30 12:26:14.504794: Current learning rate: 0.00434 +2025-10-30 12:26:36.316189: train_loss -0.9906 +2025-10-30 12:26:36.318290: val_loss -0.8857 +2025-10-30 12:26:36.319876: Pseudo dice [np.float32(0.9833), np.float32(0.9892), np.float32(0.9941), np.float32(0.7769)] +2025-10-30 12:26:36.321506: Epoch time: 21.82 s +2025-10-30 12:26:37.367800: +2025-10-30 12:26:37.370083: Epoch 605 +2025-10-30 12:26:37.372626: Current learning rate: 0.00433 +2025-10-30 12:26:57.838809: train_loss -0.9907 +2025-10-30 12:26:57.841599: val_loss -0.88 +2025-10-30 12:26:57.843201: Pseudo dice [np.float32(0.9807), np.float32(0.9894), np.float32(0.994), np.float32(0.762)] +2025-10-30 12:26:57.844931: Epoch time: 20.47 s +2025-10-30 12:26:59.716631: +2025-10-30 12:26:59.718768: Epoch 606 +2025-10-30 12:26:59.720405: Current learning rate: 0.00432 +2025-10-30 12:27:21.464677: train_loss -0.9913 +2025-10-30 12:27:21.467497: val_loss -0.879 +2025-10-30 12:27:21.469214: Pseudo dice [np.float32(0.9809), np.float32(0.9886), np.float32(0.9941), np.float32(0.7706)] +2025-10-30 12:27:21.470808: Epoch time: 21.75 s +2025-10-30 12:27:22.705717: +2025-10-30 12:27:22.708368: Epoch 607 +2025-10-30 12:27:22.710086: Current learning rate: 0.00431 +2025-10-30 12:27:44.973958: train_loss -0.9909 +2025-10-30 12:27:44.976671: val_loss -0.8807 +2025-10-30 12:27:44.980197: Pseudo dice [np.float32(0.9809), np.float32(0.9887), np.float32(0.9941), np.float32(0.7613)] +2025-10-30 12:27:44.981910: Epoch time: 22.27 s +2025-10-30 12:27:46.282060: +2025-10-30 12:27:46.284469: Epoch 608 +2025-10-30 12:27:46.286138: Current learning rate: 0.0043 +2025-10-30 12:28:07.227411: train_loss -0.9909 +2025-10-30 12:28:07.230385: val_loss -0.8835 +2025-10-30 12:28:07.232162: Pseudo dice [np.float32(0.9802), np.float32(0.9873), np.float32(0.9942), np.float32(0.7786)] +2025-10-30 12:28:07.233842: Epoch time: 20.95 s +2025-10-30 12:28:08.306567: +2025-10-30 12:28:08.308710: Epoch 609 +2025-10-30 12:28:08.312028: Current learning rate: 0.00429 +2025-10-30 12:28:30.144903: train_loss -0.9921 +2025-10-30 12:28:30.147522: val_loss -0.8784 +2025-10-30 12:28:30.149515: Pseudo dice [np.float32(0.98), np.float32(0.9868), np.float32(0.994), np.float32(0.7681)] +2025-10-30 12:28:30.151117: Epoch time: 21.84 s +2025-10-30 12:28:31.330575: +2025-10-30 12:28:31.332591: Epoch 610 +2025-10-30 12:28:31.334325: Current learning rate: 0.00429 +2025-10-30 12:28:52.965859: train_loss -0.9912 +2025-10-30 12:28:52.969098: val_loss -0.878 +2025-10-30 12:28:52.970885: Pseudo dice [np.float32(0.9805), np.float32(0.9887), np.float32(0.9943), np.float32(0.7723)] +2025-10-30 12:28:52.972462: Epoch time: 21.64 s +2025-10-30 12:28:54.011782: +2025-10-30 12:28:54.013984: Epoch 611 +2025-10-30 12:28:54.016161: Current learning rate: 0.00428 +2025-10-30 12:29:14.515661: train_loss -0.9916 +2025-10-30 12:29:14.519083: val_loss -0.8733 +2025-10-30 12:29:14.521838: Pseudo dice [np.float32(0.9796), np.float32(0.9868), np.float32(0.994), np.float32(0.768)] +2025-10-30 12:29:14.523711: Epoch time: 20.51 s +2025-10-30 12:29:15.756886: +2025-10-30 12:29:15.759463: Epoch 612 +2025-10-30 12:29:15.761650: Current learning rate: 0.00427 +2025-10-30 12:29:36.981323: train_loss -0.9911 +2025-10-30 12:29:36.983736: val_loss -0.8823 +2025-10-30 12:29:36.985549: Pseudo dice [np.float32(0.9809), np.float32(0.9885), np.float32(0.9942), np.float32(0.7714)] +2025-10-30 12:29:36.987250: Epoch time: 21.23 s +2025-10-30 12:29:38.108039: +2025-10-30 12:29:38.110756: Epoch 613 +2025-10-30 12:29:38.113152: Current learning rate: 0.00426 +2025-10-30 12:29:59.842713: train_loss -0.992 +2025-10-30 12:29:59.847204: val_loss -0.8816 +2025-10-30 12:29:59.850546: Pseudo dice [np.float32(0.9815), np.float32(0.988), np.float32(0.994), np.float32(0.7808)] +2025-10-30 12:29:59.852065: Epoch time: 21.74 s +2025-10-30 12:30:01.102520: +2025-10-30 12:30:01.105159: Epoch 614 +2025-10-30 12:30:01.106821: Current learning rate: 0.00425 +2025-10-30 12:30:21.981454: train_loss -0.9916 +2025-10-30 12:30:21.984313: val_loss -0.8828 +2025-10-30 12:30:21.986026: Pseudo dice [np.float32(0.9803), np.float32(0.9872), np.float32(0.9941), np.float32(0.7879)] +2025-10-30 12:30:21.987557: Epoch time: 20.88 s +2025-10-30 12:30:23.038991: +2025-10-30 12:30:23.040670: Epoch 615 +2025-10-30 12:30:23.042871: Current learning rate: 0.00424 +2025-10-30 12:30:44.965655: train_loss -0.9916 +2025-10-30 12:30:44.968276: val_loss -0.8733 +2025-10-30 12:30:44.970257: Pseudo dice [np.float32(0.9801), np.float32(0.9859), np.float32(0.9932), np.float32(0.7615)] +2025-10-30 12:30:44.972057: Epoch time: 21.93 s +2025-10-30 12:30:46.314870: +2025-10-30 12:30:46.317006: Epoch 616 +2025-10-30 12:30:46.318765: Current learning rate: 0.00423 +2025-10-30 12:31:07.772251: train_loss -0.9915 +2025-10-30 12:31:07.776822: val_loss -0.8866 +2025-10-30 12:31:07.778555: Pseudo dice [np.float32(0.9807), np.float32(0.9878), np.float32(0.9942), np.float32(0.7796)] +2025-10-30 12:31:07.780138: Epoch time: 21.46 s +2025-10-30 12:31:08.917626: +2025-10-30 12:31:08.919424: Epoch 617 +2025-10-30 12:31:08.921268: Current learning rate: 0.00422 +2025-10-30 12:31:30.644713: train_loss -0.9899 +2025-10-30 12:31:30.648899: val_loss -0.874 +2025-10-30 12:31:30.651242: Pseudo dice [np.float32(0.9812), np.float32(0.9885), np.float32(0.994), np.float32(0.7603)] +2025-10-30 12:31:30.652999: Epoch time: 21.73 s +2025-10-30 12:31:31.719122: +2025-10-30 12:31:31.721593: Epoch 618 +2025-10-30 12:31:31.723222: Current learning rate: 0.00421 +2025-10-30 12:31:52.841470: train_loss -0.9913 +2025-10-30 12:31:52.844507: val_loss -0.876 +2025-10-30 12:31:52.846456: Pseudo dice [np.float32(0.9829), np.float32(0.9886), np.float32(0.9941), np.float32(0.7573)] +2025-10-30 12:31:52.849602: Epoch time: 21.12 s +2025-10-30 12:31:53.881646: +2025-10-30 12:31:53.883884: Epoch 619 +2025-10-30 12:31:53.886344: Current learning rate: 0.0042 +2025-10-30 12:32:15.536070: train_loss -0.9914 +2025-10-30 12:32:15.541298: val_loss -0.8853 +2025-10-30 12:32:15.543190: Pseudo dice [np.float32(0.9831), np.float32(0.9886), np.float32(0.9942), np.float32(0.7772)] +2025-10-30 12:32:15.545393: Epoch time: 21.66 s +2025-10-30 12:32:16.662724: +2025-10-30 12:32:16.666230: Epoch 620 +2025-10-30 12:32:16.669178: Current learning rate: 0.00419 +2025-10-30 12:32:38.020646: train_loss -0.9917 +2025-10-30 12:32:38.057782: val_loss -0.8777 +2025-10-30 12:32:38.075229: Pseudo dice [np.float32(0.9829), np.float32(0.9886), np.float32(0.9936), np.float32(0.7603)] +2025-10-30 12:32:38.091997: Epoch time: 21.36 s +2025-10-30 12:32:39.419661: +2025-10-30 12:32:39.421507: Epoch 621 +2025-10-30 12:32:39.424278: Current learning rate: 0.00418 +2025-10-30 12:33:00.842537: train_loss -0.9909 +2025-10-30 12:33:00.845401: val_loss -0.887 +2025-10-30 12:33:00.847070: Pseudo dice [np.float32(0.9822), np.float32(0.9885), np.float32(0.9943), np.float32(0.7836)] +2025-10-30 12:33:00.848748: Epoch time: 21.42 s +2025-10-30 12:33:02.561825: +2025-10-30 12:33:02.563644: Epoch 622 +2025-10-30 12:33:02.565334: Current learning rate: 0.00417 +2025-10-30 12:33:24.294675: train_loss -0.9923 +2025-10-30 12:33:24.297129: val_loss -0.8814 +2025-10-30 12:33:24.299186: Pseudo dice [np.float32(0.9814), np.float32(0.9879), np.float32(0.9941), np.float32(0.7774)] +2025-10-30 12:33:24.302257: Epoch time: 21.73 s +2025-10-30 12:33:25.337963: +2025-10-30 12:33:25.339926: Epoch 623 +2025-10-30 12:33:25.341697: Current learning rate: 0.00416 +2025-10-30 12:33:47.223191: train_loss -0.9923 +2025-10-30 12:33:47.227868: val_loss -0.8839 +2025-10-30 12:33:47.229572: Pseudo dice [np.float32(0.9811), np.float32(0.9882), np.float32(0.9942), np.float32(0.7829)] +2025-10-30 12:33:47.231194: Epoch time: 21.89 s +2025-10-30 12:33:48.538153: +2025-10-30 12:33:48.541379: Epoch 624 +2025-10-30 12:33:48.543236: Current learning rate: 0.00415 +2025-10-30 12:34:09.307721: train_loss -0.9919 +2025-10-30 12:34:09.312223: val_loss -0.8845 +2025-10-30 12:34:09.315187: Pseudo dice [np.float32(0.9826), np.float32(0.9888), np.float32(0.9942), np.float32(0.7844)] +2025-10-30 12:34:09.319208: Epoch time: 20.77 s +2025-10-30 12:34:10.588619: +2025-10-30 12:34:10.591591: Epoch 625 +2025-10-30 12:34:10.594221: Current learning rate: 0.00414 +2025-10-30 12:34:32.424143: train_loss -0.9925 +2025-10-30 12:34:32.427243: val_loss -0.8833 +2025-10-30 12:34:32.429192: Pseudo dice [np.float32(0.9803), np.float32(0.988), np.float32(0.9943), np.float32(0.7718)] +2025-10-30 12:34:32.430804: Epoch time: 21.84 s +2025-10-30 12:34:33.470020: +2025-10-30 12:34:33.472062: Epoch 626 +2025-10-30 12:34:33.473560: Current learning rate: 0.00413 +2025-10-30 12:34:54.958675: train_loss -0.9917 +2025-10-30 12:34:54.961202: val_loss -0.8884 +2025-10-30 12:34:54.964203: Pseudo dice [np.float32(0.9812), np.float32(0.988), np.float32(0.9945), np.float32(0.7933)] +2025-10-30 12:34:54.965839: Epoch time: 21.49 s +2025-10-30 12:34:56.003623: +2025-10-30 12:34:56.006006: Epoch 627 +2025-10-30 12:34:56.008097: Current learning rate: 0.00412 +2025-10-30 12:35:16.511262: train_loss -0.9913 +2025-10-30 12:35:16.514173: val_loss -0.8826 +2025-10-30 12:35:16.516532: Pseudo dice [np.float32(0.9826), np.float32(0.988), np.float32(0.9938), np.float32(0.7754)] +2025-10-30 12:35:16.518116: Epoch time: 20.51 s +2025-10-30 12:35:17.907794: +2025-10-30 12:35:17.909462: Epoch 628 +2025-10-30 12:35:17.911353: Current learning rate: 0.00411 +2025-10-30 12:35:39.667864: train_loss -0.9915 +2025-10-30 12:35:39.672947: val_loss -0.8881 +2025-10-30 12:35:39.674713: Pseudo dice [np.float32(0.9817), np.float32(0.9883), np.float32(0.9945), np.float32(0.7854)] +2025-10-30 12:35:39.676286: Epoch time: 21.76 s +2025-10-30 12:35:40.989699: +2025-10-30 12:35:40.993432: Epoch 629 +2025-10-30 12:35:40.997323: Current learning rate: 0.0041 +2025-10-30 12:36:02.622096: train_loss -0.9913 +2025-10-30 12:36:02.624888: val_loss -0.8859 +2025-10-30 12:36:02.627009: Pseudo dice [np.float32(0.9814), np.float32(0.9884), np.float32(0.9947), np.float32(0.7811)] +2025-10-30 12:36:02.628667: Epoch time: 21.63 s +2025-10-30 12:36:03.885956: +2025-10-30 12:36:03.889582: Epoch 630 +2025-10-30 12:36:03.892682: Current learning rate: 0.00409 +2025-10-30 12:36:25.814295: train_loss -0.9916 +2025-10-30 12:36:25.818523: val_loss -0.8883 +2025-10-30 12:36:25.820996: Pseudo dice [np.float32(0.982), np.float32(0.9879), np.float32(0.9945), np.float32(0.7798)] +2025-10-30 12:36:25.823540: Epoch time: 21.93 s +2025-10-30 12:36:26.874702: +2025-10-30 12:36:26.876871: Epoch 631 +2025-10-30 12:36:26.880487: Current learning rate: 0.00408 +2025-10-30 12:36:46.392018: train_loss -0.9916 +2025-10-30 12:36:46.394926: val_loss -0.8828 +2025-10-30 12:36:46.396537: Pseudo dice [np.float32(0.9801), np.float32(0.9879), np.float32(0.9943), np.float32(0.7772)] +2025-10-30 12:36:46.401523: Epoch time: 19.52 s +2025-10-30 12:36:47.449328: +2025-10-30 12:36:47.451735: Epoch 632 +2025-10-30 12:36:47.453473: Current learning rate: 0.00407 +2025-10-30 12:37:09.051759: train_loss -0.992 +2025-10-30 12:37:09.056209: val_loss -0.8812 +2025-10-30 12:37:09.058272: Pseudo dice [np.float32(0.9813), np.float32(0.9883), np.float32(0.9938), np.float32(0.7647)] +2025-10-30 12:37:09.060018: Epoch time: 21.6 s +2025-10-30 12:37:10.343856: +2025-10-30 12:37:10.345908: Epoch 633 +2025-10-30 12:37:10.347624: Current learning rate: 0.00406 +2025-10-30 12:37:31.021381: train_loss -0.9918 +2025-10-30 12:37:31.028977: val_loss -0.8809 +2025-10-30 12:37:31.030747: Pseudo dice [np.float32(0.9796), np.float32(0.9884), np.float32(0.9942), np.float32(0.7798)] +2025-10-30 12:37:31.032702: Epoch time: 20.68 s +2025-10-30 12:37:32.260034: +2025-10-30 12:37:32.261993: Epoch 634 +2025-10-30 12:37:32.263919: Current learning rate: 0.00405 +2025-10-30 12:37:53.933407: train_loss -0.9918 +2025-10-30 12:37:53.939648: val_loss -0.8748 +2025-10-30 12:37:53.941695: Pseudo dice [np.float32(0.9801), np.float32(0.9868), np.float32(0.9937), np.float32(0.7712)] +2025-10-30 12:37:53.943703: Epoch time: 21.68 s +2025-10-30 12:37:55.114254: +2025-10-30 12:37:55.115880: Epoch 635 +2025-10-30 12:37:55.117582: Current learning rate: 0.00404 +2025-10-30 12:38:17.491655: train_loss -0.992 +2025-10-30 12:38:17.494840: val_loss -0.8788 +2025-10-30 12:38:17.496896: Pseudo dice [np.float32(0.9816), np.float32(0.9871), np.float32(0.9939), np.float32(0.7799)] +2025-10-30 12:38:17.498924: Epoch time: 22.38 s +2025-10-30 12:38:18.732659: +2025-10-30 12:38:18.734722: Epoch 636 +2025-10-30 12:38:18.737243: Current learning rate: 0.00403 +2025-10-30 12:38:40.873703: train_loss -0.9922 +2025-10-30 12:38:40.876161: val_loss -0.885 +2025-10-30 12:38:40.877899: Pseudo dice [np.float32(0.9819), np.float32(0.9885), np.float32(0.9941), np.float32(0.7788)] +2025-10-30 12:38:40.879604: Epoch time: 22.14 s +2025-10-30 12:38:42.199120: +2025-10-30 12:38:42.201228: Epoch 637 +2025-10-30 12:38:42.202866: Current learning rate: 0.00402 +2025-10-30 12:39:03.455227: train_loss -0.9921 +2025-10-30 12:39:03.457981: val_loss -0.8829 +2025-10-30 12:39:03.459609: Pseudo dice [np.float32(0.981), np.float32(0.9881), np.float32(0.9943), np.float32(0.7824)] +2025-10-30 12:39:03.461497: Epoch time: 21.26 s +2025-10-30 12:39:04.686348: +2025-10-30 12:39:04.688292: Epoch 638 +2025-10-30 12:39:04.689874: Current learning rate: 0.00401 +2025-10-30 12:39:26.710490: train_loss -0.9924 +2025-10-30 12:39:26.713138: val_loss -0.8839 +2025-10-30 12:39:26.715255: Pseudo dice [np.float32(0.9809), np.float32(0.9884), np.float32(0.9945), np.float32(0.7748)] +2025-10-30 12:39:26.717132: Epoch time: 22.03 s +2025-10-30 12:39:27.764429: +2025-10-30 12:39:27.767899: Epoch 639 +2025-10-30 12:39:27.770189: Current learning rate: 0.004 +2025-10-30 12:39:48.652788: train_loss -0.9918 +2025-10-30 12:39:48.655942: val_loss -0.8734 +2025-10-30 12:39:48.657624: Pseudo dice [np.float32(0.9812), np.float32(0.9879), np.float32(0.9938), np.float32(0.7597)] +2025-10-30 12:39:48.659192: Epoch time: 20.89 s +2025-10-30 12:39:50.612106: +2025-10-30 12:39:50.613873: Epoch 640 +2025-10-30 12:39:50.615342: Current learning rate: 0.00399 +2025-10-30 12:40:12.447746: train_loss -0.9922 +2025-10-30 12:40:12.453681: val_loss -0.8833 +2025-10-30 12:40:12.455336: Pseudo dice [np.float32(0.9806), np.float32(0.989), np.float32(0.994), np.float32(0.7796)] +2025-10-30 12:40:12.457114: Epoch time: 21.84 s +2025-10-30 12:40:13.553341: +2025-10-30 12:40:13.556145: Epoch 641 +2025-10-30 12:40:13.559228: Current learning rate: 0.00398 +2025-10-30 12:40:35.750204: train_loss -0.9916 +2025-10-30 12:40:35.752689: val_loss -0.8849 +2025-10-30 12:40:35.755307: Pseudo dice [np.float32(0.9801), np.float32(0.9888), np.float32(0.9944), np.float32(0.7886)] +2025-10-30 12:40:35.757712: Epoch time: 22.2 s +2025-10-30 12:40:37.033787: +2025-10-30 12:40:37.036074: Epoch 642 +2025-10-30 12:40:37.038006: Current learning rate: 0.00397 +2025-10-30 12:40:59.310441: train_loss -0.9914 +2025-10-30 12:40:59.315146: val_loss -0.879 +2025-10-30 12:40:59.318162: Pseudo dice [np.float32(0.9807), np.float32(0.9886), np.float32(0.9941), np.float32(0.7591)] +2025-10-30 12:40:59.320575: Epoch time: 22.28 s +2025-10-30 12:41:00.511412: +2025-10-30 12:41:00.513870: Epoch 643 +2025-10-30 12:41:00.515852: Current learning rate: 0.00396 +2025-10-30 12:41:22.704021: train_loss -0.9914 +2025-10-30 12:41:22.707362: val_loss -0.8837 +2025-10-30 12:41:22.709169: Pseudo dice [np.float32(0.9821), np.float32(0.989), np.float32(0.9943), np.float32(0.7706)] +2025-10-30 12:41:22.710804: Epoch time: 22.19 s +2025-10-30 12:41:23.837240: +2025-10-30 12:41:23.839757: Epoch 644 +2025-10-30 12:41:23.841984: Current learning rate: 0.00395 +2025-10-30 12:41:45.605899: train_loss -0.9924 +2025-10-30 12:41:45.610423: val_loss -0.8873 +2025-10-30 12:41:45.614183: Pseudo dice [np.float32(0.9816), np.float32(0.9896), np.float32(0.9946), np.float32(0.7824)] +2025-10-30 12:41:45.617162: Epoch time: 21.77 s +2025-10-30 12:41:46.916897: +2025-10-30 12:41:46.918910: Epoch 645 +2025-10-30 12:41:46.920982: Current learning rate: 0.00394 +2025-10-30 12:42:08.218689: train_loss -0.9917 +2025-10-30 12:42:08.221544: val_loss -0.8867 +2025-10-30 12:42:08.223368: Pseudo dice [np.float32(0.981), np.float32(0.9883), np.float32(0.9944), np.float32(0.7867)] +2025-10-30 12:42:08.225113: Epoch time: 21.3 s +2025-10-30 12:42:09.580755: +2025-10-30 12:42:09.583051: Epoch 646 +2025-10-30 12:42:09.584901: Current learning rate: 0.00393 +2025-10-30 12:42:31.064220: train_loss -0.9914 +2025-10-30 12:42:31.066983: val_loss -0.88 +2025-10-30 12:42:31.069481: Pseudo dice [np.float32(0.9815), np.float32(0.9895), np.float32(0.9942), np.float32(0.7643)] +2025-10-30 12:42:31.071569: Epoch time: 21.49 s +2025-10-30 12:42:32.209867: +2025-10-30 12:42:32.212313: Epoch 647 +2025-10-30 12:42:32.213875: Current learning rate: 0.00392 +2025-10-30 12:42:54.114706: train_loss -0.9925 +2025-10-30 12:42:54.117667: val_loss -0.8846 +2025-10-30 12:42:54.119417: Pseudo dice [np.float32(0.9819), np.float32(0.9888), np.float32(0.9942), np.float32(0.7795)] +2025-10-30 12:42:54.121009: Epoch time: 21.91 s +2025-10-30 12:42:55.328928: +2025-10-30 12:42:55.332309: Epoch 648 +2025-10-30 12:42:55.334641: Current learning rate: 0.00391 +2025-10-30 12:43:17.261094: train_loss -0.9919 +2025-10-30 12:43:17.264435: val_loss -0.9016 +2025-10-30 12:43:17.266602: Pseudo dice [np.float32(0.9822), np.float32(0.9886), np.float32(0.9945), np.float32(0.8064)] +2025-10-30 12:43:17.269149: Epoch time: 21.93 s +2025-10-30 12:43:18.320142: +2025-10-30 12:43:18.321782: Epoch 649 +2025-10-30 12:43:18.323519: Current learning rate: 0.0039 +2025-10-30 12:43:40.195602: train_loss -0.9922 +2025-10-30 12:43:40.197797: val_loss -0.8771 +2025-10-30 12:43:40.199755: Pseudo dice [np.float32(0.9792), np.float32(0.9882), np.float32(0.994), np.float32(0.7679)] +2025-10-30 12:43:40.203682: Epoch time: 21.88 s +2025-10-30 12:43:42.628820: +2025-10-30 12:43:42.630553: Epoch 650 +2025-10-30 12:43:42.632153: Current learning rate: 0.00389 +2025-10-30 12:44:03.282911: train_loss -0.9918 +2025-10-30 12:44:03.287101: val_loss -0.8735 +2025-10-30 12:44:03.289104: Pseudo dice [np.float32(0.9821), np.float32(0.989), np.float32(0.9938), np.float32(0.7531)] +2025-10-30 12:44:03.292410: Epoch time: 20.66 s +2025-10-30 12:44:04.413805: +2025-10-30 12:44:04.415697: Epoch 651 +2025-10-30 12:44:04.418000: Current learning rate: 0.00388 +2025-10-30 12:44:25.473671: train_loss -0.9918 +2025-10-30 12:44:25.476629: val_loss -0.8834 +2025-10-30 12:44:25.478775: Pseudo dice [np.float32(0.9806), np.float32(0.9887), np.float32(0.9943), np.float32(0.7732)] +2025-10-30 12:44:25.480448: Epoch time: 21.06 s +2025-10-30 12:44:26.727255: +2025-10-30 12:44:26.730586: Epoch 652 +2025-10-30 12:44:26.733341: Current learning rate: 0.00387 +2025-10-30 12:44:48.424012: train_loss -0.9916 +2025-10-30 12:44:48.427136: val_loss -0.8717 +2025-10-30 12:44:48.428831: Pseudo dice [np.float32(0.9812), np.float32(0.9888), np.float32(0.9939), np.float32(0.7446)] +2025-10-30 12:44:48.430580: Epoch time: 21.7 s +2025-10-30 12:44:49.685639: +2025-10-30 12:44:49.687939: Epoch 653 +2025-10-30 12:44:49.692239: Current learning rate: 0.00386 +2025-10-30 12:45:11.670619: train_loss -0.9915 +2025-10-30 12:45:11.674097: val_loss -0.8835 +2025-10-30 12:45:11.675802: Pseudo dice [np.float32(0.9806), np.float32(0.988), np.float32(0.9944), np.float32(0.7797)] +2025-10-30 12:45:11.677325: Epoch time: 21.99 s +2025-10-30 12:45:12.945187: +2025-10-30 12:45:12.948068: Epoch 654 +2025-10-30 12:45:12.951200: Current learning rate: 0.00385 +2025-10-30 12:45:34.426856: train_loss -0.9926 +2025-10-30 12:45:34.429513: val_loss -0.8673 +2025-10-30 12:45:34.431174: Pseudo dice [np.float32(0.9795), np.float32(0.9872), np.float32(0.9935), np.float32(0.7456)] +2025-10-30 12:45:34.432872: Epoch time: 21.48 s +2025-10-30 12:45:35.728885: +2025-10-30 12:45:35.731842: Epoch 655 +2025-10-30 12:45:35.733714: Current learning rate: 0.00384 +2025-10-30 12:45:57.367378: train_loss -0.9921 +2025-10-30 12:45:57.369857: val_loss -0.8868 +2025-10-30 12:45:57.371335: Pseudo dice [np.float32(0.9814), np.float32(0.9886), np.float32(0.9943), np.float32(0.7833)] +2025-10-30 12:45:57.375081: Epoch time: 21.64 s +2025-10-30 12:45:58.651598: +2025-10-30 12:45:58.654018: Epoch 656 +2025-10-30 12:45:58.667604: Current learning rate: 0.00383 +2025-10-30 12:46:21.446108: train_loss -0.9917 +2025-10-30 12:46:21.449632: val_loss -0.8902 +2025-10-30 12:46:21.452624: Pseudo dice [np.float32(0.9829), np.float32(0.9892), np.float32(0.9945), np.float32(0.7849)] +2025-10-30 12:46:21.455321: Epoch time: 22.8 s +2025-10-30 12:46:22.768048: +2025-10-30 12:46:22.770372: Epoch 657 +2025-10-30 12:46:22.772269: Current learning rate: 0.00382 +2025-10-30 12:46:42.873217: train_loss -0.9919 +2025-10-30 12:46:42.875798: val_loss -0.8776 +2025-10-30 12:46:42.877545: Pseudo dice [np.float32(0.9815), np.float32(0.9881), np.float32(0.9941), np.float32(0.7665)] +2025-10-30 12:46:42.879454: Epoch time: 20.11 s +2025-10-30 12:46:44.115712: +2025-10-30 12:46:44.118261: Epoch 658 +2025-10-30 12:46:44.120832: Current learning rate: 0.00381 +2025-10-30 12:47:05.895194: train_loss -0.9924 +2025-10-30 12:47:05.897783: val_loss -0.8874 +2025-10-30 12:47:05.899541: Pseudo dice [np.float32(0.9797), np.float32(0.9876), np.float32(0.9945), np.float32(0.7896)] +2025-10-30 12:47:05.901508: Epoch time: 21.78 s +2025-10-30 12:47:07.109578: +2025-10-30 12:47:07.111420: Epoch 659 +2025-10-30 12:47:07.113531: Current learning rate: 0.0038 +2025-10-30 12:47:28.911447: train_loss -0.9915 +2025-10-30 12:47:28.918544: val_loss -0.886 +2025-10-30 12:47:28.921217: Pseudo dice [np.float32(0.9796), np.float32(0.9877), np.float32(0.994), np.float32(0.7943)] +2025-10-30 12:47:28.923754: Epoch time: 21.8 s +2025-10-30 12:47:30.143969: +2025-10-30 12:47:30.146646: Epoch 660 +2025-10-30 12:47:30.148691: Current learning rate: 0.00379 +2025-10-30 12:47:51.929887: train_loss -0.9918 +2025-10-30 12:47:51.936105: val_loss -0.886 +2025-10-30 12:47:51.938054: Pseudo dice [np.float32(0.9827), np.float32(0.9891), np.float32(0.9943), np.float32(0.7738)] +2025-10-30 12:47:51.940068: Epoch time: 21.79 s +2025-10-30 12:47:53.218448: +2025-10-30 12:47:53.220818: Epoch 661 +2025-10-30 12:47:53.222453: Current learning rate: 0.00378 +2025-10-30 12:48:14.924531: train_loss -0.992 +2025-10-30 12:48:14.941352: val_loss -0.8868 +2025-10-30 12:48:14.943220: Pseudo dice [np.float32(0.9815), np.float32(0.9889), np.float32(0.9945), np.float32(0.7863)] +2025-10-30 12:48:14.945108: Epoch time: 21.71 s +2025-10-30 12:48:16.071277: +2025-10-30 12:48:16.073260: Epoch 662 +2025-10-30 12:48:16.075216: Current learning rate: 0.00377 +2025-10-30 12:48:37.232389: train_loss -0.9916 +2025-10-30 12:48:37.236297: val_loss -0.8774 +2025-10-30 12:48:37.238075: Pseudo dice [np.float32(0.9807), np.float32(0.9868), np.float32(0.9937), np.float32(0.7653)] +2025-10-30 12:48:37.239980: Epoch time: 21.16 s +2025-10-30 12:48:38.494483: +2025-10-30 12:48:38.496389: Epoch 663 +2025-10-30 12:48:38.497962: Current learning rate: 0.00376 +2025-10-30 12:48:57.840476: train_loss -0.9915 +2025-10-30 12:48:57.843276: val_loss -0.889 +2025-10-30 12:48:57.845738: Pseudo dice [np.float32(0.981), np.float32(0.9886), np.float32(0.9948), np.float32(0.7851)] +2025-10-30 12:48:57.847814: Epoch time: 19.35 s +2025-10-30 12:48:59.091504: +2025-10-30 12:48:59.095253: Epoch 664 +2025-10-30 12:48:59.098021: Current learning rate: 0.00375 +2025-10-30 12:49:20.555247: train_loss -0.9913 +2025-10-30 12:49:20.561182: val_loss -0.8896 +2025-10-30 12:49:20.563432: Pseudo dice [np.float32(0.9812), np.float32(0.9885), np.float32(0.9944), np.float32(0.7856)] +2025-10-30 12:49:20.565584: Epoch time: 21.47 s +2025-10-30 12:49:21.685271: +2025-10-30 12:49:21.687521: Epoch 665 +2025-10-30 12:49:21.690487: Current learning rate: 0.00374 +2025-10-30 12:49:42.993500: train_loss -0.992 +2025-10-30 12:49:42.996739: val_loss -0.8821 +2025-10-30 12:49:42.999119: Pseudo dice [np.float32(0.982), np.float32(0.9885), np.float32(0.9944), np.float32(0.7676)] +2025-10-30 12:49:43.000893: Epoch time: 21.31 s +2025-10-30 12:49:44.178838: +2025-10-30 12:49:44.181797: Epoch 666 +2025-10-30 12:49:44.184139: Current learning rate: 0.00373 +2025-10-30 12:50:05.722832: train_loss -0.992 +2025-10-30 12:50:05.725575: val_loss -0.8853 +2025-10-30 12:50:05.727404: Pseudo dice [np.float32(0.9828), np.float32(0.9887), np.float32(0.9944), np.float32(0.7774)] +2025-10-30 12:50:05.728903: Epoch time: 21.55 s +2025-10-30 12:50:06.799871: +2025-10-30 12:50:06.803121: Epoch 667 +2025-10-30 12:50:06.805015: Current learning rate: 0.00372 +2025-10-30 12:50:28.275843: train_loss -0.9917 +2025-10-30 12:50:28.278316: val_loss -0.8921 +2025-10-30 12:50:28.280252: Pseudo dice [np.float32(0.9817), np.float32(0.9885), np.float32(0.9946), np.float32(0.7906)] +2025-10-30 12:50:28.282164: Epoch time: 21.48 s +2025-10-30 12:50:29.377738: +2025-10-30 12:50:29.379640: Epoch 668 +2025-10-30 12:50:29.381469: Current learning rate: 0.00371 +2025-10-30 12:50:51.229871: train_loss -0.9923 +2025-10-30 12:50:51.236108: val_loss -0.8782 +2025-10-30 12:50:51.238123: Pseudo dice [np.float32(0.9819), np.float32(0.9886), np.float32(0.9942), np.float32(0.7685)] +2025-10-30 12:50:51.240033: Epoch time: 21.85 s +2025-10-30 12:50:52.516616: +2025-10-30 12:50:52.518650: Epoch 669 +2025-10-30 12:50:52.520541: Current learning rate: 0.0037 +2025-10-30 12:51:12.872790: train_loss -0.9922 +2025-10-30 12:51:12.875851: val_loss -0.8749 +2025-10-30 12:51:12.877812: Pseudo dice [np.float32(0.9789), np.float32(0.9873), np.float32(0.9939), np.float32(0.7633)] +2025-10-30 12:51:12.879882: Epoch time: 20.36 s +2025-10-30 12:51:14.016288: +2025-10-30 12:51:14.018337: Epoch 670 +2025-10-30 12:51:14.020135: Current learning rate: 0.00369 +2025-10-30 12:51:34.377894: train_loss -0.9924 +2025-10-30 12:51:34.380550: val_loss -0.875 +2025-10-30 12:51:34.382228: Pseudo dice [np.float32(0.9803), np.float32(0.9886), np.float32(0.9937), np.float32(0.7577)] +2025-10-30 12:51:34.383892: Epoch time: 20.36 s +2025-10-30 12:51:35.581121: +2025-10-30 12:51:35.583615: Epoch 671 +2025-10-30 12:51:35.585826: Current learning rate: 0.00368 +2025-10-30 12:51:57.170359: train_loss -0.9918 +2025-10-30 12:51:57.172950: val_loss -0.8901 +2025-10-30 12:51:57.174896: Pseudo dice [np.float32(0.9818), np.float32(0.9883), np.float32(0.9945), np.float32(0.7907)] +2025-10-30 12:51:57.176436: Epoch time: 21.59 s +2025-10-30 12:51:58.459916: +2025-10-30 12:51:58.461978: Epoch 672 +2025-10-30 12:51:58.464358: Current learning rate: 0.00367 +2025-10-30 12:52:20.744371: train_loss -0.9918 +2025-10-30 12:52:20.746676: val_loss -0.8827 +2025-10-30 12:52:20.748451: Pseudo dice [np.float32(0.9809), np.float32(0.9882), np.float32(0.9945), np.float32(0.7772)] +2025-10-30 12:52:20.750103: Epoch time: 22.29 s +2025-10-30 12:52:22.051500: +2025-10-30 12:52:22.053351: Epoch 673 +2025-10-30 12:52:22.055185: Current learning rate: 0.00366 +2025-10-30 12:52:45.055791: train_loss -0.992 +2025-10-30 12:52:45.058352: val_loss -0.884 +2025-10-30 12:52:45.060163: Pseudo dice [np.float32(0.9826), np.float32(0.989), np.float32(0.9944), np.float32(0.7785)] +2025-10-30 12:52:45.065793: Epoch time: 23.01 s +2025-10-30 12:52:46.364521: +2025-10-30 12:52:46.367237: Epoch 674 +2025-10-30 12:52:46.369364: Current learning rate: 0.00365 +2025-10-30 12:53:08.473311: train_loss -0.9919 +2025-10-30 12:53:08.476243: val_loss -0.8817 +2025-10-30 12:53:08.477922: Pseudo dice [np.float32(0.9817), np.float32(0.9884), np.float32(0.9945), np.float32(0.7583)] +2025-10-30 12:53:08.479303: Epoch time: 22.11 s +2025-10-30 12:53:09.764415: +2025-10-30 12:53:09.766333: Epoch 675 +2025-10-30 12:53:09.768192: Current learning rate: 0.00364 +2025-10-30 12:53:30.838939: train_loss -0.9922 +2025-10-30 12:53:30.842486: val_loss -0.8879 +2025-10-30 12:53:30.844084: Pseudo dice [np.float32(0.9825), np.float32(0.9876), np.float32(0.9947), np.float32(0.7869)] +2025-10-30 12:53:30.845740: Epoch time: 21.08 s +2025-10-30 12:53:32.073228: +2025-10-30 12:53:32.075787: Epoch 676 +2025-10-30 12:53:32.077478: Current learning rate: 0.00363 +2025-10-30 12:53:53.383298: train_loss -0.9927 +2025-10-30 12:53:53.385935: val_loss -0.8851 +2025-10-30 12:53:53.388437: Pseudo dice [np.float32(0.9797), np.float32(0.9878), np.float32(0.9945), np.float32(0.7919)] +2025-10-30 12:53:53.389933: Epoch time: 21.31 s +2025-10-30 12:53:54.441116: +2025-10-30 12:53:54.442914: Epoch 677 +2025-10-30 12:53:54.444811: Current learning rate: 0.00362 +2025-10-30 12:54:15.865392: train_loss -0.9925 +2025-10-30 12:54:15.867983: val_loss -0.8806 +2025-10-30 12:54:15.869573: Pseudo dice [np.float32(0.9811), np.float32(0.9881), np.float32(0.9943), np.float32(0.778)] +2025-10-30 12:54:15.871263: Epoch time: 21.43 s +2025-10-30 12:54:17.137748: +2025-10-30 12:54:17.140633: Epoch 678 +2025-10-30 12:54:17.142368: Current learning rate: 0.00361 +2025-10-30 12:54:39.177495: train_loss -0.9918 +2025-10-30 12:54:39.180604: val_loss -0.8806 +2025-10-30 12:54:39.182689: Pseudo dice [np.float32(0.9824), np.float32(0.9885), np.float32(0.9943), np.float32(0.7637)] +2025-10-30 12:54:39.184243: Epoch time: 22.04 s +2025-10-30 12:54:40.411236: +2025-10-30 12:54:40.414441: Epoch 679 +2025-10-30 12:54:40.416337: Current learning rate: 0.0036 +2025-10-30 12:55:02.071577: train_loss -0.9918 +2025-10-30 12:55:02.074224: val_loss -0.8937 +2025-10-30 12:55:02.075969: Pseudo dice [np.float32(0.9804), np.float32(0.9882), np.float32(0.995), np.float32(0.8022)] +2025-10-30 12:55:02.077665: Epoch time: 21.66 s +2025-10-30 12:55:03.168551: +2025-10-30 12:55:03.171911: Epoch 680 +2025-10-30 12:55:03.173999: Current learning rate: 0.00359 +2025-10-30 12:55:25.135051: train_loss -0.9913 +2025-10-30 12:55:25.137444: val_loss -0.8838 +2025-10-30 12:55:25.139317: Pseudo dice [np.float32(0.9806), np.float32(0.9882), np.float32(0.9945), np.float32(0.7858)] +2025-10-30 12:55:25.141811: Epoch time: 21.97 s +2025-10-30 12:55:26.359123: +2025-10-30 12:55:26.361265: Epoch 681 +2025-10-30 12:55:26.363188: Current learning rate: 0.00358 +2025-10-30 12:55:47.032566: train_loss -0.9922 +2025-10-30 12:55:47.039555: val_loss -0.8858 +2025-10-30 12:55:47.041119: Pseudo dice [np.float32(0.9831), np.float32(0.9885), np.float32(0.9941), np.float32(0.7816)] +2025-10-30 12:55:47.043175: Epoch time: 20.68 s +2025-10-30 12:55:48.325796: +2025-10-30 12:55:48.327930: Epoch 682 +2025-10-30 12:55:48.329567: Current learning rate: 0.00357 +2025-10-30 12:56:10.037197: train_loss -0.9922 +2025-10-30 12:56:10.041186: val_loss -0.8777 +2025-10-30 12:56:10.043132: Pseudo dice [np.float32(0.9801), np.float32(0.9882), np.float32(0.9942), np.float32(0.7772)] +2025-10-30 12:56:10.044965: Epoch time: 21.71 s +2025-10-30 12:56:11.314539: +2025-10-30 12:56:11.316474: Epoch 683 +2025-10-30 12:56:11.318376: Current learning rate: 0.00356 +2025-10-30 12:56:32.772760: train_loss -0.9923 +2025-10-30 12:56:32.775612: val_loss -0.8779 +2025-10-30 12:56:32.777236: Pseudo dice [np.float32(0.9822), np.float32(0.9885), np.float32(0.9941), np.float32(0.7693)] +2025-10-30 12:56:32.780357: Epoch time: 21.46 s +2025-10-30 12:56:33.892497: +2025-10-30 12:56:33.895090: Epoch 684 +2025-10-30 12:56:33.896832: Current learning rate: 0.00355 +2025-10-30 12:56:55.662703: train_loss -0.9923 +2025-10-30 12:56:55.665061: val_loss -0.8794 +2025-10-30 12:56:55.666568: Pseudo dice [np.float32(0.9826), np.float32(0.9886), np.float32(0.9943), np.float32(0.7696)] +2025-10-30 12:56:55.667970: Epoch time: 21.77 s +2025-10-30 12:56:56.718434: +2025-10-30 12:56:56.720825: Epoch 685 +2025-10-30 12:56:56.723039: Current learning rate: 0.00354 +2025-10-30 12:57:18.847325: train_loss -0.9924 +2025-10-30 12:57:18.849961: val_loss -0.8896 +2025-10-30 12:57:18.851922: Pseudo dice [np.float32(0.9838), np.float32(0.9904), np.float32(0.9951), np.float32(0.7761)] +2025-10-30 12:57:18.853775: Epoch time: 22.13 s +2025-10-30 12:57:20.105863: +2025-10-30 12:57:20.111156: Epoch 686 +2025-10-30 12:57:20.117282: Current learning rate: 0.00353 +2025-10-30 12:57:42.221025: train_loss -0.9925 +2025-10-30 12:57:42.227147: val_loss -0.8804 +2025-10-30 12:57:42.229376: Pseudo dice [np.float32(0.9829), np.float32(0.9883), np.float32(0.9939), np.float32(0.7726)] +2025-10-30 12:57:42.240114: Epoch time: 22.12 s +2025-10-30 12:57:43.362343: +2025-10-30 12:57:43.364160: Epoch 687 +2025-10-30 12:57:43.366057: Current learning rate: 0.00352 +2025-10-30 12:58:04.507086: train_loss -0.9915 +2025-10-30 12:58:04.510103: val_loss -0.8833 +2025-10-30 12:58:04.513016: Pseudo dice [np.float32(0.9832), np.float32(0.9884), np.float32(0.9939), np.float32(0.7735)] +2025-10-30 12:58:04.515394: Epoch time: 21.15 s +2025-10-30 12:58:05.752967: +2025-10-30 12:58:05.755097: Epoch 688 +2025-10-30 12:58:05.756871: Current learning rate: 0.00351 +2025-10-30 12:58:27.644549: train_loss -0.9919 +2025-10-30 12:58:27.647125: val_loss -0.8927 +2025-10-30 12:58:27.649652: Pseudo dice [np.float32(0.9839), np.float32(0.989), np.float32(0.995), np.float32(0.7921)] +2025-10-30 12:58:27.652284: Epoch time: 21.89 s +2025-10-30 12:58:28.779088: +2025-10-30 12:58:28.781177: Epoch 689 +2025-10-30 12:58:28.784070: Current learning rate: 0.0035 +2025-10-30 12:58:49.618380: train_loss -0.9923 +2025-10-30 12:58:49.621203: val_loss -0.8883 +2025-10-30 12:58:49.622813: Pseudo dice [np.float32(0.9813), np.float32(0.9888), np.float32(0.9948), np.float32(0.7939)] +2025-10-30 12:58:49.624492: Epoch time: 20.84 s +2025-10-30 12:58:51.518396: +2025-10-30 12:58:51.522188: Epoch 690 +2025-10-30 12:58:51.524992: Current learning rate: 0.00349 +2025-10-30 12:59:13.424024: train_loss -0.9926 +2025-10-30 12:59:13.426833: val_loss -0.876 +2025-10-30 12:59:13.428410: Pseudo dice [np.float32(0.9804), np.float32(0.9877), np.float32(0.9942), np.float32(0.7602)] +2025-10-30 12:59:13.430239: Epoch time: 21.91 s +2025-10-30 12:59:14.674385: +2025-10-30 12:59:14.677572: Epoch 691 +2025-10-30 12:59:14.679973: Current learning rate: 0.00348 +2025-10-30 12:59:36.467088: train_loss -0.9917 +2025-10-30 12:59:36.469599: val_loss -0.8821 +2025-10-30 12:59:36.471427: Pseudo dice [np.float32(0.9836), np.float32(0.9878), np.float32(0.9938), np.float32(0.781)] +2025-10-30 12:59:36.473064: Epoch time: 21.79 s +2025-10-30 12:59:37.843251: +2025-10-30 12:59:37.845188: Epoch 692 +2025-10-30 12:59:37.847095: Current learning rate: 0.00346 +2025-10-30 12:59:59.954511: train_loss -0.9919 +2025-10-30 12:59:59.957134: val_loss -0.8822 +2025-10-30 12:59:59.958626: Pseudo dice [np.float32(0.9818), np.float32(0.9878), np.float32(0.9941), np.float32(0.7833)] +2025-10-30 12:59:59.960067: Epoch time: 22.11 s +2025-10-30 13:00:01.107562: +2025-10-30 13:00:01.109416: Epoch 693 +2025-10-30 13:00:01.111032: Current learning rate: 0.00345 +2025-10-30 13:00:22.819152: train_loss -0.992 +2025-10-30 13:00:22.822092: val_loss -0.8814 +2025-10-30 13:00:22.823701: Pseudo dice [np.float32(0.9818), np.float32(0.9875), np.float32(0.9942), np.float32(0.7748)] +2025-10-30 13:00:22.825647: Epoch time: 21.71 s +2025-10-30 13:00:23.898070: +2025-10-30 13:00:23.900006: Epoch 694 +2025-10-30 13:00:23.901879: Current learning rate: 0.00344 +2025-10-30 13:00:45.649485: train_loss -0.9918 +2025-10-30 13:00:45.651877: val_loss -0.8764 +2025-10-30 13:00:45.654652: Pseudo dice [np.float32(0.983), np.float32(0.9887), np.float32(0.994), np.float32(0.7542)] +2025-10-30 13:00:45.657176: Epoch time: 21.75 s +2025-10-30 13:00:47.013274: +2025-10-30 13:00:47.015687: Epoch 695 +2025-10-30 13:00:47.017527: Current learning rate: 0.00343 +2025-10-30 13:01:07.647012: train_loss -0.9921 +2025-10-30 13:01:07.649804: val_loss -0.8773 +2025-10-30 13:01:07.651732: Pseudo dice [np.float32(0.982), np.float32(0.9884), np.float32(0.9941), np.float32(0.7657)] +2025-10-30 13:01:07.654193: Epoch time: 20.64 s +2025-10-30 13:01:08.733035: +2025-10-30 13:01:08.736009: Epoch 696 +2025-10-30 13:01:08.737662: Current learning rate: 0.00342 +2025-10-30 13:01:30.990097: train_loss -0.992 +2025-10-30 13:01:30.992511: val_loss -0.8891 +2025-10-30 13:01:30.994301: Pseudo dice [np.float32(0.9821), np.float32(0.9887), np.float32(0.9944), np.float32(0.7899)] +2025-10-30 13:01:30.997137: Epoch time: 22.26 s +2025-10-30 13:01:32.216976: +2025-10-30 13:01:32.218947: Epoch 697 +2025-10-30 13:01:32.220715: Current learning rate: 0.00341 +2025-10-30 13:01:54.186735: train_loss -0.9924 +2025-10-30 13:01:54.188837: val_loss -0.8784 +2025-10-30 13:01:54.191164: Pseudo dice [np.float32(0.9815), np.float32(0.9882), np.float32(0.9938), np.float32(0.7708)] +2025-10-30 13:01:54.193141: Epoch time: 21.97 s +2025-10-30 13:01:55.110927: +2025-10-30 13:01:55.112912: Epoch 698 +2025-10-30 13:01:55.114938: Current learning rate: 0.0034 +2025-10-30 13:02:17.263663: train_loss -0.9929 +2025-10-30 13:02:17.266553: val_loss -0.8871 +2025-10-30 13:02:17.270368: Pseudo dice [np.float32(0.9804), np.float32(0.9878), np.float32(0.9946), np.float32(0.7903)] +2025-10-30 13:02:17.271961: Epoch time: 22.15 s +2025-10-30 13:02:18.559222: +2025-10-30 13:02:18.561352: Epoch 699 +2025-10-30 13:02:18.563008: Current learning rate: 0.00339 +2025-10-30 13:02:40.504913: train_loss -0.9921 +2025-10-30 13:02:40.507773: val_loss -0.8723 +2025-10-30 13:02:40.509835: Pseudo dice [np.float32(0.9794), np.float32(0.988), np.float32(0.9938), np.float32(0.7516)] +2025-10-30 13:02:40.511299: Epoch time: 21.95 s +2025-10-30 13:02:43.161906: +2025-10-30 13:02:43.163899: Epoch 700 +2025-10-30 13:02:43.165779: Current learning rate: 0.00338 +2025-10-30 13:03:05.660830: train_loss -0.9921 +2025-10-30 13:03:05.663668: val_loss -0.8798 +2025-10-30 13:03:05.668878: Pseudo dice [np.float32(0.9814), np.float32(0.9882), np.float32(0.9939), np.float32(0.7724)] +2025-10-30 13:03:05.670477: Epoch time: 22.5 s +2025-10-30 13:03:06.975891: +2025-10-30 13:03:06.977874: Epoch 701 +2025-10-30 13:03:06.980203: Current learning rate: 0.00337 +2025-10-30 13:03:29.349609: train_loss -0.9923 +2025-10-30 13:03:29.352720: val_loss -0.877 +2025-10-30 13:03:29.354247: Pseudo dice [np.float32(0.9819), np.float32(0.9889), np.float32(0.9942), np.float32(0.761)] +2025-10-30 13:03:29.355704: Epoch time: 22.38 s +2025-10-30 13:03:30.567125: +2025-10-30 13:03:30.569470: Epoch 702 +2025-10-30 13:03:30.571209: Current learning rate: 0.00336 +2025-10-30 13:03:48.354697: train_loss -0.9926 +2025-10-30 13:03:48.365602: val_loss -0.8798 +2025-10-30 13:03:48.373171: Pseudo dice [np.float32(0.9831), np.float32(0.9883), np.float32(0.9941), np.float32(0.7677)] +2025-10-30 13:03:48.382507: Epoch time: 17.79 s +2025-10-30 13:03:49.759004: +2025-10-30 13:03:49.766537: Epoch 703 +2025-10-30 13:03:49.773848: Current learning rate: 0.00335 +2025-10-30 13:04:11.737208: train_loss -0.9917 +2025-10-30 13:04:11.744198: val_loss -0.8888 +2025-10-30 13:04:11.746025: Pseudo dice [np.float32(0.984), np.float32(0.9898), np.float32(0.9945), np.float32(0.7804)] +2025-10-30 13:04:11.748245: Epoch time: 21.98 s +2025-10-30 13:04:13.091652: +2025-10-30 13:04:13.094179: Epoch 704 +2025-10-30 13:04:13.095693: Current learning rate: 0.00334 +2025-10-30 13:04:35.336418: train_loss -0.9918 +2025-10-30 13:04:35.339965: val_loss -0.8749 +2025-10-30 13:04:35.341573: Pseudo dice [np.float32(0.9793), np.float32(0.9871), np.float32(0.994), np.float32(0.7663)] +2025-10-30 13:04:35.343436: Epoch time: 22.25 s +2025-10-30 13:04:36.488144: +2025-10-30 13:04:36.490490: Epoch 705 +2025-10-30 13:04:36.492067: Current learning rate: 0.00333 +2025-10-30 13:04:58.162292: train_loss -0.9919 +2025-10-30 13:04:58.164455: val_loss -0.8797 +2025-10-30 13:04:58.166403: Pseudo dice [np.float32(0.981), np.float32(0.9878), np.float32(0.9942), np.float32(0.7775)] +2025-10-30 13:04:58.168211: Epoch time: 21.68 s +2025-10-30 13:05:00.577740: +2025-10-30 13:05:00.579712: Epoch 706 +2025-10-30 13:05:00.584119: Current learning rate: 0.00332 +2025-10-30 13:05:22.925125: train_loss -0.9929 +2025-10-30 13:05:22.928752: val_loss -0.8877 +2025-10-30 13:05:22.932491: Pseudo dice [np.float32(0.9825), np.float32(0.9887), np.float32(0.9946), np.float32(0.7885)] +2025-10-30 13:05:22.934256: Epoch time: 22.35 s +2025-10-30 13:05:24.248800: +2025-10-30 13:05:24.250735: Epoch 707 +2025-10-30 13:05:24.252661: Current learning rate: 0.00331 +2025-10-30 13:05:46.470026: train_loss -0.9924 +2025-10-30 13:05:46.472942: val_loss -0.8739 +2025-10-30 13:05:46.476497: Pseudo dice [np.float32(0.9831), np.float32(0.9889), np.float32(0.9936), np.float32(0.75)] +2025-10-30 13:05:46.479093: Epoch time: 22.22 s +2025-10-30 13:05:47.713191: +2025-10-30 13:05:47.715209: Epoch 708 +2025-10-30 13:05:47.717256: Current learning rate: 0.0033 +2025-10-30 13:06:08.332279: train_loss -0.9921 +2025-10-30 13:06:08.334815: val_loss -0.8825 +2025-10-30 13:06:08.336945: Pseudo dice [np.float32(0.9834), np.float32(0.9887), np.float32(0.9939), np.float32(0.7782)] +2025-10-30 13:06:08.338616: Epoch time: 20.62 s +2025-10-30 13:06:09.727509: +2025-10-30 13:06:09.730245: Epoch 709 +2025-10-30 13:06:09.731893: Current learning rate: 0.00329 +2025-10-30 13:06:32.580704: train_loss -0.9927 +2025-10-30 13:06:32.582844: val_loss -0.8793 +2025-10-30 13:06:32.584695: Pseudo dice [np.float32(0.9824), np.float32(0.989), np.float32(0.9938), np.float32(0.7625)] +2025-10-30 13:06:32.586386: Epoch time: 22.86 s +2025-10-30 13:06:33.891077: +2025-10-30 13:06:33.894965: Epoch 710 +2025-10-30 13:06:33.896596: Current learning rate: 0.00328 +2025-10-30 13:06:56.314590: train_loss -0.9922 +2025-10-30 13:06:56.318254: val_loss -0.875 +2025-10-30 13:06:56.321251: Pseudo dice [np.float32(0.9806), np.float32(0.9876), np.float32(0.9939), np.float32(0.7666)] +2025-10-30 13:06:56.325050: Epoch time: 22.42 s +2025-10-30 13:06:57.606607: +2025-10-30 13:06:57.609215: Epoch 711 +2025-10-30 13:06:57.611530: Current learning rate: 0.00327 +2025-10-30 13:07:18.811152: train_loss -0.9929 +2025-10-30 13:07:18.814879: val_loss -0.8839 +2025-10-30 13:07:18.816841: Pseudo dice [np.float32(0.9824), np.float32(0.9885), np.float32(0.9943), np.float32(0.7749)] +2025-10-30 13:07:18.818761: Epoch time: 21.21 s +2025-10-30 13:07:19.941405: +2025-10-30 13:07:19.943312: Epoch 712 +2025-10-30 13:07:19.945101: Current learning rate: 0.00326 +2025-10-30 13:07:42.507699: train_loss -0.9928 +2025-10-30 13:07:42.510006: val_loss -0.8845 +2025-10-30 13:07:42.512112: Pseudo dice [np.float32(0.9813), np.float32(0.9877), np.float32(0.9942), np.float32(0.7842)] +2025-10-30 13:07:42.513689: Epoch time: 22.57 s +2025-10-30 13:07:43.660131: +2025-10-30 13:07:43.662531: Epoch 713 +2025-10-30 13:07:43.666487: Current learning rate: 0.00325 +2025-10-30 13:08:05.694946: train_loss -0.9926 +2025-10-30 13:08:05.701780: val_loss -0.8814 +2025-10-30 13:08:05.704269: Pseudo dice [np.float32(0.9812), np.float32(0.9881), np.float32(0.994), np.float32(0.7774)] +2025-10-30 13:08:05.706089: Epoch time: 22.04 s +2025-10-30 13:08:06.975800: +2025-10-30 13:08:06.977960: Epoch 714 +2025-10-30 13:08:06.980193: Current learning rate: 0.00324 +2025-10-30 13:08:29.334132: train_loss -0.9925 +2025-10-30 13:08:29.337774: val_loss -0.8713 +2025-10-30 13:08:29.345078: Pseudo dice [np.float32(0.9812), np.float32(0.9879), np.float32(0.9941), np.float32(0.7593)] +2025-10-30 13:08:29.351143: Epoch time: 22.36 s +2025-10-30 13:08:30.872206: +2025-10-30 13:08:30.879805: Epoch 715 +2025-10-30 13:08:30.887020: Current learning rate: 0.00323 +2025-10-30 13:08:52.308774: train_loss -0.992 +2025-10-30 13:08:52.312255: val_loss -0.8766 +2025-10-30 13:08:52.313879: Pseudo dice [np.float32(0.9806), np.float32(0.9882), np.float32(0.9938), np.float32(0.7714)] +2025-10-30 13:08:52.315764: Epoch time: 21.44 s +2025-10-30 13:08:53.635375: +2025-10-30 13:08:53.639111: Epoch 716 +2025-10-30 13:08:53.641977: Current learning rate: 0.00322 +2025-10-30 13:09:15.513199: train_loss -0.9933 +2025-10-30 13:09:15.516212: val_loss -0.8851 +2025-10-30 13:09:15.517841: Pseudo dice [np.float32(0.9814), np.float32(0.9883), np.float32(0.9944), np.float32(0.7896)] +2025-10-30 13:09:15.519787: Epoch time: 21.88 s +2025-10-30 13:09:16.597024: +2025-10-30 13:09:16.598974: Epoch 717 +2025-10-30 13:09:16.601012: Current learning rate: 0.00321 +2025-10-30 13:09:38.012396: train_loss -0.993 +2025-10-30 13:09:38.015337: val_loss -0.8862 +2025-10-30 13:09:38.017432: Pseudo dice [np.float32(0.9835), np.float32(0.9893), np.float32(0.9946), np.float32(0.7865)] +2025-10-30 13:09:38.019094: Epoch time: 21.42 s +2025-10-30 13:09:39.315659: +2025-10-30 13:09:39.317644: Epoch 718 +2025-10-30 13:09:39.319219: Current learning rate: 0.0032 +2025-10-30 13:10:01.189965: train_loss -0.9925 +2025-10-30 13:10:01.195674: val_loss -0.8846 +2025-10-30 13:10:01.197989: Pseudo dice [np.float32(0.9825), np.float32(0.9884), np.float32(0.9938), np.float32(0.7771)] +2025-10-30 13:10:01.199473: Epoch time: 21.88 s +2025-10-30 13:10:02.523588: +2025-10-30 13:10:02.526402: Epoch 719 +2025-10-30 13:10:02.529610: Current learning rate: 0.00319 +2025-10-30 13:10:25.026338: train_loss -0.9925 +2025-10-30 13:10:25.032920: val_loss -0.8886 +2025-10-30 13:10:25.034699: Pseudo dice [np.float32(0.9838), np.float32(0.9887), np.float32(0.9944), np.float32(0.789)] +2025-10-30 13:10:25.036334: Epoch time: 22.5 s +2025-10-30 13:10:26.284992: +2025-10-30 13:10:26.287827: Epoch 720 +2025-10-30 13:10:26.290066: Current learning rate: 0.00318 +2025-10-30 13:10:48.854515: train_loss -0.9929 +2025-10-30 13:10:48.857200: val_loss -0.883 +2025-10-30 13:10:48.858974: Pseudo dice [np.float32(0.9804), np.float32(0.9878), np.float32(0.9942), np.float32(0.7831)] +2025-10-30 13:10:48.860792: Epoch time: 22.57 s +2025-10-30 13:10:50.191496: +2025-10-30 13:10:50.193793: Epoch 721 +2025-10-30 13:10:50.195678: Current learning rate: 0.00317 +2025-10-30 13:11:11.153918: train_loss -0.9921 +2025-10-30 13:11:11.158386: val_loss -0.8825 +2025-10-30 13:11:11.160187: Pseudo dice [np.float32(0.9824), np.float32(0.9893), np.float32(0.9942), np.float32(0.7736)] +2025-10-30 13:11:11.161874: Epoch time: 20.96 s +2025-10-30 13:11:12.352412: +2025-10-30 13:11:12.355804: Epoch 722 +2025-10-30 13:11:12.357773: Current learning rate: 0.00316 +2025-10-30 13:11:34.755646: train_loss -0.9923 +2025-10-30 13:11:34.760259: val_loss -0.8833 +2025-10-30 13:11:34.762905: Pseudo dice [np.float32(0.9835), np.float32(0.9887), np.float32(0.9943), np.float32(0.7778)] +2025-10-30 13:11:34.764847: Epoch time: 22.4 s +2025-10-30 13:11:37.210083: +2025-10-30 13:11:37.211803: Epoch 723 +2025-10-30 13:11:37.213648: Current learning rate: 0.00315 +2025-10-30 13:11:57.856435: train_loss -0.9924 +2025-10-30 13:11:57.861643: val_loss -0.8826 +2025-10-30 13:11:57.863889: Pseudo dice [np.float32(0.9809), np.float32(0.9889), np.float32(0.9944), np.float32(0.775)] +2025-10-30 13:11:57.866647: Epoch time: 20.65 s +2025-10-30 13:11:59.230944: +2025-10-30 13:11:59.234234: Epoch 724 +2025-10-30 13:11:59.235932: Current learning rate: 0.00314 +2025-10-30 13:12:21.787169: train_loss -0.9929 +2025-10-30 13:12:21.790263: val_loss -0.8767 +2025-10-30 13:12:21.792327: Pseudo dice [np.float32(0.9821), np.float32(0.9884), np.float32(0.9942), np.float32(0.7641)] +2025-10-30 13:12:21.794257: Epoch time: 22.56 s +2025-10-30 13:12:23.047918: +2025-10-30 13:12:23.049947: Epoch 725 +2025-10-30 13:12:23.051594: Current learning rate: 0.00313 +2025-10-30 13:12:45.529529: train_loss -0.9923 +2025-10-30 13:12:45.535088: val_loss -0.8755 +2025-10-30 13:12:45.536657: Pseudo dice [np.float32(0.9808), np.float32(0.9864), np.float32(0.9938), np.float32(0.7648)] +2025-10-30 13:12:45.540093: Epoch time: 22.48 s +2025-10-30 13:12:46.768431: +2025-10-30 13:12:46.770793: Epoch 726 +2025-10-30 13:12:46.772636: Current learning rate: 0.00312 +2025-10-30 13:13:09.290751: train_loss -0.9928 +2025-10-30 13:13:09.293254: val_loss -0.8816 +2025-10-30 13:13:09.295216: Pseudo dice [np.float32(0.9819), np.float32(0.988), np.float32(0.9942), np.float32(0.7757)] +2025-10-30 13:13:09.297316: Epoch time: 22.52 s +2025-10-30 13:13:10.394169: +2025-10-30 13:13:10.396791: Epoch 727 +2025-10-30 13:13:10.398374: Current learning rate: 0.00311 +2025-10-30 13:13:31.667318: train_loss -0.9925 +2025-10-30 13:13:31.671501: val_loss -0.8818 +2025-10-30 13:13:31.673143: Pseudo dice [np.float32(0.9804), np.float32(0.988), np.float32(0.9942), np.float32(0.7762)] +2025-10-30 13:13:31.674812: Epoch time: 21.28 s +2025-10-30 13:13:33.051663: +2025-10-30 13:13:33.053595: Epoch 728 +2025-10-30 13:13:33.055055: Current learning rate: 0.0031 +2025-10-30 13:13:55.544824: train_loss -0.9926 +2025-10-30 13:13:55.548960: val_loss -0.8861 +2025-10-30 13:13:55.551083: Pseudo dice [np.float32(0.98), np.float32(0.9883), np.float32(0.9944), np.float32(0.7778)] +2025-10-30 13:13:55.553914: Epoch time: 22.49 s +2025-10-30 13:13:56.821969: +2025-10-30 13:13:56.824037: Epoch 729 +2025-10-30 13:13:56.826015: Current learning rate: 0.00309 +2025-10-30 13:14:18.687422: train_loss -0.9925 +2025-10-30 13:14:18.692291: val_loss -0.8916 +2025-10-30 13:14:18.693939: Pseudo dice [np.float32(0.9815), np.float32(0.9885), np.float32(0.9949), np.float32(0.7947)] +2025-10-30 13:14:18.695472: Epoch time: 21.87 s +2025-10-30 13:14:19.948231: +2025-10-30 13:14:19.950415: Epoch 730 +2025-10-30 13:14:19.952324: Current learning rate: 0.00308 +2025-10-30 13:14:41.950279: train_loss -0.9932 +2025-10-30 13:14:41.954867: val_loss -0.8811 +2025-10-30 13:14:41.956683: Pseudo dice [np.float32(0.9821), np.float32(0.9877), np.float32(0.9938), np.float32(0.7792)] +2025-10-30 13:14:41.958020: Epoch time: 22.0 s +2025-10-30 13:14:43.295482: +2025-10-30 13:14:43.298283: Epoch 731 +2025-10-30 13:14:43.302322: Current learning rate: 0.00307 +2025-10-30 13:15:05.539304: train_loss -0.9922 +2025-10-30 13:15:05.544130: val_loss -0.8844 +2025-10-30 13:15:05.545944: Pseudo dice [np.float32(0.9816), np.float32(0.9876), np.float32(0.9943), np.float32(0.781)] +2025-10-30 13:15:05.547634: Epoch time: 22.25 s +2025-10-30 13:15:06.910692: +2025-10-30 13:15:06.912748: Epoch 732 +2025-10-30 13:15:06.914490: Current learning rate: 0.00306 +2025-10-30 13:15:29.637835: train_loss -0.9926 +2025-10-30 13:15:29.640389: val_loss -0.8954 +2025-10-30 13:15:29.642025: Pseudo dice [np.float32(0.9829), np.float32(0.9886), np.float32(0.9946), np.float32(0.8078)] +2025-10-30 13:15:29.643657: Epoch time: 22.73 s +2025-10-30 13:15:30.891878: +2025-10-30 13:15:30.894155: Epoch 733 +2025-10-30 13:15:30.895858: Current learning rate: 0.00305 +2025-10-30 13:15:53.062946: train_loss -0.9927 +2025-10-30 13:15:53.068364: val_loss -0.8911 +2025-10-30 13:15:53.070917: Pseudo dice [np.float32(0.98), np.float32(0.9877), np.float32(0.9946), np.float32(0.8036)] +2025-10-30 13:15:53.073001: Epoch time: 22.17 s +2025-10-30 13:15:54.432701: +2025-10-30 13:15:54.439932: Epoch 734 +2025-10-30 13:15:54.447785: Current learning rate: 0.00304 +2025-10-30 13:16:16.335406: train_loss -0.9927 +2025-10-30 13:16:16.342093: val_loss -0.8868 +2025-10-30 13:16:16.344245: Pseudo dice [np.float32(0.9805), np.float32(0.9879), np.float32(0.9944), np.float32(0.7923)] +2025-10-30 13:16:16.345969: Epoch time: 21.9 s +2025-10-30 13:16:17.610514: +2025-10-30 13:16:17.614592: Epoch 735 +2025-10-30 13:16:17.616788: Current learning rate: 0.00303 +2025-10-30 13:16:39.118705: train_loss -0.9926 +2025-10-30 13:16:39.121936: val_loss -0.8841 +2025-10-30 13:16:39.124346: Pseudo dice [np.float32(0.9823), np.float32(0.9879), np.float32(0.9941), np.float32(0.7875)] +2025-10-30 13:16:39.128513: Epoch time: 21.51 s +2025-10-30 13:16:40.364721: +2025-10-30 13:16:40.366606: Epoch 736 +2025-10-30 13:16:40.368391: Current learning rate: 0.00302 +2025-10-30 13:17:02.956194: train_loss -0.9926 +2025-10-30 13:17:02.959450: val_loss -0.8779 +2025-10-30 13:17:02.961708: Pseudo dice [np.float32(0.9809), np.float32(0.9881), np.float32(0.9944), np.float32(0.7716)] +2025-10-30 13:17:02.963634: Epoch time: 22.59 s +2025-10-30 13:17:04.192086: +2025-10-30 13:17:04.195953: Epoch 737 +2025-10-30 13:17:04.197813: Current learning rate: 0.00301 +2025-10-30 13:17:26.397109: train_loss -0.9925 +2025-10-30 13:17:26.401638: val_loss -0.8909 +2025-10-30 13:17:26.403271: Pseudo dice [np.float32(0.9817), np.float32(0.9883), np.float32(0.9943), np.float32(0.8025)] +2025-10-30 13:17:26.405407: Epoch time: 22.21 s +2025-10-30 13:17:27.678818: +2025-10-30 13:17:27.680925: Epoch 738 +2025-10-30 13:17:27.684100: Current learning rate: 0.003 +2025-10-30 13:17:49.512485: train_loss -0.992 +2025-10-30 13:17:49.515505: val_loss -0.8796 +2025-10-30 13:17:49.517081: Pseudo dice [np.float32(0.9826), np.float32(0.9888), np.float32(0.9943), np.float32(0.7779)] +2025-10-30 13:17:49.518743: Epoch time: 21.84 s +2025-10-30 13:17:50.724221: +2025-10-30 13:17:50.726219: Epoch 739 +2025-10-30 13:17:50.728159: Current learning rate: 0.00299 +2025-10-30 13:18:12.881837: train_loss -0.9927 +2025-10-30 13:18:12.884713: val_loss -0.8857 +2025-10-30 13:18:12.886496: Pseudo dice [np.float32(0.9816), np.float32(0.9887), np.float32(0.9943), np.float32(0.7851)] +2025-10-30 13:18:12.888385: Epoch time: 22.16 s +2025-10-30 13:18:14.874721: +2025-10-30 13:18:14.877628: Epoch 740 +2025-10-30 13:18:14.879697: Current learning rate: 0.00297 +2025-10-30 13:18:35.806031: train_loss -0.9925 +2025-10-30 13:18:35.811591: val_loss -0.8824 +2025-10-30 13:18:35.816630: Pseudo dice [np.float32(0.9805), np.float32(0.9871), np.float32(0.9942), np.float32(0.7844)] +2025-10-30 13:18:35.818668: Epoch time: 20.93 s +2025-10-30 13:18:37.082582: +2025-10-30 13:18:37.085026: Epoch 741 +2025-10-30 13:18:37.087017: Current learning rate: 0.00296 +2025-10-30 13:18:58.713831: train_loss -0.993 +2025-10-30 13:18:58.721110: val_loss -0.8877 +2025-10-30 13:18:58.728774: Pseudo dice [np.float32(0.98), np.float32(0.9877), np.float32(0.9946), np.float32(0.7925)] +2025-10-30 13:18:58.752378: Epoch time: 21.63 s +2025-10-30 13:19:00.056267: +2025-10-30 13:19:00.058348: Epoch 742 +2025-10-30 13:19:00.064517: Current learning rate: 0.00295 +2025-10-30 13:19:22.144891: train_loss -0.9925 +2025-10-30 13:19:22.151021: val_loss -0.8882 +2025-10-30 13:19:22.153201: Pseudo dice [np.float32(0.9812), np.float32(0.9881), np.float32(0.9948), np.float32(0.7919)] +2025-10-30 13:19:22.154957: Epoch time: 22.09 s +2025-10-30 13:19:23.371356: +2025-10-30 13:19:23.373419: Epoch 743 +2025-10-30 13:19:23.375514: Current learning rate: 0.00294 +2025-10-30 13:19:46.074646: train_loss -0.9925 +2025-10-30 13:19:46.077755: val_loss -0.8831 +2025-10-30 13:19:46.079305: Pseudo dice [np.float32(0.9811), np.float32(0.9879), np.float32(0.9941), np.float32(0.7818)] +2025-10-30 13:19:46.081294: Epoch time: 22.7 s +2025-10-30 13:19:47.389133: +2025-10-30 13:19:47.391606: Epoch 744 +2025-10-30 13:19:47.395073: Current learning rate: 0.00293 +2025-10-30 13:20:09.325862: train_loss -0.9928 +2025-10-30 13:20:09.329394: val_loss -0.8889 +2025-10-30 13:20:09.331286: Pseudo dice [np.float32(0.9819), np.float32(0.9893), np.float32(0.9948), np.float32(0.79)] +2025-10-30 13:20:09.332797: Epoch time: 21.94 s +2025-10-30 13:20:10.606838: +2025-10-30 13:20:10.609718: Epoch 745 +2025-10-30 13:20:10.612954: Current learning rate: 0.00292 +2025-10-30 13:20:32.847510: train_loss -0.9921 +2025-10-30 13:20:32.853793: val_loss -0.8852 +2025-10-30 13:20:32.856245: Pseudo dice [np.float32(0.9804), np.float32(0.9872), np.float32(0.9944), np.float32(0.7855)] +2025-10-30 13:20:32.858008: Epoch time: 22.24 s +2025-10-30 13:20:34.165944: +2025-10-30 13:20:34.167814: Epoch 746 +2025-10-30 13:20:34.169839: Current learning rate: 0.00291 +2025-10-30 13:20:55.287767: train_loss -0.9932 +2025-10-30 13:20:55.290735: val_loss -0.8827 +2025-10-30 13:20:55.292534: Pseudo dice [np.float32(0.9809), np.float32(0.9859), np.float32(0.9942), np.float32(0.7899)] +2025-10-30 13:20:55.294563: Epoch time: 21.12 s +2025-10-30 13:20:56.607375: +2025-10-30 13:20:56.609448: Epoch 747 +2025-10-30 13:20:56.611204: Current learning rate: 0.0029 +2025-10-30 13:21:18.643790: train_loss -0.9928 +2025-10-30 13:21:18.647977: val_loss -0.8896 +2025-10-30 13:21:18.649628: Pseudo dice [np.float32(0.9806), np.float32(0.988), np.float32(0.9948), np.float32(0.7927)] +2025-10-30 13:21:18.651263: Epoch time: 22.04 s +2025-10-30 13:21:19.895250: +2025-10-30 13:21:19.896802: Epoch 748 +2025-10-30 13:21:19.898269: Current learning rate: 0.00289 +2025-10-30 13:21:42.510576: train_loss -0.9927 +2025-10-30 13:21:42.516115: val_loss -0.8859 +2025-10-30 13:21:42.517787: Pseudo dice [np.float32(0.9836), np.float32(0.9891), np.float32(0.9946), np.float32(0.769)] +2025-10-30 13:21:42.519512: Epoch time: 22.62 s +2025-10-30 13:21:43.668454: +2025-10-30 13:21:43.670787: Epoch 749 +2025-10-30 13:21:43.672327: Current learning rate: 0.00288 +2025-10-30 13:22:06.222526: train_loss -0.9927 +2025-10-30 13:22:06.229477: val_loss -0.8757 +2025-10-30 13:22:06.232626: Pseudo dice [np.float32(0.9797), np.float32(0.9872), np.float32(0.994), np.float32(0.7657)] +2025-10-30 13:22:06.237038: Epoch time: 22.56 s +2025-10-30 13:22:08.968910: +2025-10-30 13:22:08.970871: Epoch 750 +2025-10-30 13:22:08.973441: Current learning rate: 0.00287 +2025-10-30 13:22:31.481085: train_loss -0.9931 +2025-10-30 13:22:31.485933: val_loss -0.8927 +2025-10-30 13:22:31.487892: Pseudo dice [np.float32(0.9822), np.float32(0.9893), np.float32(0.9947), np.float32(0.7997)] +2025-10-30 13:22:31.492917: Epoch time: 22.51 s +2025-10-30 13:22:32.818383: +2025-10-30 13:22:32.821970: Epoch 751 +2025-10-30 13:22:32.824228: Current learning rate: 0.00286 +2025-10-30 13:22:55.393628: train_loss -0.9931 +2025-10-30 13:22:55.397565: val_loss -0.8847 +2025-10-30 13:22:55.400450: Pseudo dice [np.float32(0.9813), np.float32(0.9883), np.float32(0.9946), np.float32(0.7817)] +2025-10-30 13:22:55.402878: Epoch time: 22.58 s +2025-10-30 13:22:56.655884: +2025-10-30 13:22:56.660862: Epoch 752 +2025-10-30 13:22:56.665059: Current learning rate: 0.00285 +2025-10-30 13:23:17.406238: train_loss -0.9925 +2025-10-30 13:23:17.409138: val_loss -0.8855 +2025-10-30 13:23:17.410952: Pseudo dice [np.float32(0.9814), np.float32(0.9882), np.float32(0.9945), np.float32(0.7912)] +2025-10-30 13:23:17.413993: Epoch time: 20.75 s +2025-10-30 13:23:18.684258: +2025-10-30 13:23:18.690212: Epoch 753 +2025-10-30 13:23:18.695382: Current learning rate: 0.00284 +2025-10-30 13:23:40.886757: train_loss -0.9926 +2025-10-30 13:23:40.889643: val_loss -0.8859 +2025-10-30 13:23:40.891510: Pseudo dice [np.float32(0.9831), np.float32(0.9891), np.float32(0.9947), np.float32(0.7785)] +2025-10-30 13:23:40.893131: Epoch time: 22.2 s +2025-10-30 13:23:42.065849: +2025-10-30 13:23:42.068594: Epoch 754 +2025-10-30 13:23:42.070840: Current learning rate: 0.00283 +2025-10-30 13:24:04.713776: train_loss -0.9923 +2025-10-30 13:24:04.716137: val_loss -0.888 +2025-10-30 13:24:04.717922: Pseudo dice [np.float32(0.9825), np.float32(0.9891), np.float32(0.9944), np.float32(0.7799)] +2025-10-30 13:24:04.719300: Epoch time: 22.65 s +2025-10-30 13:24:05.863568: +2025-10-30 13:24:05.865927: Epoch 755 +2025-10-30 13:24:05.867710: Current learning rate: 0.00282 +2025-10-30 13:24:28.788332: train_loss -0.9932 +2025-10-30 13:24:28.793996: val_loss -0.8827 +2025-10-30 13:24:28.796294: Pseudo dice [np.float32(0.9803), np.float32(0.9885), np.float32(0.9945), np.float32(0.7807)] +2025-10-30 13:24:28.798633: Epoch time: 22.93 s +2025-10-30 13:24:30.202242: +2025-10-30 13:24:30.204919: Epoch 756 +2025-10-30 13:24:30.207238: Current learning rate: 0.00281 +2025-10-30 13:24:52.771003: train_loss -0.9927 +2025-10-30 13:24:52.774961: val_loss -0.8719 +2025-10-30 13:24:52.777288: Pseudo dice [np.float32(0.9817), np.float32(0.9885), np.float32(0.9938), np.float32(0.7507)] +2025-10-30 13:24:52.780123: Epoch time: 22.57 s +2025-10-30 13:24:55.237463: +2025-10-30 13:24:55.244003: Epoch 757 +2025-10-30 13:24:55.248783: Current learning rate: 0.0028 +2025-10-30 13:25:17.813449: train_loss -0.9928 +2025-10-30 13:25:17.816627: val_loss -0.8811 +2025-10-30 13:25:17.818457: Pseudo dice [np.float32(0.9819), np.float32(0.9892), np.float32(0.9937), np.float32(0.7733)] +2025-10-30 13:25:17.821088: Epoch time: 22.58 s +2025-10-30 13:25:19.139698: +2025-10-30 13:25:19.145240: Epoch 758 +2025-10-30 13:25:19.147573: Current learning rate: 0.00279 +2025-10-30 13:25:38.869150: train_loss -0.9923 +2025-10-30 13:25:38.875980: val_loss -0.8829 +2025-10-30 13:25:38.879563: Pseudo dice [np.float32(0.9805), np.float32(0.9882), np.float32(0.9944), np.float32(0.7746)] +2025-10-30 13:25:38.883265: Epoch time: 19.73 s +2025-10-30 13:25:39.986838: +2025-10-30 13:25:39.991987: Epoch 759 +2025-10-30 13:25:39.995775: Current learning rate: 0.00278 +2025-10-30 13:26:01.585386: train_loss -0.9929 +2025-10-30 13:26:01.588382: val_loss -0.8742 +2025-10-30 13:26:01.590274: Pseudo dice [np.float32(0.9817), np.float32(0.9884), np.float32(0.9943), np.float32(0.7568)] +2025-10-30 13:26:01.591905: Epoch time: 21.6 s +2025-10-30 13:26:02.958688: +2025-10-30 13:26:02.960975: Epoch 760 +2025-10-30 13:26:02.962692: Current learning rate: 0.00277 +2025-10-30 13:26:25.193213: train_loss -0.9921 +2025-10-30 13:26:25.198594: val_loss -0.8867 +2025-10-30 13:26:25.200334: Pseudo dice [np.float32(0.9808), np.float32(0.9886), np.float32(0.9947), np.float32(0.7888)] +2025-10-30 13:26:25.202029: Epoch time: 22.24 s +2025-10-30 13:26:26.530249: +2025-10-30 13:26:26.534264: Epoch 761 +2025-10-30 13:26:26.539395: Current learning rate: 0.00276 +2025-10-30 13:26:48.355573: train_loss -0.9925 +2025-10-30 13:26:48.359075: val_loss -0.8708 +2025-10-30 13:26:48.361894: Pseudo dice [np.float32(0.9797), np.float32(0.9877), np.float32(0.9937), np.float32(0.758)] +2025-10-30 13:26:48.365021: Epoch time: 21.83 s +2025-10-30 13:26:49.594348: +2025-10-30 13:26:49.596210: Epoch 762 +2025-10-30 13:26:49.598327: Current learning rate: 0.00275 +2025-10-30 13:27:11.530662: train_loss -0.9928 +2025-10-30 13:27:11.533445: val_loss -0.8815 +2025-10-30 13:27:11.536476: Pseudo dice [np.float32(0.9831), np.float32(0.9881), np.float32(0.994), np.float32(0.7769)] +2025-10-30 13:27:11.539846: Epoch time: 21.94 s +2025-10-30 13:27:12.683172: +2025-10-30 13:27:12.685845: Epoch 763 +2025-10-30 13:27:12.687549: Current learning rate: 0.00274 +2025-10-30 13:27:34.365261: train_loss -0.9929 +2025-10-30 13:27:34.371697: val_loss -0.8807 +2025-10-30 13:27:34.374472: Pseudo dice [np.float32(0.9816), np.float32(0.9884), np.float32(0.9942), np.float32(0.7709)] +2025-10-30 13:27:34.376755: Epoch time: 21.68 s +2025-10-30 13:27:35.630161: +2025-10-30 13:27:35.632284: Epoch 764 +2025-10-30 13:27:35.634045: Current learning rate: 0.00273 +2025-10-30 13:27:57.072442: train_loss -0.993 +2025-10-30 13:27:57.075166: val_loss -0.8889 +2025-10-30 13:27:57.076833: Pseudo dice [np.float32(0.983), np.float32(0.9893), np.float32(0.9945), np.float32(0.7857)] +2025-10-30 13:27:57.079404: Epoch time: 21.44 s +2025-10-30 13:27:58.413809: +2025-10-30 13:27:58.416216: Epoch 765 +2025-10-30 13:27:58.418038: Current learning rate: 0.00272 +2025-10-30 13:28:19.376249: train_loss -0.9925 +2025-10-30 13:28:19.383240: val_loss -0.8793 +2025-10-30 13:28:19.385594: Pseudo dice [np.float32(0.9816), np.float32(0.9883), np.float32(0.9941), np.float32(0.7718)] +2025-10-30 13:28:19.387254: Epoch time: 20.96 s +2025-10-30 13:28:20.715530: +2025-10-30 13:28:20.719073: Epoch 766 +2025-10-30 13:28:20.722594: Current learning rate: 0.00271 +2025-10-30 13:28:42.979254: train_loss -0.9922 +2025-10-30 13:28:42.981707: val_loss -0.8879 +2025-10-30 13:28:42.984181: Pseudo dice [np.float32(0.9837), np.float32(0.9887), np.float32(0.9944), np.float32(0.7852)] +2025-10-30 13:28:42.989373: Epoch time: 22.27 s +2025-10-30 13:28:44.184625: +2025-10-30 13:28:44.188219: Epoch 767 +2025-10-30 13:28:44.190741: Current learning rate: 0.0027 +2025-10-30 13:29:05.599018: train_loss -0.9923 +2025-10-30 13:29:05.601485: val_loss -0.8802 +2025-10-30 13:29:05.605230: Pseudo dice [np.float32(0.9799), np.float32(0.9876), np.float32(0.9941), np.float32(0.7761)] +2025-10-30 13:29:05.607962: Epoch time: 21.42 s +2025-10-30 13:29:06.746381: +2025-10-30 13:29:06.750202: Epoch 768 +2025-10-30 13:29:06.752149: Current learning rate: 0.00268 +2025-10-30 13:29:28.363184: train_loss -0.9925 +2025-10-30 13:29:28.378279: val_loss -0.8836 +2025-10-30 13:29:28.383197: Pseudo dice [np.float32(0.9812), np.float32(0.9872), np.float32(0.9944), np.float32(0.7901)] +2025-10-30 13:29:28.386268: Epoch time: 21.62 s +2025-10-30 13:29:29.638960: +2025-10-30 13:29:29.640874: Epoch 769 +2025-10-30 13:29:29.643044: Current learning rate: 0.00267 +2025-10-30 13:29:51.600379: train_loss -0.9928 +2025-10-30 13:29:51.602846: val_loss -0.8732 +2025-10-30 13:29:51.604534: Pseudo dice [np.float32(0.9802), np.float32(0.9878), np.float32(0.9938), np.float32(0.7701)] +2025-10-30 13:29:51.606122: Epoch time: 21.96 s +2025-10-30 13:29:52.982967: +2025-10-30 13:29:52.986244: Epoch 770 +2025-10-30 13:29:52.990398: Current learning rate: 0.00266 +2025-10-30 13:30:14.477939: train_loss -0.9929 +2025-10-30 13:30:14.481802: val_loss -0.8804 +2025-10-30 13:30:14.484363: Pseudo dice [np.float32(0.9813), np.float32(0.9879), np.float32(0.9942), np.float32(0.777)] +2025-10-30 13:30:14.486638: Epoch time: 21.5 s +2025-10-30 13:30:15.554377: +2025-10-30 13:30:15.557165: Epoch 771 +2025-10-30 13:30:15.559222: Current learning rate: 0.00265 +2025-10-30 13:30:35.629974: train_loss -0.9932 +2025-10-30 13:30:35.632224: val_loss -0.8884 +2025-10-30 13:30:35.635018: Pseudo dice [np.float32(0.9813), np.float32(0.9874), np.float32(0.9946), np.float32(0.795)] +2025-10-30 13:30:35.637320: Epoch time: 20.08 s +2025-10-30 13:30:36.769387: +2025-10-30 13:30:36.771505: Epoch 772 +2025-10-30 13:30:36.773279: Current learning rate: 0.00264 +2025-10-30 13:30:58.853299: train_loss -0.9927 +2025-10-30 13:30:58.857640: val_loss -0.8885 +2025-10-30 13:30:58.860205: Pseudo dice [np.float32(0.9838), np.float32(0.9894), np.float32(0.9943), np.float32(0.7844)] +2025-10-30 13:30:58.862441: Epoch time: 22.09 s +2025-10-30 13:31:01.001050: +2025-10-30 13:31:01.003854: Epoch 773 +2025-10-30 13:31:01.005669: Current learning rate: 0.00263 +2025-10-30 13:31:22.696845: train_loss -0.9925 +2025-10-30 13:31:22.699659: val_loss -0.8891 +2025-10-30 13:31:22.701480: Pseudo dice [np.float32(0.9828), np.float32(0.9878), np.float32(0.9939), np.float32(0.797)] +2025-10-30 13:31:22.705855: Epoch time: 21.7 s +2025-10-30 13:31:24.034222: +2025-10-30 13:31:24.036248: Epoch 774 +2025-10-30 13:31:24.038090: Current learning rate: 0.00262 +2025-10-30 13:31:45.889795: train_loss -0.9927 +2025-10-30 13:31:45.895060: val_loss -0.8872 +2025-10-30 13:31:45.898145: Pseudo dice [np.float32(0.9834), np.float32(0.9885), np.float32(0.9939), np.float32(0.7899)] +2025-10-30 13:31:45.903293: Epoch time: 21.86 s +2025-10-30 13:31:47.076929: +2025-10-30 13:31:47.086816: Epoch 775 +2025-10-30 13:31:47.092813: Current learning rate: 0.00261 +2025-10-30 13:32:08.680046: train_loss -0.9928 +2025-10-30 13:32:08.683473: val_loss -0.8768 +2025-10-30 13:32:08.686144: Pseudo dice [np.float32(0.9827), np.float32(0.9887), np.float32(0.9942), np.float32(0.7651)] +2025-10-30 13:32:08.687917: Epoch time: 21.6 s +2025-10-30 13:32:09.756381: +2025-10-30 13:32:09.758974: Epoch 776 +2025-10-30 13:32:09.762136: Current learning rate: 0.0026 +2025-10-30 13:32:31.270340: train_loss -0.9924 +2025-10-30 13:32:31.272832: val_loss -0.8882 +2025-10-30 13:32:31.274803: Pseudo dice [np.float32(0.9829), np.float32(0.9895), np.float32(0.9947), np.float32(0.7824)] +2025-10-30 13:32:31.276749: Epoch time: 21.52 s +2025-10-30 13:32:32.369905: +2025-10-30 13:32:32.372423: Epoch 777 +2025-10-30 13:32:32.374524: Current learning rate: 0.00259 +2025-10-30 13:32:53.180510: train_loss -0.9927 +2025-10-30 13:32:53.183503: val_loss -0.88 +2025-10-30 13:32:53.185250: Pseudo dice [np.float32(0.9827), np.float32(0.9876), np.float32(0.9936), np.float32(0.7734)] +2025-10-30 13:32:53.188187: Epoch time: 20.81 s +2025-10-30 13:32:54.484669: +2025-10-30 13:32:54.486786: Epoch 778 +2025-10-30 13:32:54.488650: Current learning rate: 0.00258 +2025-10-30 13:33:15.493958: train_loss -0.9924 +2025-10-30 13:33:15.497323: val_loss -0.8887 +2025-10-30 13:33:15.500356: Pseudo dice [np.float32(0.9829), np.float32(0.9882), np.float32(0.9943), np.float32(0.7923)] +2025-10-30 13:33:15.502402: Epoch time: 21.01 s +2025-10-30 13:33:16.679211: +2025-10-30 13:33:16.681782: Epoch 779 +2025-10-30 13:33:16.684818: Current learning rate: 0.00257 +2025-10-30 13:33:38.434856: train_loss -0.9924 +2025-10-30 13:33:38.439652: val_loss -0.879 +2025-10-30 13:33:38.443326: Pseudo dice [np.float32(0.9807), np.float32(0.988), np.float32(0.994), np.float32(0.7737)] +2025-10-30 13:33:38.449340: Epoch time: 21.76 s +2025-10-30 13:33:39.764269: +2025-10-30 13:33:39.766698: Epoch 780 +2025-10-30 13:33:39.769720: Current learning rate: 0.00256 +2025-10-30 13:34:02.026595: train_loss -0.9928 +2025-10-30 13:34:02.047632: val_loss -0.8777 +2025-10-30 13:34:02.051179: Pseudo dice [np.float32(0.9802), np.float32(0.9874), np.float32(0.9941), np.float32(0.7663)] +2025-10-30 13:34:02.061198: Epoch time: 22.26 s +2025-10-30 13:34:03.178615: +2025-10-30 13:34:03.180481: Epoch 781 +2025-10-30 13:34:03.182675: Current learning rate: 0.00255 +2025-10-30 13:34:24.964862: train_loss -0.9923 +2025-10-30 13:34:24.967319: val_loss -0.8784 +2025-10-30 13:34:24.968888: Pseudo dice [np.float32(0.9818), np.float32(0.9885), np.float32(0.994), np.float32(0.7705)] +2025-10-30 13:34:24.972110: Epoch time: 21.79 s +2025-10-30 13:34:26.261325: +2025-10-30 13:34:26.263680: Epoch 782 +2025-10-30 13:34:26.266095: Current learning rate: 0.00254 +2025-10-30 13:34:47.612508: train_loss -0.992 +2025-10-30 13:34:47.615014: val_loss -0.8821 +2025-10-30 13:34:47.616787: Pseudo dice [np.float32(0.9803), np.float32(0.9878), np.float32(0.9944), np.float32(0.7757)] +2025-10-30 13:34:47.618552: Epoch time: 21.35 s +2025-10-30 13:34:48.789007: +2025-10-30 13:34:48.791071: Epoch 783 +2025-10-30 13:34:48.793029: Current learning rate: 0.00253 +2025-10-30 13:35:10.046088: train_loss -0.9927 +2025-10-30 13:35:10.048493: val_loss -0.8769 +2025-10-30 13:35:10.050345: Pseudo dice [np.float32(0.9822), np.float32(0.9881), np.float32(0.994), np.float32(0.7614)] +2025-10-30 13:35:10.052489: Epoch time: 21.26 s +2025-10-30 13:35:11.135224: +2025-10-30 13:35:11.137945: Epoch 784 +2025-10-30 13:35:11.140576: Current learning rate: 0.00252 +2025-10-30 13:35:32.155154: train_loss -0.9931 +2025-10-30 13:35:32.158073: val_loss -0.8873 +2025-10-30 13:35:32.160563: Pseudo dice [np.float32(0.9841), np.float32(0.9897), np.float32(0.9943), np.float32(0.7807)] +2025-10-30 13:35:32.164303: Epoch time: 21.02 s +2025-10-30 13:35:33.449722: +2025-10-30 13:35:33.458790: Epoch 785 +2025-10-30 13:35:33.466864: Current learning rate: 0.00251 +2025-10-30 13:35:55.300654: train_loss -0.9928 +2025-10-30 13:35:55.316671: val_loss -0.8791 +2025-10-30 13:35:55.326030: Pseudo dice [np.float32(0.9815), np.float32(0.9876), np.float32(0.9937), np.float32(0.7747)] +2025-10-30 13:35:55.334296: Epoch time: 21.85 s +2025-10-30 13:35:56.672944: +2025-10-30 13:35:56.679044: Epoch 786 +2025-10-30 13:35:56.686691: Current learning rate: 0.0025 +2025-10-30 13:36:18.866917: train_loss -0.9931 +2025-10-30 13:36:18.869262: val_loss -0.8901 +2025-10-30 13:36:18.871067: Pseudo dice [np.float32(0.9812), np.float32(0.9883), np.float32(0.9947), np.float32(0.8014)] +2025-10-30 13:36:18.872669: Epoch time: 22.2 s +2025-10-30 13:36:20.079360: +2025-10-30 13:36:20.081265: Epoch 787 +2025-10-30 13:36:20.082913: Current learning rate: 0.00249 +2025-10-30 13:36:41.450116: train_loss -0.9936 +2025-10-30 13:36:41.456061: val_loss -0.8833 +2025-10-30 13:36:41.458643: Pseudo dice [np.float32(0.9792), np.float32(0.9872), np.float32(0.9942), np.float32(0.789)] +2025-10-30 13:36:41.460538: Epoch time: 21.37 s +2025-10-30 13:36:42.718309: +2025-10-30 13:36:42.720280: Epoch 788 +2025-10-30 13:36:42.722286: Current learning rate: 0.00248 +2025-10-30 13:37:04.263403: train_loss -0.9928 +2025-10-30 13:37:04.267102: val_loss -0.8796 +2025-10-30 13:37:04.269501: Pseudo dice [np.float32(0.9804), np.float32(0.988), np.float32(0.9944), np.float32(0.7767)] +2025-10-30 13:37:04.272238: Epoch time: 21.55 s +2025-10-30 13:37:06.562328: +2025-10-30 13:37:06.564817: Epoch 789 +2025-10-30 13:37:06.566534: Current learning rate: 0.00247 +2025-10-30 13:37:27.391361: train_loss -0.9934 +2025-10-30 13:37:27.396885: val_loss -0.8702 +2025-10-30 13:37:27.399153: Pseudo dice [np.float32(0.9809), np.float32(0.9874), np.float32(0.9935), np.float32(0.7673)] +2025-10-30 13:37:27.400859: Epoch time: 20.83 s +2025-10-30 13:37:28.339005: +2025-10-30 13:37:28.341061: Epoch 790 +2025-10-30 13:37:28.343584: Current learning rate: 0.00245 +2025-10-30 13:37:50.330487: train_loss -0.9929 +2025-10-30 13:37:50.332673: val_loss -0.8852 +2025-10-30 13:37:50.334183: Pseudo dice [np.float32(0.9819), np.float32(0.9883), np.float32(0.9943), np.float32(0.7822)] +2025-10-30 13:37:50.335650: Epoch time: 21.99 s +2025-10-30 13:37:51.488162: +2025-10-30 13:37:51.490818: Epoch 791 +2025-10-30 13:37:51.493307: Current learning rate: 0.00244 +2025-10-30 13:38:12.780556: train_loss -0.9933 +2025-10-30 13:38:12.785003: val_loss -0.8833 +2025-10-30 13:38:12.788632: Pseudo dice [np.float32(0.9845), np.float32(0.9891), np.float32(0.9942), np.float32(0.776)] +2025-10-30 13:38:12.791045: Epoch time: 21.29 s +2025-10-30 13:38:13.957076: +2025-10-30 13:38:13.963156: Epoch 792 +2025-10-30 13:38:13.966057: Current learning rate: 0.00243 +2025-10-30 13:38:36.024463: train_loss -0.993 +2025-10-30 13:38:36.026848: val_loss -0.8862 +2025-10-30 13:38:36.028760: Pseudo dice [np.float32(0.9843), np.float32(0.9889), np.float32(0.9943), np.float32(0.786)] +2025-10-30 13:38:36.034814: Epoch time: 22.07 s +2025-10-30 13:38:37.203941: +2025-10-30 13:38:37.206820: Epoch 793 +2025-10-30 13:38:37.209878: Current learning rate: 0.00242 +2025-10-30 13:38:59.027593: train_loss -0.993 +2025-10-30 13:38:59.031309: val_loss -0.8778 +2025-10-30 13:38:59.034428: Pseudo dice [np.float32(0.9815), np.float32(0.9887), np.float32(0.9942), np.float32(0.7688)] +2025-10-30 13:38:59.036740: Epoch time: 21.83 s +2025-10-30 13:39:00.417530: +2025-10-30 13:39:00.419667: Epoch 794 +2025-10-30 13:39:00.421595: Current learning rate: 0.00241 +2025-10-30 13:39:22.219817: train_loss -0.9932 +2025-10-30 13:39:22.222314: val_loss -0.8744 +2025-10-30 13:39:22.224254: Pseudo dice [np.float32(0.9808), np.float32(0.9882), np.float32(0.9941), np.float32(0.7597)] +2025-10-30 13:39:22.226157: Epoch time: 21.8 s +2025-10-30 13:39:23.357543: +2025-10-30 13:39:23.359314: Epoch 795 +2025-10-30 13:39:23.361248: Current learning rate: 0.0024 +2025-10-30 13:39:44.941086: train_loss -0.9932 +2025-10-30 13:39:44.943825: val_loss -0.88 +2025-10-30 13:39:44.945524: Pseudo dice [np.float32(0.9824), np.float32(0.9889), np.float32(0.9943), np.float32(0.7693)] +2025-10-30 13:39:44.947250: Epoch time: 21.59 s +2025-10-30 13:39:46.011102: +2025-10-30 13:39:46.012875: Epoch 796 +2025-10-30 13:39:46.014479: Current learning rate: 0.00239 +2025-10-30 13:40:08.187554: train_loss -0.9926 +2025-10-30 13:40:08.192595: val_loss -0.8822 +2025-10-30 13:40:08.195501: Pseudo dice [np.float32(0.9808), np.float32(0.9877), np.float32(0.9944), np.float32(0.7803)] +2025-10-30 13:40:08.197974: Epoch time: 22.18 s +2025-10-30 13:40:09.475032: +2025-10-30 13:40:09.477165: Epoch 797 +2025-10-30 13:40:09.479201: Current learning rate: 0.00238 +2025-10-30 13:40:30.549683: train_loss -0.9933 +2025-10-30 13:40:30.552627: val_loss -0.8877 +2025-10-30 13:40:30.554830: Pseudo dice [np.float32(0.982), np.float32(0.9882), np.float32(0.9942), np.float32(0.7954)] +2025-10-30 13:40:30.556543: Epoch time: 21.08 s +2025-10-30 13:40:31.650548: +2025-10-30 13:40:31.653009: Epoch 798 +2025-10-30 13:40:31.655207: Current learning rate: 0.00237 +2025-10-30 13:40:54.105320: train_loss -0.9929 +2025-10-30 13:40:54.108591: val_loss -0.8719 +2025-10-30 13:40:54.110293: Pseudo dice [np.float32(0.9814), np.float32(0.988), np.float32(0.9938), np.float32(0.7552)] +2025-10-30 13:40:54.112029: Epoch time: 22.46 s +2025-10-30 13:40:55.196333: +2025-10-30 13:40:55.199548: Epoch 799 +2025-10-30 13:40:55.201330: Current learning rate: 0.00236 +2025-10-30 13:41:17.531042: train_loss -0.9931 +2025-10-30 13:41:17.534330: val_loss -0.8879 +2025-10-30 13:41:17.537896: Pseudo dice [np.float32(0.9832), np.float32(0.9894), np.float32(0.9947), np.float32(0.7912)] +2025-10-30 13:41:17.540764: Epoch time: 22.34 s +2025-10-30 13:41:20.171335: +2025-10-30 13:41:20.173432: Epoch 800 +2025-10-30 13:41:20.174978: Current learning rate: 0.00235 +2025-10-30 13:41:42.147429: train_loss -0.9929 +2025-10-30 13:41:42.152643: val_loss -0.8916 +2025-10-30 13:41:42.155473: Pseudo dice [np.float32(0.9841), np.float32(0.9895), np.float32(0.9948), np.float32(0.7967)] +2025-10-30 13:41:42.158896: Epoch time: 21.98 s +2025-10-30 13:41:43.249015: +2025-10-30 13:41:43.252087: Epoch 801 +2025-10-30 13:41:43.255558: Current learning rate: 0.00234 +2025-10-30 13:42:04.907452: train_loss -0.9932 +2025-10-30 13:42:04.913697: val_loss -0.8827 +2025-10-30 13:42:04.921983: Pseudo dice [np.float32(0.9827), np.float32(0.9883), np.float32(0.9942), np.float32(0.78)] +2025-10-30 13:42:04.926642: Epoch time: 21.66 s +2025-10-30 13:42:06.342139: +2025-10-30 13:42:06.344412: Epoch 802 +2025-10-30 13:42:06.346183: Current learning rate: 0.00233 +2025-10-30 13:42:29.159425: train_loss -0.9932 +2025-10-30 13:42:29.166934: val_loss -0.8862 +2025-10-30 13:42:29.170308: Pseudo dice [np.float32(0.9821), np.float32(0.9886), np.float32(0.9947), np.float32(0.7974)] +2025-10-30 13:42:29.172514: Epoch time: 22.82 s +2025-10-30 13:42:30.503783: +2025-10-30 13:42:30.514384: Epoch 803 +2025-10-30 13:42:30.521225: Current learning rate: 0.00232 +2025-10-30 13:42:51.632540: train_loss -0.9934 +2025-10-30 13:42:51.636463: val_loss -0.884 +2025-10-30 13:42:51.638640: Pseudo dice [np.float32(0.9805), np.float32(0.988), np.float32(0.9943), np.float32(0.7855)] +2025-10-30 13:42:51.640745: Epoch time: 21.13 s +2025-10-30 13:42:53.077798: +2025-10-30 13:42:53.080135: Epoch 804 +2025-10-30 13:42:53.082602: Current learning rate: 0.00231 +2025-10-30 13:43:15.157080: train_loss -0.9933 +2025-10-30 13:43:15.159872: val_loss -0.8771 +2025-10-30 13:43:15.162220: Pseudo dice [np.float32(0.98), np.float32(0.9876), np.float32(0.9941), np.float32(0.7792)] +2025-10-30 13:43:15.166743: Epoch time: 22.08 s +2025-10-30 13:43:17.009333: +2025-10-30 13:43:17.012231: Epoch 805 +2025-10-30 13:43:17.014893: Current learning rate: 0.0023 +2025-10-30 13:43:38.989291: train_loss -0.9926 +2025-10-30 13:43:38.991716: val_loss -0.8787 +2025-10-30 13:43:38.993515: Pseudo dice [np.float32(0.9817), np.float32(0.9881), np.float32(0.9942), np.float32(0.7678)] +2025-10-30 13:43:38.995763: Epoch time: 21.98 s +2025-10-30 13:43:40.136923: +2025-10-30 13:43:40.139210: Epoch 806 +2025-10-30 13:43:40.141420: Current learning rate: 0.00229 +2025-10-30 13:44:02.170347: train_loss -0.9929 +2025-10-30 13:44:02.174003: val_loss -0.8762 +2025-10-30 13:44:02.177250: Pseudo dice [np.float32(0.9816), np.float32(0.9877), np.float32(0.9942), np.float32(0.7685)] +2025-10-30 13:44:02.179326: Epoch time: 22.04 s +2025-10-30 13:44:03.446265: +2025-10-30 13:44:03.448693: Epoch 807 +2025-10-30 13:44:03.451092: Current learning rate: 0.00228 +2025-10-30 13:44:24.806879: train_loss -0.9932 +2025-10-30 13:44:24.811793: val_loss -0.8775 +2025-10-30 13:44:24.816444: Pseudo dice [np.float32(0.9798), np.float32(0.9879), np.float32(0.994), np.float32(0.7782)] +2025-10-30 13:44:24.819514: Epoch time: 21.36 s +2025-10-30 13:44:26.123267: +2025-10-30 13:44:26.125533: Epoch 808 +2025-10-30 13:44:26.128025: Current learning rate: 0.00226 +2025-10-30 13:44:47.891355: train_loss -0.9932 +2025-10-30 13:44:47.894322: val_loss -0.8855 +2025-10-30 13:44:47.896273: Pseudo dice [np.float32(0.9815), np.float32(0.989), np.float32(0.9945), np.float32(0.7862)] +2025-10-30 13:44:47.898423: Epoch time: 21.77 s +2025-10-30 13:44:49.196232: +2025-10-30 13:44:49.198180: Epoch 809 +2025-10-30 13:44:49.200128: Current learning rate: 0.00225 +2025-10-30 13:45:11.843317: train_loss -0.9932 +2025-10-30 13:45:11.846787: val_loss -0.8705 +2025-10-30 13:45:11.848715: Pseudo dice [np.float32(0.9809), np.float32(0.9882), np.float32(0.9938), np.float32(0.7626)] +2025-10-30 13:45:11.850236: Epoch time: 22.65 s +2025-10-30 13:45:12.943929: +2025-10-30 13:45:12.945766: Epoch 810 +2025-10-30 13:45:12.947624: Current learning rate: 0.00224 +2025-10-30 13:45:36.817487: train_loss -0.9933 +2025-10-30 13:45:36.825905: val_loss -0.8721 +2025-10-30 13:45:36.830171: Pseudo dice [np.float32(0.9818), np.float32(0.9887), np.float32(0.9939), np.float32(0.7589)] +2025-10-30 13:45:36.832832: Epoch time: 23.88 s +2025-10-30 13:45:38.925360: +2025-10-30 13:45:38.934682: Epoch 811 +2025-10-30 13:45:38.945150: Current learning rate: 0.00223 +2025-10-30 13:46:00.718070: train_loss -0.9935 +2025-10-30 13:46:00.723071: val_loss -0.8749 +2025-10-30 13:46:00.724782: Pseudo dice [np.float32(0.9808), np.float32(0.9882), np.float32(0.9937), np.float32(0.7692)] +2025-10-30 13:46:00.726145: Epoch time: 21.79 s +2025-10-30 13:46:01.651338: +2025-10-30 13:46:01.655149: Epoch 812 +2025-10-30 13:46:01.659215: Current learning rate: 0.00222 +2025-10-30 13:46:23.729311: train_loss -0.9931 +2025-10-30 13:46:23.735008: val_loss -0.8781 +2025-10-30 13:46:23.736900: Pseudo dice [np.float32(0.9812), np.float32(0.988), np.float32(0.9945), np.float32(0.7739)] +2025-10-30 13:46:23.739361: Epoch time: 22.08 s +2025-10-30 13:46:25.025811: +2025-10-30 13:46:25.028060: Epoch 813 +2025-10-30 13:46:25.029873: Current learning rate: 0.00221 +2025-10-30 13:46:46.484009: train_loss -0.9929 +2025-10-30 13:46:46.486203: val_loss -0.8903 +2025-10-30 13:46:46.487832: Pseudo dice [np.float32(0.9827), np.float32(0.9886), np.float32(0.9943), np.float32(0.8006)] +2025-10-30 13:46:46.489388: Epoch time: 21.46 s +2025-10-30 13:46:47.567483: +2025-10-30 13:46:47.569801: Epoch 814 +2025-10-30 13:46:47.572261: Current learning rate: 0.0022 +2025-10-30 13:47:09.446223: train_loss -0.993 +2025-10-30 13:47:09.449092: val_loss -0.8862 +2025-10-30 13:47:09.451761: Pseudo dice [np.float32(0.9821), np.float32(0.9884), np.float32(0.9946), np.float32(0.793)] +2025-10-30 13:47:09.453564: Epoch time: 21.88 s +2025-10-30 13:47:10.634489: +2025-10-30 13:47:10.636476: Epoch 815 +2025-10-30 13:47:10.638116: Current learning rate: 0.00219 +2025-10-30 13:47:32.751372: train_loss -0.9934 +2025-10-30 13:47:32.754823: val_loss -0.8727 +2025-10-30 13:47:32.757150: Pseudo dice [np.float32(0.9808), np.float32(0.9867), np.float32(0.9938), np.float32(0.7642)] +2025-10-30 13:47:32.760197: Epoch time: 22.12 s +2025-10-30 13:47:33.966254: +2025-10-30 13:47:33.968264: Epoch 816 +2025-10-30 13:47:33.970198: Current learning rate: 0.00218 +2025-10-30 13:47:55.502341: train_loss -0.993 +2025-10-30 13:47:55.504798: val_loss -0.8863 +2025-10-30 13:47:55.506672: Pseudo dice [np.float32(0.982), np.float32(0.9888), np.float32(0.9948), np.float32(0.7822)] +2025-10-30 13:47:55.508275: Epoch time: 21.54 s +2025-10-30 13:47:56.847344: +2025-10-30 13:47:56.849572: Epoch 817 +2025-10-30 13:47:56.852615: Current learning rate: 0.00217 +2025-10-30 13:48:19.461456: train_loss -0.9937 +2025-10-30 13:48:19.464414: val_loss -0.879 +2025-10-30 13:48:19.466294: Pseudo dice [np.float32(0.9819), np.float32(0.989), np.float32(0.994), np.float32(0.7704)] +2025-10-30 13:48:19.467946: Epoch time: 22.62 s +2025-10-30 13:48:20.869534: +2025-10-30 13:48:20.872748: Epoch 818 +2025-10-30 13:48:20.874252: Current learning rate: 0.00216 +2025-10-30 13:48:42.906305: train_loss -0.994 +2025-10-30 13:48:42.909505: val_loss -0.8857 +2025-10-30 13:48:42.911516: Pseudo dice [np.float32(0.9813), np.float32(0.9882), np.float32(0.9946), np.float32(0.7912)] +2025-10-30 13:48:42.913527: Epoch time: 22.04 s +2025-10-30 13:48:44.078247: +2025-10-30 13:48:44.080433: Epoch 819 +2025-10-30 13:48:44.082099: Current learning rate: 0.00215 +2025-10-30 13:49:05.373120: train_loss -0.993 +2025-10-30 13:49:05.382589: val_loss -0.8791 +2025-10-30 13:49:05.390463: Pseudo dice [np.float32(0.9802), np.float32(0.9876), np.float32(0.9941), np.float32(0.7732)] +2025-10-30 13:49:05.396037: Epoch time: 21.3 s +2025-10-30 13:49:06.613516: +2025-10-30 13:49:06.617236: Epoch 820 +2025-10-30 13:49:06.620418: Current learning rate: 0.00214 +2025-10-30 13:49:28.786489: train_loss -0.9936 +2025-10-30 13:49:28.789141: val_loss -0.8782 +2025-10-30 13:49:28.791270: Pseudo dice [np.float32(0.9804), np.float32(0.9863), np.float32(0.994), np.float32(0.7789)] +2025-10-30 13:49:28.793010: Epoch time: 22.17 s +2025-10-30 13:49:29.886837: +2025-10-30 13:49:29.890793: Epoch 821 +2025-10-30 13:49:29.894585: Current learning rate: 0.00213 +2025-10-30 13:49:52.153056: train_loss -0.9931 +2025-10-30 13:49:52.155869: val_loss -0.8766 +2025-10-30 13:49:52.158247: Pseudo dice [np.float32(0.9798), np.float32(0.988), np.float32(0.9943), np.float32(0.7834)] +2025-10-30 13:49:52.160525: Epoch time: 22.27 s +2025-10-30 13:49:54.078972: +2025-10-30 13:49:54.081043: Epoch 822 +2025-10-30 13:49:54.086327: Current learning rate: 0.00212 +2025-10-30 13:50:15.937622: train_loss -0.9933 +2025-10-30 13:50:15.940674: val_loss -0.8815 +2025-10-30 13:50:15.942791: Pseudo dice [np.float32(0.9809), np.float32(0.988), np.float32(0.9944), np.float32(0.7765)] +2025-10-30 13:50:15.945285: Epoch time: 21.86 s +2025-10-30 13:50:16.949426: +2025-10-30 13:50:16.951404: Epoch 823 +2025-10-30 13:50:16.953928: Current learning rate: 0.0021 +2025-10-30 13:50:37.965797: train_loss -0.9932 +2025-10-30 13:50:37.969173: val_loss -0.8766 +2025-10-30 13:50:37.970779: Pseudo dice [np.float32(0.9813), np.float32(0.9878), np.float32(0.994), np.float32(0.7723)] +2025-10-30 13:50:37.972366: Epoch time: 21.02 s +2025-10-30 13:50:39.231449: +2025-10-30 13:50:39.236747: Epoch 824 +2025-10-30 13:50:39.247692: Current learning rate: 0.00209 +2025-10-30 13:51:01.260380: train_loss -0.9929 +2025-10-30 13:51:01.263969: val_loss -0.8803 +2025-10-30 13:51:01.266186: Pseudo dice [np.float32(0.9803), np.float32(0.9881), np.float32(0.9945), np.float32(0.7801)] +2025-10-30 13:51:01.268168: Epoch time: 22.03 s +2025-10-30 13:51:02.439015: +2025-10-30 13:51:02.441768: Epoch 825 +2025-10-30 13:51:02.443567: Current learning rate: 0.00208 +2025-10-30 13:51:23.521775: train_loss -0.9936 +2025-10-30 13:51:23.525431: val_loss -0.8816 +2025-10-30 13:51:23.528038: Pseudo dice [np.float32(0.9821), np.float32(0.9891), np.float32(0.9945), np.float32(0.7804)] +2025-10-30 13:51:23.529950: Epoch time: 21.08 s +2025-10-30 13:51:24.600835: +2025-10-30 13:51:24.603023: Epoch 826 +2025-10-30 13:51:24.606201: Current learning rate: 0.00207 +2025-10-30 13:51:46.509982: train_loss -0.9937 +2025-10-30 13:51:46.513236: val_loss -0.8844 +2025-10-30 13:51:46.514957: Pseudo dice [np.float32(0.9817), np.float32(0.9887), np.float32(0.9947), np.float32(0.7859)] +2025-10-30 13:51:46.516599: Epoch time: 21.91 s +2025-10-30 13:51:47.563839: +2025-10-30 13:51:47.567772: Epoch 827 +2025-10-30 13:51:47.569531: Current learning rate: 0.00206 +2025-10-30 13:52:09.297666: train_loss -0.9936 +2025-10-30 13:52:09.302418: val_loss -0.8791 +2025-10-30 13:52:09.305503: Pseudo dice [np.float32(0.9813), np.float32(0.9882), np.float32(0.9939), np.float32(0.7739)] +2025-10-30 13:52:09.308328: Epoch time: 21.74 s +2025-10-30 13:52:10.594447: +2025-10-30 13:52:10.596538: Epoch 828 +2025-10-30 13:52:10.598213: Current learning rate: 0.00205 +2025-10-30 13:52:32.147438: train_loss -0.9937 +2025-10-30 13:52:32.149903: val_loss -0.8867 +2025-10-30 13:52:32.151829: Pseudo dice [np.float32(0.9801), np.float32(0.9873), np.float32(0.9947), np.float32(0.7992)] +2025-10-30 13:52:32.154193: Epoch time: 21.55 s +2025-10-30 13:52:33.312977: +2025-10-30 13:52:33.317642: Epoch 829 +2025-10-30 13:52:33.321111: Current learning rate: 0.00204 +2025-10-30 13:52:53.989601: train_loss -0.9933 +2025-10-30 13:52:53.992740: val_loss -0.885 +2025-10-30 13:52:53.994265: Pseudo dice [np.float32(0.984), np.float32(0.9894), np.float32(0.9942), np.float32(0.7777)] +2025-10-30 13:52:53.998161: Epoch time: 20.68 s +2025-10-30 13:52:55.214022: +2025-10-30 13:52:55.216390: Epoch 830 +2025-10-30 13:52:55.218164: Current learning rate: 0.00203 +2025-10-30 13:53:17.523887: train_loss -0.9935 +2025-10-30 13:53:17.532711: val_loss -0.8788 +2025-10-30 13:53:17.538766: Pseudo dice [np.float32(0.9816), np.float32(0.9882), np.float32(0.9945), np.float32(0.7736)] +2025-10-30 13:53:17.544960: Epoch time: 22.31 s +2025-10-30 13:53:18.912394: +2025-10-30 13:53:18.917905: Epoch 831 +2025-10-30 13:53:18.920353: Current learning rate: 0.00202 +2025-10-30 13:53:40.017962: train_loss -0.9934 +2025-10-30 13:53:40.024341: val_loss -0.877 +2025-10-30 13:53:40.025911: Pseudo dice [np.float32(0.9816), np.float32(0.9893), np.float32(0.9946), np.float32(0.7656)] +2025-10-30 13:53:40.027528: Epoch time: 21.11 s +2025-10-30 13:53:41.116053: +2025-10-30 13:53:41.119462: Epoch 832 +2025-10-30 13:53:41.122486: Current learning rate: 0.00201 +2025-10-30 13:54:03.069070: train_loss -0.9933 +2025-10-30 13:54:03.073334: val_loss -0.8852 +2025-10-30 13:54:03.075180: Pseudo dice [np.float32(0.9811), np.float32(0.9889), np.float32(0.9949), np.float32(0.7906)] +2025-10-30 13:54:03.076977: Epoch time: 21.95 s +2025-10-30 13:54:04.148719: +2025-10-30 13:54:04.153137: Epoch 833 +2025-10-30 13:54:04.155092: Current learning rate: 0.002 +2025-10-30 13:54:26.021708: train_loss -0.9929 +2025-10-30 13:54:26.024815: val_loss -0.8785 +2025-10-30 13:54:26.027441: Pseudo dice [np.float32(0.9819), np.float32(0.9877), np.float32(0.9941), np.float32(0.7726)] +2025-10-30 13:54:26.030995: Epoch time: 21.87 s +2025-10-30 13:54:27.316240: +2025-10-30 13:54:27.318721: Epoch 834 +2025-10-30 13:54:27.320634: Current learning rate: 0.00199 +2025-10-30 13:54:49.246679: train_loss -0.9931 +2025-10-30 13:54:49.252134: val_loss -0.884 +2025-10-30 13:54:49.256239: Pseudo dice [np.float32(0.9822), np.float32(0.9893), np.float32(0.9942), np.float32(0.7883)] +2025-10-30 13:54:49.259476: Epoch time: 21.93 s +2025-10-30 13:54:50.367503: +2025-10-30 13:54:50.370322: Epoch 835 +2025-10-30 13:54:50.372431: Current learning rate: 0.00198 +2025-10-30 13:55:12.003514: train_loss -0.9938 +2025-10-30 13:55:12.012541: val_loss -0.8783 +2025-10-30 13:55:12.014886: Pseudo dice [np.float32(0.9817), np.float32(0.9881), np.float32(0.9941), np.float32(0.7686)] +2025-10-30 13:55:12.018340: Epoch time: 21.64 s +2025-10-30 13:55:13.033008: +2025-10-30 13:55:13.036567: Epoch 836 +2025-10-30 13:55:13.038459: Current learning rate: 0.00196 +2025-10-30 13:55:34.199611: train_loss -0.9934 +2025-10-30 13:55:34.207308: val_loss -0.8822 +2025-10-30 13:55:34.211517: Pseudo dice [np.float32(0.9808), np.float32(0.9871), np.float32(0.9947), np.float32(0.7893)] +2025-10-30 13:55:34.215267: Epoch time: 21.17 s +2025-10-30 13:55:35.364222: +2025-10-30 13:55:35.366646: Epoch 837 +2025-10-30 13:55:35.368396: Current learning rate: 0.00195 +2025-10-30 13:55:56.631456: train_loss -0.9933 +2025-10-30 13:55:56.635960: val_loss -0.8765 +2025-10-30 13:55:56.637918: Pseudo dice [np.float32(0.9804), np.float32(0.9878), np.float32(0.9942), np.float32(0.7734)] +2025-10-30 13:55:56.640516: Epoch time: 21.27 s +2025-10-30 13:55:57.954943: +2025-10-30 13:55:57.958243: Epoch 838 +2025-10-30 13:55:57.960297: Current learning rate: 0.00194 +2025-10-30 13:56:19.403592: train_loss -0.9933 +2025-10-30 13:56:19.406190: val_loss -0.8801 +2025-10-30 13:56:19.407827: Pseudo dice [np.float32(0.9811), np.float32(0.9878), np.float32(0.9945), np.float32(0.7816)] +2025-10-30 13:56:19.411160: Epoch time: 21.45 s +2025-10-30 13:56:20.539400: +2025-10-30 13:56:20.542829: Epoch 839 +2025-10-30 13:56:20.545506: Current learning rate: 0.00193 +2025-10-30 13:56:42.680886: train_loss -0.9934 +2025-10-30 13:56:42.684252: val_loss -0.8907 +2025-10-30 13:56:42.686799: Pseudo dice [np.float32(0.9823), np.float32(0.9889), np.float32(0.9948), np.float32(0.7968)] +2025-10-30 13:56:42.688776: Epoch time: 22.14 s +2025-10-30 13:56:44.396339: +2025-10-30 13:56:44.398606: Epoch 840 +2025-10-30 13:56:44.400318: Current learning rate: 0.00192 +2025-10-30 13:57:06.584119: train_loss -0.9938 +2025-10-30 13:57:06.612416: val_loss -0.8881 +2025-10-30 13:57:06.614516: Pseudo dice [np.float32(0.9816), np.float32(0.9891), np.float32(0.9949), np.float32(0.7947)] +2025-10-30 13:57:06.616583: Epoch time: 22.19 s +2025-10-30 13:57:08.039302: +2025-10-30 13:57:08.041807: Epoch 841 +2025-10-30 13:57:08.043904: Current learning rate: 0.00191 +2025-10-30 13:57:30.024105: train_loss -0.9933 +2025-10-30 13:57:30.027191: val_loss -0.8811 +2025-10-30 13:57:30.029417: Pseudo dice [np.float32(0.9828), np.float32(0.9892), np.float32(0.9946), np.float32(0.776)] +2025-10-30 13:57:30.030946: Epoch time: 21.99 s +2025-10-30 13:57:31.215511: +2025-10-30 13:57:31.217549: Epoch 842 +2025-10-30 13:57:31.219236: Current learning rate: 0.0019 +2025-10-30 13:57:52.502699: train_loss -0.9934 +2025-10-30 13:57:52.506607: val_loss -0.8796 +2025-10-30 13:57:52.509096: Pseudo dice [np.float32(0.9819), np.float32(0.9887), np.float32(0.9946), np.float32(0.7713)] +2025-10-30 13:57:52.510831: Epoch time: 21.29 s +2025-10-30 13:57:53.571289: +2025-10-30 13:57:53.574279: Epoch 843 +2025-10-30 13:57:53.576601: Current learning rate: 0.00189 +2025-10-30 13:58:14.535366: train_loss -0.9937 +2025-10-30 13:58:14.538578: val_loss -0.8843 +2025-10-30 13:58:14.540810: Pseudo dice [np.float32(0.9813), np.float32(0.9884), np.float32(0.9944), np.float32(0.788)] +2025-10-30 13:58:14.543278: Epoch time: 20.97 s +2025-10-30 13:58:15.890808: +2025-10-30 13:58:15.893064: Epoch 844 +2025-10-30 13:58:15.894846: Current learning rate: 0.00188 +2025-10-30 13:58:37.648171: train_loss -0.9938 +2025-10-30 13:58:37.651500: val_loss -0.884 +2025-10-30 13:58:37.653689: Pseudo dice [np.float32(0.9825), np.float32(0.9887), np.float32(0.9946), np.float32(0.7853)] +2025-10-30 13:58:37.655816: Epoch time: 21.76 s +2025-10-30 13:58:38.695482: +2025-10-30 13:58:38.698267: Epoch 845 +2025-10-30 13:58:38.701378: Current learning rate: 0.00187 +2025-10-30 13:59:00.862404: train_loss -0.9938 +2025-10-30 13:59:00.866836: val_loss -0.8738 +2025-10-30 13:59:00.869883: Pseudo dice [np.float32(0.9797), np.float32(0.9874), np.float32(0.994), np.float32(0.7675)] +2025-10-30 13:59:00.872057: Epoch time: 22.17 s +2025-10-30 13:59:02.089200: +2025-10-30 13:59:02.091677: Epoch 846 +2025-10-30 13:59:02.094566: Current learning rate: 0.00186 +2025-10-30 13:59:24.331162: train_loss -0.9938 +2025-10-30 13:59:24.341289: val_loss -0.8808 +2025-10-30 13:59:24.350829: Pseudo dice [np.float32(0.9814), np.float32(0.9889), np.float32(0.9947), np.float32(0.7758)] +2025-10-30 13:59:24.358228: Epoch time: 22.24 s +2025-10-30 13:59:25.498712: +2025-10-30 13:59:25.502024: Epoch 847 +2025-10-30 13:59:25.503752: Current learning rate: 0.00185 +2025-10-30 13:59:47.168176: train_loss -0.9935 +2025-10-30 13:59:47.170901: val_loss -0.8849 +2025-10-30 13:59:47.173307: Pseudo dice [np.float32(0.9807), np.float32(0.9885), np.float32(0.9948), np.float32(0.7902)] +2025-10-30 13:59:47.175334: Epoch time: 21.67 s +2025-10-30 13:59:48.335610: +2025-10-30 13:59:48.337693: Epoch 848 +2025-10-30 13:59:48.339375: Current learning rate: 0.00184 +2025-10-30 14:00:10.189070: train_loss -0.993 +2025-10-30 14:00:10.192021: val_loss -0.8805 +2025-10-30 14:00:10.194055: Pseudo dice [np.float32(0.9815), np.float32(0.9889), np.float32(0.9939), np.float32(0.7742)] +2025-10-30 14:00:10.195722: Epoch time: 21.86 s +2025-10-30 14:00:11.248596: +2025-10-30 14:00:11.251559: Epoch 849 +2025-10-30 14:00:11.254450: Current learning rate: 0.00182 +2025-10-30 14:00:31.438709: train_loss -0.9937 +2025-10-30 14:00:31.441405: val_loss -0.8807 +2025-10-30 14:00:31.443518: Pseudo dice [np.float32(0.9811), np.float32(0.9879), np.float32(0.9945), np.float32(0.7795)] +2025-10-30 14:00:31.445626: Epoch time: 20.19 s +2025-10-30 14:00:33.868510: +2025-10-30 14:00:33.870469: Epoch 850 +2025-10-30 14:00:33.872699: Current learning rate: 0.00181 +2025-10-30 14:00:56.057038: train_loss -0.9935 +2025-10-30 14:00:56.063388: val_loss -0.8882 +2025-10-30 14:00:56.065648: Pseudo dice [np.float32(0.981), np.float32(0.9877), np.float32(0.9947), np.float32(0.798)] +2025-10-30 14:00:56.067456: Epoch time: 22.19 s +2025-10-30 14:00:57.171141: +2025-10-30 14:00:57.174706: Epoch 851 +2025-10-30 14:00:57.177039: Current learning rate: 0.0018 +2025-10-30 14:01:19.371006: train_loss -0.9939 +2025-10-30 14:01:19.374134: val_loss -0.8844 +2025-10-30 14:01:19.375823: Pseudo dice [np.float32(0.981), np.float32(0.9884), np.float32(0.9945), np.float32(0.7851)] +2025-10-30 14:01:19.377470: Epoch time: 22.2 s +2025-10-30 14:01:20.418338: +2025-10-30 14:01:20.420815: Epoch 852 +2025-10-30 14:01:20.422581: Current learning rate: 0.00179 +2025-10-30 14:01:42.372536: train_loss -0.9932 +2025-10-30 14:01:42.374892: val_loss -0.8885 +2025-10-30 14:01:42.376673: Pseudo dice [np.float32(0.9816), np.float32(0.9885), np.float32(0.995), np.float32(0.7932)] +2025-10-30 14:01:42.378061: Epoch time: 21.96 s +2025-10-30 14:01:43.451647: +2025-10-30 14:01:43.453919: Epoch 853 +2025-10-30 14:01:43.456178: Current learning rate: 0.00178 +2025-10-30 14:02:05.252911: train_loss -0.9935 +2025-10-30 14:02:05.257776: val_loss -0.8771 +2025-10-30 14:02:05.262236: Pseudo dice [np.float32(0.9804), np.float32(0.9874), np.float32(0.9941), np.float32(0.7688)] +2025-10-30 14:02:05.264624: Epoch time: 21.8 s +2025-10-30 14:02:06.429731: +2025-10-30 14:02:06.434778: Epoch 854 +2025-10-30 14:02:06.437928: Current learning rate: 0.00177 +2025-10-30 14:02:28.373694: train_loss -0.9935 +2025-10-30 14:02:28.378350: val_loss -0.8738 +2025-10-30 14:02:28.382321: Pseudo dice [np.float32(0.9804), np.float32(0.9871), np.float32(0.9937), np.float32(0.768)] +2025-10-30 14:02:28.385615: Epoch time: 21.95 s +2025-10-30 14:02:29.777173: +2025-10-30 14:02:29.779283: Epoch 855 +2025-10-30 14:02:29.785635: Current learning rate: 0.00176 +2025-10-30 14:02:49.975426: train_loss -0.9933 +2025-10-30 14:02:49.978207: val_loss -0.8768 +2025-10-30 14:02:49.980352: Pseudo dice [np.float32(0.9801), np.float32(0.9882), np.float32(0.9941), np.float32(0.7687)] +2025-10-30 14:02:49.982765: Epoch time: 20.2 s +2025-10-30 14:02:51.223744: +2025-10-30 14:02:51.226724: Epoch 856 +2025-10-30 14:02:51.229167: Current learning rate: 0.00175 +2025-10-30 14:03:13.380976: train_loss -0.9939 +2025-10-30 14:03:13.383408: val_loss -0.8853 +2025-10-30 14:03:13.385222: Pseudo dice [np.float32(0.9816), np.float32(0.9888), np.float32(0.9949), np.float32(0.7841)] +2025-10-30 14:03:13.386986: Epoch time: 22.16 s +2025-10-30 14:03:15.783942: +2025-10-30 14:03:15.791064: Epoch 857 +2025-10-30 14:03:15.797035: Current learning rate: 0.00174 +2025-10-30 14:03:37.486581: train_loss -0.9935 +2025-10-30 14:03:37.495936: val_loss -0.8792 +2025-10-30 14:03:37.502565: Pseudo dice [np.float32(0.9819), np.float32(0.989), np.float32(0.9941), np.float32(0.76)] +2025-10-30 14:03:37.508375: Epoch time: 21.7 s +2025-10-30 14:03:38.552785: +2025-10-30 14:03:38.555050: Epoch 858 +2025-10-30 14:03:38.557155: Current learning rate: 0.00173 +2025-10-30 14:04:00.395606: train_loss -0.9937 +2025-10-30 14:04:00.402350: val_loss -0.8786 +2025-10-30 14:04:00.406338: Pseudo dice [np.float32(0.9802), np.float32(0.9882), np.float32(0.9938), np.float32(0.7754)] +2025-10-30 14:04:00.408237: Epoch time: 21.84 s +2025-10-30 14:04:01.686030: +2025-10-30 14:04:01.688014: Epoch 859 +2025-10-30 14:04:01.689574: Current learning rate: 0.00172 +2025-10-30 14:04:23.812336: train_loss -0.9937 +2025-10-30 14:04:23.815189: val_loss -0.8763 +2025-10-30 14:04:23.817152: Pseudo dice [np.float32(0.9804), np.float32(0.9886), np.float32(0.9941), np.float32(0.7668)] +2025-10-30 14:04:23.819048: Epoch time: 22.13 s +2025-10-30 14:04:24.918572: +2025-10-30 14:04:24.920539: Epoch 860 +2025-10-30 14:04:24.922480: Current learning rate: 0.0017 +2025-10-30 14:04:46.926489: train_loss -0.9934 +2025-10-30 14:04:46.929544: val_loss -0.8801 +2025-10-30 14:04:46.932916: Pseudo dice [np.float32(0.9809), np.float32(0.9889), np.float32(0.9945), np.float32(0.7731)] +2025-10-30 14:04:46.934750: Epoch time: 22.01 s +2025-10-30 14:04:48.162061: +2025-10-30 14:04:48.164253: Epoch 861 +2025-10-30 14:04:48.166061: Current learning rate: 0.00169 +2025-10-30 14:05:08.670304: train_loss -0.9937 +2025-10-30 14:05:08.673230: val_loss -0.8692 +2025-10-30 14:05:08.675210: Pseudo dice [np.float32(0.9802), np.float32(0.9876), np.float32(0.9938), np.float32(0.7529)] +2025-10-30 14:05:08.677428: Epoch time: 20.51 s +2025-10-30 14:05:09.708560: +2025-10-30 14:05:09.710489: Epoch 862 +2025-10-30 14:05:09.712242: Current learning rate: 0.00168 +2025-10-30 14:05:31.606950: train_loss -0.9941 +2025-10-30 14:05:31.609370: val_loss -0.8781 +2025-10-30 14:05:31.613791: Pseudo dice [np.float32(0.9811), np.float32(0.9887), np.float32(0.9943), np.float32(0.7739)] +2025-10-30 14:05:31.615607: Epoch time: 21.9 s +2025-10-30 14:05:32.993572: +2025-10-30 14:05:32.997314: Epoch 863 +2025-10-30 14:05:33.000427: Current learning rate: 0.00167 +2025-10-30 14:05:54.932630: train_loss -0.9938 +2025-10-30 14:05:54.936035: val_loss -0.8733 +2025-10-30 14:05:54.938789: Pseudo dice [np.float32(0.9809), np.float32(0.9882), np.float32(0.9938), np.float32(0.7692)] +2025-10-30 14:05:54.942917: Epoch time: 21.94 s +2025-10-30 14:05:56.072574: +2025-10-30 14:05:56.075183: Epoch 864 +2025-10-30 14:05:56.077339: Current learning rate: 0.00166 +2025-10-30 14:06:17.557473: train_loss -0.9939 +2025-10-30 14:06:17.563390: val_loss -0.8818 +2025-10-30 14:06:17.565631: Pseudo dice [np.float32(0.9813), np.float32(0.9878), np.float32(0.994), np.float32(0.7827)] +2025-10-30 14:06:17.567671: Epoch time: 21.49 s +2025-10-30 14:06:18.621970: +2025-10-30 14:06:18.624323: Epoch 865 +2025-10-30 14:06:18.626413: Current learning rate: 0.00165 +2025-10-30 14:06:40.710169: train_loss -0.9937 +2025-10-30 14:06:40.713295: val_loss -0.877 +2025-10-30 14:06:40.716669: Pseudo dice [np.float32(0.9814), np.float32(0.9887), np.float32(0.9939), np.float32(0.7711)] +2025-10-30 14:06:40.719054: Epoch time: 22.09 s +2025-10-30 14:06:42.050632: +2025-10-30 14:06:42.054180: Epoch 866 +2025-10-30 14:06:42.056560: Current learning rate: 0.00164 +2025-10-30 14:07:03.894457: train_loss -0.9938 +2025-10-30 14:07:03.902233: val_loss -0.8783 +2025-10-30 14:07:03.907011: Pseudo dice [np.float32(0.9798), np.float32(0.9875), np.float32(0.9941), np.float32(0.785)] +2025-10-30 14:07:03.909888: Epoch time: 21.85 s +2025-10-30 14:07:04.959996: +2025-10-30 14:07:04.963262: Epoch 867 +2025-10-30 14:07:04.966475: Current learning rate: 0.00163 +2025-10-30 14:07:24.995018: train_loss -0.9937 +2025-10-30 14:07:24.999600: val_loss -0.878 +2025-10-30 14:07:25.002426: Pseudo dice [np.float32(0.9822), np.float32(0.9871), np.float32(0.9939), np.float32(0.7796)] +2025-10-30 14:07:25.004597: Epoch time: 20.04 s +2025-10-30 14:07:26.233632: +2025-10-30 14:07:26.236322: Epoch 868 +2025-10-30 14:07:26.238399: Current learning rate: 0.00162 +2025-10-30 14:07:47.823821: train_loss -0.9939 +2025-10-30 14:07:47.830507: val_loss -0.8824 +2025-10-30 14:07:47.832006: Pseudo dice [np.float32(0.9815), np.float32(0.9881), np.float32(0.9944), np.float32(0.7849)] +2025-10-30 14:07:47.833976: Epoch time: 21.59 s +2025-10-30 14:07:49.226557: +2025-10-30 14:07:49.228565: Epoch 869 +2025-10-30 14:07:49.232752: Current learning rate: 0.00161 +2025-10-30 14:08:11.318246: train_loss -0.9933 +2025-10-30 14:08:11.324358: val_loss -0.8794 +2025-10-30 14:08:11.327380: Pseudo dice [np.float32(0.9818), np.float32(0.9884), np.float32(0.9941), np.float32(0.7784)] +2025-10-30 14:08:11.329613: Epoch time: 22.09 s +2025-10-30 14:08:12.582067: +2025-10-30 14:08:12.585837: Epoch 870 +2025-10-30 14:08:12.588371: Current learning rate: 0.00159 +2025-10-30 14:08:34.449273: train_loss -0.9935 +2025-10-30 14:08:34.457275: val_loss -0.8807 +2025-10-30 14:08:34.461195: Pseudo dice [np.float32(0.9816), np.float32(0.9885), np.float32(0.9941), np.float32(0.7761)] +2025-10-30 14:08:34.466798: Epoch time: 21.87 s +2025-10-30 14:08:35.608760: +2025-10-30 14:08:35.612170: Epoch 871 +2025-10-30 14:08:35.614260: Current learning rate: 0.00158 +2025-10-30 14:08:57.863535: train_loss -0.9936 +2025-10-30 14:08:57.868168: val_loss -0.8831 +2025-10-30 14:08:57.870759: Pseudo dice [np.float32(0.9822), np.float32(0.9884), np.float32(0.9944), np.float32(0.7828)] +2025-10-30 14:08:57.872859: Epoch time: 22.26 s +2025-10-30 14:08:59.098370: +2025-10-30 14:08:59.100985: Epoch 872 +2025-10-30 14:08:59.102837: Current learning rate: 0.00157 +2025-10-30 14:09:20.764812: train_loss -0.9936 +2025-10-30 14:09:20.768211: val_loss -0.8827 +2025-10-30 14:09:20.770041: Pseudo dice [np.float32(0.9837), np.float32(0.9895), np.float32(0.9941), np.float32(0.7771)] +2025-10-30 14:09:20.772023: Epoch time: 21.67 s +2025-10-30 14:09:21.883952: +2025-10-30 14:09:21.886498: Epoch 873 +2025-10-30 14:09:21.888237: Current learning rate: 0.00156 +2025-10-30 14:09:43.155248: train_loss -0.994 +2025-10-30 14:09:43.157664: val_loss -0.8833 +2025-10-30 14:09:43.162860: Pseudo dice [np.float32(0.9812), np.float32(0.988), np.float32(0.9942), np.float32(0.7817)] +2025-10-30 14:09:43.166057: Epoch time: 21.27 s +2025-10-30 14:09:44.381885: +2025-10-30 14:09:44.386373: Epoch 874 +2025-10-30 14:09:44.388540: Current learning rate: 0.00155 +2025-10-30 14:10:05.168830: train_loss -0.9935 +2025-10-30 14:10:05.174511: val_loss -0.8802 +2025-10-30 14:10:05.177596: Pseudo dice [np.float32(0.981), np.float32(0.9884), np.float32(0.9945), np.float32(0.7796)] +2025-10-30 14:10:05.182715: Epoch time: 20.79 s +2025-10-30 14:10:07.446647: +2025-10-30 14:10:07.448953: Epoch 875 +2025-10-30 14:10:07.451810: Current learning rate: 0.00154 +2025-10-30 14:10:29.025700: train_loss -0.9942 +2025-10-30 14:10:29.030245: val_loss -0.8767 +2025-10-30 14:10:29.031816: Pseudo dice [np.float32(0.9807), np.float32(0.9884), np.float32(0.9943), np.float32(0.7699)] +2025-10-30 14:10:29.033509: Epoch time: 21.58 s +2025-10-30 14:10:30.112067: +2025-10-30 14:10:30.117584: Epoch 876 +2025-10-30 14:10:30.123128: Current learning rate: 0.00153 +2025-10-30 14:10:51.716953: train_loss -0.9941 +2025-10-30 14:10:51.720036: val_loss -0.8822 +2025-10-30 14:10:51.721985: Pseudo dice [np.float32(0.9823), np.float32(0.9887), np.float32(0.994), np.float32(0.7796)] +2025-10-30 14:10:51.724767: Epoch time: 21.61 s +2025-10-30 14:10:52.976945: +2025-10-30 14:10:52.980092: Epoch 877 +2025-10-30 14:10:52.981805: Current learning rate: 0.00152 +2025-10-30 14:11:14.596080: train_loss -0.9939 +2025-10-30 14:11:14.599686: val_loss -0.8739 +2025-10-30 14:11:14.602004: Pseudo dice [np.float32(0.9827), np.float32(0.9887), np.float32(0.9935), np.float32(0.7593)] +2025-10-30 14:11:14.604358: Epoch time: 21.62 s +2025-10-30 14:11:15.944502: +2025-10-30 14:11:15.948591: Epoch 878 +2025-10-30 14:11:15.951530: Current learning rate: 0.00151 +2025-10-30 14:11:37.938463: train_loss -0.994 +2025-10-30 14:11:37.942894: val_loss -0.8719 +2025-10-30 14:11:37.946578: Pseudo dice [np.float32(0.9796), np.float32(0.9866), np.float32(0.9937), np.float32(0.7659)] +2025-10-30 14:11:37.949439: Epoch time: 22.0 s +2025-10-30 14:11:39.027756: +2025-10-30 14:11:39.029848: Epoch 879 +2025-10-30 14:11:39.031832: Current learning rate: 0.00149 +2025-10-30 14:12:00.313194: train_loss -0.9941 +2025-10-30 14:12:00.317284: val_loss -0.885 +2025-10-30 14:12:00.320181: Pseudo dice [np.float32(0.9833), np.float32(0.9894), np.float32(0.9942), np.float32(0.781)] +2025-10-30 14:12:00.322150: Epoch time: 21.29 s +2025-10-30 14:12:01.550375: +2025-10-30 14:12:01.553251: Epoch 880 +2025-10-30 14:12:01.555332: Current learning rate: 0.00148 +2025-10-30 14:12:23.550132: train_loss -0.9936 +2025-10-30 14:12:23.554640: val_loss -0.8885 +2025-10-30 14:12:23.557117: Pseudo dice [np.float32(0.9806), np.float32(0.9884), np.float32(0.9947), np.float32(0.7964)] +2025-10-30 14:12:23.559035: Epoch time: 22.0 s +2025-10-30 14:12:24.672735: +2025-10-30 14:12:24.674578: Epoch 881 +2025-10-30 14:12:24.677011: Current learning rate: 0.00147 +2025-10-30 14:12:45.665719: train_loss -0.9939 +2025-10-30 14:12:45.670403: val_loss -0.8851 +2025-10-30 14:12:45.673446: Pseudo dice [np.float32(0.9821), np.float32(0.9885), np.float32(0.9947), np.float32(0.7826)] +2025-10-30 14:12:45.675493: Epoch time: 20.99 s +2025-10-30 14:12:46.844157: +2025-10-30 14:12:46.848609: Epoch 882 +2025-10-30 14:12:46.850715: Current learning rate: 0.00146 +2025-10-30 14:13:08.996218: train_loss -0.9941 +2025-10-30 14:13:08.999628: val_loss -0.8797 +2025-10-30 14:13:09.004562: Pseudo dice [np.float32(0.9827), np.float32(0.9893), np.float32(0.9941), np.float32(0.7686)] +2025-10-30 14:13:09.009720: Epoch time: 22.15 s +2025-10-30 14:13:10.303222: +2025-10-30 14:13:10.305108: Epoch 883 +2025-10-30 14:13:10.306683: Current learning rate: 0.00145 +2025-10-30 14:13:32.192034: train_loss -0.9939 +2025-10-30 14:13:32.194457: val_loss -0.881 +2025-10-30 14:13:32.196224: Pseudo dice [np.float32(0.9829), np.float32(0.9893), np.float32(0.9941), np.float32(0.7776)] +2025-10-30 14:13:32.198031: Epoch time: 21.89 s +2025-10-30 14:13:33.384559: +2025-10-30 14:13:33.386502: Epoch 884 +2025-10-30 14:13:33.388091: Current learning rate: 0.00144 +2025-10-30 14:13:55.394630: train_loss -0.9939 +2025-10-30 14:13:55.397300: val_loss -0.8789 +2025-10-30 14:13:55.399390: Pseudo dice [np.float32(0.9815), np.float32(0.9891), np.float32(0.9943), np.float32(0.7671)] +2025-10-30 14:13:55.401264: Epoch time: 22.01 s +2025-10-30 14:13:56.451620: +2025-10-30 14:13:56.453831: Epoch 885 +2025-10-30 14:13:56.455736: Current learning rate: 0.00143 +2025-10-30 14:14:17.206415: train_loss -0.9942 +2025-10-30 14:14:17.210769: val_loss -0.8766 +2025-10-30 14:14:17.217555: Pseudo dice [np.float32(0.9817), np.float32(0.9885), np.float32(0.9941), np.float32(0.7717)] +2025-10-30 14:14:17.219691: Epoch time: 20.76 s +2025-10-30 14:14:18.394224: +2025-10-30 14:14:18.396494: Epoch 886 +2025-10-30 14:14:18.399276: Current learning rate: 0.00142 +2025-10-30 14:14:40.273707: train_loss -0.9942 +2025-10-30 14:14:40.276466: val_loss -0.8843 +2025-10-30 14:14:40.278824: Pseudo dice [np.float32(0.9818), np.float32(0.9885), np.float32(0.9948), np.float32(0.7837)] +2025-10-30 14:14:40.280655: Epoch time: 21.88 s +2025-10-30 14:14:41.429595: +2025-10-30 14:14:41.431972: Epoch 887 +2025-10-30 14:14:41.434767: Current learning rate: 0.00141 +2025-10-30 14:15:03.162383: train_loss -0.9945 +2025-10-30 14:15:03.166746: val_loss -0.8862 +2025-10-30 14:15:03.168790: Pseudo dice [np.float32(0.9818), np.float32(0.989), np.float32(0.9947), np.float32(0.7929)] +2025-10-30 14:15:03.171182: Epoch time: 21.73 s +2025-10-30 14:15:04.414347: +2025-10-30 14:15:04.417504: Epoch 888 +2025-10-30 14:15:04.419576: Current learning rate: 0.00139 +2025-10-30 14:15:26.543102: train_loss -0.9943 +2025-10-30 14:15:26.546469: val_loss -0.8815 +2025-10-30 14:15:26.552723: Pseudo dice [np.float32(0.9809), np.float32(0.9884), np.float32(0.9945), np.float32(0.7801)] +2025-10-30 14:15:26.555157: Epoch time: 22.13 s +2025-10-30 14:15:27.816349: +2025-10-30 14:15:27.823263: Epoch 889 +2025-10-30 14:15:27.828292: Current learning rate: 0.00138 +2025-10-30 14:15:49.866320: train_loss -0.9938 +2025-10-30 14:15:49.869468: val_loss -0.8791 +2025-10-30 14:15:49.871844: Pseudo dice [np.float32(0.9815), np.float32(0.9875), np.float32(0.994), np.float32(0.776)] +2025-10-30 14:15:49.873987: Epoch time: 22.05 s +2025-10-30 14:15:51.146651: +2025-10-30 14:15:51.148956: Epoch 890 +2025-10-30 14:15:51.151465: Current learning rate: 0.00137 +2025-10-30 14:16:13.370075: train_loss -0.994 +2025-10-30 14:16:13.373558: val_loss -0.8814 +2025-10-30 14:16:13.376623: Pseudo dice [np.float32(0.982), np.float32(0.9883), np.float32(0.9941), np.float32(0.7749)] +2025-10-30 14:16:13.378657: Epoch time: 22.23 s +2025-10-30 14:16:14.471315: +2025-10-30 14:16:14.474315: Epoch 891 +2025-10-30 14:16:14.476088: Current learning rate: 0.00136 +2025-10-30 14:16:36.019081: train_loss -0.9938 +2025-10-30 14:16:36.021784: val_loss -0.8871 +2025-10-30 14:16:36.024037: Pseudo dice [np.float32(0.9823), np.float32(0.9887), np.float32(0.9946), np.float32(0.7941)] +2025-10-30 14:16:36.026540: Epoch time: 21.55 s +2025-10-30 14:16:37.229031: +2025-10-30 14:16:37.236789: Epoch 892 +2025-10-30 14:16:37.244546: Current learning rate: 0.00135 +2025-10-30 14:16:59.615878: train_loss -0.9941 +2025-10-30 14:16:59.622527: val_loss -0.8742 +2025-10-30 14:16:59.624316: Pseudo dice [np.float32(0.9818), np.float32(0.9885), np.float32(0.9942), np.float32(0.7642)] +2025-10-30 14:16:59.626326: Epoch time: 22.39 s +2025-10-30 14:17:01.939149: +2025-10-30 14:17:01.945128: Epoch 893 +2025-10-30 14:17:01.947789: Current learning rate: 0.00134 +2025-10-30 14:17:23.381645: train_loss -0.9941 +2025-10-30 14:17:23.384516: val_loss -0.8903 +2025-10-30 14:17:23.386195: Pseudo dice [np.float32(0.9828), np.float32(0.988), np.float32(0.9945), np.float32(0.7988)] +2025-10-30 14:17:23.387803: Epoch time: 21.44 s +2025-10-30 14:17:24.492079: +2025-10-30 14:17:24.493984: Epoch 894 +2025-10-30 14:17:24.495855: Current learning rate: 0.00133 +2025-10-30 14:17:46.436065: train_loss -0.9943 +2025-10-30 14:17:46.438865: val_loss -0.8839 +2025-10-30 14:17:46.440986: Pseudo dice [np.float32(0.9836), np.float32(0.9897), np.float32(0.9946), np.float32(0.7818)] +2025-10-30 14:17:46.442952: Epoch time: 21.95 s +2025-10-30 14:17:47.489750: +2025-10-30 14:17:47.491977: Epoch 895 +2025-10-30 14:17:47.493900: Current learning rate: 0.00132 +2025-10-30 14:18:09.493232: train_loss -0.9944 +2025-10-30 14:18:09.496538: val_loss -0.8834 +2025-10-30 14:18:09.498689: Pseudo dice [np.float32(0.9838), np.float32(0.9894), np.float32(0.9946), np.float32(0.778)] +2025-10-30 14:18:09.500995: Epoch time: 22.0 s +2025-10-30 14:18:10.839734: +2025-10-30 14:18:10.841998: Epoch 896 +2025-10-30 14:18:10.843893: Current learning rate: 0.0013 +2025-10-30 14:18:32.772619: train_loss -0.9942 +2025-10-30 14:18:32.778723: val_loss -0.8721 +2025-10-30 14:18:32.780584: Pseudo dice [np.float32(0.9793), np.float32(0.9874), np.float32(0.9941), np.float32(0.7669)] +2025-10-30 14:18:32.782579: Epoch time: 21.93 s +2025-10-30 14:18:33.912756: +2025-10-30 14:18:33.915087: Epoch 897 +2025-10-30 14:18:33.916941: Current learning rate: 0.00129 +2025-10-30 14:18:53.696499: train_loss -0.9937 +2025-10-30 14:18:53.699289: val_loss -0.8733 +2025-10-30 14:18:53.701325: Pseudo dice [np.float32(0.982), np.float32(0.9893), np.float32(0.9941), np.float32(0.7562)] +2025-10-30 14:18:53.703453: Epoch time: 19.79 s +2025-10-30 14:18:54.770863: +2025-10-30 14:18:54.773488: Epoch 898 +2025-10-30 14:18:54.775571: Current learning rate: 0.00128 +2025-10-30 14:19:16.842872: train_loss -0.9941 +2025-10-30 14:19:16.847764: val_loss -0.8763 +2025-10-30 14:19:16.853190: Pseudo dice [np.float32(0.9819), np.float32(0.9892), np.float32(0.9942), np.float32(0.7676)] +2025-10-30 14:19:16.858391: Epoch time: 22.07 s +2025-10-30 14:19:18.149068: +2025-10-30 14:19:18.151218: Epoch 899 +2025-10-30 14:19:18.153195: Current learning rate: 0.00127 +2025-10-30 14:19:39.978266: train_loss -0.9943 +2025-10-30 14:19:39.982011: val_loss -0.8877 +2025-10-30 14:19:39.984071: Pseudo dice [np.float32(0.9826), np.float32(0.9892), np.float32(0.9949), np.float32(0.7882)] +2025-10-30 14:19:39.985683: Epoch time: 21.83 s +2025-10-30 14:19:42.471918: +2025-10-30 14:19:42.473861: Epoch 900 +2025-10-30 14:19:42.475412: Current learning rate: 0.00126 +2025-10-30 14:20:02.921972: train_loss -0.9945 +2025-10-30 14:20:02.925392: val_loss -0.8782 +2025-10-30 14:20:02.928108: Pseudo dice [np.float32(0.9806), np.float32(0.9881), np.float32(0.9943), np.float32(0.7791)] +2025-10-30 14:20:02.932269: Epoch time: 20.45 s +2025-10-30 14:20:04.091953: +2025-10-30 14:20:04.098069: Epoch 901 +2025-10-30 14:20:04.101772: Current learning rate: 0.00125 +2025-10-30 14:20:25.845718: train_loss -0.9944 +2025-10-30 14:20:25.849156: val_loss -0.8867 +2025-10-30 14:20:25.851326: Pseudo dice [np.float32(0.9825), np.float32(0.9893), np.float32(0.9948), np.float32(0.7879)] +2025-10-30 14:20:25.853344: Epoch time: 21.76 s +2025-10-30 14:20:27.032867: +2025-10-30 14:20:27.035396: Epoch 902 +2025-10-30 14:20:27.037174: Current learning rate: 0.00124 +2025-10-30 14:20:49.103567: train_loss -0.9942 +2025-10-30 14:20:49.106630: val_loss -0.8801 +2025-10-30 14:20:49.108476: Pseudo dice [np.float32(0.9808), np.float32(0.9881), np.float32(0.9943), np.float32(0.7773)] +2025-10-30 14:20:49.110678: Epoch time: 22.07 s +2025-10-30 14:20:50.153376: +2025-10-30 14:20:50.155872: Epoch 903 +2025-10-30 14:20:50.157847: Current learning rate: 0.00122 +2025-10-30 14:21:11.146393: train_loss -0.9946 +2025-10-30 14:21:11.150277: val_loss -0.8751 +2025-10-30 14:21:11.155369: Pseudo dice [np.float32(0.9812), np.float32(0.9879), np.float32(0.994), np.float32(0.774)] +2025-10-30 14:21:11.158956: Epoch time: 20.99 s +2025-10-30 14:21:12.152956: +2025-10-30 14:21:12.157218: Epoch 904 +2025-10-30 14:21:12.159858: Current learning rate: 0.00121 +2025-10-30 14:21:34.235367: train_loss -0.9941 +2025-10-30 14:21:34.238142: val_loss -0.8794 +2025-10-30 14:21:34.241892: Pseudo dice [np.float32(0.9811), np.float32(0.9884), np.float32(0.9944), np.float32(0.7808)] +2025-10-30 14:21:34.243853: Epoch time: 22.08 s +2025-10-30 14:21:35.468643: +2025-10-30 14:21:35.470724: Epoch 905 +2025-10-30 14:21:35.472608: Current learning rate: 0.0012 +2025-10-30 14:21:57.540491: train_loss -0.9946 +2025-10-30 14:21:57.544020: val_loss -0.8829 +2025-10-30 14:21:57.547137: Pseudo dice [np.float32(0.9827), np.float32(0.9888), np.float32(0.9946), np.float32(0.7822)] +2025-10-30 14:21:57.550454: Epoch time: 22.07 s +2025-10-30 14:21:58.714101: +2025-10-30 14:21:58.715924: Epoch 906 +2025-10-30 14:21:58.717549: Current learning rate: 0.00119 +2025-10-30 14:22:20.407830: train_loss -0.9943 +2025-10-30 14:22:20.411809: val_loss -0.874 +2025-10-30 14:22:20.413944: Pseudo dice [np.float32(0.9807), np.float32(0.9868), np.float32(0.9937), np.float32(0.777)] +2025-10-30 14:22:20.416214: Epoch time: 21.7 s +2025-10-30 14:22:21.691000: +2025-10-30 14:22:21.695336: Epoch 907 +2025-10-30 14:22:21.698518: Current learning rate: 0.00118 +2025-10-30 14:22:43.889406: train_loss -0.9938 +2025-10-30 14:22:43.902243: val_loss -0.8833 +2025-10-30 14:22:43.904749: Pseudo dice [np.float32(0.9819), np.float32(0.988), np.float32(0.9941), np.float32(0.7821)] +2025-10-30 14:22:43.906950: Epoch time: 22.2 s +2025-10-30 14:22:45.170954: +2025-10-30 14:22:45.173172: Epoch 908 +2025-10-30 14:22:45.175351: Current learning rate: 0.00117 +2025-10-30 14:23:07.235883: train_loss -0.9941 +2025-10-30 14:23:07.241003: val_loss -0.8913 +2025-10-30 14:23:07.242771: Pseudo dice [np.float32(0.9841), np.float32(0.9902), np.float32(0.9948), np.float32(0.7922)] +2025-10-30 14:23:07.244849: Epoch time: 22.07 s +2025-10-30 14:23:08.296871: +2025-10-30 14:23:08.298851: Epoch 909 +2025-10-30 14:23:08.300419: Current learning rate: 0.00116 +2025-10-30 14:23:29.620134: train_loss -0.9945 +2025-10-30 14:23:29.626859: val_loss -0.8797 +2025-10-30 14:23:29.630274: Pseudo dice [np.float32(0.9816), np.float32(0.988), np.float32(0.9943), np.float32(0.7821)] +2025-10-30 14:23:29.632978: Epoch time: 21.33 s +2025-10-30 14:23:31.014693: +2025-10-30 14:23:31.020014: Epoch 910 +2025-10-30 14:23:31.024235: Current learning rate: 0.00115 +2025-10-30 14:23:53.100399: train_loss -0.9944 +2025-10-30 14:23:53.104951: val_loss -0.8811 +2025-10-30 14:23:53.107689: Pseudo dice [np.float32(0.9819), np.float32(0.9882), np.float32(0.9942), np.float32(0.7751)] +2025-10-30 14:23:53.110347: Epoch time: 22.09 s +2025-10-30 14:23:55.004845: +2025-10-30 14:23:55.007435: Epoch 911 +2025-10-30 14:23:55.010354: Current learning rate: 0.00113 +2025-10-30 14:24:17.340455: train_loss -0.9939 +2025-10-30 14:24:17.344103: val_loss -0.8789 +2025-10-30 14:24:17.346554: Pseudo dice [np.float32(0.9822), np.float32(0.9886), np.float32(0.9939), np.float32(0.7716)] +2025-10-30 14:24:17.348385: Epoch time: 22.34 s +2025-10-30 14:24:18.450406: +2025-10-30 14:24:18.454071: Epoch 912 +2025-10-30 14:24:18.456237: Current learning rate: 0.00112 +2025-10-30 14:24:40.376888: train_loss -0.9944 +2025-10-30 14:24:40.380038: val_loss -0.8801 +2025-10-30 14:24:40.381701: Pseudo dice [np.float32(0.9835), np.float32(0.9897), np.float32(0.9942), np.float32(0.7638)] +2025-10-30 14:24:40.383522: Epoch time: 21.93 s +2025-10-30 14:24:41.667044: +2025-10-30 14:24:41.669858: Epoch 913 +2025-10-30 14:24:41.673978: Current learning rate: 0.00111 +2025-10-30 14:25:02.822507: train_loss -0.9942 +2025-10-30 14:25:02.828753: val_loss -0.8767 +2025-10-30 14:25:02.833075: Pseudo dice [np.float32(0.9811), np.float32(0.988), np.float32(0.9939), np.float32(0.7678)] +2025-10-30 14:25:02.837159: Epoch time: 21.16 s +2025-10-30 14:25:04.061067: +2025-10-30 14:25:04.063665: Epoch 914 +2025-10-30 14:25:04.065724: Current learning rate: 0.0011 +2025-10-30 14:25:26.069546: train_loss -0.9938 +2025-10-30 14:25:26.073508: val_loss -0.8743 +2025-10-30 14:25:26.076460: Pseudo dice [np.float32(0.9808), np.float32(0.988), np.float32(0.9939), np.float32(0.7581)] +2025-10-30 14:25:26.078743: Epoch time: 22.01 s +2025-10-30 14:25:27.318247: +2025-10-30 14:25:27.320708: Epoch 915 +2025-10-30 14:25:27.323463: Current learning rate: 0.00109 +2025-10-30 14:25:48.387400: train_loss -0.9945 +2025-10-30 14:25:48.392308: val_loss -0.8753 +2025-10-30 14:25:48.394354: Pseudo dice [np.float32(0.9826), np.float32(0.9886), np.float32(0.9939), np.float32(0.7649)] +2025-10-30 14:25:48.397049: Epoch time: 21.07 s +2025-10-30 14:25:49.684031: +2025-10-30 14:25:49.686413: Epoch 916 +2025-10-30 14:25:49.688379: Current learning rate: 0.00108 +2025-10-30 14:26:11.399045: train_loss -0.994 +2025-10-30 14:26:11.403375: val_loss -0.8756 +2025-10-30 14:26:11.405333: Pseudo dice [np.float32(0.9835), np.float32(0.9892), np.float32(0.994), np.float32(0.7599)] +2025-10-30 14:26:11.407198: Epoch time: 21.72 s +2025-10-30 14:26:12.460914: +2025-10-30 14:26:12.463088: Epoch 917 +2025-10-30 14:26:12.465073: Current learning rate: 0.00106 +2025-10-30 14:26:34.237696: train_loss -0.9946 +2025-10-30 14:26:34.241639: val_loss -0.8856 +2025-10-30 14:26:34.244661: Pseudo dice [np.float32(0.982), np.float32(0.9892), np.float32(0.9943), np.float32(0.7882)] +2025-10-30 14:26:34.251898: Epoch time: 21.78 s +2025-10-30 14:26:35.622378: +2025-10-30 14:26:35.624377: Epoch 918 +2025-10-30 14:26:35.626498: Current learning rate: 0.00105 +2025-10-30 14:26:55.881866: train_loss -0.9946 +2025-10-30 14:26:55.888760: val_loss -0.881 +2025-10-30 14:26:55.890624: Pseudo dice [np.float32(0.9809), np.float32(0.9877), np.float32(0.9944), np.float32(0.7843)] +2025-10-30 14:26:55.892735: Epoch time: 20.26 s +2025-10-30 14:26:57.123668: +2025-10-30 14:26:57.125455: Epoch 919 +2025-10-30 14:26:57.127018: Current learning rate: 0.00104 +2025-10-30 14:27:17.945077: train_loss -0.9945 +2025-10-30 14:27:17.950591: val_loss -0.8778 +2025-10-30 14:27:17.952274: Pseudo dice [np.float32(0.9819), np.float32(0.9886), np.float32(0.9938), np.float32(0.7716)] +2025-10-30 14:27:17.953980: Epoch time: 20.82 s +2025-10-30 14:27:19.190896: +2025-10-30 14:27:19.193439: Epoch 920 +2025-10-30 14:27:19.195138: Current learning rate: 0.00103 +2025-10-30 14:27:40.472152: train_loss -0.9944 +2025-10-30 14:27:40.476256: val_loss -0.8747 +2025-10-30 14:27:40.479350: Pseudo dice [np.float32(0.9808), np.float32(0.9876), np.float32(0.9941), np.float32(0.7652)] +2025-10-30 14:27:40.480979: Epoch time: 21.28 s +2025-10-30 14:27:41.716858: +2025-10-30 14:27:41.720047: Epoch 921 +2025-10-30 14:27:41.721991: Current learning rate: 0.00102 +2025-10-30 14:28:03.191011: train_loss -0.9944 +2025-10-30 14:28:03.193651: val_loss -0.8738 +2025-10-30 14:28:03.195763: Pseudo dice [np.float32(0.9825), np.float32(0.9883), np.float32(0.9939), np.float32(0.7536)] +2025-10-30 14:28:03.197835: Epoch time: 21.48 s +2025-10-30 14:28:04.219473: +2025-10-30 14:28:04.221586: Epoch 922 +2025-10-30 14:28:04.223527: Current learning rate: 0.00101 +2025-10-30 14:28:25.707343: train_loss -0.9943 +2025-10-30 14:28:25.709867: val_loss -0.8755 +2025-10-30 14:28:25.711564: Pseudo dice [np.float32(0.9818), np.float32(0.9885), np.float32(0.9942), np.float32(0.7678)] +2025-10-30 14:28:25.713294: Epoch time: 21.49 s +2025-10-30 14:28:26.810431: +2025-10-30 14:28:26.814412: Epoch 923 +2025-10-30 14:28:26.816333: Current learning rate: 0.001 +2025-10-30 14:28:48.614965: train_loss -0.9946 +2025-10-30 14:28:48.618002: val_loss -0.8738 +2025-10-30 14:28:48.620610: Pseudo dice [np.float32(0.9824), np.float32(0.9886), np.float32(0.9942), np.float32(0.7633)] +2025-10-30 14:28:48.622922: Epoch time: 21.81 s +2025-10-30 14:28:49.674343: +2025-10-30 14:28:49.678602: Epoch 924 +2025-10-30 14:28:49.681019: Current learning rate: 0.00098 +2025-10-30 14:29:12.366585: train_loss -0.9942 +2025-10-30 14:29:12.369433: val_loss -0.8792 +2025-10-30 14:29:12.371223: Pseudo dice [np.float32(0.9833), np.float32(0.9892), np.float32(0.9942), np.float32(0.7729)] +2025-10-30 14:29:12.373199: Epoch time: 22.69 s +2025-10-30 14:29:13.559692: +2025-10-30 14:29:13.562936: Epoch 925 +2025-10-30 14:29:13.565520: Current learning rate: 0.00097 +2025-10-30 14:29:35.886848: train_loss -0.9944 +2025-10-30 14:29:35.889919: val_loss -0.889 +2025-10-30 14:29:35.891966: Pseudo dice [np.float32(0.9828), np.float32(0.989), np.float32(0.9946), np.float32(0.7903)] +2025-10-30 14:29:35.893670: Epoch time: 22.33 s +2025-10-30 14:29:37.208722: +2025-10-30 14:29:37.210743: Epoch 926 +2025-10-30 14:29:37.212562: Current learning rate: 0.00096 +2025-10-30 14:29:57.885545: train_loss -0.9946 +2025-10-30 14:29:57.890859: val_loss -0.8782 +2025-10-30 14:29:57.893330: Pseudo dice [np.float32(0.9825), np.float32(0.989), np.float32(0.9941), np.float32(0.7701)] +2025-10-30 14:29:57.895074: Epoch time: 20.68 s +2025-10-30 14:29:58.960608: +2025-10-30 14:29:58.962319: Epoch 927 +2025-10-30 14:29:58.963897: Current learning rate: 0.00095 +2025-10-30 14:30:21.048384: train_loss -0.9946 +2025-10-30 14:30:21.051168: val_loss -0.8816 +2025-10-30 14:30:21.052945: Pseudo dice [np.float32(0.9819), np.float32(0.9876), np.float32(0.9943), np.float32(0.7901)] +2025-10-30 14:30:21.054608: Epoch time: 22.09 s +2025-10-30 14:30:22.123962: +2025-10-30 14:30:22.125737: Epoch 928 +2025-10-30 14:30:22.129277: Current learning rate: 0.00094 +2025-10-30 14:30:43.902657: train_loss -0.9945 +2025-10-30 14:30:43.905514: val_loss -0.8749 +2025-10-30 14:30:43.908649: Pseudo dice [np.float32(0.9818), np.float32(0.988), np.float32(0.994), np.float32(0.7687)] +2025-10-30 14:30:43.911228: Epoch time: 21.78 s +2025-10-30 14:30:45.284523: +2025-10-30 14:30:45.286505: Epoch 929 +2025-10-30 14:30:45.289430: Current learning rate: 0.00092 +2025-10-30 14:31:07.877742: train_loss -0.9943 +2025-10-30 14:31:07.882897: val_loss -0.8871 +2025-10-30 14:31:07.885900: Pseudo dice [np.float32(0.985), np.float32(0.9904), np.float32(0.9947), np.float32(0.7822)] +2025-10-30 14:31:07.887843: Epoch time: 22.59 s +2025-10-30 14:31:09.038288: +2025-10-30 14:31:09.040349: Epoch 930 +2025-10-30 14:31:09.042165: Current learning rate: 0.00091 +2025-10-30 14:31:31.550589: train_loss -0.9944 +2025-10-30 14:31:31.558421: val_loss -0.8723 +2025-10-30 14:31:31.563733: Pseudo dice [np.float32(0.9809), np.float32(0.9878), np.float32(0.994), np.float32(0.7628)] +2025-10-30 14:31:31.567111: Epoch time: 22.51 s +2025-10-30 14:31:32.837779: +2025-10-30 14:31:32.840250: Epoch 931 +2025-10-30 14:31:32.841933: Current learning rate: 0.0009 +2025-10-30 14:31:54.813055: train_loss -0.9944 +2025-10-30 14:31:54.815500: val_loss -0.886 +2025-10-30 14:31:54.817347: Pseudo dice [np.float32(0.9833), np.float32(0.989), np.float32(0.9944), np.float32(0.7868)] +2025-10-30 14:31:54.819253: Epoch time: 21.98 s +2025-10-30 14:31:56.090197: +2025-10-30 14:31:56.092484: Epoch 932 +2025-10-30 14:31:56.094333: Current learning rate: 0.00089 +2025-10-30 14:32:16.940560: train_loss -0.9943 +2025-10-30 14:32:16.943858: val_loss -0.8776 +2025-10-30 14:32:16.946126: Pseudo dice [np.float32(0.9818), np.float32(0.9881), np.float32(0.9938), np.float32(0.7704)] +2025-10-30 14:32:16.948372: Epoch time: 20.85 s +2025-10-30 14:32:18.112542: +2025-10-30 14:32:18.115635: Epoch 933 +2025-10-30 14:32:18.118192: Current learning rate: 0.00088 +2025-10-30 14:32:40.446946: train_loss -0.9948 +2025-10-30 14:32:40.449564: val_loss -0.8815 +2025-10-30 14:32:40.451774: Pseudo dice [np.float32(0.9827), np.float32(0.9882), np.float32(0.9941), np.float32(0.777)] +2025-10-30 14:32:40.453426: Epoch time: 22.34 s +2025-10-30 14:32:41.710326: +2025-10-30 14:32:41.712383: Epoch 934 +2025-10-30 14:32:41.713837: Current learning rate: 0.00087 +2025-10-30 14:33:03.662680: train_loss -0.9949 +2025-10-30 14:33:03.665543: val_loss -0.881 +2025-10-30 14:33:03.669301: Pseudo dice [np.float32(0.9816), np.float32(0.9874), np.float32(0.9944), np.float32(0.7878)] +2025-10-30 14:33:03.671197: Epoch time: 21.95 s +2025-10-30 14:33:04.956989: +2025-10-30 14:33:04.962286: Epoch 935 +2025-10-30 14:33:04.965260: Current learning rate: 0.00085 +2025-10-30 14:33:27.068594: train_loss -0.9949 +2025-10-30 14:33:27.088927: val_loss -0.8831 +2025-10-30 14:33:27.097454: Pseudo dice [np.float32(0.9843), np.float32(0.9889), np.float32(0.9942), np.float32(0.7823)] +2025-10-30 14:33:27.108034: Epoch time: 22.11 s +2025-10-30 14:33:28.220459: +2025-10-30 14:33:28.222777: Epoch 936 +2025-10-30 14:33:28.225030: Current learning rate: 0.00084 +2025-10-30 14:33:50.718316: train_loss -0.9945 +2025-10-30 14:33:50.726533: val_loss -0.8744 +2025-10-30 14:33:50.733483: Pseudo dice [np.float32(0.9828), np.float32(0.9887), np.float32(0.9943), np.float32(0.7568)] +2025-10-30 14:33:50.740902: Epoch time: 22.5 s +2025-10-30 14:33:51.957080: +2025-10-30 14:33:51.959113: Epoch 937 +2025-10-30 14:33:51.960872: Current learning rate: 0.00083 +2025-10-30 14:34:14.513186: train_loss -0.9944 +2025-10-30 14:34:14.518619: val_loss -0.8765 +2025-10-30 14:34:14.522908: Pseudo dice [np.float32(0.9821), np.float32(0.9885), np.float32(0.9939), np.float32(0.7664)] +2025-10-30 14:34:14.524922: Epoch time: 22.56 s +2025-10-30 14:34:15.801389: +2025-10-30 14:34:15.804720: Epoch 938 +2025-10-30 14:34:15.807550: Current learning rate: 0.00082 +2025-10-30 14:34:37.335408: train_loss -0.9946 +2025-10-30 14:34:37.338120: val_loss -0.8735 +2025-10-30 14:34:37.341002: Pseudo dice [np.float32(0.9827), np.float32(0.9883), np.float32(0.9941), np.float32(0.7618)] +2025-10-30 14:34:37.343172: Epoch time: 21.54 s +2025-10-30 14:34:38.445628: +2025-10-30 14:34:38.448410: Epoch 939 +2025-10-30 14:34:38.453302: Current learning rate: 0.00081 +2025-10-30 14:35:00.467500: train_loss -0.995 +2025-10-30 14:35:00.469836: val_loss -0.8769 +2025-10-30 14:35:00.471278: Pseudo dice [np.float32(0.9814), np.float32(0.9881), np.float32(0.9943), np.float32(0.7735)] +2025-10-30 14:35:00.472531: Epoch time: 22.02 s +2025-10-30 14:35:01.416069: +2025-10-30 14:35:01.422433: Epoch 940 +2025-10-30 14:35:01.428297: Current learning rate: 0.00079 +2025-10-30 14:35:23.682767: train_loss -0.9948 +2025-10-30 14:35:23.688481: val_loss -0.8648 +2025-10-30 14:35:23.690599: Pseudo dice [np.float32(0.983), np.float32(0.9886), np.float32(0.9935), np.float32(0.7374)] +2025-10-30 14:35:23.692805: Epoch time: 22.27 s +2025-10-30 14:35:24.981508: +2025-10-30 14:35:24.983565: Epoch 941 +2025-10-30 14:35:24.985339: Current learning rate: 0.00078 +2025-10-30 14:35:47.307753: train_loss -0.9949 +2025-10-30 14:35:47.311584: val_loss -0.8744 +2025-10-30 14:35:47.313768: Pseudo dice [np.float32(0.9821), np.float32(0.988), np.float32(0.994), np.float32(0.7687)] +2025-10-30 14:35:47.315532: Epoch time: 22.33 s +2025-10-30 14:35:48.545739: +2025-10-30 14:35:48.562655: Epoch 942 +2025-10-30 14:35:48.575491: Current learning rate: 0.00077 +2025-10-30 14:36:11.034807: train_loss -0.995 +2025-10-30 14:36:11.038208: val_loss -0.8742 +2025-10-30 14:36:11.041701: Pseudo dice [np.float32(0.9831), np.float32(0.9882), np.float32(0.9941), np.float32(0.7611)] +2025-10-30 14:36:11.045166: Epoch time: 22.49 s +2025-10-30 14:36:12.206364: +2025-10-30 14:36:12.209141: Epoch 943 +2025-10-30 14:36:12.211455: Current learning rate: 0.00076 +2025-10-30 14:36:34.317608: train_loss -0.9947 +2025-10-30 14:36:34.319693: val_loss -0.8884 +2025-10-30 14:36:34.322335: Pseudo dice [np.float32(0.9833), np.float32(0.9887), np.float32(0.9947), np.float32(0.7903)] +2025-10-30 14:36:34.324285: Epoch time: 22.11 s +2025-10-30 14:36:35.551548: +2025-10-30 14:36:35.553457: Epoch 944 +2025-10-30 14:36:35.555949: Current learning rate: 0.00075 +2025-10-30 14:36:57.586278: train_loss -0.9953 +2025-10-30 14:36:57.588927: val_loss -0.8754 +2025-10-30 14:36:57.590931: Pseudo dice [np.float32(0.9822), np.float32(0.988), np.float32(0.9944), np.float32(0.7718)] +2025-10-30 14:36:57.593287: Epoch time: 22.04 s +2025-10-30 14:36:58.824635: +2025-10-30 14:36:58.826471: Epoch 945 +2025-10-30 14:36:58.828095: Current learning rate: 0.00074 +2025-10-30 14:37:19.959442: train_loss -0.9946 +2025-10-30 14:37:19.962395: val_loss -0.8813 +2025-10-30 14:37:19.964528: Pseudo dice [np.float32(0.9822), np.float32(0.988), np.float32(0.9945), np.float32(0.7822)] +2025-10-30 14:37:19.966568: Epoch time: 21.14 s +2025-10-30 14:37:21.245224: +2025-10-30 14:37:21.248469: Epoch 946 +2025-10-30 14:37:21.251218: Current learning rate: 0.00072 +2025-10-30 14:37:43.731685: train_loss -0.9949 +2025-10-30 14:37:43.734890: val_loss -0.8722 +2025-10-30 14:37:43.736813: Pseudo dice [np.float32(0.9803), np.float32(0.988), np.float32(0.9941), np.float32(0.7596)] +2025-10-30 14:37:43.740167: Epoch time: 22.49 s +2025-10-30 14:37:44.776219: +2025-10-30 14:37:44.778333: Epoch 947 +2025-10-30 14:37:44.780264: Current learning rate: 0.00071 +2025-10-30 14:38:07.297568: train_loss -0.9948 +2025-10-30 14:38:07.300863: val_loss -0.8775 +2025-10-30 14:38:07.302847: Pseudo dice [np.float32(0.9836), np.float32(0.989), np.float32(0.9941), np.float32(0.7601)] +2025-10-30 14:38:07.304685: Epoch time: 22.52 s +2025-10-30 14:38:09.033623: +2025-10-30 14:38:09.036632: Epoch 948 +2025-10-30 14:38:09.038536: Current learning rate: 0.0007 +2025-10-30 14:38:31.025270: train_loss -0.9948 +2025-10-30 14:38:31.028609: val_loss -0.878 +2025-10-30 14:38:31.030813: Pseudo dice [np.float32(0.9824), np.float32(0.9889), np.float32(0.9944), np.float32(0.7679)] +2025-10-30 14:38:31.032690: Epoch time: 21.99 s +2025-10-30 14:38:32.241388: +2025-10-30 14:38:32.244265: Epoch 949 +2025-10-30 14:38:32.247185: Current learning rate: 0.00069 +2025-10-30 14:38:54.637968: train_loss -0.9941 +2025-10-30 14:38:54.643135: val_loss -0.8819 +2025-10-30 14:38:54.645055: Pseudo dice [np.float32(0.9825), np.float32(0.9886), np.float32(0.9944), np.float32(0.7794)] +2025-10-30 14:38:54.647035: Epoch time: 22.4 s +2025-10-30 14:38:57.096976: +2025-10-30 14:38:57.101136: Epoch 950 +2025-10-30 14:38:57.103132: Current learning rate: 0.00067 +2025-10-30 14:39:19.287622: train_loss -0.9952 +2025-10-30 14:39:19.292076: val_loss -0.8846 +2025-10-30 14:39:19.295480: Pseudo dice [np.float32(0.982), np.float32(0.9887), np.float32(0.9946), np.float32(0.7858)] +2025-10-30 14:39:19.298225: Epoch time: 22.19 s +2025-10-30 14:39:20.376455: +2025-10-30 14:39:20.379302: Epoch 951 +2025-10-30 14:39:20.381724: Current learning rate: 0.00066 +2025-10-30 14:39:40.036527: train_loss -0.9949 +2025-10-30 14:39:40.040371: val_loss -0.8833 +2025-10-30 14:39:40.042346: Pseudo dice [np.float32(0.9816), np.float32(0.9887), np.float32(0.9944), np.float32(0.7811)] +2025-10-30 14:39:40.045130: Epoch time: 19.66 s +2025-10-30 14:39:41.180528: +2025-10-30 14:39:41.183355: Epoch 952 +2025-10-30 14:39:41.184908: Current learning rate: 0.00065 +2025-10-30 14:40:03.533304: train_loss -0.9952 +2025-10-30 14:40:03.535502: val_loss -0.8765 +2025-10-30 14:40:03.539387: Pseudo dice [np.float32(0.9818), np.float32(0.9878), np.float32(0.994), np.float32(0.7656)] +2025-10-30 14:40:03.541964: Epoch time: 22.35 s +2025-10-30 14:40:04.740606: +2025-10-30 14:40:04.744316: Epoch 953 +2025-10-30 14:40:04.748861: Current learning rate: 0.00064 +2025-10-30 14:40:27.179172: train_loss -0.995 +2025-10-30 14:40:27.185582: val_loss -0.8787 +2025-10-30 14:40:27.188043: Pseudo dice [np.float32(0.9819), np.float32(0.9885), np.float32(0.9941), np.float32(0.7728)] +2025-10-30 14:40:27.189870: Epoch time: 22.44 s +2025-10-30 14:40:28.471214: +2025-10-30 14:40:28.474026: Epoch 954 +2025-10-30 14:40:28.475896: Current learning rate: 0.00063 +2025-10-30 14:40:50.802998: train_loss -0.9951 +2025-10-30 14:40:50.805452: val_loss -0.888 +2025-10-30 14:40:50.807551: Pseudo dice [np.float32(0.9822), np.float32(0.9893), np.float32(0.9948), np.float32(0.7902)] +2025-10-30 14:40:50.809410: Epoch time: 22.33 s +2025-10-30 14:40:52.193548: +2025-10-30 14:40:52.195577: Epoch 955 +2025-10-30 14:40:52.197635: Current learning rate: 0.00061 +2025-10-30 14:41:14.689100: train_loss -0.9944 +2025-10-30 14:41:14.695963: val_loss -0.881 +2025-10-30 14:41:14.699043: Pseudo dice [np.float32(0.9824), np.float32(0.9892), np.float32(0.9945), np.float32(0.7725)] +2025-10-30 14:41:14.702006: Epoch time: 22.5 s +2025-10-30 14:41:16.148594: +2025-10-30 14:41:16.151037: Epoch 956 +2025-10-30 14:41:16.152987: Current learning rate: 0.0006 +2025-10-30 14:41:37.970974: train_loss -0.9952 +2025-10-30 14:41:37.978335: val_loss -0.8814 +2025-10-30 14:41:37.983534: Pseudo dice [np.float32(0.9824), np.float32(0.9892), np.float32(0.9946), np.float32(0.7751)] +2025-10-30 14:41:37.986890: Epoch time: 21.82 s +2025-10-30 14:41:39.105640: +2025-10-30 14:41:39.107752: Epoch 957 +2025-10-30 14:41:39.112363: Current learning rate: 0.00059 +2025-10-30 14:41:59.497430: train_loss -0.9949 +2025-10-30 14:41:59.502026: val_loss -0.8672 +2025-10-30 14:41:59.503905: Pseudo dice [np.float32(0.9822), np.float32(0.9878), np.float32(0.9939), np.float32(0.7489)] +2025-10-30 14:41:59.505839: Epoch time: 20.39 s +2025-10-30 14:42:00.696079: +2025-10-30 14:42:00.698317: Epoch 958 +2025-10-30 14:42:00.700276: Current learning rate: 0.00058 +2025-10-30 14:42:23.059304: train_loss -0.9951 +2025-10-30 14:42:23.062078: val_loss -0.8802 +2025-10-30 14:42:23.064402: Pseudo dice [np.float32(0.9818), np.float32(0.9885), np.float32(0.9943), np.float32(0.7825)] +2025-10-30 14:42:23.066864: Epoch time: 22.37 s +2025-10-30 14:42:24.362691: +2025-10-30 14:42:24.365648: Epoch 959 +2025-10-30 14:42:24.368236: Current learning rate: 0.00056 +2025-10-30 14:42:46.696464: train_loss -0.9948 +2025-10-30 14:42:46.699893: val_loss -0.8738 +2025-10-30 14:42:46.701983: Pseudo dice [np.float32(0.9818), np.float32(0.9881), np.float32(0.9943), np.float32(0.7675)] +2025-10-30 14:42:46.703760: Epoch time: 22.34 s +2025-10-30 14:42:47.774153: +2025-10-30 14:42:47.776554: Epoch 960 +2025-10-30 14:42:47.779579: Current learning rate: 0.00055 +2025-10-30 14:43:09.833566: train_loss -0.9946 +2025-10-30 14:43:09.839288: val_loss -0.8811 +2025-10-30 14:43:09.843411: Pseudo dice [np.float32(0.9816), np.float32(0.9884), np.float32(0.9941), np.float32(0.7858)] +2025-10-30 14:43:09.847152: Epoch time: 22.06 s +2025-10-30 14:43:11.216629: +2025-10-30 14:43:11.221152: Epoch 961 +2025-10-30 14:43:11.223777: Current learning rate: 0.00054 +2025-10-30 14:43:33.264471: train_loss -0.995 +2025-10-30 14:43:33.267280: val_loss -0.8863 +2025-10-30 14:43:33.269151: Pseudo dice [np.float32(0.9837), np.float32(0.9896), np.float32(0.9947), np.float32(0.7885)] +2025-10-30 14:43:33.271221: Epoch time: 22.05 s +2025-10-30 14:43:34.412752: +2025-10-30 14:43:34.416231: Epoch 962 +2025-10-30 14:43:34.418705: Current learning rate: 0.00053 +2025-10-30 14:43:56.482912: train_loss -0.9948 +2025-10-30 14:43:56.485739: val_loss -0.8788 +2025-10-30 14:43:56.487743: Pseudo dice [np.float32(0.9825), np.float32(0.9886), np.float32(0.9943), np.float32(0.7791)] +2025-10-30 14:43:56.489279: Epoch time: 22.07 s +2025-10-30 14:43:57.656710: +2025-10-30 14:43:57.658664: Epoch 963 +2025-10-30 14:43:57.660297: Current learning rate: 0.00051 +2025-10-30 14:44:18.884169: train_loss -0.9955 +2025-10-30 14:44:18.888582: val_loss -0.8875 +2025-10-30 14:44:18.891272: Pseudo dice [np.float32(0.9845), np.float32(0.9899), np.float32(0.9948), np.float32(0.7939)] +2025-10-30 14:44:18.893585: Epoch time: 21.23 s +2025-10-30 14:44:20.278304: +2025-10-30 14:44:20.280238: Epoch 964 +2025-10-30 14:44:20.282493: Current learning rate: 0.0005 +2025-10-30 14:44:40.788426: train_loss -0.9954 +2025-10-30 14:44:40.793148: val_loss -0.8835 +2025-10-30 14:44:40.795445: Pseudo dice [np.float32(0.9825), np.float32(0.989), np.float32(0.9943), np.float32(0.7874)] +2025-10-30 14:44:40.797024: Epoch time: 20.51 s +2025-10-30 14:44:42.039856: +2025-10-30 14:44:42.041752: Epoch 965 +2025-10-30 14:44:42.043529: Current learning rate: 0.00049 +2025-10-30 14:45:04.612211: train_loss -0.9949 +2025-10-30 14:45:04.618558: val_loss -0.8836 +2025-10-30 14:45:04.626659: Pseudo dice [np.float32(0.9823), np.float32(0.9896), np.float32(0.9948), np.float32(0.7782)] +2025-10-30 14:45:04.632326: Epoch time: 22.57 s +2025-10-30 14:45:05.911436: +2025-10-30 14:45:05.915036: Epoch 966 +2025-10-30 14:45:05.917551: Current learning rate: 0.00048 +2025-10-30 14:45:28.753099: train_loss -0.9949 +2025-10-30 14:45:28.757650: val_loss -0.8835 +2025-10-30 14:45:28.761371: Pseudo dice [np.float32(0.9831), np.float32(0.9895), np.float32(0.9944), np.float32(0.7829)] +2025-10-30 14:45:28.763151: Epoch time: 22.84 s +2025-10-30 14:45:29.884503: +2025-10-30 14:45:29.886910: Epoch 967 +2025-10-30 14:45:29.889342: Current learning rate: 0.00046 +2025-10-30 14:45:51.857230: train_loss -0.9956 +2025-10-30 14:45:51.863039: val_loss -0.8806 +2025-10-30 14:45:51.865287: Pseudo dice [np.float32(0.9825), np.float32(0.9884), np.float32(0.9941), np.float32(0.7844)] +2025-10-30 14:45:51.868322: Epoch time: 21.97 s +2025-10-30 14:45:52.942380: +2025-10-30 14:45:52.944964: Epoch 968 +2025-10-30 14:45:52.946573: Current learning rate: 0.00045 +2025-10-30 14:46:15.273362: train_loss -0.9947 +2025-10-30 14:46:15.279430: val_loss -0.8768 +2025-10-30 14:46:15.281023: Pseudo dice [np.float32(0.982), np.float32(0.9886), np.float32(0.9943), np.float32(0.775)] +2025-10-30 14:46:15.282872: Epoch time: 22.33 s +2025-10-30 14:46:16.369639: +2025-10-30 14:46:16.371427: Epoch 969 +2025-10-30 14:46:16.373057: Current learning rate: 0.00044 +2025-10-30 14:46:37.686220: train_loss -0.9952 +2025-10-30 14:46:37.688872: val_loss -0.8769 +2025-10-30 14:46:37.690659: Pseudo dice [np.float32(0.9825), np.float32(0.9882), np.float32(0.9942), np.float32(0.7735)] +2025-10-30 14:46:37.692214: Epoch time: 21.32 s +2025-10-30 14:46:38.597805: +2025-10-30 14:46:38.601352: Epoch 970 +2025-10-30 14:46:38.605243: Current learning rate: 0.00043 +2025-10-30 14:47:00.162780: train_loss -0.995 +2025-10-30 14:47:00.167706: val_loss -0.8728 +2025-10-30 14:47:00.169744: Pseudo dice [np.float32(0.9817), np.float32(0.9879), np.float32(0.9943), np.float32(0.7636)] +2025-10-30 14:47:00.173422: Epoch time: 21.57 s +2025-10-30 14:47:01.319919: +2025-10-30 14:47:01.322085: Epoch 971 +2025-10-30 14:47:01.323864: Current learning rate: 0.00041 +2025-10-30 14:47:23.412903: train_loss -0.9954 +2025-10-30 14:47:23.418654: val_loss -0.8783 +2025-10-30 14:47:23.420705: Pseudo dice [np.float32(0.9812), np.float32(0.9884), np.float32(0.9944), np.float32(0.774)] +2025-10-30 14:47:23.422304: Epoch time: 22.09 s +2025-10-30 14:47:24.664409: +2025-10-30 14:47:24.666586: Epoch 972 +2025-10-30 14:47:24.668576: Current learning rate: 0.0004 +2025-10-30 14:47:46.958691: train_loss -0.9951 +2025-10-30 14:47:46.961840: val_loss -0.8819 +2025-10-30 14:47:46.963916: Pseudo dice [np.float32(0.9832), np.float32(0.9895), np.float32(0.9946), np.float32(0.7757)] +2025-10-30 14:47:46.965923: Epoch time: 22.3 s +2025-10-30 14:47:48.322433: +2025-10-30 14:47:48.325083: Epoch 973 +2025-10-30 14:47:48.326853: Current learning rate: 0.00039 +2025-10-30 14:48:10.254260: train_loss -0.9954 +2025-10-30 14:48:10.257512: val_loss -0.8763 +2025-10-30 14:48:10.259253: Pseudo dice [np.float32(0.9826), np.float32(0.9892), np.float32(0.9942), np.float32(0.7732)] +2025-10-30 14:48:10.260895: Epoch time: 21.93 s +2025-10-30 14:48:11.386753: +2025-10-30 14:48:11.389507: Epoch 974 +2025-10-30 14:48:11.391448: Current learning rate: 0.00037 +2025-10-30 14:48:33.567528: train_loss -0.9952 +2025-10-30 14:48:33.570557: val_loss -0.8727 +2025-10-30 14:48:33.572473: Pseudo dice [np.float32(0.9819), np.float32(0.9885), np.float32(0.9938), np.float32(0.7641)] +2025-10-30 14:48:33.574244: Epoch time: 22.18 s +2025-10-30 14:48:34.645248: +2025-10-30 14:48:34.648244: Epoch 975 +2025-10-30 14:48:34.650151: Current learning rate: 0.00036 +2025-10-30 14:48:56.334291: train_loss -0.995 +2025-10-30 14:48:56.337493: val_loss -0.8773 +2025-10-30 14:48:56.339707: Pseudo dice [np.float32(0.9824), np.float32(0.9883), np.float32(0.9943), np.float32(0.779)] +2025-10-30 14:48:56.342319: Epoch time: 21.69 s +2025-10-30 14:48:57.727033: +2025-10-30 14:48:57.732343: Epoch 976 +2025-10-30 14:48:57.734013: Current learning rate: 0.00035 +2025-10-30 14:49:19.069360: train_loss -0.9953 +2025-10-30 14:49:19.072115: val_loss -0.8796 +2025-10-30 14:49:19.074028: Pseudo dice [np.float32(0.9826), np.float32(0.989), np.float32(0.9944), np.float32(0.779)] +2025-10-30 14:49:19.075860: Epoch time: 21.34 s +2025-10-30 14:49:20.234026: +2025-10-30 14:49:20.237363: Epoch 977 +2025-10-30 14:49:20.238980: Current learning rate: 0.00034 +2025-10-30 14:49:42.767492: train_loss -0.9955 +2025-10-30 14:49:42.770576: val_loss -0.8797 +2025-10-30 14:49:42.772456: Pseudo dice [np.float32(0.9825), np.float32(0.9883), np.float32(0.9946), np.float32(0.7812)] +2025-10-30 14:49:42.774493: Epoch time: 22.54 s +2025-10-30 14:49:43.820473: +2025-10-30 14:49:43.822441: Epoch 978 +2025-10-30 14:49:43.824668: Current learning rate: 0.00032 +2025-10-30 14:50:06.170015: train_loss -0.9955 +2025-10-30 14:50:06.174122: val_loss -0.8777 +2025-10-30 14:50:06.176196: Pseudo dice [np.float32(0.9815), np.float32(0.9891), np.float32(0.9946), np.float32(0.7734)] +2025-10-30 14:50:06.177992: Epoch time: 22.35 s +2025-10-30 14:50:07.338209: +2025-10-30 14:50:07.340526: Epoch 979 +2025-10-30 14:50:07.343006: Current learning rate: 0.00031 +2025-10-30 14:50:29.539244: train_loss -0.9955 +2025-10-30 14:50:29.546868: val_loss -0.8761 +2025-10-30 14:50:29.549018: Pseudo dice [np.float32(0.9809), np.float32(0.9879), np.float32(0.9942), np.float32(0.7747)] +2025-10-30 14:50:29.553178: Epoch time: 22.2 s +2025-10-30 14:50:30.800263: +2025-10-30 14:50:30.805402: Epoch 980 +2025-10-30 14:50:30.810324: Current learning rate: 0.0003 +2025-10-30 14:50:53.603556: train_loss -0.9954 +2025-10-30 14:50:53.606272: val_loss -0.8725 +2025-10-30 14:50:53.609213: Pseudo dice [np.float32(0.9808), np.float32(0.9879), np.float32(0.9939), np.float32(0.7691)] +2025-10-30 14:50:53.610685: Epoch time: 22.8 s +2025-10-30 14:50:54.821711: +2025-10-30 14:50:54.824431: Epoch 981 +2025-10-30 14:50:54.826178: Current learning rate: 0.00028 +2025-10-30 14:51:16.810344: train_loss -0.9957 +2025-10-30 14:51:16.814415: val_loss -0.8763 +2025-10-30 14:51:16.816212: Pseudo dice [np.float32(0.9834), np.float32(0.9894), np.float32(0.9944), np.float32(0.7676)] +2025-10-30 14:51:16.817875: Epoch time: 21.99 s +2025-10-30 14:51:18.190100: +2025-10-30 14:51:18.192741: Epoch 982 +2025-10-30 14:51:18.194941: Current learning rate: 0.00027 +2025-10-30 14:51:40.318080: train_loss -0.9954 +2025-10-30 14:51:40.322293: val_loss -0.8772 +2025-10-30 14:51:40.325151: Pseudo dice [np.float32(0.9813), np.float32(0.9876), np.float32(0.9943), np.float32(0.7792)] +2025-10-30 14:51:40.327158: Epoch time: 22.13 s +2025-10-30 14:51:42.609742: +2025-10-30 14:51:42.615663: Epoch 983 +2025-10-30 14:51:42.619053: Current learning rate: 0.00026 +2025-10-30 14:52:04.428810: train_loss -0.9953 +2025-10-30 14:52:04.431790: val_loss -0.8756 +2025-10-30 14:52:04.433708: Pseudo dice [np.float32(0.9829), np.float32(0.9889), np.float32(0.9941), np.float32(0.7632)] +2025-10-30 14:52:04.435516: Epoch time: 21.82 s +2025-10-30 14:52:05.581286: +2025-10-30 14:52:05.583545: Epoch 984 +2025-10-30 14:52:05.585936: Current learning rate: 0.00024 +2025-10-30 14:52:28.225627: train_loss -0.9955 +2025-10-30 14:52:28.228702: val_loss -0.88 +2025-10-30 14:52:28.230600: Pseudo dice [np.float32(0.9822), np.float32(0.9889), np.float32(0.9943), np.float32(0.7784)] +2025-10-30 14:52:28.232450: Epoch time: 22.65 s +2025-10-30 14:52:29.645957: +2025-10-30 14:52:29.652453: Epoch 985 +2025-10-30 14:52:29.655314: Current learning rate: 0.00023 +2025-10-30 14:52:51.835474: train_loss -0.9956 +2025-10-30 14:52:51.838290: val_loss -0.882 +2025-10-30 14:52:51.840206: Pseudo dice [np.float32(0.9818), np.float32(0.9884), np.float32(0.9943), np.float32(0.786)] +2025-10-30 14:52:51.842041: Epoch time: 22.19 s +2025-10-30 14:52:52.963773: +2025-10-30 14:52:52.966054: Epoch 986 +2025-10-30 14:52:52.968283: Current learning rate: 0.00021 +2025-10-30 14:53:14.666884: train_loss -0.9956 +2025-10-30 14:53:14.669737: val_loss -0.8846 +2025-10-30 14:53:14.671387: Pseudo dice [np.float32(0.9819), np.float32(0.9884), np.float32(0.9944), np.float32(0.792)] +2025-10-30 14:53:14.673186: Epoch time: 21.7 s +2025-10-30 14:53:15.730525: +2025-10-30 14:53:15.732585: Epoch 987 +2025-10-30 14:53:15.734367: Current learning rate: 0.0002 +2025-10-30 14:53:36.858242: train_loss -0.9959 +2025-10-30 14:53:36.860445: val_loss -0.8798 +2025-10-30 14:53:36.862615: Pseudo dice [np.float32(0.981), np.float32(0.988), np.float32(0.9941), np.float32(0.7828)] +2025-10-30 14:53:36.864144: Epoch time: 21.13 s +2025-10-30 14:53:38.167580: +2025-10-30 14:53:38.169928: Epoch 988 +2025-10-30 14:53:38.172057: Current learning rate: 0.00019 +2025-10-30 14:54:00.183647: train_loss -0.9957 +2025-10-30 14:54:00.185898: val_loss -0.8807 +2025-10-30 14:54:00.188190: Pseudo dice [np.float32(0.9818), np.float32(0.9883), np.float32(0.9943), np.float32(0.7829)] +2025-10-30 14:54:00.189839: Epoch time: 22.02 s +2025-10-30 14:54:01.254887: +2025-10-30 14:54:01.259913: Epoch 989 +2025-10-30 14:54:01.263721: Current learning rate: 0.00017 +2025-10-30 14:54:22.287126: train_loss -0.9958 +2025-10-30 14:54:22.291936: val_loss -0.8763 +2025-10-30 14:54:22.294410: Pseudo dice [np.float32(0.9829), np.float32(0.9885), np.float32(0.9943), np.float32(0.777)] +2025-10-30 14:54:22.296463: Epoch time: 21.03 s +2025-10-30 14:54:23.573800: +2025-10-30 14:54:23.575897: Epoch 990 +2025-10-30 14:54:23.577990: Current learning rate: 0.00016 +2025-10-30 14:54:45.908880: train_loss -0.9959 +2025-10-30 14:54:45.911877: val_loss -0.8734 +2025-10-30 14:54:45.913996: Pseudo dice [np.float32(0.9818), np.float32(0.9884), np.float32(0.9941), np.float32(0.7647)] +2025-10-30 14:54:45.916019: Epoch time: 22.34 s +2025-10-30 14:54:47.157199: +2025-10-30 14:54:47.161426: Epoch 991 +2025-10-30 14:54:47.164350: Current learning rate: 0.00014 +2025-10-30 14:55:09.282152: train_loss -0.9952 +2025-10-30 14:55:09.284879: val_loss -0.8786 +2025-10-30 14:55:09.286666: Pseudo dice [np.float32(0.9833), np.float32(0.989), np.float32(0.9944), np.float32(0.7754)] +2025-10-30 14:55:09.288364: Epoch time: 22.13 s +2025-10-30 14:55:10.434898: +2025-10-30 14:55:10.438545: Epoch 992 +2025-10-30 14:55:10.440644: Current learning rate: 0.00013 +2025-10-30 14:55:32.366325: train_loss -0.9955 +2025-10-30 14:55:32.368959: val_loss -0.8754 +2025-10-30 14:55:32.370807: Pseudo dice [np.float32(0.9825), np.float32(0.9887), np.float32(0.994), np.float32(0.7706)] +2025-10-30 14:55:32.373438: Epoch time: 21.93 s +2025-10-30 14:55:33.469873: +2025-10-30 14:55:33.471871: Epoch 993 +2025-10-30 14:55:33.473786: Current learning rate: 0.00011 +2025-10-30 14:55:55.071830: train_loss -0.9958 +2025-10-30 14:55:55.075180: val_loss -0.8796 +2025-10-30 14:55:55.076952: Pseudo dice [np.float32(0.9824), np.float32(0.9887), np.float32(0.9944), np.float32(0.7805)] +2025-10-30 14:55:55.078802: Epoch time: 21.6 s +2025-10-30 14:55:56.152083: +2025-10-30 14:55:56.154190: Epoch 994 +2025-10-30 14:55:56.155835: Current learning rate: 0.0001 +2025-10-30 14:56:18.395177: train_loss -0.9958 +2025-10-30 14:56:18.398227: val_loss -0.8726 +2025-10-30 14:56:18.401733: Pseudo dice [np.float32(0.9825), np.float32(0.9885), np.float32(0.9943), np.float32(0.7661)] +2025-10-30 14:56:18.404088: Epoch time: 22.24 s +2025-10-30 14:56:19.532670: +2025-10-30 14:56:19.534825: Epoch 995 +2025-10-30 14:56:19.536767: Current learning rate: 8e-05 +2025-10-30 14:56:40.865266: train_loss -0.9958 +2025-10-30 14:56:40.868210: val_loss -0.871 +2025-10-30 14:56:40.870970: Pseudo dice [np.float32(0.9812), np.float32(0.9883), np.float32(0.9941), np.float32(0.7626)] +2025-10-30 14:56:40.875478: Epoch time: 21.33 s +2025-10-30 14:56:42.164900: +2025-10-30 14:56:42.166982: Epoch 996 +2025-10-30 14:56:42.168814: Current learning rate: 7e-05 +2025-10-30 14:57:04.307052: train_loss -0.9957 +2025-10-30 14:57:04.309572: val_loss -0.8771 +2025-10-30 14:57:04.311691: Pseudo dice [np.float32(0.9826), np.float32(0.9889), np.float32(0.9943), np.float32(0.7726)] +2025-10-30 14:57:04.314273: Epoch time: 22.14 s +2025-10-30 14:57:05.368469: +2025-10-30 14:57:05.370350: Epoch 997 +2025-10-30 14:57:05.372213: Current learning rate: 5e-05 +2025-10-30 14:57:27.620081: train_loss -0.9954 +2025-10-30 14:57:27.622765: val_loss -0.8749 +2025-10-30 14:57:27.624650: Pseudo dice [np.float32(0.9826), np.float32(0.9883), np.float32(0.9944), np.float32(0.775)] +2025-10-30 14:57:27.626631: Epoch time: 22.25 s +2025-10-30 14:57:28.691029: +2025-10-30 14:57:28.693297: Epoch 998 +2025-10-30 14:57:28.695836: Current learning rate: 4e-05 +2025-10-30 14:57:51.107985: train_loss -0.9957 +2025-10-30 14:57:51.114570: val_loss -0.8763 +2025-10-30 14:57:51.123165: Pseudo dice [np.float32(0.9817), np.float32(0.9879), np.float32(0.9942), np.float32(0.7786)] +2025-10-30 14:57:51.130253: Epoch time: 22.42 s +2025-10-30 14:57:52.380890: +2025-10-30 14:57:52.383936: Epoch 999 +2025-10-30 14:57:52.386048: Current learning rate: 2e-05 +2025-10-30 14:58:13.835032: train_loss -0.9958 +2025-10-30 14:58:13.840452: val_loss -0.8743 +2025-10-30 14:58:13.842871: Pseudo dice [np.float32(0.9829), np.float32(0.9883), np.float32(0.9937), np.float32(0.771)] +2025-10-30 14:58:13.845536: Epoch time: 21.46 s +2025-10-30 14:58:16.926297: Training done. +2025-10-30 14:58:16.986061: Using splits from existing split file: /hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/splits_final.json +2025-10-30 14:58:16.992994: The split file contains 5 splits. +2025-10-30 14:58:16.995306: Desired fold for training: 0 +2025-10-30 14:58:16.996834: This split has 86 training and 22 validation cases. +2025-10-30 14:58:17.000247: predicting fish0004 +2025-10-30 14:58:17.009305: fish0004, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 14:58:56.142102: predicting fish0009 +2025-10-30 14:58:56.153443: fish0009, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 14:58:56.203947: predicting fish0013 +2025-10-30 14:58:56.210703: fish0013, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 14:58:56.271377: predicting fish0016 +2025-10-30 14:58:56.277425: fish0016, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 14:58:56.326271: predicting fish0019 +2025-10-30 14:58:56.337129: fish0019, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 14:58:56.376226: predicting fish0028 +2025-10-30 14:58:56.380808: fish0028, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 14:58:56.477688: predicting fish0033 +2025-10-30 14:58:56.484635: fish0033, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 14:58:56.565883: predicting fish0039 +2025-10-30 14:58:56.571161: fish0039, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 14:58:56.658450: predicting fish0040 +2025-10-30 14:58:56.663496: fish0040, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 14:58:56.727435: predicting fish0042 +2025-10-30 14:58:56.738132: fish0042, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 14:58:56.788047: predicting fish0049 +2025-10-30 14:58:56.803065: fish0049, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 14:58:56.871346: predicting fish0052 +2025-10-30 14:58:56.879647: fish0052, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 14:58:56.937495: predicting fish0054 +2025-10-30 14:58:56.943048: fish0054, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 14:58:56.987388: predicting fish0058 +2025-10-30 14:58:56.992518: fish0058, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 14:58:57.044816: predicting fish0060 +2025-10-30 14:58:57.051744: fish0060, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 14:58:57.096479: predicting fish0062 +2025-10-30 14:58:57.103278: fish0062, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 14:58:57.149484: predicting fish0063 +2025-10-30 14:58:57.154955: fish0063, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 14:58:57.195054: predicting fish0074 +2025-10-30 14:58:57.200902: fish0074, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 14:58:57.247746: predicting fish0078 +2025-10-30 14:58:57.277793: fish0078, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 14:58:57.317861: predicting fish0089 +2025-10-30 14:58:57.337288: fish0089, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 14:58:57.394508: predicting fish0092 +2025-10-30 14:58:57.399599: fish0092, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 14:58:57.441347: predicting fish0094 +2025-10-30 14:58:57.460579: fish0094, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 14:59:07.471822: Validation complete +2025-10-30 14:59:07.474955: Mean Validation Dice: 0.9381609999853798 diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0004.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0004.png new file mode 100644 index 0000000000000000000000000000000000000000..807ad47bec970580bd6a4f9a836366ede34a3d1a Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0004.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0009.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0009.png new file mode 100644 index 0000000000000000000000000000000000000000..c6e79ec081ae3ab356855871a946e56cb5ecb8aa Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0009.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0013.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0013.png new file mode 100644 index 0000000000000000000000000000000000000000..a53a57f5923f372f3a795655bb125566f31f01b3 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0013.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0016.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0016.png new file mode 100644 index 0000000000000000000000000000000000000000..da3b3ef070bde2fcfcb9a2cf642d05a8cf56c64f Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0016.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0019.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0019.png new file mode 100644 index 0000000000000000000000000000000000000000..c26396dfe35556932afe60c8e71bd98578329021 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0019.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0028.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0028.png new file mode 100644 index 0000000000000000000000000000000000000000..b4d29937771eb7da211c75d918237b5171159422 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0028.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0033.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0033.png new file mode 100644 index 0000000000000000000000000000000000000000..bfe16ac2ad5372a8fc29c2ce10010bc4f12ad623 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0033.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0039.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0039.png new file mode 100644 index 0000000000000000000000000000000000000000..a7821b09dbd88e7f1b948e0a3c7c0cb583d66a5b Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0039.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0040.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0040.png new file mode 100644 index 0000000000000000000000000000000000000000..864b20108a76a5f6251ff3826c07cec52146722a Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0040.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0042.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0042.png new file mode 100644 index 0000000000000000000000000000000000000000..f3f424f23171d80daad97b2a8348a6d51e52591e Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0042.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0049.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0049.png new file mode 100644 index 0000000000000000000000000000000000000000..b0a51925141f0c6bf2a8d3f77007c1703135b605 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0049.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0052.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0052.png new file mode 100644 index 0000000000000000000000000000000000000000..3881fbfd1d21d9f1d1d6680596d8f6a5b783569d Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0052.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0054.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0054.png new file mode 100644 index 0000000000000000000000000000000000000000..2f05d1e96453c03d7a37fd1769bb2ce706be06e4 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0054.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0058.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0058.png new file mode 100644 index 0000000000000000000000000000000000000000..c27aba75f56bfc639c7f1a11fc22e912cde9ceee Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0058.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0060.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0060.png new file mode 100644 index 0000000000000000000000000000000000000000..64b3028a2512b0075f3285b7b9844138eeee6716 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0060.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0062.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0062.png new file mode 100644 index 0000000000000000000000000000000000000000..43b99a24a50a2df8f79807f692b3fd36442f085b Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0062.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0063.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0063.png new file mode 100644 index 0000000000000000000000000000000000000000..d861bcbb73a717885d2b3a4f281b9d560259a795 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0063.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0074.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0074.png new file mode 100644 index 0000000000000000000000000000000000000000..64dcc15df6cde9f10a13d9c4cfd69acb2538f150 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0074.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0078.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0078.png new file mode 100644 index 0000000000000000000000000000000000000000..6d6a0f5c0721aae7224ae484a88517124930e370 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0078.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0089.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0089.png new file mode 100644 index 0000000000000000000000000000000000000000..0713bca0dc24822f9bda3cea9b4ec37b84aa2176 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0089.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0092.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0092.png new file mode 100644 index 0000000000000000000000000000000000000000..f20011137e4796199457814d5b79333df71f4ac6 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0092.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0094.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0094.png new file mode 100644 index 0000000000000000000000000000000000000000..c2182a76c89225656ae370d832ba0e0768d84a93 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0094.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/summary.json b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/summary.json new file mode 100644 index 0000000000000000000000000000000000000000..b9a7080053a5076511f24e98168f30b918a857fb --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/summary.json @@ -0,0 +1,1068 @@ +{ + "foreground_mean": { + "Dice": 0.9381609999853798, + "FN": 141.70454545454544, + "FP": 128.14772727272728, + "IoU": 0.8973557637396948, + "TN": 92626.94318181818, + "TP": 11551.204545454544, + "n_pred": 11679.352272727274, + "n_ref": 11692.909090909092 + }, + "mean": { + "1": { + "Dice": 0.9820573832820152, + "FN": 87.22727272727273, + "FP": 130.6818181818182, + "IoU": 0.9650193424393703, + "TN": 98239.04545454546, + "TP": 5991.045454545455, + "n_pred": 6121.727272727273, + "n_ref": 6078.272727272727 + }, + "2": { + "Dice": 0.9883763726706863, + "FN": 153.77272727272728, + "FP": 88.54545454545455, + "IoU": 0.9771657747700953, + "TN": 93366.63636363637, + "TP": 10839.045454545454, + "n_pred": 10927.59090909091, + "n_ref": 10992.818181818182 + }, + "3": { + "Dice": 0.9945642882669948, + "FN": 178.9090909090909, + "FP": 129.3181818181818, + "IoU": 0.9892015915985823, + "TN": 75350.68181818182, + "TP": 28789.090909090908, + "n_pred": 28918.409090909092, + "n_ref": 28968.0 + }, + "4": { + "Dice": 0.7876459557218229, + "FN": 146.9090909090909, + "FP": 164.04545454545453, + "IoU": 0.6580363461507317, + "TN": 103551.40909090909, + "TP": 585.6363636363636, + "n_pred": 749.6818181818181, + "n_ref": 732.5454545454545 + } + }, + "metric_per_case": [ + { + "metrics": { + "1": { + "Dice": 0.9967478385024193, + "FN": 41, + "FP": 0, + "IoU": 0.993516761543327, + "TN": 98124, + "TP": 6283, + "n_pred": 6283, + "n_ref": 6324 + }, + "2": { + "Dice": 0.9965562053281352, + "FN": 65, + "FP": 41, + "IoU": 0.9931360486952017, + "TN": 89005, + "TP": 15337, + "n_pred": 15378, + "n_ref": 15402 + }, + "3": { + "Dice": 0.9991230082167384, + "FN": 0, + "FP": 65, + "IoU": 0.9982475533148203, + "TN": 67357, + "TP": 37026, + "n_pred": 37091, + "n_ref": 37026 + }, + "4": { + "Dice": 0.8942465753424658, + "FN": 0, + "FP": 193, + "IoU": 0.8087215064420218, + "TN": 103439, + "TP": 816, + "n_pred": 1009, + "n_ref": 816 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0004.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0004.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9855023600809171, + "FN": 70, + "FP": 102, + "IoU": 0.9714190761050183, + "TN": 98430, + "TP": 5846, + "n_pred": 5948, + "n_ref": 5916 + }, + "2": { + "Dice": 0.9951391957578436, + "FN": 144, + "FP": 21, + "IoU": 0.990325417766051, + "TN": 87393, + "TP": 16890, + "n_pred": 16911, + "n_ref": 17034 + }, + "3": { + "Dice": 0.9931855290323451, + "FN": 21, + "FP": 484, + "IoU": 0.9864633034900552, + "TN": 67142, + "TP": 36801, + "n_pred": 37285, + "n_ref": 36822 + }, + "4": { + "Dice": 0.7848678213309025, + "FN": 465, + "FP": 7, + "IoU": 0.6459114778694673, + "TN": 103115, + "TP": 861, + "n_pred": 868, + "n_ref": 1326 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0009.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0009.png" + }, + { + "metrics": { + "1": { + "Dice": 0.991869918699187, + "FN": 0, + "FP": 102, + "IoU": 0.9838709677419355, + "TN": 98124, + "TP": 6222, + "n_pred": 6324, + "n_ref": 6222 + }, + "2": { + "Dice": 0.9982025164769323, + "FN": 0, + "FP": 36, + "IoU": 0.9964114832535885, + "TN": 94416, + "TP": 9996, + "n_pred": 10032, + "n_ref": 9996 + }, + "3": { + "Dice": 0.9955406911928651, + "FN": 36, + "FP": 204, + "IoU": 0.9911209766925638, + "TN": 77418, + "TP": 26790, + "n_pred": 26994, + "n_ref": 26826 + }, + "4": { + "Dice": 0.6857551896921976, + "FN": 439, + "FP": 0, + "IoU": 0.5217864923747276, + "TN": 103530, + "TP": 479, + "n_pred": 479, + "n_ref": 918 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0013.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0013.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9885645741703318, + "FN": 143, + "FP": 0, + "IoU": 0.9773877292852625, + "TN": 98124, + "TP": 6181, + "n_pred": 6181, + "n_ref": 6324 + }, + "2": { + "Dice": 0.994413407821229, + "FN": 102, + "FP": 0, + "IoU": 0.9888888888888889, + "TN": 95268, + "TP": 9078, + "n_pred": 9078, + "n_ref": 9180 + }, + "3": { + "Dice": 0.9960629921259843, + "FN": 102, + "FP": 102, + "IoU": 0.9921568627450981, + "TN": 78438, + "TP": 25806, + "n_pred": 25908, + "n_ref": 25908 + }, + "4": { + "Dice": 0.875, + "FN": 0, + "FP": 204, + "IoU": 0.7777777777777778, + "TN": 103530, + "TP": 714, + "n_pred": 918, + "n_ref": 714 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0016.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0016.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9642857142857143, + "FN": 0, + "FP": 408, + "IoU": 0.9310344827586207, + "TN": 98532, + "TP": 5508, + "n_pred": 5916, + "n_ref": 5508 + }, + "2": { + "Dice": 0.9716944552151997, + "FN": 584, + "FP": 0, + "IoU": 0.944947209653092, + "TN": 93840, + "TP": 10024, + "n_pred": 10024, + "n_ref": 10608 + }, + "3": { + "Dice": 0.9891803871901574, + "FN": 0, + "FP": 598, + "IoU": 0.9785923963628553, + "TN": 76514, + "TP": 27336, + "n_pred": 27934, + "n_ref": 27336 + }, + "4": { + "Dice": 0.6543535620052771, + "FN": 524, + "FP": 0, + "IoU": 0.48627450980392156, + "TN": 103428, + "TP": 496, + "n_pred": 496, + "n_ref": 1020 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0019.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0019.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9860821735144596, + "FN": 0, + "FP": 167, + "IoU": 0.9725464409008713, + "TN": 98365, + "TP": 5916, + "n_pred": 6083, + "n_ref": 5916 + }, + "2": { + "Dice": 0.99449115685706, + "FN": 133, + "FP": 0, + "IoU": 0.989042675893887, + "TN": 92310, + "TP": 12005, + "n_pred": 12005, + "n_ref": 12138 + }, + "3": { + "Dice": 0.9951792007447303, + "FN": 259, + "FP": 31, + "IoU": 0.9904046587036363, + "TN": 74225, + "TP": 29933, + "n_pred": 29964, + "n_ref": 30192 + }, + "4": { + "Dice": 0.7900852052672347, + "FN": 0, + "FP": 271, + "IoU": 0.6530089628681178, + "TN": 103667, + "TP": 510, + "n_pred": 781, + "n_ref": 510 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0028.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0028.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9628501827040195, + "FN": 0, + "FP": 488, + "IoU": 0.9283617146212566, + "TN": 97636, + "TP": 6324, + "n_pred": 6812, + "n_ref": 6324 + }, + "2": { + "Dice": 0.9799509591807298, + "FN": 417, + "FP": 0, + "IoU": 0.9606900452488688, + "TN": 93840, + "TP": 10191, + "n_pred": 10191, + "n_ref": 10608 + }, + "3": { + "Dice": 0.9964815092079653, + "FN": 0, + "FP": 188, + "IoU": 0.992987691160015, + "TN": 77638, + "TP": 26622, + "n_pred": 26810, + "n_ref": 26622 + }, + "4": { + "Dice": 0.8, + "FN": 102, + "FP": 102, + "IoU": 0.6666666666666666, + "TN": 103836, + "TP": 408, + "n_pred": 510, + "n_ref": 510 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0033.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0033.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9666666666666667, + "FN": 0, + "FP": 408, + "IoU": 0.9354838709677419, + "TN": 98124, + "TP": 5916, + "n_pred": 6324, + "n_ref": 5916 + }, + "2": { + "Dice": 0.9811074918566776, + "FN": 348, + "FP": 0, + "IoU": 0.9629156010230179, + "TN": 95064, + "TP": 9036, + "n_pred": 9036, + "n_ref": 9384 + }, + "3": { + "Dice": 0.9940455341506129, + "FN": 264, + "FP": 42, + "IoU": 0.9881615598885793, + "TN": 78600, + "TP": 25542, + "n_pred": 25584, + "n_ref": 25806 + }, + "4": { + "Dice": 0.769811320754717, + "FN": 102, + "FP": 264, + "IoU": 0.6257668711656442, + "TN": 103470, + "TP": 612, + "n_pred": 876, + "n_ref": 714 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0039.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0039.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9871542280715581, + "FN": 61, + "FP": 102, + "IoU": 0.97463429816371, + "TN": 98022, + "TP": 6263, + "n_pred": 6365, + "n_ref": 6324 + }, + "2": { + "Dice": 0.9941710463449593, + "FN": 102, + "FP": 20, + "IoU": 0.9884096522895687, + "TN": 93922, + "TP": 10404, + "n_pred": 10424, + "n_ref": 10506 + }, + "3": { + "Dice": 0.9992921356268138, + "FN": 20, + "FP": 20, + "IoU": 0.9985852726886892, + "TN": 76174, + "TP": 28234, + "n_pred": 28254, + "n_ref": 28254 + }, + "4": { + "Dice": 0.9857954545454546, + "FN": 20, + "FP": 0, + "IoU": 0.9719887955182073, + "TN": 103734, + "TP": 694, + "n_pred": 694, + "n_ref": 714 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0040.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0040.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9916551891760512, + "FN": 0, + "FP": 103, + "IoU": 0.9834484975092399, + "TN": 98225, + "TP": 6120, + "n_pred": 6223, + "n_ref": 6120 + }, + "2": { + "Dice": 0.991860712010758, + "FN": 31, + "FP": 84, + "IoU": 0.983852850322943, + "TN": 97326, + "TP": 7007, + "n_pred": 7091, + "n_ref": 7038 + }, + "3": { + "Dice": 0.9920372412103393, + "FN": 84, + "FP": 306, + "IoU": 0.9842002916869227, + "TN": 79764, + "TP": 24294, + "n_pred": 24600, + "n_ref": 24378 + }, + "4": { + "Dice": 0.5911602209944752, + "FN": 592, + "FP": 0, + "IoU": 0.4196078431372549, + "TN": 103428, + "TP": 428, + "n_pred": 428, + "n_ref": 1020 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0042.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0042.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9711451012815213, + "FN": 349, + "FP": 0, + "IoU": 0.9439087110253938, + "TN": 98226, + "TP": 5873, + "n_pred": 5873, + "n_ref": 6222 + }, + "2": { + "Dice": 0.9693034802119636, + "FN": 354, + "FP": 289, + "IoU": 0.9404353867531264, + "TN": 93653, + "TP": 10152, + "n_pred": 10441, + "n_ref": 10506 + }, + "3": { + "Dice": 0.9916354831609069, + "FN": 102, + "FP": 354, + "IoU": 0.9834097358655316, + "TN": 76962, + "TP": 27030, + "n_pred": 27384, + "n_ref": 27132 + }, + "4": { + "Dice": 0.7673716012084593, + "FN": 129, + "FP": 102, + "IoU": 0.6225490196078431, + "TN": 103836, + "TP": 381, + "n_pred": 483, + "n_ref": 510 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0049.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0049.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9852652259332023, + "FN": 0, + "FP": 180, + "IoU": 0.9709583736689255, + "TN": 98250, + "TP": 6018, + "n_pred": 6198, + "n_ref": 6018 + }, + "2": { + "Dice": 0.9842931937172775, + "FN": 102, + "FP": 204, + "IoU": 0.9690721649484536, + "TN": 94554, + "TP": 9588, + "n_pred": 9792, + "n_ref": 9690 + }, + "3": { + "Dice": 0.9932140653917335, + "FN": 374, + "FP": 0, + "IoU": 0.9865196078431373, + "TN": 76704, + "TP": 27370, + "n_pred": 27370, + "n_ref": 27744 + }, + "4": { + "Dice": 0.8780487804878049, + "FN": 0, + "FP": 170, + "IoU": 0.782608695652174, + "TN": 103666, + "TP": 612, + "n_pred": 782, + "n_ref": 612 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0052.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0052.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9593414816662509, + "FN": 147, + "FP": 342, + "IoU": 0.9218600191754555, + "TN": 98190, + "TP": 5769, + "n_pred": 6111, + "n_ref": 5916 + }, + "2": { + "Dice": 0.9759144693374977, + "FN": 342, + "FP": 59, + "IoU": 0.9529618768328446, + "TN": 95923, + "TP": 8124, + "n_pred": 8183, + "n_ref": 8466 + }, + "3": { + "Dice": 0.9927190559879487, + "FN": 348, + "FP": 0, + "IoU": 0.985543369890329, + "TN": 80376, + "TP": 23724, + "n_pred": 23724, + "n_ref": 24072 + }, + "4": { + "Dice": 0.7717140661029976, + "FN": 8, + "FP": 289, + "IoU": 0.6282853566958698, + "TN": 103649, + "TP": 502, + "n_pred": 791, + "n_ref": 510 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0054.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0054.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9900128040973112, + "FN": 117, + "FP": 0, + "IoU": 0.9802231237322515, + "TN": 98532, + "TP": 5799, + "n_pred": 5799, + "n_ref": 5916 + }, + "2": { + "Dice": 0.9925226288862653, + "FN": 75, + "FP": 96, + "IoU": 0.98515625, + "TN": 92928, + "TP": 11349, + "n_pred": 11445, + "n_ref": 11424 + }, + "3": { + "Dice": 0.9965586127012372, + "FN": 0, + "FP": 205, + "IoU": 0.9931408304614047, + "TN": 74561, + "TP": 29682, + "n_pred": 29887, + "n_ref": 29682 + }, + "4": { + "Dice": 0.7776298268974701, + "FN": 334, + "FP": 0, + "IoU": 0.6361655773420479, + "TN": 103530, + "TP": 584, + "n_pred": 584, + "n_ref": 918 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0058.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0058.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9790340378575673, + "FN": 47, + "FP": 200, + "IoU": 0.958929165281011, + "TN": 98434, + "TP": 5767, + "n_pred": 5967, + "n_ref": 5814 + }, + "2": { + "Dice": 0.99019800039208, + "FN": 200, + "FP": 0, + "IoU": 0.98058629392351, + "TN": 94146, + "TP": 10102, + "n_pred": 10102, + "n_ref": 10302 + }, + "3": { + "Dice": 0.9962962962962963, + "FN": 204, + "FP": 0, + "IoU": 0.992619926199262, + "TN": 76806, + "TP": 27438, + "n_pred": 27438, + "n_ref": 27642 + }, + "4": { + "Dice": 0.8333333333333334, + "FN": 0, + "FP": 204, + "IoU": 0.7142857142857143, + "TN": 103734, + "TP": 510, + "n_pred": 714, + "n_ref": 510 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0060.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0060.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9612866725935505, + "FN": 479, + "FP": 0, + "IoU": 0.925459072517896, + "TN": 98022, + "TP": 5947, + "n_pred": 5947, + "n_ref": 6426 + }, + "2": { + "Dice": 0.9790794979079498, + "FN": 42, + "FP": 488, + "IoU": 0.9590163934426229, + "TN": 91516, + "TP": 12402, + "n_pred": 12890, + "n_ref": 12444 + }, + "3": { + "Dice": 0.994117915279741, + "FN": 345, + "FP": 42, + "IoU": 0.9883046237533998, + "TN": 71358, + "TP": 32703, + "n_pred": 32745, + "n_ref": 33048 + }, + "4": { + "Dice": 0.7482292337411461, + "FN": 31, + "FP": 360, + "IoU": 0.5977366255144033, + "TN": 103476, + "TP": 581, + "n_pred": 941, + "n_ref": 612 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0062.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0062.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9927641099855282, + "FN": 85, + "FP": 0, + "IoU": 0.985632183908046, + "TN": 98532, + "TP": 5831, + "n_pred": 5831, + "n_ref": 5916 + }, + "2": { + "Dice": 1.0, + "FN": 0, + "FP": 0, + "IoU": 1.0, + "TN": 94044, + "TP": 10404, + "n_pred": 10404, + "n_ref": 10404 + }, + "3": { + "Dice": 0.9966907395557181, + "FN": 181, + "FP": 0, + "IoU": 0.9934033092791019, + "TN": 77010, + "TP": 27257, + "n_pred": 27257, + "n_ref": 27438 + }, + "4": { + "Dice": 0.7424931756141947, + "FN": 0, + "FP": 283, + "IoU": 0.5904486251808972, + "TN": 103757, + "TP": 408, + "n_pred": 691, + "n_ref": 408 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0063.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0063.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9849904635541918, + "FN": 79, + "FP": 102, + "IoU": 0.9704248366013072, + "TN": 98328, + "TP": 5939, + "n_pred": 6041, + "n_ref": 6018 + }, + "2": { + "Dice": 0.9873417721518988, + "FN": 102, + "FP": 204, + "IoU": 0.975, + "TN": 92208, + "TP": 11934, + "n_pred": 12138, + "n_ref": 12036 + }, + "3": { + "Dice": 0.9949028248215989, + "FN": 244, + "FP": 66, + "IoU": 0.9898573485145923, + "TN": 73884, + "TP": 30254, + "n_pred": 30320, + "n_ref": 30498 + }, + "4": { + "Dice": 0.8782201405152225, + "FN": 168, + "FP": 40, + "IoU": 0.7828810020876826, + "TN": 103490, + "TP": 750, + "n_pred": 790, + "n_ref": 918 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0074.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0074.png" + }, + { + "metrics": { + "1": { + "Dice": 0.983744100681699, + "FN": 84, + "FP": 102, + "IoU": 0.9680082559339526, + "TN": 98634, + "TP": 5628, + "n_pred": 5730, + "n_ref": 5712 + }, + "2": { + "Dice": 0.9855589980570288, + "FN": 102, + "FP": 173, + "IoU": 0.9715291438037064, + "TN": 94789, + "TP": 9384, + "n_pred": 9557, + "n_ref": 9486 + }, + "3": { + "Dice": 0.9889675863509485, + "FN": 581, + "FP": 0, + "IoU": 0.9781759447073849, + "TN": 77826, + "TP": 26041, + "n_pred": 26041, + "n_ref": 26622 + }, + "4": { + "Dice": 0.6876340243030736, + "FN": 29, + "FP": 408, + "IoU": 0.5239651416122004, + "TN": 103530, + "TP": 481, + "n_pred": 889, + "n_ref": 510 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0078.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0078.png" + }, + { + "metrics": { + "1": { + "Dice": 1.0, + "FN": 0, + "FP": 0, + "IoU": 1.0, + "TN": 98022, + "TP": 6426, + "n_pred": 6426, + "n_ref": 6426 + }, + "2": { + "Dice": 0.9987644151565074, + "FN": 36, + "FP": 0, + "IoU": 0.9975318798848211, + "TN": 89862, + "TP": 14550, + "n_pred": 14550, + "n_ref": 14586 + }, + "3": { + "Dice": 0.9948793599909218, + "FN": 325, + "FP": 36, + "IoU": 0.989810894721987, + "TN": 69018, + "TP": 35069, + "n_pred": 35105, + "n_ref": 35394 + }, + "4": { + "Dice": 0.7634285714285715, + "FN": 46, + "FP": 368, + "IoU": 0.6173752310536045, + "TN": 103366, + "TP": 668, + "n_pred": 1036, + "n_ref": 714 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0089.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0089.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9816397326338946, + "FN": 217, + "FP": 0, + "IoU": 0.9639415088069127, + "TN": 98430, + "TP": 5801, + "n_pred": 5801, + "n_ref": 6018 + }, + "2": { + "Dice": 0.9885946448675902, + "FN": 0, + "FP": 233, + "IoU": 0.9774465201819765, + "TN": 94117, + "TP": 10098, + "n_pred": 10331, + "n_ref": 10098 + }, + "3": { + "Dice": 0.9925373134328358, + "FN": 408, + "FP": 0, + "IoU": 0.9851851851851852, + "TN": 76908, + "TP": 27132, + "n_pred": 27132, + "n_ref": 27540 + }, + "4": { + "Dice": 0.831858407079646, + "FN": 17, + "FP": 306, + "IoU": 0.7121212121212122, + "TN": 103326, + "TP": 799, + "n_pred": 1105, + "n_ref": 816 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0092.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0092.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9946598560482934, + "FN": 0, + "FP": 69, + "IoU": 0.9893764434180139, + "TN": 97953, + "TP": 6426, + "n_pred": 6495, + "n_ref": 6426 + }, + "2": { + "Dice": 0.9951219512195122, + "FN": 102, + "FP": 0, + "IoU": 0.9902912621359223, + "TN": 93942, + "TP": 10404, + "n_pred": 10404, + "n_ref": 10506 + }, + "3": { + "Dice": 0.9977668602054489, + "FN": 38, + "FP": 102, + "IoU": 0.9955436720142602, + "TN": 73032, + "TP": 31276, + "n_pred": 31378, + "n_ref": 31314 + }, + "4": { + "Dice": 0.817174515235457, + "FN": 226, + "FP": 38, + "IoU": 0.6908665105386417, + "TN": 103594, + "TP": 590, + "n_pred": 628, + "n_ref": 816 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_0/validation/fish0094.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0094.png" + } + ] +} \ No newline at end of file diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/checkpoint_best.pth b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/checkpoint_best.pth new file mode 100644 index 0000000000000000000000000000000000000000..4aa6e1db8e27f6bba9271a65bec8141002678a8e --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/checkpoint_best.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f36c0c535fc77dfaaf48f387db4745124a480fb29132b815f0279f0c5ec5e6bc +size 358310658 diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/checkpoint_final.pth b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/checkpoint_final.pth new file mode 100644 index 0000000000000000000000000000000000000000..e95671df226b8499d7508099c0ccb924be0615a3 --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/checkpoint_final.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:700690b2672a32c681e76c356bb1a68e7874ba8c63110d1b138a9d1ce60d1f4a +size 358732270 diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/debug.json b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/debug.json new file mode 100644 index 0000000000000000000000000000000000000000..abf2338443ad2e163afc3b1c1205fecb8cfe266d --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/debug.json @@ -0,0 +1,53 @@ +{ + "_best_ema": "None", + "batch_size": "5", + "configuration_manager": "{'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 5, 'patch_size': [1024, 112], 'median_image_size_in_voxels': [1024.0, 102.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['ZScoreNormalization'], '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': 8, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 1], [2, 1], [2, 1]], 'n_conv_per_stage': [2, 2, 2, 2, 2, 2, 2, 2], 'n_conv_per_stage_decoder': [2, 2, 2, 2, 2, 2, 2], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}", + "configuration_name": "2d", + "cudnn_version": 90100, + "current_epoch": "0", + "dataloader_train": "", + "dataloader_train.generator": "", + "dataloader_train.num_processes": "12", + "dataloader_train.transform": "None", + "dataloader_val": "", + "dataloader_val.generator": "", + "dataloader_val.num_processes": "6", + "dataloader_val.transform": "None", + "dataset_json": "{'channel_names': {'0': '\u00b5OCT'}, 'labels': {'background': 0, 'Retina': 1, 'VCD': 2, 'lens': 3, 'cornea': 4}, 'numTraining': 108, 'file_ending': '.png'}", + "device": "cuda:0", + "disable_checkpointing": "False", + "enable_deep_supervision": "True", + "fold": "1", + "folder_with_segs_from_previous_stage": "None", + "gpu_name": "NVIDIA A100 80GB PCIe", + "grad_scaler": "", + "hostname": "hpc5", + "inference_allowed_mirroring_axes": "(0, 1)", + "initial_lr": "0.01", + "is_cascaded": "False", + "is_ddp": "False", + "label_manager": "", + "local_rank": "0", + "log_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/training_log_2025_10_30_14_59_19.txt", + "logger": "", + "loss": "DeepSupervisionWrapper(\n (loss): DC_and_CE_loss(\n (ce): RobustCrossEntropyLoss()\n (dc): OptimizedModule(\n (_orig_mod): MemoryEfficientSoftDiceLoss()\n )\n )\n)", + "lr_scheduler": "", + "my_init_kwargs": "{'plans': {'dataset_name': 'Dataset001_zebrafish', 'plans_name': 'nnUNetPlans', 'original_median_spacing_after_transp': [999.0, 1.0, 1.0], 'original_median_shape_after_transp': [1, 1024, 102], 'image_reader_writer': 'NaturalImage2DIO', 'transpose_forward': [0, 1, 2], 'transpose_backward': [0, 1, 2], 'configurations': {'2d': {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 5, 'patch_size': [1024, 112], 'median_image_size_in_voxels': [1024.0, 102.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['ZScoreNormalization'], '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': 8, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 1], [2, 1], [2, 1]], 'n_conv_per_stage': [2, 2, 2, 2, 2, 2, 2, 2], 'n_conv_per_stage_decoder': [2, 2, 2, 2, 2, 2, 2], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}}, 'experiment_planner_used': 'ExperimentPlanner', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 255.0, 'mean': 49.659568786621094, 'median': 45.0, 'min': 0.0, 'percentile_00_5': 10.0, 'percentile_99_5': 163.0, 'std': 24.689043045043945}}}, 'configuration': '2d', 'fold': 1, 'dataset_json': {'channel_names': {'0': '\u00b5OCT'}, 'labels': {'background': 0, 'Retina': 1, 'VCD': 2, 'lens': 3, 'cornea': 4}, 'numTraining': 108, 'file_ending': '.png'}, 'device': device(type='cuda')}", + "network": "OptimizedModule", + "num_epochs": "1000", + "num_input_channels": "1", + "num_iterations_per_epoch": "250", + "num_val_iterations_per_epoch": "50", + "optimizer": "SGD (\nParameter Group 0\n dampening: 0\n differentiable: False\n foreach: None\n fused: None\n initial_lr: 0.01\n lr: 0.01\n maximize: False\n momentum: 0.99\n nesterov: True\n weight_decay: 3e-05\n)", + "output_folder": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1", + "output_folder_base": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d", + "oversample_foreground_percent": "0.33", + "plans_manager": "{'dataset_name': 'Dataset001_zebrafish', 'plans_name': 'nnUNetPlans', 'original_median_spacing_after_transp': [999.0, 1.0, 1.0], 'original_median_shape_after_transp': [1, 1024, 102], 'image_reader_writer': 'NaturalImage2DIO', 'transpose_forward': [0, 1, 2], 'transpose_backward': [0, 1, 2], 'configurations': {'2d': {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 5, 'patch_size': [1024, 112], 'median_image_size_in_voxels': [1024.0, 102.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['ZScoreNormalization'], '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': 8, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 1], [2, 1], [2, 1]], 'n_conv_per_stage': [2, 2, 2, 2, 2, 2, 2, 2], 'n_conv_per_stage_decoder': [2, 2, 2, 2, 2, 2, 2], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}}, 'experiment_planner_used': 'ExperimentPlanner', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 255.0, 'mean': 49.659568786621094, 'median': 45.0, 'min': 0.0, 'percentile_00_5': 10.0, 'percentile_99_5': 163.0, 'std': 24.689043045043945}}}", + "preprocessed_dataset_folder": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/nnUNetPlans_2d", + "preprocessed_dataset_folder_base": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish", + "probabilistic_oversampling": "False", + "save_every": "50", + "torch_version": "2.5.1+cu121", + "was_initialized": "True", + "weight_decay": "3e-05" +} \ No newline at end of file diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/progress.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/progress.png new file mode 100644 index 0000000000000000000000000000000000000000..8fe8e4cfb5076bc7cd6b04d3770ff84769bc4292 --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/progress.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c623031ec76ee442a0095b22a1f9eafacb9a09d3e00c5b670ad06a466ee42fcc +size 937810 diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/training_log_2025_10_30_08_32_08.txt b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/training_log_2025_10_30_08_32_08.txt new file mode 100644 index 0000000000000000000000000000000000000000..1fff66f68589ef235416c2ef4bf702821efce5db --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/training_log_2025_10_30_08_32_08.txt @@ -0,0 +1,12 @@ + +####################################################################### +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. +####################################################################### + +2025-10-30 08:32:10.865681: Using torch.compile... +2025-10-30 08:32:11.762300: do_dummy_2d_data_aug: False +2025-10-30 08:32:11.764857: Using splits from existing split file: /hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/splits_final.json +2025-10-30 08:32:11.766589: The split file contains 5 splits. +2025-10-30 08:32:11.768494: Desired fold for training: 1 +2025-10-30 08:32:11.769945: This split has 86 training and 22 validation cases. diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/training_log_2025_10_30_14_59_19.txt b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/training_log_2025_10_30_14_59_19.txt new file mode 100644 index 0000000000000000000000000000000000000000..2e11f1eff9313ae0644b5883131ab777f1411b04 --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/training_log_2025_10_30_14_59_19.txt @@ -0,0 +1,7127 @@ + +####################################################################### +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. +####################################################################### + +2025-10-30 14:59:21.886330: Using torch.compile... +2025-10-30 14:59:23.189573: do_dummy_2d_data_aug: False +2025-10-30 14:59:23.192376: Using splits from existing split file: /hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/splits_final.json +2025-10-30 14:59:23.196480: The split file contains 5 splits. +2025-10-30 14:59:23.198840: Desired fold for training: 1 +2025-10-30 14:59:23.203140: This split has 86 training and 22 validation cases. + +This is the configuration used by this training: +Configuration name: 2d + {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 5, 'patch_size': [1024, 112], 'median_image_size_in_voxels': [1024.0, 102.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['ZScoreNormalization'], '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': 8, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 1], [2, 1], [2, 1]], 'n_conv_per_stage': [2, 2, 2, 2, 2, 2, 2, 2], 'n_conv_per_stage_decoder': [2, 2, 2, 2, 2, 2, 2], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True} + +These are the global plan.json settings: + {'dataset_name': 'Dataset001_zebrafish', 'plans_name': 'nnUNetPlans', 'original_median_spacing_after_transp': [999.0, 1.0, 1.0], 'original_median_shape_after_transp': [1, 1024, 102], 'image_reader_writer': 'NaturalImage2DIO', 'transpose_forward': [0, 1, 2], 'transpose_backward': [0, 1, 2], 'experiment_planner_used': 'ExperimentPlanner', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 255.0, 'mean': 49.659568786621094, 'median': 45.0, 'min': 0.0, 'percentile_00_5': 10.0, 'percentile_99_5': 163.0, 'std': 24.689043045043945}}} + +2025-10-30 14:59:24.868211: Unable to plot network architecture: nnUNet_compile is enabled! +2025-10-30 14:59:24.884456: +2025-10-30 14:59:24.886227: Epoch 0 +2025-10-30 14:59:24.888579: Current learning rate: 0.01 +2025-10-30 15:00:26.103833: train_loss -0.1844 +2025-10-30 15:00:26.106616: val_loss -0.8252 +2025-10-30 15:00:26.108517: Pseudo dice [np.float32(0.9676), np.float32(0.9568), np.float32(0.9784), np.float32(0.7183)] +2025-10-30 15:00:26.110361: Epoch time: 61.22 s +2025-10-30 15:00:26.112321: Yayy! New best EMA pseudo Dice: 0.9053000211715698 +2025-10-30 15:00:27.872511: +2025-10-30 15:00:27.874405: Epoch 1 +2025-10-30 15:00:27.876034: Current learning rate: 0.00999 +2025-10-30 15:00:48.071680: train_loss -0.8485 +2025-10-30 15:00:48.074145: val_loss -0.9006 +2025-10-30 15:00:48.075589: Pseudo dice [np.float32(0.9753), np.float32(0.984), np.float32(0.9919), np.float32(0.8128)] +2025-10-30 15:00:48.077536: Epoch time: 20.2 s +2025-10-30 15:00:48.079324: Yayy! New best EMA pseudo Dice: 0.9088000059127808 +2025-10-30 15:00:50.296457: +2025-10-30 15:00:50.299228: Epoch 2 +2025-10-30 15:00:50.302296: Current learning rate: 0.00998 +2025-10-30 15:01:10.927676: train_loss -0.8886 +2025-10-30 15:01:10.929981: val_loss -0.9007 +2025-10-30 15:01:10.931682: Pseudo dice [np.float32(0.9793), np.float32(0.9867), np.float32(0.9916), np.float32(0.8025)] +2025-10-30 15:01:10.933286: Epoch time: 20.63 s +2025-10-30 15:01:10.934776: Yayy! New best EMA pseudo Dice: 0.9120000004768372 +2025-10-30 15:01:13.423230: +2025-10-30 15:01:13.425175: Epoch 3 +2025-10-30 15:01:13.426636: Current learning rate: 0.00997 +2025-10-30 15:01:33.695649: train_loss -0.8798 +2025-10-30 15:01:33.699702: val_loss -0.901 +2025-10-30 15:01:33.701226: Pseudo dice [np.float32(0.9811), np.float32(0.985), np.float32(0.9921), np.float32(0.8098)] +2025-10-30 15:01:33.702779: Epoch time: 20.27 s +2025-10-30 15:01:33.704430: Yayy! New best EMA pseudo Dice: 0.9150000214576721 +2025-10-30 15:01:35.592037: +2025-10-30 15:01:35.594215: Epoch 4 +2025-10-30 15:01:35.595760: Current learning rate: 0.00996 +2025-10-30 15:01:55.509192: train_loss -0.8843 +2025-10-30 15:01:55.512172: val_loss -0.9158 +2025-10-30 15:01:55.514092: Pseudo dice [np.float32(0.9752), np.float32(0.9883), np.float32(0.9946), np.float32(0.8348)] +2025-10-30 15:01:55.516287: Epoch time: 19.92 s +2025-10-30 15:01:55.517927: Yayy! New best EMA pseudo Dice: 0.9182999730110168 +2025-10-30 15:01:57.661865: +2025-10-30 15:01:57.663884: Epoch 5 +2025-10-30 15:01:57.665410: Current learning rate: 0.00995 +2025-10-30 15:02:18.131153: train_loss -0.9046 +2025-10-30 15:02:18.133259: val_loss -0.9113 +2025-10-30 15:02:18.135356: Pseudo dice [np.float32(0.9813), np.float32(0.9894), np.float32(0.9948), np.float32(0.8023)] +2025-10-30 15:02:18.138217: Epoch time: 20.47 s +2025-10-30 15:02:18.140034: Yayy! New best EMA pseudo Dice: 0.9207000136375427 +2025-10-30 15:02:20.234197: +2025-10-30 15:02:20.238233: Epoch 6 +2025-10-30 15:02:20.240792: Current learning rate: 0.00995 +2025-10-30 15:02:40.794257: train_loss -0.9136 +2025-10-30 15:02:40.801012: val_loss -0.9059 +2025-10-30 15:02:40.802789: Pseudo dice [np.float32(0.9802), np.float32(0.9874), np.float32(0.991), np.float32(0.7935)] +2025-10-30 15:02:40.804898: Epoch time: 20.56 s +2025-10-30 15:02:40.806454: Yayy! New best EMA pseudo Dice: 0.9223999977111816 +2025-10-30 15:02:43.559704: +2025-10-30 15:02:43.561460: Epoch 7 +2025-10-30 15:02:43.563308: Current learning rate: 0.00994 +2025-10-30 15:03:04.039721: train_loss -0.9211 +2025-10-30 15:03:04.042079: val_loss -0.9198 +2025-10-30 15:03:04.043808: Pseudo dice [np.float32(0.982), np.float32(0.9883), np.float32(0.994), np.float32(0.8233)] +2025-10-30 15:03:04.045467: Epoch time: 20.48 s +2025-10-30 15:03:04.046985: Yayy! New best EMA pseudo Dice: 0.9247999787330627 +2025-10-30 15:03:06.373445: +2025-10-30 15:03:06.375176: Epoch 8 +2025-10-30 15:03:06.376783: Current learning rate: 0.00993 +2025-10-30 15:03:26.282783: train_loss -0.9301 +2025-10-30 15:03:26.285176: val_loss -0.917 +2025-10-30 15:03:26.287193: Pseudo dice [np.float32(0.9799), np.float32(0.9903), np.float32(0.9946), np.float32(0.8116)] +2025-10-30 15:03:26.288745: Epoch time: 19.91 s +2025-10-30 15:03:26.292160: Yayy! New best EMA pseudo Dice: 0.926800012588501 +2025-10-30 15:03:28.428497: +2025-10-30 15:03:28.430888: Epoch 9 +2025-10-30 15:03:28.432862: Current learning rate: 0.00992 +2025-10-30 15:03:49.120946: train_loss -0.9347 +2025-10-30 15:03:49.123925: val_loss -0.9105 +2025-10-30 15:03:49.125799: Pseudo dice [np.float32(0.9831), np.float32(0.9899), np.float32(0.9939), np.float32(0.7859)] +2025-10-30 15:03:49.127334: Epoch time: 20.69 s +2025-10-30 15:03:49.129601: Yayy! New best EMA pseudo Dice: 0.9279000163078308 +2025-10-30 15:03:51.274909: +2025-10-30 15:03:51.276841: Epoch 10 +2025-10-30 15:03:51.278582: Current learning rate: 0.00991 +2025-10-30 15:04:11.026576: train_loss -0.9328 +2025-10-30 15:04:11.028986: val_loss -0.9144 +2025-10-30 15:04:11.030803: Pseudo dice [np.float32(0.9834), np.float32(0.9905), np.float32(0.9945), np.float32(0.7951)] +2025-10-30 15:04:11.032414: Epoch time: 19.75 s +2025-10-30 15:04:11.034564: Yayy! New best EMA pseudo Dice: 0.9291999936103821 +2025-10-30 15:04:13.250946: +2025-10-30 15:04:13.252903: Epoch 11 +2025-10-30 15:04:13.256324: Current learning rate: 0.0099 +2025-10-30 15:04:34.026545: train_loss -0.9362 +2025-10-30 15:04:34.031671: val_loss -0.9164 +2025-10-30 15:04:34.033419: Pseudo dice [np.float32(0.9829), np.float32(0.9884), np.float32(0.9942), np.float32(0.8111)] +2025-10-30 15:04:34.035021: Epoch time: 20.78 s +2025-10-30 15:04:34.036563: Yayy! New best EMA pseudo Dice: 0.9307000041007996 +2025-10-30 15:04:36.523439: +2025-10-30 15:04:36.525780: Epoch 12 +2025-10-30 15:04:36.527541: Current learning rate: 0.00989 +2025-10-30 15:04:57.104213: train_loss -0.9324 +2025-10-30 15:04:57.106941: val_loss -0.9098 +2025-10-30 15:04:57.108649: Pseudo dice [np.float32(0.9804), np.float32(0.9892), np.float32(0.9939), np.float32(0.7964)] +2025-10-30 15:04:57.110877: Epoch time: 20.58 s +2025-10-30 15:04:57.114005: Yayy! New best EMA pseudo Dice: 0.9315999746322632 +2025-10-30 15:04:59.280902: +2025-10-30 15:04:59.283367: Epoch 13 +2025-10-30 15:04:59.285132: Current learning rate: 0.00988 +2025-10-30 15:05:19.406935: train_loss -0.9344 +2025-10-30 15:05:19.409483: val_loss -0.9162 +2025-10-30 15:05:19.411027: Pseudo dice [np.float32(0.9833), np.float32(0.989), np.float32(0.9938), np.float32(0.8089)] +2025-10-30 15:05:19.412939: Epoch time: 20.13 s +2025-10-30 15:05:19.414334: Yayy! New best EMA pseudo Dice: 0.9327999949455261 +2025-10-30 15:05:21.448364: +2025-10-30 15:05:21.450299: Epoch 14 +2025-10-30 15:05:21.452490: Current learning rate: 0.00987 +2025-10-30 15:05:41.013547: train_loss -0.9381 +2025-10-30 15:05:41.015481: val_loss -0.9208 +2025-10-30 15:05:41.017065: Pseudo dice [np.float32(0.9836), np.float32(0.9906), np.float32(0.9947), np.float32(0.8262)] +2025-10-30 15:05:41.018589: Epoch time: 19.57 s +2025-10-30 15:05:41.020278: Yayy! New best EMA pseudo Dice: 0.9344000220298767 +2025-10-30 15:05:43.136219: +2025-10-30 15:05:43.138607: Epoch 15 +2025-10-30 15:05:43.140418: Current learning rate: 0.00986 +2025-10-30 15:06:03.689676: train_loss -0.9418 +2025-10-30 15:06:03.692405: val_loss -0.9191 +2025-10-30 15:06:03.694301: Pseudo dice [np.float32(0.984), np.float32(0.9905), np.float32(0.9944), np.float32(0.8136)] +2025-10-30 15:06:03.696297: Epoch time: 20.56 s +2025-10-30 15:06:03.698700: Yayy! New best EMA pseudo Dice: 0.9355000257492065 +2025-10-30 15:06:05.983219: +2025-10-30 15:06:05.985399: Epoch 16 +2025-10-30 15:06:05.987394: Current learning rate: 0.00986 +2025-10-30 15:06:25.368776: train_loss -0.9387 +2025-10-30 15:06:25.371282: val_loss -0.9179 +2025-10-30 15:06:25.372803: Pseudo dice [np.float32(0.9795), np.float32(0.9892), np.float32(0.9944), np.float32(0.8187)] +2025-10-30 15:06:25.374372: Epoch time: 19.39 s +2025-10-30 15:06:25.376284: Yayy! New best EMA pseudo Dice: 0.9365000128746033 +2025-10-30 15:06:27.380506: +2025-10-30 15:06:27.382411: Epoch 17 +2025-10-30 15:06:27.384111: Current learning rate: 0.00985 +2025-10-30 15:06:48.181607: train_loss -0.9418 +2025-10-30 15:06:48.184138: val_loss -0.9261 +2025-10-30 15:06:48.185931: Pseudo dice [np.float32(0.9835), np.float32(0.9899), np.float32(0.9948), np.float32(0.8379)] +2025-10-30 15:06:48.187787: Epoch time: 20.8 s +2025-10-30 15:06:48.189548: Yayy! New best EMA pseudo Dice: 0.9380000233650208 +2025-10-30 15:06:50.596705: +2025-10-30 15:06:50.598795: Epoch 18 +2025-10-30 15:06:50.601107: Current learning rate: 0.00984 +2025-10-30 15:07:11.349895: train_loss -0.9472 +2025-10-30 15:07:11.352611: val_loss -0.9225 +2025-10-30 15:07:11.354312: Pseudo dice [np.float32(0.9835), np.float32(0.9911), np.float32(0.9951), np.float32(0.8252)] +2025-10-30 15:07:11.355872: Epoch time: 20.76 s +2025-10-30 15:07:11.357400: Yayy! New best EMA pseudo Dice: 0.9391000270843506 +2025-10-30 15:07:14.449781: +2025-10-30 15:07:14.451874: Epoch 19 +2025-10-30 15:07:14.453721: Current learning rate: 0.00983 +2025-10-30 15:07:35.494391: train_loss -0.9497 +2025-10-30 15:07:35.497130: val_loss -0.9193 +2025-10-30 15:07:35.498627: Pseudo dice [np.float32(0.9847), np.float32(0.9899), np.float32(0.9946), np.float32(0.8142)] +2025-10-30 15:07:35.500388: Epoch time: 21.05 s +2025-10-30 15:07:35.501880: Yayy! New best EMA pseudo Dice: 0.9398000240325928 +2025-10-30 15:07:37.875963: +2025-10-30 15:07:37.877881: Epoch 20 +2025-10-30 15:07:37.879450: Current learning rate: 0.00982 +2025-10-30 15:07:57.556390: train_loss -0.9485 +2025-10-30 15:07:57.559515: val_loss -0.9183 +2025-10-30 15:07:57.561248: Pseudo dice [np.float32(0.9822), np.float32(0.9892), np.float32(0.9944), np.float32(0.8142)] +2025-10-30 15:07:57.562980: Epoch time: 19.68 s +2025-10-30 15:07:57.564758: Yayy! New best EMA pseudo Dice: 0.9402999877929688 +2025-10-30 15:07:59.804355: +2025-10-30 15:07:59.806393: Epoch 21 +2025-10-30 15:07:59.808513: Current learning rate: 0.00981 +2025-10-30 15:08:20.402046: train_loss -0.9495 +2025-10-30 15:08:20.405160: val_loss -0.901 +2025-10-30 15:08:20.406847: Pseudo dice [np.float32(0.9851), np.float32(0.9762), np.float32(0.9863), np.float32(0.8274)] +2025-10-30 15:08:20.408711: Epoch time: 20.6 s +2025-10-30 15:08:20.410539: Yayy! New best EMA pseudo Dice: 0.9405999779701233 +2025-10-30 15:08:22.422077: +2025-10-30 15:08:22.424601: Epoch 22 +2025-10-30 15:08:22.428381: Current learning rate: 0.0098 +2025-10-30 15:08:43.111893: train_loss -0.9339 +2025-10-30 15:08:43.115292: val_loss -0.9193 +2025-10-30 15:08:43.116978: Pseudo dice [np.float32(0.9818), np.float32(0.9859), np.float32(0.9934), np.float32(0.8282)] +2025-10-30 15:08:43.118700: Epoch time: 20.69 s +2025-10-30 15:08:43.120452: Yayy! New best EMA pseudo Dice: 0.9412999749183655 +2025-10-30 15:08:45.303483: +2025-10-30 15:08:45.305773: Epoch 23 +2025-10-30 15:08:45.307891: Current learning rate: 0.00979 +2025-10-30 15:09:06.117131: train_loss -0.9454 +2025-10-30 15:09:06.119496: val_loss -0.9201 +2025-10-30 15:09:06.121256: Pseudo dice [np.float32(0.9839), np.float32(0.9893), np.float32(0.9946), np.float32(0.8214)] +2025-10-30 15:09:06.123009: Epoch time: 20.82 s +2025-10-30 15:09:06.124812: Yayy! New best EMA pseudo Dice: 0.9419000148773193 +2025-10-30 15:09:08.471287: +2025-10-30 15:09:08.474298: Epoch 24 +2025-10-30 15:09:08.478486: Current learning rate: 0.00978 +2025-10-30 15:09:29.569779: train_loss -0.9485 +2025-10-30 15:09:29.572449: val_loss -0.9187 +2025-10-30 15:09:29.574100: Pseudo dice [np.float32(0.9822), np.float32(0.9904), np.float32(0.9951), np.float32(0.823)] +2025-10-30 15:09:29.575842: Epoch time: 21.1 s +2025-10-30 15:09:29.577629: Yayy! New best EMA pseudo Dice: 0.9424999952316284 +2025-10-30 15:09:31.646912: +2025-10-30 15:09:31.648851: Epoch 25 +2025-10-30 15:09:31.650782: Current learning rate: 0.00977 +2025-10-30 15:09:52.106538: train_loss -0.9516 +2025-10-30 15:09:52.109508: val_loss -0.9259 +2025-10-30 15:09:52.111482: Pseudo dice [np.float32(0.983), np.float32(0.9909), np.float32(0.9957), np.float32(0.8272)] +2025-10-30 15:09:52.113407: Epoch time: 20.46 s +2025-10-30 15:09:52.115079: Yayy! New best EMA pseudo Dice: 0.9431999921798706 +2025-10-30 15:09:54.036286: +2025-10-30 15:09:54.038358: Epoch 26 +2025-10-30 15:09:54.040180: Current learning rate: 0.00977 +2025-10-30 15:10:13.853588: train_loss -0.9526 +2025-10-30 15:10:13.859028: val_loss -0.9225 +2025-10-30 15:10:13.860974: Pseudo dice [np.float32(0.9832), np.float32(0.99), np.float32(0.9949), np.float32(0.8295)] +2025-10-30 15:10:13.862766: Epoch time: 19.82 s +2025-10-30 15:10:13.864419: Yayy! New best EMA pseudo Dice: 0.9437999725341797 +2025-10-30 15:10:16.117882: +2025-10-30 15:10:16.119908: Epoch 27 +2025-10-30 15:10:16.121752: Current learning rate: 0.00976 +2025-10-30 15:10:35.803866: train_loss -0.9556 +2025-10-30 15:10:35.806973: val_loss -0.9231 +2025-10-30 15:10:35.808514: Pseudo dice [np.float32(0.9816), np.float32(0.9886), np.float32(0.9947), np.float32(0.8368)] +2025-10-30 15:10:35.810073: Epoch time: 19.69 s +2025-10-30 15:10:35.811649: Yayy! New best EMA pseudo Dice: 0.9444000124931335 +2025-10-30 15:10:37.929152: +2025-10-30 15:10:37.931044: Epoch 28 +2025-10-30 15:10:37.932864: Current learning rate: 0.00975 +2025-10-30 15:10:58.685739: train_loss -0.9563 +2025-10-30 15:10:58.688471: val_loss -0.9166 +2025-10-30 15:10:58.690693: Pseudo dice [np.float32(0.9824), np.float32(0.9898), np.float32(0.9937), np.float32(0.8136)] +2025-10-30 15:10:58.692580: Epoch time: 20.76 s +2025-10-30 15:10:58.694381: Yayy! New best EMA pseudo Dice: 0.9445000290870667 +2025-10-30 15:11:01.064824: +2025-10-30 15:11:01.066446: Epoch 29 +2025-10-30 15:11:01.068231: Current learning rate: 0.00974 +2025-10-30 15:11:21.906155: train_loss -0.9605 +2025-10-30 15:11:21.908261: val_loss -0.9223 +2025-10-30 15:11:21.910121: Pseudo dice [np.float32(0.9838), np.float32(0.9898), np.float32(0.995), np.float32(0.828)] +2025-10-30 15:11:21.911886: Epoch time: 20.84 s +2025-10-30 15:11:21.913575: Yayy! New best EMA pseudo Dice: 0.9449999928474426 +2025-10-30 15:11:24.189559: +2025-10-30 15:11:24.191941: Epoch 30 +2025-10-30 15:11:24.193657: Current learning rate: 0.00973 +2025-10-30 15:11:44.837497: train_loss -0.9603 +2025-10-30 15:11:44.848673: val_loss -0.9209 +2025-10-30 15:11:44.850989: Pseudo dice [np.float32(0.9847), np.float32(0.9904), np.float32(0.995), np.float32(0.8242)] +2025-10-30 15:11:44.853106: Epoch time: 20.65 s +2025-10-30 15:11:44.854885: Yayy! New best EMA pseudo Dice: 0.9452999830245972 +2025-10-30 15:11:47.752363: +2025-10-30 15:11:47.754904: Epoch 31 +2025-10-30 15:11:47.756943: Current learning rate: 0.00972 +2025-10-30 15:12:08.501865: train_loss -0.9625 +2025-10-30 15:12:08.504614: val_loss -0.9229 +2025-10-30 15:12:08.506436: Pseudo dice [np.float32(0.9836), np.float32(0.9889), np.float32(0.9945), np.float32(0.8268)] +2025-10-30 15:12:08.508293: Epoch time: 20.75 s +2025-10-30 15:12:08.509888: Yayy! New best EMA pseudo Dice: 0.9455999732017517 +2025-10-30 15:12:10.720989: +2025-10-30 15:12:10.723668: Epoch 32 +2025-10-30 15:12:10.725448: Current learning rate: 0.00971 +2025-10-30 15:12:31.023030: train_loss -0.9627 +2025-10-30 15:12:31.025317: val_loss -0.9166 +2025-10-30 15:12:31.026967: Pseudo dice [np.float32(0.9823), np.float32(0.989), np.float32(0.9952), np.float32(0.8244)] +2025-10-30 15:12:31.028757: Epoch time: 20.3 s +2025-10-30 15:12:31.030445: Yayy! New best EMA pseudo Dice: 0.9458000063896179 +2025-10-30 15:12:33.099338: +2025-10-30 15:12:33.101738: Epoch 33 +2025-10-30 15:12:33.104059: Current learning rate: 0.0097 +2025-10-30 15:12:52.613150: train_loss -0.9585 +2025-10-30 15:12:52.616224: val_loss -0.9201 +2025-10-30 15:12:52.618425: Pseudo dice [np.float32(0.9838), np.float32(0.9907), np.float32(0.9951), np.float32(0.8283)] +2025-10-30 15:12:52.620094: Epoch time: 19.52 s +2025-10-30 15:12:52.621750: Yayy! New best EMA pseudo Dice: 0.9462000131607056 +2025-10-30 15:12:54.845477: +2025-10-30 15:12:54.847436: Epoch 34 +2025-10-30 15:12:54.849196: Current learning rate: 0.00969 +2025-10-30 15:13:15.648818: train_loss -0.961 +2025-10-30 15:13:15.652304: val_loss -0.9245 +2025-10-30 15:13:15.655754: Pseudo dice [np.float32(0.9834), np.float32(0.9903), np.float32(0.995), np.float32(0.8368)] +2025-10-30 15:13:15.658667: Epoch time: 20.81 s +2025-10-30 15:13:15.661806: Yayy! New best EMA pseudo Dice: 0.9466999769210815 +2025-10-30 15:13:17.995716: +2025-10-30 15:13:17.998441: Epoch 35 +2025-10-30 15:13:18.000787: Current learning rate: 0.00968 +2025-10-30 15:13:38.681971: train_loss -0.9642 +2025-10-30 15:13:38.684761: val_loss -0.9145 +2025-10-30 15:13:38.687423: Pseudo dice [np.float32(0.9824), np.float32(0.989), np.float32(0.9948), np.float32(0.8233)] +2025-10-30 15:13:38.690208: Epoch time: 20.69 s +2025-10-30 15:13:38.692999: Yayy! New best EMA pseudo Dice: 0.9467999935150146 +2025-10-30 15:13:41.141067: +2025-10-30 15:13:41.143152: Epoch 36 +2025-10-30 15:13:41.144942: Current learning rate: 0.00968 +2025-10-30 15:14:01.728092: train_loss -0.9645 +2025-10-30 15:14:01.732025: val_loss -0.9229 +2025-10-30 15:14:01.733779: Pseudo dice [np.float32(0.9831), np.float32(0.9909), np.float32(0.9954), np.float32(0.8323)] +2025-10-30 15:14:01.735987: Epoch time: 20.59 s +2025-10-30 15:14:01.737753: Yayy! New best EMA pseudo Dice: 0.9470999836921692 +2025-10-30 15:14:03.904049: +2025-10-30 15:14:03.906475: Epoch 37 +2025-10-30 15:14:03.908542: Current learning rate: 0.00967 +2025-10-30 15:14:23.268273: train_loss -0.966 +2025-10-30 15:14:23.273746: val_loss -0.9218 +2025-10-30 15:14:23.278592: Pseudo dice [np.float32(0.9839), np.float32(0.9903), np.float32(0.9952), np.float32(0.8317)] +2025-10-30 15:14:23.283873: Epoch time: 19.37 s +2025-10-30 15:14:23.288257: Yayy! New best EMA pseudo Dice: 0.9474999904632568 +2025-10-30 15:14:26.099312: +2025-10-30 15:14:26.106376: Epoch 38 +2025-10-30 15:14:26.114748: Current learning rate: 0.00966 +2025-10-30 15:14:46.197446: train_loss -0.961 +2025-10-30 15:14:46.199369: val_loss -0.9094 +2025-10-30 15:14:46.201128: Pseudo dice [np.float32(0.9816), np.float32(0.9885), np.float32(0.994), np.float32(0.8015)] +2025-10-30 15:14:46.202832: Epoch time: 20.1 s +2025-10-30 15:14:47.247521: +2025-10-30 15:14:47.249516: Epoch 39 +2025-10-30 15:14:47.251640: Current learning rate: 0.00965 +2025-10-30 15:15:05.812144: train_loss -0.9565 +2025-10-30 15:15:05.815713: val_loss -0.9196 +2025-10-30 15:15:05.817466: Pseudo dice [np.float32(0.9808), np.float32(0.9895), np.float32(0.9951), np.float32(0.8291)] +2025-10-30 15:15:05.819260: Epoch time: 18.57 s +2025-10-30 15:15:06.959963: +2025-10-30 15:15:06.962234: Epoch 40 +2025-10-30 15:15:06.964060: Current learning rate: 0.00964 +2025-10-30 15:15:27.476167: train_loss -0.9626 +2025-10-30 15:15:27.478251: val_loss -0.9179 +2025-10-30 15:15:27.480042: Pseudo dice [np.float32(0.9825), np.float32(0.9901), np.float32(0.9951), np.float32(0.8232)] +2025-10-30 15:15:27.481721: Epoch time: 20.52 s +2025-10-30 15:15:28.540413: +2025-10-30 15:15:28.542506: Epoch 41 +2025-10-30 15:15:28.544322: Current learning rate: 0.00963 +2025-10-30 15:15:49.268198: train_loss -0.9657 +2025-10-30 15:15:49.270684: val_loss -0.9206 +2025-10-30 15:15:49.272487: Pseudo dice [np.float32(0.9822), np.float32(0.9899), np.float32(0.9952), np.float32(0.8293)] +2025-10-30 15:15:49.274670: Epoch time: 20.73 s +2025-10-30 15:15:50.486624: +2025-10-30 15:15:50.488496: Epoch 42 +2025-10-30 15:15:50.490222: Current learning rate: 0.00962 +2025-10-30 15:16:10.864956: train_loss -0.9655 +2025-10-30 15:16:10.868046: val_loss -0.9266 +2025-10-30 15:16:10.869771: Pseudo dice [np.float32(0.9838), np.float32(0.9916), np.float32(0.9956), np.float32(0.8452)] +2025-10-30 15:16:10.871489: Epoch time: 20.38 s +2025-10-30 15:16:10.873186: Yayy! New best EMA pseudo Dice: 0.9480000138282776 +2025-10-30 15:16:13.579699: +2025-10-30 15:16:13.582421: Epoch 43 +2025-10-30 15:16:13.584425: Current learning rate: 0.00961 +2025-10-30 15:16:34.885321: train_loss -0.9681 +2025-10-30 15:16:34.888487: val_loss -0.9173 +2025-10-30 15:16:34.891189: Pseudo dice [np.float32(0.982), np.float32(0.9901), np.float32(0.9952), np.float32(0.8262)] +2025-10-30 15:16:34.893617: Epoch time: 21.31 s +2025-10-30 15:16:34.895404: Yayy! New best EMA pseudo Dice: 0.9480000138282776 +2025-10-30 15:16:37.375836: +2025-10-30 15:16:37.378385: Epoch 44 +2025-10-30 15:16:37.380398: Current learning rate: 0.0096 +2025-10-30 15:16:57.895605: train_loss -0.9673 +2025-10-30 15:16:57.897595: val_loss -0.9169 +2025-10-30 15:16:57.899308: Pseudo dice [np.float32(0.9823), np.float32(0.9908), np.float32(0.9953), np.float32(0.8256)] +2025-10-30 15:16:57.901774: Epoch time: 20.52 s +2025-10-30 15:16:57.903940: Yayy! New best EMA pseudo Dice: 0.9480999708175659 +2025-10-30 15:17:00.127866: +2025-10-30 15:17:00.129635: Epoch 45 +2025-10-30 15:17:00.131711: Current learning rate: 0.00959 +2025-10-30 15:17:19.022553: train_loss -0.9661 +2025-10-30 15:17:19.026846: val_loss -0.9181 +2025-10-30 15:17:19.028331: Pseudo dice [np.float32(0.9831), np.float32(0.9893), np.float32(0.9951), np.float32(0.8304)] +2025-10-30 15:17:19.029819: Epoch time: 18.9 s +2025-10-30 15:17:19.031469: Yayy! New best EMA pseudo Dice: 0.948199987411499 +2025-10-30 15:17:21.012299: +2025-10-30 15:17:21.013999: Epoch 46 +2025-10-30 15:17:21.015403: Current learning rate: 0.00959 +2025-10-30 15:17:41.831161: train_loss -0.9671 +2025-10-30 15:17:41.833453: val_loss -0.918 +2025-10-30 15:17:41.835101: Pseudo dice [np.float32(0.9838), np.float32(0.9905), np.float32(0.995), np.float32(0.8138)] +2025-10-30 15:17:41.836702: Epoch time: 20.82 s +2025-10-30 15:17:43.297690: +2025-10-30 15:17:43.299873: Epoch 47 +2025-10-30 15:17:43.301364: Current learning rate: 0.00958 +2025-10-30 15:18:03.832771: train_loss -0.9689 +2025-10-30 15:18:03.835063: val_loss -0.9236 +2025-10-30 15:18:03.836676: Pseudo dice [np.float32(0.9824), np.float32(0.9896), np.float32(0.9953), np.float32(0.8425)] +2025-10-30 15:18:03.838376: Epoch time: 20.54 s +2025-10-30 15:18:03.839844: Yayy! New best EMA pseudo Dice: 0.9484000205993652 +2025-10-30 15:18:06.091164: +2025-10-30 15:18:06.093091: Epoch 48 +2025-10-30 15:18:06.094846: Current learning rate: 0.00957 +2025-10-30 15:18:26.339441: train_loss -0.9667 +2025-10-30 15:18:26.344386: val_loss -0.9251 +2025-10-30 15:18:26.346909: Pseudo dice [np.float32(0.9836), np.float32(0.9898), np.float32(0.9951), np.float32(0.8466)] +2025-10-30 15:18:26.348888: Epoch time: 20.25 s +2025-10-30 15:18:26.350527: Yayy! New best EMA pseudo Dice: 0.9490000009536743 +2025-10-30 15:18:28.397539: +2025-10-30 15:18:28.399683: Epoch 49 +2025-10-30 15:18:28.401509: Current learning rate: 0.00956 +2025-10-30 15:18:49.192263: train_loss -0.9575 +2025-10-30 15:18:49.194597: val_loss -0.92 +2025-10-30 15:18:49.196392: Pseudo dice [np.float32(0.9817), np.float32(0.9906), np.float32(0.9948), np.float32(0.8212)] +2025-10-30 15:18:49.197926: Epoch time: 20.8 s +2025-10-30 15:18:51.462150: +2025-10-30 15:18:51.464186: Epoch 50 +2025-10-30 15:18:51.466085: Current learning rate: 0.00955 +2025-10-30 15:19:12.052930: train_loss -0.9647 +2025-10-30 15:19:12.055312: val_loss -0.9307 +2025-10-30 15:19:12.057209: Pseudo dice [np.float32(0.9844), np.float32(0.991), np.float32(0.9954), np.float32(0.8525)] +2025-10-30 15:19:12.059146: Epoch time: 20.59 s +2025-10-30 15:19:12.061028: Yayy! New best EMA pseudo Dice: 0.9495000243186951 +2025-10-30 15:19:14.334051: +2025-10-30 15:19:14.336781: Epoch 51 +2025-10-30 15:19:14.338786: Current learning rate: 0.00954 +2025-10-30 15:19:33.836357: train_loss -0.9679 +2025-10-30 15:19:33.839229: val_loss -0.924 +2025-10-30 15:19:33.840887: Pseudo dice [np.float32(0.9825), np.float32(0.9899), np.float32(0.9957), np.float32(0.8449)] +2025-10-30 15:19:33.842657: Epoch time: 19.5 s +2025-10-30 15:19:33.844629: Yayy! New best EMA pseudo Dice: 0.9498000144958496 +2025-10-30 15:19:36.140648: +2025-10-30 15:19:36.142601: Epoch 52 +2025-10-30 15:19:36.144208: Current learning rate: 0.00953 +2025-10-30 15:19:56.586232: train_loss -0.9704 +2025-10-30 15:19:56.588681: val_loss -0.9129 +2025-10-30 15:19:56.590540: Pseudo dice [np.float32(0.9799), np.float32(0.9896), np.float32(0.9953), np.float32(0.8234)] +2025-10-30 15:19:56.592247: Epoch time: 20.45 s +2025-10-30 15:19:57.745567: +2025-10-30 15:19:57.747482: Epoch 53 +2025-10-30 15:19:57.749316: Current learning rate: 0.00952 +2025-10-30 15:20:18.281072: train_loss -0.9704 +2025-10-30 15:20:18.285344: val_loss -0.9282 +2025-10-30 15:20:18.287099: Pseudo dice [np.float32(0.9825), np.float32(0.9904), np.float32(0.9955), np.float32(0.8572)] +2025-10-30 15:20:18.288822: Epoch time: 20.54 s +2025-10-30 15:20:18.290503: Yayy! New best EMA pseudo Dice: 0.9502000212669373 +2025-10-30 15:20:20.533079: +2025-10-30 15:20:20.535219: Epoch 54 +2025-10-30 15:20:20.537032: Current learning rate: 0.00951 +2025-10-30 15:20:41.375907: train_loss -0.974 +2025-10-30 15:20:41.379870: val_loss -0.9203 +2025-10-30 15:20:41.382087: Pseudo dice [np.float32(0.9832), np.float32(0.9909), np.float32(0.995), np.float32(0.8339)] +2025-10-30 15:20:41.384064: Epoch time: 20.84 s +2025-10-30 15:20:41.386023: Yayy! New best EMA pseudo Dice: 0.9502999782562256 +2025-10-30 15:20:44.249220: +2025-10-30 15:20:44.251924: Epoch 55 +2025-10-30 15:20:44.254027: Current learning rate: 0.0095 +2025-10-30 15:21:05.039816: train_loss -0.9718 +2025-10-30 15:21:05.042782: val_loss -0.9198 +2025-10-30 15:21:05.044358: Pseudo dice [np.float32(0.9826), np.float32(0.9907), np.float32(0.9949), np.float32(0.8312)] +2025-10-30 15:21:05.046080: Epoch time: 20.79 s +2025-10-30 15:21:06.122757: +2025-10-30 15:21:06.124896: Epoch 56 +2025-10-30 15:21:06.128685: Current learning rate: 0.00949 +2025-10-30 15:21:26.614580: train_loss -0.9727 +2025-10-30 15:21:26.617390: val_loss -0.9185 +2025-10-30 15:21:26.619228: Pseudo dice [np.float32(0.9815), np.float32(0.9895), np.float32(0.9951), np.float32(0.838)] +2025-10-30 15:21:26.620855: Epoch time: 20.49 s +2025-10-30 15:21:26.622395: Yayy! New best EMA pseudo Dice: 0.9502999782562256 +2025-10-30 15:21:28.911532: +2025-10-30 15:21:28.913420: Epoch 57 +2025-10-30 15:21:28.915125: Current learning rate: 0.00949 +2025-10-30 15:21:49.519126: train_loss -0.9737 +2025-10-30 15:21:49.522596: val_loss -0.9229 +2025-10-30 15:21:49.524291: Pseudo dice [np.float32(0.9832), np.float32(0.9912), np.float32(0.9956), np.float32(0.8412)] +2025-10-30 15:21:49.526192: Epoch time: 20.61 s +2025-10-30 15:21:49.528296: Yayy! New best EMA pseudo Dice: 0.9506000280380249 +2025-10-30 15:21:52.025919: +2025-10-30 15:21:52.045243: Epoch 58 +2025-10-30 15:21:52.064319: Current learning rate: 0.00948 +2025-10-30 15:22:10.976887: train_loss -0.9738 +2025-10-30 15:22:10.979519: val_loss -0.9169 +2025-10-30 15:22:10.981469: Pseudo dice [np.float32(0.9829), np.float32(0.9915), np.float32(0.9953), np.float32(0.8325)] +2025-10-30 15:22:10.983420: Epoch time: 18.95 s +2025-10-30 15:22:11.961775: +2025-10-30 15:22:11.964046: Epoch 59 +2025-10-30 15:22:11.965780: Current learning rate: 0.00947 +2025-10-30 15:22:32.594510: train_loss -0.9715 +2025-10-30 15:22:32.597122: val_loss -0.919 +2025-10-30 15:22:32.598788: Pseudo dice [np.float32(0.982), np.float32(0.9901), np.float32(0.9953), np.float32(0.8374)] +2025-10-30 15:22:32.600440: Epoch time: 20.63 s +2025-10-30 15:22:32.602038: Yayy! New best EMA pseudo Dice: 0.9506000280380249 +2025-10-30 15:22:34.839194: +2025-10-30 15:22:34.841216: Epoch 60 +2025-10-30 15:22:34.843168: Current learning rate: 0.00946 +2025-10-30 15:22:55.693517: train_loss -0.9686 +2025-10-30 15:22:55.696477: val_loss -0.9223 +2025-10-30 15:22:55.698125: Pseudo dice [np.float32(0.9814), np.float32(0.9898), np.float32(0.9955), np.float32(0.8399)] +2025-10-30 15:22:55.699689: Epoch time: 20.86 s +2025-10-30 15:22:55.701604: Yayy! New best EMA pseudo Dice: 0.9506999850273132 +2025-10-30 15:22:57.847679: +2025-10-30 15:22:57.850026: Epoch 61 +2025-10-30 15:22:57.852185: Current learning rate: 0.00945 +2025-10-30 15:23:18.633838: train_loss -0.9733 +2025-10-30 15:23:18.636319: val_loss -0.927 +2025-10-30 15:23:18.638427: Pseudo dice [np.float32(0.9829), np.float32(0.9904), np.float32(0.9956), np.float32(0.8556)] +2025-10-30 15:23:18.640323: Epoch time: 20.79 s +2025-10-30 15:23:18.642267: Yayy! New best EMA pseudo Dice: 0.9513000249862671 +2025-10-30 15:23:20.706905: +2025-10-30 15:23:20.709153: Epoch 62 +2025-10-30 15:23:20.711346: Current learning rate: 0.00944 +2025-10-30 15:23:41.213946: train_loss -0.9732 +2025-10-30 15:23:41.216461: val_loss -0.9186 +2025-10-30 15:23:41.218307: Pseudo dice [np.float32(0.9829), np.float32(0.9914), np.float32(0.9956), np.float32(0.8353)] +2025-10-30 15:23:41.219934: Epoch time: 20.51 s +2025-10-30 15:23:41.221585: Yayy! New best EMA pseudo Dice: 0.9513000249862671 +2025-10-30 15:23:43.182739: +2025-10-30 15:23:43.185065: Epoch 63 +2025-10-30 15:23:43.187215: Current learning rate: 0.00943 +2025-10-30 15:24:04.015514: train_loss -0.9728 +2025-10-30 15:24:04.018493: val_loss -0.9146 +2025-10-30 15:24:04.020304: Pseudo dice [np.float32(0.9825), np.float32(0.9903), np.float32(0.9952), np.float32(0.825)] +2025-10-30 15:24:04.022704: Epoch time: 20.83 s +2025-10-30 15:24:05.289283: +2025-10-30 15:24:05.292228: Epoch 64 +2025-10-30 15:24:05.294894: Current learning rate: 0.00942 +2025-10-30 15:24:24.412085: train_loss -0.9742 +2025-10-30 15:24:24.415436: val_loss -0.9199 +2025-10-30 15:24:24.417388: Pseudo dice [np.float32(0.9816), np.float32(0.9899), np.float32(0.9955), np.float32(0.8412)] +2025-10-30 15:24:24.419118: Epoch time: 19.13 s +2025-10-30 15:24:25.521426: +2025-10-30 15:24:25.523988: Epoch 65 +2025-10-30 15:24:25.525988: Current learning rate: 0.00941 +2025-10-30 15:24:46.449972: train_loss -0.9672 +2025-10-30 15:24:46.453177: val_loss -0.9077 +2025-10-30 15:24:46.455154: Pseudo dice [np.float32(0.9825), np.float32(0.9887), np.float32(0.9898), np.float32(0.8312)] +2025-10-30 15:24:46.456978: Epoch time: 20.93 s +2025-10-30 15:24:47.647096: +2025-10-30 15:24:47.649906: Epoch 66 +2025-10-30 15:24:47.652403: Current learning rate: 0.0094 +2025-10-30 15:25:08.260398: train_loss -0.9671 +2025-10-30 15:25:08.263937: val_loss -0.921 +2025-10-30 15:25:08.266187: Pseudo dice [np.float32(0.9823), np.float32(0.9901), np.float32(0.9951), np.float32(0.8326)] +2025-10-30 15:25:08.268673: Epoch time: 20.62 s +2025-10-30 15:25:09.340165: +2025-10-30 15:25:09.342297: Epoch 67 +2025-10-30 15:25:09.343990: Current learning rate: 0.00939 +2025-10-30 15:25:29.794363: train_loss -0.9664 +2025-10-30 15:25:29.797019: val_loss -0.9268 +2025-10-30 15:25:29.798855: Pseudo dice [np.float32(0.9842), np.float32(0.9916), np.float32(0.9954), np.float32(0.8473)] +2025-10-30 15:25:29.800634: Epoch time: 20.46 s +2025-10-30 15:25:31.360877: +2025-10-30 15:25:31.363277: Epoch 68 +2025-10-30 15:25:31.365211: Current learning rate: 0.00939 +2025-10-30 15:25:52.087174: train_loss -0.9718 +2025-10-30 15:25:52.090050: val_loss -0.919 +2025-10-30 15:25:52.092663: Pseudo dice [np.float32(0.9837), np.float32(0.9909), np.float32(0.9952), np.float32(0.8275)] +2025-10-30 15:25:52.094888: Epoch time: 20.73 s +2025-10-30 15:25:53.364322: +2025-10-30 15:25:53.366508: Epoch 69 +2025-10-30 15:25:53.368447: Current learning rate: 0.00938 +2025-10-30 15:26:13.760619: train_loss -0.9736 +2025-10-30 15:26:13.764299: val_loss -0.9127 +2025-10-30 15:26:13.766340: Pseudo dice [np.float32(0.9847), np.float32(0.9906), np.float32(0.9947), np.float32(0.8139)] +2025-10-30 15:26:13.768489: Epoch time: 20.4 s +2025-10-30 15:26:14.857976: +2025-10-30 15:26:14.860214: Epoch 70 +2025-10-30 15:26:14.862116: Current learning rate: 0.00937 +2025-10-30 15:26:34.390282: train_loss -0.974 +2025-10-30 15:26:34.393283: val_loss -0.9135 +2025-10-30 15:26:34.395910: Pseudo dice [np.float32(0.9816), np.float32(0.9904), np.float32(0.9949), np.float32(0.8265)] +2025-10-30 15:26:34.398886: Epoch time: 19.53 s +2025-10-30 15:26:35.384992: +2025-10-30 15:26:35.387300: Epoch 71 +2025-10-30 15:26:35.389321: Current learning rate: 0.00936 +2025-10-30 15:26:55.000867: train_loss -0.9738 +2025-10-30 15:26:55.003367: val_loss -0.9215 +2025-10-30 15:26:55.005033: Pseudo dice [np.float32(0.9832), np.float32(0.991), np.float32(0.9956), np.float32(0.8369)] +2025-10-30 15:26:55.006562: Epoch time: 19.62 s +2025-10-30 15:26:56.157381: +2025-10-30 15:26:56.159701: Epoch 72 +2025-10-30 15:26:56.161579: Current learning rate: 0.00935 +2025-10-30 15:27:16.675523: train_loss -0.976 +2025-10-30 15:27:16.678586: val_loss -0.9136 +2025-10-30 15:27:16.680250: Pseudo dice [np.float32(0.983), np.float32(0.9909), np.float32(0.9947), np.float32(0.8208)] +2025-10-30 15:27:16.681943: Epoch time: 20.52 s +2025-10-30 15:27:17.942427: +2025-10-30 15:27:17.944410: Epoch 73 +2025-10-30 15:27:17.946716: Current learning rate: 0.00934 +2025-10-30 15:27:38.523219: train_loss -0.9749 +2025-10-30 15:27:38.525977: val_loss -0.9061 +2025-10-30 15:27:38.527778: Pseudo dice [np.float32(0.9813), np.float32(0.9893), np.float32(0.9946), np.float32(0.8125)] +2025-10-30 15:27:38.529688: Epoch time: 20.58 s +2025-10-30 15:27:39.633828: +2025-10-30 15:27:39.636785: Epoch 74 +2025-10-30 15:27:39.639049: Current learning rate: 0.00933 +2025-10-30 15:28:00.000264: train_loss -0.9769 +2025-10-30 15:28:00.002550: val_loss -0.9119 +2025-10-30 15:28:00.004371: Pseudo dice [np.float32(0.9809), np.float32(0.9899), np.float32(0.9952), np.float32(0.8322)] +2025-10-30 15:28:00.006267: Epoch time: 20.37 s +2025-10-30 15:28:01.004350: +2025-10-30 15:28:01.010365: Epoch 75 +2025-10-30 15:28:01.012130: Current learning rate: 0.00932 +2025-10-30 15:28:21.410163: train_loss -0.9769 +2025-10-30 15:28:21.413523: val_loss -0.9122 +2025-10-30 15:28:21.415318: Pseudo dice [np.float32(0.9808), np.float32(0.9896), np.float32(0.9954), np.float32(0.8299)] +2025-10-30 15:28:21.417969: Epoch time: 20.41 s +2025-10-30 15:28:22.637878: +2025-10-30 15:28:22.640325: Epoch 76 +2025-10-30 15:28:22.642105: Current learning rate: 0.00931 +2025-10-30 15:28:42.593686: train_loss -0.9755 +2025-10-30 15:28:42.617626: val_loss -0.9165 +2025-10-30 15:28:42.636961: Pseudo dice [np.float32(0.9827), np.float32(0.9915), np.float32(0.9956), np.float32(0.8335)] +2025-10-30 15:28:42.657176: Epoch time: 19.96 s +2025-10-30 15:28:43.761253: +2025-10-30 15:28:43.763668: Epoch 77 +2025-10-30 15:28:43.765630: Current learning rate: 0.0093 +2025-10-30 15:29:03.446229: train_loss -0.9758 +2025-10-30 15:29:03.449071: val_loss -0.9175 +2025-10-30 15:29:03.451083: Pseudo dice [np.float32(0.9829), np.float32(0.9915), np.float32(0.9959), np.float32(0.8333)] +2025-10-30 15:29:03.453914: Epoch time: 19.69 s +2025-10-30 15:29:04.652985: +2025-10-30 15:29:04.655066: Epoch 78 +2025-10-30 15:29:04.656899: Current learning rate: 0.0093 +2025-10-30 15:29:24.489393: train_loss -0.975 +2025-10-30 15:29:24.492116: val_loss -0.9238 +2025-10-30 15:29:24.493626: Pseudo dice [np.float32(0.9837), np.float32(0.9914), np.float32(0.9957), np.float32(0.8443)] +2025-10-30 15:29:24.495422: Epoch time: 19.84 s +2025-10-30 15:29:25.678455: +2025-10-30 15:29:25.680649: Epoch 79 +2025-10-30 15:29:25.682656: Current learning rate: 0.00929 +2025-10-30 15:29:46.318303: train_loss -0.975 +2025-10-30 15:29:46.321173: val_loss -0.9227 +2025-10-30 15:29:46.322968: Pseudo dice [np.float32(0.9837), np.float32(0.9911), np.float32(0.9954), np.float32(0.8428)] +2025-10-30 15:29:46.325445: Epoch time: 20.64 s +2025-10-30 15:29:48.018943: +2025-10-30 15:29:48.021000: Epoch 80 +2025-10-30 15:29:48.022819: Current learning rate: 0.00928 +2025-10-30 15:30:08.435568: train_loss -0.9718 +2025-10-30 15:30:08.438198: val_loss -0.919 +2025-10-30 15:30:08.440317: Pseudo dice [np.float32(0.9829), np.float32(0.991), np.float32(0.9954), np.float32(0.8352)] +2025-10-30 15:30:08.442245: Epoch time: 20.42 s +2025-10-30 15:30:09.483691: +2025-10-30 15:30:09.485391: Epoch 81 +2025-10-30 15:30:09.487857: Current learning rate: 0.00927 +2025-10-30 15:30:30.003761: train_loss -0.9691 +2025-10-30 15:30:30.006789: val_loss -0.9094 +2025-10-30 15:30:30.008512: Pseudo dice [np.float32(0.983), np.float32(0.991), np.float32(0.9949), np.float32(0.8174)] +2025-10-30 15:30:30.010281: Epoch time: 20.52 s +2025-10-30 15:30:31.225668: +2025-10-30 15:30:31.227957: Epoch 82 +2025-10-30 15:30:31.229738: Current learning rate: 0.00926 +2025-10-30 15:30:51.767157: train_loss -0.9696 +2025-10-30 15:30:51.769537: val_loss -0.9081 +2025-10-30 15:30:51.771487: Pseudo dice [np.float32(0.9806), np.float32(0.9898), np.float32(0.995), np.float32(0.8167)] +2025-10-30 15:30:51.773208: Epoch time: 20.54 s +2025-10-30 15:30:52.752353: +2025-10-30 15:30:52.754255: Epoch 83 +2025-10-30 15:30:52.756083: Current learning rate: 0.00925 +2025-10-30 15:31:12.298138: train_loss -0.9733 +2025-10-30 15:31:12.300435: val_loss -0.9173 +2025-10-30 15:31:12.302067: Pseudo dice [np.float32(0.9836), np.float32(0.9913), np.float32(0.9953), np.float32(0.8253)] +2025-10-30 15:31:12.303650: Epoch time: 19.55 s +2025-10-30 15:31:13.332955: +2025-10-30 15:31:13.335651: Epoch 84 +2025-10-30 15:31:13.338012: Current learning rate: 0.00924 +2025-10-30 15:31:32.828600: train_loss -0.9752 +2025-10-30 15:31:32.831553: val_loss -0.9126 +2025-10-30 15:31:32.833210: Pseudo dice [np.float32(0.9822), np.float32(0.9907), np.float32(0.9949), np.float32(0.8269)] +2025-10-30 15:31:32.834820: Epoch time: 19.5 s +2025-10-30 15:31:34.049653: +2025-10-30 15:31:34.051455: Epoch 85 +2025-10-30 15:31:34.053013: Current learning rate: 0.00923 +2025-10-30 15:31:54.400952: train_loss -0.9754 +2025-10-30 15:31:54.403549: val_loss -0.9188 +2025-10-30 15:31:54.405410: Pseudo dice [np.float32(0.9838), np.float32(0.9904), np.float32(0.9952), np.float32(0.8404)] +2025-10-30 15:31:54.407125: Epoch time: 20.35 s +2025-10-30 15:31:55.510359: +2025-10-30 15:31:55.512363: Epoch 86 +2025-10-30 15:31:55.514333: Current learning rate: 0.00922 +2025-10-30 15:32:16.044541: train_loss -0.9776 +2025-10-30 15:32:16.046942: val_loss -0.9172 +2025-10-30 15:32:16.048929: Pseudo dice [np.float32(0.9832), np.float32(0.9904), np.float32(0.9954), np.float32(0.8358)] +2025-10-30 15:32:16.050893: Epoch time: 20.54 s +2025-10-30 15:32:17.219521: +2025-10-30 15:32:17.221946: Epoch 87 +2025-10-30 15:32:17.223851: Current learning rate: 0.00921 +2025-10-30 15:32:37.802777: train_loss -0.9744 +2025-10-30 15:32:37.806148: val_loss -0.9117 +2025-10-30 15:32:37.807925: Pseudo dice [np.float32(0.9842), np.float32(0.991), np.float32(0.9949), np.float32(0.8196)] +2025-10-30 15:32:37.809931: Epoch time: 20.58 s +2025-10-30 15:32:39.045991: +2025-10-30 15:32:39.047787: Epoch 88 +2025-10-30 15:32:39.049511: Current learning rate: 0.0092 +2025-10-30 15:32:59.517549: train_loss -0.9743 +2025-10-30 15:32:59.520780: val_loss -0.9126 +2025-10-30 15:32:59.523137: Pseudo dice [np.float32(0.9833), np.float32(0.9897), np.float32(0.9953), np.float32(0.8277)] +2025-10-30 15:32:59.525142: Epoch time: 20.47 s +2025-10-30 15:33:00.717187: +2025-10-30 15:33:00.719740: Epoch 89 +2025-10-30 15:33:00.721585: Current learning rate: 0.0092 +2025-10-30 15:33:20.351982: train_loss -0.9778 +2025-10-30 15:33:20.357492: val_loss -0.9165 +2025-10-30 15:33:20.359184: Pseudo dice [np.float32(0.9844), np.float32(0.9908), np.float32(0.995), np.float32(0.83)] +2025-10-30 15:33:20.361086: Epoch time: 19.64 s +2025-10-30 15:33:21.433101: +2025-10-30 15:33:21.435519: Epoch 90 +2025-10-30 15:33:21.437738: Current learning rate: 0.00919 +2025-10-30 15:33:41.971597: train_loss -0.9786 +2025-10-30 15:33:41.978478: val_loss -0.9206 +2025-10-30 15:33:41.980488: Pseudo dice [np.float32(0.9852), np.float32(0.9915), np.float32(0.9954), np.float32(0.8311)] +2025-10-30 15:33:41.982627: Epoch time: 20.54 s +2025-10-30 15:33:42.961903: +2025-10-30 15:33:42.963947: Epoch 91 +2025-10-30 15:33:42.965873: Current learning rate: 0.00918 +2025-10-30 15:34:02.650210: train_loss -0.9776 +2025-10-30 15:34:02.652801: val_loss -0.9137 +2025-10-30 15:34:02.654619: Pseudo dice [np.float32(0.9826), np.float32(0.9909), np.float32(0.9951), np.float32(0.8275)] +2025-10-30 15:34:02.656368: Epoch time: 19.69 s +2025-10-30 15:34:04.421796: +2025-10-30 15:34:04.423890: Epoch 92 +2025-10-30 15:34:04.426143: Current learning rate: 0.00917 +2025-10-30 15:34:24.808213: train_loss -0.9781 +2025-10-30 15:34:24.810432: val_loss -0.925 +2025-10-30 15:34:24.811990: Pseudo dice [np.float32(0.9839), np.float32(0.9915), np.float32(0.9958), np.float32(0.8557)] +2025-10-30 15:34:24.813400: Epoch time: 20.39 s +2025-10-30 15:34:25.872645: +2025-10-30 15:34:25.874902: Epoch 93 +2025-10-30 15:34:25.876456: Current learning rate: 0.00916 +2025-10-30 15:34:46.405465: train_loss -0.9789 +2025-10-30 15:34:46.408240: val_loss -0.9109 +2025-10-30 15:34:46.409869: Pseudo dice [np.float32(0.9837), np.float32(0.9908), np.float32(0.995), np.float32(0.8259)] +2025-10-30 15:34:46.411294: Epoch time: 20.53 s +2025-10-30 15:34:47.459925: +2025-10-30 15:34:47.461713: Epoch 94 +2025-10-30 15:34:47.463309: Current learning rate: 0.00915 +2025-10-30 15:35:08.021062: train_loss -0.9778 +2025-10-30 15:35:08.023264: val_loss -0.9083 +2025-10-30 15:35:08.024832: Pseudo dice [np.float32(0.9823), np.float32(0.9899), np.float32(0.9951), np.float32(0.8284)] +2025-10-30 15:35:08.026429: Epoch time: 20.56 s +2025-10-30 15:35:09.211006: +2025-10-30 15:35:09.213018: Epoch 95 +2025-10-30 15:35:09.214716: Current learning rate: 0.00914 +2025-10-30 15:35:29.172046: train_loss -0.9761 +2025-10-30 15:35:29.174138: val_loss -0.917 +2025-10-30 15:35:29.175696: Pseudo dice [np.float32(0.9824), np.float32(0.9918), np.float32(0.9955), np.float32(0.8367)] +2025-10-30 15:35:29.177374: Epoch time: 19.96 s +2025-10-30 15:35:30.048187: +2025-10-30 15:35:30.050056: Epoch 96 +2025-10-30 15:35:30.051618: Current learning rate: 0.00913 +2025-10-30 15:35:50.075351: train_loss -0.9769 +2025-10-30 15:35:50.082329: val_loss -0.9126 +2025-10-30 15:35:50.083985: Pseudo dice [np.float32(0.9823), np.float32(0.9897), np.float32(0.9953), np.float32(0.8252)] +2025-10-30 15:35:50.085625: Epoch time: 20.03 s +2025-10-30 15:35:51.233957: +2025-10-30 15:35:51.238853: Epoch 97 +2025-10-30 15:35:51.243722: Current learning rate: 0.00912 +2025-10-30 15:36:11.870103: train_loss -0.9783 +2025-10-30 15:36:11.872504: val_loss -0.9173 +2025-10-30 15:36:11.874181: Pseudo dice [np.float32(0.9831), np.float32(0.9902), np.float32(0.9952), np.float32(0.8411)] +2025-10-30 15:36:11.875846: Epoch time: 20.64 s +2025-10-30 15:36:12.848130: +2025-10-30 15:36:12.850357: Epoch 98 +2025-10-30 15:36:12.852143: Current learning rate: 0.00911 +2025-10-30 15:36:32.525466: train_loss -0.98 +2025-10-30 15:36:32.528167: val_loss -0.9156 +2025-10-30 15:36:32.530082: Pseudo dice [np.float32(0.9828), np.float32(0.9902), np.float32(0.9952), np.float32(0.8374)] +2025-10-30 15:36:32.531887: Epoch time: 19.68 s +2025-10-30 15:36:33.730007: +2025-10-30 15:36:33.732255: Epoch 99 +2025-10-30 15:36:33.734367: Current learning rate: 0.0091 +2025-10-30 15:36:54.332785: train_loss -0.9795 +2025-10-30 15:36:54.335771: val_loss -0.9144 +2025-10-30 15:36:54.337544: Pseudo dice [np.float32(0.9814), np.float32(0.9901), np.float32(0.9953), np.float32(0.8342)] +2025-10-30 15:36:54.339804: Epoch time: 20.6 s +2025-10-30 15:36:56.769951: +2025-10-30 15:36:56.771542: Epoch 100 +2025-10-30 15:36:56.773272: Current learning rate: 0.0091 +2025-10-30 15:37:17.300157: train_loss -0.9784 +2025-10-30 15:37:17.302809: val_loss -0.906 +2025-10-30 15:37:17.304815: Pseudo dice [np.float32(0.9812), np.float32(0.9898), np.float32(0.9952), np.float32(0.8186)] +2025-10-30 15:37:17.306695: Epoch time: 20.53 s +2025-10-30 15:37:18.343853: +2025-10-30 15:37:18.345575: Epoch 101 +2025-10-30 15:37:18.347334: Current learning rate: 0.00909 +2025-10-30 15:37:38.866908: train_loss -0.9753 +2025-10-30 15:37:38.869377: val_loss -0.9105 +2025-10-30 15:37:38.871792: Pseudo dice [np.float32(0.9824), np.float32(0.9902), np.float32(0.9951), np.float32(0.8255)] +2025-10-30 15:37:38.874043: Epoch time: 20.53 s +2025-10-30 15:37:39.859019: +2025-10-30 15:37:39.860983: Epoch 102 +2025-10-30 15:37:39.862833: Current learning rate: 0.00908 +2025-10-30 15:37:59.528915: train_loss -0.9769 +2025-10-30 15:37:59.531989: val_loss -0.9179 +2025-10-30 15:37:59.533883: Pseudo dice [np.float32(0.9836), np.float32(0.9906), np.float32(0.9952), np.float32(0.833)] +2025-10-30 15:37:59.535712: Epoch time: 19.67 s +2025-10-30 15:38:00.503281: +2025-10-30 15:38:00.505293: Epoch 103 +2025-10-30 15:38:00.507128: Current learning rate: 0.00907 +2025-10-30 15:38:21.173380: train_loss -0.9776 +2025-10-30 15:38:21.175900: val_loss -0.9061 +2025-10-30 15:38:21.177628: Pseudo dice [np.float32(0.9831), np.float32(0.9912), np.float32(0.9951), np.float32(0.8121)] +2025-10-30 15:38:21.179482: Epoch time: 20.67 s +2025-10-30 15:38:22.411438: +2025-10-30 15:38:22.413412: Epoch 104 +2025-10-30 15:38:22.415086: Current learning rate: 0.00906 +2025-10-30 15:38:42.779392: train_loss -0.9766 +2025-10-30 15:38:42.781817: val_loss -0.9013 +2025-10-30 15:38:42.783428: Pseudo dice [np.float32(0.9831), np.float32(0.9907), np.float32(0.9947), np.float32(0.8014)] +2025-10-30 15:38:42.785090: Epoch time: 20.37 s +2025-10-30 15:38:44.144609: +2025-10-30 15:38:44.147798: Epoch 105 +2025-10-30 15:38:44.150848: Current learning rate: 0.00905 +2025-10-30 15:39:04.111471: train_loss -0.9769 +2025-10-30 15:39:04.117563: val_loss -0.9224 +2025-10-30 15:39:04.119150: Pseudo dice [np.float32(0.9848), np.float32(0.9913), np.float32(0.9954), np.float32(0.8411)] +2025-10-30 15:39:04.121037: Epoch time: 19.97 s +2025-10-30 15:39:05.393352: +2025-10-30 15:39:05.395720: Epoch 106 +2025-10-30 15:39:05.397716: Current learning rate: 0.00904 +2025-10-30 15:39:26.171359: train_loss -0.9769 +2025-10-30 15:39:26.173997: val_loss -0.91 +2025-10-30 15:39:26.175400: Pseudo dice [np.float32(0.9828), np.float32(0.9907), np.float32(0.9954), np.float32(0.8222)] +2025-10-30 15:39:26.176884: Epoch time: 20.78 s +2025-10-30 15:39:27.353292: +2025-10-30 15:39:27.355763: Epoch 107 +2025-10-30 15:39:27.358991: Current learning rate: 0.00903 +2025-10-30 15:39:48.044174: train_loss -0.9793 +2025-10-30 15:39:48.047216: val_loss -0.9176 +2025-10-30 15:39:48.049045: Pseudo dice [np.float32(0.9815), np.float32(0.9903), np.float32(0.9955), np.float32(0.8476)] +2025-10-30 15:39:48.050760: Epoch time: 20.69 s +2025-10-30 15:39:49.250351: +2025-10-30 15:39:49.252650: Epoch 108 +2025-10-30 15:39:49.254170: Current learning rate: 0.00902 +2025-10-30 15:40:08.811257: train_loss -0.9791 +2025-10-30 15:40:08.814561: val_loss -0.9225 +2025-10-30 15:40:08.816530: Pseudo dice [np.float32(0.9846), np.float32(0.9909), np.float32(0.9955), np.float32(0.8481)] +2025-10-30 15:40:08.818319: Epoch time: 19.56 s +2025-10-30 15:40:09.799415: +2025-10-30 15:40:09.801895: Epoch 109 +2025-10-30 15:40:09.803923: Current learning rate: 0.00901 +2025-10-30 15:40:30.472824: train_loss -0.9792 +2025-10-30 15:40:30.475141: val_loss -0.9173 +2025-10-30 15:40:30.476755: Pseudo dice [np.float32(0.9839), np.float32(0.9912), np.float32(0.9951), np.float32(0.8428)] +2025-10-30 15:40:30.478344: Epoch time: 20.68 s +2025-10-30 15:40:31.483099: +2025-10-30 15:40:31.484790: Epoch 110 +2025-10-30 15:40:31.486299: Current learning rate: 0.009 +2025-10-30 15:40:52.056589: train_loss -0.98 +2025-10-30 15:40:52.059326: val_loss -0.9119 +2025-10-30 15:40:52.061202: Pseudo dice [np.float32(0.9825), np.float32(0.9904), np.float32(0.9952), np.float32(0.8287)] +2025-10-30 15:40:52.063088: Epoch time: 20.57 s +2025-10-30 15:40:53.176016: +2025-10-30 15:40:53.178137: Epoch 111 +2025-10-30 15:40:53.180078: Current learning rate: 0.009 +2025-10-30 15:41:13.056671: train_loss -0.9794 +2025-10-30 15:41:13.059879: val_loss -0.9071 +2025-10-30 15:41:13.061764: Pseudo dice [np.float32(0.9809), np.float32(0.9901), np.float32(0.995), np.float32(0.825)] +2025-10-30 15:41:13.064263: Epoch time: 19.88 s +2025-10-30 15:41:14.246874: +2025-10-30 15:41:14.249048: Epoch 112 +2025-10-30 15:41:14.250973: Current learning rate: 0.00899 +2025-10-30 15:41:34.533372: train_loss -0.9797 +2025-10-30 15:41:34.535588: val_loss -0.9119 +2025-10-30 15:41:34.537155: Pseudo dice [np.float32(0.9824), np.float32(0.9907), np.float32(0.9952), np.float32(0.831)] +2025-10-30 15:41:34.540373: Epoch time: 20.29 s +2025-10-30 15:41:35.693718: +2025-10-30 15:41:35.695848: Epoch 113 +2025-10-30 15:41:35.697614: Current learning rate: 0.00898 +2025-10-30 15:41:56.321494: train_loss -0.9793 +2025-10-30 15:41:56.323872: val_loss -0.9082 +2025-10-30 15:41:56.325647: Pseudo dice [np.float32(0.982), np.float32(0.9908), np.float32(0.9953), np.float32(0.8241)] +2025-10-30 15:41:56.327302: Epoch time: 20.63 s +2025-10-30 15:41:57.390980: +2025-10-30 15:41:57.393253: Epoch 114 +2025-10-30 15:41:57.394967: Current learning rate: 0.00897 +2025-10-30 15:42:17.971543: train_loss -0.9757 +2025-10-30 15:42:17.973962: val_loss -0.9116 +2025-10-30 15:42:17.975451: Pseudo dice [np.float32(0.9837), np.float32(0.9906), np.float32(0.9944), np.float32(0.8191)] +2025-10-30 15:42:17.976946: Epoch time: 20.58 s +2025-10-30 15:42:19.111143: +2025-10-30 15:42:19.113163: Epoch 115 +2025-10-30 15:42:19.114872: Current learning rate: 0.00896 +2025-10-30 15:42:39.174322: train_loss -0.976 +2025-10-30 15:42:39.177292: val_loss -0.9212 +2025-10-30 15:42:39.179280: Pseudo dice [np.float32(0.9831), np.float32(0.9915), np.float32(0.9955), np.float32(0.851)] +2025-10-30 15:42:39.181290: Epoch time: 20.07 s +2025-10-30 15:42:40.435253: +2025-10-30 15:42:40.437224: Epoch 116 +2025-10-30 15:42:40.438886: Current learning rate: 0.00895 +2025-10-30 15:43:01.074062: train_loss -0.9811 +2025-10-30 15:43:01.076537: val_loss -0.9197 +2025-10-30 15:43:01.078420: Pseudo dice [np.float32(0.9843), np.float32(0.9912), np.float32(0.9957), np.float32(0.8426)] +2025-10-30 15:43:01.079986: Epoch time: 20.64 s +2025-10-30 15:43:02.546421: +2025-10-30 15:43:02.548355: Epoch 117 +2025-10-30 15:43:02.550211: Current learning rate: 0.00894 +2025-10-30 15:43:23.097488: train_loss -0.9803 +2025-10-30 15:43:23.100646: val_loss -0.9153 +2025-10-30 15:43:23.102421: Pseudo dice [np.float32(0.9824), np.float32(0.9911), np.float32(0.9952), np.float32(0.8351)] +2025-10-30 15:43:23.104007: Epoch time: 20.55 s +2025-10-30 15:43:24.298019: +2025-10-30 15:43:24.300083: Epoch 118 +2025-10-30 15:43:24.302491: Current learning rate: 0.00893 +2025-10-30 15:43:44.058739: train_loss -0.981 +2025-10-30 15:43:44.061761: val_loss -0.9093 +2025-10-30 15:43:44.064109: Pseudo dice [np.float32(0.9822), np.float32(0.9908), np.float32(0.9952), np.float32(0.8223)] +2025-10-30 15:43:44.065830: Epoch time: 19.76 s +2025-10-30 15:43:45.326100: +2025-10-30 15:43:45.328056: Epoch 119 +2025-10-30 15:43:45.329847: Current learning rate: 0.00892 +2025-10-30 15:44:05.921361: train_loss -0.9809 +2025-10-30 15:44:05.924011: val_loss -0.911 +2025-10-30 15:44:05.925402: Pseudo dice [np.float32(0.9835), np.float32(0.9899), np.float32(0.995), np.float32(0.8249)] +2025-10-30 15:44:05.926872: Epoch time: 20.6 s +2025-10-30 15:44:07.060322: +2025-10-30 15:44:07.062472: Epoch 120 +2025-10-30 15:44:07.064337: Current learning rate: 0.00891 +2025-10-30 15:44:27.502443: train_loss -0.9808 +2025-10-30 15:44:27.505191: val_loss -0.9141 +2025-10-30 15:44:27.506617: Pseudo dice [np.float32(0.9839), np.float32(0.9907), np.float32(0.9952), np.float32(0.8343)] +2025-10-30 15:44:27.508117: Epoch time: 20.44 s +2025-10-30 15:44:28.503467: +2025-10-30 15:44:28.505256: Epoch 121 +2025-10-30 15:44:28.506891: Current learning rate: 0.0089 +2025-10-30 15:44:48.139814: train_loss -0.9801 +2025-10-30 15:44:48.142808: val_loss -0.9123 +2025-10-30 15:44:48.145568: Pseudo dice [np.float32(0.9826), np.float32(0.9909), np.float32(0.9953), np.float32(0.8263)] +2025-10-30 15:44:48.148280: Epoch time: 19.64 s +2025-10-30 15:44:49.379267: +2025-10-30 15:44:49.381376: Epoch 122 +2025-10-30 15:44:49.383422: Current learning rate: 0.00889 +2025-10-30 15:45:09.827039: train_loss -0.9805 +2025-10-30 15:45:09.829468: val_loss -0.9149 +2025-10-30 15:45:09.831508: Pseudo dice [np.float32(0.9838), np.float32(0.9913), np.float32(0.9954), np.float32(0.8403)] +2025-10-30 15:45:09.833319: Epoch time: 20.45 s +2025-10-30 15:45:10.955221: +2025-10-30 15:45:10.957580: Epoch 123 +2025-10-30 15:45:10.959703: Current learning rate: 0.00889 +2025-10-30 15:45:31.875838: train_loss -0.9803 +2025-10-30 15:45:31.878063: val_loss -0.9147 +2025-10-30 15:45:31.879534: Pseudo dice [np.float32(0.9842), np.float32(0.9913), np.float32(0.9953), np.float32(0.8412)] +2025-10-30 15:45:31.880981: Epoch time: 20.92 s +2025-10-30 15:45:32.863501: +2025-10-30 15:45:32.865375: Epoch 124 +2025-10-30 15:45:32.866943: Current learning rate: 0.00888 +2025-10-30 15:45:53.407913: train_loss -0.98 +2025-10-30 15:45:53.410554: val_loss -0.9119 +2025-10-30 15:45:53.413112: Pseudo dice [np.float32(0.982), np.float32(0.9906), np.float32(0.9955), np.float32(0.829)] +2025-10-30 15:45:53.414847: Epoch time: 20.55 s +2025-10-30 15:45:54.395762: +2025-10-30 15:45:54.397694: Epoch 125 +2025-10-30 15:45:54.399323: Current learning rate: 0.00887 +2025-10-30 15:46:14.123295: train_loss -0.9811 +2025-10-30 15:46:14.125655: val_loss -0.9164 +2025-10-30 15:46:14.127372: Pseudo dice [np.float32(0.9849), np.float32(0.9915), np.float32(0.9956), np.float32(0.8385)] +2025-10-30 15:46:14.129471: Epoch time: 19.73 s +2025-10-30 15:46:15.442675: +2025-10-30 15:46:15.444837: Epoch 126 +2025-10-30 15:46:15.446676: Current learning rate: 0.00886 +2025-10-30 15:46:36.249953: train_loss -0.9815 +2025-10-30 15:46:36.252704: val_loss -0.9137 +2025-10-30 15:46:36.255150: Pseudo dice [np.float32(0.9827), np.float32(0.9905), np.float32(0.9954), np.float32(0.8389)] +2025-10-30 15:46:36.257447: Epoch time: 20.81 s +2025-10-30 15:46:37.437439: +2025-10-30 15:46:37.439709: Epoch 127 +2025-10-30 15:46:37.442748: Current learning rate: 0.00885 +2025-10-30 15:46:56.861772: train_loss -0.9812 +2025-10-30 15:46:56.865858: val_loss -0.9123 +2025-10-30 15:46:56.868153: Pseudo dice [np.float32(0.9844), np.float32(0.9907), np.float32(0.995), np.float32(0.8262)] +2025-10-30 15:46:56.869925: Epoch time: 19.43 s +2025-10-30 15:46:57.930609: +2025-10-30 15:46:57.932505: Epoch 128 +2025-10-30 15:46:57.934320: Current learning rate: 0.00884 +2025-10-30 15:47:18.714395: train_loss -0.9779 +2025-10-30 15:47:18.717852: val_loss -0.9084 +2025-10-30 15:47:18.719485: Pseudo dice [np.float32(0.9818), np.float32(0.9904), np.float32(0.9953), np.float32(0.8192)] +2025-10-30 15:47:18.721247: Epoch time: 20.79 s +2025-10-30 15:47:19.937637: +2025-10-30 15:47:19.939721: Epoch 129 +2025-10-30 15:47:19.941497: Current learning rate: 0.00883 +2025-10-30 15:47:40.851438: train_loss -0.9809 +2025-10-30 15:47:40.854147: val_loss -0.9065 +2025-10-30 15:47:40.855934: Pseudo dice [np.float32(0.9827), np.float32(0.99), np.float32(0.995), np.float32(0.8191)] +2025-10-30 15:47:40.857798: Epoch time: 20.92 s +2025-10-30 15:47:41.907432: +2025-10-30 15:47:41.909257: Epoch 130 +2025-10-30 15:47:41.910867: Current learning rate: 0.00882 +2025-10-30 15:48:02.380518: train_loss -0.9819 +2025-10-30 15:48:02.385910: val_loss -0.909 +2025-10-30 15:48:02.387792: Pseudo dice [np.float32(0.983), np.float32(0.9905), np.float32(0.9949), np.float32(0.8235)] +2025-10-30 15:48:02.389361: Epoch time: 20.47 s +2025-10-30 15:48:03.410068: +2025-10-30 15:48:03.412104: Epoch 131 +2025-10-30 15:48:03.415009: Current learning rate: 0.00881 +2025-10-30 15:48:24.025349: train_loss -0.9824 +2025-10-30 15:48:24.027946: val_loss -0.912 +2025-10-30 15:48:24.029810: Pseudo dice [np.float32(0.9844), np.float32(0.9907), np.float32(0.9951), np.float32(0.8289)] +2025-10-30 15:48:24.031500: Epoch time: 20.62 s +2025-10-30 15:48:25.302087: +2025-10-30 15:48:25.304056: Epoch 132 +2025-10-30 15:48:25.305743: Current learning rate: 0.0088 +2025-10-30 15:48:44.511763: train_loss -0.9815 +2025-10-30 15:48:44.515680: val_loss -0.9167 +2025-10-30 15:48:44.518064: Pseudo dice [np.float32(0.9846), np.float32(0.9917), np.float32(0.9955), np.float32(0.8323)] +2025-10-30 15:48:44.520262: Epoch time: 19.21 s +2025-10-30 15:48:45.653125: +2025-10-30 15:48:45.655361: Epoch 133 +2025-10-30 15:48:45.657628: Current learning rate: 0.00879 +2025-10-30 15:49:06.026623: train_loss -0.9807 +2025-10-30 15:49:06.029191: val_loss -0.9191 +2025-10-30 15:49:06.031988: Pseudo dice [np.float32(0.9814), np.float32(0.9905), np.float32(0.9958), np.float32(0.8529)] +2025-10-30 15:49:06.034638: Epoch time: 20.37 s +2025-10-30 15:49:07.087205: +2025-10-30 15:49:07.089077: Epoch 134 +2025-10-30 15:49:07.091518: Current learning rate: 0.00879 +2025-10-30 15:49:26.613347: train_loss -0.9804 +2025-10-30 15:49:26.615349: val_loss -0.9114 +2025-10-30 15:49:26.617109: Pseudo dice [np.float32(0.9829), np.float32(0.99), np.float32(0.9953), np.float32(0.8311)] +2025-10-30 15:49:26.619014: Epoch time: 19.53 s +2025-10-30 15:49:27.800289: +2025-10-30 15:49:27.802133: Epoch 135 +2025-10-30 15:49:27.803689: Current learning rate: 0.00878 +2025-10-30 15:49:48.555279: train_loss -0.9792 +2025-10-30 15:49:48.558169: val_loss -0.9163 +2025-10-30 15:49:48.560033: Pseudo dice [np.float32(0.9839), np.float32(0.9906), np.float32(0.9951), np.float32(0.8345)] +2025-10-30 15:49:48.561918: Epoch time: 20.76 s +2025-10-30 15:49:49.766859: +2025-10-30 15:49:49.769169: Epoch 136 +2025-10-30 15:49:49.771160: Current learning rate: 0.00877 +2025-10-30 15:50:10.250557: train_loss -0.9818 +2025-10-30 15:50:10.253675: val_loss -0.9136 +2025-10-30 15:50:10.255595: Pseudo dice [np.float32(0.9827), np.float32(0.9909), np.float32(0.9954), np.float32(0.8332)] +2025-10-30 15:50:10.257524: Epoch time: 20.49 s +2025-10-30 15:50:11.431216: +2025-10-30 15:50:11.433123: Epoch 137 +2025-10-30 15:50:11.435070: Current learning rate: 0.00876 +2025-10-30 15:50:32.159941: train_loss -0.9814 +2025-10-30 15:50:32.162213: val_loss -0.9072 +2025-10-30 15:50:32.164038: Pseudo dice [np.float32(0.9833), np.float32(0.9901), np.float32(0.9949), np.float32(0.8249)] +2025-10-30 15:50:32.165768: Epoch time: 20.73 s +2025-10-30 15:50:33.157550: +2025-10-30 15:50:33.159499: Epoch 138 +2025-10-30 15:50:33.161163: Current learning rate: 0.00875 +2025-10-30 15:50:53.518852: train_loss -0.9823 +2025-10-30 15:50:53.521819: val_loss -0.9072 +2025-10-30 15:50:53.523580: Pseudo dice [np.float32(0.9825), np.float32(0.9894), np.float32(0.9949), np.float32(0.8272)] +2025-10-30 15:50:53.525327: Epoch time: 20.36 s +2025-10-30 15:50:54.591758: +2025-10-30 15:50:54.594068: Epoch 139 +2025-10-30 15:50:54.595961: Current learning rate: 0.00874 +2025-10-30 15:51:14.505842: train_loss -0.9591 +2025-10-30 15:51:14.511724: val_loss -0.92 +2025-10-30 15:51:14.513521: Pseudo dice [np.float32(0.9799), np.float32(0.9902), np.float32(0.995), np.float32(0.8324)] +2025-10-30 15:51:14.515213: Epoch time: 19.92 s +2025-10-30 15:51:15.782819: +2025-10-30 15:51:15.784845: Epoch 140 +2025-10-30 15:51:15.786482: Current learning rate: 0.00873 +2025-10-30 15:51:35.229512: train_loss -0.9441 +2025-10-30 15:51:35.231704: val_loss -0.9135 +2025-10-30 15:51:35.233647: Pseudo dice [np.float32(0.9836), np.float32(0.9911), np.float32(0.9945), np.float32(0.8122)] +2025-10-30 15:51:35.235461: Epoch time: 19.45 s +2025-10-30 15:51:36.622117: +2025-10-30 15:51:36.624017: Epoch 141 +2025-10-30 15:51:36.626377: Current learning rate: 0.00872 +2025-10-30 15:51:57.297534: train_loss -0.9585 +2025-10-30 15:51:57.305058: val_loss -0.9162 +2025-10-30 15:51:57.309338: Pseudo dice [np.float32(0.9825), np.float32(0.9894), np.float32(0.995), np.float32(0.8267)] +2025-10-30 15:51:57.313797: Epoch time: 20.68 s +2025-10-30 15:51:58.475789: +2025-10-30 15:51:58.477741: Epoch 142 +2025-10-30 15:51:58.479799: Current learning rate: 0.00871 +2025-10-30 15:52:19.248822: train_loss -0.9684 +2025-10-30 15:52:19.251965: val_loss -0.9139 +2025-10-30 15:52:19.254223: Pseudo dice [np.float32(0.9829), np.float32(0.9906), np.float32(0.9947), np.float32(0.8175)] +2025-10-30 15:52:19.256455: Epoch time: 20.78 s +2025-10-30 15:52:20.580470: +2025-10-30 15:52:20.582561: Epoch 143 +2025-10-30 15:52:20.584456: Current learning rate: 0.0087 +2025-10-30 15:52:41.073004: train_loss -0.9687 +2025-10-30 15:52:41.074804: val_loss -0.9193 +2025-10-30 15:52:41.076286: Pseudo dice [np.float32(0.9841), np.float32(0.9911), np.float32(0.9949), np.float32(0.8355)] +2025-10-30 15:52:41.077756: Epoch time: 20.49 s +2025-10-30 15:52:42.180798: +2025-10-30 15:52:42.182540: Epoch 144 +2025-10-30 15:52:42.184083: Current learning rate: 0.00869 +2025-10-30 15:53:02.681085: train_loss -0.9702 +2025-10-30 15:53:02.684433: val_loss -0.9079 +2025-10-30 15:53:02.686250: Pseudo dice [np.float32(0.9818), np.float32(0.9897), np.float32(0.9947), np.float32(0.8147)] +2025-10-30 15:53:02.687842: Epoch time: 20.5 s +2025-10-30 15:53:03.674780: +2025-10-30 15:53:03.676560: Epoch 145 +2025-10-30 15:53:03.680051: Current learning rate: 0.00868 +2025-10-30 15:53:23.900592: train_loss -0.9688 +2025-10-30 15:53:23.902960: val_loss -0.9088 +2025-10-30 15:53:23.904545: Pseudo dice [np.float32(0.9794), np.float32(0.9874), np.float32(0.9947), np.float32(0.8248)] +2025-10-30 15:53:23.906107: Epoch time: 20.23 s +2025-10-30 15:53:25.081492: +2025-10-30 15:53:25.083438: Epoch 146 +2025-10-30 15:53:25.085290: Current learning rate: 0.00868 +2025-10-30 15:53:44.280750: train_loss -0.9624 +2025-10-30 15:53:44.283257: val_loss -0.9237 +2025-10-30 15:53:44.284875: Pseudo dice [np.float32(0.9843), np.float32(0.9914), np.float32(0.995), np.float32(0.836)] +2025-10-30 15:53:44.286506: Epoch time: 19.2 s +2025-10-30 15:53:45.279914: +2025-10-30 15:53:45.281884: Epoch 147 +2025-10-30 15:53:45.283658: Current learning rate: 0.00867 +2025-10-30 15:54:05.995089: train_loss -0.9696 +2025-10-30 15:54:05.998114: val_loss -0.9168 +2025-10-30 15:54:05.999913: Pseudo dice [np.float32(0.984), np.float32(0.9912), np.float32(0.9952), np.float32(0.8274)] +2025-10-30 15:54:06.001834: Epoch time: 20.72 s +2025-10-30 15:54:07.184371: +2025-10-30 15:54:07.186146: Epoch 148 +2025-10-30 15:54:07.187880: Current learning rate: 0.00866 +2025-10-30 15:54:27.972523: train_loss -0.9761 +2025-10-30 15:54:27.975418: val_loss -0.9193 +2025-10-30 15:54:27.977224: Pseudo dice [np.float32(0.9858), np.float32(0.9916), np.float32(0.9951), np.float32(0.8269)] +2025-10-30 15:54:27.978899: Epoch time: 20.79 s +2025-10-30 15:54:29.074279: +2025-10-30 15:54:29.075968: Epoch 149 +2025-10-30 15:54:29.077376: Current learning rate: 0.00865 +2025-10-30 15:54:49.657147: train_loss -0.9744 +2025-10-30 15:54:49.659002: val_loss -0.9161 +2025-10-30 15:54:49.660769: Pseudo dice [np.float32(0.982), np.float32(0.9904), np.float32(0.9953), np.float32(0.8334)] +2025-10-30 15:54:49.662301: Epoch time: 20.58 s +2025-10-30 15:54:51.904341: +2025-10-30 15:54:51.906390: Epoch 150 +2025-10-30 15:54:51.908247: Current learning rate: 0.00864 +2025-10-30 15:55:12.323144: train_loss -0.977 +2025-10-30 15:55:12.326387: val_loss -0.9165 +2025-10-30 15:55:12.328333: Pseudo dice [np.float32(0.9842), np.float32(0.9908), np.float32(0.9951), np.float32(0.8297)] +2025-10-30 15:55:12.330187: Epoch time: 20.42 s +2025-10-30 15:55:13.563102: +2025-10-30 15:55:13.565132: Epoch 151 +2025-10-30 15:55:13.567099: Current learning rate: 0.00863 +2025-10-30 15:55:34.376529: train_loss -0.9811 +2025-10-30 15:55:34.379130: val_loss -0.9185 +2025-10-30 15:55:34.381076: Pseudo dice [np.float32(0.9826), np.float32(0.99), np.float32(0.9952), np.float32(0.8405)] +2025-10-30 15:55:34.382740: Epoch time: 20.82 s +2025-10-30 15:55:35.577530: +2025-10-30 15:55:35.579764: Epoch 152 +2025-10-30 15:55:35.581575: Current learning rate: 0.00862 +2025-10-30 15:55:55.209651: train_loss -0.9791 +2025-10-30 15:55:55.211974: val_loss -0.9109 +2025-10-30 15:55:55.213512: Pseudo dice [np.float32(0.9827), np.float32(0.9907), np.float32(0.9951), np.float32(0.8223)] +2025-10-30 15:55:55.215201: Epoch time: 19.63 s +2025-10-30 15:55:56.548845: +2025-10-30 15:55:56.550759: Epoch 153 +2025-10-30 15:55:56.556084: Current learning rate: 0.00861 +2025-10-30 15:56:16.477550: train_loss -0.9765 +2025-10-30 15:56:16.481260: val_loss -0.9198 +2025-10-30 15:56:16.483776: Pseudo dice [np.float32(0.9851), np.float32(0.9911), np.float32(0.9952), np.float32(0.8357)] +2025-10-30 15:56:16.485596: Epoch time: 19.93 s +2025-10-30 15:56:17.546883: +2025-10-30 15:56:17.551481: Epoch 154 +2025-10-30 15:56:17.553491: Current learning rate: 0.0086 +2025-10-30 15:56:38.086330: train_loss -0.9787 +2025-10-30 15:56:38.088539: val_loss -0.9174 +2025-10-30 15:56:38.090213: Pseudo dice [np.float32(0.9844), np.float32(0.9905), np.float32(0.9951), np.float32(0.8405)] +2025-10-30 15:56:38.091869: Epoch time: 20.54 s +2025-10-30 15:56:39.244722: +2025-10-30 15:56:39.266510: Epoch 155 +2025-10-30 15:56:39.268741: Current learning rate: 0.00859 +2025-10-30 15:57:00.060756: train_loss -0.9796 +2025-10-30 15:57:00.063945: val_loss -0.9175 +2025-10-30 15:57:00.066532: Pseudo dice [np.float32(0.9846), np.float32(0.9911), np.float32(0.9954), np.float32(0.8422)] +2025-10-30 15:57:00.068346: Epoch time: 20.82 s +2025-10-30 15:57:01.246604: +2025-10-30 15:57:01.248609: Epoch 156 +2025-10-30 15:57:01.250442: Current learning rate: 0.00858 +2025-10-30 15:57:21.919160: train_loss -0.9804 +2025-10-30 15:57:21.922095: val_loss -0.9073 +2025-10-30 15:57:21.924312: Pseudo dice [np.float32(0.9824), np.float32(0.9897), np.float32(0.9949), np.float32(0.8212)] +2025-10-30 15:57:21.925951: Epoch time: 20.67 s +2025-10-30 15:57:23.158452: +2025-10-30 15:57:23.160311: Epoch 157 +2025-10-30 15:57:23.162195: Current learning rate: 0.00858 +2025-10-30 15:57:43.562351: train_loss -0.9811 +2025-10-30 15:57:43.564555: val_loss -0.9121 +2025-10-30 15:57:43.566092: Pseudo dice [np.float32(0.9833), np.float32(0.9906), np.float32(0.9951), np.float32(0.8339)] +2025-10-30 15:57:43.567575: Epoch time: 20.41 s +2025-10-30 15:57:44.619850: +2025-10-30 15:57:44.622461: Epoch 158 +2025-10-30 15:57:44.624839: Current learning rate: 0.00857 +2025-10-30 15:58:05.116531: train_loss -0.9818 +2025-10-30 15:58:05.121024: val_loss -0.9168 +2025-10-30 15:58:05.122723: Pseudo dice [np.float32(0.9839), np.float32(0.9908), np.float32(0.9951), np.float32(0.8399)] +2025-10-30 15:58:05.124596: Epoch time: 20.5 s +2025-10-30 15:58:06.312042: +2025-10-30 15:58:06.314187: Epoch 159 +2025-10-30 15:58:06.316669: Current learning rate: 0.00856 +2025-10-30 15:58:24.259299: train_loss -0.9815 +2025-10-30 15:58:24.262110: val_loss -0.9125 +2025-10-30 15:58:24.264211: Pseudo dice [np.float32(0.9808), np.float32(0.9895), np.float32(0.9954), np.float32(0.837)] +2025-10-30 15:58:24.266915: Epoch time: 17.95 s +2025-10-30 15:58:25.449459: +2025-10-30 15:58:25.451442: Epoch 160 +2025-10-30 15:58:25.453350: Current learning rate: 0.00855 +2025-10-30 15:58:46.048071: train_loss -0.9829 +2025-10-30 15:58:46.050540: val_loss -0.9109 +2025-10-30 15:58:46.052122: Pseudo dice [np.float32(0.984), np.float32(0.9909), np.float32(0.9949), np.float32(0.8302)] +2025-10-30 15:58:46.053926: Epoch time: 20.6 s +2025-10-30 15:58:47.313135: +2025-10-30 15:58:47.314919: Epoch 161 +2025-10-30 15:58:47.316756: Current learning rate: 0.00854 +2025-10-30 15:59:07.929135: train_loss -0.9832 +2025-10-30 15:59:07.931408: val_loss -0.9161 +2025-10-30 15:59:07.933043: Pseudo dice [np.float32(0.9836), np.float32(0.9907), np.float32(0.9952), np.float32(0.8393)] +2025-10-30 15:59:07.934664: Epoch time: 20.62 s +2025-10-30 15:59:09.007245: +2025-10-30 15:59:09.009490: Epoch 162 +2025-10-30 15:59:09.011357: Current learning rate: 0.00853 +2025-10-30 15:59:29.820274: train_loss -0.9824 +2025-10-30 15:59:29.826489: val_loss -0.8992 +2025-10-30 15:59:29.828335: Pseudo dice [np.float32(0.9831), np.float32(0.9907), np.float32(0.9947), np.float32(0.8003)] +2025-10-30 15:59:29.829841: Epoch time: 20.81 s +2025-10-30 15:59:31.006161: +2025-10-30 15:59:31.008214: Epoch 163 +2025-10-30 15:59:31.009987: Current learning rate: 0.00852 +2025-10-30 15:59:51.481970: train_loss -0.9835 +2025-10-30 15:59:51.487068: val_loss -0.906 +2025-10-30 15:59:51.488806: Pseudo dice [np.float32(0.9838), np.float32(0.9908), np.float32(0.9951), np.float32(0.8143)] +2025-10-30 15:59:51.490327: Epoch time: 20.48 s +2025-10-30 15:59:52.656258: +2025-10-30 15:59:52.658259: Epoch 164 +2025-10-30 15:59:52.660021: Current learning rate: 0.00851 +2025-10-30 16:00:12.920857: train_loss -0.9838 +2025-10-30 16:00:12.923463: val_loss -0.9134 +2025-10-30 16:00:12.925245: Pseudo dice [np.float32(0.9831), np.float32(0.991), np.float32(0.9956), np.float32(0.8341)] +2025-10-30 16:00:12.926804: Epoch time: 20.27 s +2025-10-30 16:00:14.326612: +2025-10-30 16:00:14.328624: Epoch 165 +2025-10-30 16:00:14.330609: Current learning rate: 0.0085 +2025-10-30 16:00:33.931819: train_loss -0.9831 +2025-10-30 16:00:33.934466: val_loss -0.9122 +2025-10-30 16:00:33.936095: Pseudo dice [np.float32(0.9841), np.float32(0.9908), np.float32(0.9954), np.float32(0.8373)] +2025-10-30 16:00:33.937828: Epoch time: 19.61 s +2025-10-30 16:00:34.960979: +2025-10-30 16:00:34.964097: Epoch 166 +2025-10-30 16:00:34.966338: Current learning rate: 0.00849 +2025-10-30 16:00:54.949719: train_loss -0.9825 +2025-10-30 16:00:54.952386: val_loss -0.9049 +2025-10-30 16:00:54.954328: Pseudo dice [np.float32(0.9835), np.float32(0.9905), np.float32(0.9954), np.float32(0.8226)] +2025-10-30 16:00:54.956057: Epoch time: 19.99 s +2025-10-30 16:00:56.242906: +2025-10-30 16:00:56.246043: Epoch 167 +2025-10-30 16:00:56.247944: Current learning rate: 0.00848 +2025-10-30 16:01:16.612519: train_loss -0.983 +2025-10-30 16:01:16.615093: val_loss -0.9175 +2025-10-30 16:01:16.616929: Pseudo dice [np.float32(0.9827), np.float32(0.9906), np.float32(0.9959), np.float32(0.8521)] +2025-10-30 16:01:16.618985: Epoch time: 20.37 s +2025-10-30 16:01:17.715536: +2025-10-30 16:01:17.717491: Epoch 168 +2025-10-30 16:01:17.719261: Current learning rate: 0.00847 +2025-10-30 16:01:38.019451: train_loss -0.984 +2025-10-30 16:01:38.022474: val_loss -0.9215 +2025-10-30 16:01:38.024457: Pseudo dice [np.float32(0.9833), np.float32(0.9909), np.float32(0.996), np.float32(0.8568)] +2025-10-30 16:01:38.026577: Epoch time: 20.31 s +2025-10-30 16:01:39.370691: +2025-10-30 16:01:39.372459: Epoch 169 +2025-10-30 16:01:39.374488: Current learning rate: 0.00847 +2025-10-30 16:01:58.974467: train_loss -0.9826 +2025-10-30 16:01:58.982295: val_loss -0.9182 +2025-10-30 16:01:58.992187: Pseudo dice [np.float32(0.9829), np.float32(0.9901), np.float32(0.9956), np.float32(0.8533)] +2025-10-30 16:01:59.002851: Epoch time: 19.61 s +2025-10-30 16:02:00.210633: +2025-10-30 16:02:00.212806: Epoch 170 +2025-10-30 16:02:00.215178: Current learning rate: 0.00846 +2025-10-30 16:02:20.837636: train_loss -0.9844 +2025-10-30 16:02:20.839618: val_loss -0.9091 +2025-10-30 16:02:20.841005: Pseudo dice [np.float32(0.9846), np.float32(0.9911), np.float32(0.9953), np.float32(0.8205)] +2025-10-30 16:02:20.842459: Epoch time: 20.63 s +2025-10-30 16:02:21.878261: +2025-10-30 16:02:21.880240: Epoch 171 +2025-10-30 16:02:21.881963: Current learning rate: 0.00845 +2025-10-30 16:02:42.367047: train_loss -0.9828 +2025-10-30 16:02:42.369763: val_loss -0.9183 +2025-10-30 16:02:42.371311: Pseudo dice [np.float32(0.9844), np.float32(0.9917), np.float32(0.9954), np.float32(0.8421)] +2025-10-30 16:02:42.372889: Epoch time: 20.49 s +2025-10-30 16:02:43.569830: +2025-10-30 16:02:43.571697: Epoch 172 +2025-10-30 16:02:43.573429: Current learning rate: 0.00844 +2025-10-30 16:03:03.075180: train_loss -0.9853 +2025-10-30 16:03:03.077543: val_loss -0.9125 +2025-10-30 16:03:03.079235: Pseudo dice [np.float32(0.9835), np.float32(0.9916), np.float32(0.9956), np.float32(0.8367)] +2025-10-30 16:03:03.081072: Epoch time: 19.51 s +2025-10-30 16:03:04.175134: +2025-10-30 16:03:04.176986: Epoch 173 +2025-10-30 16:03:04.178600: Current learning rate: 0.00843 +2025-10-30 16:03:24.264618: train_loss -0.9837 +2025-10-30 16:03:24.266875: val_loss -0.9189 +2025-10-30 16:03:24.268480: Pseudo dice [np.float32(0.9833), np.float32(0.9909), np.float32(0.996), np.float32(0.8562)] +2025-10-30 16:03:24.270067: Epoch time: 20.09 s +2025-10-30 16:03:24.271581: Yayy! New best EMA pseudo Dice: 0.9517999887466431 +2025-10-30 16:03:26.307214: +2025-10-30 16:03:26.309507: Epoch 174 +2025-10-30 16:03:26.312553: Current learning rate: 0.00842 +2025-10-30 16:03:47.091768: train_loss -0.9837 +2025-10-30 16:03:47.095214: val_loss -0.9093 +2025-10-30 16:03:47.097974: Pseudo dice [np.float32(0.982), np.float32(0.9889), np.float32(0.9952), np.float32(0.8397)] +2025-10-30 16:03:47.100469: Epoch time: 20.79 s +2025-10-30 16:03:48.208129: +2025-10-30 16:03:48.210057: Epoch 175 +2025-10-30 16:03:48.211804: Current learning rate: 0.00841 +2025-10-30 16:04:08.704528: train_loss -0.9821 +2025-10-30 16:04:08.706874: val_loss -0.9114 +2025-10-30 16:04:08.708764: Pseudo dice [np.float32(0.9822), np.float32(0.9909), np.float32(0.9956), np.float32(0.8304)] +2025-10-30 16:04:08.710456: Epoch time: 20.5 s +2025-10-30 16:04:09.740036: +2025-10-30 16:04:09.741845: Epoch 176 +2025-10-30 16:04:09.743497: Current learning rate: 0.0084 +2025-10-30 16:04:30.540648: train_loss -0.9835 +2025-10-30 16:04:30.542801: val_loss -0.9106 +2025-10-30 16:04:30.545333: Pseudo dice [np.float32(0.9823), np.float32(0.9908), np.float32(0.9953), np.float32(0.8351)] +2025-10-30 16:04:30.547100: Epoch time: 20.8 s +2025-10-30 16:04:32.455768: +2025-10-30 16:04:32.458000: Epoch 177 +2025-10-30 16:04:32.460040: Current learning rate: 0.00839 +2025-10-30 16:04:52.852113: train_loss -0.9841 +2025-10-30 16:04:52.854831: val_loss -0.9044 +2025-10-30 16:04:52.856417: Pseudo dice [np.float32(0.9838), np.float32(0.9917), np.float32(0.9951), np.float32(0.8153)] +2025-10-30 16:04:52.857988: Epoch time: 20.4 s +2025-10-30 16:04:53.960092: +2025-10-30 16:04:53.962016: Epoch 178 +2025-10-30 16:04:53.963566: Current learning rate: 0.00838 +2025-10-30 16:05:13.186406: train_loss -0.9832 +2025-10-30 16:05:13.188711: val_loss -0.9169 +2025-10-30 16:05:13.190653: Pseudo dice [np.float32(0.9843), np.float32(0.9914), np.float32(0.9954), np.float32(0.8447)] +2025-10-30 16:05:13.192430: Epoch time: 19.23 s +2025-10-30 16:05:14.419083: +2025-10-30 16:05:14.421005: Epoch 179 +2025-10-30 16:05:14.424647: Current learning rate: 0.00837 +2025-10-30 16:05:33.886199: train_loss -0.9847 +2025-10-30 16:05:33.888778: val_loss -0.9079 +2025-10-30 16:05:33.890712: Pseudo dice [np.float32(0.9839), np.float32(0.9917), np.float32(0.9953), np.float32(0.8254)] +2025-10-30 16:05:33.892546: Epoch time: 19.47 s +2025-10-30 16:05:34.786358: +2025-10-30 16:05:34.788294: Epoch 180 +2025-10-30 16:05:34.789874: Current learning rate: 0.00836 +2025-10-30 16:05:55.341959: train_loss -0.9847 +2025-10-30 16:05:55.345173: val_loss -0.9057 +2025-10-30 16:05:55.346937: Pseudo dice [np.float32(0.9829), np.float32(0.9896), np.float32(0.9948), np.float32(0.8186)] +2025-10-30 16:05:55.348885: Epoch time: 20.56 s +2025-10-30 16:05:56.457531: +2025-10-30 16:05:56.460282: Epoch 181 +2025-10-30 16:05:56.463507: Current learning rate: 0.00836 +2025-10-30 16:06:17.283447: train_loss -0.9842 +2025-10-30 16:06:17.285752: val_loss -0.9041 +2025-10-30 16:06:17.287563: Pseudo dice [np.float32(0.9813), np.float32(0.9906), np.float32(0.9952), np.float32(0.8296)] +2025-10-30 16:06:17.289140: Epoch time: 20.83 s +2025-10-30 16:06:18.284991: +2025-10-30 16:06:18.286966: Epoch 182 +2025-10-30 16:06:18.288751: Current learning rate: 0.00835 +2025-10-30 16:06:39.249422: train_loss -0.9845 +2025-10-30 16:06:39.252190: val_loss -0.9158 +2025-10-30 16:06:39.253871: Pseudo dice [np.float32(0.9829), np.float32(0.9912), np.float32(0.9955), np.float32(0.8476)] +2025-10-30 16:06:39.255550: Epoch time: 20.97 s +2025-10-30 16:06:40.614476: +2025-10-30 16:06:40.616861: Epoch 183 +2025-10-30 16:06:40.618814: Current learning rate: 0.00834 +2025-10-30 16:07:01.138664: train_loss -0.9851 +2025-10-30 16:07:01.148405: val_loss -0.91 +2025-10-30 16:07:01.150181: Pseudo dice [np.float32(0.9825), np.float32(0.9913), np.float32(0.9954), np.float32(0.8381)] +2025-10-30 16:07:01.151708: Epoch time: 20.53 s +2025-10-30 16:07:02.192528: +2025-10-30 16:07:02.194607: Epoch 184 +2025-10-30 16:07:02.196114: Current learning rate: 0.00833 +2025-10-30 16:07:21.994614: train_loss -0.984 +2025-10-30 16:07:22.000058: val_loss -0.9079 +2025-10-30 16:07:22.001925: Pseudo dice [np.float32(0.9835), np.float32(0.9907), np.float32(0.9953), np.float32(0.8314)] +2025-10-30 16:07:22.003721: Epoch time: 19.8 s +2025-10-30 16:07:23.058806: +2025-10-30 16:07:23.060834: Epoch 185 +2025-10-30 16:07:23.062694: Current learning rate: 0.00832 +2025-10-30 16:07:43.407386: train_loss -0.985 +2025-10-30 16:07:43.409593: val_loss -0.9092 +2025-10-30 16:07:43.411127: Pseudo dice [np.float32(0.9835), np.float32(0.9908), np.float32(0.9953), np.float32(0.83)] +2025-10-30 16:07:43.412635: Epoch time: 20.35 s +2025-10-30 16:07:44.652390: +2025-10-30 16:07:44.654525: Epoch 186 +2025-10-30 16:07:44.656432: Current learning rate: 0.00831 +2025-10-30 16:08:04.236251: train_loss -0.9847 +2025-10-30 16:08:04.239094: val_loss -0.9011 +2025-10-30 16:08:04.240935: Pseudo dice [np.float32(0.9818), np.float32(0.9906), np.float32(0.9953), np.float32(0.8192)] +2025-10-30 16:08:04.242496: Epoch time: 19.59 s +2025-10-30 16:08:05.389751: +2025-10-30 16:08:05.391958: Epoch 187 +2025-10-30 16:08:05.397836: Current learning rate: 0.0083 +2025-10-30 16:08:25.924011: train_loss -0.9835 +2025-10-30 16:08:25.926409: val_loss -0.9096 +2025-10-30 16:08:25.928137: Pseudo dice [np.float32(0.9824), np.float32(0.9903), np.float32(0.9956), np.float32(0.8373)] +2025-10-30 16:08:25.930112: Epoch time: 20.54 s +2025-10-30 16:08:27.083662: +2025-10-30 16:08:27.085300: Epoch 188 +2025-10-30 16:08:27.086812: Current learning rate: 0.00829 +2025-10-30 16:08:47.910156: train_loss -0.9846 +2025-10-30 16:08:47.913021: val_loss -0.9136 +2025-10-30 16:08:47.915435: Pseudo dice [np.float32(0.9833), np.float32(0.9909), np.float32(0.9957), np.float32(0.8448)] +2025-10-30 16:08:47.917808: Epoch time: 20.83 s +2025-10-30 16:08:49.811733: +2025-10-30 16:08:49.813658: Epoch 189 +2025-10-30 16:08:49.815322: Current learning rate: 0.00828 +2025-10-30 16:09:10.208491: train_loss -0.9849 +2025-10-30 16:09:10.211378: val_loss -0.8978 +2025-10-30 16:09:10.213871: Pseudo dice [np.float32(0.9824), np.float32(0.9898), np.float32(0.9953), np.float32(0.8169)] +2025-10-30 16:09:10.215409: Epoch time: 20.4 s +2025-10-30 16:09:11.302653: +2025-10-30 16:09:11.304366: Epoch 190 +2025-10-30 16:09:11.306144: Current learning rate: 0.00827 +2025-10-30 16:09:31.857930: train_loss -0.9843 +2025-10-30 16:09:31.860137: val_loss -0.9116 +2025-10-30 16:09:31.861548: Pseudo dice [np.float32(0.9837), np.float32(0.9906), np.float32(0.9954), np.float32(0.8362)] +2025-10-30 16:09:31.863150: Epoch time: 20.56 s +2025-10-30 16:09:32.967667: +2025-10-30 16:09:32.969917: Epoch 191 +2025-10-30 16:09:32.971999: Current learning rate: 0.00826 +2025-10-30 16:09:52.894386: train_loss -0.9845 +2025-10-30 16:09:52.896379: val_loss -0.9116 +2025-10-30 16:09:52.898050: Pseudo dice [np.float32(0.9831), np.float32(0.99), np.float32(0.9957), np.float32(0.8459)] +2025-10-30 16:09:52.899724: Epoch time: 19.93 s +2025-10-30 16:09:54.138898: +2025-10-30 16:09:54.140613: Epoch 192 +2025-10-30 16:09:54.143078: Current learning rate: 0.00825 +2025-10-30 16:10:14.937516: train_loss -0.9837 +2025-10-30 16:10:14.941308: val_loss -0.9043 +2025-10-30 16:10:14.943424: Pseudo dice [np.float32(0.981), np.float32(0.9905), np.float32(0.9954), np.float32(0.8304)] +2025-10-30 16:10:14.945183: Epoch time: 20.8 s +2025-10-30 16:10:16.197902: +2025-10-30 16:10:16.199780: Epoch 193 +2025-10-30 16:10:16.201628: Current learning rate: 0.00824 +2025-10-30 16:10:35.897537: train_loss -0.9849 +2025-10-30 16:10:35.899574: val_loss -0.9026 +2025-10-30 16:10:35.901782: Pseudo dice [np.float32(0.9837), np.float32(0.9912), np.float32(0.9952), np.float32(0.8149)] +2025-10-30 16:10:35.903950: Epoch time: 19.7 s +2025-10-30 16:10:36.972778: +2025-10-30 16:10:36.974403: Epoch 194 +2025-10-30 16:10:36.976487: Current learning rate: 0.00824 +2025-10-30 16:10:57.506716: train_loss -0.9846 +2025-10-30 16:10:57.509932: val_loss -0.9062 +2025-10-30 16:10:57.511837: Pseudo dice [np.float32(0.9833), np.float32(0.9906), np.float32(0.995), np.float32(0.8334)] +2025-10-30 16:10:57.513688: Epoch time: 20.54 s +2025-10-30 16:10:58.522294: +2025-10-30 16:10:58.524138: Epoch 195 +2025-10-30 16:10:58.525784: Current learning rate: 0.00823 +2025-10-30 16:11:18.749502: train_loss -0.986 +2025-10-30 16:11:18.753572: val_loss -0.8996 +2025-10-30 16:11:18.755890: Pseudo dice [np.float32(0.9829), np.float32(0.9904), np.float32(0.994), np.float32(0.8175)] +2025-10-30 16:11:18.758062: Epoch time: 20.23 s +2025-10-30 16:11:19.770650: +2025-10-30 16:11:19.772651: Epoch 196 +2025-10-30 16:11:19.774529: Current learning rate: 0.00822 +2025-10-30 16:11:40.353351: train_loss -0.9845 +2025-10-30 16:11:40.355506: val_loss -0.9079 +2025-10-30 16:11:40.357096: Pseudo dice [np.float32(0.9832), np.float32(0.9914), np.float32(0.9951), np.float32(0.8293)] +2025-10-30 16:11:40.358675: Epoch time: 20.58 s +2025-10-30 16:11:41.529207: +2025-10-30 16:11:41.531057: Epoch 197 +2025-10-30 16:11:41.532753: Current learning rate: 0.00821 +2025-10-30 16:12:00.630969: train_loss -0.9862 +2025-10-30 16:12:00.635744: val_loss -0.894 +2025-10-30 16:12:00.639461: Pseudo dice [np.float32(0.9835), np.float32(0.9908), np.float32(0.9934), np.float32(0.8019)] +2025-10-30 16:12:00.641209: Epoch time: 19.1 s +2025-10-30 16:12:01.663788: +2025-10-30 16:12:01.666395: Epoch 198 +2025-10-30 16:12:01.668407: Current learning rate: 0.0082 +2025-10-30 16:12:22.296632: train_loss -0.9842 +2025-10-30 16:12:22.299744: val_loss -0.9069 +2025-10-30 16:12:22.301681: Pseudo dice [np.float32(0.9823), np.float32(0.9899), np.float32(0.995), np.float32(0.8349)] +2025-10-30 16:12:22.303658: Epoch time: 20.63 s +2025-10-30 16:12:23.505213: +2025-10-30 16:12:23.507276: Epoch 199 +2025-10-30 16:12:23.509067: Current learning rate: 0.00819 +2025-10-30 16:12:44.302282: train_loss -0.9852 +2025-10-30 16:12:44.305225: val_loss -0.9142 +2025-10-30 16:12:44.306983: Pseudo dice [np.float32(0.9849), np.float32(0.9916), np.float32(0.9953), np.float32(0.843)] +2025-10-30 16:12:44.308913: Epoch time: 20.8 s +2025-10-30 16:12:47.311335: +2025-10-30 16:12:47.326420: Epoch 200 +2025-10-30 16:12:47.339166: Current learning rate: 0.00818 +2025-10-30 16:13:06.292095: train_loss -0.9856 +2025-10-30 16:13:06.294617: val_loss -0.9094 +2025-10-30 16:13:06.295997: Pseudo dice [np.float32(0.9817), np.float32(0.9904), np.float32(0.9956), np.float32(0.8385)] +2025-10-30 16:13:06.297239: Epoch time: 18.98 s +2025-10-30 16:13:07.345137: +2025-10-30 16:13:07.346961: Epoch 201 +2025-10-30 16:13:07.348465: Current learning rate: 0.00817 +2025-10-30 16:13:27.801784: train_loss -0.9832 +2025-10-30 16:13:27.804857: val_loss -0.9169 +2025-10-30 16:13:27.806651: Pseudo dice [np.float32(0.9836), np.float32(0.9906), np.float32(0.9957), np.float32(0.8508)] +2025-10-30 16:13:27.808305: Epoch time: 20.46 s +2025-10-30 16:13:28.814660: +2025-10-30 16:13:28.816485: Epoch 202 +2025-10-30 16:13:28.818220: Current learning rate: 0.00816 +2025-10-30 16:13:49.491615: train_loss -0.9846 +2025-10-30 16:13:49.494356: val_loss -0.9069 +2025-10-30 16:13:49.496045: Pseudo dice [np.float32(0.9832), np.float32(0.9905), np.float32(0.9953), np.float32(0.8334)] +2025-10-30 16:13:49.497712: Epoch time: 20.68 s +2025-10-30 16:13:50.762485: +2025-10-30 16:13:50.764238: Epoch 203 +2025-10-30 16:13:50.765904: Current learning rate: 0.00815 +2025-10-30 16:14:09.816401: train_loss -0.9856 +2025-10-30 16:14:09.818530: val_loss -0.9113 +2025-10-30 16:14:09.820091: Pseudo dice [np.float32(0.9824), np.float32(0.9907), np.float32(0.9956), np.float32(0.84)] +2025-10-30 16:14:09.821952: Epoch time: 19.06 s +2025-10-30 16:14:11.054857: +2025-10-30 16:14:11.056639: Epoch 204 +2025-10-30 16:14:11.058366: Current learning rate: 0.00814 +2025-10-30 16:14:31.729363: train_loss -0.9837 +2025-10-30 16:14:31.732620: val_loss -0.912 +2025-10-30 16:14:31.734229: Pseudo dice [np.float32(0.9835), np.float32(0.9906), np.float32(0.9955), np.float32(0.8418)] +2025-10-30 16:14:31.735837: Epoch time: 20.68 s +2025-10-30 16:14:32.796190: +2025-10-30 16:14:32.797956: Epoch 205 +2025-10-30 16:14:32.800356: Current learning rate: 0.00813 +2025-10-30 16:14:53.434818: train_loss -0.9859 +2025-10-30 16:14:53.437075: val_loss -0.9 +2025-10-30 16:14:53.438928: Pseudo dice [np.float32(0.983), np.float32(0.9905), np.float32(0.9952), np.float32(0.8218)] +2025-10-30 16:14:53.441219: Epoch time: 20.64 s +2025-10-30 16:14:54.402883: +2025-10-30 16:14:54.404627: Epoch 206 +2025-10-30 16:14:54.406880: Current learning rate: 0.00813 +2025-10-30 16:15:15.037814: train_loss -0.9847 +2025-10-30 16:15:15.039801: val_loss -0.909 +2025-10-30 16:15:15.041293: Pseudo dice [np.float32(0.9841), np.float32(0.9915), np.float32(0.9953), np.float32(0.8297)] +2025-10-30 16:15:15.042848: Epoch time: 20.64 s +2025-10-30 16:15:16.078562: +2025-10-30 16:15:16.095352: Epoch 207 +2025-10-30 16:15:16.112531: Current learning rate: 0.00812 +2025-10-30 16:15:35.521455: train_loss -0.9861 +2025-10-30 16:15:35.524677: val_loss -0.9041 +2025-10-30 16:15:35.526418: Pseudo dice [np.float32(0.9826), np.float32(0.9905), np.float32(0.9952), np.float32(0.8294)] +2025-10-30 16:15:35.528041: Epoch time: 19.44 s +2025-10-30 16:15:36.673936: +2025-10-30 16:15:36.676043: Epoch 208 +2025-10-30 16:15:36.678126: Current learning rate: 0.00811 +2025-10-30 16:15:57.328600: train_loss -0.9847 +2025-10-30 16:15:57.330567: val_loss -0.9037 +2025-10-30 16:15:57.332241: Pseudo dice [np.float32(0.9838), np.float32(0.9912), np.float32(0.9952), np.float32(0.8181)] +2025-10-30 16:15:57.334249: Epoch time: 20.66 s +2025-10-30 16:15:58.513631: +2025-10-30 16:15:58.515449: Epoch 209 +2025-10-30 16:15:58.517077: Current learning rate: 0.0081 +2025-10-30 16:16:19.205316: train_loss -0.9871 +2025-10-30 16:16:19.207759: val_loss -0.8965 +2025-10-30 16:16:19.209597: Pseudo dice [np.float32(0.9821), np.float32(0.9907), np.float32(0.9951), np.float32(0.8102)] +2025-10-30 16:16:19.211323: Epoch time: 20.69 s +2025-10-30 16:16:20.415710: +2025-10-30 16:16:20.418946: Epoch 210 +2025-10-30 16:16:20.420928: Current learning rate: 0.00809 +2025-10-30 16:16:40.259541: train_loss -0.9854 +2025-10-30 16:16:40.262498: val_loss -0.8985 +2025-10-30 16:16:40.264210: Pseudo dice [np.float32(0.9825), np.float32(0.9906), np.float32(0.9944), np.float32(0.8221)] +2025-10-30 16:16:40.265823: Epoch time: 19.85 s +2025-10-30 16:16:41.244056: +2025-10-30 16:16:41.246993: Epoch 211 +2025-10-30 16:16:41.249312: Current learning rate: 0.00808 +2025-10-30 16:17:02.257637: train_loss -0.986 +2025-10-30 16:17:02.259597: val_loss -0.9122 +2025-10-30 16:17:02.261173: Pseudo dice [np.float32(0.9837), np.float32(0.9911), np.float32(0.9958), np.float32(0.8469)] +2025-10-30 16:17:02.262506: Epoch time: 21.02 s +2025-10-30 16:17:03.788355: +2025-10-30 16:17:03.790522: Epoch 212 +2025-10-30 16:17:03.792291: Current learning rate: 0.00807 +2025-10-30 16:17:24.898790: train_loss -0.986 +2025-10-30 16:17:24.900983: val_loss -0.8996 +2025-10-30 16:17:24.902861: Pseudo dice [np.float32(0.9833), np.float32(0.9912), np.float32(0.9934), np.float32(0.8182)] +2025-10-30 16:17:24.904368: Epoch time: 21.11 s +2025-10-30 16:17:26.056747: +2025-10-30 16:17:26.058850: Epoch 213 +2025-10-30 16:17:26.060790: Current learning rate: 0.00806 +2025-10-30 16:17:45.579611: train_loss -0.9865 +2025-10-30 16:17:45.582199: val_loss -0.891 +2025-10-30 16:17:45.584048: Pseudo dice [np.float32(0.9823), np.float32(0.9899), np.float32(0.9928), np.float32(0.8042)] +2025-10-30 16:17:45.585722: Epoch time: 19.52 s +2025-10-30 16:17:46.669690: +2025-10-30 16:17:46.671544: Epoch 214 +2025-10-30 16:17:46.673121: Current learning rate: 0.00805 +2025-10-30 16:18:07.139605: train_loss -0.9851 +2025-10-30 16:18:07.141797: val_loss -0.9093 +2025-10-30 16:18:07.143288: Pseudo dice [np.float32(0.982), np.float32(0.9908), np.float32(0.9954), np.float32(0.8421)] +2025-10-30 16:18:07.144998: Epoch time: 20.47 s +2025-10-30 16:18:08.161228: +2025-10-30 16:18:08.163050: Epoch 215 +2025-10-30 16:18:08.164707: Current learning rate: 0.00804 +2025-10-30 16:18:28.392601: train_loss -0.9854 +2025-10-30 16:18:28.394643: val_loss -0.907 +2025-10-30 16:18:28.396007: Pseudo dice [np.float32(0.9819), np.float32(0.9902), np.float32(0.9951), np.float32(0.8386)] +2025-10-30 16:18:28.397349: Epoch time: 20.23 s +2025-10-30 16:18:29.567697: +2025-10-30 16:18:29.569539: Epoch 216 +2025-10-30 16:18:29.571196: Current learning rate: 0.00803 +2025-10-30 16:18:49.017308: train_loss -0.9853 +2025-10-30 16:18:49.020119: val_loss -0.9129 +2025-10-30 16:18:49.021821: Pseudo dice [np.float32(0.9832), np.float32(0.991), np.float32(0.9954), np.float32(0.8451)] +2025-10-30 16:18:49.023668: Epoch time: 19.45 s +2025-10-30 16:18:50.070916: +2025-10-30 16:18:50.073010: Epoch 217 +2025-10-30 16:18:50.074604: Current learning rate: 0.00802 +2025-10-30 16:19:10.550942: train_loss -0.9845 +2025-10-30 16:19:10.553043: val_loss -0.9025 +2025-10-30 16:19:10.554561: Pseudo dice [np.float32(0.9807), np.float32(0.99), np.float32(0.9952), np.float32(0.8269)] +2025-10-30 16:19:10.556076: Epoch time: 20.48 s +2025-10-30 16:19:11.556539: +2025-10-30 16:19:11.558194: Epoch 218 +2025-10-30 16:19:11.559694: Current learning rate: 0.00801 +2025-10-30 16:19:32.313413: train_loss -0.9849 +2025-10-30 16:19:32.316399: val_loss -0.9047 +2025-10-30 16:19:32.318426: Pseudo dice [np.float32(0.983), np.float32(0.9905), np.float32(0.9949), np.float32(0.8216)] +2025-10-30 16:19:32.320286: Epoch time: 20.76 s +2025-10-30 16:19:33.536932: +2025-10-30 16:19:33.538694: Epoch 219 +2025-10-30 16:19:33.540333: Current learning rate: 0.00801 +2025-10-30 16:19:54.239387: train_loss -0.985 +2025-10-30 16:19:54.242280: val_loss -0.9036 +2025-10-30 16:19:54.244087: Pseudo dice [np.float32(0.9829), np.float32(0.9898), np.float32(0.9954), np.float32(0.8224)] +2025-10-30 16:19:54.245696: Epoch time: 20.7 s +2025-10-30 16:19:55.327716: +2025-10-30 16:19:55.329575: Epoch 220 +2025-10-30 16:19:55.331426: Current learning rate: 0.008 +2025-10-30 16:20:14.736097: train_loss -0.9852 +2025-10-30 16:20:14.738209: val_loss -0.9091 +2025-10-30 16:20:14.740241: Pseudo dice [np.float32(0.9834), np.float32(0.9908), np.float32(0.9957), np.float32(0.8396)] +2025-10-30 16:20:14.743252: Epoch time: 19.41 s +2025-10-30 16:20:15.932880: +2025-10-30 16:20:15.935040: Epoch 221 +2025-10-30 16:20:15.936872: Current learning rate: 0.00799 +2025-10-30 16:20:36.552636: train_loss -0.9859 +2025-10-30 16:20:36.554968: val_loss -0.9013 +2025-10-30 16:20:36.556484: Pseudo dice [np.float32(0.9834), np.float32(0.9911), np.float32(0.995), np.float32(0.8263)] +2025-10-30 16:20:36.558023: Epoch time: 20.62 s +2025-10-30 16:20:37.686367: +2025-10-30 16:20:37.688364: Epoch 222 +2025-10-30 16:20:37.689972: Current learning rate: 0.00798 +2025-10-30 16:20:58.472325: train_loss -0.9858 +2025-10-30 16:20:58.475412: val_loss -0.8995 +2025-10-30 16:20:58.477026: Pseudo dice [np.float32(0.9836), np.float32(0.9911), np.float32(0.995), np.float32(0.8112)] +2025-10-30 16:20:58.485039: Epoch time: 20.79 s +2025-10-30 16:20:59.555909: +2025-10-30 16:20:59.557619: Epoch 223 +2025-10-30 16:20:59.559076: Current learning rate: 0.00797 +2025-10-30 16:21:19.446487: train_loss -0.9845 +2025-10-30 16:21:19.448569: val_loss -0.9009 +2025-10-30 16:21:19.450253: Pseudo dice [np.float32(0.9811), np.float32(0.99), np.float32(0.9951), np.float32(0.8247)] +2025-10-30 16:21:19.451938: Epoch time: 19.89 s +2025-10-30 16:21:20.460658: +2025-10-30 16:21:20.462431: Epoch 224 +2025-10-30 16:21:20.464052: Current learning rate: 0.00796 +2025-10-30 16:21:40.991748: train_loss -0.9862 +2025-10-30 16:21:40.994493: val_loss -0.9015 +2025-10-30 16:21:40.996214: Pseudo dice [np.float32(0.9824), np.float32(0.991), np.float32(0.9954), np.float32(0.826)] +2025-10-30 16:21:40.998104: Epoch time: 20.53 s +2025-10-30 16:21:42.319690: +2025-10-30 16:21:42.321835: Epoch 225 +2025-10-30 16:21:42.323678: Current learning rate: 0.00795 +2025-10-30 16:22:02.920244: train_loss -0.9864 +2025-10-30 16:22:02.923338: val_loss -0.9052 +2025-10-30 16:22:02.924987: Pseudo dice [np.float32(0.9841), np.float32(0.991), np.float32(0.9953), np.float32(0.8213)] +2025-10-30 16:22:02.927075: Epoch time: 20.6 s +2025-10-30 16:22:03.960507: +2025-10-30 16:22:03.962300: Epoch 226 +2025-10-30 16:22:03.964413: Current learning rate: 0.00794 +2025-10-30 16:22:24.424781: train_loss -0.9858 +2025-10-30 16:22:24.426553: val_loss -0.9059 +2025-10-30 16:22:24.428210: Pseudo dice [np.float32(0.9829), np.float32(0.9907), np.float32(0.9954), np.float32(0.8321)] +2025-10-30 16:22:24.429549: Epoch time: 20.47 s +2025-10-30 16:22:25.594458: +2025-10-30 16:22:25.596257: Epoch 227 +2025-10-30 16:22:25.597841: Current learning rate: 0.00793 +2025-10-30 16:22:45.267856: train_loss -0.9853 +2025-10-30 16:22:45.270151: val_loss -0.8971 +2025-10-30 16:22:45.271819: Pseudo dice [np.float32(0.9829), np.float32(0.9903), np.float32(0.9948), np.float32(0.8153)] +2025-10-30 16:22:45.273550: Epoch time: 19.67 s +2025-10-30 16:22:46.260826: +2025-10-30 16:22:46.262905: Epoch 228 +2025-10-30 16:22:46.264961: Current learning rate: 0.00792 +2025-10-30 16:23:06.954552: train_loss -0.9844 +2025-10-30 16:23:06.957131: val_loss -0.901 +2025-10-30 16:23:06.958661: Pseudo dice [np.float32(0.9821), np.float32(0.9907), np.float32(0.9952), np.float32(0.8221)] +2025-10-30 16:23:06.960223: Epoch time: 20.7 s +2025-10-30 16:23:08.091199: +2025-10-30 16:23:08.094056: Epoch 229 +2025-10-30 16:23:08.095929: Current learning rate: 0.00791 +2025-10-30 16:23:27.688225: train_loss -0.9843 +2025-10-30 16:23:27.690842: val_loss -0.9082 +2025-10-30 16:23:27.692689: Pseudo dice [np.float32(0.9835), np.float32(0.991), np.float32(0.9956), np.float32(0.8323)] +2025-10-30 16:23:27.694439: Epoch time: 19.6 s +2025-10-30 16:23:28.780278: +2025-10-30 16:23:28.782392: Epoch 230 +2025-10-30 16:23:28.784603: Current learning rate: 0.0079 +2025-10-30 16:23:49.670795: train_loss -0.9849 +2025-10-30 16:23:49.673356: val_loss -0.9146 +2025-10-30 16:23:49.675379: Pseudo dice [np.float32(0.9831), np.float32(0.9914), np.float32(0.9959), np.float32(0.8504)] +2025-10-30 16:23:49.677160: Epoch time: 20.89 s +2025-10-30 16:23:50.956154: +2025-10-30 16:23:50.958478: Epoch 231 +2025-10-30 16:23:50.960373: Current learning rate: 0.00789 +2025-10-30 16:24:11.656317: train_loss -0.9851 +2025-10-30 16:24:11.659209: val_loss -0.9091 +2025-10-30 16:24:11.660657: Pseudo dice [np.float32(0.9835), np.float32(0.9918), np.float32(0.9954), np.float32(0.835)] +2025-10-30 16:24:11.662191: Epoch time: 20.7 s +2025-10-30 16:24:12.713972: +2025-10-30 16:24:12.716120: Epoch 232 +2025-10-30 16:24:12.718257: Current learning rate: 0.00789 +2025-10-30 16:24:33.293971: train_loss -0.9875 +2025-10-30 16:24:33.296243: val_loss -0.9024 +2025-10-30 16:24:33.297830: Pseudo dice [np.float32(0.984), np.float32(0.9907), np.float32(0.9954), np.float32(0.824)] +2025-10-30 16:24:33.299639: Epoch time: 20.58 s +2025-10-30 16:24:34.461951: +2025-10-30 16:24:34.463664: Epoch 233 +2025-10-30 16:24:34.465319: Current learning rate: 0.00788 +2025-10-30 16:24:54.879681: train_loss -0.9855 +2025-10-30 16:24:54.881819: val_loss -0.9075 +2025-10-30 16:24:54.883664: Pseudo dice [np.float32(0.9841), np.float32(0.9916), np.float32(0.9953), np.float32(0.831)] +2025-10-30 16:24:54.885232: Epoch time: 20.42 s +2025-10-30 16:24:55.853957: +2025-10-30 16:24:55.855844: Epoch 234 +2025-10-30 16:24:55.857601: Current learning rate: 0.00787 +2025-10-30 16:25:15.603275: train_loss -0.9851 +2025-10-30 16:25:15.605962: val_loss -0.9007 +2025-10-30 16:25:15.607471: Pseudo dice [np.float32(0.981), np.float32(0.9899), np.float32(0.9952), np.float32(0.8265)] +2025-10-30 16:25:15.609369: Epoch time: 19.75 s +2025-10-30 16:25:16.631651: +2025-10-30 16:25:16.633602: Epoch 235 +2025-10-30 16:25:16.635373: Current learning rate: 0.00786 +2025-10-30 16:25:36.133235: train_loss -0.9867 +2025-10-30 16:25:36.135319: val_loss -0.9075 +2025-10-30 16:25:36.136766: Pseudo dice [np.float32(0.9836), np.float32(0.9908), np.float32(0.9954), np.float32(0.8358)] +2025-10-30 16:25:36.138228: Epoch time: 19.5 s +2025-10-30 16:25:37.103960: +2025-10-30 16:25:37.105843: Epoch 236 +2025-10-30 16:25:37.107465: Current learning rate: 0.00785 +2025-10-30 16:25:58.110904: train_loss -0.9869 +2025-10-30 16:25:58.113288: val_loss -0.9049 +2025-10-30 16:25:58.115219: Pseudo dice [np.float32(0.9836), np.float32(0.9908), np.float32(0.9951), np.float32(0.8283)] +2025-10-30 16:25:58.117152: Epoch time: 21.01 s +2025-10-30 16:25:59.380610: +2025-10-30 16:25:59.382487: Epoch 237 +2025-10-30 16:25:59.384162: Current learning rate: 0.00784 +2025-10-30 16:26:19.755937: train_loss -0.9863 +2025-10-30 16:26:19.758923: val_loss -0.907 +2025-10-30 16:26:19.760760: Pseudo dice [np.float32(0.982), np.float32(0.9909), np.float32(0.9958), np.float32(0.8334)] +2025-10-30 16:26:19.762927: Epoch time: 20.38 s +2025-10-30 16:26:21.212192: +2025-10-30 16:26:21.214081: Epoch 238 +2025-10-30 16:26:21.215884: Current learning rate: 0.00783 +2025-10-30 16:26:41.747970: train_loss -0.9831 +2025-10-30 16:26:41.753633: val_loss -0.9051 +2025-10-30 16:26:41.755466: Pseudo dice [np.float32(0.9836), np.float32(0.9905), np.float32(0.9951), np.float32(0.8255)] +2025-10-30 16:26:41.757114: Epoch time: 20.54 s +2025-10-30 16:26:42.936671: +2025-10-30 16:26:42.938486: Epoch 239 +2025-10-30 16:26:42.940102: Current learning rate: 0.00782 +2025-10-30 16:27:03.363864: train_loss -0.9802 +2025-10-30 16:27:03.366339: val_loss -0.9015 +2025-10-30 16:27:03.368044: Pseudo dice [np.float32(0.9827), np.float32(0.99), np.float32(0.9902), np.float32(0.8311)] +2025-10-30 16:27:03.369669: Epoch time: 20.43 s +2025-10-30 16:27:04.351596: +2025-10-30 16:27:04.353598: Epoch 240 +2025-10-30 16:27:04.355467: Current learning rate: 0.00781 +2025-10-30 16:27:24.472111: train_loss -0.9729 +2025-10-30 16:27:24.475068: val_loss -0.8042 +2025-10-30 16:27:24.476807: Pseudo dice [np.float32(0.9842), np.float32(0.9455), np.float32(0.977), np.float32(0.8182)] +2025-10-30 16:27:24.478477: Epoch time: 20.12 s +2025-10-30 16:27:25.687711: +2025-10-30 16:27:25.689750: Epoch 241 +2025-10-30 16:27:25.691658: Current learning rate: 0.0078 +2025-10-30 16:27:45.945377: train_loss -0.9489 +2025-10-30 16:27:45.947558: val_loss -0.9138 +2025-10-30 16:27:45.949180: Pseudo dice [np.float32(0.9828), np.float32(0.9902), np.float32(0.9935), np.float32(0.821)] +2025-10-30 16:27:45.951107: Epoch time: 20.26 s +2025-10-30 16:27:47.010097: +2025-10-30 16:27:47.012500: Epoch 242 +2025-10-30 16:27:47.014393: Current learning rate: 0.00779 +2025-10-30 16:28:06.792522: train_loss -0.8872 +2025-10-30 16:28:06.794868: val_loss -0.9016 +2025-10-30 16:28:06.796497: Pseudo dice [np.float32(0.9808), np.float32(0.9832), np.float32(0.9922), np.float32(0.8056)] +2025-10-30 16:28:06.798221: Epoch time: 19.78 s +2025-10-30 16:28:07.786329: +2025-10-30 16:28:07.788554: Epoch 243 +2025-10-30 16:28:07.790467: Current learning rate: 0.00778 +2025-10-30 16:28:28.384421: train_loss -0.9193 +2025-10-30 16:28:28.390435: val_loss -0.9114 +2025-10-30 16:28:28.392294: Pseudo dice [np.float32(0.9833), np.float32(0.9895), np.float32(0.9944), np.float32(0.7953)] +2025-10-30 16:28:28.394241: Epoch time: 20.6 s +2025-10-30 16:28:29.640336: +2025-10-30 16:28:29.642334: Epoch 244 +2025-10-30 16:28:29.644574: Current learning rate: 0.00777 +2025-10-30 16:28:50.240715: train_loss -0.9375 +2025-10-30 16:28:50.243696: val_loss -0.9224 +2025-10-30 16:28:50.245427: Pseudo dice [np.float32(0.9854), np.float32(0.9902), np.float32(0.9943), np.float32(0.8264)] +2025-10-30 16:28:50.247084: Epoch time: 20.6 s +2025-10-30 16:28:51.297188: +2025-10-30 16:28:51.299482: Epoch 245 +2025-10-30 16:28:51.301459: Current learning rate: 0.00777 +2025-10-30 16:29:11.989156: train_loss -0.9505 +2025-10-30 16:29:11.991594: val_loss -0.9239 +2025-10-30 16:29:11.993363: Pseudo dice [np.float32(0.984), np.float32(0.9914), np.float32(0.9954), np.float32(0.8312)] +2025-10-30 16:29:11.995102: Epoch time: 20.69 s +2025-10-30 16:29:12.999688: +2025-10-30 16:29:13.002186: Epoch 246 +2025-10-30 16:29:13.004658: Current learning rate: 0.00776 +2025-10-30 16:29:33.403583: train_loss -0.9574 +2025-10-30 16:29:33.406504: val_loss -0.9259 +2025-10-30 16:29:33.408312: Pseudo dice [np.float32(0.9832), np.float32(0.99), np.float32(0.9954), np.float32(0.8468)] +2025-10-30 16:29:33.409930: Epoch time: 20.41 s +2025-10-30 16:29:34.457592: +2025-10-30 16:29:34.459521: Epoch 247 +2025-10-30 16:29:34.461220: Current learning rate: 0.00775 +2025-10-30 16:29:53.672058: train_loss -0.9633 +2025-10-30 16:29:53.674749: val_loss -0.9164 +2025-10-30 16:29:53.676585: Pseudo dice [np.float32(0.9846), np.float32(0.9906), np.float32(0.9946), np.float32(0.8169)] +2025-10-30 16:29:53.678504: Epoch time: 19.22 s +2025-10-30 16:29:54.858595: +2025-10-30 16:29:54.860761: Epoch 248 +2025-10-30 16:29:54.862347: Current learning rate: 0.00774 +2025-10-30 16:30:14.608057: train_loss -0.9672 +2025-10-30 16:30:14.610428: val_loss -0.9208 +2025-10-30 16:30:14.612354: Pseudo dice [np.float32(0.9805), np.float32(0.9901), np.float32(0.9955), np.float32(0.8414)] +2025-10-30 16:30:14.614280: Epoch time: 19.75 s +2025-10-30 16:30:15.656356: +2025-10-30 16:30:15.658387: Epoch 249 +2025-10-30 16:30:15.660199: Current learning rate: 0.00773 +2025-10-30 16:30:36.192748: train_loss -0.971 +2025-10-30 16:30:36.196114: val_loss -0.9218 +2025-10-30 16:30:36.198239: Pseudo dice [np.float32(0.9853), np.float32(0.9912), np.float32(0.9953), np.float32(0.8327)] +2025-10-30 16:30:36.199986: Epoch time: 20.54 s +2025-10-30 16:30:38.656400: +2025-10-30 16:30:38.658384: Epoch 250 +2025-10-30 16:30:38.660202: Current learning rate: 0.00772 +2025-10-30 16:30:59.142879: train_loss -0.9728 +2025-10-30 16:30:59.145216: val_loss -0.9178 +2025-10-30 16:30:59.146835: Pseudo dice [np.float32(0.9837), np.float32(0.9911), np.float32(0.9952), np.float32(0.8276)] +2025-10-30 16:30:59.148334: Epoch time: 20.49 s +2025-10-30 16:31:00.213562: +2025-10-30 16:31:00.215461: Epoch 251 +2025-10-30 16:31:00.217148: Current learning rate: 0.00771 +2025-10-30 16:31:20.787924: train_loss -0.9766 +2025-10-30 16:31:20.790151: val_loss -0.919 +2025-10-30 16:31:20.791848: Pseudo dice [np.float32(0.9822), np.float32(0.9897), np.float32(0.9954), np.float32(0.8394)] +2025-10-30 16:31:20.793956: Epoch time: 20.58 s +2025-10-30 16:31:21.777501: +2025-10-30 16:31:21.779487: Epoch 252 +2025-10-30 16:31:21.782062: Current learning rate: 0.0077 +2025-10-30 16:31:42.056946: train_loss -0.9777 +2025-10-30 16:31:42.059854: val_loss -0.9186 +2025-10-30 16:31:42.061611: Pseudo dice [np.float32(0.9841), np.float32(0.9908), np.float32(0.9954), np.float32(0.8411)] +2025-10-30 16:31:42.063463: Epoch time: 20.28 s +2025-10-30 16:31:43.053167: +2025-10-30 16:31:43.055510: Epoch 253 +2025-10-30 16:31:43.057285: Current learning rate: 0.00769 +2025-10-30 16:32:03.759152: train_loss -0.9778 +2025-10-30 16:32:03.761445: val_loss -0.9124 +2025-10-30 16:32:03.763017: Pseudo dice [np.float32(0.9834), np.float32(0.9909), np.float32(0.9952), np.float32(0.818)] +2025-10-30 16:32:03.764541: Epoch time: 20.71 s +2025-10-30 16:32:04.837800: +2025-10-30 16:32:04.839686: Epoch 254 +2025-10-30 16:32:04.841463: Current learning rate: 0.00768 +2025-10-30 16:32:22.773051: train_loss -0.9784 +2025-10-30 16:32:22.775505: val_loss -0.9141 +2025-10-30 16:32:22.777508: Pseudo dice [np.float32(0.9839), np.float32(0.9909), np.float32(0.9952), np.float32(0.8251)] +2025-10-30 16:32:22.779375: Epoch time: 17.94 s +2025-10-30 16:32:24.071933: +2025-10-30 16:32:24.079792: Epoch 255 +2025-10-30 16:32:24.087225: Current learning rate: 0.00767 +2025-10-30 16:32:43.637759: train_loss -0.9785 +2025-10-30 16:32:43.640824: val_loss -0.9088 +2025-10-30 16:32:43.642616: Pseudo dice [np.float32(0.9833), np.float32(0.99), np.float32(0.9949), np.float32(0.8162)] +2025-10-30 16:32:43.644202: Epoch time: 19.57 s +2025-10-30 16:32:44.767794: +2025-10-30 16:32:44.770034: Epoch 256 +2025-10-30 16:32:44.771768: Current learning rate: 0.00766 +2025-10-30 16:33:04.928888: train_loss -0.9775 +2025-10-30 16:33:04.930740: val_loss -0.9131 +2025-10-30 16:33:04.931990: Pseudo dice [np.float32(0.9839), np.float32(0.9906), np.float32(0.9944), np.float32(0.8234)] +2025-10-30 16:33:04.933338: Epoch time: 20.16 s +2025-10-30 16:33:05.943567: +2025-10-30 16:33:05.945140: Epoch 257 +2025-10-30 16:33:05.946384: Current learning rate: 0.00765 +2025-10-30 16:33:26.105690: train_loss -0.9794 +2025-10-30 16:33:26.107675: val_loss -0.9159 +2025-10-30 16:33:26.109682: Pseudo dice [np.float32(0.9824), np.float32(0.991), np.float32(0.9957), np.float32(0.8406)] +2025-10-30 16:33:26.111514: Epoch time: 20.16 s +2025-10-30 16:33:27.127270: +2025-10-30 16:33:27.129167: Epoch 258 +2025-10-30 16:33:27.130907: Current learning rate: 0.00764 +2025-10-30 16:33:47.416041: train_loss -0.9729 +2025-10-30 16:33:47.425433: val_loss -0.917 +2025-10-30 16:33:47.429196: Pseudo dice [np.float32(0.9813), np.float32(0.9899), np.float32(0.9953), np.float32(0.8409)] +2025-10-30 16:33:47.432565: Epoch time: 20.29 s +2025-10-30 16:33:48.428138: +2025-10-30 16:33:48.430629: Epoch 259 +2025-10-30 16:33:48.432411: Current learning rate: 0.00764 +2025-10-30 16:34:09.100220: train_loss -0.9788 +2025-10-30 16:34:09.102566: val_loss -0.9088 +2025-10-30 16:34:09.104194: Pseudo dice [np.float32(0.9829), np.float32(0.9903), np.float32(0.995), np.float32(0.8201)] +2025-10-30 16:34:09.105800: Epoch time: 20.67 s +2025-10-30 16:34:10.344841: +2025-10-30 16:34:10.346991: Epoch 260 +2025-10-30 16:34:10.348765: Current learning rate: 0.00763 +2025-10-30 16:34:30.467578: train_loss -0.9822 +2025-10-30 16:34:30.469418: val_loss -0.908 +2025-10-30 16:34:30.471099: Pseudo dice [np.float32(0.9835), np.float32(0.9905), np.float32(0.9947), np.float32(0.8249)] +2025-10-30 16:34:30.472661: Epoch time: 20.12 s +2025-10-30 16:34:31.696411: +2025-10-30 16:34:31.698239: Epoch 261 +2025-10-30 16:34:31.700296: Current learning rate: 0.00762 +2025-10-30 16:34:50.149765: train_loss -0.982 +2025-10-30 16:34:50.152405: val_loss -0.9121 +2025-10-30 16:34:50.153953: Pseudo dice [np.float32(0.9823), np.float32(0.9901), np.float32(0.9952), np.float32(0.8305)] +2025-10-30 16:34:50.155393: Epoch time: 18.45 s +2025-10-30 16:34:51.161946: +2025-10-30 16:34:51.163563: Epoch 262 +2025-10-30 16:34:51.164968: Current learning rate: 0.00761 +2025-10-30 16:35:11.401030: train_loss -0.9831 +2025-10-30 16:35:11.403315: val_loss -0.9023 +2025-10-30 16:35:11.404927: Pseudo dice [np.float32(0.9834), np.float32(0.9905), np.float32(0.9949), np.float32(0.8156)] +2025-10-30 16:35:11.406559: Epoch time: 20.24 s +2025-10-30 16:35:12.835316: +2025-10-30 16:35:12.839846: Epoch 263 +2025-10-30 16:35:12.841364: Current learning rate: 0.0076 +2025-10-30 16:35:33.126067: train_loss -0.9837 +2025-10-30 16:35:33.128272: val_loss -0.909 +2025-10-30 16:35:33.129762: Pseudo dice [np.float32(0.9832), np.float32(0.9906), np.float32(0.995), np.float32(0.8234)] +2025-10-30 16:35:33.131327: Epoch time: 20.29 s +2025-10-30 16:35:34.311998: +2025-10-30 16:35:34.314413: Epoch 264 +2025-10-30 16:35:34.316131: Current learning rate: 0.00759 +2025-10-30 16:35:54.533458: train_loss -0.9839 +2025-10-30 16:35:54.535869: val_loss -0.9101 +2025-10-30 16:35:54.537367: Pseudo dice [np.float32(0.9816), np.float32(0.9905), np.float32(0.9953), np.float32(0.8334)] +2025-10-30 16:35:54.539072: Epoch time: 20.22 s +2025-10-30 16:35:55.724392: +2025-10-30 16:35:55.726278: Epoch 265 +2025-10-30 16:35:55.727788: Current learning rate: 0.00758 +2025-10-30 16:36:16.359860: train_loss -0.9833 +2025-10-30 16:36:16.362425: val_loss -0.9102 +2025-10-30 16:36:16.364213: Pseudo dice [np.float32(0.9814), np.float32(0.9896), np.float32(0.9954), np.float32(0.84)] +2025-10-30 16:36:16.365875: Epoch time: 20.64 s +2025-10-30 16:36:17.480378: +2025-10-30 16:36:17.482448: Epoch 266 +2025-10-30 16:36:17.484261: Current learning rate: 0.00757 +2025-10-30 16:36:38.020619: train_loss -0.9704 +2025-10-30 16:36:38.023011: val_loss -0.9082 +2025-10-30 16:36:38.024661: Pseudo dice [np.float32(0.9799), np.float32(0.9887), np.float32(0.9947), np.float32(0.8179)] +2025-10-30 16:36:38.026657: Epoch time: 20.54 s +2025-10-30 16:36:39.041941: +2025-10-30 16:36:39.043755: Epoch 267 +2025-10-30 16:36:39.046161: Current learning rate: 0.00756 +2025-10-30 16:36:58.718927: train_loss -0.9525 +2025-10-30 16:36:58.722667: val_loss -0.919 +2025-10-30 16:36:58.724499: Pseudo dice [np.float32(0.9854), np.float32(0.9902), np.float32(0.9947), np.float32(0.814)] +2025-10-30 16:36:58.726328: Epoch time: 19.68 s +2025-10-30 16:36:59.937369: +2025-10-30 16:36:59.939170: Epoch 268 +2025-10-30 16:36:59.940745: Current learning rate: 0.00755 +2025-10-30 16:37:18.730359: train_loss -0.962 +2025-10-30 16:37:18.733048: val_loss -0.8848 +2025-10-30 16:37:18.735053: Pseudo dice [np.float32(0.9828), np.float32(0.989), np.float32(0.981), np.float32(0.7929)] +2025-10-30 16:37:18.737109: Epoch time: 18.79 s +2025-10-30 16:37:19.911596: +2025-10-30 16:37:19.913442: Epoch 269 +2025-10-30 16:37:19.915019: Current learning rate: 0.00754 +2025-10-30 16:37:40.331062: train_loss -0.9573 +2025-10-30 16:37:40.333578: val_loss -0.9173 +2025-10-30 16:37:40.335275: Pseudo dice [np.float32(0.9827), np.float32(0.9909), np.float32(0.9952), np.float32(0.8217)] +2025-10-30 16:37:40.337103: Epoch time: 20.42 s +2025-10-30 16:37:41.583028: +2025-10-30 16:37:41.585261: Epoch 270 +2025-10-30 16:37:41.587508: Current learning rate: 0.00753 +2025-10-30 16:38:01.966426: train_loss -0.97 +2025-10-30 16:38:01.969455: val_loss -0.9043 +2025-10-30 16:38:01.971078: Pseudo dice [np.float32(0.9815), np.float32(0.9898), np.float32(0.9944), np.float32(0.8031)] +2025-10-30 16:38:01.972972: Epoch time: 20.38 s +2025-10-30 16:38:02.992196: +2025-10-30 16:38:02.994064: Epoch 271 +2025-10-30 16:38:02.995738: Current learning rate: 0.00752 +2025-10-30 16:38:23.729015: train_loss -0.977 +2025-10-30 16:38:23.734273: val_loss -0.9193 +2025-10-30 16:38:23.736448: Pseudo dice [np.float32(0.9808), np.float32(0.9901), np.float32(0.9958), np.float32(0.8467)] +2025-10-30 16:38:23.738705: Epoch time: 20.74 s +2025-10-30 16:38:24.981604: +2025-10-30 16:38:24.983475: Epoch 272 +2025-10-30 16:38:24.985194: Current learning rate: 0.00751 +2025-10-30 16:38:45.559377: train_loss -0.9787 +2025-10-30 16:38:45.561554: val_loss -0.9169 +2025-10-30 16:38:45.563200: Pseudo dice [np.float32(0.9835), np.float32(0.991), np.float32(0.9956), np.float32(0.8437)] +2025-10-30 16:38:45.564828: Epoch time: 20.58 s +2025-10-30 16:38:46.570009: +2025-10-30 16:38:46.571953: Epoch 273 +2025-10-30 16:38:46.576030: Current learning rate: 0.00751 +2025-10-30 16:39:06.906251: train_loss -0.9793 +2025-10-30 16:39:06.909687: val_loss -0.9206 +2025-10-30 16:39:06.912315: Pseudo dice [np.float32(0.9837), np.float32(0.9915), np.float32(0.9954), np.float32(0.842)] +2025-10-30 16:39:06.914807: Epoch time: 20.34 s +2025-10-30 16:39:08.180317: +2025-10-30 16:39:08.182182: Epoch 274 +2025-10-30 16:39:08.183622: Current learning rate: 0.0075 +2025-10-30 16:39:27.301501: train_loss -0.9806 +2025-10-30 16:39:27.303620: val_loss -0.9034 +2025-10-30 16:39:27.305739: Pseudo dice [np.float32(0.9831), np.float32(0.9904), np.float32(0.995), np.float32(0.7981)] +2025-10-30 16:39:27.307380: Epoch time: 19.12 s +2025-10-30 16:39:28.731504: +2025-10-30 16:39:28.733591: Epoch 275 +2025-10-30 16:39:28.735638: Current learning rate: 0.00749 +2025-10-30 16:39:49.138870: train_loss -0.9815 +2025-10-30 16:39:49.140697: val_loss -0.904 +2025-10-30 16:39:49.142035: Pseudo dice [np.float32(0.9826), np.float32(0.9904), np.float32(0.9948), np.float32(0.8071)] +2025-10-30 16:39:49.143317: Epoch time: 20.41 s +2025-10-30 16:39:50.124833: +2025-10-30 16:39:50.126748: Epoch 276 +2025-10-30 16:39:50.128458: Current learning rate: 0.00748 +2025-10-30 16:40:10.471433: train_loss -0.9818 +2025-10-30 16:40:10.477147: val_loss -0.8996 +2025-10-30 16:40:10.478656: Pseudo dice [np.float32(0.9823), np.float32(0.9906), np.float32(0.9946), np.float32(0.7958)] +2025-10-30 16:40:10.480621: Epoch time: 20.35 s +2025-10-30 16:40:11.517996: +2025-10-30 16:40:11.519717: Epoch 277 +2025-10-30 16:40:11.521220: Current learning rate: 0.00747 +2025-10-30 16:40:32.160156: train_loss -0.9829 +2025-10-30 16:40:32.162281: val_loss -0.9154 +2025-10-30 16:40:32.163862: Pseudo dice [np.float32(0.9838), np.float32(0.9905), np.float32(0.9951), np.float32(0.8428)] +2025-10-30 16:40:32.165608: Epoch time: 20.64 s +2025-10-30 16:40:33.385398: +2025-10-30 16:40:33.387114: Epoch 278 +2025-10-30 16:40:33.388510: Current learning rate: 0.00746 +2025-10-30 16:40:53.893619: train_loss -0.9821 +2025-10-30 16:40:53.895586: val_loss -0.9093 +2025-10-30 16:40:53.896981: Pseudo dice [np.float32(0.9835), np.float32(0.9908), np.float32(0.995), np.float32(0.8226)] +2025-10-30 16:40:53.898314: Epoch time: 20.51 s +2025-10-30 16:40:54.942029: +2025-10-30 16:40:54.943667: Epoch 279 +2025-10-30 16:40:54.945100: Current learning rate: 0.00745 +2025-10-30 16:41:15.214477: train_loss -0.9837 +2025-10-30 16:41:15.217602: val_loss -0.914 +2025-10-30 16:41:15.219479: Pseudo dice [np.float32(0.9846), np.float32(0.9917), np.float32(0.9953), np.float32(0.835)] +2025-10-30 16:41:15.221271: Epoch time: 20.27 s +2025-10-30 16:41:16.319001: +2025-10-30 16:41:16.320797: Epoch 280 +2025-10-30 16:41:16.322450: Current learning rate: 0.00744 +2025-10-30 16:41:35.722793: train_loss -0.9854 +2025-10-30 16:41:35.724502: val_loss -0.9061 +2025-10-30 16:41:35.726182: Pseudo dice [np.float32(0.9841), np.float32(0.9905), np.float32(0.9944), np.float32(0.8243)] +2025-10-30 16:41:35.728339: Epoch time: 19.41 s +2025-10-30 16:41:36.799824: +2025-10-30 16:41:36.802212: Epoch 281 +2025-10-30 16:41:36.804784: Current learning rate: 0.00743 +2025-10-30 16:41:56.044193: train_loss -0.9844 +2025-10-30 16:41:56.045844: val_loss -0.9044 +2025-10-30 16:41:56.047523: Pseudo dice [np.float32(0.9829), np.float32(0.9908), np.float32(0.9951), np.float32(0.8178)] +2025-10-30 16:41:56.049008: Epoch time: 19.25 s +2025-10-30 16:41:57.029023: +2025-10-30 16:41:57.030841: Epoch 282 +2025-10-30 16:41:57.032976: Current learning rate: 0.00742 +2025-10-30 16:42:17.734417: train_loss -0.9835 +2025-10-30 16:42:17.737442: val_loss -0.9066 +2025-10-30 16:42:17.738946: Pseudo dice [np.float32(0.9842), np.float32(0.9912), np.float32(0.995), np.float32(0.8213)] +2025-10-30 16:42:17.740827: Epoch time: 20.71 s +2025-10-30 16:42:18.987618: +2025-10-30 16:42:18.989549: Epoch 283 +2025-10-30 16:42:18.990999: Current learning rate: 0.00741 +2025-10-30 16:42:39.525241: train_loss -0.9848 +2025-10-30 16:42:39.531134: val_loss -0.9075 +2025-10-30 16:42:39.532497: Pseudo dice [np.float32(0.9824), np.float32(0.9902), np.float32(0.9953), np.float32(0.8263)] +2025-10-30 16:42:39.533828: Epoch time: 20.54 s +2025-10-30 16:42:40.590624: +2025-10-30 16:42:40.592360: Epoch 284 +2025-10-30 16:42:40.593878: Current learning rate: 0.0074 +2025-10-30 16:43:00.997942: train_loss -0.9824 +2025-10-30 16:43:00.999978: val_loss -0.9024 +2025-10-30 16:43:01.007360: Pseudo dice [np.float32(0.981), np.float32(0.9901), np.float32(0.9953), np.float32(0.8158)] +2025-10-30 16:43:01.014216: Epoch time: 20.41 s +2025-10-30 16:43:02.154122: +2025-10-30 16:43:02.155899: Epoch 285 +2025-10-30 16:43:02.157679: Current learning rate: 0.00739 +2025-10-30 16:43:23.016029: train_loss -0.9833 +2025-10-30 16:43:23.019491: val_loss -0.9001 +2025-10-30 16:43:23.021241: Pseudo dice [np.float32(0.9826), np.float32(0.9903), np.float32(0.9948), np.float32(0.8111)] +2025-10-30 16:43:23.023066: Epoch time: 20.86 s +2025-10-30 16:43:24.203848: +2025-10-30 16:43:24.205867: Epoch 286 +2025-10-30 16:43:24.207497: Current learning rate: 0.00738 +2025-10-30 16:43:43.681967: train_loss -0.9838 +2025-10-30 16:43:43.683890: val_loss -0.9064 +2025-10-30 16:43:43.685409: Pseudo dice [np.float32(0.9826), np.float32(0.9913), np.float32(0.9957), np.float32(0.8224)] +2025-10-30 16:43:43.686964: Epoch time: 19.48 s +2025-10-30 16:43:44.720682: +2025-10-30 16:43:44.722419: Epoch 287 +2025-10-30 16:43:44.723990: Current learning rate: 0.00738 +2025-10-30 16:44:05.277061: train_loss -0.985 +2025-10-30 16:44:05.279186: val_loss -0.9036 +2025-10-30 16:44:05.280767: Pseudo dice [np.float32(0.9829), np.float32(0.9907), np.float32(0.9949), np.float32(0.8241)] +2025-10-30 16:44:05.282161: Epoch time: 20.56 s +2025-10-30 16:44:07.367491: +2025-10-30 16:44:07.369535: Epoch 288 +2025-10-30 16:44:07.371450: Current learning rate: 0.00737 +2025-10-30 16:44:27.099245: train_loss -0.9855 +2025-10-30 16:44:27.102116: val_loss -0.9094 +2025-10-30 16:44:27.104988: Pseudo dice [np.float32(0.9834), np.float32(0.9914), np.float32(0.9953), np.float32(0.8289)] +2025-10-30 16:44:27.106899: Epoch time: 19.73 s +2025-10-30 16:44:28.283127: +2025-10-30 16:44:28.285057: Epoch 289 +2025-10-30 16:44:28.286690: Current learning rate: 0.00736 +2025-10-30 16:44:48.973016: train_loss -0.9857 +2025-10-30 16:44:48.975196: val_loss -0.905 +2025-10-30 16:44:48.976807: Pseudo dice [np.float32(0.983), np.float32(0.9903), np.float32(0.9951), np.float32(0.823)] +2025-10-30 16:44:48.978760: Epoch time: 20.69 s +2025-10-30 16:44:49.996256: +2025-10-30 16:44:49.998359: Epoch 290 +2025-10-30 16:44:50.000093: Current learning rate: 0.00735 +2025-10-30 16:45:10.799448: train_loss -0.985 +2025-10-30 16:45:10.801572: val_loss -0.9002 +2025-10-30 16:45:10.803057: Pseudo dice [np.float32(0.9836), np.float32(0.9903), np.float32(0.9949), np.float32(0.819)] +2025-10-30 16:45:10.804500: Epoch time: 20.8 s +2025-10-30 16:45:12.014873: +2025-10-30 16:45:12.016659: Epoch 291 +2025-10-30 16:45:12.018035: Current learning rate: 0.00734 +2025-10-30 16:45:32.493567: train_loss -0.9856 +2025-10-30 16:45:32.496635: val_loss -0.9056 +2025-10-30 16:45:32.498512: Pseudo dice [np.float32(0.9818), np.float32(0.9901), np.float32(0.9953), np.float32(0.8335)] +2025-10-30 16:45:32.500399: Epoch time: 20.48 s +2025-10-30 16:45:33.709428: +2025-10-30 16:45:33.711380: Epoch 292 +2025-10-30 16:45:33.713017: Current learning rate: 0.00733 +2025-10-30 16:45:53.554514: train_loss -0.986 +2025-10-30 16:45:53.556446: val_loss -0.9008 +2025-10-30 16:45:53.558048: Pseudo dice [np.float32(0.983), np.float32(0.9903), np.float32(0.9949), np.float32(0.8236)] +2025-10-30 16:45:53.559412: Epoch time: 19.85 s +2025-10-30 16:45:54.582490: +2025-10-30 16:45:54.584586: Epoch 293 +2025-10-30 16:45:54.586277: Current learning rate: 0.00732 +2025-10-30 16:46:14.956424: train_loss -0.9857 +2025-10-30 16:46:14.958334: val_loss -0.8987 +2025-10-30 16:46:14.960601: Pseudo dice [np.float32(0.983), np.float32(0.9909), np.float32(0.9951), np.float32(0.8197)] +2025-10-30 16:46:14.962383: Epoch time: 20.38 s +2025-10-30 16:46:16.212922: +2025-10-30 16:46:16.214674: Epoch 294 +2025-10-30 16:46:16.216314: Current learning rate: 0.00731 +2025-10-30 16:46:36.756501: train_loss -0.9855 +2025-10-30 16:46:36.759299: val_loss -0.9 +2025-10-30 16:46:36.761081: Pseudo dice [np.float32(0.9846), np.float32(0.9906), np.float32(0.9945), np.float32(0.8134)] +2025-10-30 16:46:36.763434: Epoch time: 20.55 s +2025-10-30 16:46:37.912294: +2025-10-30 16:46:37.914185: Epoch 295 +2025-10-30 16:46:37.915848: Current learning rate: 0.0073 +2025-10-30 16:46:57.474428: train_loss -0.9856 +2025-10-30 16:46:57.476447: val_loss -0.9052 +2025-10-30 16:46:57.478011: Pseudo dice [np.float32(0.9843), np.float32(0.9913), np.float32(0.9948), np.float32(0.8286)] +2025-10-30 16:46:57.479455: Epoch time: 19.56 s +2025-10-30 16:46:58.733719: +2025-10-30 16:46:58.736019: Epoch 296 +2025-10-30 16:46:58.737750: Current learning rate: 0.00729 +2025-10-30 16:47:19.229036: train_loss -0.9856 +2025-10-30 16:47:19.231390: val_loss -0.9032 +2025-10-30 16:47:19.233429: Pseudo dice [np.float32(0.9819), np.float32(0.9901), np.float32(0.9952), np.float32(0.8342)] +2025-10-30 16:47:19.234805: Epoch time: 20.5 s +2025-10-30 16:47:20.383245: +2025-10-30 16:47:20.390203: Epoch 297 +2025-10-30 16:47:20.391927: Current learning rate: 0.00728 +2025-10-30 16:47:41.197021: train_loss -0.9866 +2025-10-30 16:47:41.199844: val_loss -0.9022 +2025-10-30 16:47:41.202455: Pseudo dice [np.float32(0.9844), np.float32(0.991), np.float32(0.9946), np.float32(0.8123)] +2025-10-30 16:47:41.204362: Epoch time: 20.82 s +2025-10-30 16:47:42.488476: +2025-10-30 16:47:42.490687: Epoch 298 +2025-10-30 16:47:42.492593: Current learning rate: 0.00727 +2025-10-30 16:48:02.744468: train_loss -0.9869 +2025-10-30 16:48:02.746705: val_loss -0.8984 +2025-10-30 16:48:02.749249: Pseudo dice [np.float32(0.9819), np.float32(0.9902), np.float32(0.9948), np.float32(0.8201)] +2025-10-30 16:48:02.750787: Epoch time: 20.26 s +2025-10-30 16:48:04.374928: +2025-10-30 16:48:04.376954: Epoch 299 +2025-10-30 16:48:04.379498: Current learning rate: 0.00726 +2025-10-30 16:48:24.257126: train_loss -0.9866 +2025-10-30 16:48:24.259143: val_loss -0.9024 +2025-10-30 16:48:24.260617: Pseudo dice [np.float32(0.9828), np.float32(0.9904), np.float32(0.995), np.float32(0.8222)] +2025-10-30 16:48:24.262158: Epoch time: 19.88 s +2025-10-30 16:48:26.542569: +2025-10-30 16:48:26.544639: Epoch 300 +2025-10-30 16:48:26.546478: Current learning rate: 0.00725 +2025-10-30 16:48:47.154229: train_loss -0.9862 +2025-10-30 16:48:47.157188: val_loss -0.9098 +2025-10-30 16:48:47.159247: Pseudo dice [np.float32(0.982), np.float32(0.9902), np.float32(0.9952), np.float32(0.839)] +2025-10-30 16:48:47.160825: Epoch time: 20.61 s +2025-10-30 16:48:48.172614: +2025-10-30 16:48:48.174638: Epoch 301 +2025-10-30 16:48:48.176396: Current learning rate: 0.00724 +2025-10-30 16:49:08.053027: train_loss -0.9874 +2025-10-30 16:49:08.056109: val_loss -0.9033 +2025-10-30 16:49:08.057957: Pseudo dice [np.float32(0.9835), np.float32(0.9909), np.float32(0.995), np.float32(0.821)] +2025-10-30 16:49:08.059903: Epoch time: 19.88 s +2025-10-30 16:49:09.411170: +2025-10-30 16:49:09.413249: Epoch 302 +2025-10-30 16:49:09.414999: Current learning rate: 0.00724 +2025-10-30 16:49:29.967686: train_loss -0.9873 +2025-10-30 16:49:29.970032: val_loss -0.9071 +2025-10-30 16:49:29.971629: Pseudo dice [np.float32(0.9833), np.float32(0.9903), np.float32(0.9951), np.float32(0.8305)] +2025-10-30 16:49:29.973114: Epoch time: 20.56 s +2025-10-30 16:49:30.980735: +2025-10-30 16:49:30.982791: Epoch 303 +2025-10-30 16:49:30.984681: Current learning rate: 0.00723 +2025-10-30 16:49:51.393077: train_loss -0.9874 +2025-10-30 16:49:51.395905: val_loss -0.905 +2025-10-30 16:49:51.397891: Pseudo dice [np.float32(0.9828), np.float32(0.9902), np.float32(0.9956), np.float32(0.8311)] +2025-10-30 16:49:51.399467: Epoch time: 20.41 s +2025-10-30 16:49:52.577243: +2025-10-30 16:49:52.579305: Epoch 304 +2025-10-30 16:49:52.581011: Current learning rate: 0.00722 +2025-10-30 16:50:13.269471: train_loss -0.9865 +2025-10-30 16:50:13.271786: val_loss -0.8974 +2025-10-30 16:50:13.273436: Pseudo dice [np.float32(0.9825), np.float32(0.9908), np.float32(0.995), np.float32(0.8203)] +2025-10-30 16:50:13.274925: Epoch time: 20.69 s +2025-10-30 16:50:14.414609: +2025-10-30 16:50:14.416821: Epoch 305 +2025-10-30 16:50:14.419164: Current learning rate: 0.00721 +2025-10-30 16:50:34.275534: train_loss -0.9867 +2025-10-30 16:50:34.278146: val_loss -0.908 +2025-10-30 16:50:34.280207: Pseudo dice [np.float32(0.9836), np.float32(0.9911), np.float32(0.9955), np.float32(0.8321)] +2025-10-30 16:50:34.281900: Epoch time: 19.86 s +2025-10-30 16:50:35.405169: +2025-10-30 16:50:35.407708: Epoch 306 +2025-10-30 16:50:35.409739: Current learning rate: 0.0072 +2025-10-30 16:50:55.860032: train_loss -0.9867 +2025-10-30 16:50:55.866586: val_loss -0.9114 +2025-10-30 16:50:55.868681: Pseudo dice [np.float32(0.9842), np.float32(0.9911), np.float32(0.9957), np.float32(0.8357)] +2025-10-30 16:50:55.870813: Epoch time: 20.46 s +2025-10-30 16:50:56.875989: +2025-10-30 16:50:56.878109: Epoch 307 +2025-10-30 16:50:56.879916: Current learning rate: 0.00719 +2025-10-30 16:51:17.557615: train_loss -0.9867 +2025-10-30 16:51:17.560344: val_loss -0.904 +2025-10-30 16:51:17.561825: Pseudo dice [np.float32(0.9831), np.float32(0.9908), np.float32(0.9954), np.float32(0.8236)] +2025-10-30 16:51:17.563387: Epoch time: 20.68 s +2025-10-30 16:51:18.767883: +2025-10-30 16:51:18.769883: Epoch 308 +2025-10-30 16:51:18.771540: Current learning rate: 0.00718 +2025-10-30 16:51:37.326700: train_loss -0.9864 +2025-10-30 16:51:37.328573: val_loss -0.8976 +2025-10-30 16:51:37.330282: Pseudo dice [np.float32(0.9843), np.float32(0.9906), np.float32(0.9951), np.float32(0.8085)] +2025-10-30 16:51:37.331826: Epoch time: 18.56 s +2025-10-30 16:51:38.443913: +2025-10-30 16:51:38.445867: Epoch 309 +2025-10-30 16:51:38.447610: Current learning rate: 0.00717 +2025-10-30 16:51:59.137867: train_loss -0.9862 +2025-10-30 16:51:59.141331: val_loss -0.9024 +2025-10-30 16:51:59.142829: Pseudo dice [np.float32(0.9837), np.float32(0.9908), np.float32(0.9947), np.float32(0.8171)] +2025-10-30 16:51:59.144159: Epoch time: 20.7 s +2025-10-30 16:52:00.323010: +2025-10-30 16:52:00.324679: Epoch 310 +2025-10-30 16:52:00.326124: Current learning rate: 0.00716 +2025-10-30 16:52:20.683182: train_loss -0.9857 +2025-10-30 16:52:20.685634: val_loss -0.9069 +2025-10-30 16:52:20.687373: Pseudo dice [np.float32(0.9812), np.float32(0.9905), np.float32(0.9954), np.float32(0.833)] +2025-10-30 16:52:20.688992: Epoch time: 20.36 s +2025-10-30 16:52:21.739561: +2025-10-30 16:52:21.741523: Epoch 311 +2025-10-30 16:52:21.743305: Current learning rate: 0.00715 +2025-10-30 16:52:42.041613: train_loss -0.9864 +2025-10-30 16:52:42.043659: val_loss -0.9062 +2025-10-30 16:52:42.045275: Pseudo dice [np.float32(0.9835), np.float32(0.9912), np.float32(0.9954), np.float32(0.8304)] +2025-10-30 16:52:42.047071: Epoch time: 20.3 s +2025-10-30 16:52:43.043496: +2025-10-30 16:52:43.045214: Epoch 312 +2025-10-30 16:52:43.047053: Current learning rate: 0.00714 +2025-10-30 16:53:03.558120: train_loss -0.9851 +2025-10-30 16:53:03.560911: val_loss -0.9111 +2025-10-30 16:53:03.562898: Pseudo dice [np.float32(0.9854), np.float32(0.9922), np.float32(0.995), np.float32(0.831)] +2025-10-30 16:53:03.564546: Epoch time: 20.52 s +2025-10-30 16:53:04.826382: +2025-10-30 16:53:04.828377: Epoch 313 +2025-10-30 16:53:04.830043: Current learning rate: 0.00713 +2025-10-30 16:53:25.177266: train_loss -0.9869 +2025-10-30 16:53:25.179826: val_loss -0.907 +2025-10-30 16:53:25.181695: Pseudo dice [np.float32(0.984), np.float32(0.9911), np.float32(0.9955), np.float32(0.8323)] +2025-10-30 16:53:25.183305: Epoch time: 20.35 s +2025-10-30 16:53:26.270205: +2025-10-30 16:53:26.272345: Epoch 314 +2025-10-30 16:53:26.274043: Current learning rate: 0.00712 +2025-10-30 16:53:46.589460: train_loss -0.9875 +2025-10-30 16:53:46.592253: val_loss -0.8991 +2025-10-30 16:53:46.594079: Pseudo dice [np.float32(0.9841), np.float32(0.9906), np.float32(0.995), np.float32(0.8062)] +2025-10-30 16:53:46.595943: Epoch time: 20.32 s +2025-10-30 16:53:47.599781: +2025-10-30 16:53:47.601684: Epoch 315 +2025-10-30 16:53:47.603279: Current learning rate: 0.00711 +2025-10-30 16:54:07.631282: train_loss -0.9867 +2025-10-30 16:54:07.634173: val_loss -0.8955 +2025-10-30 16:54:07.635763: Pseudo dice [np.float32(0.9842), np.float32(0.9903), np.float32(0.9944), np.float32(0.8045)] +2025-10-30 16:54:07.637314: Epoch time: 20.03 s +2025-10-30 16:54:08.825413: +2025-10-30 16:54:08.831090: Epoch 316 +2025-10-30 16:54:08.833902: Current learning rate: 0.0071 +2025-10-30 16:54:29.402627: train_loss -0.9862 +2025-10-30 16:54:29.404926: val_loss -0.8979 +2025-10-30 16:54:29.406640: Pseudo dice [np.float32(0.9828), np.float32(0.99), np.float32(0.9948), np.float32(0.8155)] +2025-10-30 16:54:29.409712: Epoch time: 20.58 s +2025-10-30 16:54:30.686586: +2025-10-30 16:54:30.688373: Epoch 317 +2025-10-30 16:54:30.690143: Current learning rate: 0.0071 +2025-10-30 16:54:51.046904: train_loss -0.9867 +2025-10-30 16:54:51.049330: val_loss -0.8945 +2025-10-30 16:54:51.051923: Pseudo dice [np.float32(0.984), np.float32(0.9904), np.float32(0.9941), np.float32(0.7985)] +2025-10-30 16:54:51.053610: Epoch time: 20.36 s +2025-10-30 16:54:52.200548: +2025-10-30 16:54:52.202265: Epoch 318 +2025-10-30 16:54:52.203744: Current learning rate: 0.00709 +2025-10-30 16:55:12.026440: train_loss -0.9877 +2025-10-30 16:55:12.033469: val_loss -0.9048 +2025-10-30 16:55:12.035958: Pseudo dice [np.float32(0.9824), np.float32(0.9904), np.float32(0.9951), np.float32(0.8289)] +2025-10-30 16:55:12.037844: Epoch time: 19.83 s +2025-10-30 16:55:13.121630: +2025-10-30 16:55:13.123655: Epoch 319 +2025-10-30 16:55:13.125263: Current learning rate: 0.00708 +2025-10-30 16:55:33.808655: train_loss -0.9875 +2025-10-30 16:55:33.811104: val_loss -0.9078 +2025-10-30 16:55:33.813009: Pseudo dice [np.float32(0.9836), np.float32(0.9914), np.float32(0.9954), np.float32(0.8322)] +2025-10-30 16:55:33.814804: Epoch time: 20.69 s +2025-10-30 16:55:35.031647: +2025-10-30 16:55:35.033734: Epoch 320 +2025-10-30 16:55:35.035590: Current learning rate: 0.00707 +2025-10-30 16:55:56.042542: train_loss -0.9867 +2025-10-30 16:55:56.044942: val_loss -0.9085 +2025-10-30 16:55:56.046828: Pseudo dice [np.float32(0.9852), np.float32(0.991), np.float32(0.9954), np.float32(0.8334)] +2025-10-30 16:55:56.049269: Epoch time: 21.01 s +2025-10-30 16:55:57.100289: +2025-10-30 16:55:57.102421: Epoch 321 +2025-10-30 16:55:57.104355: Current learning rate: 0.00706 +2025-10-30 16:56:17.486758: train_loss -0.9863 +2025-10-30 16:56:17.489588: val_loss -0.9116 +2025-10-30 16:56:17.491304: Pseudo dice [np.float32(0.985), np.float32(0.9917), np.float32(0.9955), np.float32(0.8369)] +2025-10-30 16:56:17.492990: Epoch time: 20.39 s +2025-10-30 16:56:18.609085: +2025-10-30 16:56:18.611173: Epoch 322 +2025-10-30 16:56:18.613003: Current learning rate: 0.00705 +2025-10-30 16:56:39.208371: train_loss -0.9871 +2025-10-30 16:56:39.210672: val_loss -0.8982 +2025-10-30 16:56:39.212410: Pseudo dice [np.float32(0.9831), np.float32(0.9901), np.float32(0.9946), np.float32(0.816)] +2025-10-30 16:56:39.214095: Epoch time: 20.6 s +2025-10-30 16:56:40.220484: +2025-10-30 16:56:40.222438: Epoch 323 +2025-10-30 16:56:40.224144: Current learning rate: 0.00704 +2025-10-30 16:57:00.607862: train_loss -0.9878 +2025-10-30 16:57:00.610155: val_loss -0.9055 +2025-10-30 16:57:00.612060: Pseudo dice [np.float32(0.9826), np.float32(0.99), np.float32(0.995), np.float32(0.8281)] +2025-10-30 16:57:00.614247: Epoch time: 20.39 s +2025-10-30 16:57:01.967985: +2025-10-30 16:57:01.969755: Epoch 324 +2025-10-30 16:57:01.971346: Current learning rate: 0.00703 +2025-10-30 16:57:20.946630: train_loss -0.9872 +2025-10-30 16:57:20.949026: val_loss -0.9052 +2025-10-30 16:57:20.950553: Pseudo dice [np.float32(0.9829), np.float32(0.9895), np.float32(0.9951), np.float32(0.8326)] +2025-10-30 16:57:20.952267: Epoch time: 18.98 s +2025-10-30 16:57:21.997975: +2025-10-30 16:57:22.000215: Epoch 325 +2025-10-30 16:57:22.002029: Current learning rate: 0.00702 +2025-10-30 16:57:42.538650: train_loss -0.9879 +2025-10-30 16:57:42.541377: val_loss -0.9051 +2025-10-30 16:57:42.543601: Pseudo dice [np.float32(0.9837), np.float32(0.9907), np.float32(0.9955), np.float32(0.8294)] +2025-10-30 16:57:42.545321: Epoch time: 20.54 s +2025-10-30 16:57:43.569180: +2025-10-30 16:57:43.570991: Epoch 326 +2025-10-30 16:57:43.572873: Current learning rate: 0.00701 +2025-10-30 16:58:03.968385: train_loss -0.9861 +2025-10-30 16:58:03.970206: val_loss -0.9063 +2025-10-30 16:58:03.971851: Pseudo dice [np.float32(0.983), np.float32(0.9905), np.float32(0.9955), np.float32(0.8307)] +2025-10-30 16:58:03.973252: Epoch time: 20.4 s +2025-10-30 16:58:05.005524: +2025-10-30 16:58:05.009413: Epoch 327 +2025-10-30 16:58:05.012059: Current learning rate: 0.007 +2025-10-30 16:58:25.537046: train_loss -0.9851 +2025-10-30 16:58:25.543019: val_loss -0.9017 +2025-10-30 16:58:25.544583: Pseudo dice [np.float32(0.983), np.float32(0.9908), np.float32(0.9952), np.float32(0.823)] +2025-10-30 16:58:25.546085: Epoch time: 20.53 s +2025-10-30 16:58:26.811630: +2025-10-30 16:58:26.813914: Epoch 328 +2025-10-30 16:58:26.815982: Current learning rate: 0.00699 +2025-10-30 16:58:46.392686: train_loss -0.9874 +2025-10-30 16:58:46.398021: val_loss -0.9041 +2025-10-30 16:58:46.399826: Pseudo dice [np.float32(0.9825), np.float32(0.9904), np.float32(0.9952), np.float32(0.8348)] +2025-10-30 16:58:46.401832: Epoch time: 19.58 s +2025-10-30 16:58:47.559769: +2025-10-30 16:58:47.561753: Epoch 329 +2025-10-30 16:58:47.563558: Current learning rate: 0.00698 +2025-10-30 16:59:08.123196: train_loss -0.9871 +2025-10-30 16:59:08.125275: val_loss -0.9107 +2025-10-30 16:59:08.127238: Pseudo dice [np.float32(0.9845), np.float32(0.9916), np.float32(0.9955), np.float32(0.841)] +2025-10-30 16:59:08.128891: Epoch time: 20.57 s +2025-10-30 16:59:09.130953: +2025-10-30 16:59:09.132746: Epoch 330 +2025-10-30 16:59:09.134483: Current learning rate: 0.00697 +2025-10-30 16:59:29.140899: train_loss -0.9878 +2025-10-30 16:59:29.144025: val_loss -0.9015 +2025-10-30 16:59:29.145705: Pseudo dice [np.float32(0.9817), np.float32(0.9905), np.float32(0.9953), np.float32(0.827)] +2025-10-30 16:59:29.147382: Epoch time: 20.01 s +2025-10-30 16:59:30.251042: +2025-10-30 16:59:30.252596: Epoch 331 +2025-10-30 16:59:30.254056: Current learning rate: 0.00696 +2025-10-30 16:59:50.353155: train_loss -0.9874 +2025-10-30 16:59:50.358840: val_loss -0.9042 +2025-10-30 16:59:50.360657: Pseudo dice [np.float32(0.9822), np.float32(0.9911), np.float32(0.9953), np.float32(0.8227)] +2025-10-30 16:59:50.362798: Epoch time: 20.1 s +2025-10-30 16:59:51.639589: +2025-10-30 16:59:51.641512: Epoch 332 +2025-10-30 16:59:51.643192: Current learning rate: 0.00696 +2025-10-30 17:00:12.169990: train_loss -0.9881 +2025-10-30 17:00:12.172367: val_loss -0.8985 +2025-10-30 17:00:12.173815: Pseudo dice [np.float32(0.9817), np.float32(0.9905), np.float32(0.9953), np.float32(0.8191)] +2025-10-30 17:00:12.176214: Epoch time: 20.53 s +2025-10-30 17:00:13.414585: +2025-10-30 17:00:13.416664: Epoch 333 +2025-10-30 17:00:13.418154: Current learning rate: 0.00695 +2025-10-30 17:00:33.974745: train_loss -0.9886 +2025-10-30 17:00:33.977533: val_loss -0.9036 +2025-10-30 17:00:33.979713: Pseudo dice [np.float32(0.9837), np.float32(0.991), np.float32(0.9952), np.float32(0.8243)] +2025-10-30 17:00:33.981504: Epoch time: 20.56 s +2025-10-30 17:00:35.113361: +2025-10-30 17:00:35.115678: Epoch 334 +2025-10-30 17:00:35.117723: Current learning rate: 0.00694 +2025-10-30 17:00:55.659768: train_loss -0.988 +2025-10-30 17:00:55.661638: val_loss -0.8984 +2025-10-30 17:00:55.663044: Pseudo dice [np.float32(0.9843), np.float32(0.9908), np.float32(0.9944), np.float32(0.8097)] +2025-10-30 17:00:55.664469: Epoch time: 20.55 s +2025-10-30 17:00:56.717624: +2025-10-30 17:00:56.719472: Epoch 335 +2025-10-30 17:00:56.721286: Current learning rate: 0.00693 +2025-10-30 17:01:16.170747: train_loss -0.988 +2025-10-30 17:01:16.173089: val_loss -0.8979 +2025-10-30 17:01:16.174607: Pseudo dice [np.float32(0.9825), np.float32(0.9905), np.float32(0.9952), np.float32(0.8197)] +2025-10-30 17:01:16.176122: Epoch time: 19.45 s +2025-10-30 17:01:17.868739: +2025-10-30 17:01:17.870482: Epoch 336 +2025-10-30 17:01:17.872037: Current learning rate: 0.00692 +2025-10-30 17:01:38.407598: train_loss -0.9862 +2025-10-30 17:01:38.410386: val_loss -0.8952 +2025-10-30 17:01:38.411916: Pseudo dice [np.float32(0.984), np.float32(0.9905), np.float32(0.9947), np.float32(0.8067)] +2025-10-30 17:01:38.414015: Epoch time: 20.54 s +2025-10-30 17:01:39.425079: +2025-10-30 17:01:39.426795: Epoch 337 +2025-10-30 17:01:39.428351: Current learning rate: 0.00691 +2025-10-30 17:01:58.120086: train_loss -0.9874 +2025-10-30 17:01:58.122942: val_loss -0.9009 +2025-10-30 17:01:58.125856: Pseudo dice [np.float32(0.9838), np.float32(0.991), np.float32(0.9952), np.float32(0.8199)] +2025-10-30 17:01:58.132797: Epoch time: 18.7 s +2025-10-30 17:01:59.316506: +2025-10-30 17:01:59.319194: Epoch 338 +2025-10-30 17:01:59.321105: Current learning rate: 0.0069 +2025-10-30 17:02:19.967740: train_loss -0.9877 +2025-10-30 17:02:19.969637: val_loss -0.9026 +2025-10-30 17:02:19.971051: Pseudo dice [np.float32(0.983), np.float32(0.9907), np.float32(0.9951), np.float32(0.8243)] +2025-10-30 17:02:19.972456: Epoch time: 20.65 s +2025-10-30 17:02:21.246741: +2025-10-30 17:02:21.248625: Epoch 339 +2025-10-30 17:02:21.250360: Current learning rate: 0.00689 +2025-10-30 17:02:41.848640: train_loss -0.9867 +2025-10-30 17:02:41.851501: val_loss -0.8989 +2025-10-30 17:02:41.853775: Pseudo dice [np.float32(0.9827), np.float32(0.991), np.float32(0.9951), np.float32(0.8201)] +2025-10-30 17:02:41.856221: Epoch time: 20.6 s +2025-10-30 17:02:43.050404: +2025-10-30 17:02:43.052529: Epoch 340 +2025-10-30 17:02:43.054293: Current learning rate: 0.00688 +2025-10-30 17:03:03.831929: train_loss -0.9853 +2025-10-30 17:03:03.834014: val_loss -0.9043 +2025-10-30 17:03:03.835603: Pseudo dice [np.float32(0.9831), np.float32(0.9904), np.float32(0.9951), np.float32(0.8258)] +2025-10-30 17:03:03.837040: Epoch time: 20.78 s +2025-10-30 17:03:04.960826: +2025-10-30 17:03:04.969344: Epoch 341 +2025-10-30 17:03:04.971092: Current learning rate: 0.00687 +2025-10-30 17:03:25.522459: train_loss -0.9868 +2025-10-30 17:03:25.524642: val_loss -0.8992 +2025-10-30 17:03:25.526419: Pseudo dice [np.float32(0.9834), np.float32(0.9905), np.float32(0.9951), np.float32(0.8213)] +2025-10-30 17:03:25.528109: Epoch time: 20.56 s +2025-10-30 17:03:26.622687: +2025-10-30 17:03:26.626300: Epoch 342 +2025-10-30 17:03:26.628060: Current learning rate: 0.00686 +2025-10-30 17:03:46.447055: train_loss -0.9852 +2025-10-30 17:03:46.449578: val_loss -0.905 +2025-10-30 17:03:46.450926: Pseudo dice [np.float32(0.9827), np.float32(0.9903), np.float32(0.9954), np.float32(0.836)] +2025-10-30 17:03:46.452279: Epoch time: 19.83 s +2025-10-30 17:03:47.725906: +2025-10-30 17:03:47.727608: Epoch 343 +2025-10-30 17:03:47.729141: Current learning rate: 0.00685 +2025-10-30 17:04:07.123220: train_loss -0.9858 +2025-10-30 17:04:07.125354: val_loss -0.9051 +2025-10-30 17:04:07.126886: Pseudo dice [np.float32(0.9828), np.float32(0.9909), np.float32(0.9953), np.float32(0.8251)] +2025-10-30 17:04:07.128594: Epoch time: 19.4 s +2025-10-30 17:04:08.299731: +2025-10-30 17:04:08.301522: Epoch 344 +2025-10-30 17:04:08.303818: Current learning rate: 0.00684 +2025-10-30 17:04:28.711518: train_loss -0.9869 +2025-10-30 17:04:28.717456: val_loss -0.9061 +2025-10-30 17:04:28.719272: Pseudo dice [np.float32(0.9821), np.float32(0.9907), np.float32(0.9955), np.float32(0.8277)] +2025-10-30 17:04:28.720974: Epoch time: 20.41 s +2025-10-30 17:04:29.914739: +2025-10-30 17:04:29.916790: Epoch 345 +2025-10-30 17:04:29.918421: Current learning rate: 0.00683 +2025-10-30 17:04:51.092121: train_loss -0.9873 +2025-10-30 17:04:51.094879: val_loss -0.9056 +2025-10-30 17:04:51.096417: Pseudo dice [np.float32(0.9848), np.float32(0.9919), np.float32(0.9952), np.float32(0.833)] +2025-10-30 17:04:51.098009: Epoch time: 21.18 s +2025-10-30 17:04:52.270299: +2025-10-30 17:04:52.272031: Epoch 346 +2025-10-30 17:04:52.273634: Current learning rate: 0.00682 +2025-10-30 17:05:13.039492: train_loss -0.9882 +2025-10-30 17:05:13.041774: val_loss -0.9002 +2025-10-30 17:05:13.043399: Pseudo dice [np.float32(0.9822), np.float32(0.9913), np.float32(0.9956), np.float32(0.8216)] +2025-10-30 17:05:13.044979: Epoch time: 20.77 s +2025-10-30 17:05:13.950615: +2025-10-30 17:05:13.952326: Epoch 347 +2025-10-30 17:05:13.954476: Current learning rate: 0.00681 +2025-10-30 17:05:34.526676: train_loss -0.9871 +2025-10-30 17:05:34.528765: val_loss -0.9101 +2025-10-30 17:05:34.530999: Pseudo dice [np.float32(0.9817), np.float32(0.9907), np.float32(0.9958), np.float32(0.843)] +2025-10-30 17:05:34.533592: Epoch time: 20.58 s +2025-10-30 17:05:36.002379: +2025-10-30 17:05:36.004319: Epoch 348 +2025-10-30 17:05:36.006117: Current learning rate: 0.0068 +2025-10-30 17:05:55.256448: train_loss -0.9874 +2025-10-30 17:05:55.259206: val_loss -0.9013 +2025-10-30 17:05:55.261102: Pseudo dice [np.float32(0.9829), np.float32(0.9905), np.float32(0.9954), np.float32(0.8275)] +2025-10-30 17:05:55.262607: Epoch time: 19.26 s +2025-10-30 17:05:56.455998: +2025-10-30 17:05:56.458019: Epoch 349 +2025-10-30 17:05:56.459895: Current learning rate: 0.0068 +2025-10-30 17:06:16.821632: train_loss -0.9877 +2025-10-30 17:06:16.827453: val_loss -0.8945 +2025-10-30 17:06:16.829203: Pseudo dice [np.float32(0.9837), np.float32(0.9916), np.float32(0.9946), np.float32(0.7995)] +2025-10-30 17:06:16.830670: Epoch time: 20.37 s +2025-10-30 17:06:19.117059: +2025-10-30 17:06:19.118718: Epoch 350 +2025-10-30 17:06:19.120814: Current learning rate: 0.00679 +2025-10-30 17:06:39.221978: train_loss -0.9882 +2025-10-30 17:06:39.224367: val_loss -0.9076 +2025-10-30 17:06:39.226427: Pseudo dice [np.float32(0.9844), np.float32(0.9915), np.float32(0.9953), np.float32(0.8324)] +2025-10-30 17:06:39.228417: Epoch time: 20.11 s +2025-10-30 17:06:40.242863: +2025-10-30 17:06:40.244763: Epoch 351 +2025-10-30 17:06:40.246588: Current learning rate: 0.00678 +2025-10-30 17:07:00.939074: train_loss -0.9878 +2025-10-30 17:07:00.950480: val_loss -0.9046 +2025-10-30 17:07:00.952378: Pseudo dice [np.float32(0.9848), np.float32(0.9912), np.float32(0.9949), np.float32(0.8265)] +2025-10-30 17:07:00.954472: Epoch time: 20.7 s +2025-10-30 17:07:02.057228: +2025-10-30 17:07:02.059221: Epoch 352 +2025-10-30 17:07:02.060818: Current learning rate: 0.00677 +2025-10-30 17:07:22.442595: train_loss -0.9876 +2025-10-30 17:07:22.459032: val_loss -0.9062 +2025-10-30 17:07:22.460952: Pseudo dice [np.float32(0.9828), np.float32(0.9918), np.float32(0.9958), np.float32(0.8313)] +2025-10-30 17:07:22.462617: Epoch time: 20.39 s +2025-10-30 17:07:23.470080: +2025-10-30 17:07:23.471868: Epoch 353 +2025-10-30 17:07:23.477064: Current learning rate: 0.00676 +2025-10-30 17:07:43.925435: train_loss -0.9875 +2025-10-30 17:07:43.927823: val_loss -0.9061 +2025-10-30 17:07:43.929838: Pseudo dice [np.float32(0.984), np.float32(0.9912), np.float32(0.9953), np.float32(0.8266)] +2025-10-30 17:07:43.932228: Epoch time: 20.46 s +2025-10-30 17:07:44.971897: +2025-10-30 17:07:44.973882: Epoch 354 +2025-10-30 17:07:44.975553: Current learning rate: 0.00675 +2025-10-30 17:08:05.781933: train_loss -0.9873 +2025-10-30 17:08:05.785697: val_loss -0.9009 +2025-10-30 17:08:05.787668: Pseudo dice [np.float32(0.9825), np.float32(0.9905), np.float32(0.9951), np.float32(0.8254)] +2025-10-30 17:08:05.789543: Epoch time: 20.81 s +2025-10-30 17:08:07.137493: +2025-10-30 17:08:07.139226: Epoch 355 +2025-10-30 17:08:07.140849: Current learning rate: 0.00674 +2025-10-30 17:08:26.028328: train_loss -0.9865 +2025-10-30 17:08:26.032278: val_loss -0.9005 +2025-10-30 17:08:26.033964: Pseudo dice [np.float32(0.9839), np.float32(0.9911), np.float32(0.9952), np.float32(0.8194)] +2025-10-30 17:08:26.036036: Epoch time: 18.89 s +2025-10-30 17:08:27.163747: +2025-10-30 17:08:27.166284: Epoch 356 +2025-10-30 17:08:27.168003: Current learning rate: 0.00673 +2025-10-30 17:08:46.685591: train_loss -0.9883 +2025-10-30 17:08:46.688031: val_loss -0.9014 +2025-10-30 17:08:46.689773: Pseudo dice [np.float32(0.9839), np.float32(0.9912), np.float32(0.9949), np.float32(0.814)] +2025-10-30 17:08:46.691633: Epoch time: 19.52 s +2025-10-30 17:08:47.783529: +2025-10-30 17:08:47.785626: Epoch 357 +2025-10-30 17:08:47.787324: Current learning rate: 0.00672 +2025-10-30 17:09:07.991254: train_loss -0.9883 +2025-10-30 17:09:07.997898: val_loss -0.9085 +2025-10-30 17:09:07.999447: Pseudo dice [np.float32(0.9837), np.float32(0.9911), np.float32(0.9956), np.float32(0.8413)] +2025-10-30 17:09:08.001136: Epoch time: 20.21 s +2025-10-30 17:09:09.003842: +2025-10-30 17:09:09.005487: Epoch 358 +2025-10-30 17:09:09.007032: Current learning rate: 0.00671 +2025-10-30 17:09:29.588897: train_loss -0.9883 +2025-10-30 17:09:29.591153: val_loss -0.8978 +2025-10-30 17:09:29.592890: Pseudo dice [np.float32(0.9816), np.float32(0.9894), np.float32(0.9954), np.float32(0.8225)] +2025-10-30 17:09:29.594395: Epoch time: 20.59 s +2025-10-30 17:09:30.616114: +2025-10-30 17:09:30.619663: Epoch 359 +2025-10-30 17:09:30.621346: Current learning rate: 0.0067 +2025-10-30 17:09:50.972022: train_loss -0.9798 +2025-10-30 17:09:50.977675: val_loss -0.9077 +2025-10-30 17:09:50.979313: Pseudo dice [np.float32(0.9844), np.float32(0.991), np.float32(0.9951), np.float32(0.8167)] +2025-10-30 17:09:50.980822: Epoch time: 20.36 s +2025-10-30 17:09:52.651919: +2025-10-30 17:09:52.653878: Epoch 360 +2025-10-30 17:09:52.655536: Current learning rate: 0.00669 +2025-10-30 17:10:13.122188: train_loss -0.9807 +2025-10-30 17:10:13.126697: val_loss -0.905 +2025-10-30 17:10:13.128434: Pseudo dice [np.float32(0.9816), np.float32(0.9893), np.float32(0.9948), np.float32(0.825)] +2025-10-30 17:10:13.130064: Epoch time: 20.47 s +2025-10-30 17:10:14.307857: +2025-10-30 17:10:14.309850: Epoch 361 +2025-10-30 17:10:14.311647: Current learning rate: 0.00668 +2025-10-30 17:10:35.013592: train_loss -0.9776 +2025-10-30 17:10:35.015936: val_loss -0.9047 +2025-10-30 17:10:35.017765: Pseudo dice [np.float32(0.9856), np.float32(0.9902), np.float32(0.9921), np.float32(0.8162)] +2025-10-30 17:10:35.019491: Epoch time: 20.71 s +2025-10-30 17:10:36.240486: +2025-10-30 17:10:36.242290: Epoch 362 +2025-10-30 17:10:36.244258: Current learning rate: 0.00667 +2025-10-30 17:10:54.491394: train_loss -0.9775 +2025-10-30 17:10:54.493644: val_loss -0.9201 +2025-10-30 17:10:54.496081: Pseudo dice [np.float32(0.9842), np.float32(0.9914), np.float32(0.9958), np.float32(0.8482)] +2025-10-30 17:10:54.498574: Epoch time: 18.25 s +2025-10-30 17:10:55.776141: +2025-10-30 17:10:55.778206: Epoch 363 +2025-10-30 17:10:55.779993: Current learning rate: 0.00666 +2025-10-30 17:11:16.162953: train_loss -0.9849 +2025-10-30 17:11:16.166830: val_loss -0.9119 +2025-10-30 17:11:16.168645: Pseudo dice [np.float32(0.9835), np.float32(0.9907), np.float32(0.9953), np.float32(0.8334)] +2025-10-30 17:11:16.170640: Epoch time: 20.39 s +2025-10-30 17:11:17.264057: +2025-10-30 17:11:17.265703: Epoch 364 +2025-10-30 17:11:17.267590: Current learning rate: 0.00665 +2025-10-30 17:11:37.776088: train_loss -0.985 +2025-10-30 17:11:37.778413: val_loss -0.9082 +2025-10-30 17:11:37.780036: Pseudo dice [np.float32(0.9839), np.float32(0.9908), np.float32(0.9953), np.float32(0.8299)] +2025-10-30 17:11:37.781672: Epoch time: 20.51 s +2025-10-30 17:11:39.000160: +2025-10-30 17:11:39.001782: Epoch 365 +2025-10-30 17:11:39.003429: Current learning rate: 0.00665 +2025-10-30 17:11:59.655736: train_loss -0.9864 +2025-10-30 17:11:59.657776: val_loss -0.8961 +2025-10-30 17:11:59.659442: Pseudo dice [np.float32(0.9835), np.float32(0.9902), np.float32(0.9948), np.float32(0.8078)] +2025-10-30 17:11:59.661211: Epoch time: 20.66 s +2025-10-30 17:12:00.721576: +2025-10-30 17:12:00.723642: Epoch 366 +2025-10-30 17:12:00.725183: Current learning rate: 0.00664 +2025-10-30 17:12:21.409304: train_loss -0.9871 +2025-10-30 17:12:21.412844: val_loss -0.9038 +2025-10-30 17:12:21.414638: Pseudo dice [np.float32(0.9835), np.float32(0.9904), np.float32(0.9954), np.float32(0.8235)] +2025-10-30 17:12:21.416537: Epoch time: 20.69 s +2025-10-30 17:12:22.664459: +2025-10-30 17:12:22.666381: Epoch 367 +2025-10-30 17:12:22.668003: Current learning rate: 0.00663 +2025-10-30 17:12:43.033710: train_loss -0.9867 +2025-10-30 17:12:43.035999: val_loss -0.9009 +2025-10-30 17:12:43.038336: Pseudo dice [np.float32(0.9833), np.float32(0.9908), np.float32(0.9953), np.float32(0.8062)] +2025-10-30 17:12:43.040523: Epoch time: 20.37 s +2025-10-30 17:12:44.222635: +2025-10-30 17:12:44.224528: Epoch 368 +2025-10-30 17:12:44.226188: Current learning rate: 0.00662 +2025-10-30 17:13:04.487663: train_loss -0.987 +2025-10-30 17:13:04.490561: val_loss -0.9012 +2025-10-30 17:13:04.492267: Pseudo dice [np.float32(0.9835), np.float32(0.9911), np.float32(0.995), np.float32(0.819)] +2025-10-30 17:13:04.493631: Epoch time: 20.27 s +2025-10-30 17:13:05.591219: +2025-10-30 17:13:05.593399: Epoch 369 +2025-10-30 17:13:05.595263: Current learning rate: 0.00661 +2025-10-30 17:13:24.249442: train_loss -0.9869 +2025-10-30 17:13:24.252719: val_loss -0.895 +2025-10-30 17:13:24.254362: Pseudo dice [np.float32(0.9835), np.float32(0.9903), np.float32(0.9944), np.float32(0.8074)] +2025-10-30 17:13:24.255985: Epoch time: 18.66 s +2025-10-30 17:13:25.228975: +2025-10-30 17:13:25.230841: Epoch 370 +2025-10-30 17:13:25.232425: Current learning rate: 0.0066 +2025-10-30 17:13:45.962553: train_loss -0.9862 +2025-10-30 17:13:45.964847: val_loss -0.9032 +2025-10-30 17:13:45.966446: Pseudo dice [np.float32(0.9823), np.float32(0.9908), np.float32(0.9954), np.float32(0.8259)] +2025-10-30 17:13:45.968175: Epoch time: 20.74 s +2025-10-30 17:13:47.307045: +2025-10-30 17:13:47.308852: Epoch 371 +2025-10-30 17:13:47.311187: Current learning rate: 0.00659 +2025-10-30 17:14:08.058905: train_loss -0.9857 +2025-10-30 17:14:08.061553: val_loss -0.9016 +2025-10-30 17:14:08.063216: Pseudo dice [np.float32(0.9822), np.float32(0.9906), np.float32(0.9951), np.float32(0.8197)] +2025-10-30 17:14:08.065087: Epoch time: 20.75 s +2025-10-30 17:14:09.629052: +2025-10-30 17:14:09.631133: Epoch 372 +2025-10-30 17:14:09.632825: Current learning rate: 0.00658 +2025-10-30 17:14:30.216098: train_loss -0.9865 +2025-10-30 17:14:30.219715: val_loss -0.8957 +2025-10-30 17:14:30.221323: Pseudo dice [np.float32(0.9826), np.float32(0.9895), np.float32(0.9947), np.float32(0.8023)] +2025-10-30 17:14:30.223538: Epoch time: 20.59 s +2025-10-30 17:14:31.311071: +2025-10-30 17:14:31.312929: Epoch 373 +2025-10-30 17:14:31.314671: Current learning rate: 0.00657 +2025-10-30 17:14:51.892131: train_loss -0.9867 +2025-10-30 17:14:51.894504: val_loss -0.904 +2025-10-30 17:14:51.895964: Pseudo dice [np.float32(0.9821), np.float32(0.99), np.float32(0.9955), np.float32(0.8272)] +2025-10-30 17:14:51.897442: Epoch time: 20.58 s +2025-10-30 17:14:53.007042: +2025-10-30 17:14:53.008952: Epoch 374 +2025-10-30 17:14:53.010685: Current learning rate: 0.00656 +2025-10-30 17:15:13.883183: train_loss -0.9873 +2025-10-30 17:15:13.885434: val_loss -0.8917 +2025-10-30 17:15:13.887079: Pseudo dice [np.float32(0.9827), np.float32(0.9906), np.float32(0.9952), np.float32(0.7985)] +2025-10-30 17:15:13.888829: Epoch time: 20.88 s +2025-10-30 17:15:15.204059: +2025-10-30 17:15:15.205989: Epoch 375 +2025-10-30 17:15:15.207818: Current learning rate: 0.00655 +2025-10-30 17:15:34.300795: train_loss -0.9875 +2025-10-30 17:15:34.303748: val_loss -0.9076 +2025-10-30 17:15:34.305336: Pseudo dice [np.float32(0.9823), np.float32(0.9909), np.float32(0.9953), np.float32(0.8368)] +2025-10-30 17:15:34.306741: Epoch time: 19.1 s +2025-10-30 17:15:35.336042: +2025-10-30 17:15:35.338044: Epoch 376 +2025-10-30 17:15:35.339581: Current learning rate: 0.00654 +2025-10-30 17:15:55.628815: train_loss -0.9867 +2025-10-30 17:15:55.631104: val_loss -0.9037 +2025-10-30 17:15:55.634069: Pseudo dice [np.float32(0.9831), np.float32(0.9899), np.float32(0.9952), np.float32(0.8278)] +2025-10-30 17:15:55.636597: Epoch time: 20.29 s +2025-10-30 17:15:56.648603: +2025-10-30 17:15:56.650839: Epoch 377 +2025-10-30 17:15:56.652547: Current learning rate: 0.00653 +2025-10-30 17:16:16.986173: train_loss -0.983 +2025-10-30 17:16:16.991228: val_loss -0.8987 +2025-10-30 17:16:16.993418: Pseudo dice [np.float32(0.9832), np.float32(0.9856), np.float32(0.9923), np.float32(0.8038)] +2025-10-30 17:16:16.995012: Epoch time: 20.34 s +2025-10-30 17:16:18.011563: +2025-10-30 17:16:18.013391: Epoch 378 +2025-10-30 17:16:18.015068: Current learning rate: 0.00652 +2025-10-30 17:16:38.966451: train_loss -0.9849 +2025-10-30 17:16:38.969697: val_loss -0.9042 +2025-10-30 17:16:38.971255: Pseudo dice [np.float32(0.9836), np.float32(0.9902), np.float32(0.9946), np.float32(0.8203)] +2025-10-30 17:16:38.972672: Epoch time: 20.96 s +2025-10-30 17:16:40.143242: +2025-10-30 17:16:40.145885: Epoch 379 +2025-10-30 17:16:40.149112: Current learning rate: 0.00651 +2025-10-30 17:17:00.663723: train_loss -0.9861 +2025-10-30 17:17:00.665949: val_loss -0.9055 +2025-10-30 17:17:00.667394: Pseudo dice [np.float32(0.9823), np.float32(0.9899), np.float32(0.9955), np.float32(0.8339)] +2025-10-30 17:17:00.669223: Epoch time: 20.52 s +2025-10-30 17:17:01.815932: +2025-10-30 17:17:01.818000: Epoch 380 +2025-10-30 17:17:01.819806: Current learning rate: 0.0065 +2025-10-30 17:17:22.260662: train_loss -0.9868 +2025-10-30 17:17:22.262585: val_loss -0.8908 +2025-10-30 17:17:22.264017: Pseudo dice [np.float32(0.9845), np.float32(0.99), np.float32(0.9942), np.float32(0.796)] +2025-10-30 17:17:22.265357: Epoch time: 20.45 s +2025-10-30 17:17:23.345748: +2025-10-30 17:17:23.347665: Epoch 381 +2025-10-30 17:17:23.349496: Current learning rate: 0.00649 +2025-10-30 17:17:43.074270: train_loss -0.987 +2025-10-30 17:17:43.077041: val_loss -0.907 +2025-10-30 17:17:43.078857: Pseudo dice [np.float32(0.9831), np.float32(0.9911), np.float32(0.9953), np.float32(0.8309)] +2025-10-30 17:17:43.080823: Epoch time: 19.73 s +2025-10-30 17:17:44.095851: +2025-10-30 17:17:44.097641: Epoch 382 +2025-10-30 17:17:44.099844: Current learning rate: 0.00648 +2025-10-30 17:18:03.775255: train_loss -0.9874 +2025-10-30 17:18:03.777736: val_loss -0.9001 +2025-10-30 17:18:03.779816: Pseudo dice [np.float32(0.9828), np.float32(0.9905), np.float32(0.9953), np.float32(0.8157)] +2025-10-30 17:18:03.781910: Epoch time: 19.68 s +2025-10-30 17:18:05.054068: +2025-10-30 17:18:05.056003: Epoch 383 +2025-10-30 17:18:05.057819: Current learning rate: 0.00648 +2025-10-30 17:18:25.601321: train_loss -0.9869 +2025-10-30 17:18:25.603566: val_loss -0.9056 +2025-10-30 17:18:25.605182: Pseudo dice [np.float32(0.9819), np.float32(0.9894), np.float32(0.9955), np.float32(0.8372)] +2025-10-30 17:18:25.606853: Epoch time: 20.55 s +2025-10-30 17:18:27.174054: +2025-10-30 17:18:27.175653: Epoch 384 +2025-10-30 17:18:27.177554: Current learning rate: 0.00647 +2025-10-30 17:18:47.650975: train_loss -0.9873 +2025-10-30 17:18:47.653801: val_loss -0.8943 +2025-10-30 17:18:47.655419: Pseudo dice [np.float32(0.9825), np.float32(0.9904), np.float32(0.9949), np.float32(0.805)] +2025-10-30 17:18:47.656937: Epoch time: 20.48 s +2025-10-30 17:18:48.869972: +2025-10-30 17:18:48.871573: Epoch 385 +2025-10-30 17:18:48.873093: Current learning rate: 0.00646 +2025-10-30 17:19:09.185139: train_loss -0.9884 +2025-10-30 17:19:09.187662: val_loss -0.9062 +2025-10-30 17:19:09.190235: Pseudo dice [np.float32(0.9837), np.float32(0.9906), np.float32(0.9949), np.float32(0.8285)] +2025-10-30 17:19:09.192038: Epoch time: 20.32 s +2025-10-30 17:19:10.409067: +2025-10-30 17:19:10.411016: Epoch 386 +2025-10-30 17:19:10.412846: Current learning rate: 0.00645 +2025-10-30 17:19:31.187183: train_loss -0.9875 +2025-10-30 17:19:31.190202: val_loss -0.8957 +2025-10-30 17:19:31.191950: Pseudo dice [np.float32(0.9828), np.float32(0.9902), np.float32(0.9952), np.float32(0.813)] +2025-10-30 17:19:31.193599: Epoch time: 20.78 s +2025-10-30 17:19:32.487651: +2025-10-30 17:19:32.489984: Epoch 387 +2025-10-30 17:19:32.491577: Current learning rate: 0.00644 +2025-10-30 17:19:53.037290: train_loss -0.9885 +2025-10-30 17:19:53.040937: val_loss -0.8954 +2025-10-30 17:19:53.042619: Pseudo dice [np.float32(0.9842), np.float32(0.9905), np.float32(0.9949), np.float32(0.8067)] +2025-10-30 17:19:53.044561: Epoch time: 20.55 s +2025-10-30 17:19:54.139476: +2025-10-30 17:19:54.141384: Epoch 388 +2025-10-30 17:19:54.143686: Current learning rate: 0.00643 +2025-10-30 17:20:13.612324: train_loss -0.9891 +2025-10-30 17:20:13.614205: val_loss -0.9056 +2025-10-30 17:20:13.616049: Pseudo dice [np.float32(0.9824), np.float32(0.9903), np.float32(0.9957), np.float32(0.8342)] +2025-10-30 17:20:13.617799: Epoch time: 19.47 s +2025-10-30 17:20:14.814717: +2025-10-30 17:20:14.816562: Epoch 389 +2025-10-30 17:20:14.818059: Current learning rate: 0.00642 +2025-10-30 17:20:34.937457: train_loss -0.9887 +2025-10-30 17:20:34.939528: val_loss -0.9021 +2025-10-30 17:20:34.941001: Pseudo dice [np.float32(0.9845), np.float32(0.991), np.float32(0.995), np.float32(0.8184)] +2025-10-30 17:20:34.942523: Epoch time: 20.12 s +2025-10-30 17:20:35.908326: +2025-10-30 17:20:35.911319: Epoch 390 +2025-10-30 17:20:35.913786: Current learning rate: 0.00641 +2025-10-30 17:20:56.774201: train_loss -0.9887 +2025-10-30 17:20:56.776985: val_loss -0.8995 +2025-10-30 17:20:56.778639: Pseudo dice [np.float32(0.9835), np.float32(0.9906), np.float32(0.995), np.float32(0.8205)] +2025-10-30 17:20:56.780413: Epoch time: 20.87 s +2025-10-30 17:20:58.012741: +2025-10-30 17:20:58.015226: Epoch 391 +2025-10-30 17:20:58.018133: Current learning rate: 0.0064 +2025-10-30 17:21:18.550664: train_loss -0.9873 +2025-10-30 17:21:18.552942: val_loss -0.9015 +2025-10-30 17:21:18.554641: Pseudo dice [np.float32(0.982), np.float32(0.9903), np.float32(0.9953), np.float32(0.8227)] +2025-10-30 17:21:18.556209: Epoch time: 20.54 s +2025-10-30 17:21:19.619375: +2025-10-30 17:21:19.622364: Epoch 392 +2025-10-30 17:21:19.624644: Current learning rate: 0.00639 +2025-10-30 17:21:40.139628: train_loss -0.9877 +2025-10-30 17:21:40.141417: val_loss -0.8964 +2025-10-30 17:21:40.143106: Pseudo dice [np.float32(0.9823), np.float32(0.9904), np.float32(0.995), np.float32(0.8085)] +2025-10-30 17:21:40.144438: Epoch time: 20.52 s +2025-10-30 17:21:41.163152: +2025-10-30 17:21:41.165185: Epoch 393 +2025-10-30 17:21:41.167037: Current learning rate: 0.00638 +2025-10-30 17:22:01.761216: train_loss -0.9889 +2025-10-30 17:22:01.763934: val_loss -0.8946 +2025-10-30 17:22:01.765440: Pseudo dice [np.float32(0.9826), np.float32(0.9899), np.float32(0.9947), np.float32(0.8104)] +2025-10-30 17:22:01.767053: Epoch time: 20.6 s +2025-10-30 17:22:02.809283: +2025-10-30 17:22:02.812281: Epoch 394 +2025-10-30 17:22:02.814956: Current learning rate: 0.00637 +2025-10-30 17:22:22.331160: train_loss -0.9886 +2025-10-30 17:22:22.333844: val_loss -0.9094 +2025-10-30 17:22:22.335898: Pseudo dice [np.float32(0.9829), np.float32(0.9901), np.float32(0.9952), np.float32(0.8421)] +2025-10-30 17:22:22.337909: Epoch time: 19.52 s +2025-10-30 17:22:23.789920: +2025-10-30 17:22:23.791812: Epoch 395 +2025-10-30 17:22:23.793711: Current learning rate: 0.00636 +2025-10-30 17:22:44.198774: train_loss -0.9885 +2025-10-30 17:22:44.201627: val_loss -0.8985 +2025-10-30 17:22:44.203559: Pseudo dice [np.float32(0.9838), np.float32(0.9907), np.float32(0.9951), np.float32(0.8123)] +2025-10-30 17:22:44.205792: Epoch time: 20.41 s +2025-10-30 17:22:45.227209: +2025-10-30 17:22:45.229054: Epoch 396 +2025-10-30 17:22:45.231539: Current learning rate: 0.00635 +2025-10-30 17:23:04.800328: train_loss -0.9878 +2025-10-30 17:23:04.804712: val_loss -0.8936 +2025-10-30 17:23:04.806845: Pseudo dice [np.float32(0.9826), np.float32(0.9903), np.float32(0.9947), np.float32(0.8093)] +2025-10-30 17:23:04.809148: Epoch time: 19.57 s +2025-10-30 17:23:05.957351: +2025-10-30 17:23:05.959948: Epoch 397 +2025-10-30 17:23:05.961718: Current learning rate: 0.00634 +2025-10-30 17:23:26.897629: train_loss -0.9882 +2025-10-30 17:23:26.900358: val_loss -0.9012 +2025-10-30 17:23:26.902133: Pseudo dice [np.float32(0.9833), np.float32(0.991), np.float32(0.9952), np.float32(0.8277)] +2025-10-30 17:23:26.903924: Epoch time: 20.94 s +2025-10-30 17:23:27.912737: +2025-10-30 17:23:27.914736: Epoch 398 +2025-10-30 17:23:27.916918: Current learning rate: 0.00633 +2025-10-30 17:23:48.119443: train_loss -0.9883 +2025-10-30 17:23:48.122214: val_loss -0.901 +2025-10-30 17:23:48.123956: Pseudo dice [np.float32(0.984), np.float32(0.9911), np.float32(0.995), np.float32(0.8155)] +2025-10-30 17:23:48.125688: Epoch time: 20.21 s +2025-10-30 17:23:49.364085: +2025-10-30 17:23:49.365986: Epoch 399 +2025-10-30 17:23:49.367967: Current learning rate: 0.00632 +2025-10-30 17:24:09.641738: train_loss -0.9893 +2025-10-30 17:24:09.646306: val_loss -0.8924 +2025-10-30 17:24:09.647848: Pseudo dice [np.float32(0.9831), np.float32(0.991), np.float32(0.9947), np.float32(0.7996)] +2025-10-30 17:24:09.649901: Epoch time: 20.28 s +2025-10-30 17:24:11.780386: +2025-10-30 17:24:11.782513: Epoch 400 +2025-10-30 17:24:11.784488: Current learning rate: 0.00631 +2025-10-30 17:24:31.943136: train_loss -0.9884 +2025-10-30 17:24:31.945316: val_loss -0.898 +2025-10-30 17:24:31.947079: Pseudo dice [np.float32(0.9836), np.float32(0.9913), np.float32(0.9953), np.float32(0.809)] +2025-10-30 17:24:31.948898: Epoch time: 20.16 s +2025-10-30 17:24:33.187982: +2025-10-30 17:24:33.192572: Epoch 401 +2025-10-30 17:24:33.194361: Current learning rate: 0.0063 +2025-10-30 17:24:52.651410: train_loss -0.9885 +2025-10-30 17:24:52.653939: val_loss -0.9036 +2025-10-30 17:24:52.656596: Pseudo dice [np.float32(0.9838), np.float32(0.991), np.float32(0.9952), np.float32(0.8249)] +2025-10-30 17:24:52.659224: Epoch time: 19.47 s +2025-10-30 17:24:53.901337: +2025-10-30 17:24:53.903390: Epoch 402 +2025-10-30 17:24:53.905315: Current learning rate: 0.0063 +2025-10-30 17:25:13.956626: train_loss -0.989 +2025-10-30 17:25:13.959482: val_loss -0.8973 +2025-10-30 17:25:13.961669: Pseudo dice [np.float32(0.9841), np.float32(0.9905), np.float32(0.9946), np.float32(0.8107)] +2025-10-30 17:25:13.963340: Epoch time: 20.06 s +2025-10-30 17:25:15.103866: +2025-10-30 17:25:15.108604: Epoch 403 +2025-10-30 17:25:15.111650: Current learning rate: 0.00629 +2025-10-30 17:25:35.122282: train_loss -0.9888 +2025-10-30 17:25:35.124327: val_loss -0.9088 +2025-10-30 17:25:35.125904: Pseudo dice [np.float32(0.9829), np.float32(0.9911), np.float32(0.9956), np.float32(0.8402)] +2025-10-30 17:25:35.127489: Epoch time: 20.02 s +2025-10-30 17:25:36.197454: +2025-10-30 17:25:36.199660: Epoch 404 +2025-10-30 17:25:36.201574: Current learning rate: 0.00628 +2025-10-30 17:25:56.808428: train_loss -0.9885 +2025-10-30 17:25:56.810774: val_loss -0.8977 +2025-10-30 17:25:56.812506: Pseudo dice [np.float32(0.9832), np.float32(0.9908), np.float32(0.995), np.float32(0.8151)] +2025-10-30 17:25:56.814149: Epoch time: 20.61 s +2025-10-30 17:25:57.830786: +2025-10-30 17:25:57.832556: Epoch 405 +2025-10-30 17:25:57.834067: Current learning rate: 0.00627 +2025-10-30 17:26:18.216611: train_loss -0.9894 +2025-10-30 17:26:18.219355: val_loss -0.885 +2025-10-30 17:26:18.224507: Pseudo dice [np.float32(0.9821), np.float32(0.9905), np.float32(0.9942), np.float32(0.7821)] +2025-10-30 17:26:18.226153: Epoch time: 20.39 s +2025-10-30 17:26:19.418190: +2025-10-30 17:26:19.419973: Epoch 406 +2025-10-30 17:26:19.421524: Current learning rate: 0.00626 +2025-10-30 17:26:40.142619: train_loss -0.9897 +2025-10-30 17:26:40.144708: val_loss -0.9025 +2025-10-30 17:26:40.146078: Pseudo dice [np.float32(0.9822), np.float32(0.9905), np.float32(0.9954), np.float32(0.8243)] +2025-10-30 17:26:40.147562: Epoch time: 20.73 s +2025-10-30 17:26:42.448097: +2025-10-30 17:26:42.450058: Epoch 407 +2025-10-30 17:26:42.452171: Current learning rate: 0.00625 +2025-10-30 17:27:01.751414: train_loss -0.9889 +2025-10-30 17:27:01.753639: val_loss -0.891 +2025-10-30 17:27:01.756055: Pseudo dice [np.float32(0.9817), np.float32(0.99), np.float32(0.995), np.float32(0.801)] +2025-10-30 17:27:01.758226: Epoch time: 19.31 s +2025-10-30 17:27:02.901717: +2025-10-30 17:27:02.903786: Epoch 408 +2025-10-30 17:27:02.905617: Current learning rate: 0.00624 +2025-10-30 17:27:23.427191: train_loss -0.9884 +2025-10-30 17:27:23.430691: val_loss -0.9005 +2025-10-30 17:27:23.432866: Pseudo dice [np.float32(0.9821), np.float32(0.99), np.float32(0.9952), np.float32(0.8213)] +2025-10-30 17:27:23.434664: Epoch time: 20.53 s +2025-10-30 17:27:24.585662: +2025-10-30 17:27:24.587355: Epoch 409 +2025-10-30 17:27:24.589145: Current learning rate: 0.00623 +2025-10-30 17:27:43.812439: train_loss -0.9888 +2025-10-30 17:27:43.815353: val_loss -0.8945 +2025-10-30 17:27:43.816957: Pseudo dice [np.float32(0.9845), np.float32(0.9917), np.float32(0.9949), np.float32(0.7991)] +2025-10-30 17:27:43.818510: Epoch time: 19.23 s +2025-10-30 17:27:45.047973: +2025-10-30 17:27:45.051484: Epoch 410 +2025-10-30 17:27:45.054001: Current learning rate: 0.00622 +2025-10-30 17:28:05.755500: train_loss -0.9882 +2025-10-30 17:28:05.758055: val_loss -0.9006 +2025-10-30 17:28:05.759960: Pseudo dice [np.float32(0.9842), np.float32(0.9903), np.float32(0.9948), np.float32(0.8152)] +2025-10-30 17:28:05.761615: Epoch time: 20.71 s +2025-10-30 17:28:06.979503: +2025-10-30 17:28:06.981524: Epoch 411 +2025-10-30 17:28:06.983111: Current learning rate: 0.00621 +2025-10-30 17:28:27.781005: train_loss -0.9877 +2025-10-30 17:28:27.784451: val_loss -0.9022 +2025-10-30 17:28:27.786304: Pseudo dice [np.float32(0.983), np.float32(0.9909), np.float32(0.9946), np.float32(0.8152)] +2025-10-30 17:28:27.788140: Epoch time: 20.8 s +2025-10-30 17:28:28.918287: +2025-10-30 17:28:28.920251: Epoch 412 +2025-10-30 17:28:28.922068: Current learning rate: 0.0062 +2025-10-30 17:28:49.486161: train_loss -0.9887 +2025-10-30 17:28:49.489404: val_loss -0.8967 +2025-10-30 17:28:49.492213: Pseudo dice [np.float32(0.9814), np.float32(0.9899), np.float32(0.9947), np.float32(0.802)] +2025-10-30 17:28:49.494797: Epoch time: 20.57 s +2025-10-30 17:28:50.566985: +2025-10-30 17:28:50.568970: Epoch 413 +2025-10-30 17:28:50.571281: Current learning rate: 0.00619 +2025-10-30 17:29:09.862290: train_loss -0.9888 +2025-10-30 17:29:09.864562: val_loss -0.9021 +2025-10-30 17:29:09.866284: Pseudo dice [np.float32(0.984), np.float32(0.9908), np.float32(0.995), np.float32(0.82)] +2025-10-30 17:29:09.868257: Epoch time: 19.3 s +2025-10-30 17:29:10.862590: +2025-10-30 17:29:10.864259: Epoch 414 +2025-10-30 17:29:10.865831: Current learning rate: 0.00618 +2025-10-30 17:29:31.201703: train_loss -0.9885 +2025-10-30 17:29:31.204827: val_loss -0.8917 +2025-10-30 17:29:31.206705: Pseudo dice [np.float32(0.9819), np.float32(0.991), np.float32(0.995), np.float32(0.8041)] +2025-10-30 17:29:31.208664: Epoch time: 20.34 s +2025-10-30 17:29:32.228504: +2025-10-30 17:29:32.230491: Epoch 415 +2025-10-30 17:29:32.232248: Current learning rate: 0.00617 +2025-10-30 17:29:52.557841: train_loss -0.9889 +2025-10-30 17:29:52.559774: val_loss -0.904 +2025-10-30 17:29:52.561513: Pseudo dice [np.float32(0.9835), np.float32(0.9912), np.float32(0.9951), np.float32(0.8226)] +2025-10-30 17:29:52.563219: Epoch time: 20.33 s +2025-10-30 17:29:53.703576: +2025-10-30 17:29:53.705463: Epoch 416 +2025-10-30 17:29:53.707280: Current learning rate: 0.00616 +2025-10-30 17:30:13.075865: train_loss -0.9896 +2025-10-30 17:30:13.078444: val_loss -0.9054 +2025-10-30 17:30:13.079909: Pseudo dice [np.float32(0.9839), np.float32(0.991), np.float32(0.9952), np.float32(0.8257)] +2025-10-30 17:30:13.081439: Epoch time: 19.37 s +2025-10-30 17:30:14.450974: +2025-10-30 17:30:14.453115: Epoch 417 +2025-10-30 17:30:14.455151: Current learning rate: 0.00615 +2025-10-30 17:30:35.127526: train_loss -0.9887 +2025-10-30 17:30:35.130368: val_loss -0.897 +2025-10-30 17:30:35.131965: Pseudo dice [np.float32(0.9839), np.float32(0.9914), np.float32(0.995), np.float32(0.8106)] +2025-10-30 17:30:35.133594: Epoch time: 20.68 s +2025-10-30 17:30:36.156341: +2025-10-30 17:30:36.158085: Epoch 418 +2025-10-30 17:30:36.159810: Current learning rate: 0.00614 +2025-10-30 17:30:56.890182: train_loss -0.9889 +2025-10-30 17:30:56.892566: val_loss -0.891 +2025-10-30 17:30:56.894442: Pseudo dice [np.float32(0.9816), np.float32(0.9896), np.float32(0.9948), np.float32(0.8068)] +2025-10-30 17:30:56.896964: Epoch time: 20.74 s +2025-10-30 17:30:58.713541: +2025-10-30 17:30:58.715560: Epoch 419 +2025-10-30 17:30:58.717290: Current learning rate: 0.00613 +2025-10-30 17:31:19.027296: train_loss -0.9883 +2025-10-30 17:31:19.030154: val_loss -0.9031 +2025-10-30 17:31:19.032376: Pseudo dice [np.float32(0.9843), np.float32(0.991), np.float32(0.9948), np.float32(0.8211)] +2025-10-30 17:31:19.034377: Epoch time: 20.32 s +2025-10-30 17:31:20.119140: +2025-10-30 17:31:20.121180: Epoch 420 +2025-10-30 17:31:20.122929: Current learning rate: 0.00612 +2025-10-30 17:31:39.626364: train_loss -0.9867 +2025-10-30 17:31:39.629780: val_loss -0.9066 +2025-10-30 17:31:39.631486: Pseudo dice [np.float32(0.9844), np.float32(0.9913), np.float32(0.995), np.float32(0.8236)] +2025-10-30 17:31:39.633401: Epoch time: 19.51 s +2025-10-30 17:31:40.708601: +2025-10-30 17:31:40.710493: Epoch 421 +2025-10-30 17:31:40.712359: Current learning rate: 0.00612 +2025-10-30 17:32:00.966575: train_loss -0.9868 +2025-10-30 17:32:00.968722: val_loss -0.896 +2025-10-30 17:32:00.970195: Pseudo dice [np.float32(0.9847), np.float32(0.9914), np.float32(0.9946), np.float32(0.8016)] +2025-10-30 17:32:00.971809: Epoch time: 20.26 s +2025-10-30 17:32:02.173574: +2025-10-30 17:32:02.175816: Epoch 422 +2025-10-30 17:32:02.181897: Current learning rate: 0.00611 +2025-10-30 17:32:22.445915: train_loss -0.9868 +2025-10-30 17:32:22.448317: val_loss -0.9004 +2025-10-30 17:32:22.450302: Pseudo dice [np.float32(0.9844), np.float32(0.9906), np.float32(0.9946), np.float32(0.8193)] +2025-10-30 17:32:22.452292: Epoch time: 20.27 s +2025-10-30 17:32:23.659405: +2025-10-30 17:32:23.661392: Epoch 423 +2025-10-30 17:32:23.663327: Current learning rate: 0.0061 +2025-10-30 17:32:42.950375: train_loss -0.9871 +2025-10-30 17:32:42.954049: val_loss -0.8929 +2025-10-30 17:32:42.956846: Pseudo dice [np.float32(0.983), np.float32(0.9899), np.float32(0.9944), np.float32(0.8039)] +2025-10-30 17:32:42.959042: Epoch time: 19.29 s +2025-10-30 17:32:43.922931: +2025-10-30 17:32:43.924844: Epoch 424 +2025-10-30 17:32:43.926425: Current learning rate: 0.00609 +2025-10-30 17:33:04.258438: train_loss -0.9884 +2025-10-30 17:33:04.262339: val_loss -0.9071 +2025-10-30 17:33:04.267369: Pseudo dice [np.float32(0.984), np.float32(0.9902), np.float32(0.9949), np.float32(0.8273)] +2025-10-30 17:33:04.271481: Epoch time: 20.34 s +2025-10-30 17:33:05.544522: +2025-10-30 17:33:05.552977: Epoch 425 +2025-10-30 17:33:05.554866: Current learning rate: 0.00608 +2025-10-30 17:33:25.790153: train_loss -0.9879 +2025-10-30 17:33:25.792682: val_loss -0.9011 +2025-10-30 17:33:25.794478: Pseudo dice [np.float32(0.9822), np.float32(0.9906), np.float32(0.9951), np.float32(0.8221)] +2025-10-30 17:33:25.796479: Epoch time: 20.25 s +2025-10-30 17:33:26.857356: +2025-10-30 17:33:26.862251: Epoch 426 +2025-10-30 17:33:26.863774: Current learning rate: 0.00607 +2025-10-30 17:33:46.013625: train_loss -0.9881 +2025-10-30 17:33:46.016595: val_loss -0.9021 +2025-10-30 17:33:46.018257: Pseudo dice [np.float32(0.9839), np.float32(0.9913), np.float32(0.9952), np.float32(0.8142)] +2025-10-30 17:33:46.019839: Epoch time: 19.16 s +2025-10-30 17:33:47.170753: +2025-10-30 17:33:47.172553: Epoch 427 +2025-10-30 17:33:47.174127: Current learning rate: 0.00606 +2025-10-30 17:34:07.414788: train_loss -0.9885 +2025-10-30 17:34:07.421398: val_loss -0.8917 +2025-10-30 17:34:07.423646: Pseudo dice [np.float32(0.9809), np.float32(0.9896), np.float32(0.9949), np.float32(0.7891)] +2025-10-30 17:34:07.425263: Epoch time: 20.25 s +2025-10-30 17:34:08.612039: +2025-10-30 17:34:08.614469: Epoch 428 +2025-10-30 17:34:08.616371: Current learning rate: 0.00605 +2025-10-30 17:34:28.919513: train_loss -0.989 +2025-10-30 17:34:28.922450: val_loss -0.8877 +2025-10-30 17:34:28.924931: Pseudo dice [np.float32(0.9834), np.float32(0.9908), np.float32(0.9944), np.float32(0.7889)] +2025-10-30 17:34:28.927190: Epoch time: 20.31 s +2025-10-30 17:34:30.067136: +2025-10-30 17:34:30.068823: Epoch 429 +2025-10-30 17:34:30.070364: Current learning rate: 0.00604 +2025-10-30 17:34:50.105130: train_loss -0.9885 +2025-10-30 17:34:50.107853: val_loss -0.9029 +2025-10-30 17:34:50.109447: Pseudo dice [np.float32(0.9829), np.float32(0.9917), np.float32(0.995), np.float32(0.8257)] +2025-10-30 17:34:50.111882: Epoch time: 20.04 s +2025-10-30 17:34:51.138714: +2025-10-30 17:34:51.140560: Epoch 430 +2025-10-30 17:34:51.142164: Current learning rate: 0.00603 +2025-10-30 17:35:10.635530: train_loss -0.989 +2025-10-30 17:35:10.637661: val_loss -0.9009 +2025-10-30 17:35:10.639463: Pseudo dice [np.float32(0.9835), np.float32(0.9909), np.float32(0.9951), np.float32(0.82)] +2025-10-30 17:35:10.641219: Epoch time: 19.5 s +2025-10-30 17:35:11.876898: +2025-10-30 17:35:11.878968: Epoch 431 +2025-10-30 17:35:11.880629: Current learning rate: 0.00602 +2025-10-30 17:35:32.415308: train_loss -0.9894 +2025-10-30 17:35:32.417559: val_loss -0.9007 +2025-10-30 17:35:32.419321: Pseudo dice [np.float32(0.9825), np.float32(0.9899), np.float32(0.9951), np.float32(0.8197)] +2025-10-30 17:35:32.421522: Epoch time: 20.54 s +2025-10-30 17:35:33.942257: +2025-10-30 17:35:33.948000: Epoch 432 +2025-10-30 17:35:33.950124: Current learning rate: 0.00601 +2025-10-30 17:35:54.465773: train_loss -0.9898 +2025-10-30 17:35:54.469745: val_loss -0.9029 +2025-10-30 17:35:54.471408: Pseudo dice [np.float32(0.9833), np.float32(0.9897), np.float32(0.9953), np.float32(0.8325)] +2025-10-30 17:35:54.473238: Epoch time: 20.52 s +2025-10-30 17:35:55.620527: +2025-10-30 17:35:55.622487: Epoch 433 +2025-10-30 17:35:55.624336: Current learning rate: 0.006 +2025-10-30 17:36:15.240191: train_loss -0.9898 +2025-10-30 17:36:15.242804: val_loss -0.903 +2025-10-30 17:36:15.244832: Pseudo dice [np.float32(0.9832), np.float32(0.9911), np.float32(0.995), np.float32(0.8272)] +2025-10-30 17:36:15.246612: Epoch time: 19.62 s +2025-10-30 17:36:16.418619: +2025-10-30 17:36:16.420794: Epoch 434 +2025-10-30 17:36:16.423093: Current learning rate: 0.00599 +2025-10-30 17:36:37.034548: train_loss -0.9884 +2025-10-30 17:36:37.037240: val_loss -0.898 +2025-10-30 17:36:37.039471: Pseudo dice [np.float32(0.9823), np.float32(0.9896), np.float32(0.9951), np.float32(0.8231)] +2025-10-30 17:36:37.041506: Epoch time: 20.62 s +2025-10-30 17:36:38.085258: +2025-10-30 17:36:38.087238: Epoch 435 +2025-10-30 17:36:38.088849: Current learning rate: 0.00598 +2025-10-30 17:36:58.648932: train_loss -0.9894 +2025-10-30 17:36:58.655032: val_loss -0.8907 +2025-10-30 17:36:58.656866: Pseudo dice [np.float32(0.9827), np.float32(0.991), np.float32(0.995), np.float32(0.8025)] +2025-10-30 17:36:58.658358: Epoch time: 20.57 s +2025-10-30 17:36:59.671271: +2025-10-30 17:36:59.673176: Epoch 436 +2025-10-30 17:36:59.675475: Current learning rate: 0.00597 +2025-10-30 17:37:18.660085: train_loss -0.9873 +2025-10-30 17:37:18.662274: val_loss -0.9056 +2025-10-30 17:37:18.664167: Pseudo dice [np.float32(0.9825), np.float32(0.9905), np.float32(0.9949), np.float32(0.8277)] +2025-10-30 17:37:18.665815: Epoch time: 18.99 s +2025-10-30 17:37:19.886991: +2025-10-30 17:37:19.889311: Epoch 437 +2025-10-30 17:37:19.893414: Current learning rate: 0.00596 +2025-10-30 17:37:38.064157: train_loss -0.9879 +2025-10-30 17:37:38.065858: val_loss -0.9037 +2025-10-30 17:37:38.067392: Pseudo dice [np.float32(0.9837), np.float32(0.9915), np.float32(0.9951), np.float32(0.8197)] +2025-10-30 17:37:38.068887: Epoch time: 18.18 s +2025-10-30 17:37:39.250560: +2025-10-30 17:37:39.252421: Epoch 438 +2025-10-30 17:37:39.254095: Current learning rate: 0.00595 +2025-10-30 17:37:59.556466: train_loss -0.9892 +2025-10-30 17:37:59.559356: val_loss -0.9089 +2025-10-30 17:37:59.561044: Pseudo dice [np.float32(0.9834), np.float32(0.9906), np.float32(0.995), np.float32(0.8371)] +2025-10-30 17:37:59.562599: Epoch time: 20.31 s +2025-10-30 17:38:00.775630: +2025-10-30 17:38:00.777302: Epoch 439 +2025-10-30 17:38:00.778883: Current learning rate: 0.00594 +2025-10-30 17:38:20.018615: train_loss -0.9885 +2025-10-30 17:38:20.021228: val_loss -0.8979 +2025-10-30 17:38:20.022964: Pseudo dice [np.float32(0.9835), np.float32(0.9912), np.float32(0.9949), np.float32(0.8177)] +2025-10-30 17:38:20.025075: Epoch time: 19.24 s +2025-10-30 17:38:21.082030: +2025-10-30 17:38:21.084466: Epoch 440 +2025-10-30 17:38:21.086316: Current learning rate: 0.00593 +2025-10-30 17:38:41.610264: train_loss -0.989 +2025-10-30 17:38:41.612536: val_loss -0.8995 +2025-10-30 17:38:41.614621: Pseudo dice [np.float32(0.9837), np.float32(0.9908), np.float32(0.9946), np.float32(0.8169)] +2025-10-30 17:38:41.616450: Epoch time: 20.53 s +2025-10-30 17:38:42.816508: +2025-10-30 17:38:42.818475: Epoch 441 +2025-10-30 17:38:42.820218: Current learning rate: 0.00592 +2025-10-30 17:39:03.111321: train_loss -0.9882 +2025-10-30 17:39:03.116315: val_loss -0.8992 +2025-10-30 17:39:03.117878: Pseudo dice [np.float32(0.9833), np.float32(0.9907), np.float32(0.9948), np.float32(0.8176)] +2025-10-30 17:39:03.119537: Epoch time: 20.3 s +2025-10-30 17:39:04.386693: +2025-10-30 17:39:04.388677: Epoch 442 +2025-10-30 17:39:04.390318: Current learning rate: 0.00592 +2025-10-30 17:39:25.072755: train_loss -0.9883 +2025-10-30 17:39:25.075463: val_loss -0.8985 +2025-10-30 17:39:25.080213: Pseudo dice [np.float32(0.9821), np.float32(0.9909), np.float32(0.9953), np.float32(0.8101)] +2025-10-30 17:39:25.082135: Epoch time: 20.69 s +2025-10-30 17:39:26.331763: +2025-10-30 17:39:26.333981: Epoch 443 +2025-10-30 17:39:26.335642: Current learning rate: 0.00591 +2025-10-30 17:39:47.468353: train_loss -0.9878 +2025-10-30 17:39:47.472913: val_loss -0.8958 +2025-10-30 17:39:47.474948: Pseudo dice [np.float32(0.9828), np.float32(0.9903), np.float32(0.9947), np.float32(0.8108)] +2025-10-30 17:39:47.476989: Epoch time: 21.14 s +2025-10-30 17:39:48.666579: +2025-10-30 17:39:48.668941: Epoch 444 +2025-10-30 17:39:48.670705: Current learning rate: 0.0059 +2025-10-30 17:40:08.342099: train_loss -0.9835 +2025-10-30 17:40:08.345025: val_loss -0.9079 +2025-10-30 17:40:08.347149: Pseudo dice [np.float32(0.9833), np.float32(0.9907), np.float32(0.9949), np.float32(0.8228)] +2025-10-30 17:40:08.349504: Epoch time: 19.68 s +2025-10-30 17:40:09.957336: +2025-10-30 17:40:09.959806: Epoch 445 +2025-10-30 17:40:09.961780: Current learning rate: 0.00589 +2025-10-30 17:40:30.005997: train_loss -0.9729 +2025-10-30 17:40:30.008930: val_loss -0.8801 +2025-10-30 17:40:30.014066: Pseudo dice [np.float32(0.9833), np.float32(0.976), np.float32(0.9886), np.float32(0.8015)] +2025-10-30 17:40:30.015920: Epoch time: 20.05 s +2025-10-30 17:40:31.193506: +2025-10-30 17:40:31.195717: Epoch 446 +2025-10-30 17:40:31.197764: Current learning rate: 0.00588 +2025-10-30 17:40:50.711325: train_loss -0.9723 +2025-10-30 17:40:50.713428: val_loss -0.9078 +2025-10-30 17:40:50.715382: Pseudo dice [np.float32(0.9841), np.float32(0.9889), np.float32(0.9941), np.float32(0.8164)] +2025-10-30 17:40:50.717193: Epoch time: 19.52 s +2025-10-30 17:40:51.862597: +2025-10-30 17:40:51.864610: Epoch 447 +2025-10-30 17:40:51.866318: Current learning rate: 0.00587 +2025-10-30 17:41:12.064899: train_loss -0.9815 +2025-10-30 17:41:12.107553: val_loss -0.9014 +2025-10-30 17:41:12.125256: Pseudo dice [np.float32(0.9838), np.float32(0.9898), np.float32(0.9919), np.float32(0.8185)] +2025-10-30 17:41:12.141110: Epoch time: 20.2 s +2025-10-30 17:41:13.336304: +2025-10-30 17:41:13.338350: Epoch 448 +2025-10-30 17:41:13.340415: Current learning rate: 0.00586 +2025-10-30 17:41:34.114569: train_loss -0.9858 +2025-10-30 17:41:34.116971: val_loss -0.9027 +2025-10-30 17:41:34.119433: Pseudo dice [np.float32(0.9841), np.float32(0.99), np.float32(0.9945), np.float32(0.8139)] +2025-10-30 17:41:34.120997: Epoch time: 20.78 s +2025-10-30 17:41:35.106940: +2025-10-30 17:41:35.109168: Epoch 449 +2025-10-30 17:41:35.110987: Current learning rate: 0.00585 +2025-10-30 17:41:55.680657: train_loss -0.9863 +2025-10-30 17:41:55.682618: val_loss -0.903 +2025-10-30 17:41:55.684039: Pseudo dice [np.float32(0.9834), np.float32(0.9897), np.float32(0.9946), np.float32(0.8175)] +2025-10-30 17:41:55.685766: Epoch time: 20.58 s +2025-10-30 17:41:57.992361: +2025-10-30 17:41:57.995062: Epoch 450 +2025-10-30 17:41:57.996961: Current learning rate: 0.00584 +2025-10-30 17:42:16.917139: train_loss -0.986 +2025-10-30 17:42:16.919682: val_loss -0.9031 +2025-10-30 17:42:16.921510: Pseudo dice [np.float32(0.9852), np.float32(0.9885), np.float32(0.9935), np.float32(0.8165)] +2025-10-30 17:42:16.923012: Epoch time: 18.93 s +2025-10-30 17:42:17.925239: +2025-10-30 17:42:17.927076: Epoch 451 +2025-10-30 17:42:17.928940: Current learning rate: 0.00583 +2025-10-30 17:42:38.205385: train_loss -0.9856 +2025-10-30 17:42:38.207695: val_loss -0.8994 +2025-10-30 17:42:38.209611: Pseudo dice [np.float32(0.9836), np.float32(0.9903), np.float32(0.9931), np.float32(0.8183)] +2025-10-30 17:42:38.211362: Epoch time: 20.28 s +2025-10-30 17:42:39.203458: +2025-10-30 17:42:39.205523: Epoch 452 +2025-10-30 17:42:39.207380: Current learning rate: 0.00582 +2025-10-30 17:42:58.631760: train_loss -0.9862 +2025-10-30 17:42:58.633616: val_loss -0.9043 +2025-10-30 17:42:58.635063: Pseudo dice [np.float32(0.9831), np.float32(0.99), np.float32(0.9945), np.float32(0.8264)] +2025-10-30 17:42:58.636597: Epoch time: 19.43 s +2025-10-30 17:42:59.771555: +2025-10-30 17:42:59.773300: Epoch 453 +2025-10-30 17:42:59.774811: Current learning rate: 0.00581 +2025-10-30 17:43:20.139674: train_loss -0.984 +2025-10-30 17:43:20.142708: val_loss -0.905 +2025-10-30 17:43:20.144379: Pseudo dice [np.float32(0.9815), np.float32(0.9898), np.float32(0.9948), np.float32(0.8303)] +2025-10-30 17:43:20.145845: Epoch time: 20.37 s +2025-10-30 17:43:21.280560: +2025-10-30 17:43:21.282790: Epoch 454 +2025-10-30 17:43:21.284946: Current learning rate: 0.0058 +2025-10-30 17:43:41.710816: train_loss -0.984 +2025-10-30 17:43:41.713885: val_loss -0.8982 +2025-10-30 17:43:41.716425: Pseudo dice [np.float32(0.9832), np.float32(0.9902), np.float32(0.9944), np.float32(0.8053)] +2025-10-30 17:43:41.718886: Epoch time: 20.43 s +2025-10-30 17:43:42.816008: +2025-10-30 17:43:42.818375: Epoch 455 +2025-10-30 17:43:42.820652: Current learning rate: 0.00579 +2025-10-30 17:44:03.149411: train_loss -0.9836 +2025-10-30 17:44:03.152043: val_loss -0.9042 +2025-10-30 17:44:03.154699: Pseudo dice [np.float32(0.9834), np.float32(0.9904), np.float32(0.9948), np.float32(0.8111)] +2025-10-30 17:44:03.158425: Epoch time: 20.33 s +2025-10-30 17:44:04.164623: +2025-10-30 17:44:04.166826: Epoch 456 +2025-10-30 17:44:04.168547: Current learning rate: 0.00578 +2025-10-30 17:44:24.551829: train_loss -0.9839 +2025-10-30 17:44:24.555309: val_loss -0.9015 +2025-10-30 17:44:24.557235: Pseudo dice [np.float32(0.9821), np.float32(0.9901), np.float32(0.9948), np.float32(0.8162)] +2025-10-30 17:44:24.559128: Epoch time: 20.39 s +2025-10-30 17:44:25.621012: +2025-10-30 17:44:25.623008: Epoch 457 +2025-10-30 17:44:25.624927: Current learning rate: 0.00577 +2025-10-30 17:44:45.344213: train_loss -0.9855 +2025-10-30 17:44:45.346689: val_loss -0.9018 +2025-10-30 17:44:45.348633: Pseudo dice [np.float32(0.9782), np.float32(0.9902), np.float32(0.9944), np.float32(0.8278)] +2025-10-30 17:44:45.350459: Epoch time: 19.72 s +2025-10-30 17:44:47.091567: +2025-10-30 17:44:47.094444: Epoch 458 +2025-10-30 17:44:47.096493: Current learning rate: 0.00576 +2025-10-30 17:45:07.311476: train_loss -0.9786 +2025-10-30 17:45:07.313843: val_loss -0.9235 +2025-10-30 17:45:07.315837: Pseudo dice [np.float32(0.9815), np.float32(0.99), np.float32(0.9959), np.float32(0.8678)] +2025-10-30 17:45:07.317472: Epoch time: 20.22 s +2025-10-30 17:45:08.259963: +2025-10-30 17:45:08.261847: Epoch 459 +2025-10-30 17:45:08.263438: Current learning rate: 0.00575 +2025-10-30 17:45:28.699915: train_loss -0.9757 +2025-10-30 17:45:28.702672: val_loss -0.9092 +2025-10-30 17:45:28.704129: Pseudo dice [np.float32(0.9832), np.float32(0.9897), np.float32(0.9947), np.float32(0.8171)] +2025-10-30 17:45:28.705554: Epoch time: 20.44 s +2025-10-30 17:45:29.698427: +2025-10-30 17:45:29.700525: Epoch 460 +2025-10-30 17:45:29.702136: Current learning rate: 0.00574 +2025-10-30 17:45:50.294943: train_loss -0.9826 +2025-10-30 17:45:50.297426: val_loss -0.9063 +2025-10-30 17:45:50.299137: Pseudo dice [np.float32(0.9832), np.float32(0.9898), np.float32(0.9947), np.float32(0.8174)] +2025-10-30 17:45:50.300770: Epoch time: 20.6 s +2025-10-30 17:45:51.317466: +2025-10-30 17:45:51.319663: Epoch 461 +2025-10-30 17:45:51.321451: Current learning rate: 0.00573 +2025-10-30 17:46:11.841090: train_loss -0.9808 +2025-10-30 17:46:11.845345: val_loss -0.9002 +2025-10-30 17:46:11.847552: Pseudo dice [np.float32(0.9823), np.float32(0.9885), np.float32(0.9945), np.float32(0.8067)] +2025-10-30 17:46:11.850002: Epoch time: 20.53 s +2025-10-30 17:46:12.780660: +2025-10-30 17:46:12.782415: Epoch 462 +2025-10-30 17:46:12.783939: Current learning rate: 0.00572 +2025-10-30 17:46:33.127682: train_loss -0.9851 +2025-10-30 17:46:33.130944: val_loss -0.9014 +2025-10-30 17:46:33.132672: Pseudo dice [np.float32(0.9828), np.float32(0.9903), np.float32(0.9949), np.float32(0.8142)] +2025-10-30 17:46:33.134405: Epoch time: 20.35 s +2025-10-30 17:46:34.333214: +2025-10-30 17:46:34.335263: Epoch 463 +2025-10-30 17:46:34.337160: Current learning rate: 0.00571 +2025-10-30 17:46:54.770499: train_loss -0.9872 +2025-10-30 17:46:54.772849: val_loss -0.8978 +2025-10-30 17:46:54.774760: Pseudo dice [np.float32(0.9835), np.float32(0.9902), np.float32(0.9944), np.float32(0.805)] +2025-10-30 17:46:54.776969: Epoch time: 20.44 s +2025-10-30 17:46:55.828567: +2025-10-30 17:46:55.830687: Epoch 464 +2025-10-30 17:46:55.832404: Current learning rate: 0.0057 +2025-10-30 17:47:15.500788: train_loss -0.9875 +2025-10-30 17:47:15.502936: val_loss -0.8909 +2025-10-30 17:47:15.505553: Pseudo dice [np.float32(0.9834), np.float32(0.9907), np.float32(0.9945), np.float32(0.7984)] +2025-10-30 17:47:15.507592: Epoch time: 19.67 s +2025-10-30 17:47:16.688322: +2025-10-30 17:47:16.690948: Epoch 465 +2025-10-30 17:47:16.692703: Current learning rate: 0.0057 +2025-10-30 17:47:36.598658: train_loss -0.9884 +2025-10-30 17:47:36.601664: val_loss -0.904 +2025-10-30 17:47:36.603610: Pseudo dice [np.float32(0.9842), np.float32(0.991), np.float32(0.9951), np.float32(0.8228)] +2025-10-30 17:47:36.605593: Epoch time: 19.91 s +2025-10-30 17:47:37.560426: +2025-10-30 17:47:37.562387: Epoch 466 +2025-10-30 17:47:37.564560: Current learning rate: 0.00569 +2025-10-30 17:47:58.106196: train_loss -0.9878 +2025-10-30 17:47:58.108247: val_loss -0.9015 +2025-10-30 17:47:58.110193: Pseudo dice [np.float32(0.9833), np.float32(0.9909), np.float32(0.9951), np.float32(0.8153)] +2025-10-30 17:47:58.111933: Epoch time: 20.55 s +2025-10-30 17:47:59.305380: +2025-10-30 17:47:59.307266: Epoch 467 +2025-10-30 17:47:59.308862: Current learning rate: 0.00568 +2025-10-30 17:48:20.004629: train_loss -0.9884 +2025-10-30 17:48:20.006761: val_loss -0.8975 +2025-10-30 17:48:20.008628: Pseudo dice [np.float32(0.9824), np.float32(0.9901), np.float32(0.9949), np.float32(0.8095)] +2025-10-30 17:48:20.010272: Epoch time: 20.7 s +2025-10-30 17:48:21.012533: +2025-10-30 17:48:21.014573: Epoch 468 +2025-10-30 17:48:21.017082: Current learning rate: 0.00567 +2025-10-30 17:48:41.673107: train_loss -0.9883 +2025-10-30 17:48:41.680460: val_loss -0.8968 +2025-10-30 17:48:41.682287: Pseudo dice [np.float32(0.9826), np.float32(0.9909), np.float32(0.995), np.float32(0.8056)] +2025-10-30 17:48:41.684253: Epoch time: 20.66 s +2025-10-30 17:48:42.696376: +2025-10-30 17:48:42.698133: Epoch 469 +2025-10-30 17:48:42.699888: Current learning rate: 0.00566 +2025-10-30 17:49:03.468087: train_loss -0.9875 +2025-10-30 17:49:03.470673: val_loss -0.8969 +2025-10-30 17:49:03.472342: Pseudo dice [np.float32(0.9825), np.float32(0.9901), np.float32(0.9945), np.float32(0.8098)] +2025-10-30 17:49:03.474777: Epoch time: 20.77 s +2025-10-30 17:49:04.876391: +2025-10-30 17:49:04.879171: Epoch 470 +2025-10-30 17:49:04.881156: Current learning rate: 0.00565 +2025-10-30 17:49:25.355991: train_loss -0.9883 +2025-10-30 17:49:25.358587: val_loss -0.9071 +2025-10-30 17:49:25.360679: Pseudo dice [np.float32(0.9835), np.float32(0.991), np.float32(0.9952), np.float32(0.819)] +2025-10-30 17:49:25.362674: Epoch time: 20.48 s +2025-10-30 17:49:26.573035: +2025-10-30 17:49:26.575016: Epoch 471 +2025-10-30 17:49:26.576794: Current learning rate: 0.00564 +2025-10-30 17:49:45.005524: train_loss -0.9892 +2025-10-30 17:49:45.008763: val_loss -0.899 +2025-10-30 17:49:45.010647: Pseudo dice [np.float32(0.9834), np.float32(0.9914), np.float32(0.9948), np.float32(0.8133)] +2025-10-30 17:49:45.012875: Epoch time: 18.43 s +2025-10-30 17:49:46.090765: +2025-10-30 17:49:46.093121: Epoch 472 +2025-10-30 17:49:46.095908: Current learning rate: 0.00563 +2025-10-30 17:50:06.589879: train_loss -0.9886 +2025-10-30 17:50:06.591994: val_loss -0.9039 +2025-10-30 17:50:06.593504: Pseudo dice [np.float32(0.9833), np.float32(0.9903), np.float32(0.995), np.float32(0.8267)] +2025-10-30 17:50:06.594878: Epoch time: 20.5 s +2025-10-30 17:50:07.704458: +2025-10-30 17:50:07.706461: Epoch 473 +2025-10-30 17:50:07.708102: Current learning rate: 0.00562 +2025-10-30 17:50:28.464049: train_loss -0.9897 +2025-10-30 17:50:28.466104: val_loss -0.9058 +2025-10-30 17:50:28.468805: Pseudo dice [np.float32(0.9835), np.float32(0.991), np.float32(0.9953), np.float32(0.8306)] +2025-10-30 17:50:28.470373: Epoch time: 20.76 s +2025-10-30 17:50:29.471499: +2025-10-30 17:50:29.473274: Epoch 474 +2025-10-30 17:50:29.474867: Current learning rate: 0.00561 +2025-10-30 17:50:50.046815: train_loss -0.9887 +2025-10-30 17:50:50.052511: val_loss -0.9023 +2025-10-30 17:50:50.054097: Pseudo dice [np.float32(0.9842), np.float32(0.9903), np.float32(0.995), np.float32(0.8206)] +2025-10-30 17:50:50.055680: Epoch time: 20.58 s +2025-10-30 17:50:51.305188: +2025-10-30 17:50:51.306999: Epoch 475 +2025-10-30 17:50:51.308538: Current learning rate: 0.0056 +2025-10-30 17:51:11.713501: train_loss -0.9892 +2025-10-30 17:51:11.716048: val_loss -0.9005 +2025-10-30 17:51:11.717792: Pseudo dice [np.float32(0.9832), np.float32(0.9912), np.float32(0.9948), np.float32(0.8099)] +2025-10-30 17:51:11.719584: Epoch time: 20.41 s +2025-10-30 17:51:12.914201: +2025-10-30 17:51:12.916104: Epoch 476 +2025-10-30 17:51:12.918077: Current learning rate: 0.00559 +2025-10-30 17:51:33.275394: train_loss -0.9894 +2025-10-30 17:51:33.277385: val_loss -0.9049 +2025-10-30 17:51:33.278894: Pseudo dice [np.float32(0.9834), np.float32(0.9905), np.float32(0.9954), np.float32(0.826)] +2025-10-30 17:51:33.280396: Epoch time: 20.36 s +2025-10-30 17:51:34.276590: +2025-10-30 17:51:34.278295: Epoch 477 +2025-10-30 17:51:34.280058: Current learning rate: 0.00558 +2025-10-30 17:51:54.400969: train_loss -0.99 +2025-10-30 17:51:54.409722: val_loss -0.9077 +2025-10-30 17:51:54.411336: Pseudo dice [np.float32(0.9831), np.float32(0.9916), np.float32(0.9953), np.float32(0.8329)] +2025-10-30 17:51:54.414209: Epoch time: 20.13 s +2025-10-30 17:51:55.551717: +2025-10-30 17:51:55.553740: Epoch 478 +2025-10-30 17:51:55.555421: Current learning rate: 0.00557 +2025-10-30 17:52:14.107627: train_loss -0.9895 +2025-10-30 17:52:14.111014: val_loss -0.8952 +2025-10-30 17:52:14.112578: Pseudo dice [np.float32(0.9824), np.float32(0.9904), np.float32(0.9947), np.float32(0.8071)] +2025-10-30 17:52:14.113992: Epoch time: 18.56 s +2025-10-30 17:52:15.361665: +2025-10-30 17:52:15.363662: Epoch 479 +2025-10-30 17:52:15.365706: Current learning rate: 0.00556 +2025-10-30 17:52:35.820458: train_loss -0.9896 +2025-10-30 17:52:35.822590: val_loss -0.8962 +2025-10-30 17:52:35.824995: Pseudo dice [np.float32(0.9832), np.float32(0.99), np.float32(0.9945), np.float32(0.8048)] +2025-10-30 17:52:35.826620: Epoch time: 20.46 s +2025-10-30 17:52:36.849872: +2025-10-30 17:52:36.851972: Epoch 480 +2025-10-30 17:52:36.853981: Current learning rate: 0.00555 +2025-10-30 17:52:57.224202: train_loss -0.9895 +2025-10-30 17:52:57.227159: val_loss -0.892 +2025-10-30 17:52:57.230296: Pseudo dice [np.float32(0.9833), np.float32(0.9902), np.float32(0.9942), np.float32(0.7954)] +2025-10-30 17:52:57.232274: Epoch time: 20.38 s +2025-10-30 17:52:58.243560: +2025-10-30 17:52:58.246220: Epoch 481 +2025-10-30 17:52:58.248161: Current learning rate: 0.00554 +2025-10-30 17:53:18.893042: train_loss -0.9897 +2025-10-30 17:53:18.895475: val_loss -0.8998 +2025-10-30 17:53:18.897343: Pseudo dice [np.float32(0.9829), np.float32(0.9911), np.float32(0.995), np.float32(0.8129)] +2025-10-30 17:53:18.898946: Epoch time: 20.65 s +2025-10-30 17:53:20.134243: +2025-10-30 17:53:20.136481: Epoch 482 +2025-10-30 17:53:20.138486: Current learning rate: 0.00553 +2025-10-30 17:53:40.389580: train_loss -0.9901 +2025-10-30 17:53:40.392092: val_loss -0.901 +2025-10-30 17:53:40.393929: Pseudo dice [np.float32(0.9841), np.float32(0.9907), np.float32(0.995), np.float32(0.8143)] +2025-10-30 17:53:40.395611: Epoch time: 20.26 s +2025-10-30 17:53:41.908731: +2025-10-30 17:53:41.911213: Epoch 483 +2025-10-30 17:53:41.913134: Current learning rate: 0.00552 +2025-10-30 17:54:02.407403: train_loss -0.9898 +2025-10-30 17:54:02.413156: val_loss -0.9091 +2025-10-30 17:54:02.415881: Pseudo dice [np.float32(0.9843), np.float32(0.9912), np.float32(0.9954), np.float32(0.8367)] +2025-10-30 17:54:02.418254: Epoch time: 20.5 s +2025-10-30 17:54:03.464530: +2025-10-30 17:54:03.466443: Epoch 484 +2025-10-30 17:54:03.468119: Current learning rate: 0.00551 +2025-10-30 17:54:22.618142: train_loss -0.9904 +2025-10-30 17:54:22.620620: val_loss -0.8929 +2025-10-30 17:54:22.622031: Pseudo dice [np.float32(0.9826), np.float32(0.9902), np.float32(0.9946), np.float32(0.8041)] +2025-10-30 17:54:22.623512: Epoch time: 19.16 s +2025-10-30 17:54:23.614873: +2025-10-30 17:54:23.616543: Epoch 485 +2025-10-30 17:54:23.618009: Current learning rate: 0.0055 +2025-10-30 17:54:43.715290: train_loss -0.9897 +2025-10-30 17:54:43.718057: val_loss -0.9023 +2025-10-30 17:54:43.720072: Pseudo dice [np.float32(0.9826), np.float32(0.9906), np.float32(0.9952), np.float32(0.8228)] +2025-10-30 17:54:43.722049: Epoch time: 20.1 s +2025-10-30 17:54:44.899894: +2025-10-30 17:54:44.901961: Epoch 486 +2025-10-30 17:54:44.903829: Current learning rate: 0.00549 +2025-10-30 17:55:05.306118: train_loss -0.9897 +2025-10-30 17:55:05.311231: val_loss -0.8973 +2025-10-30 17:55:05.313619: Pseudo dice [np.float32(0.9831), np.float32(0.9909), np.float32(0.9951), np.float32(0.809)] +2025-10-30 17:55:05.315935: Epoch time: 20.41 s +2025-10-30 17:55:06.496568: +2025-10-30 17:55:06.498691: Epoch 487 +2025-10-30 17:55:06.500537: Current learning rate: 0.00548 +2025-10-30 17:55:27.278065: train_loss -0.9901 +2025-10-30 17:55:27.280381: val_loss -0.9007 +2025-10-30 17:55:27.282568: Pseudo dice [np.float32(0.9818), np.float32(0.9901), np.float32(0.9952), np.float32(0.8261)] +2025-10-30 17:55:27.284899: Epoch time: 20.78 s +2025-10-30 17:55:28.305838: +2025-10-30 17:55:28.307841: Epoch 488 +2025-10-30 17:55:28.309511: Current learning rate: 0.00547 +2025-10-30 17:55:48.867978: train_loss -0.9892 +2025-10-30 17:55:48.870106: val_loss -0.9042 +2025-10-30 17:55:48.871934: Pseudo dice [np.float32(0.9842), np.float32(0.9907), np.float32(0.9951), np.float32(0.8269)] +2025-10-30 17:55:48.873625: Epoch time: 20.56 s +2025-10-30 17:55:49.868898: +2025-10-30 17:55:49.871183: Epoch 489 +2025-10-30 17:55:49.873004: Current learning rate: 0.00546 +2025-10-30 17:56:10.368305: train_loss -0.9901 +2025-10-30 17:56:10.371396: val_loss -0.9079 +2025-10-30 17:56:10.373046: Pseudo dice [np.float32(0.9849), np.float32(0.9905), np.float32(0.995), np.float32(0.8296)] +2025-10-30 17:56:10.374803: Epoch time: 20.5 s +2025-10-30 17:56:11.453336: +2025-10-30 17:56:11.455106: Epoch 490 +2025-10-30 17:56:11.456799: Current learning rate: 0.00546 +2025-10-30 17:56:31.983036: train_loss -0.9902 +2025-10-30 17:56:31.985444: val_loss -0.8892 +2025-10-30 17:56:31.987849: Pseudo dice [np.float32(0.9837), np.float32(0.9899), np.float32(0.9942), np.float32(0.7906)] +2025-10-30 17:56:31.990162: Epoch time: 20.53 s +2025-10-30 17:56:33.092660: +2025-10-30 17:56:33.094761: Epoch 491 +2025-10-30 17:56:33.096962: Current learning rate: 0.00545 +2025-10-30 17:56:51.775178: train_loss -0.9895 +2025-10-30 17:56:51.777432: val_loss -0.9071 +2025-10-30 17:56:51.781512: Pseudo dice [np.float32(0.9834), np.float32(0.9912), np.float32(0.9952), np.float32(0.8339)] +2025-10-30 17:56:51.784269: Epoch time: 18.68 s +2025-10-30 17:56:52.806965: +2025-10-30 17:56:52.808740: Epoch 492 +2025-10-30 17:56:52.810317: Current learning rate: 0.00544 +2025-10-30 17:57:13.365413: train_loss -0.9894 +2025-10-30 17:57:13.368362: val_loss -0.9034 +2025-10-30 17:57:13.370468: Pseudo dice [np.float32(0.9831), np.float32(0.9912), np.float32(0.9952), np.float32(0.8216)] +2025-10-30 17:57:13.372399: Epoch time: 20.56 s +2025-10-30 17:57:14.499367: +2025-10-30 17:57:14.503323: Epoch 493 +2025-10-30 17:57:14.507102: Current learning rate: 0.00543 +2025-10-30 17:57:35.200695: train_loss -0.9899 +2025-10-30 17:57:35.203269: val_loss -0.9054 +2025-10-30 17:57:35.205084: Pseudo dice [np.float32(0.9852), np.float32(0.9911), np.float32(0.9949), np.float32(0.8272)] +2025-10-30 17:57:35.207500: Epoch time: 20.7 s +2025-10-30 17:57:36.425086: +2025-10-30 17:57:36.427156: Epoch 494 +2025-10-30 17:57:36.428855: Current learning rate: 0.00542 +2025-10-30 17:57:56.838535: train_loss -0.9896 +2025-10-30 17:57:56.840631: val_loss -0.8961 +2025-10-30 17:57:56.842267: Pseudo dice [np.float32(0.9833), np.float32(0.9912), np.float32(0.9948), np.float32(0.8113)] +2025-10-30 17:57:56.843800: Epoch time: 20.42 s +2025-10-30 17:57:58.373677: +2025-10-30 17:57:58.375489: Epoch 495 +2025-10-30 17:57:58.377215: Current learning rate: 0.00541 +2025-10-30 17:58:18.837677: train_loss -0.9902 +2025-10-30 17:58:18.840477: val_loss -0.9037 +2025-10-30 17:58:18.842620: Pseudo dice [np.float32(0.9837), np.float32(0.9913), np.float32(0.9952), np.float32(0.8277)] +2025-10-30 17:58:18.844363: Epoch time: 20.47 s +2025-10-30 17:58:19.839257: +2025-10-30 17:58:19.841025: Epoch 496 +2025-10-30 17:58:19.842473: Current learning rate: 0.0054 +2025-10-30 17:58:40.309724: train_loss -0.9905 +2025-10-30 17:58:40.312160: val_loss -0.8968 +2025-10-30 17:58:40.314162: Pseudo dice [np.float32(0.9827), np.float32(0.9906), np.float32(0.9952), np.float32(0.8112)] +2025-10-30 17:58:40.316148: Epoch time: 20.47 s +2025-10-30 17:58:41.314059: +2025-10-30 17:58:41.316409: Epoch 497 +2025-10-30 17:58:41.318371: Current learning rate: 0.00539 +2025-10-30 17:59:00.481357: train_loss -0.9902 +2025-10-30 17:59:00.484361: val_loss -0.8975 +2025-10-30 17:59:00.486629: Pseudo dice [np.float32(0.9833), np.float32(0.9904), np.float32(0.9947), np.float32(0.8089)] +2025-10-30 17:59:00.488939: Epoch time: 19.17 s +2025-10-30 17:59:01.736408: +2025-10-30 17:59:01.738612: Epoch 498 +2025-10-30 17:59:01.740980: Current learning rate: 0.00538 +2025-10-30 17:59:20.906958: train_loss -0.9904 +2025-10-30 17:59:20.910764: val_loss -0.8999 +2025-10-30 17:59:20.913006: Pseudo dice [np.float32(0.9844), np.float32(0.9915), np.float32(0.995), np.float32(0.8114)] +2025-10-30 17:59:20.915122: Epoch time: 19.17 s +2025-10-30 17:59:22.174814: +2025-10-30 17:59:22.176699: Epoch 499 +2025-10-30 17:59:22.178230: Current learning rate: 0.00537 +2025-10-30 17:59:42.905489: train_loss -0.9901 +2025-10-30 17:59:42.910617: val_loss -0.8955 +2025-10-30 17:59:42.912437: Pseudo dice [np.float32(0.9833), np.float32(0.9903), np.float32(0.9947), np.float32(0.8098)] +2025-10-30 17:59:42.913955: Epoch time: 20.73 s +2025-10-30 17:59:45.483707: +2025-10-30 17:59:45.485876: Epoch 500 +2025-10-30 17:59:45.487818: Current learning rate: 0.00536 +2025-10-30 18:00:05.755504: train_loss -0.9901 +2025-10-30 18:00:05.758618: val_loss -0.9061 +2025-10-30 18:00:05.760389: Pseudo dice [np.float32(0.9843), np.float32(0.9915), np.float32(0.9952), np.float32(0.8286)] +2025-10-30 18:00:05.762966: Epoch time: 20.27 s +2025-10-30 18:00:07.095554: +2025-10-30 18:00:07.097863: Epoch 501 +2025-10-30 18:00:07.099720: Current learning rate: 0.00535 +2025-10-30 18:00:27.843473: train_loss -0.9901 +2025-10-30 18:00:27.846547: val_loss -0.8987 +2025-10-30 18:00:27.848111: Pseudo dice [np.float32(0.9841), np.float32(0.9908), np.float32(0.9947), np.float32(0.8184)] +2025-10-30 18:00:27.849886: Epoch time: 20.75 s +2025-10-30 18:00:29.050935: +2025-10-30 18:00:29.053328: Epoch 502 +2025-10-30 18:00:29.055020: Current learning rate: 0.00534 +2025-10-30 18:00:49.910415: train_loss -0.9905 +2025-10-30 18:00:49.913156: val_loss -0.8899 +2025-10-30 18:00:49.914758: Pseudo dice [np.float32(0.9831), np.float32(0.9907), np.float32(0.9944), np.float32(0.8043)] +2025-10-30 18:00:49.916502: Epoch time: 20.86 s +2025-10-30 18:00:51.141549: +2025-10-30 18:00:51.143566: Epoch 503 +2025-10-30 18:00:51.145425: Current learning rate: 0.00533 +2025-10-30 18:01:11.802936: train_loss -0.9896 +2025-10-30 18:01:11.806769: val_loss -0.9 +2025-10-30 18:01:11.808469: Pseudo dice [np.float32(0.9848), np.float32(0.9906), np.float32(0.9945), np.float32(0.8188)] +2025-10-30 18:01:11.810071: Epoch time: 20.66 s +2025-10-30 18:01:13.018013: +2025-10-30 18:01:13.019977: Epoch 504 +2025-10-30 18:01:13.021545: Current learning rate: 0.00532 +2025-10-30 18:01:32.704855: train_loss -0.9906 +2025-10-30 18:01:32.708176: val_loss -0.9063 +2025-10-30 18:01:32.710710: Pseudo dice [np.float32(0.9847), np.float32(0.992), np.float32(0.9955), np.float32(0.8269)] +2025-10-30 18:01:32.712686: Epoch time: 19.69 s +2025-10-30 18:01:33.828082: +2025-10-30 18:01:33.830167: Epoch 505 +2025-10-30 18:01:33.831754: Current learning rate: 0.00531 +2025-10-30 18:01:53.576321: train_loss -0.99 +2025-10-30 18:01:53.579354: val_loss -0.9026 +2025-10-30 18:01:53.581818: Pseudo dice [np.float32(0.9832), np.float32(0.9913), np.float32(0.995), np.float32(0.8237)] +2025-10-30 18:01:53.583905: Epoch time: 19.75 s +2025-10-30 18:01:54.472216: +2025-10-30 18:01:54.474161: Epoch 506 +2025-10-30 18:01:54.475937: Current learning rate: 0.0053 +2025-10-30 18:02:15.049416: train_loss -0.9899 +2025-10-30 18:02:15.051389: val_loss -0.9055 +2025-10-30 18:02:15.053031: Pseudo dice [np.float32(0.9829), np.float32(0.9908), np.float32(0.9955), np.float32(0.8288)] +2025-10-30 18:02:15.054607: Epoch time: 20.58 s +2025-10-30 18:02:16.597749: +2025-10-30 18:02:16.599655: Epoch 507 +2025-10-30 18:02:16.601209: Current learning rate: 0.00529 +2025-10-30 18:02:37.326445: train_loss -0.989 +2025-10-30 18:02:37.329571: val_loss -0.9024 +2025-10-30 18:02:37.331456: Pseudo dice [np.float32(0.9832), np.float32(0.9913), np.float32(0.9953), np.float32(0.8212)] +2025-10-30 18:02:37.333531: Epoch time: 20.73 s +2025-10-30 18:02:38.326242: +2025-10-30 18:02:38.328210: Epoch 508 +2025-10-30 18:02:38.330012: Current learning rate: 0.00528 +2025-10-30 18:02:58.943799: train_loss -0.9902 +2025-10-30 18:02:58.946923: val_loss -0.8995 +2025-10-30 18:02:58.948824: Pseudo dice [np.float32(0.9827), np.float32(0.9911), np.float32(0.9952), np.float32(0.814)] +2025-10-30 18:02:58.950805: Epoch time: 20.62 s +2025-10-30 18:02:59.913407: +2025-10-30 18:02:59.915137: Epoch 509 +2025-10-30 18:02:59.916544: Current learning rate: 0.00527 +2025-10-30 18:03:20.767200: train_loss -0.9904 +2025-10-30 18:03:20.772394: val_loss -0.9025 +2025-10-30 18:03:20.774033: Pseudo dice [np.float32(0.9839), np.float32(0.9912), np.float32(0.9949), np.float32(0.8209)] +2025-10-30 18:03:20.775651: Epoch time: 20.86 s +2025-10-30 18:03:21.949988: +2025-10-30 18:03:21.952077: Epoch 510 +2025-10-30 18:03:21.954115: Current learning rate: 0.00526 +2025-10-30 18:03:41.234785: train_loss -0.99 +2025-10-30 18:03:41.237584: val_loss -0.8975 +2025-10-30 18:03:41.239076: Pseudo dice [np.float32(0.9831), np.float32(0.9912), np.float32(0.9954), np.float32(0.8168)] +2025-10-30 18:03:41.240469: Epoch time: 19.29 s +2025-10-30 18:03:42.246273: +2025-10-30 18:03:42.248208: Epoch 511 +2025-10-30 18:03:42.250339: Current learning rate: 0.00525 +2025-10-30 18:04:02.754087: train_loss -0.9901 +2025-10-30 18:04:02.759017: val_loss -0.8956 +2025-10-30 18:04:02.760796: Pseudo dice [np.float32(0.9838), np.float32(0.9904), np.float32(0.9947), np.float32(0.8017)] +2025-10-30 18:04:02.762436: Epoch time: 20.51 s +2025-10-30 18:04:03.805225: +2025-10-30 18:04:03.809070: Epoch 512 +2025-10-30 18:04:03.812793: Current learning rate: 0.00524 +2025-10-30 18:04:23.941757: train_loss -0.9904 +2025-10-30 18:04:23.944120: val_loss -0.9039 +2025-10-30 18:04:23.945747: Pseudo dice [np.float32(0.9845), np.float32(0.9908), np.float32(0.9951), np.float32(0.8247)] +2025-10-30 18:04:23.948014: Epoch time: 20.14 s +2025-10-30 18:04:25.288387: +2025-10-30 18:04:25.290608: Epoch 513 +2025-10-30 18:04:25.292322: Current learning rate: 0.00523 +2025-10-30 18:04:46.062383: train_loss -0.9898 +2025-10-30 18:04:46.065147: val_loss -0.9011 +2025-10-30 18:04:46.067238: Pseudo dice [np.float32(0.9838), np.float32(0.9916), np.float32(0.9953), np.float32(0.8192)] +2025-10-30 18:04:46.069359: Epoch time: 20.78 s +2025-10-30 18:04:47.153679: +2025-10-30 18:04:47.155363: Epoch 514 +2025-10-30 18:04:47.157070: Current learning rate: 0.00522 +2025-10-30 18:05:07.910899: train_loss -0.9913 +2025-10-30 18:05:07.915106: val_loss -0.8991 +2025-10-30 18:05:07.919904: Pseudo dice [np.float32(0.9841), np.float32(0.991), np.float32(0.9947), np.float32(0.8079)] +2025-10-30 18:05:07.926342: Epoch time: 20.76 s +2025-10-30 18:05:09.140044: +2025-10-30 18:05:09.141825: Epoch 515 +2025-10-30 18:05:09.143857: Current learning rate: 0.00521 +2025-10-30 18:05:29.947501: train_loss -0.9897 +2025-10-30 18:05:29.950018: val_loss -0.8889 +2025-10-30 18:05:29.951714: Pseudo dice [np.float32(0.9826), np.float32(0.9904), np.float32(0.9944), np.float32(0.7955)] +2025-10-30 18:05:29.953436: Epoch time: 20.81 s +2025-10-30 18:05:31.239702: +2025-10-30 18:05:31.242600: Epoch 516 +2025-10-30 18:05:31.245489: Current learning rate: 0.0052 +2025-10-30 18:05:50.968692: train_loss -0.9889 +2025-10-30 18:05:50.972303: val_loss -0.882 +2025-10-30 18:05:50.974227: Pseudo dice [np.float32(0.9809), np.float32(0.9892), np.float32(0.9941), np.float32(0.7804)] +2025-10-30 18:05:50.976032: Epoch time: 19.73 s +2025-10-30 18:05:52.068841: +2025-10-30 18:05:52.073733: Epoch 517 +2025-10-30 18:05:52.076190: Current learning rate: 0.00519 +2025-10-30 18:06:12.455626: train_loss -0.9897 +2025-10-30 18:06:12.460023: val_loss -0.896 +2025-10-30 18:06:12.462424: Pseudo dice [np.float32(0.9844), np.float32(0.9904), np.float32(0.9945), np.float32(0.8047)] +2025-10-30 18:06:12.463990: Epoch time: 20.39 s +2025-10-30 18:06:13.595938: +2025-10-30 18:06:13.599179: Epoch 518 +2025-10-30 18:06:13.600973: Current learning rate: 0.00518 +2025-10-30 18:06:33.013998: train_loss -0.9908 +2025-10-30 18:06:33.016028: val_loss -0.8968 +2025-10-30 18:06:33.017799: Pseudo dice [np.float32(0.9835), np.float32(0.9914), np.float32(0.9946), np.float32(0.8093)] +2025-10-30 18:06:33.019440: Epoch time: 19.42 s +2025-10-30 18:06:34.247412: +2025-10-30 18:06:34.249638: Epoch 519 +2025-10-30 18:06:34.251662: Current learning rate: 0.00518 +2025-10-30 18:06:54.792906: train_loss -0.9902 +2025-10-30 18:06:54.796410: val_loss -0.902 +2025-10-30 18:06:54.798239: Pseudo dice [np.float32(0.9827), np.float32(0.9912), np.float32(0.9955), np.float32(0.826)] +2025-10-30 18:06:54.799837: Epoch time: 20.55 s +2025-10-30 18:06:56.527641: +2025-10-30 18:06:56.530137: Epoch 520 +2025-10-30 18:06:56.531960: Current learning rate: 0.00517 +2025-10-30 18:07:16.922615: train_loss -0.9903 +2025-10-30 18:07:16.924984: val_loss -0.9091 +2025-10-30 18:07:16.927234: Pseudo dice [np.float32(0.9842), np.float32(0.9917), np.float32(0.9958), np.float32(0.8323)] +2025-10-30 18:07:16.928875: Epoch time: 20.4 s +2025-10-30 18:07:18.139483: +2025-10-30 18:07:18.141724: Epoch 521 +2025-10-30 18:07:18.143428: Current learning rate: 0.00516 +2025-10-30 18:07:38.692429: train_loss -0.99 +2025-10-30 18:07:38.695078: val_loss -0.8969 +2025-10-30 18:07:38.697290: Pseudo dice [np.float32(0.9842), np.float32(0.9912), np.float32(0.9947), np.float32(0.8121)] +2025-10-30 18:07:38.699171: Epoch time: 20.55 s +2025-10-30 18:07:39.693388: +2025-10-30 18:07:39.695657: Epoch 522 +2025-10-30 18:07:39.697657: Current learning rate: 0.00515 +2025-10-30 18:08:00.496632: train_loss -0.9894 +2025-10-30 18:08:00.499639: val_loss -0.8959 +2025-10-30 18:08:00.501290: Pseudo dice [np.float32(0.9843), np.float32(0.9912), np.float32(0.9948), np.float32(0.8101)] +2025-10-30 18:08:00.503073: Epoch time: 20.8 s +2025-10-30 18:08:01.662134: +2025-10-30 18:08:01.667535: Epoch 523 +2025-10-30 18:08:01.669033: Current learning rate: 0.00514 +2025-10-30 18:08:20.657695: train_loss -0.9901 +2025-10-30 18:08:20.660214: val_loss -0.902 +2025-10-30 18:08:20.663967: Pseudo dice [np.float32(0.9846), np.float32(0.9917), np.float32(0.9951), np.float32(0.8234)] +2025-10-30 18:08:20.666128: Epoch time: 19.0 s +2025-10-30 18:08:21.784467: +2025-10-30 18:08:21.786260: Epoch 524 +2025-10-30 18:08:21.788449: Current learning rate: 0.00513 +2025-10-30 18:08:42.083339: train_loss -0.9905 +2025-10-30 18:08:42.085504: val_loss -0.8941 +2025-10-30 18:08:42.087166: Pseudo dice [np.float32(0.9835), np.float32(0.9907), np.float32(0.9946), np.float32(0.8102)] +2025-10-30 18:08:42.088694: Epoch time: 20.3 s +2025-10-30 18:08:43.106715: +2025-10-30 18:08:43.108336: Epoch 525 +2025-10-30 18:08:43.110491: Current learning rate: 0.00512 +2025-10-30 18:09:02.285884: train_loss -0.9904 +2025-10-30 18:09:02.288838: val_loss -0.8894 +2025-10-30 18:09:02.290540: Pseudo dice [np.float32(0.9836), np.float32(0.9909), np.float32(0.9948), np.float32(0.7993)] +2025-10-30 18:09:02.292201: Epoch time: 19.18 s +2025-10-30 18:09:03.448961: +2025-10-30 18:09:03.450802: Epoch 526 +2025-10-30 18:09:03.452595: Current learning rate: 0.00511 +2025-10-30 18:09:23.829279: train_loss -0.99 +2025-10-30 18:09:23.831294: val_loss -0.8983 +2025-10-30 18:09:23.832907: Pseudo dice [np.float32(0.9822), np.float32(0.9912), np.float32(0.9951), np.float32(0.8176)] +2025-10-30 18:09:23.834447: Epoch time: 20.38 s +2025-10-30 18:09:24.939024: +2025-10-30 18:09:24.941010: Epoch 527 +2025-10-30 18:09:24.942743: Current learning rate: 0.0051 +2025-10-30 18:09:45.665793: train_loss -0.9896 +2025-10-30 18:09:45.668113: val_loss -0.901 +2025-10-30 18:09:45.669754: Pseudo dice [np.float32(0.9829), np.float32(0.9901), np.float32(0.9951), np.float32(0.8214)] +2025-10-30 18:09:45.671455: Epoch time: 20.73 s +2025-10-30 18:09:46.866395: +2025-10-30 18:09:46.868539: Epoch 528 +2025-10-30 18:09:46.870096: Current learning rate: 0.00509 +2025-10-30 18:10:07.464382: train_loss -0.9904 +2025-10-30 18:10:07.467463: val_loss -0.902 +2025-10-30 18:10:07.469704: Pseudo dice [np.float32(0.9845), np.float32(0.9916), np.float32(0.9949), np.float32(0.8178)] +2025-10-30 18:10:07.472080: Epoch time: 20.6 s +2025-10-30 18:10:08.547197: +2025-10-30 18:10:08.549212: Epoch 529 +2025-10-30 18:10:08.551107: Current learning rate: 0.00508 +2025-10-30 18:10:28.114352: train_loss -0.9907 +2025-10-30 18:10:28.116704: val_loss -0.8949 +2025-10-30 18:10:28.118510: Pseudo dice [np.float32(0.9823), np.float32(0.9898), np.float32(0.995), np.float32(0.8059)] +2025-10-30 18:10:28.120199: Epoch time: 19.57 s +2025-10-30 18:10:29.132461: +2025-10-30 18:10:29.134436: Epoch 530 +2025-10-30 18:10:29.136495: Current learning rate: 0.00507 +2025-10-30 18:10:49.467798: train_loss -0.9896 +2025-10-30 18:10:49.470246: val_loss -0.905 +2025-10-30 18:10:49.472141: Pseudo dice [np.float32(0.9824), np.float32(0.991), np.float32(0.9952), np.float32(0.8282)] +2025-10-30 18:10:49.474298: Epoch time: 20.34 s +2025-10-30 18:10:50.496028: +2025-10-30 18:10:50.497991: Epoch 531 +2025-10-30 18:10:50.499615: Current learning rate: 0.00506 +2025-10-30 18:11:11.146081: train_loss -0.9909 +2025-10-30 18:11:11.149181: val_loss -0.8985 +2025-10-30 18:11:11.150842: Pseudo dice [np.float32(0.9846), np.float32(0.9919), np.float32(0.9948), np.float32(0.803)] +2025-10-30 18:11:11.152451: Epoch time: 20.65 s +2025-10-30 18:11:12.812560: +2025-10-30 18:11:12.814395: Epoch 532 +2025-10-30 18:11:12.816086: Current learning rate: 0.00505 +2025-10-30 18:11:32.410425: train_loss -0.9906 +2025-10-30 18:11:32.413030: val_loss -0.904 +2025-10-30 18:11:32.414642: Pseudo dice [np.float32(0.9826), np.float32(0.991), np.float32(0.9954), np.float32(0.8287)] +2025-10-30 18:11:32.416722: Epoch time: 19.6 s +2025-10-30 18:11:33.548391: +2025-10-30 18:11:33.551033: Epoch 533 +2025-10-30 18:11:33.552647: Current learning rate: 0.00504 +2025-10-30 18:11:54.138024: train_loss -0.9909 +2025-10-30 18:11:54.140712: val_loss -0.9034 +2025-10-30 18:11:54.142675: Pseudo dice [np.float32(0.9831), np.float32(0.9909), np.float32(0.9953), np.float32(0.8251)] +2025-10-30 18:11:54.144528: Epoch time: 20.59 s +2025-10-30 18:11:55.287453: +2025-10-30 18:11:55.289291: Epoch 534 +2025-10-30 18:11:55.290946: Current learning rate: 0.00503 +2025-10-30 18:12:15.630449: train_loss -0.9915 +2025-10-30 18:12:15.639386: val_loss -0.8945 +2025-10-30 18:12:15.640858: Pseudo dice [np.float32(0.9822), np.float32(0.9912), np.float32(0.9948), np.float32(0.8037)] +2025-10-30 18:12:15.642222: Epoch time: 20.34 s +2025-10-30 18:12:16.730595: +2025-10-30 18:12:16.732273: Epoch 535 +2025-10-30 18:12:16.734333: Current learning rate: 0.00502 +2025-10-30 18:12:37.215477: train_loss -0.9902 +2025-10-30 18:12:37.218022: val_loss -0.9065 +2025-10-30 18:12:37.219721: Pseudo dice [np.float32(0.9826), np.float32(0.9912), np.float32(0.9954), np.float32(0.8343)] +2025-10-30 18:12:37.221400: Epoch time: 20.49 s +2025-10-30 18:12:38.401940: +2025-10-30 18:12:38.403960: Epoch 536 +2025-10-30 18:12:38.405672: Current learning rate: 0.00501 +2025-10-30 18:12:57.820888: train_loss -0.9907 +2025-10-30 18:12:57.823129: val_loss -0.9009 +2025-10-30 18:12:57.824714: Pseudo dice [np.float32(0.9829), np.float32(0.991), np.float32(0.9951), np.float32(0.8248)] +2025-10-30 18:12:57.826322: Epoch time: 19.42 s +2025-10-30 18:12:59.073756: +2025-10-30 18:12:59.075615: Epoch 537 +2025-10-30 18:12:59.077059: Current learning rate: 0.005 +2025-10-30 18:13:19.412817: train_loss -0.9909 +2025-10-30 18:13:19.415376: val_loss -0.9109 +2025-10-30 18:13:19.417030: Pseudo dice [np.float32(0.984), np.float32(0.9913), np.float32(0.9955), np.float32(0.841)] +2025-10-30 18:13:19.418610: Epoch time: 20.34 s +2025-10-30 18:13:20.562452: +2025-10-30 18:13:20.565539: Epoch 538 +2025-10-30 18:13:20.568628: Current learning rate: 0.00499 +2025-10-30 18:13:40.845632: train_loss -0.9908 +2025-10-30 18:13:40.848027: val_loss -0.9064 +2025-10-30 18:13:40.849717: Pseudo dice [np.float32(0.983), np.float32(0.9905), np.float32(0.9954), np.float32(0.8374)] +2025-10-30 18:13:40.851487: Epoch time: 20.28 s +2025-10-30 18:13:41.837749: +2025-10-30 18:13:41.839465: Epoch 539 +2025-10-30 18:13:41.840990: Current learning rate: 0.00498 +2025-10-30 18:14:01.434353: train_loss -0.9905 +2025-10-30 18:14:01.437001: val_loss -0.9013 +2025-10-30 18:14:01.439134: Pseudo dice [np.float32(0.9829), np.float32(0.9903), np.float32(0.9948), np.float32(0.8245)] +2025-10-30 18:14:01.441599: Epoch time: 19.6 s +2025-10-30 18:14:02.542213: +2025-10-30 18:14:02.543956: Epoch 540 +2025-10-30 18:14:02.547981: Current learning rate: 0.00497 +2025-10-30 18:14:22.883675: train_loss -0.9909 +2025-10-30 18:14:22.886790: val_loss -0.8983 +2025-10-30 18:14:22.888494: Pseudo dice [np.float32(0.983), np.float32(0.9906), np.float32(0.9951), np.float32(0.817)] +2025-10-30 18:14:22.890673: Epoch time: 20.34 s +2025-10-30 18:14:23.940684: +2025-10-30 18:14:23.942947: Epoch 541 +2025-10-30 18:14:23.946299: Current learning rate: 0.00496 +2025-10-30 18:14:44.266454: train_loss -0.9906 +2025-10-30 18:14:44.268614: val_loss -0.9031 +2025-10-30 18:14:44.270672: Pseudo dice [np.float32(0.9832), np.float32(0.9916), np.float32(0.9951), np.float32(0.8221)] +2025-10-30 18:14:44.272400: Epoch time: 20.33 s +2025-10-30 18:14:45.278594: +2025-10-30 18:14:45.281247: Epoch 542 +2025-10-30 18:14:45.283436: Current learning rate: 0.00495 +2025-10-30 18:15:05.213231: train_loss -0.9904 +2025-10-30 18:15:05.218588: val_loss -0.9004 +2025-10-30 18:15:05.221124: Pseudo dice [np.float32(0.983), np.float32(0.9911), np.float32(0.9952), np.float32(0.8118)] +2025-10-30 18:15:05.223091: Epoch time: 19.94 s +2025-10-30 18:15:06.436357: +2025-10-30 18:15:06.438047: Epoch 543 +2025-10-30 18:15:06.439644: Current learning rate: 0.00494 +2025-10-30 18:15:26.965875: train_loss -0.9909 +2025-10-30 18:15:26.969174: val_loss -0.9041 +2025-10-30 18:15:26.970803: Pseudo dice [np.float32(0.9847), np.float32(0.9911), np.float32(0.9951), np.float32(0.827)] +2025-10-30 18:15:26.972568: Epoch time: 20.53 s +2025-10-30 18:15:28.004933: +2025-10-30 18:15:28.006704: Epoch 544 +2025-10-30 18:15:28.008362: Current learning rate: 0.00493 +2025-10-30 18:15:48.344887: train_loss -0.9908 +2025-10-30 18:15:48.347246: val_loss -0.8972 +2025-10-30 18:15:48.348938: Pseudo dice [np.float32(0.9831), np.float32(0.9903), np.float32(0.9948), np.float32(0.8098)] +2025-10-30 18:15:48.350587: Epoch time: 20.34 s +2025-10-30 18:15:50.015737: +2025-10-30 18:15:50.017815: Epoch 545 +2025-10-30 18:15:50.019811: Current learning rate: 0.00492 +2025-10-30 18:16:10.176780: train_loss -0.9902 +2025-10-30 18:16:10.179010: val_loss -0.9102 +2025-10-30 18:16:10.180935: Pseudo dice [np.float32(0.9836), np.float32(0.9911), np.float32(0.9955), np.float32(0.8447)] +2025-10-30 18:16:10.182563: Epoch time: 20.16 s +2025-10-30 18:16:11.189549: +2025-10-30 18:16:11.191489: Epoch 546 +2025-10-30 18:16:11.193253: Current learning rate: 0.00491 +2025-10-30 18:16:31.108583: train_loss -0.9908 +2025-10-30 18:16:31.111511: val_loss -0.9052 +2025-10-30 18:16:31.113069: Pseudo dice [np.float32(0.984), np.float32(0.9915), np.float32(0.9954), np.float32(0.8234)] +2025-10-30 18:16:31.114710: Epoch time: 19.92 s +2025-10-30 18:16:32.387572: +2025-10-30 18:16:32.392479: Epoch 547 +2025-10-30 18:16:32.394087: Current learning rate: 0.0049 +2025-10-30 18:16:52.972377: train_loss -0.9903 +2025-10-30 18:16:52.975376: val_loss -0.9068 +2025-10-30 18:16:52.977376: Pseudo dice [np.float32(0.985), np.float32(0.9918), np.float32(0.9953), np.float32(0.8274)] +2025-10-30 18:16:52.978866: Epoch time: 20.59 s +2025-10-30 18:16:54.083407: +2025-10-30 18:16:54.086456: Epoch 548 +2025-10-30 18:16:54.088363: Current learning rate: 0.00489 +2025-10-30 18:17:13.900632: train_loss -0.9906 +2025-10-30 18:17:13.902676: val_loss -0.8977 +2025-10-30 18:17:13.905163: Pseudo dice [np.float32(0.983), np.float32(0.9921), np.float32(0.9948), np.float32(0.8026)] +2025-10-30 18:17:13.907606: Epoch time: 19.82 s +2025-10-30 18:17:14.931451: +2025-10-30 18:17:14.933447: Epoch 549 +2025-10-30 18:17:14.935094: Current learning rate: 0.00488 +2025-10-30 18:17:35.117134: train_loss -0.9904 +2025-10-30 18:17:35.120291: val_loss -0.9029 +2025-10-30 18:17:35.121862: Pseudo dice [np.float32(0.9834), np.float32(0.991), np.float32(0.9953), np.float32(0.8256)] +2025-10-30 18:17:35.123691: Epoch time: 20.19 s +2025-10-30 18:17:37.478808: +2025-10-30 18:17:37.480772: Epoch 550 +2025-10-30 18:17:37.483152: Current learning rate: 0.00487 +2025-10-30 18:17:57.917519: train_loss -0.9905 +2025-10-30 18:17:57.919651: val_loss -0.9049 +2025-10-30 18:17:57.921337: Pseudo dice [np.float32(0.984), np.float32(0.9912), np.float32(0.9949), np.float32(0.8247)] +2025-10-30 18:17:57.923008: Epoch time: 20.44 s +2025-10-30 18:17:58.992343: +2025-10-30 18:17:58.994321: Epoch 551 +2025-10-30 18:17:58.996044: Current learning rate: 0.00486 +2025-10-30 18:18:19.230995: train_loss -0.9891 +2025-10-30 18:18:19.233179: val_loss -0.9045 +2025-10-30 18:18:19.235040: Pseudo dice [np.float32(0.9828), np.float32(0.9906), np.float32(0.9951), np.float32(0.8213)] +2025-10-30 18:18:19.237245: Epoch time: 20.24 s +2025-10-30 18:18:20.265749: +2025-10-30 18:18:20.268060: Epoch 552 +2025-10-30 18:18:20.269735: Current learning rate: 0.00485 +2025-10-30 18:18:39.476168: train_loss -0.9893 +2025-10-30 18:18:39.479456: val_loss -0.9012 +2025-10-30 18:18:39.481366: Pseudo dice [np.float32(0.9837), np.float32(0.9906), np.float32(0.9948), np.float32(0.8187)] +2025-10-30 18:18:39.495928: Epoch time: 19.21 s +2025-10-30 18:18:40.647543: +2025-10-30 18:18:40.649778: Epoch 553 +2025-10-30 18:18:40.652634: Current learning rate: 0.00484 +2025-10-30 18:19:01.207092: train_loss -0.99 +2025-10-30 18:19:01.209791: val_loss -0.8981 +2025-10-30 18:19:01.212539: Pseudo dice [np.float32(0.9831), np.float32(0.9903), np.float32(0.9952), np.float32(0.8185)] +2025-10-30 18:19:01.215041: Epoch time: 20.56 s +2025-10-30 18:19:02.437047: +2025-10-30 18:19:02.439062: Epoch 554 +2025-10-30 18:19:02.440808: Current learning rate: 0.00484 +2025-10-30 18:19:23.069749: train_loss -0.9904 +2025-10-30 18:19:23.074377: val_loss -0.9026 +2025-10-30 18:19:23.076599: Pseudo dice [np.float32(0.9832), np.float32(0.9908), np.float32(0.9954), np.float32(0.8292)] +2025-10-30 18:19:23.078517: Epoch time: 20.63 s +2025-10-30 18:19:24.304159: +2025-10-30 18:19:24.306122: Epoch 555 +2025-10-30 18:19:24.307978: Current learning rate: 0.00483 +2025-10-30 18:19:43.613873: train_loss -0.9901 +2025-10-30 18:19:43.617411: val_loss -0.8903 +2025-10-30 18:19:43.619389: Pseudo dice [np.float32(0.9827), np.float32(0.9905), np.float32(0.9945), np.float32(0.7873)] +2025-10-30 18:19:43.621127: Epoch time: 19.31 s +2025-10-30 18:19:44.693652: +2025-10-30 18:19:44.695662: Epoch 556 +2025-10-30 18:19:44.697582: Current learning rate: 0.00482 +2025-10-30 18:20:05.263560: train_loss -0.9905 +2025-10-30 18:20:05.266531: val_loss -0.8928 +2025-10-30 18:20:05.268418: Pseudo dice [np.float32(0.9819), np.float32(0.9896), np.float32(0.9948), np.float32(0.8051)] +2025-10-30 18:20:05.270107: Epoch time: 20.57 s +2025-10-30 18:20:06.702455: +2025-10-30 18:20:06.704292: Epoch 557 +2025-10-30 18:20:06.706036: Current learning rate: 0.00481 +2025-10-30 18:20:27.267198: train_loss -0.9904 +2025-10-30 18:20:27.269903: val_loss -0.9036 +2025-10-30 18:20:27.271881: Pseudo dice [np.float32(0.9835), np.float32(0.9917), np.float32(0.9952), np.float32(0.8219)] +2025-10-30 18:20:27.273947: Epoch time: 20.57 s +2025-10-30 18:20:28.575133: +2025-10-30 18:20:28.577238: Epoch 558 +2025-10-30 18:20:28.579537: Current learning rate: 0.0048 +2025-10-30 18:20:49.003564: train_loss -0.9901 +2025-10-30 18:20:49.006647: val_loss -0.8974 +2025-10-30 18:20:49.008330: Pseudo dice [np.float32(0.9827), np.float32(0.991), np.float32(0.9948), np.float32(0.8118)] +2025-10-30 18:20:49.010798: Epoch time: 20.43 s +2025-10-30 18:20:50.072927: +2025-10-30 18:20:50.075039: Epoch 559 +2025-10-30 18:20:50.077006: Current learning rate: 0.00479 +2025-10-30 18:21:09.832408: train_loss -0.991 +2025-10-30 18:21:09.835139: val_loss -0.9063 +2025-10-30 18:21:09.836971: Pseudo dice [np.float32(0.9839), np.float32(0.9909), np.float32(0.9955), np.float32(0.8355)] +2025-10-30 18:21:09.838567: Epoch time: 19.76 s +2025-10-30 18:21:11.035606: +2025-10-30 18:21:11.037629: Epoch 560 +2025-10-30 18:21:11.039164: Current learning rate: 0.00478 +2025-10-30 18:21:31.539763: train_loss -0.9916 +2025-10-30 18:21:31.542889: val_loss -0.8948 +2025-10-30 18:21:31.545380: Pseudo dice [np.float32(0.9835), np.float32(0.9906), np.float32(0.995), np.float32(0.8147)] +2025-10-30 18:21:31.547151: Epoch time: 20.51 s +2025-10-30 18:21:32.576938: +2025-10-30 18:21:32.578809: Epoch 561 +2025-10-30 18:21:32.581232: Current learning rate: 0.00477 +2025-10-30 18:21:52.550685: train_loss -0.9897 +2025-10-30 18:21:52.554341: val_loss -0.8956 +2025-10-30 18:21:52.558863: Pseudo dice [np.float32(0.9831), np.float32(0.9911), np.float32(0.9949), np.float32(0.8156)] +2025-10-30 18:21:52.560471: Epoch time: 19.97 s +2025-10-30 18:21:53.683434: +2025-10-30 18:21:53.685309: Epoch 562 +2025-10-30 18:21:53.686903: Current learning rate: 0.00476 +2025-10-30 18:22:14.065441: train_loss -0.9906 +2025-10-30 18:22:14.067331: val_loss -0.9116 +2025-10-30 18:22:14.068969: Pseudo dice [np.float32(0.9826), np.float32(0.9912), np.float32(0.9956), np.float32(0.8443)] +2025-10-30 18:22:14.070657: Epoch time: 20.38 s +2025-10-30 18:22:15.135527: +2025-10-30 18:22:15.137555: Epoch 563 +2025-10-30 18:22:15.139569: Current learning rate: 0.00475 +2025-10-30 18:22:35.619491: train_loss -0.9906 +2025-10-30 18:22:35.622221: val_loss -0.8953 +2025-10-30 18:22:35.623924: Pseudo dice [np.float32(0.9835), np.float32(0.9911), np.float32(0.9949), np.float32(0.8092)] +2025-10-30 18:22:35.625625: Epoch time: 20.49 s +2025-10-30 18:22:36.820387: +2025-10-30 18:22:36.822270: Epoch 564 +2025-10-30 18:22:36.824598: Current learning rate: 0.00474 +2025-10-30 18:22:57.457464: train_loss -0.9902 +2025-10-30 18:22:57.461959: val_loss -0.9067 +2025-10-30 18:22:57.463620: Pseudo dice [np.float32(0.9844), np.float32(0.9916), np.float32(0.9952), np.float32(0.8353)] +2025-10-30 18:22:57.465414: Epoch time: 20.64 s +2025-10-30 18:22:58.725652: +2025-10-30 18:22:58.727306: Epoch 565 +2025-10-30 18:22:58.728899: Current learning rate: 0.00473 +2025-10-30 18:23:19.430502: train_loss -0.9907 +2025-10-30 18:23:19.432925: val_loss -0.9067 +2025-10-30 18:23:19.434756: Pseudo dice [np.float32(0.9846), np.float32(0.9918), np.float32(0.9953), np.float32(0.8298)] +2025-10-30 18:23:19.436578: Epoch time: 20.71 s +2025-10-30 18:23:20.648341: +2025-10-30 18:23:20.650806: Epoch 566 +2025-10-30 18:23:20.653017: Current learning rate: 0.00472 +2025-10-30 18:23:39.751494: train_loss -0.9907 +2025-10-30 18:23:39.753880: val_loss -0.909 +2025-10-30 18:23:39.755809: Pseudo dice [np.float32(0.985), np.float32(0.9917), np.float32(0.9953), np.float32(0.8304)] +2025-10-30 18:23:39.758200: Epoch time: 19.1 s +2025-10-30 18:23:40.791577: +2025-10-30 18:23:40.793426: Epoch 567 +2025-10-30 18:23:40.795451: Current learning rate: 0.00471 +2025-10-30 18:24:01.220722: train_loss -0.9911 +2025-10-30 18:24:01.223863: val_loss -0.8974 +2025-10-30 18:24:01.225468: Pseudo dice [np.float32(0.9822), np.float32(0.9905), np.float32(0.9954), np.float32(0.8144)] +2025-10-30 18:24:01.227168: Epoch time: 20.43 s +2025-10-30 18:24:02.341503: +2025-10-30 18:24:02.343336: Epoch 568 +2025-10-30 18:24:02.345009: Current learning rate: 0.0047 +2025-10-30 18:24:21.557012: train_loss -0.9907 +2025-10-30 18:24:21.559708: val_loss -0.9062 +2025-10-30 18:24:21.561326: Pseudo dice [np.float32(0.9839), np.float32(0.9916), np.float32(0.9956), np.float32(0.8349)] +2025-10-30 18:24:21.563040: Epoch time: 19.22 s +2025-10-30 18:24:23.411892: +2025-10-30 18:24:23.413623: Epoch 569 +2025-10-30 18:24:23.415446: Current learning rate: 0.00469 +2025-10-30 18:24:43.639248: train_loss -0.9903 +2025-10-30 18:24:43.641683: val_loss -0.9023 +2025-10-30 18:24:43.654956: Pseudo dice [np.float32(0.9838), np.float32(0.9909), np.float32(0.9952), np.float32(0.8205)] +2025-10-30 18:24:43.658295: Epoch time: 20.23 s +2025-10-30 18:24:44.899282: +2025-10-30 18:24:44.901163: Epoch 570 +2025-10-30 18:24:44.902793: Current learning rate: 0.00468 +2025-10-30 18:25:05.489810: train_loss -0.9902 +2025-10-30 18:25:05.500485: val_loss -0.8999 +2025-10-30 18:25:05.502598: Pseudo dice [np.float32(0.9846), np.float32(0.9918), np.float32(0.9949), np.float32(0.8086)] +2025-10-30 18:25:05.504587: Epoch time: 20.59 s +2025-10-30 18:25:06.745493: +2025-10-30 18:25:06.747975: Epoch 571 +2025-10-30 18:25:06.749876: Current learning rate: 0.00467 +2025-10-30 18:25:27.411332: train_loss -0.9904 +2025-10-30 18:25:27.413820: val_loss -0.8909 +2025-10-30 18:25:27.415534: Pseudo dice [np.float32(0.9827), np.float32(0.9896), np.float32(0.9948), np.float32(0.8065)] +2025-10-30 18:25:27.417243: Epoch time: 20.67 s +2025-10-30 18:25:28.605123: +2025-10-30 18:25:28.607087: Epoch 572 +2025-10-30 18:25:28.608755: Current learning rate: 0.00466 +2025-10-30 18:25:49.184050: train_loss -0.9902 +2025-10-30 18:25:49.186288: val_loss -0.8952 +2025-10-30 18:25:49.187969: Pseudo dice [np.float32(0.9829), np.float32(0.9905), np.float32(0.9951), np.float32(0.81)] +2025-10-30 18:25:49.189444: Epoch time: 20.58 s +2025-10-30 18:25:50.475786: +2025-10-30 18:25:50.478212: Epoch 573 +2025-10-30 18:25:50.480239: Current learning rate: 0.00465 +2025-10-30 18:26:10.338070: train_loss -0.9906 +2025-10-30 18:26:10.341615: val_loss -0.9149 +2025-10-30 18:26:10.343516: Pseudo dice [np.float32(0.9843), np.float32(0.9909), np.float32(0.9954), np.float32(0.8502)] +2025-10-30 18:26:10.345453: Epoch time: 19.86 s +2025-10-30 18:26:11.447565: +2025-10-30 18:26:11.449824: Epoch 574 +2025-10-30 18:26:11.451542: Current learning rate: 0.00464 +2025-10-30 18:26:30.927923: train_loss -0.9906 +2025-10-30 18:26:30.931002: val_loss -0.9042 +2025-10-30 18:26:30.932866: Pseudo dice [np.float32(0.9836), np.float32(0.9909), np.float32(0.9953), np.float32(0.8247)] +2025-10-30 18:26:30.934613: Epoch time: 19.48 s +2025-10-30 18:26:32.107473: +2025-10-30 18:26:32.109186: Epoch 575 +2025-10-30 18:26:32.110712: Current learning rate: 0.00463 +2025-10-30 18:26:52.938390: train_loss -0.9903 +2025-10-30 18:26:52.940672: val_loss -0.9078 +2025-10-30 18:26:52.942393: Pseudo dice [np.float32(0.9832), np.float32(0.9912), np.float32(0.9953), np.float32(0.8332)] +2025-10-30 18:26:52.943963: Epoch time: 20.83 s +2025-10-30 18:26:54.210081: +2025-10-30 18:26:54.212300: Epoch 576 +2025-10-30 18:26:54.213996: Current learning rate: 0.00462 +2025-10-30 18:27:14.607136: train_loss -0.9908 +2025-10-30 18:27:14.610424: val_loss -0.9 +2025-10-30 18:27:14.611906: Pseudo dice [np.float32(0.983), np.float32(0.99), np.float32(0.9953), np.float32(0.8271)] +2025-10-30 18:27:14.613439: Epoch time: 20.4 s +2025-10-30 18:27:15.628164: +2025-10-30 18:27:15.629865: Epoch 577 +2025-10-30 18:27:15.631373: Current learning rate: 0.00461 +2025-10-30 18:27:36.052049: train_loss -0.9904 +2025-10-30 18:27:36.054266: val_loss -0.91 +2025-10-30 18:27:36.055951: Pseudo dice [np.float32(0.9842), np.float32(0.9919), np.float32(0.9953), np.float32(0.833)] +2025-10-30 18:27:36.058646: Epoch time: 20.42 s +2025-10-30 18:27:37.088237: +2025-10-30 18:27:37.090528: Epoch 578 +2025-10-30 18:27:37.092938: Current learning rate: 0.0046 +2025-10-30 18:27:57.452340: train_loss -0.9898 +2025-10-30 18:27:57.455404: val_loss -0.8915 +2025-10-30 18:27:57.457415: Pseudo dice [np.float32(0.9842), np.float32(0.991), np.float32(0.9944), np.float32(0.796)] +2025-10-30 18:27:57.459662: Epoch time: 20.37 s +2025-10-30 18:27:58.755947: +2025-10-30 18:27:58.757777: Epoch 579 +2025-10-30 18:27:58.760081: Current learning rate: 0.00459 +2025-10-30 18:28:19.069689: train_loss -0.9911 +2025-10-30 18:28:19.072454: val_loss -0.8998 +2025-10-30 18:28:19.074198: Pseudo dice [np.float32(0.9846), np.float32(0.9911), np.float32(0.995), np.float32(0.8169)] +2025-10-30 18:28:19.076233: Epoch time: 20.32 s +2025-10-30 18:28:20.167658: +2025-10-30 18:28:20.170042: Epoch 580 +2025-10-30 18:28:20.171872: Current learning rate: 0.00458 +2025-10-30 18:28:38.532205: train_loss -0.9906 +2025-10-30 18:28:38.537310: val_loss -0.8974 +2025-10-30 18:28:38.539747: Pseudo dice [np.float32(0.9821), np.float32(0.9898), np.float32(0.9951), np.float32(0.8206)] +2025-10-30 18:28:38.541476: Epoch time: 18.37 s +2025-10-30 18:28:39.670277: +2025-10-30 18:28:39.672389: Epoch 581 +2025-10-30 18:28:39.674335: Current learning rate: 0.00457 +2025-10-30 18:29:01.358972: train_loss -0.9907 +2025-10-30 18:29:01.361306: val_loss -0.9025 +2025-10-30 18:29:01.362777: Pseudo dice [np.float32(0.985), np.float32(0.9911), np.float32(0.9949), np.float32(0.8195)] +2025-10-30 18:29:01.364178: Epoch time: 21.69 s +2025-10-30 18:29:03.658270: +2025-10-30 18:29:03.664148: Epoch 582 +2025-10-30 18:29:03.666261: Current learning rate: 0.00456 +2025-10-30 18:29:24.684132: train_loss -0.9915 +2025-10-30 18:29:24.686870: val_loss -0.8988 +2025-10-30 18:29:24.688416: Pseudo dice [np.float32(0.9836), np.float32(0.9909), np.float32(0.9951), np.float32(0.8215)] +2025-10-30 18:29:24.689863: Epoch time: 21.03 s +2025-10-30 18:29:25.922035: +2025-10-30 18:29:25.924534: Epoch 583 +2025-10-30 18:29:25.926608: Current learning rate: 0.00455 +2025-10-30 18:29:46.732688: train_loss -0.9911 +2025-10-30 18:29:46.736091: val_loss -0.9037 +2025-10-30 18:29:46.738491: Pseudo dice [np.float32(0.9829), np.float32(0.9907), np.float32(0.9953), np.float32(0.8281)] +2025-10-30 18:29:46.740455: Epoch time: 20.82 s +2025-10-30 18:29:48.043120: +2025-10-30 18:29:48.045573: Epoch 584 +2025-10-30 18:29:48.047516: Current learning rate: 0.00454 +2025-10-30 18:30:08.860945: train_loss -0.9912 +2025-10-30 18:30:08.863192: val_loss -0.9004 +2025-10-30 18:30:08.864970: Pseudo dice [np.float32(0.9846), np.float32(0.9912), np.float32(0.9951), np.float32(0.8246)] +2025-10-30 18:30:08.866725: Epoch time: 20.82 s +2025-10-30 18:30:09.933080: +2025-10-30 18:30:09.935217: Epoch 585 +2025-10-30 18:30:09.937029: Current learning rate: 0.00453 +2025-10-30 18:30:30.560152: train_loss -0.991 +2025-10-30 18:30:30.564297: val_loss -0.9011 +2025-10-30 18:30:30.566088: Pseudo dice [np.float32(0.9819), np.float32(0.9909), np.float32(0.9956), np.float32(0.8257)] +2025-10-30 18:30:30.568011: Epoch time: 20.63 s +2025-10-30 18:30:31.619375: +2025-10-30 18:30:31.621343: Epoch 586 +2025-10-30 18:30:31.623026: Current learning rate: 0.00452 +2025-10-30 18:30:50.804387: train_loss -0.9908 +2025-10-30 18:30:50.806812: val_loss -0.9017 +2025-10-30 18:30:50.808587: Pseudo dice [np.float32(0.9831), np.float32(0.9911), np.float32(0.9953), np.float32(0.8206)] +2025-10-30 18:30:50.810311: Epoch time: 19.19 s +2025-10-30 18:30:51.942900: +2025-10-30 18:30:51.950622: Epoch 587 +2025-10-30 18:30:51.955967: Current learning rate: 0.00451 +2025-10-30 18:31:11.859394: train_loss -0.9888 +2025-10-30 18:31:11.861604: val_loss -0.9054 +2025-10-30 18:31:11.863167: Pseudo dice [np.float32(0.9846), np.float32(0.9914), np.float32(0.9952), np.float32(0.831)] +2025-10-30 18:31:11.864713: Epoch time: 19.92 s +2025-10-30 18:31:13.007459: +2025-10-30 18:31:13.009603: Epoch 588 +2025-10-30 18:31:13.011582: Current learning rate: 0.0045 +2025-10-30 18:31:33.498095: train_loss -0.9908 +2025-10-30 18:31:33.501135: val_loss -0.9017 +2025-10-30 18:31:33.502811: Pseudo dice [np.float32(0.9842), np.float32(0.9916), np.float32(0.995), np.float32(0.8222)] +2025-10-30 18:31:33.504410: Epoch time: 20.49 s +2025-10-30 18:31:34.646720: +2025-10-30 18:31:34.648620: Epoch 589 +2025-10-30 18:31:34.650578: Current learning rate: 0.00449 +2025-10-30 18:31:54.953500: train_loss -0.9908 +2025-10-30 18:31:54.955720: val_loss -0.8974 +2025-10-30 18:31:54.957467: Pseudo dice [np.float32(0.9826), np.float32(0.9907), np.float32(0.9951), np.float32(0.8133)] +2025-10-30 18:31:54.959085: Epoch time: 20.31 s +2025-10-30 18:31:56.096966: +2025-10-30 18:31:56.099029: Epoch 590 +2025-10-30 18:31:56.100766: Current learning rate: 0.00448 +2025-10-30 18:32:16.583255: train_loss -0.9902 +2025-10-30 18:32:16.585136: val_loss -0.9019 +2025-10-30 18:32:16.586782: Pseudo dice [np.float32(0.9847), np.float32(0.9913), np.float32(0.9949), np.float32(0.8157)] +2025-10-30 18:32:16.588374: Epoch time: 20.49 s +2025-10-30 18:32:17.606607: +2025-10-30 18:32:17.608651: Epoch 591 +2025-10-30 18:32:17.610341: Current learning rate: 0.00447 +2025-10-30 18:32:38.341012: train_loss -0.9902 +2025-10-30 18:32:38.345531: val_loss -0.8942 +2025-10-30 18:32:38.347406: Pseudo dice [np.float32(0.984), np.float32(0.9907), np.float32(0.9947), np.float32(0.7984)] +2025-10-30 18:32:38.349109: Epoch time: 20.74 s +2025-10-30 18:32:39.600486: +2025-10-30 18:32:39.602222: Epoch 592 +2025-10-30 18:32:39.603746: Current learning rate: 0.00446 +2025-10-30 18:33:00.239142: train_loss -0.9903 +2025-10-30 18:33:00.241527: val_loss -0.9018 +2025-10-30 18:33:00.242996: Pseudo dice [np.float32(0.9839), np.float32(0.9913), np.float32(0.9952), np.float32(0.816)] +2025-10-30 18:33:00.244584: Epoch time: 20.64 s +2025-10-30 18:33:01.817296: +2025-10-30 18:33:01.819732: Epoch 593 +2025-10-30 18:33:01.821402: Current learning rate: 0.00445 +2025-10-30 18:33:19.761496: train_loss -0.9907 +2025-10-30 18:33:19.764755: val_loss -0.895 +2025-10-30 18:33:19.767690: Pseudo dice [np.float32(0.9823), np.float32(0.9905), np.float32(0.9947), np.float32(0.8111)] +2025-10-30 18:33:19.770480: Epoch time: 17.95 s +2025-10-30 18:33:20.764574: +2025-10-30 18:33:20.766572: Epoch 594 +2025-10-30 18:33:20.767998: Current learning rate: 0.00444 +2025-10-30 18:33:41.532418: train_loss -0.9904 +2025-10-30 18:33:41.535281: val_loss -0.9031 +2025-10-30 18:33:41.537378: Pseudo dice [np.float32(0.9831), np.float32(0.9912), np.float32(0.9953), np.float32(0.823)] +2025-10-30 18:33:41.539893: Epoch time: 20.77 s +2025-10-30 18:33:42.600605: +2025-10-30 18:33:42.602600: Epoch 595 +2025-10-30 18:33:42.604394: Current learning rate: 0.00443 +2025-10-30 18:34:03.081589: train_loss -0.991 +2025-10-30 18:34:03.092520: val_loss -0.8932 +2025-10-30 18:34:03.094896: Pseudo dice [np.float32(0.9825), np.float32(0.9906), np.float32(0.9949), np.float32(0.8071)] +2025-10-30 18:34:03.097441: Epoch time: 20.48 s +2025-10-30 18:34:04.168991: +2025-10-30 18:34:04.171601: Epoch 596 +2025-10-30 18:34:04.173412: Current learning rate: 0.00442 +2025-10-30 18:34:24.641303: train_loss -0.9911 +2025-10-30 18:34:24.643710: val_loss -0.8989 +2025-10-30 18:34:24.645398: Pseudo dice [np.float32(0.9842), np.float32(0.9904), np.float32(0.9946), np.float32(0.8196)] +2025-10-30 18:34:24.647084: Epoch time: 20.47 s +2025-10-30 18:34:25.676333: +2025-10-30 18:34:25.678502: Epoch 597 +2025-10-30 18:34:25.680435: Current learning rate: 0.00441 +2025-10-30 18:34:46.071052: train_loss -0.9916 +2025-10-30 18:34:46.074362: val_loss -0.8983 +2025-10-30 18:34:46.076098: Pseudo dice [np.float32(0.9814), np.float32(0.9896), np.float32(0.9952), np.float32(0.8209)] +2025-10-30 18:34:46.077792: Epoch time: 20.4 s +2025-10-30 18:34:47.105717: +2025-10-30 18:34:47.107491: Epoch 598 +2025-10-30 18:34:47.108987: Current learning rate: 0.0044 +2025-10-30 18:35:07.323785: train_loss -0.9914 +2025-10-30 18:35:07.326083: val_loss -0.8983 +2025-10-30 18:35:07.328638: Pseudo dice [np.float32(0.9838), np.float32(0.9906), np.float32(0.9951), np.float32(0.8219)] +2025-10-30 18:35:07.331010: Epoch time: 20.22 s +2025-10-30 18:35:08.531155: +2025-10-30 18:35:08.533744: Epoch 599 +2025-10-30 18:35:08.536161: Current learning rate: 0.00439 +2025-10-30 18:35:28.710200: train_loss -0.9912 +2025-10-30 18:35:28.712314: val_loss -0.9071 +2025-10-30 18:35:28.714091: Pseudo dice [np.float32(0.9838), np.float32(0.9911), np.float32(0.9954), np.float32(0.8362)] +2025-10-30 18:35:28.715832: Epoch time: 20.18 s +2025-10-30 18:35:31.296674: +2025-10-30 18:35:31.299137: Epoch 600 +2025-10-30 18:35:31.301119: Current learning rate: 0.00438 +2025-10-30 18:35:50.206205: train_loss -0.9904 +2025-10-30 18:35:50.208871: val_loss -0.907 +2025-10-30 18:35:50.210614: Pseudo dice [np.float32(0.9832), np.float32(0.9906), np.float32(0.9956), np.float32(0.8367)] +2025-10-30 18:35:50.212065: Epoch time: 18.91 s +2025-10-30 18:35:51.316195: +2025-10-30 18:35:51.319286: Epoch 601 +2025-10-30 18:35:51.322424: Current learning rate: 0.00437 +2025-10-30 18:36:11.628878: train_loss -0.9903 +2025-10-30 18:36:11.631544: val_loss -0.9007 +2025-10-30 18:36:11.633433: Pseudo dice [np.float32(0.9826), np.float32(0.9907), np.float32(0.9949), np.float32(0.8203)] +2025-10-30 18:36:11.636455: Epoch time: 20.31 s +2025-10-30 18:36:12.674887: +2025-10-30 18:36:12.676755: Epoch 602 +2025-10-30 18:36:12.678659: Current learning rate: 0.00436 +2025-10-30 18:36:33.649892: train_loss -0.9898 +2025-10-30 18:36:33.652450: val_loss -0.9015 +2025-10-30 18:36:33.654702: Pseudo dice [np.float32(0.9826), np.float32(0.9906), np.float32(0.9948), np.float32(0.8253)] +2025-10-30 18:36:33.656468: Epoch time: 20.98 s +2025-10-30 18:36:34.917695: +2025-10-30 18:36:34.920163: Epoch 603 +2025-10-30 18:36:34.923485: Current learning rate: 0.00435 +2025-10-30 18:36:55.617587: train_loss -0.9901 +2025-10-30 18:36:55.621341: val_loss -0.8996 +2025-10-30 18:36:55.623429: Pseudo dice [np.float32(0.9842), np.float32(0.9915), np.float32(0.9949), np.float32(0.8131)] +2025-10-30 18:36:55.625680: Epoch time: 20.7 s +2025-10-30 18:36:56.763601: +2025-10-30 18:36:56.765447: Epoch 604 +2025-10-30 18:36:56.767319: Current learning rate: 0.00434 +2025-10-30 18:37:17.293576: train_loss -0.9902 +2025-10-30 18:37:17.295850: val_loss -0.9008 +2025-10-30 18:37:17.297503: Pseudo dice [np.float32(0.9834), np.float32(0.9914), np.float32(0.9949), np.float32(0.8117)] +2025-10-30 18:37:17.299250: Epoch time: 20.53 s +2025-10-30 18:37:18.375561: +2025-10-30 18:37:18.377634: Epoch 605 +2025-10-30 18:37:18.379422: Current learning rate: 0.00433 +2025-10-30 18:37:39.138481: train_loss -0.9909 +2025-10-30 18:37:39.140780: val_loss -0.9051 +2025-10-30 18:37:39.142598: Pseudo dice [np.float32(0.9836), np.float32(0.9914), np.float32(0.9952), np.float32(0.8256)] +2025-10-30 18:37:39.144476: Epoch time: 20.76 s +2025-10-30 18:37:40.796840: +2025-10-30 18:37:40.800150: Epoch 606 +2025-10-30 18:37:40.802106: Current learning rate: 0.00432 +2025-10-30 18:38:00.688007: train_loss -0.9911 +2025-10-30 18:38:00.691488: val_loss -0.9092 +2025-10-30 18:38:00.693581: Pseudo dice [np.float32(0.9847), np.float32(0.9917), np.float32(0.9954), np.float32(0.8335)] +2025-10-30 18:38:00.695150: Epoch time: 19.89 s +2025-10-30 18:38:01.878866: +2025-10-30 18:38:01.880839: Epoch 607 +2025-10-30 18:38:01.882602: Current learning rate: 0.00431 +2025-10-30 18:38:22.792068: train_loss -0.9909 +2025-10-30 18:38:22.797413: val_loss -0.9033 +2025-10-30 18:38:22.799052: Pseudo dice [np.float32(0.983), np.float32(0.9902), np.float32(0.9949), np.float32(0.8266)] +2025-10-30 18:38:22.800642: Epoch time: 20.92 s +2025-10-30 18:38:23.865400: +2025-10-30 18:38:23.867199: Epoch 608 +2025-10-30 18:38:23.868969: Current learning rate: 0.0043 +2025-10-30 18:38:44.437321: train_loss -0.9905 +2025-10-30 18:38:44.439413: val_loss -0.9038 +2025-10-30 18:38:44.441026: Pseudo dice [np.float32(0.9848), np.float32(0.9918), np.float32(0.9951), np.float32(0.8143)] +2025-10-30 18:38:44.442485: Epoch time: 20.57 s +2025-10-30 18:38:45.680935: +2025-10-30 18:38:45.683049: Epoch 609 +2025-10-30 18:38:45.684994: Current learning rate: 0.00429 +2025-10-30 18:39:06.294135: train_loss -0.9903 +2025-10-30 18:39:06.297039: val_loss -0.8988 +2025-10-30 18:39:06.298638: Pseudo dice [np.float32(0.9836), np.float32(0.9917), np.float32(0.995), np.float32(0.8102)] +2025-10-30 18:39:06.300205: Epoch time: 20.62 s +2025-10-30 18:39:07.544045: +2025-10-30 18:39:07.546074: Epoch 610 +2025-10-30 18:39:07.547975: Current learning rate: 0.00429 +2025-10-30 18:39:27.943496: train_loss -0.9906 +2025-10-30 18:39:27.948466: val_loss -0.9017 +2025-10-30 18:39:27.950023: Pseudo dice [np.float32(0.9836), np.float32(0.991), np.float32(0.9949), np.float32(0.8236)] +2025-10-30 18:39:27.951419: Epoch time: 20.4 s +2025-10-30 18:39:29.087621: +2025-10-30 18:39:29.089789: Epoch 611 +2025-10-30 18:39:29.091489: Current learning rate: 0.00428 +2025-10-30 18:39:49.528221: train_loss -0.991 +2025-10-30 18:39:49.530811: val_loss -0.8976 +2025-10-30 18:39:49.533330: Pseudo dice [np.float32(0.9827), np.float32(0.9914), np.float32(0.9951), np.float32(0.8093)] +2025-10-30 18:39:49.535433: Epoch time: 20.44 s +2025-10-30 18:39:50.622462: +2025-10-30 18:39:50.624590: Epoch 612 +2025-10-30 18:39:50.626417: Current learning rate: 0.00427 +2025-10-30 18:40:10.561272: train_loss -0.9909 +2025-10-30 18:40:10.564205: val_loss -0.893 +2025-10-30 18:40:10.566252: Pseudo dice [np.float32(0.9826), np.float32(0.9899), np.float32(0.9946), np.float32(0.806)] +2025-10-30 18:40:10.567835: Epoch time: 19.94 s +2025-10-30 18:40:11.782097: +2025-10-30 18:40:11.785089: Epoch 613 +2025-10-30 18:40:11.786854: Current learning rate: 0.00426 +2025-10-30 18:40:30.787791: train_loss -0.9915 +2025-10-30 18:40:30.790108: val_loss -0.8993 +2025-10-30 18:40:30.791913: Pseudo dice [np.float32(0.985), np.float32(0.9915), np.float32(0.9951), np.float32(0.8137)] +2025-10-30 18:40:30.793679: Epoch time: 19.01 s +2025-10-30 18:40:31.868704: +2025-10-30 18:40:31.870912: Epoch 614 +2025-10-30 18:40:31.872807: Current learning rate: 0.00425 +2025-10-30 18:40:52.438408: train_loss -0.9908 +2025-10-30 18:40:52.444698: val_loss -0.9008 +2025-10-30 18:40:52.447038: Pseudo dice [np.float32(0.9821), np.float32(0.9909), np.float32(0.9954), np.float32(0.8284)] +2025-10-30 18:40:52.449480: Epoch time: 20.57 s +2025-10-30 18:40:53.574973: +2025-10-30 18:40:53.577144: Epoch 615 +2025-10-30 18:40:53.578922: Current learning rate: 0.00424 +2025-10-30 18:41:14.226061: train_loss -0.9907 +2025-10-30 18:41:14.229267: val_loss -0.8981 +2025-10-30 18:41:14.231271: Pseudo dice [np.float32(0.9845), np.float32(0.9917), np.float32(0.9952), np.float32(0.8094)] +2025-10-30 18:41:14.233219: Epoch time: 20.65 s +2025-10-30 18:41:15.523749: +2025-10-30 18:41:15.525784: Epoch 616 +2025-10-30 18:41:15.527442: Current learning rate: 0.00423 +2025-10-30 18:41:36.168643: train_loss -0.9909 +2025-10-30 18:41:36.170762: val_loss -0.9033 +2025-10-30 18:41:36.172461: Pseudo dice [np.float32(0.984), np.float32(0.9915), np.float32(0.9952), np.float32(0.826)] +2025-10-30 18:41:36.175056: Epoch time: 20.65 s +2025-10-30 18:41:37.476218: +2025-10-30 18:41:37.478003: Epoch 617 +2025-10-30 18:41:37.480003: Current learning rate: 0.00422 +2025-10-30 18:41:57.854593: train_loss -0.9915 +2025-10-30 18:41:57.857085: val_loss -0.9039 +2025-10-30 18:41:57.859771: Pseudo dice [np.float32(0.9833), np.float32(0.9911), np.float32(0.9955), np.float32(0.8268)] +2025-10-30 18:41:57.861299: Epoch time: 20.38 s +2025-10-30 18:41:59.358624: +2025-10-30 18:41:59.360561: Epoch 618 +2025-10-30 18:41:59.362368: Current learning rate: 0.00421 +2025-10-30 18:42:18.780371: train_loss -0.991 +2025-10-30 18:42:18.783498: val_loss -0.8947 +2025-10-30 18:42:18.786503: Pseudo dice [np.float32(0.9838), np.float32(0.9911), np.float32(0.9951), np.float32(0.7958)] +2025-10-30 18:42:18.788907: Epoch time: 19.42 s +2025-10-30 18:42:19.825202: +2025-10-30 18:42:19.827268: Epoch 619 +2025-10-30 18:42:19.829035: Current learning rate: 0.0042 +2025-10-30 18:42:40.359662: train_loss -0.9901 +2025-10-30 18:42:40.361709: val_loss -0.9044 +2025-10-30 18:42:40.363404: Pseudo dice [np.float32(0.9843), np.float32(0.9915), np.float32(0.9952), np.float32(0.8133)] +2025-10-30 18:42:40.364936: Epoch time: 20.54 s +2025-10-30 18:42:41.316215: +2025-10-30 18:42:41.318142: Epoch 620 +2025-10-30 18:42:41.320036: Current learning rate: 0.00419 +2025-10-30 18:43:01.011175: train_loss -0.9908 +2025-10-30 18:43:01.013310: val_loss -0.8974 +2025-10-30 18:43:01.014957: Pseudo dice [np.float32(0.9834), np.float32(0.9907), np.float32(0.9953), np.float32(0.814)] +2025-10-30 18:43:01.016937: Epoch time: 19.7 s +2025-10-30 18:43:02.168767: +2025-10-30 18:43:02.170747: Epoch 621 +2025-10-30 18:43:02.172483: Current learning rate: 0.00418 +2025-10-30 18:43:22.578058: train_loss -0.9896 +2025-10-30 18:43:22.588917: val_loss -0.9016 +2025-10-30 18:43:22.590879: Pseudo dice [np.float32(0.9823), np.float32(0.9903), np.float32(0.995), np.float32(0.823)] +2025-10-30 18:43:22.592985: Epoch time: 20.41 s +2025-10-30 18:43:23.971457: +2025-10-30 18:43:23.973204: Epoch 622 +2025-10-30 18:43:23.975324: Current learning rate: 0.00417 +2025-10-30 18:43:44.438624: train_loss -0.99 +2025-10-30 18:43:44.441322: val_loss -0.9039 +2025-10-30 18:43:44.443178: Pseudo dice [np.float32(0.9828), np.float32(0.9905), np.float32(0.9952), np.float32(0.8237)] +2025-10-30 18:43:44.450983: Epoch time: 20.47 s +2025-10-30 18:43:45.631022: +2025-10-30 18:43:45.632981: Epoch 623 +2025-10-30 18:43:45.635022: Current learning rate: 0.00416 +2025-10-30 18:44:06.022990: train_loss -0.9892 +2025-10-30 18:44:06.025156: val_loss -0.9082 +2025-10-30 18:44:06.027162: Pseudo dice [np.float32(0.983), np.float32(0.9905), np.float32(0.9952), np.float32(0.842)] +2025-10-30 18:44:06.029531: Epoch time: 20.39 s +2025-10-30 18:44:07.061922: +2025-10-30 18:44:07.063705: Epoch 624 +2025-10-30 18:44:07.065265: Current learning rate: 0.00415 +2025-10-30 18:44:27.776969: train_loss -0.9865 +2025-10-30 18:44:27.779757: val_loss -0.8976 +2025-10-30 18:44:27.781340: Pseudo dice [np.float32(0.9828), np.float32(0.9901), np.float32(0.9946), np.float32(0.809)] +2025-10-30 18:44:27.783321: Epoch time: 20.72 s +2025-10-30 18:44:29.136914: +2025-10-30 18:44:29.138817: Epoch 625 +2025-10-30 18:44:29.140667: Current learning rate: 0.00414 +2025-10-30 18:44:48.906777: train_loss -0.9688 +2025-10-30 18:44:48.908958: val_loss -0.9004 +2025-10-30 18:44:48.910673: Pseudo dice [np.float32(0.9812), np.float32(0.9904), np.float32(0.9942), np.float32(0.7869)] +2025-10-30 18:44:48.912305: Epoch time: 19.77 s +2025-10-30 18:44:50.047646: +2025-10-30 18:44:50.049814: Epoch 626 +2025-10-30 18:44:50.051373: Current learning rate: 0.00413 +2025-10-30 18:45:10.863627: train_loss -0.9139 +2025-10-30 18:45:10.865972: val_loss -0.9123 +2025-10-30 18:45:10.867642: Pseudo dice [np.float32(0.9846), np.float32(0.9912), np.float32(0.9948), np.float32(0.7975)] +2025-10-30 18:45:10.869517: Epoch time: 20.82 s +2025-10-30 18:45:11.999034: +2025-10-30 18:45:12.001464: Epoch 627 +2025-10-30 18:45:12.004163: Current learning rate: 0.00412 +2025-10-30 18:45:31.883716: train_loss -0.924 +2025-10-30 18:45:31.886875: val_loss -0.9232 +2025-10-30 18:45:31.888771: Pseudo dice [np.float32(0.9843), np.float32(0.9906), np.float32(0.995), np.float32(0.8276)] +2025-10-30 18:45:31.890805: Epoch time: 19.89 s +2025-10-30 18:45:33.144008: +2025-10-30 18:45:33.146516: Epoch 628 +2025-10-30 18:45:33.148241: Current learning rate: 0.00411 +2025-10-30 18:45:53.376503: train_loss -0.9467 +2025-10-30 18:45:53.378569: val_loss -0.9161 +2025-10-30 18:45:53.380173: Pseudo dice [np.float32(0.9839), np.float32(0.9906), np.float32(0.9945), np.float32(0.8127)] +2025-10-30 18:45:53.381588: Epoch time: 20.23 s +2025-10-30 18:45:54.529671: +2025-10-30 18:45:54.531489: Epoch 629 +2025-10-30 18:45:54.533005: Current learning rate: 0.0041 +2025-10-30 18:46:14.860864: train_loss -0.9633 +2025-10-30 18:46:14.863059: val_loss -0.9069 +2025-10-30 18:46:14.864659: Pseudo dice [np.float32(0.982), np.float32(0.9897), np.float32(0.9939), np.float32(0.7963)] +2025-10-30 18:46:14.866939: Epoch time: 20.33 s +2025-10-30 18:46:16.315682: +2025-10-30 18:46:16.317557: Epoch 630 +2025-10-30 18:46:16.319217: Current learning rate: 0.00409 +2025-10-30 18:46:36.900679: train_loss -0.9742 +2025-10-30 18:46:36.906974: val_loss -0.9078 +2025-10-30 18:46:36.908383: Pseudo dice [np.float32(0.9841), np.float32(0.9911), np.float32(0.9933), np.float32(0.8097)] +2025-10-30 18:46:36.910002: Epoch time: 20.59 s +2025-10-30 18:46:37.924694: +2025-10-30 18:46:37.926395: Epoch 631 +2025-10-30 18:46:37.927839: Current learning rate: 0.00408 +2025-10-30 18:46:57.221608: train_loss -0.9799 +2025-10-30 18:46:57.223827: val_loss -0.916 +2025-10-30 18:46:57.225479: Pseudo dice [np.float32(0.9833), np.float32(0.9898), np.float32(0.995), np.float32(0.8352)] +2025-10-30 18:46:57.227104: Epoch time: 19.3 s +2025-10-30 18:46:58.426827: +2025-10-30 18:46:58.428679: Epoch 632 +2025-10-30 18:46:58.430378: Current learning rate: 0.00407 +2025-10-30 18:47:19.374905: train_loss -0.9824 +2025-10-30 18:47:19.377299: val_loss -0.9148 +2025-10-30 18:47:19.379226: Pseudo dice [np.float32(0.9852), np.float32(0.9908), np.float32(0.9953), np.float32(0.8327)] +2025-10-30 18:47:19.381024: Epoch time: 20.95 s +2025-10-30 18:47:20.492949: +2025-10-30 18:47:20.495085: Epoch 633 +2025-10-30 18:47:20.496696: Current learning rate: 0.00406 +2025-10-30 18:47:40.841812: train_loss -0.9812 +2025-10-30 18:47:40.845698: val_loss -0.8983 +2025-10-30 18:47:40.847595: Pseudo dice [np.float32(0.982), np.float32(0.9902), np.float32(0.995), np.float32(0.795)] +2025-10-30 18:47:40.849453: Epoch time: 20.35 s +2025-10-30 18:47:41.915546: +2025-10-30 18:47:41.917406: Epoch 634 +2025-10-30 18:47:41.919234: Current learning rate: 0.00405 +2025-10-30 18:48:02.028805: train_loss -0.9819 +2025-10-30 18:48:02.031098: val_loss -0.9022 +2025-10-30 18:48:02.032873: Pseudo dice [np.float32(0.9853), np.float32(0.9907), np.float32(0.9945), np.float32(0.8039)] +2025-10-30 18:48:02.034879: Epoch time: 20.11 s +2025-10-30 18:48:03.072117: +2025-10-30 18:48:03.074058: Epoch 635 +2025-10-30 18:48:03.075593: Current learning rate: 0.00404 +2025-10-30 18:48:23.973591: train_loss -0.9843 +2025-10-30 18:48:23.976002: val_loss -0.9104 +2025-10-30 18:48:23.977593: Pseudo dice [np.float32(0.9826), np.float32(0.99), np.float32(0.995), np.float32(0.8365)] +2025-10-30 18:48:23.979303: Epoch time: 20.9 s +2025-10-30 18:48:25.326351: +2025-10-30 18:48:25.328467: Epoch 636 +2025-10-30 18:48:25.330023: Current learning rate: 0.00403 +2025-10-30 18:48:45.984531: train_loss -0.9837 +2025-10-30 18:48:45.987398: val_loss -0.9022 +2025-10-30 18:48:45.989071: Pseudo dice [np.float32(0.9818), np.float32(0.9902), np.float32(0.9941), np.float32(0.8079)] +2025-10-30 18:48:45.990759: Epoch time: 20.66 s +2025-10-30 18:48:47.202840: +2025-10-30 18:48:47.204978: Epoch 637 +2025-10-30 18:48:47.206739: Current learning rate: 0.00402 +2025-10-30 18:49:06.728370: train_loss -0.9831 +2025-10-30 18:49:06.730854: val_loss -0.9038 +2025-10-30 18:49:06.732584: Pseudo dice [np.float32(0.9825), np.float32(0.9904), np.float32(0.9946), np.float32(0.8074)] +2025-10-30 18:49:06.734397: Epoch time: 19.53 s +2025-10-30 18:49:07.957080: +2025-10-30 18:49:07.959078: Epoch 638 +2025-10-30 18:49:07.960648: Current learning rate: 0.00401 +2025-10-30 18:49:28.712033: train_loss -0.9876 +2025-10-30 18:49:28.714530: val_loss -0.9076 +2025-10-30 18:49:28.716310: Pseudo dice [np.float32(0.9837), np.float32(0.9911), np.float32(0.9952), np.float32(0.8288)] +2025-10-30 18:49:28.717854: Epoch time: 20.76 s +2025-10-30 18:49:29.825275: +2025-10-30 18:49:29.827236: Epoch 639 +2025-10-30 18:49:29.829386: Current learning rate: 0.004 +2025-10-30 18:49:50.665511: train_loss -0.9843 +2025-10-30 18:49:50.669106: val_loss -0.9055 +2025-10-30 18:49:50.670923: Pseudo dice [np.float32(0.9826), np.float32(0.9905), np.float32(0.9948), np.float32(0.8176)] +2025-10-30 18:49:50.672626: Epoch time: 20.84 s +2025-10-30 18:49:51.868319: +2025-10-30 18:49:51.870407: Epoch 640 +2025-10-30 18:49:51.872350: Current learning rate: 0.00399 +2025-10-30 18:50:11.618125: train_loss -0.9875 +2025-10-30 18:50:11.621301: val_loss -0.9056 +2025-10-30 18:50:11.623474: Pseudo dice [np.float32(0.9838), np.float32(0.9907), np.float32(0.9954), np.float32(0.8192)] +2025-10-30 18:50:11.625458: Epoch time: 19.75 s +2025-10-30 18:50:12.646326: +2025-10-30 18:50:12.648153: Epoch 641 +2025-10-30 18:50:12.649542: Current learning rate: 0.00398 +2025-10-30 18:50:33.188876: train_loss -0.9879 +2025-10-30 18:50:33.190845: val_loss -0.9011 +2025-10-30 18:50:33.192631: Pseudo dice [np.float32(0.9837), np.float32(0.9883), np.float32(0.9938), np.float32(0.8143)] +2025-10-30 18:50:33.194761: Epoch time: 20.54 s +2025-10-30 18:50:34.812010: +2025-10-30 18:50:34.814393: Epoch 642 +2025-10-30 18:50:34.816436: Current learning rate: 0.00397 +2025-10-30 18:50:55.084506: train_loss -0.9873 +2025-10-30 18:50:55.087809: val_loss -0.9053 +2025-10-30 18:50:55.089798: Pseudo dice [np.float32(0.983), np.float32(0.9904), np.float32(0.9946), np.float32(0.8132)] +2025-10-30 18:50:55.091505: Epoch time: 20.27 s +2025-10-30 18:50:56.156754: +2025-10-30 18:50:56.158600: Epoch 643 +2025-10-30 18:50:56.160217: Current learning rate: 0.00396 +2025-10-30 18:51:16.685534: train_loss -0.9874 +2025-10-30 18:51:16.688046: val_loss -0.9106 +2025-10-30 18:51:16.689856: Pseudo dice [np.float32(0.9831), np.float32(0.9909), np.float32(0.9953), np.float32(0.8305)] +2025-10-30 18:51:16.692704: Epoch time: 20.53 s +2025-10-30 18:51:17.911331: +2025-10-30 18:51:17.914062: Epoch 644 +2025-10-30 18:51:17.915717: Current learning rate: 0.00395 +2025-10-30 18:51:37.780670: train_loss -0.987 +2025-10-30 18:51:37.782882: val_loss -0.9011 +2025-10-30 18:51:37.784914: Pseudo dice [np.float32(0.9819), np.float32(0.99), np.float32(0.9949), np.float32(0.8115)] +2025-10-30 18:51:37.786481: Epoch time: 19.87 s +2025-10-30 18:51:38.897133: +2025-10-30 18:51:38.899159: Epoch 645 +2025-10-30 18:51:38.900835: Current learning rate: 0.00394 +2025-10-30 18:51:59.080125: train_loss -0.989 +2025-10-30 18:51:59.083214: val_loss -0.9175 +2025-10-30 18:51:59.084943: Pseudo dice [np.float32(0.9836), np.float32(0.9909), np.float32(0.9953), np.float32(0.8497)] +2025-10-30 18:51:59.086578: Epoch time: 20.18 s +2025-10-30 18:52:00.175435: +2025-10-30 18:52:00.177219: Epoch 646 +2025-10-30 18:52:00.178883: Current learning rate: 0.00393 +2025-10-30 18:52:20.350989: train_loss -0.9891 +2025-10-30 18:52:20.355820: val_loss -0.9041 +2025-10-30 18:52:20.362509: Pseudo dice [np.float32(0.9824), np.float32(0.9905), np.float32(0.9952), np.float32(0.816)] +2025-10-30 18:52:20.364483: Epoch time: 20.18 s +2025-10-30 18:52:21.527176: +2025-10-30 18:52:21.531575: Epoch 647 +2025-10-30 18:52:21.533195: Current learning rate: 0.00392 +2025-10-30 18:52:38.173298: train_loss -0.9879 +2025-10-30 18:52:38.179682: val_loss -0.9026 +2025-10-30 18:52:38.186244: Pseudo dice [np.float32(0.9816), np.float32(0.9895), np.float32(0.995), np.float32(0.8227)] +2025-10-30 18:52:38.191955: Epoch time: 16.65 s +2025-10-30 18:52:39.439811: +2025-10-30 18:52:39.448196: Epoch 648 +2025-10-30 18:52:39.457520: Current learning rate: 0.00391 +2025-10-30 18:52:59.389092: train_loss -0.9883 +2025-10-30 18:52:59.391664: val_loss -0.9072 +2025-10-30 18:52:59.393445: Pseudo dice [np.float32(0.9828), np.float32(0.9902), np.float32(0.9952), np.float32(0.8299)] +2025-10-30 18:52:59.394925: Epoch time: 19.95 s +2025-10-30 18:53:00.667923: +2025-10-30 18:53:00.669930: Epoch 649 +2025-10-30 18:53:00.671790: Current learning rate: 0.0039 +2025-10-30 18:53:21.288665: train_loss -0.9876 +2025-10-30 18:53:21.290869: val_loss -0.9082 +2025-10-30 18:53:21.292824: Pseudo dice [np.float32(0.9842), np.float32(0.9912), np.float32(0.9951), np.float32(0.83)] +2025-10-30 18:53:21.294366: Epoch time: 20.62 s +2025-10-30 18:53:23.508503: +2025-10-30 18:53:23.510496: Epoch 650 +2025-10-30 18:53:23.513327: Current learning rate: 0.00389 +2025-10-30 18:53:43.166815: train_loss -0.9887 +2025-10-30 18:53:43.168890: val_loss -0.9031 +2025-10-30 18:53:43.170673: Pseudo dice [np.float32(0.9823), np.float32(0.9906), np.float32(0.9946), np.float32(0.8205)] +2025-10-30 18:53:43.173128: Epoch time: 19.66 s +2025-10-30 18:53:44.189459: +2025-10-30 18:53:44.192248: Epoch 651 +2025-10-30 18:53:44.195876: Current learning rate: 0.00388 +2025-10-30 18:54:05.020779: train_loss -0.9897 +2025-10-30 18:54:05.032275: val_loss -0.8974 +2025-10-30 18:54:05.036598: Pseudo dice [np.float32(0.9828), np.float32(0.9896), np.float32(0.995), np.float32(0.8128)] +2025-10-30 18:54:05.039799: Epoch time: 20.83 s +2025-10-30 18:54:06.297153: +2025-10-30 18:54:06.299480: Epoch 652 +2025-10-30 18:54:06.301142: Current learning rate: 0.00387 +2025-10-30 18:54:27.191473: train_loss -0.9897 +2025-10-30 18:54:27.196991: val_loss -0.8992 +2025-10-30 18:54:27.198861: Pseudo dice [np.float32(0.9837), np.float32(0.991), np.float32(0.9945), np.float32(0.8096)] +2025-10-30 18:54:27.200656: Epoch time: 20.9 s +2025-10-30 18:54:28.287379: +2025-10-30 18:54:28.289428: Epoch 653 +2025-10-30 18:54:28.291170: Current learning rate: 0.00386 +2025-10-30 18:54:49.187781: train_loss -0.9897 +2025-10-30 18:54:49.191810: val_loss -0.9116 +2025-10-30 18:54:49.193845: Pseudo dice [np.float32(0.9828), np.float32(0.9907), np.float32(0.9953), np.float32(0.8408)] +2025-10-30 18:54:49.195707: Epoch time: 20.9 s +2025-10-30 18:54:51.192774: +2025-10-30 18:54:51.194991: Epoch 654 +2025-10-30 18:54:51.196702: Current learning rate: 0.00385 +2025-10-30 18:55:11.235382: train_loss -0.9899 +2025-10-30 18:55:11.239861: val_loss -0.9081 +2025-10-30 18:55:11.241452: Pseudo dice [np.float32(0.9838), np.float32(0.9908), np.float32(0.995), np.float32(0.8304)] +2025-10-30 18:55:11.243006: Epoch time: 20.04 s +2025-10-30 18:55:12.499140: +2025-10-30 18:55:12.500958: Epoch 655 +2025-10-30 18:55:12.502715: Current learning rate: 0.00384 +2025-10-30 18:55:33.229977: train_loss -0.9902 +2025-10-30 18:55:33.233413: val_loss -0.9021 +2025-10-30 18:55:33.235216: Pseudo dice [np.float32(0.9833), np.float32(0.9909), np.float32(0.9952), np.float32(0.8137)] +2025-10-30 18:55:33.237242: Epoch time: 20.73 s +2025-10-30 18:55:34.428839: +2025-10-30 18:55:34.434460: Epoch 656 +2025-10-30 18:55:34.436238: Current learning rate: 0.00383 +2025-10-30 18:55:54.245150: train_loss -0.9904 +2025-10-30 18:55:54.247643: val_loss -0.9082 +2025-10-30 18:55:54.249493: Pseudo dice [np.float32(0.9835), np.float32(0.9911), np.float32(0.9951), np.float32(0.8319)] +2025-10-30 18:55:54.251283: Epoch time: 19.82 s +2025-10-30 18:55:55.479008: +2025-10-30 18:55:55.480881: Epoch 657 +2025-10-30 18:55:55.482621: Current learning rate: 0.00382 +2025-10-30 18:56:16.542822: train_loss -0.9908 +2025-10-30 18:56:16.547319: val_loss -0.9033 +2025-10-30 18:56:16.549062: Pseudo dice [np.float32(0.9823), np.float32(0.9906), np.float32(0.9951), np.float32(0.827)] +2025-10-30 18:56:16.550916: Epoch time: 21.07 s +2025-10-30 18:56:17.618154: +2025-10-30 18:56:17.620129: Epoch 658 +2025-10-30 18:56:17.622486: Current learning rate: 0.00381 +2025-10-30 18:56:38.948079: train_loss -0.9908 +2025-10-30 18:56:38.950554: val_loss -0.9062 +2025-10-30 18:56:38.952008: Pseudo dice [np.float32(0.9844), np.float32(0.9907), np.float32(0.9949), np.float32(0.8282)] +2025-10-30 18:56:38.953461: Epoch time: 21.33 s +2025-10-30 18:56:40.180836: +2025-10-30 18:56:40.182737: Epoch 659 +2025-10-30 18:56:40.184501: Current learning rate: 0.0038 +2025-10-30 18:57:01.104436: train_loss -0.9904 +2025-10-30 18:57:01.107897: val_loss -0.8984 +2025-10-30 18:57:01.110938: Pseudo dice [np.float32(0.9834), np.float32(0.9903), np.float32(0.9948), np.float32(0.8084)] +2025-10-30 18:57:01.113173: Epoch time: 20.93 s +2025-10-30 18:57:02.341541: +2025-10-30 18:57:02.343579: Epoch 660 +2025-10-30 18:57:02.345258: Current learning rate: 0.00379 +2025-10-30 18:57:23.110997: train_loss -0.9883 +2025-10-30 18:57:23.113954: val_loss -0.9021 +2025-10-30 18:57:23.115546: Pseudo dice [np.float32(0.9816), np.float32(0.9905), np.float32(0.9949), np.float32(0.8182)] +2025-10-30 18:57:23.117230: Epoch time: 20.77 s +2025-10-30 18:57:24.434325: +2025-10-30 18:57:24.436428: Epoch 661 +2025-10-30 18:57:24.438647: Current learning rate: 0.00378 +2025-10-30 18:57:44.684597: train_loss -0.9894 +2025-10-30 18:57:44.686692: val_loss -0.9045 +2025-10-30 18:57:44.688254: Pseudo dice [np.float32(0.9825), np.float32(0.991), np.float32(0.9947), np.float32(0.825)] +2025-10-30 18:57:44.689911: Epoch time: 20.25 s +2025-10-30 18:57:45.879695: +2025-10-30 18:57:45.881586: Epoch 662 +2025-10-30 18:57:45.883246: Current learning rate: 0.00377 +2025-10-30 18:58:06.328431: train_loss -0.99 +2025-10-30 18:58:06.333305: val_loss -0.8997 +2025-10-30 18:58:06.334980: Pseudo dice [np.float32(0.9826), np.float32(0.9911), np.float32(0.9945), np.float32(0.8167)] +2025-10-30 18:58:06.336551: Epoch time: 20.45 s +2025-10-30 18:58:07.591213: +2025-10-30 18:58:07.593356: Epoch 663 +2025-10-30 18:58:07.595699: Current learning rate: 0.00376 +2025-10-30 18:58:27.766922: train_loss -0.9895 +2025-10-30 18:58:27.769454: val_loss -0.9029 +2025-10-30 18:58:27.773580: Pseudo dice [np.float32(0.9841), np.float32(0.9909), np.float32(0.9948), np.float32(0.8167)] +2025-10-30 18:58:27.775195: Epoch time: 20.18 s +2025-10-30 18:58:29.005630: +2025-10-30 18:58:29.008064: Epoch 664 +2025-10-30 18:58:29.009704: Current learning rate: 0.00375 +2025-10-30 18:58:49.667757: train_loss -0.9893 +2025-10-30 18:58:49.670037: val_loss -0.898 +2025-10-30 18:58:49.671780: Pseudo dice [np.float32(0.984), np.float32(0.9906), np.float32(0.9944), np.float32(0.8089)] +2025-10-30 18:58:49.673543: Epoch time: 20.66 s +2025-10-30 18:58:50.954223: +2025-10-30 18:58:50.956117: Epoch 665 +2025-10-30 18:58:50.958305: Current learning rate: 0.00374 +2025-10-30 18:59:11.887137: train_loss -0.9898 +2025-10-30 18:59:11.906905: val_loss -0.8964 +2025-10-30 18:59:11.926160: Pseudo dice [np.float32(0.9816), np.float32(0.9901), np.float32(0.9951), np.float32(0.8143)] +2025-10-30 18:59:11.943550: Epoch time: 20.93 s +2025-10-30 18:59:13.739166: +2025-10-30 18:59:13.741472: Epoch 666 +2025-10-30 18:59:13.743387: Current learning rate: 0.00373 +2025-10-30 18:59:34.737733: train_loss -0.9907 +2025-10-30 18:59:34.740352: val_loss -0.9069 +2025-10-30 18:59:34.742067: Pseudo dice [np.float32(0.9853), np.float32(0.9919), np.float32(0.995), np.float32(0.8328)] +2025-10-30 18:59:34.743719: Epoch time: 21.0 s +2025-10-30 18:59:35.675390: +2025-10-30 18:59:35.677267: Epoch 667 +2025-10-30 18:59:35.679660: Current learning rate: 0.00372 +2025-10-30 18:59:55.037926: train_loss -0.9904 +2025-10-30 18:59:55.040195: val_loss -0.9059 +2025-10-30 18:59:55.041359: Pseudo dice [np.float32(0.9845), np.float32(0.9917), np.float32(0.9953), np.float32(0.8192)] +2025-10-30 18:59:55.042752: Epoch time: 19.36 s +2025-10-30 18:59:56.301204: +2025-10-30 18:59:56.303152: Epoch 668 +2025-10-30 18:59:56.304877: Current learning rate: 0.00371 +2025-10-30 19:00:16.996158: train_loss -0.9906 +2025-10-30 19:00:16.998743: val_loss -0.9032 +2025-10-30 19:00:17.000221: Pseudo dice [np.float32(0.9835), np.float32(0.9914), np.float32(0.9949), np.float32(0.8261)] +2025-10-30 19:00:17.002073: Epoch time: 20.7 s +2025-10-30 19:00:18.240254: +2025-10-30 19:00:18.242152: Epoch 669 +2025-10-30 19:00:18.243668: Current learning rate: 0.0037 +2025-10-30 19:00:37.418707: train_loss -0.9904 +2025-10-30 19:00:37.423215: val_loss -0.9088 +2025-10-30 19:00:37.425463: Pseudo dice [np.float32(0.9843), np.float32(0.9918), np.float32(0.9954), np.float32(0.8333)] +2025-10-30 19:00:37.427120: Epoch time: 19.18 s +2025-10-30 19:00:38.665773: +2025-10-30 19:00:38.667601: Epoch 670 +2025-10-30 19:00:38.669079: Current learning rate: 0.00369 +2025-10-30 19:00:58.911157: train_loss -0.9911 +2025-10-30 19:00:58.913624: val_loss -0.8947 +2025-10-30 19:00:58.915442: Pseudo dice [np.float32(0.9839), np.float32(0.9915), np.float32(0.9946), np.float32(0.7981)] +2025-10-30 19:00:58.916970: Epoch time: 20.25 s +2025-10-30 19:00:59.956960: +2025-10-30 19:00:59.958664: Epoch 671 +2025-10-30 19:00:59.960144: Current learning rate: 0.00368 +2025-10-30 19:01:20.223116: train_loss -0.9913 +2025-10-30 19:01:20.225118: val_loss -0.903 +2025-10-30 19:01:20.226698: Pseudo dice [np.float32(0.9849), np.float32(0.9915), np.float32(0.995), np.float32(0.8114)] +2025-10-30 19:01:20.228179: Epoch time: 20.27 s +2025-10-30 19:01:21.401293: +2025-10-30 19:01:21.403289: Epoch 672 +2025-10-30 19:01:21.405490: Current learning rate: 0.00367 +2025-10-30 19:01:41.854328: train_loss -0.9909 +2025-10-30 19:01:41.857264: val_loss -0.9018 +2025-10-30 19:01:41.859011: Pseudo dice [np.float32(0.9835), np.float32(0.9906), np.float32(0.9953), np.float32(0.8264)] +2025-10-30 19:01:41.860791: Epoch time: 20.46 s +2025-10-30 19:01:43.126291: +2025-10-30 19:01:43.128389: Epoch 673 +2025-10-30 19:01:43.130188: Current learning rate: 0.00366 +2025-10-30 19:02:03.554972: train_loss -0.99 +2025-10-30 19:02:03.556912: val_loss -0.9016 +2025-10-30 19:02:03.558465: Pseudo dice [np.float32(0.9834), np.float32(0.9912), np.float32(0.9952), np.float32(0.8206)] +2025-10-30 19:02:03.559912: Epoch time: 20.43 s +2025-10-30 19:02:04.803603: +2025-10-30 19:02:04.807608: Epoch 674 +2025-10-30 19:02:04.810086: Current learning rate: 0.00365 +2025-10-30 19:02:24.332397: train_loss -0.9916 +2025-10-30 19:02:24.334544: val_loss -0.9007 +2025-10-30 19:02:24.336081: Pseudo dice [np.float32(0.9836), np.float32(0.9913), np.float32(0.9949), np.float32(0.813)] +2025-10-30 19:02:24.337628: Epoch time: 19.53 s +2025-10-30 19:02:25.364501: +2025-10-30 19:02:25.366423: Epoch 675 +2025-10-30 19:02:25.368207: Current learning rate: 0.00364 +2025-10-30 19:02:44.857934: train_loss -0.9911 +2025-10-30 19:02:44.860635: val_loss -0.902 +2025-10-30 19:02:44.863114: Pseudo dice [np.float32(0.9829), np.float32(0.9903), np.float32(0.995), np.float32(0.8201)] +2025-10-30 19:02:44.865471: Epoch time: 19.49 s +2025-10-30 19:02:46.031022: +2025-10-30 19:02:46.032890: Epoch 676 +2025-10-30 19:02:46.034868: Current learning rate: 0.00363 +2025-10-30 19:03:06.787168: train_loss -0.9906 +2025-10-30 19:03:06.789939: val_loss -0.909 +2025-10-30 19:03:06.791589: Pseudo dice [np.float32(0.9853), np.float32(0.9917), np.float32(0.9952), np.float32(0.836)] +2025-10-30 19:03:06.793554: Epoch time: 20.76 s +2025-10-30 19:03:08.084962: +2025-10-30 19:03:08.086801: Epoch 677 +2025-10-30 19:03:08.088264: Current learning rate: 0.00362 +2025-10-30 19:03:28.415392: train_loss -0.9912 +2025-10-30 19:03:28.420081: val_loss -0.9007 +2025-10-30 19:03:28.421918: Pseudo dice [np.float32(0.9827), np.float32(0.9903), np.float32(0.995), np.float32(0.8197)] +2025-10-30 19:03:28.423659: Epoch time: 20.33 s +2025-10-30 19:03:30.089902: +2025-10-30 19:03:30.091877: Epoch 678 +2025-10-30 19:03:30.093913: Current learning rate: 0.00361 +2025-10-30 19:03:50.315879: train_loss -0.9911 +2025-10-30 19:03:50.319032: val_loss -0.9031 +2025-10-30 19:03:50.320850: Pseudo dice [np.float32(0.9829), np.float32(0.9897), np.float32(0.9953), np.float32(0.8276)] +2025-10-30 19:03:50.322514: Epoch time: 20.23 s +2025-10-30 19:03:51.357665: +2025-10-30 19:03:51.359814: Epoch 679 +2025-10-30 19:03:51.361461: Current learning rate: 0.0036 +2025-10-30 19:04:11.908214: train_loss -0.9911 +2025-10-30 19:04:11.911404: val_loss -0.9036 +2025-10-30 19:04:11.913744: Pseudo dice [np.float32(0.9838), np.float32(0.9913), np.float32(0.9954), np.float32(0.8218)] +2025-10-30 19:04:11.915771: Epoch time: 20.55 s +2025-10-30 19:04:13.199332: +2025-10-30 19:04:13.201261: Epoch 680 +2025-10-30 19:04:13.202756: Current learning rate: 0.00359 +2025-10-30 19:04:33.633792: train_loss -0.9904 +2025-10-30 19:04:33.635843: val_loss -0.9018 +2025-10-30 19:04:33.637644: Pseudo dice [np.float32(0.9832), np.float32(0.9908), np.float32(0.9952), np.float32(0.8198)] +2025-10-30 19:04:33.639257: Epoch time: 20.44 s +2025-10-30 19:04:34.777650: +2025-10-30 19:04:34.779382: Epoch 681 +2025-10-30 19:04:34.780848: Current learning rate: 0.00358 +2025-10-30 19:04:53.999567: train_loss -0.9909 +2025-10-30 19:04:54.002417: val_loss -0.8965 +2025-10-30 19:04:54.003988: Pseudo dice [np.float32(0.9819), np.float32(0.9899), np.float32(0.9951), np.float32(0.8126)] +2025-10-30 19:04:54.005435: Epoch time: 19.22 s +2025-10-30 19:04:55.050319: +2025-10-30 19:04:55.052827: Epoch 682 +2025-10-30 19:04:55.054494: Current learning rate: 0.00357 +2025-10-30 19:05:14.634237: train_loss -0.9911 +2025-10-30 19:05:14.639414: val_loss -0.9091 +2025-10-30 19:05:14.641313: Pseudo dice [np.float32(0.9847), np.float32(0.9923), np.float32(0.9953), np.float32(0.834)] +2025-10-30 19:05:14.643023: Epoch time: 19.59 s +2025-10-30 19:05:15.789022: +2025-10-30 19:05:15.791046: Epoch 683 +2025-10-30 19:05:15.793754: Current learning rate: 0.00356 +2025-10-30 19:05:36.155885: train_loss -0.9909 +2025-10-30 19:05:36.157840: val_loss -0.9076 +2025-10-30 19:05:36.160193: Pseudo dice [np.float32(0.9848), np.float32(0.9915), np.float32(0.9952), np.float32(0.8323)] +2025-10-30 19:05:36.162426: Epoch time: 20.37 s +2025-10-30 19:05:37.186996: +2025-10-30 19:05:37.188760: Epoch 684 +2025-10-30 19:05:37.190367: Current learning rate: 0.00355 +2025-10-30 19:05:57.703856: train_loss -0.9904 +2025-10-30 19:05:57.709754: val_loss -0.909 +2025-10-30 19:05:57.712094: Pseudo dice [np.float32(0.9837), np.float32(0.9911), np.float32(0.995), np.float32(0.8337)] +2025-10-30 19:05:57.714398: Epoch time: 20.52 s +2025-10-30 19:05:58.994721: +2025-10-30 19:05:58.996672: Epoch 685 +2025-10-30 19:05:59.002963: Current learning rate: 0.00354 +2025-10-30 19:06:19.556300: train_loss -0.9855 +2025-10-30 19:06:19.558783: val_loss -0.9085 +2025-10-30 19:06:19.560848: Pseudo dice [np.float32(0.9839), np.float32(0.9907), np.float32(0.9949), np.float32(0.8271)] +2025-10-30 19:06:19.562520: Epoch time: 20.56 s +2025-10-30 19:06:20.804812: +2025-10-30 19:06:20.808051: Epoch 686 +2025-10-30 19:06:20.810639: Current learning rate: 0.00353 +2025-10-30 19:06:41.424753: train_loss -0.9881 +2025-10-30 19:06:41.426826: val_loss -0.8976 +2025-10-30 19:06:41.428762: Pseudo dice [np.float32(0.9831), np.float32(0.9906), np.float32(0.9949), np.float32(0.8102)] +2025-10-30 19:06:41.430947: Epoch time: 20.62 s +2025-10-30 19:06:42.667932: +2025-10-30 19:06:42.670153: Epoch 687 +2025-10-30 19:06:42.672094: Current learning rate: 0.00352 +2025-10-30 19:07:03.105824: train_loss -0.9887 +2025-10-30 19:07:03.109585: val_loss -0.8916 +2025-10-30 19:07:03.111198: Pseudo dice [np.float32(0.982), np.float32(0.9905), np.float32(0.9948), np.float32(0.7926)] +2025-10-30 19:07:03.114902: Epoch time: 20.44 s +2025-10-30 19:07:04.303080: +2025-10-30 19:07:04.305386: Epoch 688 +2025-10-30 19:07:04.307032: Current learning rate: 0.00351 +2025-10-30 19:07:22.550937: train_loss -0.9896 +2025-10-30 19:07:22.552954: val_loss -0.8976 +2025-10-30 19:07:22.554851: Pseudo dice [np.float32(0.9823), np.float32(0.9908), np.float32(0.9951), np.float32(0.8105)] +2025-10-30 19:07:22.556814: Epoch time: 18.25 s +2025-10-30 19:07:23.589703: +2025-10-30 19:07:23.591674: Epoch 689 +2025-10-30 19:07:23.593402: Current learning rate: 0.0035 +2025-10-30 19:07:44.136606: train_loss -0.9901 +2025-10-30 19:07:44.138801: val_loss -0.8909 +2025-10-30 19:07:44.140421: Pseudo dice [np.float32(0.9825), np.float32(0.9902), np.float32(0.9946), np.float32(0.7995)] +2025-10-30 19:07:44.142133: Epoch time: 20.55 s +2025-10-30 19:07:45.617306: +2025-10-30 19:07:45.620308: Epoch 690 +2025-10-30 19:07:45.621962: Current learning rate: 0.00349 +2025-10-30 19:08:06.029066: train_loss -0.9908 +2025-10-30 19:08:06.032767: val_loss -0.9045 +2025-10-30 19:08:06.034607: Pseudo dice [np.float32(0.983), np.float32(0.9906), np.float32(0.9952), np.float32(0.8294)] +2025-10-30 19:08:06.036500: Epoch time: 20.41 s +2025-10-30 19:08:07.144667: +2025-10-30 19:08:07.146606: Epoch 691 +2025-10-30 19:08:07.148306: Current learning rate: 0.00348 +2025-10-30 19:08:28.275480: train_loss -0.9908 +2025-10-30 19:08:28.278070: val_loss -0.8987 +2025-10-30 19:08:28.279657: Pseudo dice [np.float32(0.9826), np.float32(0.9907), np.float32(0.9951), np.float32(0.8208)] +2025-10-30 19:08:28.281923: Epoch time: 21.13 s +2025-10-30 19:08:29.580082: +2025-10-30 19:08:29.582773: Epoch 692 +2025-10-30 19:08:29.585024: Current learning rate: 0.00346 +2025-10-30 19:08:49.841197: train_loss -0.9901 +2025-10-30 19:08:49.844007: val_loss -0.9079 +2025-10-30 19:08:49.845842: Pseudo dice [np.float32(0.9839), np.float32(0.9907), np.float32(0.9952), np.float32(0.8349)] +2025-10-30 19:08:49.847747: Epoch time: 20.26 s +2025-10-30 19:08:50.991395: +2025-10-30 19:08:50.993151: Epoch 693 +2025-10-30 19:08:50.994766: Current learning rate: 0.00345 +2025-10-30 19:09:11.575384: train_loss -0.9908 +2025-10-30 19:09:11.578236: val_loss -0.9025 +2025-10-30 19:09:11.579767: Pseudo dice [np.float32(0.9831), np.float32(0.9909), np.float32(0.9952), np.float32(0.8291)] +2025-10-30 19:09:11.581343: Epoch time: 20.59 s +2025-10-30 19:09:12.772900: +2025-10-30 19:09:12.774945: Epoch 694 +2025-10-30 19:09:12.776668: Current learning rate: 0.00344 +2025-10-30 19:09:31.978701: train_loss -0.9888 +2025-10-30 19:09:31.980893: val_loss -0.8999 +2025-10-30 19:09:31.982612: Pseudo dice [np.float32(0.9819), np.float32(0.9891), np.float32(0.9951), np.float32(0.8289)] +2025-10-30 19:09:31.996840: Epoch time: 19.21 s +2025-10-30 19:09:33.064048: +2025-10-30 19:09:33.066196: Epoch 695 +2025-10-30 19:09:33.068055: Current learning rate: 0.00343 +2025-10-30 19:09:53.394416: train_loss -0.9907 +2025-10-30 19:09:53.396755: val_loss -0.9036 +2025-10-30 19:09:53.398416: Pseudo dice [np.float32(0.9838), np.float32(0.9908), np.float32(0.9949), np.float32(0.8261)] +2025-10-30 19:09:53.400169: Epoch time: 20.33 s +2025-10-30 19:09:54.587078: +2025-10-30 19:09:54.588958: Epoch 696 +2025-10-30 19:09:54.591451: Current learning rate: 0.00342 +2025-10-30 19:10:15.143950: train_loss -0.9914 +2025-10-30 19:10:15.146698: val_loss -0.9079 +2025-10-30 19:10:15.148363: Pseudo dice [np.float32(0.9842), np.float32(0.992), np.float32(0.9953), np.float32(0.8348)] +2025-10-30 19:10:15.150164: Epoch time: 20.56 s +2025-10-30 19:10:16.298626: +2025-10-30 19:10:16.300559: Epoch 697 +2025-10-30 19:10:16.302273: Current learning rate: 0.00341 +2025-10-30 19:10:36.749902: train_loss -0.9911 +2025-10-30 19:10:36.751997: val_loss -0.8958 +2025-10-30 19:10:36.754232: Pseudo dice [np.float32(0.9829), np.float32(0.9905), np.float32(0.995), np.float32(0.8132)] +2025-10-30 19:10:36.756626: Epoch time: 20.45 s +2025-10-30 19:10:37.999715: +2025-10-30 19:10:38.002214: Epoch 698 +2025-10-30 19:10:38.005189: Current learning rate: 0.0034 +2025-10-30 19:10:58.286070: train_loss -0.9915 +2025-10-30 19:10:58.288414: val_loss -0.9044 +2025-10-30 19:10:58.290198: Pseudo dice [np.float32(0.9843), np.float32(0.9918), np.float32(0.9952), np.float32(0.8317)] +2025-10-30 19:10:58.292979: Epoch time: 20.29 s +2025-10-30 19:10:59.517879: +2025-10-30 19:10:59.520069: Epoch 699 +2025-10-30 19:10:59.521878: Current learning rate: 0.00339 +2025-10-30 19:11:19.759852: train_loss -0.9916 +2025-10-30 19:11:19.762764: val_loss -0.9037 +2025-10-30 19:11:19.764896: Pseudo dice [np.float32(0.983), np.float32(0.9904), np.float32(0.9955), np.float32(0.8311)] +2025-10-30 19:11:19.766967: Epoch time: 20.24 s +2025-10-30 19:11:22.168334: +2025-10-30 19:11:22.170428: Epoch 700 +2025-10-30 19:11:22.172156: Current learning rate: 0.00338 +2025-10-30 19:11:42.335912: train_loss -0.9907 +2025-10-30 19:11:42.338247: val_loss -0.9044 +2025-10-30 19:11:42.340238: Pseudo dice [np.float32(0.9831), np.float32(0.9906), np.float32(0.9954), np.float32(0.8272)] +2025-10-30 19:11:42.342750: Epoch time: 20.17 s +2025-10-30 19:11:43.465988: +2025-10-30 19:11:43.468256: Epoch 701 +2025-10-30 19:11:43.470202: Current learning rate: 0.00337 +2025-10-30 19:12:01.404938: train_loss -0.9911 +2025-10-30 19:12:01.407444: val_loss -0.9032 +2025-10-30 19:12:01.409271: Pseudo dice [np.float32(0.9833), np.float32(0.991), np.float32(0.9953), np.float32(0.8313)] +2025-10-30 19:12:01.410924: Epoch time: 17.94 s +2025-10-30 19:12:03.050032: +2025-10-30 19:12:03.052016: Epoch 702 +2025-10-30 19:12:03.053605: Current learning rate: 0.00336 +2025-10-30 19:12:23.444607: train_loss -0.9915 +2025-10-30 19:12:23.447709: val_loss -0.8976 +2025-10-30 19:12:23.449522: Pseudo dice [np.float32(0.9831), np.float32(0.9898), np.float32(0.9947), np.float32(0.8212)] +2025-10-30 19:12:23.451492: Epoch time: 20.4 s +2025-10-30 19:12:24.560750: +2025-10-30 19:12:24.563831: Epoch 703 +2025-10-30 19:12:24.566407: Current learning rate: 0.00335 +2025-10-30 19:12:45.268981: train_loss -0.9916 +2025-10-30 19:12:45.271386: val_loss -0.9042 +2025-10-30 19:12:45.273137: Pseudo dice [np.float32(0.9828), np.float32(0.9898), np.float32(0.9953), np.float32(0.838)] +2025-10-30 19:12:45.274872: Epoch time: 20.71 s +2025-10-30 19:12:46.343539: +2025-10-30 19:12:46.345498: Epoch 704 +2025-10-30 19:12:46.347046: Current learning rate: 0.00334 +2025-10-30 19:13:07.156526: train_loss -0.9913 +2025-10-30 19:13:07.162517: val_loss -0.9081 +2025-10-30 19:13:07.164296: Pseudo dice [np.float32(0.9843), np.float32(0.9915), np.float32(0.9954), np.float32(0.8347)] +2025-10-30 19:13:07.166093: Epoch time: 20.81 s +2025-10-30 19:13:08.562096: +2025-10-30 19:13:08.564349: Epoch 705 +2025-10-30 19:13:08.566314: Current learning rate: 0.00333 +2025-10-30 19:13:29.086630: train_loss -0.9917 +2025-10-30 19:13:29.089991: val_loss -0.9069 +2025-10-30 19:13:29.091560: Pseudo dice [np.float32(0.9844), np.float32(0.9904), np.float32(0.9951), np.float32(0.8345)] +2025-10-30 19:13:29.093301: Epoch time: 20.53 s +2025-10-30 19:13:30.219072: +2025-10-30 19:13:30.220878: Epoch 706 +2025-10-30 19:13:30.222480: Current learning rate: 0.00332 +2025-10-30 19:13:50.787724: train_loss -0.9913 +2025-10-30 19:13:50.790372: val_loss -0.9061 +2025-10-30 19:13:50.792033: Pseudo dice [np.float32(0.9844), np.float32(0.9918), np.float32(0.9952), np.float32(0.8281)] +2025-10-30 19:13:50.793709: Epoch time: 20.57 s +2025-10-30 19:13:52.024516: +2025-10-30 19:13:52.026664: Epoch 707 +2025-10-30 19:13:52.028459: Current learning rate: 0.00331 +2025-10-30 19:14:11.124402: train_loss -0.9921 +2025-10-30 19:14:11.126868: val_loss -0.903 +2025-10-30 19:14:11.128707: Pseudo dice [np.float32(0.9835), np.float32(0.9901), np.float32(0.9949), np.float32(0.8252)] +2025-10-30 19:14:11.130560: Epoch time: 19.1 s +2025-10-30 19:14:12.401862: +2025-10-30 19:14:12.403856: Epoch 708 +2025-10-30 19:14:12.405520: Current learning rate: 0.0033 +2025-10-30 19:14:32.090437: train_loss -0.9912 +2025-10-30 19:14:32.093555: val_loss -0.9017 +2025-10-30 19:14:32.095179: Pseudo dice [np.float32(0.9829), np.float32(0.9911), np.float32(0.9952), np.float32(0.821)] +2025-10-30 19:14:32.096898: Epoch time: 19.69 s +2025-10-30 19:14:33.373925: +2025-10-30 19:14:33.375961: Epoch 709 +2025-10-30 19:14:33.377646: Current learning rate: 0.00329 +2025-10-30 19:14:53.899280: train_loss -0.9915 +2025-10-30 19:14:53.901311: val_loss -0.8998 +2025-10-30 19:14:53.902868: Pseudo dice [np.float32(0.9834), np.float32(0.991), np.float32(0.9949), np.float32(0.8161)] +2025-10-30 19:14:53.904313: Epoch time: 20.53 s +2025-10-30 19:14:55.020133: +2025-10-30 19:14:55.022040: Epoch 710 +2025-10-30 19:14:55.023731: Current learning rate: 0.00328 +2025-10-30 19:15:15.451406: train_loss -0.9916 +2025-10-30 19:15:15.453919: val_loss -0.8971 +2025-10-30 19:15:15.455453: Pseudo dice [np.float32(0.9838), np.float32(0.9906), np.float32(0.9948), np.float32(0.8083)] +2025-10-30 19:15:15.456984: Epoch time: 20.43 s +2025-10-30 19:15:16.700487: +2025-10-30 19:15:16.702909: Epoch 711 +2025-10-30 19:15:16.704795: Current learning rate: 0.00327 +2025-10-30 19:15:37.029259: train_loss -0.9916 +2025-10-30 19:15:37.033806: val_loss -0.9028 +2025-10-30 19:15:37.035474: Pseudo dice [np.float32(0.9836), np.float32(0.9911), np.float32(0.9953), np.float32(0.8287)] +2025-10-30 19:15:37.037192: Epoch time: 20.33 s +2025-10-30 19:15:38.074466: +2025-10-30 19:15:38.076332: Epoch 712 +2025-10-30 19:15:38.078610: Current learning rate: 0.00326 +2025-10-30 19:15:58.640506: train_loss -0.9911 +2025-10-30 19:15:58.645095: val_loss -0.9063 +2025-10-30 19:15:58.646519: Pseudo dice [np.float32(0.9843), np.float32(0.9912), np.float32(0.9953), np.float32(0.8317)] +2025-10-30 19:15:58.647974: Epoch time: 20.57 s +2025-10-30 19:15:59.692850: +2025-10-30 19:15:59.694756: Epoch 713 +2025-10-30 19:15:59.696466: Current learning rate: 0.00325 +2025-10-30 19:16:20.525630: train_loss -0.9923 +2025-10-30 19:16:20.527748: val_loss -0.9024 +2025-10-30 19:16:20.529294: Pseudo dice [np.float32(0.982), np.float32(0.9907), np.float32(0.9955), np.float32(0.8351)] +2025-10-30 19:16:20.531532: Epoch time: 20.83 s +2025-10-30 19:16:22.246717: +2025-10-30 19:16:22.248636: Epoch 714 +2025-10-30 19:16:22.250315: Current learning rate: 0.00324 +2025-10-30 19:16:41.510642: train_loss -0.9915 +2025-10-30 19:16:41.515208: val_loss -0.8994 +2025-10-30 19:16:41.517162: Pseudo dice [np.float32(0.9821), np.float32(0.9901), np.float32(0.995), np.float32(0.8208)] +2025-10-30 19:16:41.519149: Epoch time: 19.27 s +2025-10-30 19:16:42.796442: +2025-10-30 19:16:42.798837: Epoch 715 +2025-10-30 19:16:42.800869: Current learning rate: 0.00323 +2025-10-30 19:17:02.045827: train_loss -0.9922 +2025-10-30 19:17:02.048013: val_loss -0.8948 +2025-10-30 19:17:02.049593: Pseudo dice [np.float32(0.9824), np.float32(0.9901), np.float32(0.9949), np.float32(0.8063)] +2025-10-30 19:17:02.053872: Epoch time: 19.25 s +2025-10-30 19:17:03.276783: +2025-10-30 19:17:03.278989: Epoch 716 +2025-10-30 19:17:03.280905: Current learning rate: 0.00322 +2025-10-30 19:17:23.528962: train_loss -0.9914 +2025-10-30 19:17:23.531290: val_loss -0.8956 +2025-10-30 19:17:23.532935: Pseudo dice [np.float32(0.9847), np.float32(0.9917), np.float32(0.9947), np.float32(0.8095)] +2025-10-30 19:17:23.534427: Epoch time: 20.25 s +2025-10-30 19:17:24.674893: +2025-10-30 19:17:24.678300: Epoch 717 +2025-10-30 19:17:24.680232: Current learning rate: 0.00321 +2025-10-30 19:17:44.965014: train_loss -0.9924 +2025-10-30 19:17:44.971141: val_loss -0.9022 +2025-10-30 19:17:44.972527: Pseudo dice [np.float32(0.9833), np.float32(0.9907), np.float32(0.9953), np.float32(0.8212)] +2025-10-30 19:17:44.974084: Epoch time: 20.29 s +2025-10-30 19:17:46.212414: +2025-10-30 19:17:46.214092: Epoch 718 +2025-10-30 19:17:46.215670: Current learning rate: 0.0032 +2025-10-30 19:18:06.816615: train_loss -0.9921 +2025-10-30 19:18:06.818898: val_loss -0.9052 +2025-10-30 19:18:06.820694: Pseudo dice [np.float32(0.9842), np.float32(0.991), np.float32(0.9951), np.float32(0.8329)] +2025-10-30 19:18:06.822461: Epoch time: 20.61 s +2025-10-30 19:18:08.102374: +2025-10-30 19:18:08.104308: Epoch 719 +2025-10-30 19:18:08.105855: Current learning rate: 0.00319 +2025-10-30 19:18:28.622671: train_loss -0.992 +2025-10-30 19:18:28.625753: val_loss -0.8996 +2025-10-30 19:18:28.627583: Pseudo dice [np.float32(0.9838), np.float32(0.9908), np.float32(0.9949), np.float32(0.8178)] +2025-10-30 19:18:28.630083: Epoch time: 20.52 s +2025-10-30 19:18:29.811914: +2025-10-30 19:18:29.814463: Epoch 720 +2025-10-30 19:18:29.816259: Current learning rate: 0.00318 +2025-10-30 19:18:49.464671: train_loss -0.992 +2025-10-30 19:18:49.471944: val_loss -0.8995 +2025-10-30 19:18:49.473798: Pseudo dice [np.float32(0.9834), np.float32(0.9907), np.float32(0.9946), np.float32(0.8193)] +2025-10-30 19:18:49.475785: Epoch time: 19.65 s +2025-10-30 19:18:50.596167: +2025-10-30 19:18:50.597976: Epoch 721 +2025-10-30 19:18:50.600040: Current learning rate: 0.00317 +2025-10-30 19:19:10.751188: train_loss -0.9921 +2025-10-30 19:19:10.752999: val_loss -0.9046 +2025-10-30 19:19:10.754608: Pseudo dice [np.float32(0.9834), np.float32(0.9909), np.float32(0.9953), np.float32(0.8278)] +2025-10-30 19:19:10.756219: Epoch time: 20.16 s +2025-10-30 19:19:11.781945: +2025-10-30 19:19:11.783891: Epoch 722 +2025-10-30 19:19:11.785778: Current learning rate: 0.00316 +2025-10-30 19:19:31.220830: train_loss -0.992 +2025-10-30 19:19:31.222939: val_loss -0.9017 +2025-10-30 19:19:31.224408: Pseudo dice [np.float32(0.9828), np.float32(0.9907), np.float32(0.995), np.float32(0.8248)] +2025-10-30 19:19:31.226006: Epoch time: 19.44 s +2025-10-30 19:19:32.622570: +2025-10-30 19:19:32.624505: Epoch 723 +2025-10-30 19:19:32.626380: Current learning rate: 0.00315 +2025-10-30 19:19:53.075823: train_loss -0.9924 +2025-10-30 19:19:53.078550: val_loss -0.902 +2025-10-30 19:19:53.080220: Pseudo dice [np.float32(0.9837), np.float32(0.9916), np.float32(0.9951), np.float32(0.8206)] +2025-10-30 19:19:53.081823: Epoch time: 20.46 s +2025-10-30 19:19:54.173798: +2025-10-30 19:19:54.175501: Epoch 724 +2025-10-30 19:19:54.177131: Current learning rate: 0.00314 +2025-10-30 19:20:14.648192: train_loss -0.9918 +2025-10-30 19:20:14.649863: val_loss -0.9001 +2025-10-30 19:20:14.651438: Pseudo dice [np.float32(0.9842), np.float32(0.9914), np.float32(0.9949), np.float32(0.8214)] +2025-10-30 19:20:14.652946: Epoch time: 20.48 s +2025-10-30 19:20:15.863995: +2025-10-30 19:20:15.865886: Epoch 725 +2025-10-30 19:20:15.867489: Current learning rate: 0.00313 +2025-10-30 19:20:36.201969: train_loss -0.992 +2025-10-30 19:20:36.204174: val_loss -0.9009 +2025-10-30 19:20:36.205719: Pseudo dice [np.float32(0.9835), np.float32(0.9909), np.float32(0.995), np.float32(0.8184)] +2025-10-30 19:20:36.207373: Epoch time: 20.34 s +2025-10-30 19:20:37.717847: +2025-10-30 19:20:37.720414: Epoch 726 +2025-10-30 19:20:37.722621: Current learning rate: 0.00312 +2025-10-30 19:20:58.129512: train_loss -0.9917 +2025-10-30 19:20:58.131975: val_loss -0.9081 +2025-10-30 19:20:58.133570: Pseudo dice [np.float32(0.9845), np.float32(0.9916), np.float32(0.9953), np.float32(0.8352)] +2025-10-30 19:20:58.135487: Epoch time: 20.41 s +2025-10-30 19:20:59.319420: +2025-10-30 19:20:59.321151: Epoch 727 +2025-10-30 19:20:59.322889: Current learning rate: 0.00311 +2025-10-30 19:21:18.991237: train_loss -0.9917 +2025-10-30 19:21:18.993741: val_loss -0.9112 +2025-10-30 19:21:18.995535: Pseudo dice [np.float32(0.9848), np.float32(0.9917), np.float32(0.9955), np.float32(0.8384)] +2025-10-30 19:21:18.997172: Epoch time: 19.67 s +2025-10-30 19:21:20.269956: +2025-10-30 19:21:20.271905: Epoch 728 +2025-10-30 19:21:20.273990: Current learning rate: 0.0031 +2025-10-30 19:21:39.555672: train_loss -0.9916 +2025-10-30 19:21:39.557520: val_loss -0.9011 +2025-10-30 19:21:39.559049: Pseudo dice [np.float32(0.984), np.float32(0.9908), np.float32(0.9948), np.float32(0.8163)] +2025-10-30 19:21:39.560765: Epoch time: 19.29 s +2025-10-30 19:21:40.596316: +2025-10-30 19:21:40.598462: Epoch 729 +2025-10-30 19:21:40.600132: Current learning rate: 0.00309 +2025-10-30 19:22:00.970984: train_loss -0.9923 +2025-10-30 19:22:00.973925: val_loss -0.9041 +2025-10-30 19:22:00.975670: Pseudo dice [np.float32(0.9833), np.float32(0.9914), np.float32(0.9952), np.float32(0.8305)] +2025-10-30 19:22:00.977565: Epoch time: 20.38 s +2025-10-30 19:22:02.251738: +2025-10-30 19:22:02.253749: Epoch 730 +2025-10-30 19:22:02.255672: Current learning rate: 0.00308 +2025-10-30 19:22:22.796561: train_loss -0.9921 +2025-10-30 19:22:22.798958: val_loss -0.9037 +2025-10-30 19:22:22.800799: Pseudo dice [np.float32(0.9839), np.float32(0.9913), np.float32(0.9952), np.float32(0.8228)] +2025-10-30 19:22:22.802686: Epoch time: 20.55 s +2025-10-30 19:22:23.936850: +2025-10-30 19:22:23.938840: Epoch 731 +2025-10-30 19:22:23.940912: Current learning rate: 0.00307 +2025-10-30 19:22:44.644775: train_loss -0.9916 +2025-10-30 19:22:44.647055: val_loss -0.898 +2025-10-30 19:22:44.648652: Pseudo dice [np.float32(0.9853), np.float32(0.9918), np.float32(0.9948), np.float32(0.8118)] +2025-10-30 19:22:44.650516: Epoch time: 20.71 s +2025-10-30 19:22:45.978649: +2025-10-30 19:22:45.980696: Epoch 732 +2025-10-30 19:22:45.983385: Current learning rate: 0.00306 +2025-10-30 19:23:06.050647: train_loss -0.9923 +2025-10-30 19:23:06.053146: val_loss -0.9061 +2025-10-30 19:23:06.054563: Pseudo dice [np.float32(0.9823), np.float32(0.9905), np.float32(0.9951), np.float32(0.8362)] +2025-10-30 19:23:06.056124: Epoch time: 20.07 s +2025-10-30 19:23:07.185815: +2025-10-30 19:23:07.187792: Epoch 733 +2025-10-30 19:23:07.189708: Current learning rate: 0.00305 +2025-10-30 19:23:26.385755: train_loss -0.9923 +2025-10-30 19:23:26.388387: val_loss -0.9055 +2025-10-30 19:23:26.390290: Pseudo dice [np.float32(0.9836), np.float32(0.991), np.float32(0.9951), np.float32(0.8356)] +2025-10-30 19:23:26.392095: Epoch time: 19.2 s +2025-10-30 19:23:27.517170: +2025-10-30 19:23:27.519816: Epoch 734 +2025-10-30 19:23:27.521981: Current learning rate: 0.00304 +2025-10-30 19:23:48.091227: train_loss -0.9918 +2025-10-30 19:23:48.093209: val_loss -0.8976 +2025-10-30 19:23:48.094664: Pseudo dice [np.float32(0.983), np.float32(0.9903), np.float32(0.9947), np.float32(0.816)] +2025-10-30 19:23:48.096415: Epoch time: 20.58 s +2025-10-30 19:23:49.192860: +2025-10-30 19:23:49.195008: Epoch 735 +2025-10-30 19:23:49.196527: Current learning rate: 0.00303 +2025-10-30 19:24:09.299582: train_loss -0.9919 +2025-10-30 19:24:09.306177: val_loss -0.9015 +2025-10-30 19:24:09.307582: Pseudo dice [np.float32(0.9844), np.float32(0.9916), np.float32(0.9949), np.float32(0.8222)] +2025-10-30 19:24:09.309151: Epoch time: 20.11 s +2025-10-30 19:24:10.568293: +2025-10-30 19:24:10.570522: Epoch 736 +2025-10-30 19:24:10.572919: Current learning rate: 0.00302 +2025-10-30 19:24:31.229881: train_loss -0.9914 +2025-10-30 19:24:31.232017: val_loss -0.8987 +2025-10-30 19:24:31.233565: Pseudo dice [np.float32(0.9827), np.float32(0.9905), np.float32(0.9951), np.float32(0.8219)] +2025-10-30 19:24:31.235125: Epoch time: 20.66 s +2025-10-30 19:24:32.539067: +2025-10-30 19:24:32.541029: Epoch 737 +2025-10-30 19:24:32.542615: Current learning rate: 0.00301 +2025-10-30 19:24:53.112055: train_loss -0.9915 +2025-10-30 19:24:53.114594: val_loss -0.9026 +2025-10-30 19:24:53.116434: Pseudo dice [np.float32(0.9822), np.float32(0.9905), np.float32(0.9951), np.float32(0.8308)] +2025-10-30 19:24:53.117999: Epoch time: 20.57 s +2025-10-30 19:24:54.723179: +2025-10-30 19:24:54.725116: Epoch 738 +2025-10-30 19:24:54.726927: Current learning rate: 0.003 +2025-10-30 19:25:15.217895: train_loss -0.9923 +2025-10-30 19:25:15.222277: val_loss -0.8975 +2025-10-30 19:25:15.224378: Pseudo dice [np.float32(0.9831), np.float32(0.9905), np.float32(0.995), np.float32(0.8166)] +2025-10-30 19:25:15.226504: Epoch time: 20.5 s +2025-10-30 19:25:16.434623: +2025-10-30 19:25:16.437034: Epoch 739 +2025-10-30 19:25:16.439021: Current learning rate: 0.00299 +2025-10-30 19:25:35.559306: train_loss -0.9919 +2025-10-30 19:25:35.561425: val_loss -0.9011 +2025-10-30 19:25:35.563115: Pseudo dice [np.float32(0.9839), np.float32(0.9909), np.float32(0.9949), np.float32(0.8228)] +2025-10-30 19:25:35.564696: Epoch time: 19.13 s +2025-10-30 19:25:36.798784: +2025-10-30 19:25:36.800396: Epoch 740 +2025-10-30 19:25:36.803624: Current learning rate: 0.00297 +2025-10-30 19:25:57.452954: train_loss -0.9919 +2025-10-30 19:25:57.455948: val_loss -0.9004 +2025-10-30 19:25:57.457709: Pseudo dice [np.float32(0.9848), np.float32(0.9919), np.float32(0.995), np.float32(0.8183)] +2025-10-30 19:25:57.459462: Epoch time: 20.66 s +2025-10-30 19:25:58.730808: +2025-10-30 19:25:58.732637: Epoch 741 +2025-10-30 19:25:58.734259: Current learning rate: 0.00296 +2025-10-30 19:26:19.214048: train_loss -0.9919 +2025-10-30 19:26:19.217134: val_loss -0.8972 +2025-10-30 19:26:19.218933: Pseudo dice [np.float32(0.983), np.float32(0.9908), np.float32(0.9952), np.float32(0.8198)] +2025-10-30 19:26:19.220788: Epoch time: 20.49 s +2025-10-30 19:26:20.315892: +2025-10-30 19:26:20.317791: Epoch 742 +2025-10-30 19:26:20.319450: Current learning rate: 0.00295 +2025-10-30 19:26:39.826807: train_loss -0.9919 +2025-10-30 19:26:39.828915: val_loss -0.8965 +2025-10-30 19:26:39.830398: Pseudo dice [np.float32(0.9831), np.float32(0.9898), np.float32(0.9949), np.float32(0.815)] +2025-10-30 19:26:39.832069: Epoch time: 19.51 s +2025-10-30 19:26:40.972926: +2025-10-30 19:26:40.974803: Epoch 743 +2025-10-30 19:26:40.976427: Current learning rate: 0.00294 +2025-10-30 19:27:01.604535: train_loss -0.992 +2025-10-30 19:27:01.606666: val_loss -0.9022 +2025-10-30 19:27:01.608315: Pseudo dice [np.float32(0.9836), np.float32(0.9904), np.float32(0.9951), np.float32(0.8276)] +2025-10-30 19:27:01.609942: Epoch time: 20.63 s +2025-10-30 19:27:02.641008: +2025-10-30 19:27:02.643111: Epoch 744 +2025-10-30 19:27:02.644587: Current learning rate: 0.00293 +2025-10-30 19:27:23.234665: train_loss -0.992 +2025-10-30 19:27:23.291579: val_loss -0.8976 +2025-10-30 19:27:23.315637: Pseudo dice [np.float32(0.9845), np.float32(0.9918), np.float32(0.9949), np.float32(0.8057)] +2025-10-30 19:27:23.333194: Epoch time: 20.6 s +2025-10-30 19:27:24.594276: +2025-10-30 19:27:24.596142: Epoch 745 +2025-10-30 19:27:24.598134: Current learning rate: 0.00292 +2025-10-30 19:27:44.772086: train_loss -0.9923 +2025-10-30 19:27:44.774507: val_loss -0.893 +2025-10-30 19:27:44.776587: Pseudo dice [np.float32(0.9843), np.float32(0.9908), np.float32(0.9946), np.float32(0.7965)] +2025-10-30 19:27:44.778406: Epoch time: 20.18 s +2025-10-30 19:27:45.843675: +2025-10-30 19:27:45.845554: Epoch 746 +2025-10-30 19:27:45.847197: Current learning rate: 0.00291 +2025-10-30 19:28:05.654066: train_loss -0.9918 +2025-10-30 19:28:05.657493: val_loss -0.8934 +2025-10-30 19:28:05.660040: Pseudo dice [np.float32(0.9832), np.float32(0.9912), np.float32(0.9948), np.float32(0.7995)] +2025-10-30 19:28:05.662290: Epoch time: 19.81 s +2025-10-30 19:28:07.012831: +2025-10-30 19:28:07.014782: Epoch 747 +2025-10-30 19:28:07.016625: Current learning rate: 0.0029 +2025-10-30 19:28:27.499644: train_loss -0.9924 +2025-10-30 19:28:27.503372: val_loss -0.902 +2025-10-30 19:28:27.504984: Pseudo dice [np.float32(0.9834), np.float32(0.9918), np.float32(0.9954), np.float32(0.8217)] +2025-10-30 19:28:27.506639: Epoch time: 20.49 s +2025-10-30 19:28:28.756120: +2025-10-30 19:28:28.758178: Epoch 748 +2025-10-30 19:28:28.759808: Current learning rate: 0.00289 +2025-10-30 19:28:49.353279: train_loss -0.9921 +2025-10-30 19:28:49.355750: val_loss -0.8991 +2025-10-30 19:28:49.357352: Pseudo dice [np.float32(0.9843), np.float32(0.9911), np.float32(0.995), np.float32(0.8162)] +2025-10-30 19:28:49.358902: Epoch time: 20.6 s +2025-10-30 19:28:50.427799: +2025-10-30 19:28:50.429697: Epoch 749 +2025-10-30 19:28:50.431374: Current learning rate: 0.00288 +2025-10-30 19:29:10.091314: train_loss -0.9928 +2025-10-30 19:29:10.095194: val_loss -0.904 +2025-10-30 19:29:10.097021: Pseudo dice [np.float32(0.9831), np.float32(0.9904), np.float32(0.9949), np.float32(0.8328)] +2025-10-30 19:29:10.098520: Epoch time: 19.67 s +2025-10-30 19:29:12.358709: +2025-10-30 19:29:12.360954: Epoch 750 +2025-10-30 19:29:12.362802: Current learning rate: 0.00287 +2025-10-30 19:29:32.637607: train_loss -0.9916 +2025-10-30 19:29:32.640601: val_loss -0.9039 +2025-10-30 19:29:32.642425: Pseudo dice [np.float32(0.9818), np.float32(0.9905), np.float32(0.9953), np.float32(0.8309)] +2025-10-30 19:29:32.643840: Epoch time: 20.28 s +2025-10-30 19:29:33.702216: +2025-10-30 19:29:33.704005: Epoch 751 +2025-10-30 19:29:33.705623: Current learning rate: 0.00286 +2025-10-30 19:29:54.302528: train_loss -0.9921 +2025-10-30 19:29:54.304409: val_loss -0.8994 +2025-10-30 19:29:54.305816: Pseudo dice [np.float32(0.9838), np.float32(0.9914), np.float32(0.9952), np.float32(0.8168)] +2025-10-30 19:29:54.307324: Epoch time: 20.6 s +2025-10-30 19:29:55.341753: +2025-10-30 19:29:55.343910: Epoch 752 +2025-10-30 19:29:55.345559: Current learning rate: 0.00285 +2025-10-30 19:30:15.080150: train_loss -0.9925 +2025-10-30 19:30:15.083183: val_loss -0.8983 +2025-10-30 19:30:15.085053: Pseudo dice [np.float32(0.9844), np.float32(0.9912), np.float32(0.995), np.float32(0.8165)] +2025-10-30 19:30:15.086765: Epoch time: 19.74 s +2025-10-30 19:30:16.377607: +2025-10-30 19:30:16.383425: Epoch 753 +2025-10-30 19:30:16.385240: Current learning rate: 0.00284 +2025-10-30 19:30:36.593118: train_loss -0.9924 +2025-10-30 19:30:36.596030: val_loss -0.905 +2025-10-30 19:30:36.598658: Pseudo dice [np.float32(0.9842), np.float32(0.9912), np.float32(0.9955), np.float32(0.8253)] +2025-10-30 19:30:36.601331: Epoch time: 20.22 s +2025-10-30 19:30:37.680818: +2025-10-30 19:30:37.682871: Epoch 754 +2025-10-30 19:30:37.684697: Current learning rate: 0.00283 +2025-10-30 19:30:58.316562: train_loss -0.9923 +2025-10-30 19:30:58.318641: val_loss -0.9008 +2025-10-30 19:30:58.320192: Pseudo dice [np.float32(0.9832), np.float32(0.9907), np.float32(0.9955), np.float32(0.8261)] +2025-10-30 19:30:58.321759: Epoch time: 20.64 s +2025-10-30 19:30:59.355714: +2025-10-30 19:30:59.358010: Epoch 755 +2025-10-30 19:30:59.359965: Current learning rate: 0.00282 +2025-10-30 19:31:19.627002: train_loss -0.9925 +2025-10-30 19:31:19.629178: val_loss -0.8964 +2025-10-30 19:31:19.631458: Pseudo dice [np.float32(0.9836), np.float32(0.9913), np.float32(0.9949), np.float32(0.8121)] +2025-10-30 19:31:19.633477: Epoch time: 20.27 s +2025-10-30 19:31:20.771040: +2025-10-30 19:31:20.773045: Epoch 756 +2025-10-30 19:31:20.774960: Current learning rate: 0.00281 +2025-10-30 19:31:40.320963: train_loss -0.9921 +2025-10-30 19:31:40.325672: val_loss -0.9038 +2025-10-30 19:31:40.327234: Pseudo dice [np.float32(0.9844), np.float32(0.9912), np.float32(0.9951), np.float32(0.8249)] +2025-10-30 19:31:40.328785: Epoch time: 19.55 s +2025-10-30 19:31:41.490108: +2025-10-30 19:31:41.493937: Epoch 757 +2025-10-30 19:31:41.496081: Current learning rate: 0.0028 +2025-10-30 19:32:01.753688: train_loss -0.9924 +2025-10-30 19:32:01.756145: val_loss -0.9049 +2025-10-30 19:32:01.757948: Pseudo dice [np.float32(0.9837), np.float32(0.9908), np.float32(0.9953), np.float32(0.8326)] +2025-10-30 19:32:01.760202: Epoch time: 20.27 s +2025-10-30 19:32:03.020597: +2025-10-30 19:32:03.036167: Epoch 758 +2025-10-30 19:32:03.052270: Current learning rate: 0.00279 +2025-10-30 19:32:22.416797: train_loss -0.9921 +2025-10-30 19:32:22.419209: val_loss -0.909 +2025-10-30 19:32:22.421514: Pseudo dice [np.float32(0.9845), np.float32(0.9918), np.float32(0.9954), np.float32(0.8409)] +2025-10-30 19:32:22.423308: Epoch time: 19.4 s +2025-10-30 19:32:23.666046: +2025-10-30 19:32:23.669268: Epoch 759 +2025-10-30 19:32:23.673367: Current learning rate: 0.00278 +2025-10-30 19:32:44.025571: train_loss -0.9925 +2025-10-30 19:32:44.029371: val_loss -0.9021 +2025-10-30 19:32:44.031249: Pseudo dice [np.float32(0.9832), np.float32(0.991), np.float32(0.9955), np.float32(0.8286)] +2025-10-30 19:32:44.032954: Epoch time: 20.36 s +2025-10-30 19:32:45.249921: +2025-10-30 19:32:45.251999: Epoch 760 +2025-10-30 19:32:45.253932: Current learning rate: 0.00277 +2025-10-30 19:33:05.967843: train_loss -0.9929 +2025-10-30 19:33:05.969933: val_loss -0.8986 +2025-10-30 19:33:05.971709: Pseudo dice [np.float32(0.9837), np.float32(0.9908), np.float32(0.9949), np.float32(0.8244)] +2025-10-30 19:33:05.973207: Epoch time: 20.72 s +2025-10-30 19:33:08.089955: +2025-10-30 19:33:08.092116: Epoch 761 +2025-10-30 19:33:08.094170: Current learning rate: 0.00276 +2025-10-30 19:33:28.538936: train_loss -0.9928 +2025-10-30 19:33:28.541194: val_loss -0.9068 +2025-10-30 19:33:28.542883: Pseudo dice [np.float32(0.9838), np.float32(0.9912), np.float32(0.9955), np.float32(0.8384)] +2025-10-30 19:33:28.547886: Epoch time: 20.45 s +2025-10-30 19:33:29.691921: +2025-10-30 19:33:29.693914: Epoch 762 +2025-10-30 19:33:29.695498: Current learning rate: 0.00275 +2025-10-30 19:33:48.930505: train_loss -0.992 +2025-10-30 19:33:48.933454: val_loss -0.9038 +2025-10-30 19:33:48.935160: Pseudo dice [np.float32(0.9839), np.float32(0.9912), np.float32(0.9955), np.float32(0.8303)] +2025-10-30 19:33:48.937115: Epoch time: 19.24 s +2025-10-30 19:33:50.061582: +2025-10-30 19:33:50.063625: Epoch 763 +2025-10-30 19:33:50.065659: Current learning rate: 0.00274 +2025-10-30 19:34:10.594358: train_loss -0.9922 +2025-10-30 19:34:10.596649: val_loss -0.9022 +2025-10-30 19:34:10.598353: Pseudo dice [np.float32(0.9839), np.float32(0.9909), np.float32(0.995), np.float32(0.8256)] +2025-10-30 19:34:10.600249: Epoch time: 20.53 s +2025-10-30 19:34:11.809075: +2025-10-30 19:34:11.811475: Epoch 764 +2025-10-30 19:34:11.813438: Current learning rate: 0.00273 +2025-10-30 19:34:31.844243: train_loss -0.9919 +2025-10-30 19:34:31.846846: val_loss -0.8996 +2025-10-30 19:34:31.849002: Pseudo dice [np.float32(0.9835), np.float32(0.9908), np.float32(0.995), np.float32(0.8159)] +2025-10-30 19:34:31.851430: Epoch time: 20.04 s +2025-10-30 19:34:33.012622: +2025-10-30 19:34:33.014594: Epoch 765 +2025-10-30 19:34:33.016313: Current learning rate: 0.00272 +2025-10-30 19:34:52.603286: train_loss -0.9921 +2025-10-30 19:34:52.605903: val_loss -0.9082 +2025-10-30 19:34:52.607746: Pseudo dice [np.float32(0.9829), np.float32(0.991), np.float32(0.9957), np.float32(0.8453)] +2025-10-30 19:34:52.609363: Epoch time: 19.59 s +2025-10-30 19:34:53.846442: +2025-10-30 19:34:53.848686: Epoch 766 +2025-10-30 19:34:53.850386: Current learning rate: 0.00271 +2025-10-30 19:35:14.253941: train_loss -0.9918 +2025-10-30 19:35:14.257862: val_loss -0.9046 +2025-10-30 19:35:14.259462: Pseudo dice [np.float32(0.9836), np.float32(0.9914), np.float32(0.9954), np.float32(0.8318)] +2025-10-30 19:35:14.261104: Epoch time: 20.41 s +2025-10-30 19:35:15.350886: +2025-10-30 19:35:15.352901: Epoch 767 +2025-10-30 19:35:15.354855: Current learning rate: 0.0027 +2025-10-30 19:35:35.784364: train_loss -0.9921 +2025-10-30 19:35:35.786578: val_loss -0.9069 +2025-10-30 19:35:35.788860: Pseudo dice [np.float32(0.9825), np.float32(0.9905), np.float32(0.9955), np.float32(0.8431)] +2025-10-30 19:35:35.790918: Epoch time: 20.43 s +2025-10-30 19:35:37.069229: +2025-10-30 19:35:37.071585: Epoch 768 +2025-10-30 19:35:37.073456: Current learning rate: 0.00268 +2025-10-30 19:35:57.459779: train_loss -0.9925 +2025-10-30 19:35:57.462694: val_loss -0.9006 +2025-10-30 19:35:57.464281: Pseudo dice [np.float32(0.9818), np.float32(0.9906), np.float32(0.9951), np.float32(0.8243)] +2025-10-30 19:35:57.465943: Epoch time: 20.39 s +2025-10-30 19:35:58.726654: +2025-10-30 19:35:58.729081: Epoch 769 +2025-10-30 19:35:58.730800: Current learning rate: 0.00267 +2025-10-30 19:36:17.897181: train_loss -0.9924 +2025-10-30 19:36:17.899915: val_loss -0.9015 +2025-10-30 19:36:17.902174: Pseudo dice [np.float32(0.9821), np.float32(0.9905), np.float32(0.9956), np.float32(0.8284)] +2025-10-30 19:36:17.903858: Epoch time: 19.17 s +2025-10-30 19:36:18.972080: +2025-10-30 19:36:18.975182: Epoch 770 +2025-10-30 19:36:18.978048: Current learning rate: 0.00266 +2025-10-30 19:36:39.329755: train_loss -0.9919 +2025-10-30 19:36:39.332285: val_loss -0.9031 +2025-10-30 19:36:39.334213: Pseudo dice [np.float32(0.9843), np.float32(0.9917), np.float32(0.9951), np.float32(0.8314)] +2025-10-30 19:36:39.336100: Epoch time: 20.36 s +2025-10-30 19:36:40.426044: +2025-10-30 19:36:40.428072: Epoch 771 +2025-10-30 19:36:40.430054: Current learning rate: 0.00265 +2025-10-30 19:36:58.760000: train_loss -0.9926 +2025-10-30 19:36:58.762669: val_loss -0.8985 +2025-10-30 19:36:58.764568: Pseudo dice [np.float32(0.9834), np.float32(0.9914), np.float32(0.9949), np.float32(0.8168)] +2025-10-30 19:36:58.766167: Epoch time: 18.34 s +2025-10-30 19:36:59.831674: +2025-10-30 19:36:59.833304: Epoch 772 +2025-10-30 19:36:59.834975: Current learning rate: 0.00264 +2025-10-30 19:37:19.368497: train_loss -0.9929 +2025-10-30 19:37:19.371499: val_loss -0.9106 +2025-10-30 19:37:19.377791: Pseudo dice [np.float32(0.984), np.float32(0.9916), np.float32(0.9956), np.float32(0.8456)] +2025-10-30 19:37:19.380215: Epoch time: 19.54 s +2025-10-30 19:37:21.616776: +2025-10-30 19:37:21.620700: Epoch 773 +2025-10-30 19:37:21.623047: Current learning rate: 0.00263 +2025-10-30 19:37:41.442189: train_loss -0.9929 +2025-10-30 19:37:41.444255: val_loss -0.9043 +2025-10-30 19:37:41.446417: Pseudo dice [np.float32(0.9841), np.float32(0.9913), np.float32(0.995), np.float32(0.8361)] +2025-10-30 19:37:41.448238: Epoch time: 19.83 s +2025-10-30 19:37:42.694391: +2025-10-30 19:37:42.696721: Epoch 774 +2025-10-30 19:37:42.698746: Current learning rate: 0.00262 +2025-10-30 19:38:03.205921: train_loss -0.9927 +2025-10-30 19:38:03.209819: val_loss -0.9047 +2025-10-30 19:38:03.211597: Pseudo dice [np.float32(0.9842), np.float32(0.9911), np.float32(0.9954), np.float32(0.8305)] +2025-10-30 19:38:03.213196: Epoch time: 20.51 s +2025-10-30 19:38:04.363385: +2025-10-30 19:38:04.366119: Epoch 775 +2025-10-30 19:38:04.368747: Current learning rate: 0.00261 +2025-10-30 19:38:24.959837: train_loss -0.9922 +2025-10-30 19:38:24.962840: val_loss -0.9001 +2025-10-30 19:38:24.964419: Pseudo dice [np.float32(0.983), np.float32(0.991), np.float32(0.9952), np.float32(0.8306)] +2025-10-30 19:38:24.966119: Epoch time: 20.6 s +2025-10-30 19:38:26.266874: +2025-10-30 19:38:26.269193: Epoch 776 +2025-10-30 19:38:26.271092: Current learning rate: 0.0026 +2025-10-30 19:38:46.015015: train_loss -0.9925 +2025-10-30 19:38:46.017383: val_loss -0.8989 +2025-10-30 19:38:46.019054: Pseudo dice [np.float32(0.9829), np.float32(0.991), np.float32(0.9956), np.float32(0.8239)] +2025-10-30 19:38:46.020563: Epoch time: 19.75 s +2025-10-30 19:38:47.325367: +2025-10-30 19:38:47.327442: Epoch 777 +2025-10-30 19:38:47.329067: Current learning rate: 0.00259 +2025-10-30 19:39:07.689343: train_loss -0.9924 +2025-10-30 19:39:07.691967: val_loss -0.9032 +2025-10-30 19:39:07.693353: Pseudo dice [np.float32(0.9846), np.float32(0.9909), np.float32(0.9952), np.float32(0.829)] +2025-10-30 19:39:07.694732: Epoch time: 20.37 s +2025-10-30 19:39:08.748505: +2025-10-30 19:39:08.751134: Epoch 778 +2025-10-30 19:39:08.753022: Current learning rate: 0.00258 +2025-10-30 19:39:28.330770: train_loss -0.9923 +2025-10-30 19:39:28.337284: val_loss -0.9064 +2025-10-30 19:39:28.339110: Pseudo dice [np.float32(0.9845), np.float32(0.9915), np.float32(0.9953), np.float32(0.8301)] +2025-10-30 19:39:28.340944: Epoch time: 19.59 s +2025-10-30 19:39:29.583991: +2025-10-30 19:39:29.585778: Epoch 779 +2025-10-30 19:39:29.587234: Current learning rate: 0.00257 +2025-10-30 19:39:50.047570: train_loss -0.9922 +2025-10-30 19:39:50.049809: val_loss -0.9032 +2025-10-30 19:39:50.052110: Pseudo dice [np.float32(0.9839), np.float32(0.9915), np.float32(0.9952), np.float32(0.8295)] +2025-10-30 19:39:50.054992: Epoch time: 20.47 s +2025-10-30 19:39:51.192616: +2025-10-30 19:39:51.194723: Epoch 780 +2025-10-30 19:39:51.196556: Current learning rate: 0.00256 +2025-10-30 19:40:11.617684: train_loss -0.993 +2025-10-30 19:40:11.621497: val_loss -0.8958 +2025-10-30 19:40:11.623297: Pseudo dice [np.float32(0.9832), np.float32(0.9907), np.float32(0.9949), np.float32(0.8167)] +2025-10-30 19:40:11.624789: Epoch time: 20.43 s +2025-10-30 19:40:12.823755: +2025-10-30 19:40:12.825700: Epoch 781 +2025-10-30 19:40:12.827952: Current learning rate: 0.00255 +2025-10-30 19:40:33.359343: train_loss -0.9929 +2025-10-30 19:40:33.361553: val_loss -0.9039 +2025-10-30 19:40:33.363226: Pseudo dice [np.float32(0.9831), np.float32(0.991), np.float32(0.9954), np.float32(0.8327)] +2025-10-30 19:40:33.364959: Epoch time: 20.54 s +2025-10-30 19:40:34.593525: +2025-10-30 19:40:34.595555: Epoch 782 +2025-10-30 19:40:34.597196: Current learning rate: 0.00254 +2025-10-30 19:40:54.776774: train_loss -0.9923 +2025-10-30 19:40:54.778764: val_loss -0.8984 +2025-10-30 19:40:54.780284: Pseudo dice [np.float32(0.9832), np.float32(0.991), np.float32(0.9952), np.float32(0.82)] +2025-10-30 19:40:54.781976: Epoch time: 20.18 s +2025-10-30 19:40:55.844487: +2025-10-30 19:40:55.846252: Epoch 783 +2025-10-30 19:40:55.847753: Current learning rate: 0.00253 +2025-10-30 19:41:15.133615: train_loss -0.9926 +2025-10-30 19:41:15.136859: val_loss -0.9026 +2025-10-30 19:41:15.138625: Pseudo dice [np.float32(0.9832), np.float32(0.9906), np.float32(0.9952), np.float32(0.8265)] +2025-10-30 19:41:15.140874: Epoch time: 19.29 s +2025-10-30 19:41:16.696991: +2025-10-30 19:41:16.698771: Epoch 784 +2025-10-30 19:41:16.700243: Current learning rate: 0.00252 +2025-10-30 19:41:36.418052: train_loss -0.9923 +2025-10-30 19:41:36.420484: val_loss -0.8981 +2025-10-30 19:41:36.422118: Pseudo dice [np.float32(0.9829), np.float32(0.991), np.float32(0.9951), np.float32(0.8127)] +2025-10-30 19:41:36.424425: Epoch time: 19.72 s +2025-10-30 19:41:37.676158: +2025-10-30 19:41:37.678000: Epoch 785 +2025-10-30 19:41:37.679551: Current learning rate: 0.00251 +2025-10-30 19:41:58.087007: train_loss -0.9929 +2025-10-30 19:41:58.089433: val_loss -0.8966 +2025-10-30 19:41:58.091064: Pseudo dice [np.float32(0.9847), np.float32(0.9909), np.float32(0.9948), np.float32(0.8161)] +2025-10-30 19:41:58.092613: Epoch time: 20.41 s +2025-10-30 19:41:59.325898: +2025-10-30 19:41:59.327636: Epoch 786 +2025-10-30 19:41:59.329142: Current learning rate: 0.0025 +2025-10-30 19:42:19.682925: train_loss -0.9921 +2025-10-30 19:42:19.685683: val_loss -0.897 +2025-10-30 19:42:19.687117: Pseudo dice [np.float32(0.9838), np.float32(0.9915), np.float32(0.995), np.float32(0.8149)] +2025-10-30 19:42:19.688566: Epoch time: 20.36 s +2025-10-30 19:42:20.751100: +2025-10-30 19:42:20.753412: Epoch 787 +2025-10-30 19:42:20.755059: Current learning rate: 0.00249 +2025-10-30 19:42:41.426424: train_loss -0.9927 +2025-10-30 19:42:41.428898: val_loss -0.8983 +2025-10-30 19:42:41.431603: Pseudo dice [np.float32(0.9832), np.float32(0.9911), np.float32(0.995), np.float32(0.8182)] +2025-10-30 19:42:41.433315: Epoch time: 20.68 s +2025-10-30 19:42:42.689461: +2025-10-30 19:42:42.691719: Epoch 788 +2025-10-30 19:42:42.693630: Current learning rate: 0.00248 +2025-10-30 19:43:03.395320: train_loss -0.9921 +2025-10-30 19:43:03.399724: val_loss -0.8989 +2025-10-30 19:43:03.401506: Pseudo dice [np.float32(0.982), np.float32(0.9906), np.float32(0.995), np.float32(0.8175)] +2025-10-30 19:43:03.403216: Epoch time: 20.71 s +2025-10-30 19:43:04.727996: +2025-10-30 19:43:04.729816: Epoch 789 +2025-10-30 19:43:04.731431: Current learning rate: 0.00247 +2025-10-30 19:43:24.989806: train_loss -0.9923 +2025-10-30 19:43:24.993021: val_loss -0.9091 +2025-10-30 19:43:24.994744: Pseudo dice [np.float32(0.9838), np.float32(0.9912), np.float32(0.9956), np.float32(0.8378)] +2025-10-30 19:43:24.996400: Epoch time: 20.26 s +2025-10-30 19:43:26.076834: +2025-10-30 19:43:26.078714: Epoch 790 +2025-10-30 19:43:26.080639: Current learning rate: 0.00245 +2025-10-30 19:43:45.213907: train_loss -0.9928 +2025-10-30 19:43:45.216035: val_loss -0.9057 +2025-10-30 19:43:45.218781: Pseudo dice [np.float32(0.983), np.float32(0.9908), np.float32(0.9953), np.float32(0.8385)] +2025-10-30 19:43:45.222052: Epoch time: 19.14 s +2025-10-30 19:43:46.449176: +2025-10-30 19:43:46.451502: Epoch 791 +2025-10-30 19:43:46.453265: Current learning rate: 0.00244 +2025-10-30 19:44:06.693198: train_loss -0.992 +2025-10-30 19:44:06.694889: val_loss -0.9095 +2025-10-30 19:44:06.696306: Pseudo dice [np.float32(0.9837), np.float32(0.9914), np.float32(0.9957), np.float32(0.8433)] +2025-10-30 19:44:06.697797: Epoch time: 20.25 s +2025-10-30 19:44:07.745510: +2025-10-30 19:44:07.747559: Epoch 792 +2025-10-30 19:44:07.749285: Current learning rate: 0.00243 +2025-10-30 19:44:28.148209: train_loss -0.9917 +2025-10-30 19:44:28.150427: val_loss -0.9047 +2025-10-30 19:44:28.151886: Pseudo dice [np.float32(0.9848), np.float32(0.9918), np.float32(0.9952), np.float32(0.8274)] +2025-10-30 19:44:28.153364: Epoch time: 20.4 s +2025-10-30 19:44:29.153561: +2025-10-30 19:44:29.158299: Epoch 793 +2025-10-30 19:44:29.159794: Current learning rate: 0.00242 +2025-10-30 19:44:49.560851: train_loss -0.9925 +2025-10-30 19:44:49.563098: val_loss -0.9067 +2025-10-30 19:44:49.564765: Pseudo dice [np.float32(0.9838), np.float32(0.9915), np.float32(0.9956), np.float32(0.8382)] +2025-10-30 19:44:49.566577: Epoch time: 20.41 s +2025-10-30 19:44:50.810611: +2025-10-30 19:44:50.812476: Epoch 794 +2025-10-30 19:44:50.814225: Current learning rate: 0.00241 +2025-10-30 19:45:11.113631: train_loss -0.9927 +2025-10-30 19:45:11.115822: val_loss -0.9072 +2025-10-30 19:45:11.117460: Pseudo dice [np.float32(0.9846), np.float32(0.9912), np.float32(0.9953), np.float32(0.8402)] +2025-10-30 19:45:11.118995: Epoch time: 20.3 s +2025-10-30 19:45:12.344742: +2025-10-30 19:45:12.346791: Epoch 795 +2025-10-30 19:45:12.348459: Current learning rate: 0.0024 +2025-10-30 19:45:32.622220: train_loss -0.9926 +2025-10-30 19:45:32.625295: val_loss -0.902 +2025-10-30 19:45:32.627046: Pseudo dice [np.float32(0.9828), np.float32(0.9906), np.float32(0.9955), np.float32(0.827)] +2025-10-30 19:45:32.628896: Epoch time: 20.28 s +2025-10-30 19:45:34.360349: +2025-10-30 19:45:34.363122: Epoch 796 +2025-10-30 19:45:34.366640: Current learning rate: 0.00239 +2025-10-30 19:45:55.071150: train_loss -0.993 +2025-10-30 19:45:55.073227: val_loss -0.9044 +2025-10-30 19:45:55.075615: Pseudo dice [np.float32(0.9841), np.float32(0.9917), np.float32(0.9953), np.float32(0.8335)] +2025-10-30 19:45:55.077830: Epoch time: 20.71 s +2025-10-30 19:45:56.209722: +2025-10-30 19:45:56.211754: Epoch 797 +2025-10-30 19:45:56.214216: Current learning rate: 0.00238 +2025-10-30 19:46:14.783892: train_loss -0.9917 +2025-10-30 19:46:14.786993: val_loss -0.9019 +2025-10-30 19:46:14.789433: Pseudo dice [np.float32(0.9829), np.float32(0.9906), np.float32(0.9955), np.float32(0.8289)] +2025-10-30 19:46:14.791275: Epoch time: 18.58 s +2025-10-30 19:46:16.137944: +2025-10-30 19:46:16.140298: Epoch 798 +2025-10-30 19:46:16.142153: Current learning rate: 0.00237 +2025-10-30 19:46:36.805434: train_loss -0.9924 +2025-10-30 19:46:36.811481: val_loss -0.9004 +2025-10-30 19:46:36.815279: Pseudo dice [np.float32(0.984), np.float32(0.9915), np.float32(0.995), np.float32(0.8194)] +2025-10-30 19:46:36.818662: Epoch time: 20.67 s +2025-10-30 19:46:38.075889: +2025-10-30 19:46:38.077774: Epoch 799 +2025-10-30 19:46:38.082144: Current learning rate: 0.00236 +2025-10-30 19:46:58.461554: train_loss -0.9925 +2025-10-30 19:46:58.463667: val_loss -0.9089 +2025-10-30 19:46:58.465425: Pseudo dice [np.float32(0.9842), np.float32(0.9914), np.float32(0.9957), np.float32(0.838)] +2025-10-30 19:46:58.467026: Epoch time: 20.39 s +2025-10-30 19:47:00.794778: +2025-10-30 19:47:00.796755: Epoch 800 +2025-10-30 19:47:00.798304: Current learning rate: 0.00235 +2025-10-30 19:47:21.103653: train_loss -0.9919 +2025-10-30 19:47:21.105887: val_loss -0.902 +2025-10-30 19:47:21.107659: Pseudo dice [np.float32(0.9835), np.float32(0.9909), np.float32(0.9955), np.float32(0.8293)] +2025-10-30 19:47:21.109311: Epoch time: 20.31 s +2025-10-30 19:47:22.218570: +2025-10-30 19:47:22.220578: Epoch 801 +2025-10-30 19:47:22.222488: Current learning rate: 0.00234 +2025-10-30 19:47:42.757419: train_loss -0.9927 +2025-10-30 19:47:42.761153: val_loss -0.9008 +2025-10-30 19:47:42.762981: Pseudo dice [np.float32(0.983), np.float32(0.9914), np.float32(0.9955), np.float32(0.8204)] +2025-10-30 19:47:42.764677: Epoch time: 20.54 s +2025-10-30 19:47:44.028372: +2025-10-30 19:47:44.031699: Epoch 802 +2025-10-30 19:47:44.034403: Current learning rate: 0.00233 +2025-10-30 19:48:04.462625: train_loss -0.9933 +2025-10-30 19:48:04.464842: val_loss -0.8958 +2025-10-30 19:48:04.467273: Pseudo dice [np.float32(0.9833), np.float32(0.9906), np.float32(0.9951), np.float32(0.8152)] +2025-10-30 19:48:04.469471: Epoch time: 20.44 s +2025-10-30 19:48:05.686006: +2025-10-30 19:48:05.687903: Epoch 803 +2025-10-30 19:48:05.689531: Current learning rate: 0.00232 +2025-10-30 19:48:23.755284: train_loss -0.9924 +2025-10-30 19:48:23.757442: val_loss -0.8994 +2025-10-30 19:48:23.758986: Pseudo dice [np.float32(0.9844), np.float32(0.9913), np.float32(0.9951), np.float32(0.8153)] +2025-10-30 19:48:23.760755: Epoch time: 18.07 s +2025-10-30 19:48:25.025047: +2025-10-30 19:48:25.027693: Epoch 804 +2025-10-30 19:48:25.029874: Current learning rate: 0.00231 +2025-10-30 19:48:45.367986: train_loss -0.993 +2025-10-30 19:48:45.372104: val_loss -0.8991 +2025-10-30 19:48:45.374330: Pseudo dice [np.float32(0.9842), np.float32(0.9914), np.float32(0.995), np.float32(0.8157)] +2025-10-30 19:48:45.375816: Epoch time: 20.34 s +2025-10-30 19:48:46.727041: +2025-10-30 19:48:46.732002: Epoch 805 +2025-10-30 19:48:46.736383: Current learning rate: 0.0023 +2025-10-30 19:49:07.215665: train_loss -0.9929 +2025-10-30 19:49:07.220829: val_loss -0.8996 +2025-10-30 19:49:07.222796: Pseudo dice [np.float32(0.9831), np.float32(0.9906), np.float32(0.995), np.float32(0.827)] +2025-10-30 19:49:07.225427: Epoch time: 20.49 s +2025-10-30 19:49:08.516334: +2025-10-30 19:49:08.518227: Epoch 806 +2025-10-30 19:49:08.520012: Current learning rate: 0.00229 +2025-10-30 19:49:29.018028: train_loss -0.9932 +2025-10-30 19:49:29.020827: val_loss -0.9054 +2025-10-30 19:49:29.023377: Pseudo dice [np.float32(0.9855), np.float32(0.9921), np.float32(0.9953), np.float32(0.8311)] +2025-10-30 19:49:29.025920: Epoch time: 20.5 s +2025-10-30 19:49:30.527153: +2025-10-30 19:49:30.529036: Epoch 807 +2025-10-30 19:49:30.532157: Current learning rate: 0.00228 +2025-10-30 19:49:51.059533: train_loss -0.9927 +2025-10-30 19:49:51.067757: val_loss -0.9031 +2025-10-30 19:49:51.069654: Pseudo dice [np.float32(0.9835), np.float32(0.9911), np.float32(0.9956), np.float32(0.8337)] +2025-10-30 19:49:51.071530: Epoch time: 20.53 s +2025-10-30 19:49:52.295147: +2025-10-30 19:49:52.296901: Epoch 808 +2025-10-30 19:49:52.298500: Current learning rate: 0.00226 +2025-10-30 19:50:12.633516: train_loss -0.9922 +2025-10-30 19:50:12.637806: val_loss -0.8948 +2025-10-30 19:50:12.640021: Pseudo dice [np.float32(0.9836), np.float32(0.9906), np.float32(0.9949), np.float32(0.8116)] +2025-10-30 19:50:12.642324: Epoch time: 20.34 s +2025-10-30 19:50:13.937185: +2025-10-30 19:50:13.939094: Epoch 809 +2025-10-30 19:50:13.940709: Current learning rate: 0.00225 +2025-10-30 19:50:33.570456: train_loss -0.9932 +2025-10-30 19:50:33.573741: val_loss -0.8949 +2025-10-30 19:50:33.575741: Pseudo dice [np.float32(0.9839), np.float32(0.9911), np.float32(0.9949), np.float32(0.8089)] +2025-10-30 19:50:33.577509: Epoch time: 19.63 s +2025-10-30 19:50:34.846782: +2025-10-30 19:50:34.849014: Epoch 810 +2025-10-30 19:50:34.853291: Current learning rate: 0.00224 +2025-10-30 19:50:53.173873: train_loss -0.9931 +2025-10-30 19:50:53.177253: val_loss -0.8975 +2025-10-30 19:50:53.178866: Pseudo dice [np.float32(0.9841), np.float32(0.9915), np.float32(0.9949), np.float32(0.8147)] +2025-10-30 19:50:53.180398: Epoch time: 18.33 s +2025-10-30 19:50:54.240140: +2025-10-30 19:50:54.242032: Epoch 811 +2025-10-30 19:50:54.243972: Current learning rate: 0.00223 +2025-10-30 19:51:14.790996: train_loss -0.9929 +2025-10-30 19:51:14.793410: val_loss -0.8987 +2025-10-30 19:51:14.795054: Pseudo dice [np.float32(0.9845), np.float32(0.9914), np.float32(0.9952), np.float32(0.8173)] +2025-10-30 19:51:14.796551: Epoch time: 20.55 s +2025-10-30 19:51:15.871217: +2025-10-30 19:51:15.873253: Epoch 812 +2025-10-30 19:51:15.875660: Current learning rate: 0.00222 +2025-10-30 19:51:36.448646: train_loss -0.9924 +2025-10-30 19:51:36.454090: val_loss -0.8961 +2025-10-30 19:51:36.455922: Pseudo dice [np.float32(0.9837), np.float32(0.9911), np.float32(0.9952), np.float32(0.8117)] +2025-10-30 19:51:36.457407: Epoch time: 20.58 s +2025-10-30 19:51:37.730877: +2025-10-30 19:51:37.732708: Epoch 813 +2025-10-30 19:51:37.737878: Current learning rate: 0.00221 +2025-10-30 19:51:58.331069: train_loss -0.9923 +2025-10-30 19:51:58.334485: val_loss -0.912 +2025-10-30 19:51:58.336022: Pseudo dice [np.float32(0.9854), np.float32(0.9914), np.float32(0.9952), np.float32(0.8431)] +2025-10-30 19:51:58.337531: Epoch time: 20.6 s +2025-10-30 19:51:59.618831: +2025-10-30 19:51:59.620675: Epoch 814 +2025-10-30 19:51:59.622221: Current learning rate: 0.0022 +2025-10-30 19:52:20.261484: train_loss -0.9923 +2025-10-30 19:52:20.263569: val_loss -0.8958 +2025-10-30 19:52:20.265845: Pseudo dice [np.float32(0.9836), np.float32(0.9913), np.float32(0.9951), np.float32(0.8103)] +2025-10-30 19:52:20.267902: Epoch time: 20.64 s +2025-10-30 19:52:21.411936: +2025-10-30 19:52:21.413687: Epoch 815 +2025-10-30 19:52:21.415256: Current learning rate: 0.00219 +2025-10-30 19:52:41.568398: train_loss -0.9927 +2025-10-30 19:52:41.570622: val_loss -0.9029 +2025-10-30 19:52:41.573040: Pseudo dice [np.float32(0.9853), np.float32(0.9923), np.float32(0.9952), np.float32(0.8254)] +2025-10-30 19:52:41.574691: Epoch time: 20.16 s +2025-10-30 19:52:42.762149: +2025-10-30 19:52:42.764174: Epoch 816 +2025-10-30 19:52:42.765899: Current learning rate: 0.00218 +2025-10-30 19:53:02.521459: train_loss -0.9926 +2025-10-30 19:53:02.525465: val_loss -0.9024 +2025-10-30 19:53:02.527512: Pseudo dice [np.float32(0.9846), np.float32(0.9919), np.float32(0.9953), np.float32(0.8151)] +2025-10-30 19:53:02.529305: Epoch time: 19.76 s +2025-10-30 19:53:03.846386: +2025-10-30 19:53:03.848499: Epoch 817 +2025-10-30 19:53:03.850533: Current learning rate: 0.00217 +2025-10-30 19:53:23.329255: train_loss -0.9916 +2025-10-30 19:53:23.334291: val_loss -0.8989 +2025-10-30 19:53:23.336276: Pseudo dice [np.float32(0.9849), np.float32(0.9913), np.float32(0.995), np.float32(0.8094)] +2025-10-30 19:53:23.338130: Epoch time: 19.48 s +2025-10-30 19:53:24.935169: +2025-10-30 19:53:24.937015: Epoch 818 +2025-10-30 19:53:24.938618: Current learning rate: 0.00216 +2025-10-30 19:53:45.370345: train_loss -0.9912 +2025-10-30 19:53:45.373604: val_loss -0.9072 +2025-10-30 19:53:45.375736: Pseudo dice [np.float32(0.9821), np.float32(0.9904), np.float32(0.9956), np.float32(0.8367)] +2025-10-30 19:53:45.377255: Epoch time: 20.44 s +2025-10-30 19:53:46.420250: +2025-10-30 19:53:46.422197: Epoch 819 +2025-10-30 19:53:46.423666: Current learning rate: 0.00215 +2025-10-30 19:54:06.865587: train_loss -0.9921 +2025-10-30 19:54:06.876193: val_loss -0.9 +2025-10-30 19:54:06.878211: Pseudo dice [np.float32(0.9833), np.float32(0.9901), np.float32(0.995), np.float32(0.824)] +2025-10-30 19:54:06.879851: Epoch time: 20.45 s +2025-10-30 19:54:07.888396: +2025-10-30 19:54:07.890058: Epoch 820 +2025-10-30 19:54:07.891363: Current learning rate: 0.00214 +2025-10-30 19:54:28.308654: train_loss -0.9926 +2025-10-30 19:54:28.311065: val_loss -0.8987 +2025-10-30 19:54:28.312622: Pseudo dice [np.float32(0.9837), np.float32(0.9908), np.float32(0.9951), np.float32(0.8271)] +2025-10-30 19:54:28.314301: Epoch time: 20.42 s +2025-10-30 19:54:29.473340: +2025-10-30 19:54:29.475616: Epoch 821 +2025-10-30 19:54:29.477273: Current learning rate: 0.00213 +2025-10-30 19:54:50.307620: train_loss -0.9924 +2025-10-30 19:54:50.309754: val_loss -0.8938 +2025-10-30 19:54:50.314684: Pseudo dice [np.float32(0.983), np.float32(0.9902), np.float32(0.9949), np.float32(0.8158)] +2025-10-30 19:54:50.316452: Epoch time: 20.84 s +2025-10-30 19:54:51.553222: +2025-10-30 19:54:51.556018: Epoch 822 +2025-10-30 19:54:51.557749: Current learning rate: 0.00212 +2025-10-30 19:55:10.963988: train_loss -0.9928 +2025-10-30 19:55:10.966910: val_loss -0.9001 +2025-10-30 19:55:10.969593: Pseudo dice [np.float32(0.9843), np.float32(0.9914), np.float32(0.995), np.float32(0.8175)] +2025-10-30 19:55:10.971889: Epoch time: 19.41 s +2025-10-30 19:55:12.062982: +2025-10-30 19:55:12.065063: Epoch 823 +2025-10-30 19:55:12.066827: Current learning rate: 0.0021 +2025-10-30 19:55:32.496166: train_loss -0.9926 +2025-10-30 19:55:32.498683: val_loss -0.9024 +2025-10-30 19:55:32.501300: Pseudo dice [np.float32(0.9837), np.float32(0.9917), np.float32(0.9953), np.float32(0.8236)] +2025-10-30 19:55:32.503196: Epoch time: 20.43 s +2025-10-30 19:55:33.717011: +2025-10-30 19:55:33.718913: Epoch 824 +2025-10-30 19:55:33.720446: Current learning rate: 0.00209 +2025-10-30 19:55:53.548048: train_loss -0.9925 +2025-10-30 19:55:53.550342: val_loss -0.9072 +2025-10-30 19:55:53.551939: Pseudo dice [np.float32(0.9842), np.float32(0.9917), np.float32(0.9951), np.float32(0.8384)] +2025-10-30 19:55:53.553584: Epoch time: 19.83 s +2025-10-30 19:55:54.627292: +2025-10-30 19:55:54.629520: Epoch 825 +2025-10-30 19:55:54.631310: Current learning rate: 0.00208 +2025-10-30 19:56:15.128323: train_loss -0.9924 +2025-10-30 19:56:15.131604: val_loss -0.9003 +2025-10-30 19:56:15.133398: Pseudo dice [np.float32(0.9844), np.float32(0.9912), np.float32(0.9951), np.float32(0.8207)] +2025-10-30 19:56:15.135356: Epoch time: 20.5 s +2025-10-30 19:56:16.171393: +2025-10-30 19:56:16.173252: Epoch 826 +2025-10-30 19:56:16.175001: Current learning rate: 0.00207 +2025-10-30 19:56:36.760331: train_loss -0.9927 +2025-10-30 19:56:36.763615: val_loss -0.895 +2025-10-30 19:56:36.765179: Pseudo dice [np.float32(0.9847), np.float32(0.9912), np.float32(0.9947), np.float32(0.813)] +2025-10-30 19:56:36.766650: Epoch time: 20.59 s +2025-10-30 19:56:37.946484: +2025-10-30 19:56:37.949829: Epoch 827 +2025-10-30 19:56:37.952094: Current learning rate: 0.00206 +2025-10-30 19:56:58.360703: train_loss -0.993 +2025-10-30 19:56:58.363011: val_loss -0.9042 +2025-10-30 19:56:58.364473: Pseudo dice [np.float32(0.9845), np.float32(0.9916), np.float32(0.995), np.float32(0.8309)] +2025-10-30 19:56:58.365963: Epoch time: 20.42 s +2025-10-30 19:56:59.468581: +2025-10-30 19:56:59.470459: Epoch 828 +2025-10-30 19:56:59.472239: Current learning rate: 0.00205 +2025-10-30 19:57:19.903457: train_loss -0.9932 +2025-10-30 19:57:19.906204: val_loss -0.8989 +2025-10-30 19:57:19.907757: Pseudo dice [np.float32(0.9835), np.float32(0.9913), np.float32(0.9951), np.float32(0.8187)] +2025-10-30 19:57:19.909245: Epoch time: 20.44 s +2025-10-30 19:57:20.924135: +2025-10-30 19:57:20.925819: Epoch 829 +2025-10-30 19:57:20.927284: Current learning rate: 0.00204 +2025-10-30 19:57:41.126611: train_loss -0.9929 +2025-10-30 19:57:41.128979: val_loss -0.8983 +2025-10-30 19:57:41.130562: Pseudo dice [np.float32(0.9843), np.float32(0.9916), np.float32(0.9949), np.float32(0.8152)] +2025-10-30 19:57:41.132246: Epoch time: 20.2 s +2025-10-30 19:57:42.372251: +2025-10-30 19:57:42.374222: Epoch 830 +2025-10-30 19:57:42.376133: Current learning rate: 0.00203 +2025-10-30 19:58:02.980122: train_loss -0.993 +2025-10-30 19:58:02.982079: val_loss -0.8909 +2025-10-30 19:58:02.983641: Pseudo dice [np.float32(0.9839), np.float32(0.9911), np.float32(0.9946), np.float32(0.8021)] +2025-10-30 19:58:02.985236: Epoch time: 20.61 s +2025-10-30 19:58:04.642191: +2025-10-30 19:58:04.644453: Epoch 831 +2025-10-30 19:58:04.646117: Current learning rate: 0.00202 +2025-10-30 19:58:24.356333: train_loss -0.9933 +2025-10-30 19:58:24.359092: val_loss -0.8996 +2025-10-30 19:58:24.360801: Pseudo dice [np.float32(0.9836), np.float32(0.991), np.float32(0.995), np.float32(0.818)] +2025-10-30 19:58:24.362347: Epoch time: 19.72 s +2025-10-30 19:58:25.477200: +2025-10-30 19:58:25.479062: Epoch 832 +2025-10-30 19:58:25.481164: Current learning rate: 0.00201 +2025-10-30 19:58:46.114094: train_loss -0.9935 +2025-10-30 19:58:46.116601: val_loss -0.8945 +2025-10-30 19:58:46.118290: Pseudo dice [np.float32(0.9836), np.float32(0.991), np.float32(0.9952), np.float32(0.812)] +2025-10-30 19:58:46.120013: Epoch time: 20.64 s +2025-10-30 19:58:47.141260: +2025-10-30 19:58:47.143539: Epoch 833 +2025-10-30 19:58:47.145386: Current learning rate: 0.002 +2025-10-30 19:59:07.790092: train_loss -0.993 +2025-10-30 19:59:07.792520: val_loss -0.9017 +2025-10-30 19:59:07.794400: Pseudo dice [np.float32(0.9834), np.float32(0.9909), np.float32(0.9955), np.float32(0.8223)] +2025-10-30 19:59:07.796030: Epoch time: 20.65 s +2025-10-30 19:59:08.882591: +2025-10-30 19:59:08.884791: Epoch 834 +2025-10-30 19:59:08.886720: Current learning rate: 0.00199 +2025-10-30 19:59:29.450799: train_loss -0.9931 +2025-10-30 19:59:29.456656: val_loss -0.8928 +2025-10-30 19:59:29.458422: Pseudo dice [np.float32(0.9833), np.float32(0.9906), np.float32(0.9949), np.float32(0.809)] +2025-10-30 19:59:29.460067: Epoch time: 20.57 s +2025-10-30 19:59:30.522891: +2025-10-30 19:59:30.524693: Epoch 835 +2025-10-30 19:59:30.526279: Current learning rate: 0.00198 +2025-10-30 19:59:49.995651: train_loss -0.9932 +2025-10-30 19:59:49.997823: val_loss -0.8979 +2025-10-30 19:59:49.999609: Pseudo dice [np.float32(0.9848), np.float32(0.991), np.float32(0.995), np.float32(0.8188)] +2025-10-30 19:59:50.001481: Epoch time: 19.47 s +2025-10-30 19:59:51.089036: +2025-10-30 19:59:51.090867: Epoch 836 +2025-10-30 19:59:51.092399: Current learning rate: 0.00196 +2025-10-30 20:00:11.577827: train_loss -0.9937 +2025-10-30 20:00:11.581105: val_loss -0.9061 +2025-10-30 20:00:11.583402: Pseudo dice [np.float32(0.9855), np.float32(0.9926), np.float32(0.9954), np.float32(0.8298)] +2025-10-30 20:00:11.585011: Epoch time: 20.49 s +2025-10-30 20:00:12.797951: +2025-10-30 20:00:12.801228: Epoch 837 +2025-10-30 20:00:12.805339: Current learning rate: 0.00195 +2025-10-30 20:00:33.414584: train_loss -0.9932 +2025-10-30 20:00:33.417811: val_loss -0.8984 +2025-10-30 20:00:33.419562: Pseudo dice [np.float32(0.984), np.float32(0.9911), np.float32(0.995), np.float32(0.8169)] +2025-10-30 20:00:33.421361: Epoch time: 20.62 s +2025-10-30 20:00:34.452648: +2025-10-30 20:00:34.455167: Epoch 838 +2025-10-30 20:00:34.457376: Current learning rate: 0.00194 +2025-10-30 20:00:53.978607: train_loss -0.9936 +2025-10-30 20:00:53.981367: val_loss -0.8932 +2025-10-30 20:00:53.984146: Pseudo dice [np.float32(0.9847), np.float32(0.9914), np.float32(0.9946), np.float32(0.8011)] +2025-10-30 20:00:53.985888: Epoch time: 19.53 s +2025-10-30 20:00:55.182765: +2025-10-30 20:00:55.184930: Epoch 839 +2025-10-30 20:00:55.186767: Current learning rate: 0.00193 +2025-10-30 20:01:15.718393: train_loss -0.9933 +2025-10-30 20:01:15.720677: val_loss -0.8911 +2025-10-30 20:01:15.722377: Pseudo dice [np.float32(0.9836), np.float32(0.9908), np.float32(0.9948), np.float32(0.8002)] +2025-10-30 20:01:15.724220: Epoch time: 20.54 s +2025-10-30 20:01:16.952880: +2025-10-30 20:01:16.955366: Epoch 840 +2025-10-30 20:01:16.957542: Current learning rate: 0.00192 +2025-10-30 20:01:37.309445: train_loss -0.993 +2025-10-30 20:01:37.312457: val_loss -0.8967 +2025-10-30 20:01:37.314157: Pseudo dice [np.float32(0.9838), np.float32(0.9915), np.float32(0.9949), np.float32(0.8116)] +2025-10-30 20:01:37.315944: Epoch time: 20.36 s +2025-10-30 20:01:38.405653: +2025-10-30 20:01:38.407671: Epoch 841 +2025-10-30 20:01:38.409466: Current learning rate: 0.00191 +2025-10-30 20:01:57.907577: train_loss -0.9938 +2025-10-30 20:01:57.909913: val_loss -0.9016 +2025-10-30 20:01:57.911501: Pseudo dice [np.float32(0.9849), np.float32(0.9915), np.float32(0.995), np.float32(0.8222)] +2025-10-30 20:01:57.913153: Epoch time: 19.5 s +2025-10-30 20:01:58.963793: +2025-10-30 20:01:58.965576: Epoch 842 +2025-10-30 20:01:58.967671: Current learning rate: 0.0019 +2025-10-30 20:02:19.454660: train_loss -0.9933 +2025-10-30 20:02:19.456667: val_loss -0.9001 +2025-10-30 20:02:19.458210: Pseudo dice [np.float32(0.9839), np.float32(0.9917), np.float32(0.9953), np.float32(0.8243)] +2025-10-30 20:02:19.459561: Epoch time: 20.49 s +2025-10-30 20:02:20.844347: +2025-10-30 20:02:20.846075: Epoch 843 +2025-10-30 20:02:20.847761: Current learning rate: 0.00189 +2025-10-30 20:02:41.508262: train_loss -0.9933 +2025-10-30 20:02:41.512691: val_loss -0.9011 +2025-10-30 20:02:41.514455: Pseudo dice [np.float32(0.9845), np.float32(0.9913), np.float32(0.9953), np.float32(0.8237)] +2025-10-30 20:02:41.516066: Epoch time: 20.67 s +2025-10-30 20:02:42.831437: +2025-10-30 20:02:42.833399: Epoch 844 +2025-10-30 20:02:42.835270: Current learning rate: 0.00188 +2025-10-30 20:03:02.509064: train_loss -0.9928 +2025-10-30 20:03:02.511782: val_loss -0.8959 +2025-10-30 20:03:02.514717: Pseudo dice [np.float32(0.9831), np.float32(0.9912), np.float32(0.9951), np.float32(0.817)] +2025-10-30 20:03:02.517899: Epoch time: 19.68 s +2025-10-30 20:03:03.591208: +2025-10-30 20:03:03.593153: Epoch 845 +2025-10-30 20:03:03.594805: Current learning rate: 0.00187 +2025-10-30 20:03:24.140669: train_loss -0.9934 +2025-10-30 20:03:24.143179: val_loss -0.8994 +2025-10-30 20:03:24.144885: Pseudo dice [np.float32(0.9836), np.float32(0.9912), np.float32(0.9951), np.float32(0.8234)] +2025-10-30 20:03:24.146662: Epoch time: 20.55 s +2025-10-30 20:03:25.365286: +2025-10-30 20:03:25.367742: Epoch 846 +2025-10-30 20:03:25.369529: Current learning rate: 0.00186 +2025-10-30 20:03:45.848267: train_loss -0.9931 +2025-10-30 20:03:45.852387: val_loss -0.8953 +2025-10-30 20:03:45.854017: Pseudo dice [np.float32(0.9838), np.float32(0.9913), np.float32(0.9949), np.float32(0.8091)] +2025-10-30 20:03:45.858422: Epoch time: 20.49 s +2025-10-30 20:03:47.150246: +2025-10-30 20:03:47.152529: Epoch 847 +2025-10-30 20:03:47.154348: Current learning rate: 0.00185 +2025-10-30 20:04:07.607583: train_loss -0.9925 +2025-10-30 20:04:07.610065: val_loss -0.9047 +2025-10-30 20:04:07.612112: Pseudo dice [np.float32(0.9832), np.float32(0.9912), np.float32(0.9954), np.float32(0.8348)] +2025-10-30 20:04:07.614103: Epoch time: 20.46 s +2025-10-30 20:04:08.939330: +2025-10-30 20:04:08.941434: Epoch 848 +2025-10-30 20:04:08.943293: Current learning rate: 0.00184 +2025-10-30 20:04:28.607872: train_loss -0.9935 +2025-10-30 20:04:28.611493: val_loss -0.8945 +2025-10-30 20:04:28.614830: Pseudo dice [np.float32(0.9835), np.float32(0.9908), np.float32(0.9949), np.float32(0.8115)] +2025-10-30 20:04:28.617484: Epoch time: 19.67 s +2025-10-30 20:04:29.686607: +2025-10-30 20:04:29.688807: Epoch 849 +2025-10-30 20:04:29.690745: Current learning rate: 0.00182 +2025-10-30 20:04:50.317008: train_loss -0.9928 +2025-10-30 20:04:50.320243: val_loss -0.8976 +2025-10-30 20:04:50.322281: Pseudo dice [np.float32(0.9843), np.float32(0.9916), np.float32(0.9947), np.float32(0.8181)] +2025-10-30 20:04:50.324268: Epoch time: 20.63 s +2025-10-30 20:04:52.565009: +2025-10-30 20:04:52.566911: Epoch 850 +2025-10-30 20:04:52.568691: Current learning rate: 0.00181 +2025-10-30 20:05:12.834469: train_loss -0.9937 +2025-10-30 20:05:12.837097: val_loss -0.8975 +2025-10-30 20:05:12.838786: Pseudo dice [np.float32(0.9843), np.float32(0.991), np.float32(0.995), np.float32(0.8134)] +2025-10-30 20:05:12.840437: Epoch time: 20.27 s +2025-10-30 20:05:13.856160: +2025-10-30 20:05:13.858464: Epoch 851 +2025-10-30 20:05:13.861214: Current learning rate: 0.0018 +2025-10-30 20:05:33.354795: train_loss -0.9934 +2025-10-30 20:05:33.357084: val_loss -0.8863 +2025-10-30 20:05:33.358643: Pseudo dice [np.float32(0.9834), np.float32(0.9909), np.float32(0.9948), np.float32(0.7894)] +2025-10-30 20:05:33.360175: Epoch time: 19.5 s +2025-10-30 20:05:34.558811: +2025-10-30 20:05:34.561306: Epoch 852 +2025-10-30 20:05:34.563418: Current learning rate: 0.00179 +2025-10-30 20:05:54.980017: train_loss -0.994 +2025-10-30 20:05:54.983088: val_loss -0.8924 +2025-10-30 20:05:54.985395: Pseudo dice [np.float32(0.9833), np.float32(0.9911), np.float32(0.9948), np.float32(0.8099)] +2025-10-30 20:05:54.987570: Epoch time: 20.42 s +2025-10-30 20:05:56.025817: +2025-10-30 20:05:56.028028: Epoch 853 +2025-10-30 20:05:56.029701: Current learning rate: 0.00178 +2025-10-30 20:06:16.501698: train_loss -0.9936 +2025-10-30 20:06:16.504596: val_loss -0.89 +2025-10-30 20:06:16.506782: Pseudo dice [np.float32(0.9836), np.float32(0.991), np.float32(0.9948), np.float32(0.8054)] +2025-10-30 20:06:16.509083: Epoch time: 20.48 s +2025-10-30 20:06:17.520724: +2025-10-30 20:06:17.523176: Epoch 854 +2025-10-30 20:06:17.525131: Current learning rate: 0.00177 +2025-10-30 20:06:37.191619: train_loss -0.9933 +2025-10-30 20:06:37.194493: val_loss -0.9074 +2025-10-30 20:06:37.197345: Pseudo dice [np.float32(0.9844), np.float32(0.9918), np.float32(0.9953), np.float32(0.839)] +2025-10-30 20:06:37.200340: Epoch time: 19.67 s +2025-10-30 20:06:39.110412: +2025-10-30 20:06:39.112927: Epoch 855 +2025-10-30 20:06:39.115309: Current learning rate: 0.00176 +2025-10-30 20:06:59.439659: train_loss -0.9936 +2025-10-30 20:06:59.442456: val_loss -0.8928 +2025-10-30 20:06:59.444013: Pseudo dice [np.float32(0.9831), np.float32(0.9907), np.float32(0.9948), np.float32(0.8073)] +2025-10-30 20:06:59.445673: Epoch time: 20.33 s +2025-10-30 20:07:00.668113: +2025-10-30 20:07:00.670237: Epoch 856 +2025-10-30 20:07:00.671847: Current learning rate: 0.00175 +2025-10-30 20:07:21.433915: train_loss -0.9929 +2025-10-30 20:07:21.436417: val_loss -0.8982 +2025-10-30 20:07:21.438065: Pseudo dice [np.float32(0.9834), np.float32(0.991), np.float32(0.9952), np.float32(0.8201)] +2025-10-30 20:07:21.439767: Epoch time: 20.77 s +2025-10-30 20:07:22.509503: +2025-10-30 20:07:22.511522: Epoch 857 +2025-10-30 20:07:22.513460: Current learning rate: 0.00174 +2025-10-30 20:07:43.048423: train_loss -0.9936 +2025-10-30 20:07:43.050928: val_loss -0.9038 +2025-10-30 20:07:43.052646: Pseudo dice [np.float32(0.9843), np.float32(0.9915), np.float32(0.9955), np.float32(0.8269)] +2025-10-30 20:07:43.054214: Epoch time: 20.54 s +2025-10-30 20:07:44.341247: +2025-10-30 20:07:44.344045: Epoch 858 +2025-10-30 20:07:44.346466: Current learning rate: 0.00173 +2025-10-30 20:08:03.761813: train_loss -0.9938 +2025-10-30 20:08:03.764838: val_loss -0.901 +2025-10-30 20:08:03.766742: Pseudo dice [np.float32(0.9847), np.float32(0.9911), np.float32(0.9951), np.float32(0.8251)] +2025-10-30 20:08:03.769465: Epoch time: 19.42 s +2025-10-30 20:08:04.765487: +2025-10-30 20:08:04.767215: Epoch 859 +2025-10-30 20:08:04.769939: Current learning rate: 0.00172 +2025-10-30 20:08:25.484883: train_loss -0.993 +2025-10-30 20:08:25.487205: val_loss -0.897 +2025-10-30 20:08:25.489696: Pseudo dice [np.float32(0.9844), np.float32(0.9911), np.float32(0.9952), np.float32(0.8175)] +2025-10-30 20:08:25.492034: Epoch time: 20.72 s +2025-10-30 20:08:26.553585: +2025-10-30 20:08:26.556034: Epoch 860 +2025-10-30 20:08:26.557866: Current learning rate: 0.0017 +2025-10-30 20:08:46.927579: train_loss -0.994 +2025-10-30 20:08:46.929982: val_loss -0.8988 +2025-10-30 20:08:46.931621: Pseudo dice [np.float32(0.9844), np.float32(0.9918), np.float32(0.9953), np.float32(0.8159)] +2025-10-30 20:08:46.933118: Epoch time: 20.38 s +2025-10-30 20:08:48.038450: +2025-10-30 20:08:48.040587: Epoch 861 +2025-10-30 20:08:48.042415: Current learning rate: 0.00169 +2025-10-30 20:09:07.842282: train_loss -0.9929 +2025-10-30 20:09:07.845344: val_loss -0.9064 +2025-10-30 20:09:07.847012: Pseudo dice [np.float32(0.985), np.float32(0.9922), np.float32(0.9956), np.float32(0.8322)] +2025-10-30 20:09:07.848746: Epoch time: 19.81 s +2025-10-30 20:09:08.991820: +2025-10-30 20:09:08.993460: Epoch 862 +2025-10-30 20:09:08.995640: Current learning rate: 0.00168 +2025-10-30 20:09:29.112448: train_loss -0.9935 +2025-10-30 20:09:29.115904: val_loss -0.9072 +2025-10-30 20:09:29.119076: Pseudo dice [np.float32(0.9858), np.float32(0.9926), np.float32(0.9955), np.float32(0.8297)] +2025-10-30 20:09:29.120696: Epoch time: 20.12 s +2025-10-30 20:09:30.200129: +2025-10-30 20:09:30.202024: Epoch 863 +2025-10-30 20:09:30.203757: Current learning rate: 0.00167 +2025-10-30 20:09:50.203650: train_loss -0.9938 +2025-10-30 20:09:50.205999: val_loss -0.8993 +2025-10-30 20:09:50.207693: Pseudo dice [np.float32(0.9838), np.float32(0.9911), np.float32(0.9954), np.float32(0.8237)] +2025-10-30 20:09:50.209335: Epoch time: 20.0 s +2025-10-30 20:09:51.376516: +2025-10-30 20:09:51.378575: Epoch 864 +2025-10-30 20:09:51.380547: Current learning rate: 0.00166 +2025-10-30 20:10:11.812755: train_loss -0.9935 +2025-10-30 20:10:11.816033: val_loss -0.9078 +2025-10-30 20:10:11.817518: Pseudo dice [np.float32(0.9834), np.float32(0.9911), np.float32(0.9957), np.float32(0.8412)] +2025-10-30 20:10:11.819006: Epoch time: 20.44 s +2025-10-30 20:10:13.136523: +2025-10-30 20:10:13.138329: Epoch 865 +2025-10-30 20:10:13.139854: Current learning rate: 0.00165 +2025-10-30 20:10:32.721272: train_loss -0.9938 +2025-10-30 20:10:32.723980: val_loss -0.9042 +2025-10-30 20:10:32.725935: Pseudo dice [np.float32(0.9842), np.float32(0.9916), np.float32(0.9953), np.float32(0.8364)] +2025-10-30 20:10:32.727612: Epoch time: 19.59 s +2025-10-30 20:10:33.721202: +2025-10-30 20:10:33.723060: Epoch 866 +2025-10-30 20:10:33.724711: Current learning rate: 0.00164 +2025-10-30 20:10:54.413939: train_loss -0.9936 +2025-10-30 20:10:54.416350: val_loss -0.8983 +2025-10-30 20:10:54.418049: Pseudo dice [np.float32(0.9848), np.float32(0.9913), np.float32(0.995), np.float32(0.8164)] +2025-10-30 20:10:54.419799: Epoch time: 20.69 s +2025-10-30 20:10:55.625304: +2025-10-30 20:10:55.631803: Epoch 867 +2025-10-30 20:10:55.633562: Current learning rate: 0.00163 +2025-10-30 20:11:16.188916: train_loss -0.9933 +2025-10-30 20:11:16.192432: val_loss -0.9036 +2025-10-30 20:11:16.194501: Pseudo dice [np.float32(0.9836), np.float32(0.9907), np.float32(0.9953), np.float32(0.829)] +2025-10-30 20:11:16.196269: Epoch time: 20.57 s +2025-10-30 20:11:17.953622: +2025-10-30 20:11:17.955467: Epoch 868 +2025-10-30 20:11:17.957114: Current learning rate: 0.00162 +2025-10-30 20:11:39.097572: train_loss -0.9933 +2025-10-30 20:11:39.100167: val_loss -0.8937 +2025-10-30 20:11:39.101700: Pseudo dice [np.float32(0.9854), np.float32(0.9915), np.float32(0.9947), np.float32(0.8078)] +2025-10-30 20:11:39.103359: Epoch time: 21.15 s +2025-10-30 20:11:40.292084: +2025-10-30 20:11:40.294116: Epoch 869 +2025-10-30 20:11:40.295885: Current learning rate: 0.00161 +2025-10-30 20:12:01.093091: train_loss -0.994 +2025-10-30 20:12:01.096197: val_loss -0.8968 +2025-10-30 20:12:01.098780: Pseudo dice [np.float32(0.9838), np.float32(0.991), np.float32(0.995), np.float32(0.8126)] +2025-10-30 20:12:01.100513: Epoch time: 20.8 s +2025-10-30 20:12:02.248890: +2025-10-30 20:12:02.251007: Epoch 870 +2025-10-30 20:12:02.252695: Current learning rate: 0.00159 +2025-10-30 20:12:23.270141: train_loss -0.9935 +2025-10-30 20:12:23.273297: val_loss -0.8929 +2025-10-30 20:12:23.274962: Pseudo dice [np.float32(0.9842), np.float32(0.9912), np.float32(0.995), np.float32(0.8033)] +2025-10-30 20:12:23.277418: Epoch time: 21.02 s +2025-10-30 20:12:24.370485: +2025-10-30 20:12:24.372833: Epoch 871 +2025-10-30 20:12:24.374634: Current learning rate: 0.00158 +2025-10-30 20:12:44.488815: train_loss -0.9935 +2025-10-30 20:12:44.494468: val_loss -0.8928 +2025-10-30 20:12:44.496073: Pseudo dice [np.float32(0.9842), np.float32(0.991), np.float32(0.995), np.float32(0.8042)] +2025-10-30 20:12:44.497577: Epoch time: 20.12 s +2025-10-30 20:12:45.701077: +2025-10-30 20:12:45.702914: Epoch 872 +2025-10-30 20:12:45.704568: Current learning rate: 0.00157 +2025-10-30 20:13:06.551674: train_loss -0.9933 +2025-10-30 20:13:06.554004: val_loss -0.8913 +2025-10-30 20:13:06.555820: Pseudo dice [np.float32(0.9829), np.float32(0.9907), np.float32(0.9949), np.float32(0.8063)] +2025-10-30 20:13:06.557699: Epoch time: 20.85 s +2025-10-30 20:13:07.656037: +2025-10-30 20:13:07.657981: Epoch 873 +2025-10-30 20:13:07.659847: Current learning rate: 0.00156 +2025-10-30 20:13:27.748616: train_loss -0.9932 +2025-10-30 20:13:27.751991: val_loss -0.9016 +2025-10-30 20:13:27.753983: Pseudo dice [np.float32(0.9845), np.float32(0.9921), np.float32(0.9955), np.float32(0.8248)] +2025-10-30 20:13:27.756074: Epoch time: 20.09 s +2025-10-30 20:13:29.043645: +2025-10-30 20:13:29.045670: Epoch 874 +2025-10-30 20:13:29.047760: Current learning rate: 0.00155 +2025-10-30 20:13:49.659533: train_loss -0.9935 +2025-10-30 20:13:49.661888: val_loss -0.9003 +2025-10-30 20:13:49.663503: Pseudo dice [np.float32(0.983), np.float32(0.9914), np.float32(0.9954), np.float32(0.8265)] +2025-10-30 20:13:49.665149: Epoch time: 20.62 s +2025-10-30 20:13:50.872074: +2025-10-30 20:13:50.874293: Epoch 875 +2025-10-30 20:13:50.876059: Current learning rate: 0.00154 +2025-10-30 20:14:11.730485: train_loss -0.9936 +2025-10-30 20:14:11.735759: val_loss -0.9055 +2025-10-30 20:14:11.737568: Pseudo dice [np.float32(0.9842), np.float32(0.9916), np.float32(0.9954), np.float32(0.8311)] +2025-10-30 20:14:11.739325: Epoch time: 20.86 s +2025-10-30 20:14:12.983270: +2025-10-30 20:14:12.985312: Epoch 876 +2025-10-30 20:14:12.986969: Current learning rate: 0.00153 +2025-10-30 20:14:33.973993: train_loss -0.9935 +2025-10-30 20:14:33.977042: val_loss -0.9008 +2025-10-30 20:14:33.978812: Pseudo dice [np.float32(0.9839), np.float32(0.991), np.float32(0.9954), np.float32(0.8266)] +2025-10-30 20:14:33.980467: Epoch time: 20.99 s +2025-10-30 20:14:35.239141: +2025-10-30 20:14:35.241777: Epoch 877 +2025-10-30 20:14:35.243647: Current learning rate: 0.00152 +2025-10-30 20:14:56.189334: train_loss -0.994 +2025-10-30 20:14:56.191654: val_loss -0.9024 +2025-10-30 20:14:56.193332: Pseudo dice [np.float32(0.9829), np.float32(0.991), np.float32(0.9956), np.float32(0.832)] +2025-10-30 20:14:56.195038: Epoch time: 20.95 s +2025-10-30 20:14:57.341390: +2025-10-30 20:14:57.343374: Epoch 878 +2025-10-30 20:14:57.345059: Current learning rate: 0.00151 +2025-10-30 20:15:17.619138: train_loss -0.9935 +2025-10-30 20:15:17.624106: val_loss -0.893 +2025-10-30 20:15:17.625958: Pseudo dice [np.float32(0.9841), np.float32(0.991), np.float32(0.9948), np.float32(0.8053)] +2025-10-30 20:15:17.627837: Epoch time: 20.28 s +2025-10-30 20:15:18.821023: +2025-10-30 20:15:18.822932: Epoch 879 +2025-10-30 20:15:18.826861: Current learning rate: 0.00149 +2025-10-30 20:15:38.337381: train_loss -0.9937 +2025-10-30 20:15:38.340811: val_loss -0.9062 +2025-10-30 20:15:38.342696: Pseudo dice [np.float32(0.9848), np.float32(0.9922), np.float32(0.9956), np.float32(0.8303)] +2025-10-30 20:15:38.344490: Epoch time: 19.52 s +2025-10-30 20:15:39.430969: +2025-10-30 20:15:39.434280: Epoch 880 +2025-10-30 20:15:39.437772: Current learning rate: 0.00148 +2025-10-30 20:16:00.502891: train_loss -0.9938 +2025-10-30 20:16:00.505300: val_loss -0.9042 +2025-10-30 20:16:00.506781: Pseudo dice [np.float32(0.9852), np.float32(0.9914), np.float32(0.9951), np.float32(0.8325)] +2025-10-30 20:16:00.511299: Epoch time: 21.07 s +2025-10-30 20:16:02.534012: +2025-10-30 20:16:02.537478: Epoch 881 +2025-10-30 20:16:02.539515: Current learning rate: 0.00147 +2025-10-30 20:16:23.652891: train_loss -0.9937 +2025-10-30 20:16:23.658745: val_loss -0.9047 +2025-10-30 20:16:23.660441: Pseudo dice [np.float32(0.985), np.float32(0.9917), np.float32(0.9956), np.float32(0.8298)] +2025-10-30 20:16:23.662120: Epoch time: 21.12 s +2025-10-30 20:16:24.836969: +2025-10-30 20:16:24.838706: Epoch 882 +2025-10-30 20:16:24.840485: Current learning rate: 0.00146 +2025-10-30 20:16:45.885003: train_loss -0.9938 +2025-10-30 20:16:45.890464: val_loss -0.9035 +2025-10-30 20:16:45.892385: Pseudo dice [np.float32(0.9839), np.float32(0.992), np.float32(0.9958), np.float32(0.8322)] +2025-10-30 20:16:45.894332: Epoch time: 21.05 s +2025-10-30 20:16:47.079247: +2025-10-30 20:16:47.084467: Epoch 883 +2025-10-30 20:16:47.086261: Current learning rate: 0.00145 +2025-10-30 20:17:07.675256: train_loss -0.9935 +2025-10-30 20:17:07.677840: val_loss -0.9002 +2025-10-30 20:17:07.679914: Pseudo dice [np.float32(0.9838), np.float32(0.9921), np.float32(0.9953), np.float32(0.8197)] +2025-10-30 20:17:07.681951: Epoch time: 20.6 s +2025-10-30 20:17:08.776864: +2025-10-30 20:17:08.779073: Epoch 884 +2025-10-30 20:17:08.780899: Current learning rate: 0.00144 +2025-10-30 20:17:29.123873: train_loss -0.9938 +2025-10-30 20:17:29.126337: val_loss -0.8936 +2025-10-30 20:17:29.128059: Pseudo dice [np.float32(0.9828), np.float32(0.9909), np.float32(0.9954), np.float32(0.812)] +2025-10-30 20:17:29.129718: Epoch time: 20.35 s +2025-10-30 20:17:30.341541: +2025-10-30 20:17:30.343536: Epoch 885 +2025-10-30 20:17:30.345286: Current learning rate: 0.00143 +2025-10-30 20:17:50.164790: train_loss -0.9939 +2025-10-30 20:17:50.168002: val_loss -0.8973 +2025-10-30 20:17:50.169832: Pseudo dice [np.float32(0.9853), np.float32(0.9918), np.float32(0.995), np.float32(0.8106)] +2025-10-30 20:17:50.171630: Epoch time: 19.82 s +2025-10-30 20:17:51.299294: +2025-10-30 20:17:51.301209: Epoch 886 +2025-10-30 20:17:51.302907: Current learning rate: 0.00142 +2025-10-30 20:18:12.275776: train_loss -0.9937 +2025-10-30 20:18:12.279847: val_loss -0.8973 +2025-10-30 20:18:12.284332: Pseudo dice [np.float32(0.9831), np.float32(0.9905), np.float32(0.9952), np.float32(0.8243)] +2025-10-30 20:18:12.286332: Epoch time: 20.98 s +2025-10-30 20:18:13.550307: +2025-10-30 20:18:13.552478: Epoch 887 +2025-10-30 20:18:13.553905: Current learning rate: 0.00141 +2025-10-30 20:18:34.420496: train_loss -0.9939 +2025-10-30 20:18:34.423402: val_loss -0.8981 +2025-10-30 20:18:34.425166: Pseudo dice [np.float32(0.9855), np.float32(0.9917), np.float32(0.9951), np.float32(0.8187)] +2025-10-30 20:18:34.427379: Epoch time: 20.87 s +2025-10-30 20:18:35.617472: +2025-10-30 20:18:35.619256: Epoch 888 +2025-10-30 20:18:35.620876: Current learning rate: 0.00139 +2025-10-30 20:18:56.680628: train_loss -0.9941 +2025-10-30 20:18:56.683744: val_loss -0.8969 +2025-10-30 20:18:56.686109: Pseudo dice [np.float32(0.9855), np.float32(0.9919), np.float32(0.9952), np.float32(0.8141)] +2025-10-30 20:18:56.687642: Epoch time: 21.06 s +2025-10-30 20:18:57.920466: +2025-10-30 20:18:57.923044: Epoch 889 +2025-10-30 20:18:57.925041: Current learning rate: 0.00138 +2025-10-30 20:19:18.874952: train_loss -0.9934 +2025-10-30 20:19:18.877308: val_loss -0.8979 +2025-10-30 20:19:18.878808: Pseudo dice [np.float32(0.9832), np.float32(0.99), np.float32(0.9952), np.float32(0.8167)] +2025-10-30 20:19:18.880852: Epoch time: 20.96 s +2025-10-30 20:19:20.217987: +2025-10-30 20:19:20.220014: Epoch 890 +2025-10-30 20:19:20.221555: Current learning rate: 0.00137 +2025-10-30 20:19:50.046352: train_loss -0.9937 +2025-10-30 20:19:50.049842: val_loss -0.8969 +2025-10-30 20:19:50.054907: Pseudo dice [np.float32(0.9845), np.float32(0.9917), np.float32(0.9951), np.float32(0.8165)] +2025-10-30 20:19:50.056785: Epoch time: 29.83 s +2025-10-30 20:19:51.316412: +2025-10-30 20:19:51.322702: Epoch 891 +2025-10-30 20:19:51.325184: Current learning rate: 0.00136 +2025-10-30 20:20:09.563961: train_loss -0.9941 +2025-10-30 20:20:09.570955: val_loss -0.8981 +2025-10-30 20:20:09.573072: Pseudo dice [np.float32(0.9845), np.float32(0.9911), np.float32(0.9953), np.float32(0.8233)] +2025-10-30 20:20:09.575434: Epoch time: 18.25 s +2025-10-30 20:20:10.836403: +2025-10-30 20:20:10.841693: Epoch 892 +2025-10-30 20:20:10.843611: Current learning rate: 0.00135 +2025-10-30 20:20:31.644195: train_loss -0.9938 +2025-10-30 20:20:31.648997: val_loss -0.9004 +2025-10-30 20:20:31.652540: Pseudo dice [np.float32(0.9846), np.float32(0.9914), np.float32(0.995), np.float32(0.8235)] +2025-10-30 20:20:31.658758: Epoch time: 20.81 s +2025-10-30 20:20:32.781802: +2025-10-30 20:20:32.784778: Epoch 893 +2025-10-30 20:20:32.786579: Current learning rate: 0.00134 +2025-10-30 20:20:54.161714: train_loss -0.9936 +2025-10-30 20:20:54.166129: val_loss -0.8928 +2025-10-30 20:20:54.172485: Pseudo dice [np.float32(0.9842), np.float32(0.9917), np.float32(0.995), np.float32(0.8103)] +2025-10-30 20:20:54.174695: Epoch time: 21.38 s +2025-10-30 20:20:56.034214: +2025-10-30 20:20:56.036368: Epoch 894 +2025-10-30 20:20:56.039151: Current learning rate: 0.00133 +2025-10-30 20:21:17.298334: train_loss -0.9941 +2025-10-30 20:21:17.302008: val_loss -0.9066 +2025-10-30 20:21:17.307749: Pseudo dice [np.float32(0.985), np.float32(0.9924), np.float32(0.9954), np.float32(0.8358)] +2025-10-30 20:21:17.309911: Epoch time: 21.27 s +2025-10-30 20:21:18.390883: +2025-10-30 20:21:18.393462: Epoch 895 +2025-10-30 20:21:18.395529: Current learning rate: 0.00132 +2025-10-30 20:21:39.291712: train_loss -0.9937 +2025-10-30 20:21:39.295845: val_loss -0.8967 +2025-10-30 20:21:39.298341: Pseudo dice [np.float32(0.9836), np.float32(0.991), np.float32(0.9952), np.float32(0.8245)] +2025-10-30 20:21:39.304510: Epoch time: 20.9 s +2025-10-30 20:21:40.724674: +2025-10-30 20:21:40.735080: Epoch 896 +2025-10-30 20:21:40.737327: Current learning rate: 0.0013 +2025-10-30 20:22:01.357160: train_loss -0.9937 +2025-10-30 20:22:01.359459: val_loss -0.9079 +2025-10-30 20:22:01.364829: Pseudo dice [np.float32(0.9848), np.float32(0.9915), np.float32(0.9953), np.float32(0.8392)] +2025-10-30 20:22:01.366333: Epoch time: 20.64 s +2025-10-30 20:22:02.485526: +2025-10-30 20:22:02.488064: Epoch 897 +2025-10-30 20:22:02.491078: Current learning rate: 0.00129 +2025-10-30 20:22:22.512053: train_loss -0.9937 +2025-10-30 20:22:22.526898: val_loss -0.9062 +2025-10-30 20:22:22.532960: Pseudo dice [np.float32(0.9844), np.float32(0.9915), np.float32(0.9955), np.float32(0.8345)] +2025-10-30 20:22:22.539643: Epoch time: 20.03 s +2025-10-30 20:22:23.573387: +2025-10-30 20:22:23.575334: Epoch 898 +2025-10-30 20:22:23.577595: Current learning rate: 0.00128 +2025-10-30 20:22:43.066964: train_loss -0.9939 +2025-10-30 20:22:44.604245: val_loss -0.9042 +2025-10-30 20:22:44.611260: Pseudo dice [np.float32(0.9854), np.float32(0.9916), np.float32(0.9953), np.float32(0.8332)] +2025-10-30 20:22:44.613910: Epoch time: 19.5 s +2025-10-30 20:22:45.752256: +2025-10-30 20:22:45.757755: Epoch 899 +2025-10-30 20:22:45.763573: Current learning rate: 0.00127 +2025-10-30 20:23:06.307424: train_loss -0.9943 +2025-10-30 20:23:06.322129: val_loss -0.9017 +2025-10-30 20:23:06.328501: Pseudo dice [np.float32(0.9841), np.float32(0.9916), np.float32(0.9954), np.float32(0.8269)] +2025-10-30 20:23:06.330559: Epoch time: 20.56 s +2025-10-30 20:23:09.548657: +2025-10-30 20:23:09.550987: Epoch 900 +2025-10-30 20:23:09.552836: Current learning rate: 0.00126 +2025-10-30 20:23:28.938263: train_loss -0.994 +2025-10-30 20:23:28.956448: val_loss -0.8998 +2025-10-30 20:23:28.964787: Pseudo dice [np.float32(0.9846), np.float32(0.9915), np.float32(0.9951), np.float32(0.8213)] +2025-10-30 20:23:28.976802: Epoch time: 19.39 s +2025-10-30 20:23:30.209173: +2025-10-30 20:23:30.213283: Epoch 901 +2025-10-30 20:23:30.216705: Current learning rate: 0.00125 +2025-10-30 20:23:50.239035: train_loss -0.994 +2025-10-30 20:23:50.241920: val_loss -0.8998 +2025-10-30 20:23:50.247965: Pseudo dice [np.float32(0.9837), np.float32(0.9905), np.float32(0.9951), np.float32(0.8244)] +2025-10-30 20:23:50.253548: Epoch time: 20.03 s +2025-10-30 20:23:51.289865: +2025-10-30 20:23:51.291825: Epoch 902 +2025-10-30 20:23:51.297232: Current learning rate: 0.00124 +2025-10-30 20:24:14.525887: train_loss -0.9939 +2025-10-30 20:24:14.535298: val_loss -0.8986 +2025-10-30 20:24:14.541250: Pseudo dice [np.float32(0.9851), np.float32(0.9919), np.float32(0.9952), np.float32(0.8146)] +2025-10-30 20:24:14.542899: Epoch time: 23.24 s +2025-10-30 20:24:15.849203: +2025-10-30 20:24:15.854367: Epoch 903 +2025-10-30 20:24:15.856326: Current learning rate: 0.00122 +2025-10-30 20:24:36.272573: train_loss -0.9935 +2025-10-30 20:24:36.281746: val_loss -0.9042 +2025-10-30 20:24:36.283441: Pseudo dice [np.float32(0.9841), np.float32(0.9915), np.float32(0.9955), np.float32(0.8253)] +2025-10-30 20:24:36.285528: Epoch time: 20.43 s +2025-10-30 20:24:37.590479: +2025-10-30 20:24:37.596874: Epoch 904 +2025-10-30 20:24:37.598835: Current learning rate: 0.00121 +2025-10-30 20:24:55.695621: train_loss -0.9934 +2025-10-30 20:24:55.708376: val_loss -0.8966 +2025-10-30 20:24:55.710423: Pseudo dice [np.float32(0.984), np.float32(0.9917), np.float32(0.9949), np.float32(0.8146)] +2025-10-30 20:24:55.712632: Epoch time: 18.11 s +2025-10-30 20:24:56.983740: +2025-10-30 20:24:56.992002: Epoch 905 +2025-10-30 20:24:56.994133: Current learning rate: 0.0012 +2025-10-30 20:25:19.350672: train_loss -0.9944 +2025-10-30 20:25:19.355972: val_loss -0.9061 +2025-10-30 20:25:19.357763: Pseudo dice [np.float32(0.9843), np.float32(0.9923), np.float32(0.9955), np.float32(0.8306)] +2025-10-30 20:25:19.359524: Epoch time: 22.37 s +2025-10-30 20:25:20.396846: +2025-10-30 20:25:20.402490: Epoch 906 +2025-10-30 20:25:20.404444: Current learning rate: 0.00119 +2025-10-30 20:25:41.105467: train_loss -0.994 +2025-10-30 20:25:41.113103: val_loss -0.9041 +2025-10-30 20:25:41.115486: Pseudo dice [np.float32(0.9832), np.float32(0.9918), np.float32(0.9957), np.float32(0.8322)] +2025-10-30 20:25:41.117331: Epoch time: 20.71 s +2025-10-30 20:25:43.012278: +2025-10-30 20:25:43.014671: Epoch 907 +2025-10-30 20:25:43.020953: Current learning rate: 0.00118 +2025-10-30 20:26:04.048247: train_loss -0.9938 +2025-10-30 20:26:04.064450: val_loss -0.9012 +2025-10-30 20:26:04.066681: Pseudo dice [np.float32(0.9839), np.float32(0.9919), np.float32(0.9955), np.float32(0.8223)] +2025-10-30 20:26:04.068474: Epoch time: 21.04 s +2025-10-30 20:26:05.299674: +2025-10-30 20:26:05.302452: Epoch 908 +2025-10-30 20:26:05.307468: Current learning rate: 0.00117 +2025-10-30 20:26:25.653449: train_loss -0.994 +2025-10-30 20:26:25.658974: val_loss -0.9017 +2025-10-30 20:26:25.661332: Pseudo dice [np.float32(0.9849), np.float32(0.9922), np.float32(0.9953), np.float32(0.8233)] +2025-10-30 20:26:25.663766: Epoch time: 20.36 s +2025-10-30 20:26:26.687222: +2025-10-30 20:26:26.689133: Epoch 909 +2025-10-30 20:26:26.693990: Current learning rate: 0.00116 +2025-10-30 20:26:47.252795: train_loss -0.9936 +2025-10-30 20:26:47.260848: val_loss -0.8915 +2025-10-30 20:26:47.262648: Pseudo dice [np.float32(0.9836), np.float32(0.9914), np.float32(0.9951), np.float32(0.805)] +2025-10-30 20:26:47.267972: Epoch time: 20.57 s +2025-10-30 20:26:48.344991: +2025-10-30 20:26:48.347230: Epoch 910 +2025-10-30 20:26:48.349640: Current learning rate: 0.00115 +2025-10-30 20:27:07.937261: train_loss -0.9938 +2025-10-30 20:27:07.949041: val_loss -0.8981 +2025-10-30 20:27:07.950900: Pseudo dice [np.float32(0.9849), np.float32(0.9915), np.float32(0.9952), np.float32(0.8195)] +2025-10-30 20:27:07.952476: Epoch time: 19.59 s +2025-10-30 20:27:09.171423: +2025-10-30 20:27:09.173361: Epoch 911 +2025-10-30 20:27:09.175188: Current learning rate: 0.00113 +2025-10-30 20:27:29.552063: train_loss -0.9939 +2025-10-30 20:27:29.566780: val_loss -0.8992 +2025-10-30 20:27:29.569111: Pseudo dice [np.float32(0.9849), np.float32(0.9921), np.float32(0.995), np.float32(0.8144)] +2025-10-30 20:27:29.574271: Epoch time: 20.38 s +2025-10-30 20:27:30.598384: +2025-10-30 20:27:30.600175: Epoch 912 +2025-10-30 20:27:30.602156: Current learning rate: 0.00112 +2025-10-30 20:27:50.909038: train_loss -0.9944 +2025-10-30 20:27:50.912003: val_loss -0.8975 +2025-10-30 20:27:50.913638: Pseudo dice [np.float32(0.9844), np.float32(0.9917), np.float32(0.9952), np.float32(0.813)] +2025-10-30 20:27:50.915315: Epoch time: 20.31 s +2025-10-30 20:27:51.975394: +2025-10-30 20:27:51.977637: Epoch 913 +2025-10-30 20:27:51.980274: Current learning rate: 0.00111 +2025-10-30 20:28:15.243509: train_loss -0.9948 +2025-10-30 20:28:15.253370: val_loss -0.903 +2025-10-30 20:28:15.255020: Pseudo dice [np.float32(0.9838), np.float32(0.9914), np.float32(0.9953), np.float32(0.83)] +2025-10-30 20:28:15.256561: Epoch time: 23.27 s +2025-10-30 20:28:16.313601: +2025-10-30 20:28:16.315517: Epoch 914 +2025-10-30 20:28:16.317137: Current learning rate: 0.0011 +2025-10-30 20:28:36.692955: train_loss -0.994 +2025-10-30 20:28:36.696387: val_loss -0.902 +2025-10-30 20:28:36.698935: Pseudo dice [np.float32(0.9838), np.float32(0.9914), np.float32(0.9954), np.float32(0.8255)] +2025-10-30 20:28:36.700563: Epoch time: 20.38 s +2025-10-30 20:28:37.906840: +2025-10-30 20:28:37.909011: Epoch 915 +2025-10-30 20:28:37.910713: Current learning rate: 0.00109 +2025-10-30 20:28:58.406465: train_loss -0.9941 +2025-10-30 20:28:58.417860: val_loss -0.8988 +2025-10-30 20:28:58.419572: Pseudo dice [np.float32(0.9839), np.float32(0.9911), np.float32(0.9951), np.float32(0.8211)] +2025-10-30 20:28:58.421361: Epoch time: 20.5 s +2025-10-30 20:28:59.515393: +2025-10-30 20:28:59.517246: Epoch 916 +2025-10-30 20:28:59.518868: Current learning rate: 0.00108 +2025-10-30 20:29:19.503309: train_loss -0.9944 +2025-10-30 20:29:19.505790: val_loss -0.9012 +2025-10-30 20:29:19.508361: Pseudo dice [np.float32(0.9834), np.float32(0.9913), np.float32(0.9955), np.float32(0.828)] +2025-10-30 20:29:19.510328: Epoch time: 19.99 s +2025-10-30 20:29:20.748919: +2025-10-30 20:29:20.751028: Epoch 917 +2025-10-30 20:29:20.752789: Current learning rate: 0.00106 +2025-10-30 20:29:40.052396: train_loss -0.9943 +2025-10-30 20:29:40.054774: val_loss -0.9024 +2025-10-30 20:29:40.056393: Pseudo dice [np.float32(0.985), np.float32(0.9915), np.float32(0.9954), np.float32(0.8228)] +2025-10-30 20:29:40.058011: Epoch time: 19.3 s +2025-10-30 20:29:41.285268: +2025-10-30 20:29:41.289128: Epoch 918 +2025-10-30 20:29:41.291260: Current learning rate: 0.00105 +2025-10-30 20:30:01.922353: train_loss -0.9948 +2025-10-30 20:30:01.925416: val_loss -0.9034 +2025-10-30 20:30:01.927786: Pseudo dice [np.float32(0.9845), np.float32(0.9914), np.float32(0.9955), np.float32(0.8296)] +2025-10-30 20:30:01.930253: Epoch time: 20.64 s +2025-10-30 20:30:03.552268: +2025-10-30 20:30:03.554193: Epoch 919 +2025-10-30 20:30:03.556375: Current learning rate: 0.00104 +2025-10-30 20:30:24.072234: train_loss -0.9943 +2025-10-30 20:30:24.074748: val_loss -0.9022 +2025-10-30 20:30:24.076457: Pseudo dice [np.float32(0.9842), np.float32(0.9916), np.float32(0.9955), np.float32(0.8327)] +2025-10-30 20:30:24.078135: Epoch time: 20.52 s +2025-10-30 20:30:25.173685: +2025-10-30 20:30:25.176921: Epoch 920 +2025-10-30 20:30:25.180104: Current learning rate: 0.00103 +2025-10-30 20:30:45.868785: train_loss -0.994 +2025-10-30 20:30:45.871013: val_loss -0.8968 +2025-10-30 20:30:45.872362: Pseudo dice [np.float32(0.9837), np.float32(0.9906), np.float32(0.995), np.float32(0.8218)] +2025-10-30 20:30:45.873625: Epoch time: 20.7 s +2025-10-30 20:30:47.128383: +2025-10-30 20:30:47.130389: Epoch 921 +2025-10-30 20:30:47.131973: Current learning rate: 0.00102 +2025-10-30 20:31:07.627169: train_loss -0.9939 +2025-10-30 20:31:07.630250: val_loss -0.9024 +2025-10-30 20:31:07.631850: Pseudo dice [np.float32(0.985), np.float32(0.9922), np.float32(0.9952), np.float32(0.8248)] +2025-10-30 20:31:07.633657: Epoch time: 20.5 s +2025-10-30 20:31:08.656753: +2025-10-30 20:31:08.658900: Epoch 922 +2025-10-30 20:31:08.660660: Current learning rate: 0.00101 +2025-10-30 20:31:28.175164: train_loss -0.9945 +2025-10-30 20:31:28.177497: val_loss -0.9014 +2025-10-30 20:31:28.179079: Pseudo dice [np.float32(0.9835), np.float32(0.9911), np.float32(0.9954), np.float32(0.8281)] +2025-10-30 20:31:28.180781: Epoch time: 19.52 s +2025-10-30 20:31:29.197484: +2025-10-30 20:31:29.199723: Epoch 923 +2025-10-30 20:31:29.201354: Current learning rate: 0.001 +2025-10-30 20:31:49.796303: train_loss -0.9942 +2025-10-30 20:31:49.798826: val_loss -0.9021 +2025-10-30 20:31:49.800709: Pseudo dice [np.float32(0.9838), np.float32(0.991), np.float32(0.9952), np.float32(0.8327)] +2025-10-30 20:31:49.802807: Epoch time: 20.6 s +2025-10-30 20:31:50.846705: +2025-10-30 20:31:50.848619: Epoch 924 +2025-10-30 20:31:50.850161: Current learning rate: 0.00098 +2025-10-30 20:32:10.339553: train_loss -0.9944 +2025-10-30 20:32:10.342918: val_loss -0.9045 +2025-10-30 20:32:10.346006: Pseudo dice [np.float32(0.9839), np.float32(0.9908), np.float32(0.9955), np.float32(0.835)] +2025-10-30 20:32:10.349001: Epoch time: 19.49 s +2025-10-30 20:32:11.588461: +2025-10-30 20:32:11.591460: Epoch 925 +2025-10-30 20:32:11.593745: Current learning rate: 0.00097 +2025-10-30 20:32:32.037538: train_loss -0.9945 +2025-10-30 20:32:32.040518: val_loss -0.9009 +2025-10-30 20:32:32.042431: Pseudo dice [np.float32(0.9838), np.float32(0.9912), np.float32(0.9954), np.float32(0.8282)] +2025-10-30 20:32:32.045379: Epoch time: 20.45 s +2025-10-30 20:32:33.238876: +2025-10-30 20:32:33.240850: Epoch 926 +2025-10-30 20:32:33.242834: Current learning rate: 0.00096 +2025-10-30 20:32:53.727376: train_loss -0.9944 +2025-10-30 20:32:53.729747: val_loss -0.9 +2025-10-30 20:32:53.732174: Pseudo dice [np.float32(0.9838), np.float32(0.9911), np.float32(0.9953), np.float32(0.8237)] +2025-10-30 20:32:53.734469: Epoch time: 20.49 s +2025-10-30 20:32:54.899971: +2025-10-30 20:32:54.902252: Epoch 927 +2025-10-30 20:32:54.904244: Current learning rate: 0.00095 +2025-10-30 20:33:15.465429: train_loss -0.9941 +2025-10-30 20:33:15.469124: val_loss -0.893 +2025-10-30 20:33:15.470763: Pseudo dice [np.float32(0.9834), np.float32(0.9909), np.float32(0.9951), np.float32(0.808)] +2025-10-30 20:33:15.472369: Epoch time: 20.57 s +2025-10-30 20:33:16.697896: +2025-10-30 20:33:16.700119: Epoch 928 +2025-10-30 20:33:16.702176: Current learning rate: 0.00094 +2025-10-30 20:33:37.271350: train_loss -0.9947 +2025-10-30 20:33:37.282696: val_loss -0.8978 +2025-10-30 20:33:37.284945: Pseudo dice [np.float32(0.9842), np.float32(0.9909), np.float32(0.9953), np.float32(0.8186)] +2025-10-30 20:33:37.286852: Epoch time: 20.58 s +2025-10-30 20:33:38.508629: +2025-10-30 20:33:38.510926: Epoch 929 +2025-10-30 20:33:38.513052: Current learning rate: 0.00092 +2025-10-30 20:33:57.528031: train_loss -0.9945 +2025-10-30 20:33:57.530447: val_loss -0.9007 +2025-10-30 20:33:57.532680: Pseudo dice [np.float32(0.9845), np.float32(0.9916), np.float32(0.9953), np.float32(0.8259)] +2025-10-30 20:33:57.534694: Epoch time: 19.02 s +2025-10-30 20:33:58.613625: +2025-10-30 20:33:58.615656: Epoch 930 +2025-10-30 20:33:58.617477: Current learning rate: 0.00091 +2025-10-30 20:34:19.092521: train_loss -0.9939 +2025-10-30 20:34:19.095892: val_loss -0.9025 +2025-10-30 20:34:19.097678: Pseudo dice [np.float32(0.9843), np.float32(0.9916), np.float32(0.9955), np.float32(0.829)] +2025-10-30 20:34:19.099996: Epoch time: 20.48 s +2025-10-30 20:34:20.274446: +2025-10-30 20:34:20.278892: Epoch 931 +2025-10-30 20:34:20.281360: Current learning rate: 0.0009 +2025-10-30 20:34:39.967113: train_loss -0.995 +2025-10-30 20:34:39.978656: val_loss -0.8985 +2025-10-30 20:34:39.980757: Pseudo dice [np.float32(0.9835), np.float32(0.9914), np.float32(0.9953), np.float32(0.8216)] +2025-10-30 20:34:39.982536: Epoch time: 19.69 s +2025-10-30 20:34:41.760480: +2025-10-30 20:34:41.762793: Epoch 932 +2025-10-30 20:34:41.764559: Current learning rate: 0.00089 +2025-10-30 20:35:02.288540: train_loss -0.9947 +2025-10-30 20:35:02.292390: val_loss -0.901 +2025-10-30 20:35:02.294356: Pseudo dice [np.float32(0.9838), np.float32(0.9915), np.float32(0.9954), np.float32(0.8238)] +2025-10-30 20:35:02.296136: Epoch time: 20.53 s +2025-10-30 20:35:03.383221: +2025-10-30 20:35:03.385582: Epoch 933 +2025-10-30 20:35:03.387670: Current learning rate: 0.00088 +2025-10-30 20:35:23.808589: train_loss -0.9942 +2025-10-30 20:35:23.816406: val_loss -0.9055 +2025-10-30 20:35:23.819216: Pseudo dice [np.float32(0.9843), np.float32(0.9916), np.float32(0.9955), np.float32(0.8315)] +2025-10-30 20:35:23.820978: Epoch time: 20.43 s +2025-10-30 20:35:25.048886: +2025-10-30 20:35:25.051059: Epoch 934 +2025-10-30 20:35:25.052666: Current learning rate: 0.00087 +2025-10-30 20:35:45.338864: train_loss -0.9941 +2025-10-30 20:35:45.341267: val_loss -0.9042 +2025-10-30 20:35:45.347106: Pseudo dice [np.float32(0.9846), np.float32(0.9918), np.float32(0.9955), np.float32(0.827)] +2025-10-30 20:35:45.349956: Epoch time: 20.29 s +2025-10-30 20:35:46.391890: +2025-10-30 20:35:46.393690: Epoch 935 +2025-10-30 20:35:46.395413: Current learning rate: 0.00085 +2025-10-30 20:36:04.824173: train_loss -0.9944 +2025-10-30 20:36:04.829278: val_loss -0.8951 +2025-10-30 20:36:04.830863: Pseudo dice [np.float32(0.9827), np.float32(0.9908), np.float32(0.9951), np.float32(0.8185)] +2025-10-30 20:36:04.832504: Epoch time: 18.43 s +2025-10-30 20:36:05.941636: +2025-10-30 20:36:05.945074: Epoch 936 +2025-10-30 20:36:05.948309: Current learning rate: 0.00084 +2025-10-30 20:36:26.367313: train_loss -0.9942 +2025-10-30 20:36:26.370518: val_loss -0.9005 +2025-10-30 20:36:26.372247: Pseudo dice [np.float32(0.9839), np.float32(0.9912), np.float32(0.9954), np.float32(0.8255)] +2025-10-30 20:36:26.373868: Epoch time: 20.43 s +2025-10-30 20:36:27.648092: +2025-10-30 20:36:27.650634: Epoch 937 +2025-10-30 20:36:27.653645: Current learning rate: 0.00083 +2025-10-30 20:36:47.977482: train_loss -0.9942 +2025-10-30 20:36:47.980188: val_loss -0.8991 +2025-10-30 20:36:47.982805: Pseudo dice [np.float32(0.985), np.float32(0.992), np.float32(0.9954), np.float32(0.8177)] +2025-10-30 20:36:47.985389: Epoch time: 20.33 s +2025-10-30 20:36:49.050675: +2025-10-30 20:36:49.052639: Epoch 938 +2025-10-30 20:36:49.054247: Current learning rate: 0.00082 +2025-10-30 20:37:08.413537: train_loss -0.9952 +2025-10-30 20:37:08.416443: val_loss -0.8991 +2025-10-30 20:37:08.418831: Pseudo dice [np.float32(0.9843), np.float32(0.9918), np.float32(0.9955), np.float32(0.8213)] +2025-10-30 20:37:08.420584: Epoch time: 19.36 s +2025-10-30 20:37:09.411962: +2025-10-30 20:37:09.413890: Epoch 939 +2025-10-30 20:37:09.415734: Current learning rate: 0.00081 +2025-10-30 20:37:29.906176: train_loss -0.9943 +2025-10-30 20:37:29.908943: val_loss -0.9064 +2025-10-30 20:37:29.910700: Pseudo dice [np.float32(0.9843), np.float32(0.992), np.float32(0.9958), np.float32(0.8321)] +2025-10-30 20:37:29.912669: Epoch time: 20.5 s +2025-10-30 20:37:30.930491: +2025-10-30 20:37:30.932703: Epoch 940 +2025-10-30 20:37:30.934368: Current learning rate: 0.00079 +2025-10-30 20:37:51.437447: train_loss -0.9941 +2025-10-30 20:37:51.440232: val_loss -0.9032 +2025-10-30 20:37:51.442113: Pseudo dice [np.float32(0.9848), np.float32(0.9917), np.float32(0.9953), np.float32(0.8303)] +2025-10-30 20:37:51.444149: Epoch time: 20.51 s +2025-10-30 20:37:52.360520: +2025-10-30 20:37:52.362504: Epoch 941 +2025-10-30 20:37:52.364173: Current learning rate: 0.00078 +2025-10-30 20:38:12.844994: train_loss -0.9937 +2025-10-30 20:38:12.847528: val_loss -0.8962 +2025-10-30 20:38:12.849284: Pseudo dice [np.float32(0.9839), np.float32(0.991), np.float32(0.9953), np.float32(0.8197)] +2025-10-30 20:38:12.850964: Epoch time: 20.49 s +2025-10-30 20:38:13.899152: +2025-10-30 20:38:13.901044: Epoch 942 +2025-10-30 20:38:13.902856: Current learning rate: 0.00077 +2025-10-30 20:38:33.326386: train_loss -0.9945 +2025-10-30 20:38:33.329487: val_loss -0.8984 +2025-10-30 20:38:33.331597: Pseudo dice [np.float32(0.9851), np.float32(0.9917), np.float32(0.9953), np.float32(0.8169)] +2025-10-30 20:38:33.334080: Epoch time: 19.43 s +2025-10-30 20:38:34.380384: +2025-10-30 20:38:34.382577: Epoch 943 +2025-10-30 20:38:34.384231: Current learning rate: 0.00076 +2025-10-30 20:38:55.054782: train_loss -0.9944 +2025-10-30 20:38:55.057156: val_loss -0.8931 +2025-10-30 20:38:55.058664: Pseudo dice [np.float32(0.9846), np.float32(0.9913), np.float32(0.995), np.float32(0.8095)] +2025-10-30 20:38:55.060295: Epoch time: 20.68 s +2025-10-30 20:38:56.305659: +2025-10-30 20:38:56.308122: Epoch 944 +2025-10-30 20:38:56.309997: Current learning rate: 0.00075 +2025-10-30 20:39:16.874782: train_loss -0.9945 +2025-10-30 20:39:16.877162: val_loss -0.8955 +2025-10-30 20:39:16.878814: Pseudo dice [np.float32(0.9839), np.float32(0.9913), np.float32(0.9952), np.float32(0.8169)] +2025-10-30 20:39:16.880509: Epoch time: 20.57 s +2025-10-30 20:39:18.813514: +2025-10-30 20:39:18.815278: Epoch 945 +2025-10-30 20:39:18.816826: Current learning rate: 0.00074 +2025-10-30 20:39:39.159570: train_loss -0.9946 +2025-10-30 20:39:39.162795: val_loss -0.8981 +2025-10-30 20:39:39.165046: Pseudo dice [np.float32(0.9846), np.float32(0.9916), np.float32(0.9951), np.float32(0.8183)] +2025-10-30 20:39:39.167527: Epoch time: 20.35 s +2025-10-30 20:39:40.375200: +2025-10-30 20:39:40.377484: Epoch 946 +2025-10-30 20:39:40.379465: Current learning rate: 0.00072 +2025-10-30 20:40:00.896619: train_loss -0.995 +2025-10-30 20:40:00.900437: val_loss -0.8949 +2025-10-30 20:40:00.903986: Pseudo dice [np.float32(0.9848), np.float32(0.9914), np.float32(0.9949), np.float32(0.811)] +2025-10-30 20:40:00.908025: Epoch time: 20.52 s +2025-10-30 20:40:01.985174: +2025-10-30 20:40:01.986985: Epoch 947 +2025-10-30 20:40:01.988691: Current learning rate: 0.00071 +2025-10-30 20:40:22.879950: train_loss -0.9947 +2025-10-30 20:40:22.883082: val_loss -0.8969 +2025-10-30 20:40:22.885133: Pseudo dice [np.float32(0.9847), np.float32(0.9918), np.float32(0.9953), np.float32(0.8169)] +2025-10-30 20:40:22.886827: Epoch time: 20.9 s +2025-10-30 20:40:23.897685: +2025-10-30 20:40:23.900640: Epoch 948 +2025-10-30 20:40:23.902545: Current learning rate: 0.0007 +2025-10-30 20:40:43.186761: train_loss -0.9945 +2025-10-30 20:40:43.189505: val_loss -0.8898 +2025-10-30 20:40:43.190933: Pseudo dice [np.float32(0.9828), np.float32(0.991), np.float32(0.9948), np.float32(0.8107)] +2025-10-30 20:40:43.192397: Epoch time: 19.29 s +2025-10-30 20:40:44.272261: +2025-10-30 20:40:44.275188: Epoch 949 +2025-10-30 20:40:44.277011: Current learning rate: 0.00069 +2025-10-30 20:41:05.175839: train_loss -0.9944 +2025-10-30 20:41:05.179667: val_loss -0.8995 +2025-10-30 20:41:05.181874: Pseudo dice [np.float32(0.9848), np.float32(0.9918), np.float32(0.9954), np.float32(0.8204)] +2025-10-30 20:41:05.184290: Epoch time: 20.9 s +2025-10-30 20:41:07.818053: +2025-10-30 20:41:07.820063: Epoch 950 +2025-10-30 20:41:07.822258: Current learning rate: 0.00067 +2025-10-30 20:41:28.490761: train_loss -0.9944 +2025-10-30 20:41:28.493683: val_loss -0.8974 +2025-10-30 20:41:28.496138: Pseudo dice [np.float32(0.9842), np.float32(0.9914), np.float32(0.9954), np.float32(0.8184)] +2025-10-30 20:41:28.497939: Epoch time: 20.67 s +2025-10-30 20:41:29.673203: +2025-10-30 20:41:29.675460: Epoch 951 +2025-10-30 20:41:29.677271: Current learning rate: 0.00066 +2025-10-30 20:41:48.250862: train_loss -0.9946 +2025-10-30 20:41:48.254907: val_loss -0.8969 +2025-10-30 20:41:48.256795: Pseudo dice [np.float32(0.9844), np.float32(0.9918), np.float32(0.9952), np.float32(0.8159)] +2025-10-30 20:41:48.258705: Epoch time: 18.58 s +2025-10-30 20:41:49.462985: +2025-10-30 20:41:49.464832: Epoch 952 +2025-10-30 20:41:49.466514: Current learning rate: 0.00065 +2025-10-30 20:42:10.285788: train_loss -0.9946 +2025-10-30 20:42:10.287975: val_loss -0.8947 +2025-10-30 20:42:10.290779: Pseudo dice [np.float32(0.9849), np.float32(0.992), np.float32(0.995), np.float32(0.8124)] +2025-10-30 20:42:10.293218: Epoch time: 20.82 s +2025-10-30 20:42:11.568362: +2025-10-30 20:42:11.570084: Epoch 953 +2025-10-30 20:42:11.571622: Current learning rate: 0.00064 +2025-10-30 20:42:31.791929: train_loss -0.995 +2025-10-30 20:42:31.794849: val_loss -0.8922 +2025-10-30 20:42:31.796411: Pseudo dice [np.float32(0.9836), np.float32(0.9909), np.float32(0.995), np.float32(0.8097)] +2025-10-30 20:42:31.797949: Epoch time: 20.22 s +2025-10-30 20:42:33.008387: +2025-10-30 20:42:33.010649: Epoch 954 +2025-10-30 20:42:33.012817: Current learning rate: 0.00063 +2025-10-30 20:42:51.814930: train_loss -0.9944 +2025-10-30 20:42:51.817893: val_loss -0.9028 +2025-10-30 20:42:51.821695: Pseudo dice [np.float32(0.9847), np.float32(0.9921), np.float32(0.9955), np.float32(0.8304)] +2025-10-30 20:42:51.823981: Epoch time: 18.81 s +2025-10-30 20:42:52.904977: +2025-10-30 20:42:52.907053: Epoch 955 +2025-10-30 20:42:52.908914: Current learning rate: 0.00061 +2025-10-30 20:43:13.358092: train_loss -0.9951 +2025-10-30 20:43:13.360469: val_loss -0.8973 +2025-10-30 20:43:13.363164: Pseudo dice [np.float32(0.9851), np.float32(0.992), np.float32(0.9951), np.float32(0.8112)] +2025-10-30 20:43:13.365587: Epoch time: 20.45 s +2025-10-30 20:43:14.538568: +2025-10-30 20:43:14.540673: Epoch 956 +2025-10-30 20:43:14.542637: Current learning rate: 0.0006 +2025-10-30 20:43:35.075554: train_loss -0.9948 +2025-10-30 20:43:35.078360: val_loss -0.8956 +2025-10-30 20:43:35.080287: Pseudo dice [np.float32(0.9849), np.float32(0.9919), np.float32(0.995), np.float32(0.8168)] +2025-10-30 20:43:35.082079: Epoch time: 20.54 s +2025-10-30 20:43:36.199387: +2025-10-30 20:43:36.201096: Epoch 957 +2025-10-30 20:43:36.202653: Current learning rate: 0.00059 +2025-10-30 20:43:56.823647: train_loss -0.9951 +2025-10-30 20:43:56.827247: val_loss -0.8978 +2025-10-30 20:43:56.829490: Pseudo dice [np.float32(0.9832), np.float32(0.9909), np.float32(0.9955), np.float32(0.8235)] +2025-10-30 20:43:56.832494: Epoch time: 20.63 s +2025-10-30 20:43:58.700621: +2025-10-30 20:43:58.702531: Epoch 958 +2025-10-30 20:43:58.704291: Current learning rate: 0.00058 +2025-10-30 20:44:17.697390: train_loss -0.9951 +2025-10-30 20:44:17.700022: val_loss -0.9002 +2025-10-30 20:44:17.702933: Pseudo dice [np.float32(0.9845), np.float32(0.9915), np.float32(0.9953), np.float32(0.8274)] +2025-10-30 20:44:17.704962: Epoch time: 19.0 s +2025-10-30 20:44:18.918214: +2025-10-30 20:44:18.920634: Epoch 959 +2025-10-30 20:44:18.922840: Current learning rate: 0.00056 +2025-10-30 20:44:39.172571: train_loss -0.9953 +2025-10-30 20:44:39.175255: val_loss -0.899 +2025-10-30 20:44:39.177220: Pseudo dice [np.float32(0.9837), np.float32(0.9909), np.float32(0.9955), np.float32(0.8246)] +2025-10-30 20:44:39.178884: Epoch time: 20.26 s +2025-10-30 20:44:40.204934: +2025-10-30 20:44:40.209544: Epoch 960 +2025-10-30 20:44:40.212786: Current learning rate: 0.00055 +2025-10-30 20:45:00.381812: train_loss -0.9949 +2025-10-30 20:45:00.390841: val_loss -0.8964 +2025-10-30 20:45:00.392507: Pseudo dice [np.float32(0.9838), np.float32(0.9912), np.float32(0.9952), np.float32(0.8181)] +2025-10-30 20:45:00.394465: Epoch time: 20.18 s +2025-10-30 20:45:01.682074: +2025-10-30 20:45:01.688842: Epoch 961 +2025-10-30 20:45:01.690564: Current learning rate: 0.00054 +2025-10-30 20:45:20.909558: train_loss -0.9949 +2025-10-30 20:45:20.911770: val_loss -0.8977 +2025-10-30 20:45:20.913388: Pseudo dice [np.float32(0.9841), np.float32(0.9917), np.float32(0.9952), np.float32(0.8233)] +2025-10-30 20:45:20.914955: Epoch time: 19.23 s +2025-10-30 20:45:22.291898: +2025-10-30 20:45:22.294521: Epoch 962 +2025-10-30 20:45:22.296631: Current learning rate: 0.00053 +2025-10-30 20:45:42.549469: train_loss -0.9949 +2025-10-30 20:45:42.551448: val_loss -0.9091 +2025-10-30 20:45:42.553196: Pseudo dice [np.float32(0.9848), np.float32(0.9919), np.float32(0.9957), np.float32(0.8429)] +2025-10-30 20:45:42.554759: Epoch time: 20.26 s +2025-10-30 20:45:43.651390: +2025-10-30 20:45:43.652987: Epoch 963 +2025-10-30 20:45:43.654561: Current learning rate: 0.00051 +2025-10-30 20:46:04.069906: train_loss -0.9946 +2025-10-30 20:46:04.073344: val_loss -0.9037 +2025-10-30 20:46:04.075624: Pseudo dice [np.float32(0.9851), np.float32(0.9916), np.float32(0.9954), np.float32(0.8344)] +2025-10-30 20:46:04.077401: Epoch time: 20.42 s +2025-10-30 20:46:05.322037: +2025-10-30 20:46:05.326484: Epoch 964 +2025-10-30 20:46:05.328376: Current learning rate: 0.0005 +2025-10-30 20:46:25.732363: train_loss -0.9946 +2025-10-30 20:46:25.734874: val_loss -0.8988 +2025-10-30 20:46:25.737011: Pseudo dice [np.float32(0.9852), np.float32(0.9913), np.float32(0.9952), np.float32(0.8167)] +2025-10-30 20:46:25.739137: Epoch time: 20.41 s +2025-10-30 20:46:26.779235: +2025-10-30 20:46:26.781790: Epoch 965 +2025-10-30 20:46:26.784173: Current learning rate: 0.00049 +2025-10-30 20:46:46.592938: train_loss -0.995 +2025-10-30 20:46:46.595694: val_loss -0.906 +2025-10-30 20:46:46.597630: Pseudo dice [np.float32(0.9859), np.float32(0.9927), np.float32(0.9955), np.float32(0.8282)] +2025-10-30 20:46:46.599735: Epoch time: 19.82 s +2025-10-30 20:46:47.888250: +2025-10-30 20:46:47.890218: Epoch 966 +2025-10-30 20:46:47.892848: Current learning rate: 0.00048 +2025-10-30 20:47:08.183067: train_loss -0.9945 +2025-10-30 20:47:08.187532: val_loss -0.8974 +2025-10-30 20:47:08.190156: Pseudo dice [np.float32(0.984), np.float32(0.9916), np.float32(0.9952), np.float32(0.8217)] +2025-10-30 20:47:08.193151: Epoch time: 20.3 s +2025-10-30 20:47:09.412997: +2025-10-30 20:47:09.415030: Epoch 967 +2025-10-30 20:47:09.419546: Current learning rate: 0.00046 +2025-10-30 20:47:28.884019: train_loss -0.9951 +2025-10-30 20:47:28.887285: val_loss -0.9057 +2025-10-30 20:47:28.889848: Pseudo dice [np.float32(0.9841), np.float32(0.9912), np.float32(0.9957), np.float32(0.8351)] +2025-10-30 20:47:28.891910: Epoch time: 19.47 s +2025-10-30 20:47:29.919361: +2025-10-30 20:47:29.923073: Epoch 968 +2025-10-30 20:47:29.927067: Current learning rate: 0.00045 +2025-10-30 20:47:50.236223: train_loss -0.995 +2025-10-30 20:47:50.238563: val_loss -0.903 +2025-10-30 20:47:50.240211: Pseudo dice [np.float32(0.9842), np.float32(0.9916), np.float32(0.9956), np.float32(0.8319)] +2025-10-30 20:47:50.241890: Epoch time: 20.32 s +2025-10-30 20:47:51.259356: +2025-10-30 20:47:51.261350: Epoch 969 +2025-10-30 20:47:51.263324: Current learning rate: 0.00044 +2025-10-30 20:48:11.459724: train_loss -0.995 +2025-10-30 20:48:11.465810: val_loss -0.901 +2025-10-30 20:48:11.467890: Pseudo dice [np.float32(0.9853), np.float32(0.9923), np.float32(0.9953), np.float32(0.8212)] +2025-10-30 20:48:11.469744: Epoch time: 20.2 s +2025-10-30 20:48:12.742875: +2025-10-30 20:48:12.744663: Epoch 970 +2025-10-30 20:48:12.746359: Current learning rate: 0.00043 +2025-10-30 20:48:33.544101: train_loss -0.9948 +2025-10-30 20:48:33.547230: val_loss -0.9014 +2025-10-30 20:48:33.549521: Pseudo dice [np.float32(0.984), np.float32(0.9912), np.float32(0.9954), np.float32(0.8283)] +2025-10-30 20:48:33.551594: Epoch time: 20.8 s +2025-10-30 20:48:34.761377: +2025-10-30 20:48:34.764087: Epoch 971 +2025-10-30 20:48:34.766024: Current learning rate: 0.00041 +2025-10-30 20:48:55.285923: train_loss -0.9944 +2025-10-30 20:48:55.288254: val_loss -0.8961 +2025-10-30 20:48:55.289838: Pseudo dice [np.float32(0.9849), np.float32(0.9917), np.float32(0.995), np.float32(0.8156)] +2025-10-30 20:48:55.291546: Epoch time: 20.53 s +2025-10-30 20:48:56.303664: +2025-10-30 20:48:56.305707: Epoch 972 +2025-10-30 20:48:56.308188: Current learning rate: 0.0004 +2025-10-30 20:49:15.929346: train_loss -0.9946 +2025-10-30 20:49:15.933152: val_loss -0.8933 +2025-10-30 20:49:15.935347: Pseudo dice [np.float32(0.985), np.float32(0.9914), np.float32(0.9947), np.float32(0.8104)] +2025-10-30 20:49:15.937610: Epoch time: 19.63 s +2025-10-30 20:49:16.966245: +2025-10-30 20:49:16.967985: Epoch 973 +2025-10-30 20:49:16.970206: Current learning rate: 0.00039 +2025-10-30 20:49:37.542676: train_loss -0.9952 +2025-10-30 20:49:37.545434: val_loss -0.8978 +2025-10-30 20:49:37.547285: Pseudo dice [np.float32(0.9847), np.float32(0.9918), np.float32(0.9952), np.float32(0.8183)] +2025-10-30 20:49:37.550113: Epoch time: 20.58 s +2025-10-30 20:49:38.814595: +2025-10-30 20:49:38.816597: Epoch 974 +2025-10-30 20:49:38.818332: Current learning rate: 0.00037 +2025-10-30 20:49:58.607266: train_loss -0.9949 +2025-10-30 20:49:58.610066: val_loss -0.8996 +2025-10-30 20:49:58.611962: Pseudo dice [np.float32(0.9843), np.float32(0.9907), np.float32(0.9952), np.float32(0.8248)] +2025-10-30 20:49:58.613597: Epoch time: 19.79 s +2025-10-30 20:49:59.685563: +2025-10-30 20:49:59.688658: Epoch 975 +2025-10-30 20:49:59.691275: Current learning rate: 0.00036 +2025-10-30 20:50:20.011486: train_loss -0.995 +2025-10-30 20:50:20.015372: val_loss -0.8991 +2025-10-30 20:50:20.017239: Pseudo dice [np.float32(0.9846), np.float32(0.9917), np.float32(0.9953), np.float32(0.8229)] +2025-10-30 20:50:20.019180: Epoch time: 20.33 s +2025-10-30 20:50:21.228516: +2025-10-30 20:50:21.232087: Epoch 976 +2025-10-30 20:50:21.234239: Current learning rate: 0.00035 +2025-10-30 20:50:41.791177: train_loss -0.9953 +2025-10-30 20:50:41.793734: val_loss -0.9011 +2025-10-30 20:50:41.795547: Pseudo dice [np.float32(0.985), np.float32(0.9917), np.float32(0.9953), np.float32(0.8241)] +2025-10-30 20:50:41.797386: Epoch time: 20.56 s +2025-10-30 20:50:42.996187: +2025-10-30 20:50:42.998240: Epoch 977 +2025-10-30 20:50:43.000660: Current learning rate: 0.00034 +2025-10-30 20:51:03.500337: train_loss -0.995 +2025-10-30 20:51:03.503216: val_loss -0.8975 +2025-10-30 20:51:03.505261: Pseudo dice [np.float32(0.984), np.float32(0.9914), np.float32(0.9954), np.float32(0.8211)] +2025-10-30 20:51:03.507293: Epoch time: 20.51 s +2025-10-30 20:51:04.703121: +2025-10-30 20:51:04.705509: Epoch 978 +2025-10-30 20:51:04.707565: Current learning rate: 0.00032 +2025-10-30 20:51:25.143889: train_loss -0.9952 +2025-10-30 20:51:25.148201: val_loss -0.9005 +2025-10-30 20:51:25.150513: Pseudo dice [np.float32(0.9841), np.float32(0.9918), np.float32(0.9953), np.float32(0.827)] +2025-10-30 20:51:25.155816: Epoch time: 20.44 s +2025-10-30 20:51:26.259367: +2025-10-30 20:51:26.261235: Epoch 979 +2025-10-30 20:51:26.263150: Current learning rate: 0.00031 +2025-10-30 20:51:46.346034: train_loss -0.9951 +2025-10-30 20:51:46.350269: val_loss -0.9004 +2025-10-30 20:51:46.351958: Pseudo dice [np.float32(0.9846), np.float32(0.9921), np.float32(0.9954), np.float32(0.8239)] +2025-10-30 20:51:46.353575: Epoch time: 20.09 s +2025-10-30 20:51:47.588780: +2025-10-30 20:51:47.590810: Epoch 980 +2025-10-30 20:51:47.592702: Current learning rate: 0.0003 +2025-10-30 20:52:07.184432: train_loss -0.9954 +2025-10-30 20:52:07.187395: val_loss -0.8993 +2025-10-30 20:52:07.189396: Pseudo dice [np.float32(0.984), np.float32(0.9913), np.float32(0.9956), np.float32(0.8246)] +2025-10-30 20:52:07.191328: Epoch time: 19.6 s +2025-10-30 20:52:08.195203: +2025-10-30 20:52:08.197328: Epoch 981 +2025-10-30 20:52:08.199206: Current learning rate: 0.00028 +2025-10-30 20:52:54.813045: train_loss -0.9953 +2025-10-30 20:52:54.821374: val_loss -0.8967 +2025-10-30 20:52:54.824199: Pseudo dice [np.float32(0.9848), np.float32(0.9911), np.float32(0.9951), np.float32(0.8206)] +2025-10-30 20:52:54.826694: Epoch time: 46.62 s +2025-10-30 20:52:55.925748: +2025-10-30 20:52:55.928033: Epoch 982 +2025-10-30 20:52:55.930376: Current learning rate: 0.00027 +2025-10-30 20:53:15.917145: train_loss -0.9951 +2025-10-30 20:53:15.924371: val_loss -0.8962 +2025-10-30 20:53:15.926095: Pseudo dice [np.float32(0.9847), np.float32(0.9916), np.float32(0.9951), np.float32(0.817)] +2025-10-30 20:53:15.928064: Epoch time: 19.99 s +2025-10-30 20:53:17.390597: +2025-10-30 20:53:17.392871: Epoch 983 +2025-10-30 20:53:17.398851: Current learning rate: 0.00026 +2025-10-30 20:53:37.712254: train_loss -0.9952 +2025-10-30 20:53:37.717640: val_loss -0.9061 +2025-10-30 20:53:37.719503: Pseudo dice [np.float32(0.9848), np.float32(0.9917), np.float32(0.9958), np.float32(0.8372)] +2025-10-30 20:53:37.721209: Epoch time: 20.32 s +2025-10-30 20:53:38.767684: +2025-10-30 20:53:38.774043: Epoch 984 +2025-10-30 20:53:38.776163: Current learning rate: 0.00024 +2025-10-30 20:53:59.447910: train_loss -0.995 +2025-10-30 20:53:59.455987: val_loss -0.8915 +2025-10-30 20:53:59.458077: Pseudo dice [np.float32(0.9839), np.float32(0.9915), np.float32(0.995), np.float32(0.8044)] +2025-10-30 20:53:59.460451: Epoch time: 20.68 s +2025-10-30 20:54:00.742568: +2025-10-30 20:54:00.744779: Epoch 985 +2025-10-30 20:54:00.747696: Current learning rate: 0.00023 +2025-10-30 20:54:20.359492: train_loss -0.9953 +2025-10-30 20:54:20.366208: val_loss -0.9061 +2025-10-30 20:54:20.368010: Pseudo dice [np.float32(0.9854), np.float32(0.9919), np.float32(0.9956), np.float32(0.8358)] +2025-10-30 20:54:20.374027: Epoch time: 19.62 s +2025-10-30 20:54:21.419012: +2025-10-30 20:54:21.425192: Epoch 986 +2025-10-30 20:54:21.426844: Current learning rate: 0.00021 +2025-10-30 20:54:41.147662: train_loss -0.9955 +2025-10-30 20:54:41.155429: val_loss -0.8985 +2025-10-30 20:54:41.159054: Pseudo dice [np.float32(0.9853), np.float32(0.9922), np.float32(0.9953), np.float32(0.8142)] +2025-10-30 20:54:41.162674: Epoch time: 19.73 s +2025-10-30 20:54:42.208445: +2025-10-30 20:54:42.210265: Epoch 987 +2025-10-30 20:54:42.215744: Current learning rate: 0.0002 +2025-10-30 20:55:02.632942: train_loss -0.9952 +2025-10-30 20:55:02.639120: val_loss -0.8985 +2025-10-30 20:55:02.641000: Pseudo dice [np.float32(0.9851), np.float32(0.9918), np.float32(0.9951), np.float32(0.8224)] +2025-10-30 20:55:02.642704: Epoch time: 20.43 s +2025-10-30 20:55:03.719014: +2025-10-30 20:55:03.724287: Epoch 988 +2025-10-30 20:55:03.725915: Current learning rate: 0.00019 +2025-10-30 20:55:24.344230: train_loss -0.9952 +2025-10-30 20:55:24.355485: val_loss -0.8995 +2025-10-30 20:55:24.360246: Pseudo dice [np.float32(0.9848), np.float32(0.9919), np.float32(0.9953), np.float32(0.8251)] +2025-10-30 20:55:24.369442: Epoch time: 20.63 s +2025-10-30 20:55:25.638064: +2025-10-30 20:55:25.643532: Epoch 989 +2025-10-30 20:55:25.645216: Current learning rate: 0.00017 +2025-10-30 20:55:46.211696: train_loss -0.9954 +2025-10-30 20:55:46.236169: val_loss -0.9001 +2025-10-30 20:55:46.243348: Pseudo dice [np.float32(0.9848), np.float32(0.992), np.float32(0.9955), np.float32(0.822)] +2025-10-30 20:55:46.248022: Epoch time: 20.58 s +2025-10-30 20:55:47.529702: +2025-10-30 20:55:47.531698: Epoch 990 +2025-10-30 20:55:47.533772: Current learning rate: 0.00016 +2025-10-30 20:56:08.174426: train_loss -0.9952 +2025-10-30 20:56:08.187178: val_loss -0.8961 +2025-10-30 20:56:08.196540: Pseudo dice [np.float32(0.9848), np.float32(0.9917), np.float32(0.9952), np.float32(0.8151)] +2025-10-30 20:56:08.202837: Epoch time: 20.65 s +2025-10-30 20:56:09.428999: +2025-10-30 20:56:09.431017: Epoch 991 +2025-10-30 20:56:09.432741: Current learning rate: 0.00014 +2025-10-30 20:56:30.170818: train_loss -0.9953 +2025-10-30 20:56:30.269561: val_loss -0.8982 +2025-10-30 20:56:30.273906: Pseudo dice [np.float32(0.9844), np.float32(0.9913), np.float32(0.9952), np.float32(0.8286)] +2025-10-30 20:56:30.284475: Epoch time: 20.74 s +2025-10-30 20:56:31.690723: +2025-10-30 20:56:31.695240: Epoch 992 +2025-10-30 20:56:31.696842: Current learning rate: 0.00013 +2025-10-30 20:56:49.863909: train_loss -0.9953 +2025-10-30 20:56:50.009459: val_loss -0.8994 +2025-10-30 20:56:50.011548: Pseudo dice [np.float32(0.9847), np.float32(0.9914), np.float32(0.9953), np.float32(0.824)] +2025-10-30 20:56:50.017144: Epoch time: 18.17 s +2025-10-30 20:56:51.123900: +2025-10-30 20:56:51.125781: Epoch 993 +2025-10-30 20:56:51.127525: Current learning rate: 0.00011 +2025-10-30 20:57:11.357260: train_loss -0.9952 +2025-10-30 20:57:11.360601: val_loss -0.8909 +2025-10-30 20:57:11.365347: Pseudo dice [np.float32(0.9847), np.float32(0.9912), np.float32(0.9947), np.float32(0.8067)] +2025-10-30 20:57:11.367954: Epoch time: 20.23 s +2025-10-30 20:57:12.397288: +2025-10-30 20:57:12.399398: Epoch 994 +2025-10-30 20:57:12.401371: Current learning rate: 0.0001 +2025-10-30 20:57:32.896323: train_loss -0.9955 +2025-10-30 20:57:32.901936: val_loss -0.9013 +2025-10-30 20:57:32.904194: Pseudo dice [np.float32(0.9851), np.float32(0.9919), np.float32(0.9954), np.float32(0.8299)] +2025-10-30 20:57:32.907035: Epoch time: 20.5 s +2025-10-30 20:57:34.537577: +2025-10-30 20:57:34.542776: Epoch 995 +2025-10-30 20:57:34.544865: Current learning rate: 8e-05 +2025-10-30 20:57:55.365552: train_loss -0.9956 +2025-10-30 20:57:55.377789: val_loss -0.8965 +2025-10-30 20:57:55.379939: Pseudo dice [np.float32(0.985), np.float32(0.9917), np.float32(0.9952), np.float32(0.8162)] +2025-10-30 20:57:55.384644: Epoch time: 20.83 s +2025-10-30 20:57:56.604252: +2025-10-30 20:57:56.606771: Epoch 996 +2025-10-30 20:57:56.608723: Current learning rate: 7e-05 +2025-10-30 20:58:17.002869: train_loss -0.9955 +2025-10-30 20:58:17.016098: val_loss -0.8995 +2025-10-30 20:58:17.021384: Pseudo dice [np.float32(0.9837), np.float32(0.9912), np.float32(0.9955), np.float32(0.8334)] +2025-10-30 20:58:17.022968: Epoch time: 20.4 s +2025-10-30 20:58:18.138444: +2025-10-30 20:58:18.144866: Epoch 997 +2025-10-30 20:58:18.147793: Current learning rate: 5e-05 +2025-10-30 20:58:38.471475: train_loss -0.9956 +2025-10-30 20:58:38.474133: val_loss -0.8963 +2025-10-30 20:58:38.476299: Pseudo dice [np.float32(0.9852), np.float32(0.9914), np.float32(0.9951), np.float32(0.8168)] +2025-10-30 20:58:38.478554: Epoch time: 20.33 s +2025-10-30 20:58:39.507055: +2025-10-30 20:58:39.508795: Epoch 998 +2025-10-30 20:58:39.510308: Current learning rate: 4e-05 +2025-10-30 20:58:59.168280: train_loss -0.9956 +2025-10-30 20:58:59.916359: val_loss -0.8959 +2025-10-30 20:58:59.918564: Pseudo dice [np.float32(0.985), np.float32(0.9912), np.float32(0.9951), np.float32(0.8164)] +2025-10-30 20:58:59.921091: Epoch time: 19.66 s +2025-10-30 20:59:01.026217: +2025-10-30 20:59:01.028145: Epoch 999 +2025-10-30 20:59:01.030147: Current learning rate: 2e-05 +2025-10-30 20:59:21.016263: train_loss -0.9952 +2025-10-30 20:59:21.019657: val_loss -0.9006 +2025-10-30 20:59:21.021653: Pseudo dice [np.float32(0.9847), np.float32(0.9919), np.float32(0.9954), np.float32(0.8264)] +2025-10-30 20:59:21.023528: Epoch time: 19.99 s +2025-10-30 20:59:24.214050: Training done. +2025-10-30 20:59:24.301071: Using splits from existing split file: /hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/splits_final.json +2025-10-30 20:59:24.306825: The split file contains 5 splits. +2025-10-30 20:59:24.309132: Desired fold for training: 1 +2025-10-30 20:59:24.312370: This split has 86 training and 22 validation cases. +2025-10-30 20:59:24.317148: predicting fish0002 +2025-10-30 20:59:24.323797: fish0002, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 20:59:37.145095: predicting fish0006 +2025-10-30 20:59:37.151485: fish0006, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 20:59:37.217132: predicting fish0008 +2025-10-30 20:59:37.224861: fish0008, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 20:59:37.286787: predicting fish0020 +2025-10-30 20:59:37.292292: fish0020, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 20:59:37.386365: predicting fish0025 +2025-10-30 20:59:37.391961: fish0025, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 20:59:37.496662: predicting fish0030 +2025-10-30 20:59:37.505545: fish0030, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 20:59:37.562963: predicting fish0035 +2025-10-30 20:59:37.572237: fish0035, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 20:59:37.638776: predicting fish0037 +2025-10-30 20:59:37.642540: fish0037, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 20:59:37.725462: predicting fish0044 +2025-10-30 20:59:37.730996: fish0044, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 20:59:37.776891: predicting fish0045 +2025-10-30 20:59:37.781486: fish0045, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 20:59:37.845403: predicting fish0047 +2025-10-30 20:59:37.853097: fish0047, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 20:59:37.908288: predicting fish0048 +2025-10-30 20:59:37.914073: fish0048, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 20:59:37.959337: predicting fish0051 +2025-10-30 20:59:37.963113: fish0051, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 20:59:38.016904: predicting fish0065 +2025-10-30 20:59:38.021504: fish0065, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 20:59:38.059744: predicting fish0067 +2025-10-30 20:59:38.065064: fish0067, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 20:59:38.123536: predicting fish0071 +2025-10-30 20:59:38.128501: fish0071, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 20:59:38.179161: predicting fish0076 +2025-10-30 20:59:38.184187: fish0076, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 20:59:38.245959: predicting fish0079 +2025-10-30 20:59:38.253961: fish0079, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 20:59:38.307022: predicting fish0083 +2025-10-30 20:59:38.312400: fish0083, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 20:59:38.358294: predicting fish0088 +2025-10-30 20:59:38.363063: fish0088, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 20:59:38.429814: predicting fish0095 +2025-10-30 20:59:38.434712: fish0095, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 20:59:38.472841: predicting fish0107 +2025-10-30 20:59:38.477038: fish0107, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-30 20:59:46.661910: Validation complete +2025-10-30 20:59:46.665558: Mean Validation Dice: 0.9473135159852011 diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0002.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0002.png new file mode 100644 index 0000000000000000000000000000000000000000..843671e5f023d866a0632e8f2cd39a83cc0f4de5 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0002.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0006.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0006.png new file mode 100644 index 0000000000000000000000000000000000000000..d9672c8c67c3dc54333172c399a51ff8004b0525 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0006.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0008.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0008.png new file mode 100644 index 0000000000000000000000000000000000000000..2d9f5acd48b5d470341ae24b85183453206cac1c Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0008.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0020.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0020.png new file mode 100644 index 0000000000000000000000000000000000000000..bbf9635b7df0f0cc7cadec3539c93c1a16560f0d Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0020.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0025.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0025.png new file mode 100644 index 0000000000000000000000000000000000000000..d13908b0a4c991ace2f6fefda83bdc37807c211e Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0025.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0030.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0030.png new file mode 100644 index 0000000000000000000000000000000000000000..5d5be5f9830d10806e4d5d600f72dfbd1ca4ef1d Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0030.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0035.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0035.png new file mode 100644 index 0000000000000000000000000000000000000000..e65e931e18ccb7675f6a89d85cd1ee1d5f48b4b8 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0035.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0037.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0037.png new file mode 100644 index 0000000000000000000000000000000000000000..c19790a8a18a4d601a79a4bc8d2e860a383629dc Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0037.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0044.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0044.png new file mode 100644 index 0000000000000000000000000000000000000000..c661eb857ae8ab940b0a7c682dec6d125670c774 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0044.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0045.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0045.png new file mode 100644 index 0000000000000000000000000000000000000000..c4001b2a5cef6d6e949e9fe9b557e497ea0de177 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0045.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0047.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0047.png new file mode 100644 index 0000000000000000000000000000000000000000..094a4f29b539010cde9e3695db1f50ba4f668325 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0047.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0048.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0048.png new file mode 100644 index 0000000000000000000000000000000000000000..7a2ff41bfdc200de64544a95cb636e444c4e6efc Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0048.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0051.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0051.png new file mode 100644 index 0000000000000000000000000000000000000000..38e899d113092d773b2d3bc8facf6885e929b497 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0051.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0065.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0065.png new file mode 100644 index 0000000000000000000000000000000000000000..ad27bfaa01d704bfcc33e204604ca3a00ac61db5 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0065.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0067.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0067.png new file mode 100644 index 0000000000000000000000000000000000000000..9abb2ca35bac5bf078412ac87aa6402f74159d8b Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0067.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0071.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0071.png new file mode 100644 index 0000000000000000000000000000000000000000..870746492d47316d26fc76df69fd02baeaffc2db Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0071.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0076.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0076.png new file mode 100644 index 0000000000000000000000000000000000000000..0bcc201f67946bf7f8e68849b0bfa118a7e03e47 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0076.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0079.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0079.png new file mode 100644 index 0000000000000000000000000000000000000000..52ca6c8fc71bb22a7d6c810fe43a3c16c36c496b Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0079.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0083.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0083.png new file mode 100644 index 0000000000000000000000000000000000000000..060e923f20e539e28d3e7f0cdf54fc3670753edb Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0083.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0088.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0088.png new file mode 100644 index 0000000000000000000000000000000000000000..6008ef5c9f923dc745ec3fc2460479b0a00cec7d Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0088.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0095.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0095.png new file mode 100644 index 0000000000000000000000000000000000000000..9f447add1ec08711cc1e9654b9ddca9131dfbad9 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0095.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0107.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0107.png new file mode 100644 index 0000000000000000000000000000000000000000..3d5c6d18c8b3fc8fa4e49c884368f714825eb405 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0107.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/summary.json b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/summary.json new file mode 100644 index 0000000000000000000000000000000000000000..7e1375f1accad6547465f8c53d47f6723e8f9b69 --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/summary.json @@ -0,0 +1,1068 @@ +{ + "foreground_mean": { + "Dice": 0.9473135159852011, + "FN": 117.77272727272727, + "FP": 122.125, + "IoU": 0.9124459778909428, + "TN": 92063.85227272728, + "TP": 12144.25, + "n_pred": 12266.374999999998, + "n_ref": 12262.022727272728 + }, + "mean": { + "1": { + "Dice": 0.9851168923759139, + "FN": 81.22727272727273, + "FP": 101.0909090909091, + "IoU": 0.9707880818045628, + "TN": 98213.0, + "TP": 6052.681818181818, + "n_pred": 6153.772727272727, + "n_ref": 6133.909090909091 + }, + "2": { + "Dice": 0.9911241606987393, + "FN": 117.4090909090909, + "FP": 80.27272727272727, + "IoU": 0.9824804812056833, + "TN": 92461.54545454546, + "TP": 11788.772727272728, + "n_pred": 11869.045454545454, + "n_ref": 11906.181818181818 + }, + "3": { + "Dice": 0.995104082398793, + "FN": 106.95454545454545, + "FP": 181.8181818181818, + "IoU": 0.9902792142733566, + "TN": 74102.0, + "TP": 30057.227272727272, + "n_pred": 30239.045454545456, + "n_ref": 30164.18181818182 + }, + "4": { + "Dice": 0.8179089284673581, + "FN": 165.5, + "FP": 125.31818181818181, + "IoU": 0.7062361342801687, + "TN": 103478.86363636363, + "TP": 678.3181818181819, + "n_pred": 803.6363636363636, + "n_ref": 843.8181818181819 + } + }, + "metric_per_case": [ + { + "metrics": { + "1": { + "Dice": 0.9626715902705306, + "FN": 22, + "FP": 443, + "IoU": 0.9280297167621111, + "TN": 97987, + "TP": 5996, + "n_pred": 6439, + "n_ref": 6018 + }, + "2": { + "Dice": 0.9779067752555883, + "FN": 443, + "FP": 67, + "IoU": 0.9567686700008476, + "TN": 92651, + "TP": 11287, + "n_pred": 11354, + "n_ref": 11730 + }, + "3": { + "Dice": 0.9979704262104958, + "FN": 119, + "FP": 0, + "IoU": 0.9959490740740741, + "TN": 75072, + "TP": 29257, + "n_pred": 29257, + "n_ref": 29376 + }, + "4": { + "Dice": 0.6950596252129472, + "FN": 0, + "FP": 358, + "IoU": 0.5326370757180157, + "TN": 103682, + "TP": 408, + "n_pred": 766, + "n_ref": 408 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0002.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0002.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9909179370742783, + "FN": 112, + "FP": 0, + "IoU": 0.9819993571198972, + "TN": 98226, + "TP": 6110, + "n_pred": 6110, + "n_ref": 6222 + }, + "2": { + "Dice": 0.9896593011864592, + "FN": 88, + "FP": 102, + "IoU": 0.9795302736479207, + "TN": 95166, + "TP": 9092, + "n_pred": 9194, + "n_ref": 9180 + }, + "3": { + "Dice": 0.9923337354555006, + "FN": 0, + "FP": 394, + "IoU": 0.9847841198733297, + "TN": 78554, + "TP": 25500, + "n_pred": 25894, + "n_ref": 25500 + }, + "4": { + "Dice": 0.75, + "FN": 306, + "FP": 102, + "IoU": 0.6, + "TN": 103428, + "TP": 612, + "n_pred": 714, + "n_ref": 918 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0006.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0006.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9944641824341073, + "FN": 0, + "FP": 67, + "IoU": 0.9889893179950698, + "TN": 98363, + "TP": 6018, + "n_pred": 6085, + "n_ref": 6018 + }, + "2": { + "Dice": 0.9933333333333333, + "FN": 204, + "FP": 0, + "IoU": 0.9867549668874173, + "TN": 89046, + "TP": 15198, + "n_pred": 15198, + "n_ref": 15402 + }, + "3": { + "Dice": 0.9911764705882353, + "FN": 0, + "FP": 612, + "IoU": 0.9825072886297376, + "TN": 69462, + "TP": 34374, + "n_pred": 34986, + "n_ref": 34374 + }, + "4": { + "Dice": 0.8237232289950577, + "FN": 428, + "FP": 0, + "IoU": 0.7002801120448179, + "TN": 103020, + "TP": 1000, + "n_pred": 1000, + "n_ref": 1428 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0008.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0008.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9751761153975176, + "FN": 0, + "FP": 296, + "IoU": 0.9515548281505728, + "TN": 98338, + "TP": 5814, + "n_pred": 6110, + "n_ref": 5814 + }, + "2": { + "Dice": 0.9746192893401016, + "FN": 204, + "FP": 306, + "IoU": 0.9504950495049505, + "TN": 94146, + "TP": 9792, + "n_pred": 10098, + "n_ref": 9996 + }, + "3": { + "Dice": 0.9944547134935305, + "FN": 306, + "FP": 0, + "IoU": 0.9889705882352942, + "TN": 76704, + "TP": 27438, + "n_pred": 27438, + "n_ref": 27744 + }, + "4": { + "Dice": 0.8888888888888888, + "FN": 0, + "FP": 102, + "IoU": 0.8, + "TN": 103938, + "TP": 408, + "n_pred": 510, + "n_ref": 408 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0020.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0020.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9840012189547463, + "FN": 70, + "FP": 140, + "IoU": 0.968506298740252, + "TN": 97780, + "TP": 6458, + "n_pred": 6598, + "n_ref": 6528 + }, + "2": { + "Dice": 0.9925282363162468, + "FN": 102, + "FP": 70, + "IoU": 0.9851672990686443, + "TN": 92852, + "TP": 11424, + "n_pred": 11494, + "n_ref": 11526 + }, + "3": { + "Dice": 0.9983844911147012, + "FN": 0, + "FP": 102, + "IoU": 0.9967741935483871, + "TN": 72828, + "TP": 31518, + "n_pred": 31620, + "n_ref": 31518 + }, + "4": { + "Dice": 0.9978260869565218, + "FN": 0, + "FP": 4, + "IoU": 0.9956616052060737, + "TN": 103526, + "TP": 918, + "n_pred": 922, + "n_ref": 918 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0025.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0025.png" + }, + { + "metrics": { + "1": { + "Dice": 0.990764331210191, + "FN": 102, + "FP": 14, + "IoU": 0.9816976964342063, + "TN": 98110, + "TP": 6222, + "n_pred": 6236, + "n_ref": 6324 + }, + "2": { + "Dice": 0.9957095185126331, + "FN": 14, + "FP": 94, + "IoU": 0.9914556962025316, + "TN": 91808, + "TP": 12532, + "n_pred": 12626, + "n_ref": 12546 + }, + "3": { + "Dice": 0.9964512117443659, + "FN": 94, + "FP": 140, + "IoU": 0.992927522214834, + "TN": 71362, + "TP": 32852, + "n_pred": 32992, + "n_ref": 32946 + }, + "4": { + "Dice": 0.848180677540778, + "FN": 140, + "FP": 102, + "IoU": 0.7363834422657952, + "TN": 103530, + "TP": 676, + "n_pred": 778, + "n_ref": 816 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0030.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0030.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9984452990753621, + "FN": 19, + "FP": 0, + "IoU": 0.9968954248366013, + "TN": 98328, + "TP": 6101, + "n_pred": 6101, + "n_ref": 6120 + }, + "2": { + "Dice": 0.9990101588955457, + "FN": 0, + "FP": 19, + "IoU": 0.9980222754241699, + "TN": 94841, + "TP": 9588, + "n_pred": 9607, + "n_ref": 9588 + }, + "3": { + "Dice": 0.998158379373849, + "FN": 102, + "FP": 0, + "IoU": 0.9963235294117647, + "TN": 76704, + "TP": 27642, + "n_pred": 27642, + "n_ref": 27744 + }, + "4": { + "Dice": 0.8774193548387097, + "FN": 0, + "FP": 171, + "IoU": 0.7816091954022989, + "TN": 103665, + "TP": 612, + "n_pred": 783, + "n_ref": 612 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0035.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0035.png" + }, + { + "metrics": { + "1": { + "Dice": 0.982169147717978, + "FN": 116, + "FP": 102, + "IoU": 0.9649630343940855, + "TN": 98226, + "TP": 6004, + "n_pred": 6106, + "n_ref": 6120 + }, + "2": { + "Dice": 0.9933333333333333, + "FN": 204, + "FP": 0, + "IoU": 0.9867549668874173, + "TN": 89046, + "TP": 15198, + "n_pred": 15198, + "n_ref": 15402 + }, + "3": { + "Dice": 0.98999179182927, + "FN": 0, + "FP": 695, + "IoU": 0.9801819270580855, + "TN": 69379, + "TP": 34374, + "n_pred": 35069, + "n_ref": 34374 + }, + "4": { + "Dice": 0.7379584622182943, + "FN": 593, + "FP": 0, + "IoU": 0.584733893557423, + "TN": 103020, + "TP": 835, + "n_pred": 835, + "n_ref": 1428 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0037.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0037.png" + }, + { + "metrics": { + "1": { + "Dice": 0.985427904355527, + "FN": 0, + "FP": 181, + "IoU": 0.9712744008887478, + "TN": 98147, + "TP": 6120, + "n_pred": 6301, + "n_ref": 6120 + }, + "2": { + "Dice": 0.9892681284457725, + "FN": 181, + "FP": 74, + "IoU": 0.9787641572285143, + "TN": 92440, + "TP": 11753, + "n_pred": 11827, + "n_ref": 11934 + }, + "3": { + "Dice": 0.9960122541888445, + "FN": 74, + "FP": 159, + "IoU": 0.9920561862875455, + "TN": 75117, + "TP": 29098, + "n_pred": 29257, + "n_ref": 29172 + }, + "4": { + "Dice": 0.9051878354203936, + "FN": 159, + "FP": 0, + "IoU": 0.826797385620915, + "TN": 103530, + "TP": 759, + "n_pred": 759, + "n_ref": 918 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0044.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0044.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9851180847622129, + "FN": 132, + "FP": 52, + "IoU": 0.9706726171501434, + "TN": 98174, + "TP": 6090, + "n_pred": 6142, + "n_ref": 6222 + }, + "2": { + "Dice": 0.9974293059125964, + "FN": 68, + "FP": 0, + "IoU": 0.9948717948717949, + "TN": 91188, + "TP": 13192, + "n_pred": 13192, + "n_ref": 13260 + }, + "3": { + "Dice": 0.9981860585643949, + "FN": 0, + "FP": 119, + "IoU": 0.9963786859803414, + "TN": 71587, + "TP": 32742, + "n_pred": 32861, + "n_ref": 32742 + }, + "4": { + "Dice": 0.8679245283018868, + "FN": 103, + "FP": 114, + "IoU": 0.7666666666666667, + "TN": 103518, + "TP": 713, + "n_pred": 827, + "n_ref": 816 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0045.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0045.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9878508588186008, + "FN": 21, + "FP": 124, + "IoU": 0.9759933774834437, + "TN": 98408, + "TP": 5895, + "n_pred": 6019, + "n_ref": 5916 + }, + "2": { + "Dice": 0.995260663507109, + "FN": 102, + "FP": 0, + "IoU": 0.9905660377358491, + "TN": 93636, + "TP": 10710, + "n_pred": 10710, + "n_ref": 10812 + }, + "3": { + "Dice": 0.99812382739212, + "FN": 102, + "FP": 0, + "IoU": 0.9962546816479401, + "TN": 77214, + "TP": 27132, + "n_pred": 27132, + "n_ref": 27234 + }, + "4": { + "Dice": 0.8333333333333334, + "FN": 0, + "FP": 204, + "IoU": 0.7142857142857143, + "TN": 103734, + "TP": 510, + "n_pred": 714, + "n_ref": 510 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0047.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0047.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9986406887177164, + "FN": 18, + "FP": 0, + "IoU": 0.9972850678733032, + "TN": 97818, + "TP": 6612, + "n_pred": 6612, + "n_ref": 6630 + }, + "2": { + "Dice": 0.995475113122172, + "FN": 86, + "FP": 18, + "IoU": 0.990990990990991, + "TN": 92904, + "TP": 11440, + "n_pred": 11458, + "n_ref": 11526 + }, + "3": { + "Dice": 0.9970264456535493, + "FN": 0, + "FP": 188, + "IoU": 0.994070522929414, + "TN": 72742, + "TP": 31518, + "n_pred": 31706, + "n_ref": 31518 + }, + "4": { + "Dice": 0.8888888888888888, + "FN": 204, + "FP": 0, + "IoU": 0.8, + "TN": 103428, + "TP": 816, + "n_pred": 816, + "n_ref": 1020 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0048.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0048.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9896612056624782, + "FN": 102, + "FP": 28, + "IoU": 0.9795340050377834, + "TN": 98096, + "TP": 6222, + "n_pred": 6250, + "n_ref": 6324 + }, + "2": { + "Dice": 0.9942735788236187, + "FN": 49, + "FP": 102, + "IoU": 0.9886123680241328, + "TN": 91188, + "TP": 13109, + "n_pred": 13211, + "n_ref": 13158 + }, + "3": { + "Dice": 0.9972191408208854, + "FN": 134, + "FP": 49, + "IoU": 0.9944537051068344, + "TN": 71453, + "TP": 32812, + "n_pred": 32861, + "n_ref": 32946 + }, + "4": { + "Dice": 0.8383561643835616, + "FN": 0, + "FP": 236, + "IoU": 0.7216981132075472, + "TN": 103600, + "TP": 612, + "n_pred": 848, + "n_ref": 612 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0051.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0051.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9833333333333333, + "FN": 204, + "FP": 0, + "IoU": 0.9672131147540983, + "TN": 98226, + "TP": 6018, + "n_pred": 6018, + "n_ref": 6222 + }, + "2": { + "Dice": 0.9947826086956522, + "FN": 60, + "FP": 102, + "IoU": 0.9896193771626297, + "TN": 88842, + "TP": 15444, + "n_pred": 15546, + "n_ref": 15504 + }, + "3": { + "Dice": 0.9954890467572459, + "FN": 274, + "FP": 60, + "IoU": 0.9910186081531677, + "TN": 67260, + "TP": 36854, + "n_pred": 36914, + "n_ref": 37128 + }, + "4": { + "Dice": 0.7915742793791575, + "FN": 0, + "FP": 376, + "IoU": 0.655045871559633, + "TN": 103358, + "TP": 714, + "n_pred": 1090, + "n_ref": 714 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0065.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0065.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9914529914529915, + "FN": 0, + "FP": 102, + "IoU": 0.9830508474576272, + "TN": 98430, + "TP": 5916, + "n_pred": 6018, + "n_ref": 5916 + }, + "2": { + "Dice": 0.9957805907172996, + "FN": 102, + "FP": 0, + "IoU": 0.9915966386554622, + "TN": 92310, + "TP": 12036, + "n_pred": 12036, + "n_ref": 12138 + }, + "3": { + "Dice": 0.9913968608392986, + "FN": 0, + "FP": 524, + "IoU": 0.9829404870425836, + "TN": 73732, + "TP": 30192, + "n_pred": 30716, + "n_ref": 30192 + }, + "4": { + "Dice": 0.7319461444308446, + "FN": 422, + "FP": 16, + "IoU": 0.5772200772200772, + "TN": 103412, + "TP": 598, + "n_pred": 614, + "n_ref": 1020 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0067.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0067.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9845398773006135, + "FN": 0, + "FP": 189, + "IoU": 0.9695505074915418, + "TN": 98241, + "TP": 6018, + "n_pred": 6207, + "n_ref": 6018 + }, + "2": { + "Dice": 0.9835230168167148, + "FN": 189, + "FP": 102, + "IoU": 0.9675802139037433, + "TN": 95472, + "TP": 8685, + "n_pred": 8787, + "n_ref": 8874 + }, + "3": { + "Dice": 0.9848156182212582, + "FN": 102, + "FP": 612, + "IoU": 0.9700854700854701, + "TN": 80580, + "TP": 23154, + "n_pred": 23766, + "n_ref": 23256 + }, + "4": { + "Dice": 0.42857142857142855, + "FN": 816, + "FP": 0, + "IoU": 0.2727272727272727, + "TN": 103326, + "TP": 306, + "n_pred": 306, + "n_ref": 1122 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0071.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0071.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9786950732356857, + "FN": 240, + "FP": 16, + "IoU": 0.9582790091264668, + "TN": 98312, + "TP": 5880, + "n_pred": 5896, + "n_ref": 6120 + }, + "2": { + "Dice": 0.9875, + "FN": 0, + "FP": 204, + "IoU": 0.9753086419753086, + "TN": 96186, + "TP": 8058, + "n_pred": 8262, + "n_ref": 8058 + }, + "3": { + "Dice": 0.9936305732484076, + "FN": 306, + "FP": 0, + "IoU": 0.9873417721518988, + "TN": 80274, + "TP": 23868, + "n_pred": 23868, + "n_ref": 24174 + }, + "4": { + "Dice": 0.7159716758457907, + "FN": 55, + "FP": 306, + "IoU": 0.5575980392156863, + "TN": 103632, + "TP": 455, + "n_pred": 761, + "n_ref": 510 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0076.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0076.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9779055441478439, + "FN": 65, + "FP": 204, + "IoU": 0.9567663130826101, + "TN": 98226, + "TP": 5953, + "n_pred": 6157, + "n_ref": 6018 + }, + "2": { + "Dice": 0.9882352941176471, + "FN": 204, + "FP": 102, + "IoU": 0.9767441860465116, + "TN": 91290, + "TP": 12852, + "n_pred": 12954, + "n_ref": 13056 + }, + "3": { + "Dice": 0.9967741935483871, + "FN": 204, + "FP": 0, + "IoU": 0.9935691318327974, + "TN": 72726, + "TP": 31518, + "n_pred": 31518, + "n_ref": 31722 + }, + "4": { + "Dice": 0.8961038961038961, + "FN": 90, + "FP": 102, + "IoU": 0.8117647058823529, + "TN": 103428, + "TP": 828, + "n_pred": 930, + "n_ref": 918 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0079.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0079.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9779646761984861, + "FN": 204, + "FP": 58, + "IoU": 0.95687952600395, + "TN": 98372, + "TP": 5814, + "n_pred": 5872, + "n_ref": 6018 + }, + "2": { + "Dice": 0.9980152723113668, + "FN": 58, + "FP": 1, + "IoU": 0.9960384073054455, + "TN": 89555, + "TP": 14834, + "n_pred": 14835, + "n_ref": 14892 + }, + "3": { + "Dice": 0.9986505110830366, + "FN": 1, + "FP": 93, + "IoU": 0.9973046594982079, + "TN": 69573, + "TP": 34781, + "n_pred": 34874, + "n_ref": 34782 + }, + "4": { + "Dice": 0.8905235828645608, + "FN": 93, + "FP": 160, + "IoU": 0.8026521060842434, + "TN": 103166, + "TP": 1029, + "n_pred": 1189, + "n_ref": 1122 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0083.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0083.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9866989117291415, + "FN": 0, + "FP": 154, + "IoU": 0.9737470167064439, + "TN": 98582, + "TP": 5712, + "n_pred": 5866, + "n_ref": 5712 + }, + "2": { + "Dice": 0.9899037332707208, + "FN": 0, + "FP": 258, + "IoU": 0.9800092980009298, + "TN": 91542, + "TP": 12648, + "n_pred": 12906, + "n_ref": 12648 + }, + "3": { + "Dice": 0.9922104198280223, + "FN": 462, + "FP": 0, + "IoU": 0.9845412567757479, + "TN": 74562, + "TP": 29424, + "n_pred": 29424, + "n_ref": 29886 + }, + "4": { + "Dice": 0.7989556135770235, + "FN": 0, + "FP": 308, + "IoU": 0.6652173913043479, + "TN": 103528, + "TP": 612, + "n_pred": 920, + "n_ref": 612 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0088.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0088.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9811320754716981, + "FN": 238, + "FP": 0, + "IoU": 0.9629629629629629, + "TN": 98022, + "TP": 6188, + "n_pred": 6188, + "n_ref": 6426 + }, + "2": { + "Dice": 0.995198402028195, + "FN": 102, + "FP": 23, + "IoU": 0.990442694395596, + "TN": 91369, + "TP": 12954, + "n_pred": 12977, + "n_ref": 13056 + }, + "3": { + "Dice": 0.9979352625393094, + "FN": 0, + "FP": 130, + "IoU": 0.9958790337919229, + "TN": 72902, + "TP": 31416, + "n_pred": 31546, + "n_ref": 31416 + }, + "4": { + "Dice": 0.9721463681048608, + "FN": 28, + "FP": 23, + "IoU": 0.9458023379383634, + "TN": 103507, + "TP": 890, + "n_pred": 913, + "n_ref": 918 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0095.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0095.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9855405849490634, + "FN": 122, + "FP": 54, + "IoU": 0.9714933592484613, + "TN": 98274, + "TP": 5998, + "n_pred": 6052, + "n_ref": 6120 + }, + "2": { + "Dice": 0.9839858814301589, + "FN": 123, + "FP": 122, + "IoU": 0.9684765826042203, + "TN": 96676, + "TP": 7527, + "n_pred": 7649, + "n_ref": 7650 + }, + "3": { + "Dice": 0.9958983802787428, + "FN": 73, + "FP": 123, + "IoU": 0.991830269684465, + "TN": 80457, + "TP": 23795, + "n_pred": 23918, + "n_ref": 23868 + }, + "4": { + "Dice": 0.8154563624250499, + "FN": 204, + "FP": 73, + "IoU": 0.688413948256468, + "TN": 103559, + "TP": 612, + "n_pred": 685, + "n_ref": 816 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_1/validation/fish0107.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0107.png" + } + ] +} \ No newline at end of file diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/checkpoint_best.pth b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/checkpoint_best.pth new file mode 100644 index 0000000000000000000000000000000000000000..fcfe50ed540401b282649f8a906948745cd59e4d --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/checkpoint_best.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c86b917bafa94e81c6e26c3c722e806f95d01777e7fd2d0ddb85b4f43bb57fe +size 358700674 diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/checkpoint_final.pth b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/checkpoint_final.pth new file mode 100644 index 0000000000000000000000000000000000000000..fa35cf666800c073325da14deb316884aa0c70b9 --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/checkpoint_final.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bedf35631dc6c23135968801a7c7e03a905cf6307e7009bd1d105d54a28776d1 +size 358731694 diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/debug.json b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/debug.json new file mode 100644 index 0000000000000000000000000000000000000000..f8affd108ce0cd745d9073644b42f200a596086d --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/debug.json @@ -0,0 +1,53 @@ +{ + "_best_ema": "None", + "batch_size": "5", + "configuration_manager": "{'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 5, 'patch_size': [1024, 112], 'median_image_size_in_voxels': [1024.0, 102.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['ZScoreNormalization'], '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': 8, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 1], [2, 1], [2, 1]], 'n_conv_per_stage': [2, 2, 2, 2, 2, 2, 2, 2], 'n_conv_per_stage_decoder': [2, 2, 2, 2, 2, 2, 2], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}", + "configuration_name": "2d", + "cudnn_version": 90100, + "current_epoch": "0", + "dataloader_train": "", + "dataloader_train.generator": "", + "dataloader_train.num_processes": "12", + "dataloader_train.transform": "None", + "dataloader_val": "", + "dataloader_val.generator": "", + "dataloader_val.num_processes": "6", + "dataloader_val.transform": "None", + "dataset_json": "{'channel_names': {'0': '\u00b5OCT'}, 'labels': {'background': 0, 'Retina': 1, 'VCD': 2, 'lens': 3, 'cornea': 4}, 'numTraining': 108, 'file_ending': '.png'}", + "device": "cuda:0", + "disable_checkpointing": "False", + "enable_deep_supervision": "True", + "fold": "2", + "folder_with_segs_from_previous_stage": "None", + "gpu_name": "NVIDIA A100 80GB PCIe", + "grad_scaler": "", + "hostname": "hpc5", + "inference_allowed_mirroring_axes": "(0, 1)", + "initial_lr": "0.01", + "is_cascaded": "False", + "is_ddp": "False", + "label_manager": "", + "local_rank": "0", + "log_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/training_log_2025_10_30_21_00_00.txt", + "logger": "", + "loss": "DeepSupervisionWrapper(\n (loss): DC_and_CE_loss(\n (ce): RobustCrossEntropyLoss()\n (dc): OptimizedModule(\n (_orig_mod): MemoryEfficientSoftDiceLoss()\n )\n )\n)", + "lr_scheduler": "", + "my_init_kwargs": "{'plans': {'dataset_name': 'Dataset001_zebrafish', 'plans_name': 'nnUNetPlans', 'original_median_spacing_after_transp': [999.0, 1.0, 1.0], 'original_median_shape_after_transp': [1, 1024, 102], 'image_reader_writer': 'NaturalImage2DIO', 'transpose_forward': [0, 1, 2], 'transpose_backward': [0, 1, 2], 'configurations': {'2d': {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 5, 'patch_size': [1024, 112], 'median_image_size_in_voxels': [1024.0, 102.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['ZScoreNormalization'], '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': 8, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 1], [2, 1], [2, 1]], 'n_conv_per_stage': [2, 2, 2, 2, 2, 2, 2, 2], 'n_conv_per_stage_decoder': [2, 2, 2, 2, 2, 2, 2], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}}, 'experiment_planner_used': 'ExperimentPlanner', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 255.0, 'mean': 49.659568786621094, 'median': 45.0, 'min': 0.0, 'percentile_00_5': 10.0, 'percentile_99_5': 163.0, 'std': 24.689043045043945}}}, 'configuration': '2d', 'fold': 2, 'dataset_json': {'channel_names': {'0': '\u00b5OCT'}, 'labels': {'background': 0, 'Retina': 1, 'VCD': 2, 'lens': 3, 'cornea': 4}, 'numTraining': 108, 'file_ending': '.png'}, 'device': device(type='cuda')}", + "network": "OptimizedModule", + "num_epochs": "1000", + "num_input_channels": "1", + "num_iterations_per_epoch": "250", + "num_val_iterations_per_epoch": "50", + "optimizer": "SGD (\nParameter Group 0\n dampening: 0\n differentiable: False\n foreach: None\n fused: None\n initial_lr: 0.01\n lr: 0.01\n maximize: False\n momentum: 0.99\n nesterov: True\n weight_decay: 3e-05\n)", + "output_folder": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2", + "output_folder_base": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d", + "oversample_foreground_percent": "0.33", + "plans_manager": "{'dataset_name': 'Dataset001_zebrafish', 'plans_name': 'nnUNetPlans', 'original_median_spacing_after_transp': [999.0, 1.0, 1.0], 'original_median_shape_after_transp': [1, 1024, 102], 'image_reader_writer': 'NaturalImage2DIO', 'transpose_forward': [0, 1, 2], 'transpose_backward': [0, 1, 2], 'configurations': {'2d': {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 5, 'patch_size': [1024, 112], 'median_image_size_in_voxels': [1024.0, 102.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['ZScoreNormalization'], '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': 8, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 1], [2, 1], [2, 1]], 'n_conv_per_stage': [2, 2, 2, 2, 2, 2, 2, 2], 'n_conv_per_stage_decoder': [2, 2, 2, 2, 2, 2, 2], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}}, 'experiment_planner_used': 'ExperimentPlanner', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 255.0, 'mean': 49.659568786621094, 'median': 45.0, 'min': 0.0, 'percentile_00_5': 10.0, 'percentile_99_5': 163.0, 'std': 24.689043045043945}}}", + "preprocessed_dataset_folder": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/nnUNetPlans_2d", + "preprocessed_dataset_folder_base": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish", + "probabilistic_oversampling": "False", + "save_every": "50", + "torch_version": "2.5.1+cu121", + "was_initialized": "True", + "weight_decay": "3e-05" +} \ No newline at end of file diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/progress.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/progress.png new file mode 100644 index 0000000000000000000000000000000000000000..6aecbbd5b7e097dedd1bc098432a0870af70d57a --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/progress.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:700088e8642f44d7c670b663111e485477c061240b2151f5d8c2d3273e4d96cd +size 823156 diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/training_log_2025_10_30_21_00_00.txt b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/training_log_2025_10_30_21_00_00.txt new file mode 100644 index 0000000000000000000000000000000000000000..b95d566d3e55b99defa208b12e3e0b6c53ee837d --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/training_log_2025_10_30_21_00_00.txt @@ -0,0 +1,7141 @@ + +####################################################################### +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. +####################################################################### + +2025-10-30 21:00:03.121590: Using torch.compile... +2025-10-30 21:00:04.241220: do_dummy_2d_data_aug: False +2025-10-30 21:00:04.243431: Using splits from existing split file: /hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/splits_final.json +2025-10-30 21:00:04.245444: The split file contains 5 splits. +2025-10-30 21:00:04.247089: Desired fold for training: 2 +2025-10-30 21:00:04.249287: This split has 86 training and 22 validation cases. + +This is the configuration used by this training: +Configuration name: 2d + {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 5, 'patch_size': [1024, 112], 'median_image_size_in_voxels': [1024.0, 102.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['ZScoreNormalization'], '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': 8, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 1], [2, 1], [2, 1]], 'n_conv_per_stage': [2, 2, 2, 2, 2, 2, 2, 2], 'n_conv_per_stage_decoder': [2, 2, 2, 2, 2, 2, 2], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True} + +These are the global plan.json settings: + {'dataset_name': 'Dataset001_zebrafish', 'plans_name': 'nnUNetPlans', 'original_median_spacing_after_transp': [999.0, 1.0, 1.0], 'original_median_shape_after_transp': [1, 1024, 102], 'image_reader_writer': 'NaturalImage2DIO', 'transpose_forward': [0, 1, 2], 'transpose_backward': [0, 1, 2], 'experiment_planner_used': 'ExperimentPlanner', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 255.0, 'mean': 49.659568786621094, 'median': 45.0, 'min': 0.0, 'percentile_00_5': 10.0, 'percentile_99_5': 163.0, 'std': 24.689043045043945}}} + +2025-10-30 21:00:06.272042: Unable to plot network architecture: nnUNet_compile is enabled! +2025-10-30 21:00:06.300321: +2025-10-30 21:00:06.310092: Epoch 0 +2025-10-30 21:00:06.315815: Current learning rate: 0.01 +2025-10-30 21:01:04.173638: train_loss -0.2236 +2025-10-30 21:01:04.177652: val_loss -0.7944 +2025-10-30 21:01:04.179465: Pseudo dice [np.float32(0.9497), np.float32(0.9718), np.float32(0.9762), np.float32(0.6202)] +2025-10-30 21:01:04.181296: Epoch time: 57.88 s +2025-10-30 21:01:04.182914: Yayy! New best EMA pseudo Dice: 0.8794999718666077 +2025-10-30 21:01:06.844146: +2025-10-30 21:01:06.846061: Epoch 1 +2025-10-30 21:01:06.848216: Current learning rate: 0.00999 +2025-10-30 21:01:27.259259: train_loss -0.8403 +2025-10-30 21:01:27.261255: val_loss -0.8776 +2025-10-30 21:01:27.262992: Pseudo dice [np.float32(0.9674), np.float32(0.9809), np.float32(0.9895), np.float32(0.7864)] +2025-10-30 21:01:27.264919: Epoch time: 20.42 s +2025-10-30 21:01:27.267492: Yayy! New best EMA pseudo Dice: 0.8845999836921692 +2025-10-30 21:01:29.634150: +2025-10-30 21:01:29.636263: Epoch 2 +2025-10-30 21:01:29.638103: Current learning rate: 0.00998 +2025-10-30 21:01:50.065223: train_loss -0.8828 +2025-10-30 21:01:50.067637: val_loss -0.8968 +2025-10-30 21:01:50.069825: Pseudo dice [np.float32(0.9742), np.float32(0.9864), np.float32(0.9905), np.float32(0.7926)] +2025-10-30 21:01:50.071946: Epoch time: 20.43 s +2025-10-30 21:01:50.074336: Yayy! New best EMA pseudo Dice: 0.8898000121116638 +2025-10-30 21:01:52.580765: +2025-10-30 21:01:52.584439: Epoch 3 +2025-10-30 21:01:52.586009: Current learning rate: 0.00997 +2025-10-30 21:02:12.851091: train_loss -0.8832 +2025-10-30 21:02:12.853860: val_loss -0.8943 +2025-10-30 21:02:12.855376: Pseudo dice [np.float32(0.9726), np.float32(0.9831), np.float32(0.9911), np.float32(0.7942)] +2025-10-30 21:02:12.857080: Epoch time: 20.27 s +2025-10-30 21:02:12.858562: Yayy! New best EMA pseudo Dice: 0.8942999839782715 +2025-10-30 21:02:15.356299: +2025-10-30 21:02:15.359687: Epoch 4 +2025-10-30 21:02:15.361284: Current learning rate: 0.00996 +2025-10-30 21:02:35.761598: train_loss -0.8994 +2025-10-30 21:02:35.763928: val_loss -0.9124 +2025-10-30 21:02:35.766052: Pseudo dice [np.float32(0.9776), np.float32(0.9896), np.float32(0.9942), np.float32(0.8123)] +2025-10-30 21:02:35.767560: Epoch time: 20.41 s +2025-10-30 21:02:35.769016: Yayy! New best EMA pseudo Dice: 0.8992000222206116 +2025-10-30 21:02:38.700280: +2025-10-30 21:02:38.702230: Epoch 5 +2025-10-30 21:02:38.704039: Current learning rate: 0.00995 +2025-10-30 21:02:59.170249: train_loss -0.9115 +2025-10-30 21:02:59.172956: val_loss -0.9076 +2025-10-30 21:02:59.176837: Pseudo dice [np.float32(0.9792), np.float32(0.9841), np.float32(0.991), np.float32(0.8148)] +2025-10-30 21:02:59.179291: Epoch time: 20.47 s +2025-10-30 21:02:59.181787: Yayy! New best EMA pseudo Dice: 0.9035000205039978 +2025-10-30 21:03:01.984485: +2025-10-30 21:03:01.987577: Epoch 6 +2025-10-30 21:03:01.990232: Current learning rate: 0.00995 +2025-10-30 21:03:20.902470: train_loss -0.9186 +2025-10-30 21:03:20.905485: val_loss -0.8983 +2025-10-30 21:03:20.907267: Pseudo dice [np.float32(0.9774), np.float32(0.982), np.float32(0.989), np.float32(0.8139)] +2025-10-30 21:03:20.908935: Epoch time: 18.92 s +2025-10-30 21:03:20.910589: Yayy! New best EMA pseudo Dice: 0.9071999788284302 +2025-10-30 21:03:23.951793: +2025-10-30 21:03:23.956879: Epoch 7 +2025-10-30 21:03:23.961546: Current learning rate: 0.00994 +2025-10-30 21:03:44.737229: train_loss -0.9007 +2025-10-30 21:03:44.740236: val_loss -0.8951 +2025-10-30 21:03:44.742419: Pseudo dice [np.float32(0.9777), np.float32(0.9875), np.float32(0.9914), np.float32(0.7812)] +2025-10-30 21:03:44.744242: Epoch time: 20.79 s +2025-10-30 21:03:44.746029: Yayy! New best EMA pseudo Dice: 0.9100000262260437 +2025-10-30 21:03:47.463431: +2025-10-30 21:03:47.465479: Epoch 8 +2025-10-30 21:03:47.467227: Current learning rate: 0.00993 +2025-10-30 21:04:07.882126: train_loss -0.9228 +2025-10-30 21:04:07.884313: val_loss -0.8982 +2025-10-30 21:04:07.886280: Pseudo dice [np.float32(0.9805), np.float32(0.989), np.float32(0.9921), np.float32(0.7671)] +2025-10-30 21:04:07.887872: Epoch time: 20.42 s +2025-10-30 21:04:07.889331: Yayy! New best EMA pseudo Dice: 0.9121999740600586 +2025-10-30 21:04:10.421216: +2025-10-30 21:04:10.423679: Epoch 9 +2025-10-30 21:04:10.426687: Current learning rate: 0.00992 +2025-10-30 21:04:31.356751: train_loss -0.9233 +2025-10-30 21:04:31.360334: val_loss -0.8974 +2025-10-30 21:04:31.362433: Pseudo dice [np.float32(0.9816), np.float32(0.9854), np.float32(0.9903), np.float32(0.7781)] +2025-10-30 21:04:31.364456: Epoch time: 20.94 s +2025-10-30 21:04:31.366390: Yayy! New best EMA pseudo Dice: 0.9143000245094299 +2025-10-30 21:04:34.664456: +2025-10-30 21:04:34.666822: Epoch 10 +2025-10-30 21:04:34.669145: Current learning rate: 0.00991 +2025-10-30 21:04:55.427185: train_loss -0.9296 +2025-10-30 21:04:55.429836: val_loss -0.9156 +2025-10-30 21:04:55.432675: Pseudo dice [np.float32(0.9815), np.float32(0.9897), np.float32(0.9941), np.float32(0.8109)] +2025-10-30 21:04:55.434952: Epoch time: 20.76 s +2025-10-30 21:04:55.437223: Yayy! New best EMA pseudo Dice: 0.9172999858856201 +2025-10-30 21:04:58.156534: +2025-10-30 21:04:58.158561: Epoch 11 +2025-10-30 21:04:58.160357: Current learning rate: 0.0099 +2025-10-30 21:05:17.911638: train_loss -0.9345 +2025-10-30 21:05:17.914894: val_loss -0.9101 +2025-10-30 21:05:17.917110: Pseudo dice [np.float32(0.9817), np.float32(0.9904), np.float32(0.9917), np.float32(0.796)] +2025-10-30 21:05:17.919474: Epoch time: 19.76 s +2025-10-30 21:05:17.922283: Yayy! New best EMA pseudo Dice: 0.9196000099182129 +2025-10-30 21:05:20.557568: +2025-10-30 21:05:20.559669: Epoch 12 +2025-10-30 21:05:20.564054: Current learning rate: 0.00989 +2025-10-30 21:05:40.358946: train_loss -0.9389 +2025-10-30 21:05:40.362132: val_loss -0.9123 +2025-10-30 21:05:40.364162: Pseudo dice [np.float32(0.9809), np.float32(0.9899), np.float32(0.9943), np.float32(0.7994)] +2025-10-30 21:05:40.366115: Epoch time: 19.8 s +2025-10-30 21:05:40.368090: Yayy! New best EMA pseudo Dice: 0.9217000007629395 +2025-10-30 21:05:42.895002: +2025-10-30 21:05:42.898237: Epoch 13 +2025-10-30 21:05:42.903642: Current learning rate: 0.00988 +2025-10-30 21:06:03.705719: train_loss -0.9409 +2025-10-30 21:06:03.709028: val_loss -0.9159 +2025-10-30 21:06:03.711270: Pseudo dice [np.float32(0.9836), np.float32(0.9909), np.float32(0.9944), np.float32(0.8083)] +2025-10-30 21:06:03.713464: Epoch time: 20.81 s +2025-10-30 21:06:03.716032: Yayy! New best EMA pseudo Dice: 0.9240000247955322 +2025-10-30 21:06:06.543795: +2025-10-30 21:06:06.549871: Epoch 14 +2025-10-30 21:06:06.554747: Current learning rate: 0.00987 +2025-10-30 21:06:26.905688: train_loss -0.9428 +2025-10-30 21:06:26.910547: val_loss -0.9128 +2025-10-30 21:06:26.912248: Pseudo dice [np.float32(0.9826), np.float32(0.9909), np.float32(0.9943), np.float32(0.8015)] +2025-10-30 21:06:26.913749: Epoch time: 20.36 s +2025-10-30 21:06:26.915460: Yayy! New best EMA pseudo Dice: 0.9258000254631042 +2025-10-30 21:06:29.549504: +2025-10-30 21:06:29.552996: Epoch 15 +2025-10-30 21:06:29.555546: Current learning rate: 0.00986 +2025-10-30 21:06:50.146786: train_loss -0.9459 +2025-10-30 21:06:50.149941: val_loss -0.9074 +2025-10-30 21:06:50.152327: Pseudo dice [np.float32(0.9825), np.float32(0.9898), np.float32(0.991), np.float32(0.8042)] +2025-10-30 21:06:50.154294: Epoch time: 20.6 s +2025-10-30 21:06:50.156008: Yayy! New best EMA pseudo Dice: 0.9273999929428101 +2025-10-30 21:06:52.618991: +2025-10-30 21:06:52.622108: Epoch 16 +2025-10-30 21:06:52.625157: Current learning rate: 0.00986 +2025-10-30 21:07:13.473121: train_loss -0.9484 +2025-10-30 21:07:13.482184: val_loss -0.9047 +2025-10-30 21:07:13.487645: Pseudo dice [np.float32(0.9814), np.float32(0.9903), np.float32(0.9932), np.float32(0.7876)] +2025-10-30 21:07:13.491021: Epoch time: 20.86 s +2025-10-30 21:07:13.493411: Yayy! New best EMA pseudo Dice: 0.9284999966621399 +2025-10-30 21:07:16.118423: +2025-10-30 21:07:16.122313: Epoch 17 +2025-10-30 21:07:16.126713: Current learning rate: 0.00985 +2025-10-30 21:07:35.799592: train_loss -0.9504 +2025-10-30 21:07:35.802333: val_loss -0.9122 +2025-10-30 21:07:35.804564: Pseudo dice [np.float32(0.9837), np.float32(0.9897), np.float32(0.9941), np.float32(0.8078)] +2025-10-30 21:07:35.806828: Epoch time: 19.68 s +2025-10-30 21:07:35.809653: Yayy! New best EMA pseudo Dice: 0.9300000071525574 +2025-10-30 21:07:38.476267: +2025-10-30 21:07:38.479971: Epoch 18 +2025-10-30 21:07:38.482458: Current learning rate: 0.00984 +2025-10-30 21:07:58.046946: train_loss -0.9518 +2025-10-30 21:07:58.051205: val_loss -0.9039 +2025-10-30 21:07:58.052827: Pseudo dice [np.float32(0.9811), np.float32(0.9887), np.float32(0.9929), np.float32(0.7848)] +2025-10-30 21:07:58.054953: Epoch time: 19.57 s +2025-10-30 21:07:58.056636: Yayy! New best EMA pseudo Dice: 0.9307000041007996 +2025-10-30 21:08:01.414822: +2025-10-30 21:08:01.418812: Epoch 19 +2025-10-30 21:08:01.420980: Current learning rate: 0.00983 +2025-10-30 21:08:22.151012: train_loss -0.9544 +2025-10-30 21:08:22.159168: val_loss -0.9059 +2025-10-30 21:08:22.164576: Pseudo dice [np.float32(0.9806), np.float32(0.99), np.float32(0.9947), np.float32(0.7882)] +2025-10-30 21:08:22.171181: Epoch time: 20.74 s +2025-10-30 21:08:22.175941: Yayy! New best EMA pseudo Dice: 0.9315000176429749 +2025-10-30 21:08:24.867616: +2025-10-30 21:08:24.870929: Epoch 20 +2025-10-30 21:08:24.875289: Current learning rate: 0.00982 +2025-10-30 21:08:45.237113: train_loss -0.9563 +2025-10-30 21:08:45.239379: val_loss -0.9106 +2025-10-30 21:08:45.241192: Pseudo dice [np.float32(0.9826), np.float32(0.9891), np.float32(0.9938), np.float32(0.7997)] +2025-10-30 21:08:45.242847: Epoch time: 20.37 s +2025-10-30 21:08:45.245833: Yayy! New best EMA pseudo Dice: 0.9325000047683716 +2025-10-30 21:08:47.899807: +2025-10-30 21:08:47.902313: Epoch 21 +2025-10-30 21:08:47.905867: Current learning rate: 0.00981 +2025-10-30 21:09:10.759542: train_loss -0.9528 +2025-10-30 21:09:10.774586: val_loss -0.9076 +2025-10-30 21:09:10.777244: Pseudo dice [np.float32(0.9822), np.float32(0.9898), np.float32(0.9941), np.float32(0.7859)] +2025-10-30 21:09:10.780755: Epoch time: 22.86 s +2025-10-30 21:09:10.788782: Yayy! New best EMA pseudo Dice: 0.9330000281333923 +2025-10-30 21:09:13.434123: +2025-10-30 21:09:13.438888: Epoch 22 +2025-10-30 21:09:13.443362: Current learning rate: 0.0098 +2025-10-30 21:09:33.744293: train_loss -0.9468 +2025-10-30 21:09:33.748570: val_loss -0.895 +2025-10-30 21:09:33.751508: Pseudo dice [np.float32(0.978), np.float32(0.9811), np.float32(0.99), np.float32(0.7852)] +2025-10-30 21:09:33.753757: Epoch time: 20.31 s +2025-10-30 21:09:33.755870: Yayy! New best EMA pseudo Dice: 0.9330999851226807 +2025-10-30 21:09:36.100173: +2025-10-30 21:09:36.102246: Epoch 23 +2025-10-30 21:09:36.104286: Current learning rate: 0.00979 +2025-10-30 21:09:55.886504: train_loss -0.9137 +2025-10-30 21:09:55.888713: val_loss -0.9065 +2025-10-30 21:09:55.890358: Pseudo dice [np.float32(0.9836), np.float32(0.9905), np.float32(0.9879), np.float32(0.8167)] +2025-10-30 21:09:55.891735: Epoch time: 19.79 s +2025-10-30 21:09:55.893136: Yayy! New best EMA pseudo Dice: 0.9341999888420105 +2025-10-30 21:09:58.682591: +2025-10-30 21:09:58.684633: Epoch 24 +2025-10-30 21:09:58.686787: Current learning rate: 0.00978 +2025-10-30 21:10:19.073582: train_loss -0.9353 +2025-10-30 21:10:19.076876: val_loss -0.9197 +2025-10-30 21:10:19.078552: Pseudo dice [np.float32(0.9835), np.float32(0.9909), np.float32(0.9946), np.float32(0.8173)] +2025-10-30 21:10:19.080766: Epoch time: 20.39 s +2025-10-30 21:10:19.083154: Yayy! New best EMA pseudo Dice: 0.9355000257492065 +2025-10-30 21:10:22.115283: +2025-10-30 21:10:22.117332: Epoch 25 +2025-10-30 21:10:22.119128: Current learning rate: 0.00977 +2025-10-30 21:10:42.469980: train_loss -0.9433 +2025-10-30 21:10:42.472440: val_loss -0.8981 +2025-10-30 21:10:42.474166: Pseudo dice [np.float32(0.9813), np.float32(0.9897), np.float32(0.9936), np.float32(0.762)] +2025-10-30 21:10:42.476017: Epoch time: 20.36 s +2025-10-30 21:10:43.535664: +2025-10-30 21:10:43.538396: Epoch 26 +2025-10-30 21:10:43.540490: Current learning rate: 0.00977 +2025-10-30 21:11:04.161289: train_loss -0.9474 +2025-10-30 21:11:04.163718: val_loss -0.9189 +2025-10-30 21:11:04.165799: Pseudo dice [np.float32(0.9825), np.float32(0.9909), np.float32(0.9948), np.float32(0.8181)] +2025-10-30 21:11:04.167454: Epoch time: 20.63 s +2025-10-30 21:11:04.168861: Yayy! New best EMA pseudo Dice: 0.9362000226974487 +2025-10-30 21:11:06.618379: +2025-10-30 21:11:06.620701: Epoch 27 +2025-10-30 21:11:06.622634: Current learning rate: 0.00976 +2025-10-30 21:11:27.251169: train_loss -0.9539 +2025-10-30 21:11:28.327514: val_loss -0.9115 +2025-10-30 21:11:28.329213: Pseudo dice [np.float32(0.9822), np.float32(0.9907), np.float32(0.9945), np.float32(0.7957)] +2025-10-30 21:11:28.330964: Epoch time: 20.63 s +2025-10-30 21:11:28.332832: Yayy! New best EMA pseudo Dice: 0.9366999864578247 +2025-10-30 21:11:30.845165: +2025-10-30 21:11:30.848603: Epoch 28 +2025-10-30 21:11:30.851940: Current learning rate: 0.00975 +2025-10-30 21:11:51.415983: train_loss -0.9566 +2025-10-30 21:11:51.426186: val_loss -0.9086 +2025-10-30 21:11:51.428371: Pseudo dice [np.float32(0.9823), np.float32(0.9893), np.float32(0.9947), np.float32(0.7928)] +2025-10-30 21:11:51.429826: Epoch time: 20.57 s +2025-10-30 21:11:51.431442: Yayy! New best EMA pseudo Dice: 0.9369999766349792 +2025-10-30 21:11:53.886382: +2025-10-30 21:11:53.889906: Epoch 29 +2025-10-30 21:11:53.892387: Current learning rate: 0.00974 +2025-10-30 21:12:14.235655: train_loss -0.9588 +2025-10-30 21:12:14.241346: val_loss -0.913 +2025-10-30 21:12:14.246708: Pseudo dice [np.float32(0.9819), np.float32(0.9896), np.float32(0.9942), np.float32(0.8128)] +2025-10-30 21:12:14.253420: Epoch time: 20.35 s +2025-10-30 21:12:14.257639: Yayy! New best EMA pseudo Dice: 0.9377999901771545 +2025-10-30 21:12:16.749488: +2025-10-30 21:12:16.751329: Epoch 30 +2025-10-30 21:12:16.753429: Current learning rate: 0.00973 +2025-10-30 21:12:37.290421: train_loss -0.9556 +2025-10-30 21:12:37.296561: val_loss -0.909 +2025-10-30 21:12:37.300124: Pseudo dice [np.float32(0.9808), np.float32(0.99), np.float32(0.9947), np.float32(0.7992)] +2025-10-30 21:12:37.303347: Epoch time: 20.54 s +2025-10-30 21:12:37.306587: Yayy! New best EMA pseudo Dice: 0.9380999803543091 +2025-10-30 21:12:39.844044: +2025-10-30 21:12:39.847294: Epoch 31 +2025-10-30 21:12:39.849291: Current learning rate: 0.00972 +2025-10-30 21:12:59.271075: train_loss -0.9586 +2025-10-30 21:12:59.274983: val_loss -0.9105 +2025-10-30 21:12:59.283237: Pseudo dice [np.float32(0.9816), np.float32(0.9897), np.float32(0.9947), np.float32(0.802)] +2025-10-30 21:12:59.286693: Epoch time: 19.43 s +2025-10-30 21:12:59.289654: Yayy! New best EMA pseudo Dice: 0.9384999871253967 +2025-10-30 21:13:01.617854: +2025-10-30 21:13:01.620109: Epoch 32 +2025-10-30 21:13:01.621999: Current learning rate: 0.00971 +2025-10-30 21:13:22.818426: train_loss -0.9578 +2025-10-30 21:13:22.821811: val_loss -0.9134 +2025-10-30 21:13:22.823364: Pseudo dice [np.float32(0.9834), np.float32(0.9909), np.float32(0.9948), np.float32(0.8018)] +2025-10-30 21:13:22.825256: Epoch time: 21.2 s +2025-10-30 21:13:22.828254: Yayy! New best EMA pseudo Dice: 0.9388999938964844 +2025-10-30 21:13:25.424160: +2025-10-30 21:13:25.426686: Epoch 33 +2025-10-30 21:13:25.428966: Current learning rate: 0.0097 +2025-10-30 21:13:44.484013: train_loss -0.9628 +2025-10-30 21:13:44.504611: val_loss -0.9098 +2025-10-30 21:13:44.511820: Pseudo dice [np.float32(0.984), np.float32(0.9883), np.float32(0.9939), np.float32(0.8039)] +2025-10-30 21:13:44.518984: Epoch time: 19.06 s +2025-10-30 21:13:44.529852: Yayy! New best EMA pseudo Dice: 0.939300000667572 +2025-10-30 21:13:47.810314: +2025-10-30 21:13:47.818969: Epoch 34 +2025-10-30 21:13:47.827776: Current learning rate: 0.00969 +2025-10-30 21:14:06.832532: train_loss -0.9637 +2025-10-30 21:14:06.838428: val_loss -0.9067 +2025-10-30 21:14:06.842554: Pseudo dice [np.float32(0.9818), np.float32(0.9898), np.float32(0.9942), np.float32(0.8008)] +2025-10-30 21:14:06.844848: Epoch time: 19.02 s +2025-10-30 21:14:06.846813: Yayy! New best EMA pseudo Dice: 0.9394999742507935 +2025-10-30 21:14:09.259071: +2025-10-30 21:14:09.262001: Epoch 35 +2025-10-30 21:14:09.264359: Current learning rate: 0.00968 +2025-10-30 21:14:29.408966: train_loss -0.966 +2025-10-30 21:14:29.411262: val_loss -0.9072 +2025-10-30 21:14:29.412718: Pseudo dice [np.float32(0.9839), np.float32(0.9904), np.float32(0.9944), np.float32(0.7925)] +2025-10-30 21:14:29.414328: Epoch time: 20.15 s +2025-10-30 21:14:29.416334: Yayy! New best EMA pseudo Dice: 0.9395999908447266 +2025-10-30 21:14:31.730420: +2025-10-30 21:14:31.733622: Epoch 36 +2025-10-30 21:14:31.735473: Current learning rate: 0.00968 +2025-10-30 21:14:52.428176: train_loss -0.9641 +2025-10-30 21:14:52.430936: val_loss -0.9097 +2025-10-30 21:14:52.432614: Pseudo dice [np.float32(0.9823), np.float32(0.9901), np.float32(0.9943), np.float32(0.8042)] +2025-10-30 21:14:52.434639: Epoch time: 20.7 s +2025-10-30 21:14:52.436226: Yayy! New best EMA pseudo Dice: 0.9398999810218811 +2025-10-30 21:14:55.038183: +2025-10-30 21:14:55.040349: Epoch 37 +2025-10-30 21:14:55.042690: Current learning rate: 0.00967 +2025-10-30 21:15:14.298576: train_loss -0.9627 +2025-10-30 21:15:14.300858: val_loss -0.9045 +2025-10-30 21:15:14.302957: Pseudo dice [np.float32(0.9816), np.float32(0.991), np.float32(0.9948), np.float32(0.7881)] +2025-10-30 21:15:14.304439: Epoch time: 19.26 s +2025-10-30 21:15:15.418816: +2025-10-30 21:15:15.420916: Epoch 38 +2025-10-30 21:15:15.422561: Current learning rate: 0.00966 +2025-10-30 21:15:36.025138: train_loss -0.9652 +2025-10-30 21:15:36.027257: val_loss -0.9093 +2025-10-30 21:15:36.029037: Pseudo dice [np.float32(0.9819), np.float32(0.9903), np.float32(0.9947), np.float32(0.8023)] +2025-10-30 21:15:36.030816: Epoch time: 20.61 s +2025-10-30 21:15:36.032653: Yayy! New best EMA pseudo Dice: 0.9399999976158142 +2025-10-30 21:15:38.421925: +2025-10-30 21:15:38.424149: Epoch 39 +2025-10-30 21:15:38.425895: Current learning rate: 0.00965 +2025-10-30 21:15:58.978246: train_loss -0.9675 +2025-10-30 21:15:58.980980: val_loss -0.8975 +2025-10-30 21:15:58.982640: Pseudo dice [np.float32(0.9824), np.float32(0.9897), np.float32(0.994), np.float32(0.7716)] +2025-10-30 21:15:58.984871: Epoch time: 20.56 s +2025-10-30 21:16:00.177069: +2025-10-30 21:16:00.180271: Epoch 40 +2025-10-30 21:16:00.183279: Current learning rate: 0.00964 +2025-10-30 21:16:20.671004: train_loss -0.965 +2025-10-30 21:16:20.673641: val_loss -0.9063 +2025-10-30 21:16:20.675876: Pseudo dice [np.float32(0.9804), np.float32(0.9893), np.float32(0.9938), np.float32(0.8061)] +2025-10-30 21:16:20.677901: Epoch time: 20.5 s +2025-10-30 21:16:21.938215: +2025-10-30 21:16:21.940435: Epoch 41 +2025-10-30 21:16:21.943041: Current learning rate: 0.00963 +2025-10-30 21:16:41.751009: train_loss -0.9669 +2025-10-30 21:16:41.753406: val_loss -0.9052 +2025-10-30 21:16:41.755373: Pseudo dice [np.float32(0.982), np.float32(0.989), np.float32(0.9944), np.float32(0.797)] +2025-10-30 21:16:41.756964: Epoch time: 19.81 s +2025-10-30 21:16:43.256069: +2025-10-30 21:16:43.259645: Epoch 42 +2025-10-30 21:16:43.262049: Current learning rate: 0.00962 +2025-10-30 21:17:03.850626: train_loss -0.969 +2025-10-30 21:17:03.853882: val_loss -0.9032 +2025-10-30 21:17:03.856028: Pseudo dice [np.float32(0.9812), np.float32(0.9899), np.float32(0.9945), np.float32(0.7956)] +2025-10-30 21:17:03.857564: Epoch time: 20.6 s +2025-10-30 21:17:05.010537: +2025-10-30 21:17:05.012290: Epoch 43 +2025-10-30 21:17:05.014099: Current learning rate: 0.00961 +2025-10-30 21:17:25.319343: train_loss -0.971 +2025-10-30 21:17:25.322149: val_loss -0.9148 +2025-10-30 21:17:25.324512: Pseudo dice [np.float32(0.9805), np.float32(0.9903), np.float32(0.995), np.float32(0.8229)] +2025-10-30 21:17:25.326505: Epoch time: 20.31 s +2025-10-30 21:17:25.328712: Yayy! New best EMA pseudo Dice: 0.9405999779701233 +2025-10-30 21:17:27.486755: +2025-10-30 21:17:27.488790: Epoch 44 +2025-10-30 21:17:27.490503: Current learning rate: 0.0096 +2025-10-30 21:17:47.034292: train_loss -0.97 +2025-10-30 21:17:47.037221: val_loss -0.9077 +2025-10-30 21:17:47.040872: Pseudo dice [np.float32(0.9821), np.float32(0.9904), np.float32(0.9943), np.float32(0.809)] +2025-10-30 21:17:47.043273: Epoch time: 19.55 s +2025-10-30 21:17:47.045403: Yayy! New best EMA pseudo Dice: 0.9409999847412109 +2025-10-30 21:17:49.423782: +2025-10-30 21:17:49.425709: Epoch 45 +2025-10-30 21:17:49.427479: Current learning rate: 0.00959 +2025-10-30 21:18:10.059402: train_loss -0.9727 +2025-10-30 21:18:10.062215: val_loss -0.9064 +2025-10-30 21:18:10.063808: Pseudo dice [np.float32(0.9831), np.float32(0.9905), np.float32(0.9949), np.float32(0.7981)] +2025-10-30 21:18:10.065786: Epoch time: 20.64 s +2025-10-30 21:18:10.067429: Yayy! New best EMA pseudo Dice: 0.9409999847412109 +2025-10-30 21:18:12.386672: +2025-10-30 21:18:12.388957: Epoch 46 +2025-10-30 21:18:12.392151: Current learning rate: 0.00959 +2025-10-30 21:18:32.504362: train_loss -0.9715 +2025-10-30 21:18:32.514324: val_loss -0.9014 +2025-10-30 21:18:32.517522: Pseudo dice [np.float32(0.984), np.float32(0.9907), np.float32(0.9943), np.float32(0.7919)] +2025-10-30 21:18:32.519624: Epoch time: 20.12 s +2025-10-30 21:18:33.522563: +2025-10-30 21:18:33.525491: Epoch 47 +2025-10-30 21:18:33.527741: Current learning rate: 0.00958 +2025-10-30 21:18:53.235969: train_loss -0.9706 +2025-10-30 21:18:53.239516: val_loss -0.9034 +2025-10-30 21:18:53.242235: Pseudo dice [np.float32(0.9817), np.float32(0.9902), np.float32(0.9942), np.float32(0.7977)] +2025-10-30 21:18:53.244573: Epoch time: 19.72 s +2025-10-30 21:18:54.225809: +2025-10-30 21:18:54.227416: Epoch 48 +2025-10-30 21:18:54.229067: Current learning rate: 0.00957 +2025-10-30 21:19:14.848710: train_loss -0.97 +2025-10-30 21:19:14.851466: val_loss -0.904 +2025-10-30 21:19:14.853170: Pseudo dice [np.float32(0.9826), np.float32(0.9908), np.float32(0.9947), np.float32(0.7918)] +2025-10-30 21:19:14.854714: Epoch time: 20.62 s +2025-10-30 21:19:16.029284: +2025-10-30 21:19:16.033933: Epoch 49 +2025-10-30 21:19:16.038100: Current learning rate: 0.00956 +2025-10-30 21:19:36.653884: train_loss -0.9711 +2025-10-30 21:19:36.657037: val_loss -0.9088 +2025-10-30 21:19:36.659103: Pseudo dice [np.float32(0.9826), np.float32(0.9906), np.float32(0.9949), np.float32(0.8013)] +2025-10-30 21:19:36.661670: Epoch time: 20.63 s +2025-10-30 21:19:38.968280: +2025-10-30 21:19:38.973308: Epoch 50 +2025-10-30 21:19:38.976023: Current learning rate: 0.00955 +2025-10-30 21:19:57.872997: train_loss -0.9724 +2025-10-30 21:19:57.875149: val_loss -0.9062 +2025-10-30 21:19:57.876659: Pseudo dice [np.float32(0.9833), np.float32(0.9917), np.float32(0.9947), np.float32(0.7986)] +2025-10-30 21:19:57.878302: Epoch time: 18.91 s +2025-10-30 21:19:57.880140: Yayy! New best EMA pseudo Dice: 0.941100001335144 +2025-10-30 21:20:00.259992: +2025-10-30 21:20:00.262699: Epoch 51 +2025-10-30 21:20:00.265205: Current learning rate: 0.00954 +2025-10-30 21:20:20.903548: train_loss -0.9737 +2025-10-30 21:20:20.910440: val_loss -0.9093 +2025-10-30 21:20:20.911923: Pseudo dice [np.float32(0.9827), np.float32(0.9909), np.float32(0.9948), np.float32(0.8125)] +2025-10-30 21:20:20.913419: Epoch time: 20.65 s +2025-10-30 21:20:20.914979: Yayy! New best EMA pseudo Dice: 0.9415000081062317 +2025-10-30 21:20:23.463132: +2025-10-30 21:20:23.465830: Epoch 52 +2025-10-30 21:20:23.467665: Current learning rate: 0.00953 +2025-10-30 21:20:43.903085: train_loss -0.9713 +2025-10-30 21:20:43.905267: val_loss -0.9066 +2025-10-30 21:20:43.907039: Pseudo dice [np.float32(0.9832), np.float32(0.991), np.float32(0.9942), np.float32(0.7947)] +2025-10-30 21:20:43.908476: Epoch time: 20.44 s +2025-10-30 21:20:44.905157: +2025-10-30 21:20:44.907384: Epoch 53 +2025-10-30 21:20:44.909499: Current learning rate: 0.00952 +2025-10-30 21:21:04.197795: train_loss -0.9706 +2025-10-30 21:21:04.200800: val_loss -0.9054 +2025-10-30 21:21:04.202912: Pseudo dice [np.float32(0.9831), np.float32(0.9906), np.float32(0.9946), np.float32(0.7937)] +2025-10-30 21:21:04.204428: Epoch time: 19.29 s +2025-10-30 21:21:05.171478: +2025-10-30 21:21:05.173539: Epoch 54 +2025-10-30 21:21:05.175087: Current learning rate: 0.00951 +2025-10-30 21:21:25.679634: train_loss -0.9705 +2025-10-30 21:21:25.682261: val_loss -0.9068 +2025-10-30 21:21:25.684618: Pseudo dice [np.float32(0.9828), np.float32(0.9905), np.float32(0.9948), np.float32(0.8008)] +2025-10-30 21:21:25.686399: Epoch time: 20.51 s +2025-10-30 21:21:27.236636: +2025-10-30 21:21:27.239246: Epoch 55 +2025-10-30 21:21:27.241323: Current learning rate: 0.0095 +2025-10-30 21:21:47.792838: train_loss -0.9709 +2025-10-30 21:21:47.796258: val_loss -0.9079 +2025-10-30 21:21:47.799387: Pseudo dice [np.float32(0.9837), np.float32(0.9913), np.float32(0.995), np.float32(0.8082)] +2025-10-30 21:21:47.801713: Epoch time: 20.56 s +2025-10-30 21:21:47.805469: Yayy! New best EMA pseudo Dice: 0.9417999982833862 +2025-10-30 21:21:50.060905: +2025-10-30 21:21:50.062878: Epoch 56 +2025-10-30 21:21:50.064960: Current learning rate: 0.00949 +2025-10-30 21:22:10.517792: train_loss -0.9726 +2025-10-30 21:22:10.520150: val_loss -0.8978 +2025-10-30 21:22:10.523471: Pseudo dice [np.float32(0.9826), np.float32(0.9915), np.float32(0.9928), np.float32(0.7888)] +2025-10-30 21:22:10.526918: Epoch time: 20.46 s +2025-10-30 21:22:11.692873: +2025-10-30 21:22:11.698355: Epoch 57 +2025-10-30 21:22:11.702594: Current learning rate: 0.00949 +2025-10-30 21:22:31.199323: train_loss -0.9737 +2025-10-30 21:22:31.203178: val_loss -0.907 +2025-10-30 21:22:31.205013: Pseudo dice [np.float32(0.9827), np.float32(0.9913), np.float32(0.9948), np.float32(0.807)] +2025-10-30 21:22:31.207505: Epoch time: 19.51 s +2025-10-30 21:22:32.406116: +2025-10-30 21:22:32.408375: Epoch 58 +2025-10-30 21:22:32.410420: Current learning rate: 0.00948 +2025-10-30 21:22:53.003010: train_loss -0.9732 +2025-10-30 21:22:53.011261: val_loss -0.9034 +2025-10-30 21:22:53.013923: Pseudo dice [np.float32(0.9833), np.float32(0.9917), np.float32(0.9946), np.float32(0.7869)] +2025-10-30 21:22:53.016400: Epoch time: 20.6 s +2025-10-30 21:22:54.027618: +2025-10-30 21:22:54.029348: Epoch 59 +2025-10-30 21:22:54.030918: Current learning rate: 0.00947 +2025-10-30 21:23:13.886804: train_loss -0.9708 +2025-10-30 21:23:13.888956: val_loss -0.9074 +2025-10-30 21:23:13.890755: Pseudo dice [np.float32(0.9834), np.float32(0.9913), np.float32(0.9939), np.float32(0.8036)] +2025-10-30 21:23:13.892203: Epoch time: 19.86 s +2025-10-30 21:23:15.064797: +2025-10-30 21:23:15.066683: Epoch 60 +2025-10-30 21:23:15.068619: Current learning rate: 0.00946 +2025-10-30 21:23:35.856188: train_loss -0.9734 +2025-10-30 21:23:35.859266: val_loss -0.9066 +2025-10-30 21:23:35.861206: Pseudo dice [np.float32(0.9824), np.float32(0.9901), np.float32(0.9944), np.float32(0.8009)] +2025-10-30 21:23:35.863262: Epoch time: 20.79 s +2025-10-30 21:23:37.025347: +2025-10-30 21:23:37.027701: Epoch 61 +2025-10-30 21:23:37.030029: Current learning rate: 0.00945 +2025-10-30 21:23:57.397751: train_loss -0.9717 +2025-10-30 21:23:57.400990: val_loss -0.9082 +2025-10-30 21:23:57.402681: Pseudo dice [np.float32(0.9827), np.float32(0.9909), np.float32(0.9938), np.float32(0.807)] +2025-10-30 21:23:57.404439: Epoch time: 20.37 s +2025-10-30 21:23:57.406061: Yayy! New best EMA pseudo Dice: 0.9417999982833862 +2025-10-30 21:23:59.718359: +2025-10-30 21:23:59.720801: Epoch 62 +2025-10-30 21:23:59.722886: Current learning rate: 0.00944 +2025-10-30 21:24:20.174677: train_loss -0.9755 +2025-10-30 21:24:20.177197: val_loss -0.9162 +2025-10-30 21:24:20.179867: Pseudo dice [np.float32(0.9836), np.float32(0.9914), np.float32(0.9952), np.float32(0.8204)] +2025-10-30 21:24:20.182288: Epoch time: 20.46 s +2025-10-30 21:24:20.184590: Yayy! New best EMA pseudo Dice: 0.9423999786376953 +2025-10-30 21:24:22.493423: +2025-10-30 21:24:22.498449: Epoch 63 +2025-10-30 21:24:22.501328: Current learning rate: 0.00943 +2025-10-30 21:24:43.212033: train_loss -0.976 +2025-10-30 21:24:43.215374: val_loss -0.907 +2025-10-30 21:24:43.217395: Pseudo dice [np.float32(0.9826), np.float32(0.9904), np.float32(0.9949), np.float32(0.8028)] +2025-10-30 21:24:43.221739: Epoch time: 20.72 s +2025-10-30 21:24:43.223572: Yayy! New best EMA pseudo Dice: 0.9424999952316284 +2025-10-30 21:24:45.666695: +2025-10-30 21:24:45.668642: Epoch 64 +2025-10-30 21:24:45.670422: Current learning rate: 0.00942 +2025-10-30 21:25:04.825434: train_loss -0.9738 +2025-10-30 21:25:04.828306: val_loss -0.8976 +2025-10-30 21:25:04.829875: Pseudo dice [np.float32(0.9849), np.float32(0.991), np.float32(0.9943), np.float32(0.7754)] +2025-10-30 21:25:04.831706: Epoch time: 19.16 s +2025-10-30 21:25:05.858661: +2025-10-30 21:25:05.860553: Epoch 65 +2025-10-30 21:25:05.862216: Current learning rate: 0.00941 +2025-10-30 21:25:26.376575: train_loss -0.9731 +2025-10-30 21:25:26.382348: val_loss -0.9084 +2025-10-30 21:25:26.384151: Pseudo dice [np.float32(0.9817), np.float32(0.9902), np.float32(0.995), np.float32(0.8141)] +2025-10-30 21:25:26.386083: Epoch time: 20.52 s +2025-10-30 21:25:27.527209: +2025-10-30 21:25:27.529122: Epoch 66 +2025-10-30 21:25:27.531385: Current learning rate: 0.0094 +2025-10-30 21:25:46.757272: train_loss -0.9748 +2025-10-30 21:25:46.763299: val_loss -0.9116 +2025-10-30 21:25:46.771640: Pseudo dice [np.float32(0.9818), np.float32(0.99), np.float32(0.9946), np.float32(0.8223)] +2025-10-30 21:25:46.773210: Epoch time: 19.23 s +2025-10-30 21:25:46.774658: Yayy! New best EMA pseudo Dice: 0.9427000284194946 +2025-10-30 21:25:49.694382: +2025-10-30 21:25:49.696605: Epoch 67 +2025-10-30 21:25:49.698552: Current learning rate: 0.00939 +2025-10-30 21:26:10.068290: train_loss -0.9741 +2025-10-30 21:26:10.073512: val_loss -0.9085 +2025-10-30 21:26:10.078180: Pseudo dice [np.float32(0.9817), np.float32(0.9909), np.float32(0.9947), np.float32(0.8098)] +2025-10-30 21:26:10.080402: Epoch time: 20.38 s +2025-10-30 21:26:10.082660: Yayy! New best EMA pseudo Dice: 0.942799985408783 +2025-10-30 21:26:12.883268: +2025-10-30 21:26:12.886215: Epoch 68 +2025-10-30 21:26:12.888635: Current learning rate: 0.00939 +2025-10-30 21:26:33.542074: train_loss -0.9754 +2025-10-30 21:26:33.546407: val_loss -0.9061 +2025-10-30 21:26:33.548456: Pseudo dice [np.float32(0.9825), np.float32(0.9914), np.float32(0.9949), np.float32(0.8078)] +2025-10-30 21:26:33.552509: Epoch time: 20.66 s +2025-10-30 21:26:33.554481: Yayy! New best EMA pseudo Dice: 0.9430000185966492 +2025-10-30 21:26:36.202398: +2025-10-30 21:26:36.205173: Epoch 69 +2025-10-30 21:26:36.210498: Current learning rate: 0.00938 +2025-10-30 21:26:56.587210: train_loss -0.9743 +2025-10-30 21:26:56.590141: val_loss -0.9047 +2025-10-30 21:26:56.591806: Pseudo dice [np.float32(0.9842), np.float32(0.9916), np.float32(0.9947), np.float32(0.7903)] +2025-10-30 21:26:56.596352: Epoch time: 20.39 s +2025-10-30 21:26:57.749404: +2025-10-30 21:26:57.753537: Epoch 70 +2025-10-30 21:26:57.755947: Current learning rate: 0.00937 +2025-10-30 21:27:16.897614: train_loss -0.9755 +2025-10-30 21:27:16.912380: val_loss -0.8995 +2025-10-30 21:27:16.919576: Pseudo dice [np.float32(0.9834), np.float32(0.9913), np.float32(0.9948), np.float32(0.7849)] +2025-10-30 21:27:16.926282: Epoch time: 19.15 s +2025-10-30 21:27:17.939309: +2025-10-30 21:27:17.941139: Epoch 71 +2025-10-30 21:27:17.943018: Current learning rate: 0.00936 +2025-10-30 21:27:38.313102: train_loss -0.9761 +2025-10-30 21:27:38.315524: val_loss -0.901 +2025-10-30 21:27:38.317473: Pseudo dice [np.float32(0.9831), np.float32(0.9909), np.float32(0.9947), np.float32(0.7991)] +2025-10-30 21:27:38.321873: Epoch time: 20.38 s +2025-10-30 21:27:39.359444: +2025-10-30 21:27:39.361832: Epoch 72 +2025-10-30 21:27:39.363757: Current learning rate: 0.00935 +2025-10-30 21:27:58.801011: train_loss -0.9777 +2025-10-30 21:27:58.804207: val_loss -0.9091 +2025-10-30 21:27:58.809018: Pseudo dice [np.float32(0.9834), np.float32(0.9912), np.float32(0.9947), np.float32(0.8117)] +2025-10-30 21:27:58.810878: Epoch time: 19.44 s +2025-10-30 21:28:00.016177: +2025-10-30 21:28:00.018642: Epoch 73 +2025-10-30 21:28:00.021040: Current learning rate: 0.00934 +2025-10-30 21:28:20.301096: train_loss -0.9704 +2025-10-30 21:28:20.304013: val_loss -0.9038 +2025-10-30 21:28:20.306227: Pseudo dice [np.float32(0.9839), np.float32(0.9909), np.float32(0.9921), np.float32(0.8084)] +2025-10-30 21:28:20.309644: Epoch time: 20.29 s +2025-10-30 21:28:21.387811: +2025-10-30 21:28:21.390118: Epoch 74 +2025-10-30 21:28:21.393581: Current learning rate: 0.00933 +2025-10-30 21:28:42.325321: train_loss -0.9715 +2025-10-30 21:28:42.343329: val_loss -0.9087 +2025-10-30 21:28:42.347142: Pseudo dice [np.float32(0.9807), np.float32(0.9896), np.float32(0.9949), np.float32(0.8132)] +2025-10-30 21:28:42.349434: Epoch time: 20.94 s +2025-10-30 21:28:43.544134: +2025-10-30 21:28:43.549254: Epoch 75 +2025-10-30 21:28:43.551109: Current learning rate: 0.00932 +2025-10-30 21:29:04.109081: train_loss -0.9743 +2025-10-30 21:29:04.115974: val_loss -0.9049 +2025-10-30 21:29:04.119541: Pseudo dice [np.float32(0.9824), np.float32(0.9909), np.float32(0.9947), np.float32(0.7916)] +2025-10-30 21:29:04.125535: Epoch time: 20.57 s +2025-10-30 21:29:05.169546: +2025-10-30 21:29:05.173780: Epoch 76 +2025-10-30 21:29:05.176525: Current learning rate: 0.00931 +2025-10-30 21:29:25.481469: train_loss -0.9761 +2025-10-30 21:29:25.495265: val_loss -0.909 +2025-10-30 21:29:25.497510: Pseudo dice [np.float32(0.9823), np.float32(0.9912), np.float32(0.9949), np.float32(0.8118)] +2025-10-30 21:29:25.502950: Epoch time: 20.31 s +2025-10-30 21:29:26.600239: +2025-10-30 21:29:26.602211: Epoch 77 +2025-10-30 21:29:26.604328: Current learning rate: 0.0093 +2025-10-30 21:29:46.228546: train_loss -0.9773 +2025-10-30 21:29:46.244769: val_loss -0.906 +2025-10-30 21:29:46.249043: Pseudo dice [np.float32(0.9839), np.float32(0.9917), np.float32(0.9948), np.float32(0.8041)] +2025-10-30 21:29:46.251115: Epoch time: 19.63 s +2025-10-30 21:29:47.927059: +2025-10-30 21:29:47.929178: Epoch 78 +2025-10-30 21:29:47.931452: Current learning rate: 0.0093 +2025-10-30 21:30:07.213566: train_loss -0.9757 +2025-10-30 21:30:07.217530: val_loss -0.9079 +2025-10-30 21:30:07.222377: Pseudo dice [np.float32(0.9843), np.float32(0.9921), np.float32(0.9949), np.float32(0.81)] +2025-10-30 21:30:07.224554: Epoch time: 19.29 s +2025-10-30 21:30:07.226441: Yayy! New best EMA pseudo Dice: 0.9430999755859375 +2025-10-30 21:30:09.662807: +2025-10-30 21:30:09.665185: Epoch 79 +2025-10-30 21:30:09.667085: Current learning rate: 0.00929 +2025-10-30 21:30:30.026257: train_loss -0.9768 +2025-10-30 21:30:30.028912: val_loss -0.9106 +2025-10-30 21:30:30.033722: Pseudo dice [np.float32(0.9832), np.float32(0.9917), np.float32(0.9948), np.float32(0.8069)] +2025-10-30 21:30:30.035894: Epoch time: 20.37 s +2025-10-30 21:30:30.037754: Yayy! New best EMA pseudo Dice: 0.9431999921798706 +2025-10-30 21:30:32.642126: +2025-10-30 21:30:32.647767: Epoch 80 +2025-10-30 21:30:32.650153: Current learning rate: 0.00928 +2025-10-30 21:30:53.073880: train_loss -0.9776 +2025-10-30 21:30:53.086163: val_loss -0.903 +2025-10-30 21:30:53.091455: Pseudo dice [np.float32(0.9832), np.float32(0.9916), np.float32(0.9935), np.float32(0.8003)] +2025-10-30 21:30:53.094671: Epoch time: 20.43 s +2025-10-30 21:30:54.362063: +2025-10-30 21:30:54.364000: Epoch 81 +2025-10-30 21:30:54.365869: Current learning rate: 0.00927 +2025-10-30 21:31:15.190428: train_loss -0.9767 +2025-10-30 21:31:15.196084: val_loss -0.901 +2025-10-30 21:31:15.199164: Pseudo dice [np.float32(0.982), np.float32(0.9912), np.float32(0.9947), np.float32(0.7933)] +2025-10-30 21:31:15.204560: Epoch time: 20.83 s +2025-10-30 21:31:17.803858: +2025-10-30 21:31:17.807633: Epoch 82 +2025-10-30 21:31:17.809281: Current learning rate: 0.00926 +2025-10-30 21:31:38.266592: train_loss -0.9781 +2025-10-30 21:31:38.272185: val_loss -0.9077 +2025-10-30 21:31:38.274998: Pseudo dice [np.float32(0.985), np.float32(0.9918), np.float32(0.9945), np.float32(0.8018)] +2025-10-30 21:31:38.278838: Epoch time: 20.46 s +2025-10-30 21:31:39.485700: +2025-10-30 21:31:39.489611: Epoch 83 +2025-10-30 21:31:39.492173: Current learning rate: 0.00925 +2025-10-30 21:31:59.683276: train_loss -0.9778 +2025-10-30 21:31:59.688910: val_loss -0.9082 +2025-10-30 21:31:59.690600: Pseudo dice [np.float32(0.9841), np.float32(0.9923), np.float32(0.9951), np.float32(0.8074)] +2025-10-30 21:31:59.692298: Epoch time: 20.2 s +2025-10-30 21:32:00.877115: +2025-10-30 21:32:00.879261: Epoch 84 +2025-10-30 21:32:00.881849: Current learning rate: 0.00924 +2025-10-30 21:32:18.790102: train_loss -0.9791 +2025-10-30 21:32:18.792742: val_loss -0.9032 +2025-10-30 21:32:18.794743: Pseudo dice [np.float32(0.9846), np.float32(0.9921), np.float32(0.9951), np.float32(0.8013)] +2025-10-30 21:32:18.796790: Epoch time: 17.92 s +2025-10-30 21:32:19.937765: +2025-10-30 21:32:19.941194: Epoch 85 +2025-10-30 21:32:19.943156: Current learning rate: 0.00923 +2025-10-30 21:32:40.414099: train_loss -0.9796 +2025-10-30 21:32:40.425214: val_loss -0.9019 +2025-10-30 21:32:40.427035: Pseudo dice [np.float32(0.9827), np.float32(0.9907), np.float32(0.9946), np.float32(0.7957)] +2025-10-30 21:32:40.428777: Epoch time: 20.48 s +2025-10-30 21:32:41.609450: +2025-10-30 21:32:41.611161: Epoch 86 +2025-10-30 21:32:41.612723: Current learning rate: 0.00922 +2025-10-30 21:33:01.910957: train_loss -0.9796 +2025-10-30 21:33:01.913430: val_loss -0.9065 +2025-10-30 21:33:01.915006: Pseudo dice [np.float32(0.9843), np.float32(0.9917), np.float32(0.9949), np.float32(0.8021)] +2025-10-30 21:33:01.916486: Epoch time: 20.3 s +2025-10-30 21:33:03.091302: +2025-10-30 21:33:03.092934: Epoch 87 +2025-10-30 21:33:03.094631: Current learning rate: 0.00921 +2025-10-30 21:33:23.293594: train_loss -0.9778 +2025-10-30 21:33:23.296431: val_loss -0.9065 +2025-10-30 21:33:23.298952: Pseudo dice [np.float32(0.9846), np.float32(0.9916), np.float32(0.9945), np.float32(0.8071)] +2025-10-30 21:33:23.300552: Epoch time: 20.2 s +2025-10-30 21:33:24.305508: +2025-10-30 21:33:24.307284: Epoch 88 +2025-10-30 21:33:24.308772: Current learning rate: 0.0092 +2025-10-30 21:33:44.954999: train_loss -0.9743 +2025-10-30 21:33:44.962412: val_loss -0.9051 +2025-10-30 21:33:44.966548: Pseudo dice [np.float32(0.9831), np.float32(0.9907), np.float32(0.9943), np.float32(0.7945)] +2025-10-30 21:33:44.968294: Epoch time: 20.65 s +2025-10-30 21:33:46.165771: +2025-10-30 21:33:46.167669: Epoch 89 +2025-10-30 21:33:46.169337: Current learning rate: 0.0092 +2025-10-30 21:34:06.592402: train_loss -0.9751 +2025-10-30 21:34:06.595242: val_loss -0.9058 +2025-10-30 21:34:06.597190: Pseudo dice [np.float32(0.9852), np.float32(0.9919), np.float32(0.9947), np.float32(0.8)] +2025-10-30 21:34:06.599263: Epoch time: 20.43 s +2025-10-30 21:34:08.512265: +2025-10-30 21:34:08.514316: Epoch 90 +2025-10-30 21:34:08.515932: Current learning rate: 0.00919 +2025-10-30 21:34:28.634413: train_loss -0.9766 +2025-10-30 21:34:28.637517: val_loss -0.9098 +2025-10-30 21:34:28.639139: Pseudo dice [np.float32(0.9831), np.float32(0.9912), np.float32(0.9947), np.float32(0.8101)] +2025-10-30 21:34:28.640966: Epoch time: 20.12 s +2025-10-30 21:34:32.585204: +2025-10-30 21:34:32.587425: Epoch 91 +2025-10-30 21:34:32.590037: Current learning rate: 0.00918 +2025-10-30 21:34:51.604136: train_loss -0.9788 +2025-10-30 21:34:51.606850: val_loss -0.9099 +2025-10-30 21:34:51.608681: Pseudo dice [np.float32(0.9832), np.float32(0.9915), np.float32(0.995), np.float32(0.8119)] +2025-10-30 21:34:51.610397: Epoch time: 19.02 s +2025-10-30 21:34:51.611855: Yayy! New best EMA pseudo Dice: 0.9433000087738037 +2025-10-30 21:34:54.165004: +2025-10-30 21:34:54.166895: Epoch 92 +2025-10-30 21:34:54.168504: Current learning rate: 0.00917 +2025-10-30 21:35:14.688721: train_loss -0.9809 +2025-10-30 21:35:14.690697: val_loss -0.9042 +2025-10-30 21:35:14.692273: Pseudo dice [np.float32(0.9842), np.float32(0.992), np.float32(0.9948), np.float32(0.806)] +2025-10-30 21:35:14.693664: Epoch time: 20.53 s +2025-10-30 21:35:14.695032: Yayy! New best EMA pseudo Dice: 0.9434000253677368 +2025-10-30 21:35:17.308888: +2025-10-30 21:35:17.310666: Epoch 93 +2025-10-30 21:35:17.312383: Current learning rate: 0.00916 +2025-10-30 21:35:38.651639: train_loss -0.9801 +2025-10-30 21:35:38.658493: val_loss -0.8877 +2025-10-30 21:35:38.660192: Pseudo dice [np.float32(0.9852), np.float32(0.9922), np.float32(0.9906), np.float32(0.802)] +2025-10-30 21:35:38.661885: Epoch time: 21.34 s +2025-10-30 21:35:39.845869: +2025-10-30 21:35:39.848136: Epoch 94 +2025-10-30 21:35:39.852064: Current learning rate: 0.00915 +2025-10-30 21:36:00.361360: train_loss -0.978 +2025-10-30 21:36:00.365861: val_loss -0.9043 +2025-10-30 21:36:00.368112: Pseudo dice [np.float32(0.9846), np.float32(0.9927), np.float32(0.9948), np.float32(0.7945)] +2025-10-30 21:36:00.369911: Epoch time: 20.52 s +2025-10-30 21:36:01.337655: +2025-10-30 21:36:01.339567: Epoch 95 +2025-10-30 21:36:01.341288: Current learning rate: 0.00914 +2025-10-30 21:36:21.733299: train_loss -0.9798 +2025-10-30 21:36:21.736000: val_loss -0.9062 +2025-10-30 21:36:21.738593: Pseudo dice [np.float32(0.9832), np.float32(0.9915), np.float32(0.9947), np.float32(0.8139)] +2025-10-30 21:36:21.740933: Epoch time: 20.4 s +2025-10-30 21:36:21.743475: Yayy! New best EMA pseudo Dice: 0.9434000253677368 +2025-10-30 21:36:25.630312: +2025-10-30 21:36:25.632370: Epoch 96 +2025-10-30 21:36:25.634588: Current learning rate: 0.00913 +2025-10-30 21:36:45.669872: train_loss -0.9808 +2025-10-30 21:36:45.677260: val_loss -0.9018 +2025-10-30 21:36:45.681002: Pseudo dice [np.float32(0.9834), np.float32(0.9919), np.float32(0.9947), np.float32(0.8026)] +2025-10-30 21:36:45.685667: Epoch time: 20.04 s +2025-10-30 21:36:46.906493: +2025-10-30 21:36:46.908858: Epoch 97 +2025-10-30 21:36:46.910702: Current learning rate: 0.00912 +2025-10-30 21:37:05.305147: train_loss -0.9796 +2025-10-30 21:37:05.311725: val_loss -0.901 +2025-10-30 21:37:05.313491: Pseudo dice [np.float32(0.9838), np.float32(0.9919), np.float32(0.9945), np.float32(0.8004)] +2025-10-30 21:37:05.315362: Epoch time: 18.4 s +2025-10-30 21:37:06.373996: +2025-10-30 21:37:06.376090: Epoch 98 +2025-10-30 21:37:06.378073: Current learning rate: 0.00911 +2025-10-30 21:37:26.610213: train_loss -0.9756 +2025-10-30 21:37:26.613542: val_loss -0.903 +2025-10-30 21:37:26.616525: Pseudo dice [np.float32(0.9849), np.float32(0.9921), np.float32(0.9946), np.float32(0.8024)] +2025-10-30 21:37:26.618809: Epoch time: 20.24 s +2025-10-30 21:37:27.819383: +2025-10-30 21:37:27.821433: Epoch 99 +2025-10-30 21:37:27.823202: Current learning rate: 0.0091 +2025-10-30 21:37:48.191099: train_loss -0.9791 +2025-10-30 21:37:48.194306: val_loss -0.8993 +2025-10-30 21:37:48.195983: Pseudo dice [np.float32(0.9833), np.float32(0.9917), np.float32(0.9933), np.float32(0.7955)] +2025-10-30 21:37:48.197653: Epoch time: 20.37 s +2025-10-30 21:37:50.444254: +2025-10-30 21:37:50.446600: Epoch 100 +2025-10-30 21:37:50.448524: Current learning rate: 0.0091 +2025-10-30 21:38:10.963855: train_loss -0.9745 +2025-10-30 21:38:10.967240: val_loss -0.91 +2025-10-30 21:38:10.969451: Pseudo dice [np.float32(0.9825), np.float32(0.9926), np.float32(0.9949), np.float32(0.8111)] +2025-10-30 21:38:10.972038: Epoch time: 20.52 s +2025-10-30 21:38:11.945164: +2025-10-30 21:38:11.947192: Epoch 101 +2025-10-30 21:38:11.949098: Current learning rate: 0.00909 +2025-10-30 21:38:32.259346: train_loss -0.9743 +2025-10-30 21:38:32.261585: val_loss -0.9083 +2025-10-30 21:38:32.263336: Pseudo dice [np.float32(0.9819), np.float32(0.9915), np.float32(0.9952), np.float32(0.8169)] +2025-10-30 21:38:32.264848: Epoch time: 20.32 s +2025-10-30 21:38:32.266282: Yayy! New best EMA pseudo Dice: 0.9435999989509583 +2025-10-30 21:38:34.993373: +2025-10-30 21:38:34.996928: Epoch 102 +2025-10-30 21:38:34.998653: Current learning rate: 0.00908 +2025-10-30 21:38:55.325854: train_loss -0.9722 +2025-10-30 21:38:55.329594: val_loss -0.9006 +2025-10-30 21:38:55.331468: Pseudo dice [np.float32(0.9838), np.float32(0.9905), np.float32(0.9939), np.float32(0.7781)] +2025-10-30 21:38:55.333119: Epoch time: 20.33 s +2025-10-30 21:38:56.462917: +2025-10-30 21:38:56.464836: Epoch 103 +2025-10-30 21:38:56.466997: Current learning rate: 0.00907 +2025-10-30 21:39:16.011530: train_loss -0.9635 +2025-10-30 21:39:16.013827: val_loss -0.905 +2025-10-30 21:39:16.015356: Pseudo dice [np.float32(0.9847), np.float32(0.9907), np.float32(0.9936), np.float32(0.7949)] +2025-10-30 21:39:16.016952: Epoch time: 19.55 s +2025-10-30 21:39:17.209332: +2025-10-30 21:39:17.212319: Epoch 104 +2025-10-30 21:39:17.214119: Current learning rate: 0.00906 +2025-10-30 21:39:36.482890: train_loss -0.9584 +2025-10-30 21:39:36.485387: val_loss -0.9094 +2025-10-30 21:39:36.487249: Pseudo dice [np.float32(0.9844), np.float32(0.991), np.float32(0.9944), np.float32(0.8019)] +2025-10-30 21:39:36.489374: Epoch time: 19.28 s +2025-10-30 21:39:37.742519: +2025-10-30 21:39:37.744478: Epoch 105 +2025-10-30 21:39:37.746398: Current learning rate: 0.00905 +2025-10-30 21:39:58.201700: train_loss -0.9665 +2025-10-30 21:39:58.208973: val_loss -0.9008 +2025-10-30 21:39:58.210947: Pseudo dice [np.float32(0.9843), np.float32(0.9914), np.float32(0.9909), np.float32(0.8156)] +2025-10-30 21:39:58.213096: Epoch time: 20.46 s +2025-10-30 21:39:59.204526: +2025-10-30 21:39:59.206300: Epoch 106 +2025-10-30 21:39:59.207880: Current learning rate: 0.00904 +2025-10-30 21:40:19.592396: train_loss -0.9732 +2025-10-30 21:40:19.595045: val_loss -0.9052 +2025-10-30 21:40:19.597259: Pseudo dice [np.float32(0.983), np.float32(0.9915), np.float32(0.9944), np.float32(0.7956)] +2025-10-30 21:40:19.599351: Epoch time: 20.39 s +2025-10-30 21:40:20.615640: +2025-10-30 21:40:20.617998: Epoch 107 +2025-10-30 21:40:20.619630: Current learning rate: 0.00903 +2025-10-30 21:40:41.008839: train_loss -0.9746 +2025-10-30 21:40:41.011237: val_loss -0.8958 +2025-10-30 21:40:41.012800: Pseudo dice [np.float32(0.9832), np.float32(0.9915), np.float32(0.9913), np.float32(0.7933)] +2025-10-30 21:40:41.015536: Epoch time: 20.39 s +2025-10-30 21:40:42.183707: +2025-10-30 21:40:42.185628: Epoch 108 +2025-10-30 21:40:42.188403: Current learning rate: 0.00902 +2025-10-30 21:41:02.530077: train_loss -0.9778 +2025-10-30 21:41:02.537550: val_loss -0.9057 +2025-10-30 21:41:02.540379: Pseudo dice [np.float32(0.9817), np.float32(0.9912), np.float32(0.9949), np.float32(0.8075)] +2025-10-30 21:41:02.542040: Epoch time: 20.35 s +2025-10-30 21:41:03.680699: +2025-10-30 21:41:03.682618: Epoch 109 +2025-10-30 21:41:03.684413: Current learning rate: 0.00901 +2025-10-30 21:41:23.292207: train_loss -0.9775 +2025-10-30 21:41:23.294615: val_loss -0.9043 +2025-10-30 21:41:23.296190: Pseudo dice [np.float32(0.9848), np.float32(0.9918), np.float32(0.9945), np.float32(0.7986)] +2025-10-30 21:41:23.297752: Epoch time: 19.61 s +2025-10-30 21:41:24.459529: +2025-10-30 21:41:24.461436: Epoch 110 +2025-10-30 21:41:24.463278: Current learning rate: 0.009 +2025-10-30 21:41:44.826342: train_loss -0.979 +2025-10-30 21:41:44.828965: val_loss -0.904 +2025-10-30 21:41:44.830783: Pseudo dice [np.float32(0.9863), np.float32(0.9929), np.float32(0.9948), np.float32(0.7945)] +2025-10-30 21:41:44.832534: Epoch time: 20.37 s +2025-10-30 21:41:45.969405: +2025-10-30 21:41:45.971402: Epoch 111 +2025-10-30 21:41:45.973256: Current learning rate: 0.009 +2025-10-30 21:42:05.016763: train_loss -0.9797 +2025-10-30 21:42:05.023060: val_loss -0.9016 +2025-10-30 21:42:05.028439: Pseudo dice [np.float32(0.9836), np.float32(0.992), np.float32(0.9947), np.float32(0.8028)] +2025-10-30 21:42:05.033026: Epoch time: 19.05 s +2025-10-30 21:42:06.028033: +2025-10-30 21:42:06.030147: Epoch 112 +2025-10-30 21:42:06.032113: Current learning rate: 0.00899 +2025-10-30 21:42:26.467074: train_loss -0.9797 +2025-10-30 21:42:26.470167: val_loss -0.905 +2025-10-30 21:42:26.471828: Pseudo dice [np.float32(0.9855), np.float32(0.992), np.float32(0.9938), np.float32(0.8098)] +2025-10-30 21:42:26.473886: Epoch time: 20.44 s +2025-10-30 21:42:27.636624: +2025-10-30 21:42:27.638790: Epoch 113 +2025-10-30 21:42:27.640509: Current learning rate: 0.00898 +2025-10-30 21:42:48.427937: train_loss -0.9786 +2025-10-30 21:42:48.430634: val_loss -0.8927 +2025-10-30 21:42:48.433323: Pseudo dice [np.float32(0.9827), np.float32(0.9918), np.float32(0.9929), np.float32(0.7927)] +2025-10-30 21:42:48.435642: Epoch time: 20.79 s +2025-10-30 21:42:49.658355: +2025-10-30 21:42:49.660381: Epoch 114 +2025-10-30 21:42:49.662395: Current learning rate: 0.00897 +2025-10-30 21:43:09.899044: train_loss -0.9782 +2025-10-30 21:43:09.901943: val_loss -0.9055 +2025-10-30 21:43:09.903744: Pseudo dice [np.float32(0.984), np.float32(0.9923), np.float32(0.9945), np.float32(0.8123)] +2025-10-30 21:43:09.905634: Epoch time: 20.24 s +2025-10-30 21:43:11.410149: +2025-10-30 21:43:11.413952: Epoch 115 +2025-10-30 21:43:11.416068: Current learning rate: 0.00896 +2025-10-30 21:43:31.815725: train_loss -0.9777 +2025-10-30 21:43:31.818616: val_loss -0.9021 +2025-10-30 21:43:31.820876: Pseudo dice [np.float32(0.984), np.float32(0.991), np.float32(0.9942), np.float32(0.8015)] +2025-10-30 21:43:31.822424: Epoch time: 20.41 s +2025-10-30 21:43:32.816924: +2025-10-30 21:43:32.818889: Epoch 116 +2025-10-30 21:43:32.820902: Current learning rate: 0.00895 +2025-10-30 21:43:52.171741: train_loss -0.9797 +2025-10-30 21:43:52.174904: val_loss -0.8969 +2025-10-30 21:43:52.176536: Pseudo dice [np.float32(0.9842), np.float32(0.992), np.float32(0.9945), np.float32(0.7953)] +2025-10-30 21:43:52.178162: Epoch time: 19.36 s +2025-10-30 21:43:53.232296: +2025-10-30 21:43:53.234653: Epoch 117 +2025-10-30 21:43:53.236518: Current learning rate: 0.00894 +2025-10-30 21:44:13.281833: train_loss -0.9803 +2025-10-30 21:44:13.297499: val_loss -0.9013 +2025-10-30 21:44:13.299193: Pseudo dice [np.float32(0.9831), np.float32(0.9923), np.float32(0.9949), np.float32(0.8046)] +2025-10-30 21:44:13.300853: Epoch time: 20.05 s +2025-10-30 21:44:14.333254: +2025-10-30 21:44:14.335113: Epoch 118 +2025-10-30 21:44:14.336790: Current learning rate: 0.00893 +2025-10-30 21:44:33.304276: train_loss -0.9819 +2025-10-30 21:44:33.306953: val_loss -0.9008 +2025-10-30 21:44:33.308816: Pseudo dice [np.float32(0.9833), np.float32(0.9926), np.float32(0.9938), np.float32(0.8042)] +2025-10-30 21:44:33.310631: Epoch time: 18.97 s +2025-10-30 21:44:34.399418: +2025-10-30 21:44:34.402066: Epoch 119 +2025-10-30 21:44:34.404074: Current learning rate: 0.00892 +2025-10-30 21:44:54.816417: train_loss -0.9811 +2025-10-30 21:44:54.818905: val_loss -0.9064 +2025-10-30 21:44:54.820868: Pseudo dice [np.float32(0.9846), np.float32(0.9923), np.float32(0.9949), np.float32(0.8138)] +2025-10-30 21:44:54.822658: Epoch time: 20.42 s +2025-10-30 21:44:56.059960: +2025-10-30 21:44:56.062161: Epoch 120 +2025-10-30 21:44:56.064075: Current learning rate: 0.00891 +2025-10-30 21:45:16.431351: train_loss -0.9801 +2025-10-30 21:45:16.436085: val_loss -0.897 +2025-10-30 21:45:16.437767: Pseudo dice [np.float32(0.9829), np.float32(0.9916), np.float32(0.9945), np.float32(0.7925)] +2025-10-30 21:45:16.439487: Epoch time: 20.37 s +2025-10-30 21:45:17.635133: +2025-10-30 21:45:17.637458: Epoch 121 +2025-10-30 21:45:17.639310: Current learning rate: 0.0089 +2025-10-30 21:45:38.077123: train_loss -0.9812 +2025-10-30 21:45:38.079669: val_loss -0.9058 +2025-10-30 21:45:38.081334: Pseudo dice [np.float32(0.9845), np.float32(0.9925), np.float32(0.9941), np.float32(0.8118)] +2025-10-30 21:45:38.083426: Epoch time: 20.44 s +2025-10-30 21:45:39.274217: +2025-10-30 21:45:39.277846: Epoch 122 +2025-10-30 21:45:39.279775: Current learning rate: 0.00889 +2025-10-30 21:45:58.763950: train_loss -0.9816 +2025-10-30 21:45:58.767831: val_loss -0.9021 +2025-10-30 21:45:58.771639: Pseudo dice [np.float32(0.9837), np.float32(0.9919), np.float32(0.9945), np.float32(0.7996)] +2025-10-30 21:45:58.776723: Epoch time: 19.49 s +2025-10-30 21:45:59.767280: +2025-10-30 21:45:59.769146: Epoch 123 +2025-10-30 21:45:59.771329: Current learning rate: 0.00889 +2025-10-30 21:46:20.346627: train_loss -0.9823 +2025-10-30 21:46:20.350064: val_loss -0.9034 +2025-10-30 21:46:20.351977: Pseudo dice [np.float32(0.9834), np.float32(0.9923), np.float32(0.9949), np.float32(0.7993)] +2025-10-30 21:46:20.353919: Epoch time: 20.58 s +2025-10-30 21:46:21.569220: +2025-10-30 21:46:21.571341: Epoch 124 +2025-10-30 21:46:21.573077: Current learning rate: 0.00888 +2025-10-30 21:46:41.559926: train_loss -0.9814 +2025-10-30 21:46:41.561980: val_loss -0.9025 +2025-10-30 21:46:41.563689: Pseudo dice [np.float32(0.9844), np.float32(0.9923), np.float32(0.9947), np.float32(0.8047)] +2025-10-30 21:46:41.565549: Epoch time: 19.99 s +2025-10-30 21:46:42.617053: +2025-10-30 21:46:42.619599: Epoch 125 +2025-10-30 21:46:42.621299: Current learning rate: 0.00887 +2025-10-30 21:47:02.714031: train_loss -0.9805 +2025-10-30 21:47:02.719799: val_loss -0.8968 +2025-10-30 21:47:02.722866: Pseudo dice [np.float32(0.9851), np.float32(0.9924), np.float32(0.9945), np.float32(0.7855)] +2025-10-30 21:47:02.727283: Epoch time: 20.1 s +2025-10-30 21:47:03.769872: +2025-10-30 21:47:03.775017: Epoch 126 +2025-10-30 21:47:03.779837: Current learning rate: 0.00886 +2025-10-30 21:47:24.387979: train_loss -0.9826 +2025-10-30 21:47:24.390408: val_loss -0.9017 +2025-10-30 21:47:24.391752: Pseudo dice [np.float32(0.9856), np.float32(0.9926), np.float32(0.9948), np.float32(0.7982)] +2025-10-30 21:47:24.393506: Epoch time: 20.62 s +2025-10-30 21:47:25.752169: +2025-10-30 21:47:25.756114: Epoch 127 +2025-10-30 21:47:25.758368: Current learning rate: 0.00885 +2025-10-30 21:47:46.198789: train_loss -0.9824 +2025-10-30 21:47:46.201332: val_loss -0.9054 +2025-10-30 21:47:46.203770: Pseudo dice [np.float32(0.9831), np.float32(0.992), np.float32(0.9952), np.float32(0.8171)] +2025-10-30 21:47:46.205916: Epoch time: 20.45 s +2025-10-30 21:47:47.243099: +2025-10-30 21:47:47.247313: Epoch 128 +2025-10-30 21:47:47.251272: Current learning rate: 0.00884 +2025-10-30 21:48:07.783058: train_loss -0.9833 +2025-10-30 21:48:07.786983: val_loss -0.8985 +2025-10-30 21:48:07.789351: Pseudo dice [np.float32(0.9853), np.float32(0.9921), np.float32(0.9946), np.float32(0.7944)] +2025-10-30 21:48:07.792268: Epoch time: 20.54 s +2025-10-30 21:48:09.070275: +2025-10-30 21:48:09.072328: Epoch 129 +2025-10-30 21:48:09.074111: Current learning rate: 0.00883 +2025-10-30 21:48:28.543643: train_loss -0.9829 +2025-10-30 21:48:28.547350: val_loss -0.8945 +2025-10-30 21:48:28.549468: Pseudo dice [np.float32(0.9842), np.float32(0.9921), np.float32(0.9946), np.float32(0.7868)] +2025-10-30 21:48:28.551894: Epoch time: 19.48 s +2025-10-30 21:48:29.656075: +2025-10-30 21:48:29.658240: Epoch 130 +2025-10-30 21:48:29.660595: Current learning rate: 0.00882 +2025-10-30 21:48:50.116458: train_loss -0.9822 +2025-10-30 21:48:50.120371: val_loss -0.8961 +2025-10-30 21:48:50.122658: Pseudo dice [np.float32(0.9844), np.float32(0.9919), np.float32(0.9945), np.float32(0.7928)] +2025-10-30 21:48:50.124508: Epoch time: 20.46 s +2025-10-30 21:48:51.251494: +2025-10-30 21:48:51.253431: Epoch 131 +2025-10-30 21:48:51.256577: Current learning rate: 0.00881 +2025-10-30 21:49:11.096354: train_loss -0.983 +2025-10-30 21:49:11.099595: val_loss -0.909 +2025-10-30 21:49:11.101015: Pseudo dice [np.float32(0.9851), np.float32(0.9923), np.float32(0.995), np.float32(0.8166)] +2025-10-30 21:49:11.102577: Epoch time: 19.85 s +2025-10-30 21:49:12.280074: +2025-10-30 21:49:12.282084: Epoch 132 +2025-10-30 21:49:12.283945: Current learning rate: 0.0088 +2025-10-30 21:49:32.670133: train_loss -0.9842 +2025-10-30 21:49:32.673373: val_loss -0.9037 +2025-10-30 21:49:32.675792: Pseudo dice [np.float32(0.9851), np.float32(0.9923), np.float32(0.9949), np.float32(0.8096)] +2025-10-30 21:49:32.677362: Epoch time: 20.39 s +2025-10-30 21:49:33.863516: +2025-10-30 21:49:33.865449: Epoch 133 +2025-10-30 21:49:33.867367: Current learning rate: 0.00879 +2025-10-30 21:49:54.476877: train_loss -0.9765 +2025-10-30 21:49:59.019473: val_loss -0.9049 +2025-10-30 21:49:59.157784: Pseudo dice [np.float32(0.9854), np.float32(0.9904), np.float32(0.9939), np.float32(0.7979)] +2025-10-30 21:49:59.176520: Epoch time: 20.61 s +2025-10-30 21:50:00.557751: +2025-10-30 21:50:00.560496: Epoch 134 +2025-10-30 21:50:00.562803: Current learning rate: 0.00879 +2025-10-30 21:50:19.923058: train_loss -0.952 +2025-10-30 21:50:19.935050: val_loss -0.8859 +2025-10-30 21:50:19.936868: Pseudo dice [np.float32(0.9795), np.float32(0.9876), np.float32(0.9859), np.float32(0.7769)] +2025-10-30 21:50:19.938477: Epoch time: 19.37 s +2025-10-30 21:50:21.314087: +2025-10-30 21:50:21.316692: Epoch 135 +2025-10-30 21:50:21.322740: Current learning rate: 0.00878 +2025-10-30 21:50:37.674901: train_loss -0.941 +2025-10-30 21:50:37.699306: val_loss -0.8977 +2025-10-30 21:50:37.712359: Pseudo dice [np.float32(0.9814), np.float32(0.9904), np.float32(0.9925), np.float32(0.7791)] +2025-10-30 21:50:37.725030: Epoch time: 16.36 s +2025-10-30 21:50:38.847994: +2025-10-30 21:50:38.856948: Epoch 136 +2025-10-30 21:50:38.871853: Current learning rate: 0.00877 +2025-10-30 21:50:58.307231: train_loss -0.9546 +2025-10-30 21:50:58.314004: val_loss -0.8894 +2025-10-30 21:50:58.315904: Pseudo dice [np.float32(0.9843), np.float32(0.9908), np.float32(0.9898), np.float32(0.7767)] +2025-10-30 21:50:58.317693: Epoch time: 19.46 s +2025-10-30 21:50:59.329449: +2025-10-30 21:50:59.331764: Epoch 137 +2025-10-30 21:50:59.338360: Current learning rate: 0.00876 +2025-10-30 21:51:19.823033: train_loss -0.9665 +2025-10-30 21:51:19.825628: val_loss -0.908 +2025-10-30 21:51:19.827455: Pseudo dice [np.float32(0.984), np.float32(0.9913), np.float32(0.994), np.float32(0.8019)] +2025-10-30 21:51:19.833044: Epoch time: 20.49 s +2025-10-30 21:51:20.841348: +2025-10-30 21:51:20.848351: Epoch 138 +2025-10-30 21:51:20.850393: Current learning rate: 0.00875 +2025-10-30 21:51:39.974568: train_loss -0.9704 +2025-10-30 21:51:39.977848: val_loss -0.9014 +2025-10-30 21:51:39.979983: Pseudo dice [np.float32(0.9846), np.float32(0.9919), np.float32(0.9943), np.float32(0.7903)] +2025-10-30 21:51:39.985914: Epoch time: 19.13 s +2025-10-30 21:51:41.656533: +2025-10-30 21:51:41.666025: Epoch 139 +2025-10-30 21:51:41.668233: Current learning rate: 0.00874 +2025-10-30 21:52:02.106443: train_loss -0.9745 +2025-10-30 21:52:02.113193: val_loss -0.9013 +2025-10-30 21:52:02.119681: Pseudo dice [np.float32(0.9855), np.float32(0.9925), np.float32(0.9945), np.float32(0.7868)] +2025-10-30 21:52:02.122490: Epoch time: 20.45 s +2025-10-30 21:52:03.199507: +2025-10-30 21:52:03.201989: Epoch 140 +2025-10-30 21:52:03.204965: Current learning rate: 0.00873 +2025-10-30 21:52:23.659326: train_loss -0.9686 +2025-10-30 21:52:23.666330: val_loss -0.9049 +2025-10-30 21:52:23.668454: Pseudo dice [np.float32(0.9828), np.float32(0.9918), np.float32(0.9911), np.float32(0.8024)] +2025-10-30 21:52:23.670295: Epoch time: 20.46 s +2025-10-30 21:52:24.707225: +2025-10-30 21:52:24.709561: Epoch 141 +2025-10-30 21:52:24.711474: Current learning rate: 0.00872 +2025-10-30 21:52:44.669965: train_loss -0.9726 +2025-10-30 21:52:44.698996: val_loss -0.9152 +2025-10-30 21:52:44.700902: Pseudo dice [np.float32(0.9839), np.float32(0.9919), np.float32(0.9951), np.float32(0.8234)] +2025-10-30 21:52:44.702582: Epoch time: 19.96 s +2025-10-30 21:52:45.845366: +2025-10-30 21:52:45.848070: Epoch 142 +2025-10-30 21:52:45.849998: Current learning rate: 0.00871 +2025-10-30 21:53:03.326286: train_loss -0.9758 +2025-10-30 21:53:03.336519: val_loss -0.9113 +2025-10-30 21:53:03.338320: Pseudo dice [np.float32(0.9822), np.float32(0.991), np.float32(0.9948), np.float32(0.8124)] +2025-10-30 21:53:03.340156: Epoch time: 17.48 s +2025-10-30 21:53:04.367110: +2025-10-30 21:53:04.369108: Epoch 143 +2025-10-30 21:53:04.371914: Current learning rate: 0.0087 +2025-10-30 21:53:27.286657: train_loss -0.9717 +2025-10-30 21:53:27.301336: val_loss -0.9029 +2025-10-30 21:53:27.303655: Pseudo dice [np.float32(0.9831), np.float32(0.992), np.float32(0.9941), np.float32(0.7995)] +2025-10-30 21:53:27.305863: Epoch time: 22.92 s +2025-10-30 21:53:28.583584: +2025-10-30 21:53:28.586595: Epoch 144 +2025-10-30 21:53:28.588705: Current learning rate: 0.00869 +2025-10-30 21:53:48.698928: train_loss -0.9724 +2025-10-30 21:53:48.706384: val_loss -0.9077 +2025-10-30 21:53:48.708432: Pseudo dice [np.float32(0.9839), np.float32(0.9909), np.float32(0.9945), np.float32(0.8018)] +2025-10-30 21:53:48.710463: Epoch time: 20.12 s +2025-10-30 21:53:49.743755: +2025-10-30 21:53:49.746486: Epoch 145 +2025-10-30 21:53:49.755837: Current learning rate: 0.00868 +2025-10-30 21:54:11.011756: train_loss -0.9699 +2025-10-30 21:54:11.017781: val_loss -0.9035 +2025-10-30 21:54:11.019870: Pseudo dice [np.float32(0.9838), np.float32(0.9918), np.float32(0.9945), np.float32(0.7904)] +2025-10-30 21:54:11.021697: Epoch time: 21.27 s +2025-10-30 21:54:12.211008: +2025-10-30 21:54:12.213604: Epoch 146 +2025-10-30 21:54:12.219792: Current learning rate: 0.00868 +2025-10-30 21:54:34.266310: train_loss -0.9761 +2025-10-30 21:54:34.282866: val_loss -0.904 +2025-10-30 21:54:34.285020: Pseudo dice [np.float32(0.984), np.float32(0.9918), np.float32(0.9946), np.float32(0.7933)] +2025-10-30 21:54:34.287106: Epoch time: 22.06 s +2025-10-30 21:54:35.454506: +2025-10-30 21:54:35.460686: Epoch 147 +2025-10-30 21:54:35.466400: Current learning rate: 0.00867 +2025-10-30 21:54:55.889000: train_loss -0.9783 +2025-10-30 21:54:55.892951: val_loss -0.9083 +2025-10-30 21:54:55.961134: Pseudo dice [np.float32(0.9832), np.float32(0.9924), np.float32(0.9948), np.float32(0.8078)] +2025-10-30 21:54:55.963497: Epoch time: 20.44 s +2025-10-30 21:54:57.017891: +2025-10-30 21:54:57.019880: Epoch 148 +2025-10-30 21:54:57.025448: Current learning rate: 0.00866 +2025-10-30 21:55:16.788137: train_loss -0.9782 +2025-10-30 21:55:16.795590: val_loss -0.9027 +2025-10-30 21:55:16.798332: Pseudo dice [np.float32(0.9852), np.float32(0.9922), np.float32(0.9944), np.float32(0.7935)] +2025-10-30 21:55:16.801010: Epoch time: 19.77 s +2025-10-30 21:55:18.041408: +2025-10-30 21:55:18.047449: Epoch 149 +2025-10-30 21:55:18.049410: Current learning rate: 0.00865 +2025-10-30 21:55:38.660149: train_loss -0.9795 +2025-10-30 21:55:38.662489: val_loss -0.9018 +2025-10-30 21:55:38.669022: Pseudo dice [np.float32(0.9841), np.float32(0.9918), np.float32(0.9945), np.float32(0.798)] +2025-10-30 21:55:38.671247: Epoch time: 20.62 s +2025-10-30 21:55:42.183430: +2025-10-30 21:55:42.185749: Epoch 150 +2025-10-30 21:55:42.188238: Current learning rate: 0.00864 +2025-10-30 21:56:02.810342: train_loss -0.9799 +2025-10-30 21:56:02.821314: val_loss -0.9046 +2025-10-30 21:56:02.823559: Pseudo dice [np.float32(0.986), np.float32(0.9926), np.float32(0.9936), np.float32(0.7952)] +2025-10-30 21:56:02.831182: Epoch time: 20.63 s +2025-10-30 21:56:04.017306: +2025-10-30 21:56:04.020416: Epoch 151 +2025-10-30 21:56:04.022979: Current learning rate: 0.00863 +2025-10-30 21:56:23.119419: train_loss -0.9809 +2025-10-30 21:56:23.134455: val_loss -0.9065 +2025-10-30 21:56:23.140383: Pseudo dice [np.float32(0.985), np.float32(0.9922), np.float32(0.9948), np.float32(0.8022)] +2025-10-30 21:56:23.144671: Epoch time: 19.1 s +2025-10-30 21:56:24.345307: +2025-10-30 21:56:24.348617: Epoch 152 +2025-10-30 21:56:24.351268: Current learning rate: 0.00862 +2025-10-30 21:56:44.835340: train_loss -0.9815 +2025-10-30 21:56:44.841879: val_loss -0.8943 +2025-10-30 21:56:44.843692: Pseudo dice [np.float32(0.9855), np.float32(0.992), np.float32(0.9941), np.float32(0.7713)] +2025-10-30 21:56:44.845220: Epoch time: 20.49 s +2025-10-30 21:56:45.928797: +2025-10-30 21:56:45.932999: Epoch 153 +2025-10-30 21:56:45.934771: Current learning rate: 0.00861 +2025-10-30 21:57:06.407722: train_loss -0.9823 +2025-10-30 21:57:06.428289: val_loss -0.894 +2025-10-30 21:57:06.430578: Pseudo dice [np.float32(0.9842), np.float32(0.9921), np.float32(0.9937), np.float32(0.7832)] +2025-10-30 21:57:06.433082: Epoch time: 20.48 s +2025-10-30 21:57:07.617153: +2025-10-30 21:57:07.622174: Epoch 154 +2025-10-30 21:57:07.623961: Current learning rate: 0.0086 +2025-10-30 21:57:26.737425: train_loss -0.9819 +2025-10-30 21:57:26.860222: val_loss -0.9064 +2025-10-30 21:57:26.865315: Pseudo dice [np.float32(0.984), np.float32(0.992), np.float32(0.9952), np.float32(0.818)] +2025-10-30 21:57:26.870907: Epoch time: 19.12 s +2025-10-30 21:57:28.072256: +2025-10-30 21:57:28.077940: Epoch 155 +2025-10-30 21:57:28.082312: Current learning rate: 0.00859 +2025-10-30 21:57:48.698967: train_loss -0.983 +2025-10-30 21:57:48.702355: val_loss -0.8953 +2025-10-30 21:57:48.705068: Pseudo dice [np.float32(0.9842), np.float32(0.9922), np.float32(0.9945), np.float32(0.7908)] +2025-10-30 21:57:48.706744: Epoch time: 20.63 s +2025-10-30 21:57:49.930138: +2025-10-30 21:57:49.932100: Epoch 156 +2025-10-30 21:57:49.933946: Current learning rate: 0.00858 +2025-10-30 21:58:10.334275: train_loss -0.982 +2025-10-30 21:58:10.342458: val_loss -0.9088 +2025-10-30 21:58:10.344022: Pseudo dice [np.float32(0.9841), np.float32(0.9924), np.float32(0.9944), np.float32(0.8194)] +2025-10-30 21:58:10.345674: Epoch time: 20.41 s +2025-10-30 21:58:11.634659: +2025-10-30 21:58:11.636640: Epoch 157 +2025-10-30 21:58:11.638446: Current learning rate: 0.00858 +2025-10-30 21:58:31.991026: train_loss -0.9834 +2025-10-30 21:58:31.995943: val_loss -0.9053 +2025-10-30 21:58:31.997983: Pseudo dice [np.float32(0.9867), np.float32(0.9934), np.float32(0.9946), np.float32(0.7986)] +2025-10-30 21:58:32.001768: Epoch time: 20.36 s +2025-10-30 21:58:33.177731: +2025-10-30 21:58:33.180183: Epoch 158 +2025-10-30 21:58:33.182056: Current learning rate: 0.00857 +2025-10-30 21:58:52.223148: train_loss -0.9826 +2025-10-30 21:58:52.226264: val_loss -0.8964 +2025-10-30 21:58:52.231029: Pseudo dice [np.float32(0.9836), np.float32(0.9919), np.float32(0.9933), np.float32(0.7861)] +2025-10-30 21:58:52.233526: Epoch time: 19.05 s +2025-10-30 21:58:53.302968: +2025-10-30 21:58:53.304965: Epoch 159 +2025-10-30 21:58:53.308544: Current learning rate: 0.00856 +2025-10-30 21:59:14.140343: train_loss -0.9809 +2025-10-30 21:59:14.143980: val_loss -0.8858 +2025-10-30 21:59:14.145716: Pseudo dice [np.float32(0.983), np.float32(0.9918), np.float32(0.9928), np.float32(0.7712)] +2025-10-30 21:59:14.147358: Epoch time: 20.84 s +2025-10-30 21:59:15.271532: +2025-10-30 21:59:15.273664: Epoch 160 +2025-10-30 21:59:15.276193: Current learning rate: 0.00855 +2025-10-30 21:59:36.189263: train_loss -0.9802 +2025-10-30 21:59:36.192071: val_loss -0.9001 +2025-10-30 21:59:36.193843: Pseudo dice [np.float32(0.9814), np.float32(0.9915), np.float32(0.9942), np.float32(0.8013)] +2025-10-30 21:59:36.195472: Epoch time: 20.92 s +2025-10-30 21:59:37.330487: +2025-10-30 21:59:37.332218: Epoch 161 +2025-10-30 21:59:37.333755: Current learning rate: 0.00854 +2025-10-30 21:59:56.959279: train_loss -0.9807 +2025-10-30 21:59:56.963658: val_loss -0.9011 +2025-10-30 21:59:56.967952: Pseudo dice [np.float32(0.983), np.float32(0.9923), np.float32(0.995), np.float32(0.7986)] +2025-10-30 21:59:56.971418: Epoch time: 19.63 s +2025-10-30 21:59:58.778649: +2025-10-30 21:59:58.780909: Epoch 162 +2025-10-30 21:59:58.782558: Current learning rate: 0.00853 +2025-10-30 22:00:19.348133: train_loss -0.9828 +2025-10-30 22:00:19.350830: val_loss -0.8999 +2025-10-30 22:00:19.352565: Pseudo dice [np.float32(0.9835), np.float32(0.9919), np.float32(0.995), np.float32(0.8006)] +2025-10-30 22:00:19.354542: Epoch time: 20.57 s +2025-10-30 22:00:20.425077: +2025-10-30 22:00:20.427212: Epoch 163 +2025-10-30 22:00:20.431069: Current learning rate: 0.00852 +2025-10-30 22:00:40.559324: train_loss -0.9832 +2025-10-30 22:00:40.561609: val_loss -0.9029 +2025-10-30 22:00:40.563963: Pseudo dice [np.float32(0.9853), np.float32(0.9927), np.float32(0.9944), np.float32(0.7971)] +2025-10-30 22:00:40.566342: Epoch time: 20.14 s +2025-10-30 22:00:41.488593: +2025-10-30 22:00:41.490824: Epoch 164 +2025-10-30 22:00:41.492409: Current learning rate: 0.00851 +2025-10-30 22:01:01.976991: train_loss -0.9838 +2025-10-30 22:01:01.982783: val_loss -0.8883 +2025-10-30 22:01:01.986564: Pseudo dice [np.float32(0.9849), np.float32(0.992), np.float32(0.9917), np.float32(0.79)] +2025-10-30 22:01:01.988248: Epoch time: 20.49 s +2025-10-30 22:01:03.180356: +2025-10-30 22:01:03.182516: Epoch 165 +2025-10-30 22:01:03.185118: Current learning rate: 0.0085 +2025-10-30 22:01:25.388981: train_loss -0.9813 +2025-10-30 22:01:25.407097: val_loss -0.8882 +2025-10-30 22:01:25.409600: Pseudo dice [np.float32(0.9853), np.float32(0.9909), np.float32(0.9898), np.float32(0.7873)] +2025-10-30 22:01:25.412086: Epoch time: 22.21 s +2025-10-30 22:01:26.615902: +2025-10-30 22:01:26.617830: Epoch 166 +2025-10-30 22:01:26.619851: Current learning rate: 0.00849 +2025-10-30 22:01:46.933871: train_loss -0.9809 +2025-10-30 22:01:46.936475: val_loss -0.8934 +2025-10-30 22:01:46.938093: Pseudo dice [np.float32(0.9841), np.float32(0.9923), np.float32(0.994), np.float32(0.7832)] +2025-10-30 22:01:46.939930: Epoch time: 20.32 s +2025-10-30 22:01:48.004056: +2025-10-30 22:01:48.006037: Epoch 167 +2025-10-30 22:01:48.007598: Current learning rate: 0.00848 +2025-10-30 22:02:09.509067: train_loss -0.9797 +2025-10-30 22:02:09.522788: val_loss -0.8979 +2025-10-30 22:02:09.525696: Pseudo dice [np.float32(0.9817), np.float32(0.992), np.float32(0.9944), np.float32(0.795)] +2025-10-30 22:02:09.529085: Epoch time: 21.51 s +2025-10-30 22:02:10.805702: +2025-10-30 22:02:10.809721: Epoch 168 +2025-10-30 22:02:10.811605: Current learning rate: 0.00847 +2025-10-30 22:02:32.002166: train_loss -0.9822 +2025-10-30 22:02:32.005816: val_loss -0.9022 +2025-10-30 22:02:32.007977: Pseudo dice [np.float32(0.9842), np.float32(0.992), np.float32(0.9945), np.float32(0.7983)] +2025-10-30 22:02:32.010063: Epoch time: 21.2 s +2025-10-30 22:02:33.086041: +2025-10-30 22:02:33.087986: Epoch 169 +2025-10-30 22:02:33.089841: Current learning rate: 0.00847 +2025-10-30 22:02:53.553656: train_loss -0.9762 +2025-10-30 22:02:53.557087: val_loss -0.9017 +2025-10-30 22:02:53.564024: Pseudo dice [np.float32(0.9824), np.float32(0.9919), np.float32(0.9946), np.float32(0.8046)] +2025-10-30 22:02:53.567132: Epoch time: 20.47 s +2025-10-30 22:02:54.599512: +2025-10-30 22:02:54.603204: Epoch 170 +2025-10-30 22:02:54.605658: Current learning rate: 0.00846 +2025-10-30 22:03:14.945619: train_loss -0.9761 +2025-10-30 22:03:14.949785: val_loss -0.8964 +2025-10-30 22:03:14.952109: Pseudo dice [np.float32(0.9857), np.float32(0.9923), np.float32(0.9945), np.float32(0.7753)] +2025-10-30 22:03:14.954034: Epoch time: 20.35 s +2025-10-30 22:03:16.153892: +2025-10-30 22:03:16.155931: Epoch 171 +2025-10-30 22:03:16.158069: Current learning rate: 0.00845 +2025-10-30 22:03:35.679928: train_loss -0.976 +2025-10-30 22:03:35.683870: val_loss -0.8989 +2025-10-30 22:03:35.685540: Pseudo dice [np.float32(0.9826), np.float32(0.9909), np.float32(0.9944), np.float32(0.7917)] +2025-10-30 22:03:35.687195: Epoch time: 19.53 s +2025-10-30 22:03:36.914160: +2025-10-30 22:03:36.916477: Epoch 172 +2025-10-30 22:03:36.918318: Current learning rate: 0.00844 +2025-10-30 22:03:57.371918: train_loss -0.9744 +2025-10-30 22:03:57.374921: val_loss -0.8979 +2025-10-30 22:03:57.376711: Pseudo dice [np.float32(0.9849), np.float32(0.9914), np.float32(0.9923), np.float32(0.7908)] +2025-10-30 22:03:57.378664: Epoch time: 20.46 s +2025-10-30 22:03:58.865317: +2025-10-30 22:03:58.867252: Epoch 173 +2025-10-30 22:03:58.868943: Current learning rate: 0.00843 +2025-10-30 22:04:17.937850: train_loss -0.9787 +2025-10-30 22:04:17.940477: val_loss -0.903 +2025-10-30 22:04:17.942097: Pseudo dice [np.float32(0.9854), np.float32(0.9916), np.float32(0.9942), np.float32(0.7983)] +2025-10-30 22:04:17.943776: Epoch time: 19.07 s +2025-10-30 22:04:19.013158: +2025-10-30 22:04:19.015013: Epoch 174 +2025-10-30 22:04:19.016858: Current learning rate: 0.00842 +2025-10-30 22:04:39.149434: train_loss -0.9814 +2025-10-30 22:04:39.153080: val_loss -0.8975 +2025-10-30 22:04:39.154555: Pseudo dice [np.float32(0.9847), np.float32(0.9921), np.float32(0.994), np.float32(0.7901)] +2025-10-30 22:04:39.155988: Epoch time: 20.14 s +2025-10-30 22:04:40.197169: +2025-10-30 22:04:40.198976: Epoch 175 +2025-10-30 22:04:40.201078: Current learning rate: 0.00841 +2025-10-30 22:05:00.685456: train_loss -0.9828 +2025-10-30 22:05:00.688819: val_loss -0.8943 +2025-10-30 22:05:00.690432: Pseudo dice [np.float32(0.9841), np.float32(0.9921), np.float32(0.9943), np.float32(0.7822)] +2025-10-30 22:05:00.692085: Epoch time: 20.49 s +2025-10-30 22:05:01.989078: +2025-10-30 22:05:01.992194: Epoch 176 +2025-10-30 22:05:01.994004: Current learning rate: 0.0084 +2025-10-30 22:05:22.222466: train_loss -0.9826 +2025-10-30 22:05:22.225172: val_loss -0.8925 +2025-10-30 22:05:22.227130: Pseudo dice [np.float32(0.9828), np.float32(0.9912), np.float32(0.994), np.float32(0.7883)] +2025-10-30 22:05:22.228963: Epoch time: 20.23 s +2025-10-30 22:05:23.342299: +2025-10-30 22:05:23.344034: Epoch 177 +2025-10-30 22:05:23.345880: Current learning rate: 0.00839 +2025-10-30 22:05:43.823849: train_loss -0.9818 +2025-10-30 22:05:43.829448: val_loss -0.8975 +2025-10-30 22:05:43.833390: Pseudo dice [np.float32(0.9874), np.float32(0.9932), np.float32(0.993), np.float32(0.7866)] +2025-10-30 22:05:43.836496: Epoch time: 20.48 s +2025-10-30 22:05:44.889510: +2025-10-30 22:05:44.891572: Epoch 178 +2025-10-30 22:05:44.895034: Current learning rate: 0.00838 +2025-10-30 22:06:04.231709: train_loss -0.9818 +2025-10-30 22:06:04.235793: val_loss -0.8995 +2025-10-30 22:06:04.237651: Pseudo dice [np.float32(0.9852), np.float32(0.9917), np.float32(0.9944), np.float32(0.787)] +2025-10-30 22:06:04.239563: Epoch time: 19.34 s +2025-10-30 22:06:05.202096: +2025-10-30 22:06:05.204987: Epoch 179 +2025-10-30 22:06:05.207752: Current learning rate: 0.00837 +2025-10-30 22:06:24.893396: train_loss -0.9822 +2025-10-30 22:06:24.896044: val_loss -0.9015 +2025-10-30 22:06:24.897802: Pseudo dice [np.float32(0.9859), np.float32(0.992), np.float32(0.9943), np.float32(0.7997)] +2025-10-30 22:06:24.899513: Epoch time: 19.69 s +2025-10-30 22:06:26.020780: +2025-10-30 22:06:26.022982: Epoch 180 +2025-10-30 22:06:26.025698: Current learning rate: 0.00836 +2025-10-30 22:06:46.394485: train_loss -0.9845 +2025-10-30 22:06:46.397972: val_loss -0.8947 +2025-10-30 22:06:46.399920: Pseudo dice [np.float32(0.9849), np.float32(0.9923), np.float32(0.9945), np.float32(0.7837)] +2025-10-30 22:06:46.401921: Epoch time: 20.38 s +2025-10-30 22:06:47.528675: +2025-10-30 22:06:47.531477: Epoch 181 +2025-10-30 22:06:47.533971: Current learning rate: 0.00836 +2025-10-30 22:07:07.980549: train_loss -0.9837 +2025-10-30 22:07:07.983449: val_loss -0.8959 +2025-10-30 22:07:07.985735: Pseudo dice [np.float32(0.9857), np.float32(0.992), np.float32(0.9937), np.float32(0.7922)] +2025-10-30 22:07:07.987380: Epoch time: 20.45 s +2025-10-30 22:07:08.994791: +2025-10-30 22:07:08.996793: Epoch 182 +2025-10-30 22:07:08.998947: Current learning rate: 0.00835 +2025-10-30 22:07:29.819568: train_loss -0.9842 +2025-10-30 22:07:29.821544: val_loss -0.9019 +2025-10-30 22:07:29.823201: Pseudo dice [np.float32(0.9845), np.float32(0.9918), np.float32(0.9945), np.float32(0.8001)] +2025-10-30 22:07:29.825469: Epoch time: 20.83 s +2025-10-30 22:07:31.007694: +2025-10-30 22:07:31.009546: Epoch 183 +2025-10-30 22:07:31.011143: Current learning rate: 0.00834 +2025-10-30 22:07:51.284089: train_loss -0.9826 +2025-10-30 22:07:51.287278: val_loss -0.8939 +2025-10-30 22:07:51.289245: Pseudo dice [np.float32(0.9853), np.float32(0.9919), np.float32(0.9944), np.float32(0.7826)] +2025-10-30 22:07:51.291885: Epoch time: 20.28 s +2025-10-30 22:07:52.397007: +2025-10-30 22:07:52.400656: Epoch 184 +2025-10-30 22:07:52.403582: Current learning rate: 0.00833 +2025-10-30 22:08:13.142884: train_loss -0.9839 +2025-10-30 22:08:13.145278: val_loss -0.895 +2025-10-30 22:08:13.147402: Pseudo dice [np.float32(0.9839), np.float32(0.9919), np.float32(0.9947), np.float32(0.7894)] +2025-10-30 22:08:13.150190: Epoch time: 20.75 s +2025-10-30 22:08:14.784515: +2025-10-30 22:08:14.787894: Epoch 185 +2025-10-30 22:08:14.790417: Current learning rate: 0.00832 +2025-10-30 22:08:33.903757: train_loss -0.9847 +2025-10-30 22:08:33.907076: val_loss -0.8916 +2025-10-30 22:08:33.909516: Pseudo dice [np.float32(0.9844), np.float32(0.9924), np.float32(0.9945), np.float32(0.7872)] +2025-10-30 22:08:33.911534: Epoch time: 19.12 s +2025-10-30 22:08:34.958016: +2025-10-30 22:08:34.960129: Epoch 186 +2025-10-30 22:08:34.961846: Current learning rate: 0.00831 +2025-10-30 22:08:54.945043: train_loss -0.9845 +2025-10-30 22:08:54.948700: val_loss -0.8917 +2025-10-30 22:08:54.950538: Pseudo dice [np.float32(0.9842), np.float32(0.9918), np.float32(0.9945), np.float32(0.7869)] +2025-10-30 22:08:54.952234: Epoch time: 19.99 s +2025-10-30 22:08:56.176492: +2025-10-30 22:08:56.179216: Epoch 187 +2025-10-30 22:08:56.182261: Current learning rate: 0.0083 +2025-10-30 22:09:16.675341: train_loss -0.9847 +2025-10-30 22:09:16.677953: val_loss -0.8872 +2025-10-30 22:09:16.679524: Pseudo dice [np.float32(0.9849), np.float32(0.992), np.float32(0.9925), np.float32(0.7908)] +2025-10-30 22:09:16.680967: Epoch time: 20.5 s +2025-10-30 22:09:17.909714: +2025-10-30 22:09:17.912326: Epoch 188 +2025-10-30 22:09:17.914330: Current learning rate: 0.00829 +2025-10-30 22:09:38.604843: train_loss -0.9852 +2025-10-30 22:09:38.607414: val_loss -0.885 +2025-10-30 22:09:38.609409: Pseudo dice [np.float32(0.9838), np.float32(0.992), np.float32(0.9913), np.float32(0.7869)] +2025-10-30 22:09:38.612983: Epoch time: 20.7 s +2025-10-30 22:09:39.817080: +2025-10-30 22:09:39.821104: Epoch 189 +2025-10-30 22:09:39.824250: Current learning rate: 0.00828 +2025-10-30 22:10:00.064128: train_loss -0.985 +2025-10-30 22:10:00.066701: val_loss -0.8953 +2025-10-30 22:10:00.069063: Pseudo dice [np.float32(0.9842), np.float32(0.9918), np.float32(0.9941), np.float32(0.7967)] +2025-10-30 22:10:00.071212: Epoch time: 20.25 s +2025-10-30 22:10:01.096656: +2025-10-30 22:10:01.098710: Epoch 190 +2025-10-30 22:10:01.100379: Current learning rate: 0.00827 +2025-10-30 22:10:21.484134: train_loss -0.985 +2025-10-30 22:10:21.486912: val_loss -0.8983 +2025-10-30 22:10:21.488780: Pseudo dice [np.float32(0.983), np.float32(0.992), np.float32(0.9947), np.float32(0.8001)] +2025-10-30 22:10:21.490463: Epoch time: 20.39 s +2025-10-30 22:10:22.754464: +2025-10-30 22:10:22.756288: Epoch 191 +2025-10-30 22:10:22.758110: Current learning rate: 0.00826 +2025-10-30 22:10:43.084997: train_loss -0.985 +2025-10-30 22:10:43.087381: val_loss -0.9019 +2025-10-30 22:10:43.089833: Pseudo dice [np.float32(0.9847), np.float32(0.9919), np.float32(0.995), np.float32(0.8106)] +2025-10-30 22:10:43.092175: Epoch time: 20.33 s +2025-10-30 22:10:44.201863: +2025-10-30 22:10:44.204740: Epoch 192 +2025-10-30 22:10:44.206780: Current learning rate: 0.00825 +2025-10-30 22:11:01.987621: train_loss -0.9849 +2025-10-30 22:11:01.994826: val_loss -0.8992 +2025-10-30 22:11:01.997355: Pseudo dice [np.float32(0.9844), np.float32(0.9921), np.float32(0.9946), np.float32(0.7995)] +2025-10-30 22:11:01.999444: Epoch time: 17.79 s +2025-10-30 22:11:03.193036: +2025-10-30 22:11:03.199035: Epoch 193 +2025-10-30 22:11:03.204316: Current learning rate: 0.00824 +2025-10-30 22:11:23.756042: train_loss -0.9852 +2025-10-30 22:11:23.759876: val_loss -0.8911 +2025-10-30 22:11:23.762185: Pseudo dice [np.float32(0.9858), np.float32(0.9925), np.float32(0.9943), np.float32(0.7824)] +2025-10-30 22:11:23.765119: Epoch time: 20.56 s +2025-10-30 22:11:25.045896: +2025-10-30 22:11:25.048716: Epoch 194 +2025-10-30 22:11:25.050939: Current learning rate: 0.00824 +2025-10-30 22:11:45.563322: train_loss -0.9848 +2025-10-30 22:11:45.565797: val_loss -0.8949 +2025-10-30 22:11:45.567413: Pseudo dice [np.float32(0.9846), np.float32(0.9918), np.float32(0.9944), np.float32(0.7882)] +2025-10-30 22:11:45.569147: Epoch time: 20.52 s +2025-10-30 22:11:46.687776: +2025-10-30 22:11:46.689609: Epoch 195 +2025-10-30 22:11:46.691622: Current learning rate: 0.00823 +2025-10-30 22:12:06.935154: train_loss -0.9847 +2025-10-30 22:12:06.937601: val_loss -0.8918 +2025-10-30 22:12:06.939163: Pseudo dice [np.float32(0.985), np.float32(0.991), np.float32(0.9936), np.float32(0.787)] +2025-10-30 22:12:06.940799: Epoch time: 20.25 s +2025-10-30 22:12:08.527105: +2025-10-30 22:12:08.531715: Epoch 196 +2025-10-30 22:12:08.533536: Current learning rate: 0.00822 +2025-10-30 22:12:28.997528: train_loss -0.9847 +2025-10-30 22:12:29.000530: val_loss -0.8948 +2025-10-30 22:12:29.003749: Pseudo dice [np.float32(0.9843), np.float32(0.9917), np.float32(0.994), np.float32(0.7959)] +2025-10-30 22:12:29.005673: Epoch time: 20.47 s +2025-10-30 22:12:30.074953: +2025-10-30 22:12:30.076969: Epoch 197 +2025-10-30 22:12:30.078746: Current learning rate: 0.00821 +2025-10-30 22:12:50.632419: train_loss -0.9853 +2025-10-30 22:12:50.635547: val_loss -0.8988 +2025-10-30 22:12:50.637429: Pseudo dice [np.float32(0.9863), np.float32(0.9926), np.float32(0.9948), np.float32(0.7971)] +2025-10-30 22:12:50.639388: Epoch time: 20.56 s +2025-10-30 22:12:51.876640: +2025-10-30 22:12:51.878762: Epoch 198 +2025-10-30 22:12:51.880570: Current learning rate: 0.0082 +2025-10-30 22:13:12.177034: train_loss -0.9837 +2025-10-30 22:13:12.179843: val_loss -0.8948 +2025-10-30 22:13:12.181537: Pseudo dice [np.float32(0.9838), np.float32(0.9923), np.float32(0.9946), np.float32(0.7961)] +2025-10-30 22:13:12.183234: Epoch time: 20.3 s +2025-10-30 22:13:13.381055: +2025-10-30 22:13:13.383198: Epoch 199 +2025-10-30 22:13:13.384904: Current learning rate: 0.00819 +2025-10-30 22:13:31.360994: train_loss -0.9842 +2025-10-30 22:13:31.363425: val_loss -0.901 +2025-10-30 22:13:31.365944: Pseudo dice [np.float32(0.9854), np.float32(0.992), np.float32(0.9944), np.float32(0.795)] +2025-10-30 22:13:31.368286: Epoch time: 17.98 s +2025-10-30 22:13:33.607893: +2025-10-30 22:13:33.612770: Epoch 200 +2025-10-30 22:13:33.614544: Current learning rate: 0.00818 +2025-10-30 22:13:54.268300: train_loss -0.9848 +2025-10-30 22:13:54.270616: val_loss -0.9073 +2025-10-30 22:13:54.272219: Pseudo dice [np.float32(0.9849), np.float32(0.9915), np.float32(0.9949), np.float32(0.8228)] +2025-10-30 22:13:54.273898: Epoch time: 20.66 s +2025-10-30 22:13:55.565266: +2025-10-30 22:13:55.567273: Epoch 201 +2025-10-30 22:13:55.569042: Current learning rate: 0.00817 +2025-10-30 22:14:15.886897: train_loss -0.9841 +2025-10-30 22:14:15.890098: val_loss -0.8988 +2025-10-30 22:14:15.892179: Pseudo dice [np.float32(0.9857), np.float32(0.9925), np.float32(0.9944), np.float32(0.7976)] +2025-10-30 22:14:15.893892: Epoch time: 20.32 s +2025-10-30 22:14:16.977950: +2025-10-30 22:14:16.979966: Epoch 202 +2025-10-30 22:14:16.981696: Current learning rate: 0.00816 +2025-10-30 22:14:37.429810: train_loss -0.985 +2025-10-30 22:14:37.432557: val_loss -0.8986 +2025-10-30 22:14:37.434801: Pseudo dice [np.float32(0.9841), np.float32(0.9914), np.float32(0.9946), np.float32(0.8045)] +2025-10-30 22:14:37.436689: Epoch time: 20.45 s +2025-10-30 22:14:38.461008: +2025-10-30 22:14:38.462924: Epoch 203 +2025-10-30 22:14:38.464445: Current learning rate: 0.00815 +2025-10-30 22:14:58.871743: train_loss -0.9847 +2025-10-30 22:14:58.874239: val_loss -0.8969 +2025-10-30 22:14:58.875970: Pseudo dice [np.float32(0.9842), np.float32(0.9915), np.float32(0.9947), np.float32(0.8012)] +2025-10-30 22:14:58.877675: Epoch time: 20.41 s +2025-10-30 22:14:59.901482: +2025-10-30 22:14:59.903314: Epoch 204 +2025-10-30 22:14:59.904907: Current learning rate: 0.00814 +2025-10-30 22:15:20.290151: train_loss -0.9854 +2025-10-30 22:15:20.293751: val_loss -0.9039 +2025-10-30 22:15:20.295751: Pseudo dice [np.float32(0.9844), np.float32(0.9926), np.float32(0.9952), np.float32(0.8068)] +2025-10-30 22:15:20.297878: Epoch time: 20.39 s +2025-10-30 22:15:21.481369: +2025-10-30 22:15:21.483029: Epoch 205 +2025-10-30 22:15:21.484546: Current learning rate: 0.00813 +2025-10-30 22:15:40.714443: train_loss -0.986 +2025-10-30 22:15:40.716875: val_loss -0.9091 +2025-10-30 22:15:40.718710: Pseudo dice [np.float32(0.9838), np.float32(0.9916), np.float32(0.9951), np.float32(0.8261)] +2025-10-30 22:15:40.721180: Epoch time: 19.23 s +2025-10-30 22:15:41.786510: +2025-10-30 22:15:41.788416: Epoch 206 +2025-10-30 22:15:41.789849: Current learning rate: 0.00813 +2025-10-30 22:16:01.398907: train_loss -0.9852 +2025-10-30 22:16:01.402516: val_loss -0.8999 +2025-10-30 22:16:01.404417: Pseudo dice [np.float32(0.9856), np.float32(0.9924), np.float32(0.9945), np.float32(0.8004)] +2025-10-30 22:16:01.406353: Epoch time: 19.61 s +2025-10-30 22:16:02.591350: +2025-10-30 22:16:02.593680: Epoch 207 +2025-10-30 22:16:02.595799: Current learning rate: 0.00812 +2025-10-30 22:16:23.123302: train_loss -0.985 +2025-10-30 22:16:23.126455: val_loss -0.9087 +2025-10-30 22:16:23.128188: Pseudo dice [np.float32(0.9852), np.float32(0.9915), np.float32(0.9951), np.float32(0.8212)] +2025-10-30 22:16:23.129798: Epoch time: 20.53 s +2025-10-30 22:16:24.671108: +2025-10-30 22:16:24.673396: Epoch 208 +2025-10-30 22:16:24.676770: Current learning rate: 0.00811 +2025-10-30 22:16:45.220335: train_loss -0.9831 +2025-10-30 22:16:45.223161: val_loss -0.8996 +2025-10-30 22:16:45.225055: Pseudo dice [np.float32(0.9844), np.float32(0.9917), np.float32(0.9946), np.float32(0.8068)] +2025-10-30 22:16:45.227496: Epoch time: 20.55 s +2025-10-30 22:16:45.229556: Yayy! New best EMA pseudo Dice: 0.9437000155448914 +2025-10-30 22:16:47.821157: +2025-10-30 22:16:47.823316: Epoch 209 +2025-10-30 22:16:47.825405: Current learning rate: 0.0081 +2025-10-30 22:17:08.275254: train_loss -0.9838 +2025-10-30 22:17:08.278078: val_loss -0.8978 +2025-10-30 22:17:08.279922: Pseudo dice [np.float32(0.9849), np.float32(0.9922), np.float32(0.9942), np.float32(0.7941)] +2025-10-30 22:17:08.281733: Epoch time: 20.46 s +2025-10-30 22:17:09.287363: +2025-10-30 22:17:09.289319: Epoch 210 +2025-10-30 22:17:09.291024: Current learning rate: 0.00809 +2025-10-30 22:17:29.919693: train_loss -0.983 +2025-10-30 22:17:29.923244: val_loss -0.9026 +2025-10-30 22:17:29.925002: Pseudo dice [np.float32(0.9849), np.float32(0.9921), np.float32(0.9949), np.float32(0.8134)] +2025-10-30 22:17:29.926791: Epoch time: 20.63 s +2025-10-30 22:17:29.928376: Yayy! New best EMA pseudo Dice: 0.9437000155448914 +2025-10-30 22:17:32.305572: +2025-10-30 22:17:32.307907: Epoch 211 +2025-10-30 22:17:32.310420: Current learning rate: 0.00808 +2025-10-30 22:17:52.330006: train_loss -0.9854 +2025-10-30 22:17:52.333266: val_loss -0.9015 +2025-10-30 22:17:52.335338: Pseudo dice [np.float32(0.9848), np.float32(0.9926), np.float32(0.995), np.float32(0.809)] +2025-10-30 22:17:52.337101: Epoch time: 20.03 s +2025-10-30 22:17:52.338921: Yayy! New best EMA pseudo Dice: 0.9438999891281128 +2025-10-30 22:17:54.572562: +2025-10-30 22:17:54.575051: Epoch 212 +2025-10-30 22:17:54.576786: Current learning rate: 0.00807 +2025-10-30 22:18:13.730902: train_loss -0.986 +2025-10-30 22:18:13.732908: val_loss -0.89 +2025-10-30 22:18:13.734421: Pseudo dice [np.float32(0.9837), np.float32(0.9918), np.float32(0.9941), np.float32(0.785)] +2025-10-30 22:18:13.735852: Epoch time: 19.16 s +2025-10-30 22:18:14.797706: +2025-10-30 22:18:14.799874: Epoch 213 +2025-10-30 22:18:14.801599: Current learning rate: 0.00806 +2025-10-30 22:18:34.854070: train_loss -0.9869 +2025-10-30 22:18:34.857485: val_loss -0.8933 +2025-10-30 22:18:34.859157: Pseudo dice [np.float32(0.9811), np.float32(0.9913), np.float32(0.9945), np.float32(0.7972)] +2025-10-30 22:18:34.861273: Epoch time: 20.06 s +2025-10-30 22:18:35.867140: +2025-10-30 22:18:35.869221: Epoch 214 +2025-10-30 22:18:35.870865: Current learning rate: 0.00805 +2025-10-30 22:18:56.105572: train_loss -0.9862 +2025-10-30 22:18:56.108025: val_loss -0.8982 +2025-10-30 22:18:56.109835: Pseudo dice [np.float32(0.9845), np.float32(0.9916), np.float32(0.9943), np.float32(0.7951)] +2025-10-30 22:18:56.111522: Epoch time: 20.24 s +2025-10-30 22:18:57.109219: +2025-10-30 22:18:57.111840: Epoch 215 +2025-10-30 22:18:57.113883: Current learning rate: 0.00804 +2025-10-30 22:19:17.826327: train_loss -0.9851 +2025-10-30 22:19:17.830793: val_loss -0.9014 +2025-10-30 22:19:17.832573: Pseudo dice [np.float32(0.9848), np.float32(0.992), np.float32(0.9948), np.float32(0.7987)] +2025-10-30 22:19:17.834044: Epoch time: 20.72 s +2025-10-30 22:19:19.056397: +2025-10-30 22:19:19.058487: Epoch 216 +2025-10-30 22:19:19.060691: Current learning rate: 0.00803 +2025-10-30 22:19:39.505283: train_loss -0.9846 +2025-10-30 22:19:39.510974: val_loss -0.9053 +2025-10-30 22:19:39.512665: Pseudo dice [np.float32(0.9845), np.float32(0.9919), np.float32(0.9949), np.float32(0.8188)] +2025-10-30 22:19:39.514468: Epoch time: 20.45 s +2025-10-30 22:19:40.679654: +2025-10-30 22:19:40.681859: Epoch 217 +2025-10-30 22:19:40.684233: Current learning rate: 0.00802 +2025-10-30 22:20:01.016943: train_loss -0.9854 +2025-10-30 22:20:01.021776: val_loss -0.9048 +2025-10-30 22:20:01.024194: Pseudo dice [np.float32(0.9848), np.float32(0.9927), np.float32(0.9948), np.float32(0.8054)] +2025-10-30 22:20:01.026070: Epoch time: 20.34 s +2025-10-30 22:20:02.070656: +2025-10-30 22:20:02.072530: Epoch 218 +2025-10-30 22:20:02.078119: Current learning rate: 0.00801 +2025-10-30 22:20:21.778249: train_loss -0.9861 +2025-10-30 22:20:21.780680: val_loss -0.8958 +2025-10-30 22:20:21.782356: Pseudo dice [np.float32(0.9849), np.float32(0.9924), np.float32(0.9945), np.float32(0.7898)] +2025-10-30 22:20:21.784105: Epoch time: 19.71 s +2025-10-30 22:20:22.879245: +2025-10-30 22:20:22.881510: Epoch 219 +2025-10-30 22:20:22.883398: Current learning rate: 0.00801 +2025-10-30 22:20:41.924920: train_loss -0.9855 +2025-10-30 22:20:41.928071: val_loss -0.8987 +2025-10-30 22:20:41.930825: Pseudo dice [np.float32(0.9849), np.float32(0.992), np.float32(0.9947), np.float32(0.7956)] +2025-10-30 22:20:41.933381: Epoch time: 19.05 s +2025-10-30 22:20:43.183908: +2025-10-30 22:20:43.186328: Epoch 220 +2025-10-30 22:20:43.188304: Current learning rate: 0.008 +2025-10-30 22:21:03.643884: train_loss -0.9842 +2025-10-30 22:21:03.646638: val_loss -0.8976 +2025-10-30 22:21:03.648939: Pseudo dice [np.float32(0.9823), np.float32(0.9913), np.float32(0.9947), np.float32(0.8066)] +2025-10-30 22:21:03.650675: Epoch time: 20.46 s +2025-10-30 22:21:04.711357: +2025-10-30 22:21:04.713499: Epoch 221 +2025-10-30 22:21:04.716314: Current learning rate: 0.00799 +2025-10-30 22:21:25.051259: train_loss -0.9863 +2025-10-30 22:21:25.053694: val_loss -0.8954 +2025-10-30 22:21:25.055782: Pseudo dice [np.float32(0.9837), np.float32(0.9916), np.float32(0.9946), np.float32(0.7897)] +2025-10-30 22:21:25.057860: Epoch time: 20.34 s +2025-10-30 22:21:26.238589: +2025-10-30 22:21:26.240445: Epoch 222 +2025-10-30 22:21:26.242087: Current learning rate: 0.00798 +2025-10-30 22:21:46.829288: train_loss -0.9871 +2025-10-30 22:21:46.832895: val_loss -0.8956 +2025-10-30 22:21:46.834717: Pseudo dice [np.float32(0.9826), np.float32(0.9908), np.float32(0.9945), np.float32(0.804)] +2025-10-30 22:21:46.836816: Epoch time: 20.59 s +2025-10-30 22:21:47.859851: +2025-10-30 22:21:47.862040: Epoch 223 +2025-10-30 22:21:47.863847: Current learning rate: 0.00797 +2025-10-30 22:22:08.544737: train_loss -0.9857 +2025-10-30 22:22:08.547545: val_loss -0.8989 +2025-10-30 22:22:08.550106: Pseudo dice [np.float32(0.9844), np.float32(0.992), np.float32(0.9948), np.float32(0.806)] +2025-10-30 22:22:08.552413: Epoch time: 20.69 s +2025-10-30 22:22:09.833696: +2025-10-30 22:22:09.836109: Epoch 224 +2025-10-30 22:22:09.838000: Current learning rate: 0.00796 +2025-10-30 22:22:29.516958: train_loss -0.9854 +2025-10-30 22:22:29.523214: val_loss -0.8989 +2025-10-30 22:22:29.530178: Pseudo dice [np.float32(0.9852), np.float32(0.9919), np.float32(0.9947), np.float32(0.7971)] +2025-10-30 22:22:29.536140: Epoch time: 19.68 s +2025-10-30 22:22:30.589855: +2025-10-30 22:22:30.591885: Epoch 225 +2025-10-30 22:22:30.593770: Current learning rate: 0.00795 +2025-10-30 22:22:51.099416: train_loss -0.9855 +2025-10-30 22:22:51.103187: val_loss -0.901 +2025-10-30 22:22:51.105060: Pseudo dice [np.float32(0.9864), np.float32(0.9922), np.float32(0.9947), np.float32(0.8061)] +2025-10-30 22:22:51.107435: Epoch time: 20.51 s +2025-10-30 22:22:52.088574: +2025-10-30 22:22:52.090322: Epoch 226 +2025-10-30 22:22:52.092855: Current learning rate: 0.00794 +2025-10-30 22:23:11.155838: train_loss -0.9869 +2025-10-30 22:23:11.157970: val_loss -0.9031 +2025-10-30 22:23:11.159775: Pseudo dice [np.float32(0.9862), np.float32(0.9923), np.float32(0.9948), np.float32(0.8114)] +2025-10-30 22:23:11.161568: Epoch time: 19.07 s +2025-10-30 22:23:12.344741: +2025-10-30 22:23:12.346723: Epoch 227 +2025-10-30 22:23:12.348803: Current learning rate: 0.00793 +2025-10-30 22:23:32.812198: train_loss -0.9859 +2025-10-30 22:23:32.814468: val_loss -0.8908 +2025-10-30 22:23:32.816962: Pseudo dice [np.float32(0.9851), np.float32(0.9923), np.float32(0.9947), np.float32(0.7825)] +2025-10-30 22:23:32.819184: Epoch time: 20.47 s +2025-10-30 22:23:34.141401: +2025-10-30 22:23:34.143722: Epoch 228 +2025-10-30 22:23:34.146702: Current learning rate: 0.00792 +2025-10-30 22:23:54.585543: train_loss -0.9852 +2025-10-30 22:23:54.589904: val_loss -0.897 +2025-10-30 22:23:54.591681: Pseudo dice [np.float32(0.9854), np.float32(0.992), np.float32(0.9945), np.float32(0.7954)] +2025-10-30 22:23:54.593396: Epoch time: 20.45 s +2025-10-30 22:23:55.669139: +2025-10-30 22:23:55.671005: Epoch 229 +2025-10-30 22:23:55.672809: Current learning rate: 0.00791 +2025-10-30 22:24:16.241558: train_loss -0.9852 +2025-10-30 22:24:16.244178: val_loss -0.9001 +2025-10-30 22:24:16.246258: Pseudo dice [np.float32(0.9817), np.float32(0.9921), np.float32(0.9949), np.float32(0.8137)] +2025-10-30 22:24:16.248265: Epoch time: 20.57 s +2025-10-30 22:24:17.326193: +2025-10-30 22:24:17.329550: Epoch 230 +2025-10-30 22:24:17.331964: Current learning rate: 0.0079 +2025-10-30 22:24:37.832022: train_loss -0.984 +2025-10-30 22:24:37.835679: val_loss -0.8993 +2025-10-30 22:24:37.838469: Pseudo dice [np.float32(0.9849), np.float32(0.9919), np.float32(0.9944), np.float32(0.7946)] +2025-10-30 22:24:37.840978: Epoch time: 20.51 s +2025-10-30 22:24:38.991199: +2025-10-30 22:24:38.993113: Epoch 231 +2025-10-30 22:24:38.994874: Current learning rate: 0.00789 +2025-10-30 22:24:58.699686: train_loss -0.9844 +2025-10-30 22:24:58.707600: val_loss -0.8743 +2025-10-30 22:24:58.709595: Pseudo dice [np.float32(0.9849), np.float32(0.9926), np.float32(0.9914), np.float32(0.7656)] +2025-10-30 22:24:58.712040: Epoch time: 19.71 s +2025-10-30 22:24:59.756708: +2025-10-30 22:24:59.758571: Epoch 232 +2025-10-30 22:24:59.760226: Current learning rate: 0.00789 +2025-10-30 22:25:20.217226: train_loss -0.9826 +2025-10-30 22:25:20.219979: val_loss -0.89 +2025-10-30 22:25:20.221842: Pseudo dice [np.float32(0.9847), np.float32(0.9918), np.float32(0.9938), np.float32(0.7724)] +2025-10-30 22:25:20.223493: Epoch time: 20.46 s +2025-10-30 22:25:21.757400: +2025-10-30 22:25:21.759971: Epoch 233 +2025-10-30 22:25:21.761572: Current learning rate: 0.00788 +2025-10-30 22:25:41.071774: train_loss -0.9844 +2025-10-30 22:25:41.074228: val_loss -0.896 +2025-10-30 22:25:41.076200: Pseudo dice [np.float32(0.9851), np.float32(0.9918), np.float32(0.9946), np.float32(0.7961)] +2025-10-30 22:25:41.078137: Epoch time: 19.32 s +2025-10-30 22:25:42.068450: +2025-10-30 22:25:42.070920: Epoch 234 +2025-10-30 22:25:42.072884: Current learning rate: 0.00787 +2025-10-30 22:26:02.701541: train_loss -0.985 +2025-10-30 22:26:02.704213: val_loss -0.8945 +2025-10-30 22:26:02.706443: Pseudo dice [np.float32(0.9836), np.float32(0.9914), np.float32(0.9949), np.float32(0.7947)] +2025-10-30 22:26:02.708027: Epoch time: 20.63 s +2025-10-30 22:26:03.842828: +2025-10-30 22:26:03.844888: Epoch 235 +2025-10-30 22:26:03.846634: Current learning rate: 0.00786 +2025-10-30 22:26:24.597633: train_loss -0.9837 +2025-10-30 22:26:24.600938: val_loss -0.8882 +2025-10-30 22:26:24.602766: Pseudo dice [np.float32(0.9826), np.float32(0.9904), np.float32(0.9935), np.float32(0.7835)] +2025-10-30 22:26:24.604559: Epoch time: 20.76 s +2025-10-30 22:26:25.838276: +2025-10-30 22:26:25.840328: Epoch 236 +2025-10-30 22:26:25.842171: Current learning rate: 0.00785 +2025-10-30 22:26:46.101239: train_loss -0.9809 +2025-10-30 22:26:46.103645: val_loss -0.8978 +2025-10-30 22:26:46.105366: Pseudo dice [np.float32(0.9852), np.float32(0.9922), np.float32(0.9942), np.float32(0.7858)] +2025-10-30 22:26:46.106945: Epoch time: 20.26 s +2025-10-30 22:26:47.251467: +2025-10-30 22:26:47.253492: Epoch 237 +2025-10-30 22:26:47.255151: Current learning rate: 0.00784 +2025-10-30 22:27:06.637532: train_loss -0.9822 +2025-10-30 22:27:06.639926: val_loss -0.8947 +2025-10-30 22:27:06.641765: Pseudo dice [np.float32(0.9857), np.float32(0.9917), np.float32(0.9941), np.float32(0.7849)] +2025-10-30 22:27:06.643549: Epoch time: 19.39 s +2025-10-30 22:27:07.823679: +2025-10-30 22:27:07.830939: Epoch 238 +2025-10-30 22:27:07.833140: Current learning rate: 0.00783 +2025-10-30 22:27:28.273989: train_loss -0.9856 +2025-10-30 22:27:28.276175: val_loss -0.8932 +2025-10-30 22:27:28.302097: Pseudo dice [np.float32(0.9825), np.float32(0.9913), np.float32(0.9944), np.float32(0.7878)] +2025-10-30 22:27:28.303751: Epoch time: 20.45 s +2025-10-30 22:27:29.316410: +2025-10-30 22:27:29.318200: Epoch 239 +2025-10-30 22:27:29.320265: Current learning rate: 0.00782 +2025-10-30 22:27:49.690644: train_loss -0.9844 +2025-10-30 22:27:49.692812: val_loss -0.8964 +2025-10-30 22:27:49.696916: Pseudo dice [np.float32(0.9844), np.float32(0.9926), np.float32(0.9945), np.float32(0.8016)] +2025-10-30 22:27:49.698854: Epoch time: 20.38 s +2025-10-30 22:27:50.846942: +2025-10-30 22:27:50.849385: Epoch 240 +2025-10-30 22:27:50.851170: Current learning rate: 0.00781 +2025-10-30 22:28:09.438215: train_loss -0.9863 +2025-10-30 22:28:09.440696: val_loss -0.8977 +2025-10-30 22:28:09.442569: Pseudo dice [np.float32(0.9863), np.float32(0.9924), np.float32(0.9943), np.float32(0.7941)] +2025-10-30 22:28:09.444462: Epoch time: 18.59 s +2025-10-30 22:28:10.590085: +2025-10-30 22:28:10.593392: Epoch 241 +2025-10-30 22:28:10.596066: Current learning rate: 0.0078 +2025-10-30 22:28:31.217740: train_loss -0.9863 +2025-10-30 22:28:31.223608: val_loss -0.8939 +2025-10-30 22:28:31.225504: Pseudo dice [np.float32(0.9846), np.float32(0.9927), np.float32(0.9942), np.float32(0.7938)] +2025-10-30 22:28:31.227520: Epoch time: 20.63 s +2025-10-30 22:28:32.229806: +2025-10-30 22:28:32.232187: Epoch 242 +2025-10-30 22:28:32.233952: Current learning rate: 0.00779 +2025-10-30 22:28:52.915590: train_loss -0.9867 +2025-10-30 22:28:52.917826: val_loss -0.8957 +2025-10-30 22:28:52.919466: Pseudo dice [np.float32(0.984), np.float32(0.9923), np.float32(0.9948), np.float32(0.8028)] +2025-10-30 22:28:52.921069: Epoch time: 20.69 s +2025-10-30 22:28:53.972774: +2025-10-30 22:28:53.974744: Epoch 243 +2025-10-30 22:28:53.976364: Current learning rate: 0.00778 +2025-10-30 22:29:14.604172: train_loss -0.9869 +2025-10-30 22:29:14.607047: val_loss -0.889 +2025-10-30 22:29:14.609359: Pseudo dice [np.float32(0.9838), np.float32(0.9915), np.float32(0.9938), np.float32(0.785)] +2025-10-30 22:29:14.611302: Epoch time: 20.63 s +2025-10-30 22:29:15.656099: +2025-10-30 22:29:15.658771: Epoch 244 +2025-10-30 22:29:15.660550: Current learning rate: 0.00777 +2025-10-30 22:29:34.861668: train_loss -0.9871 +2025-10-30 22:29:34.864753: val_loss -0.8982 +2025-10-30 22:29:34.866508: Pseudo dice [np.float32(0.9825), np.float32(0.9919), np.float32(0.9946), np.float32(0.8049)] +2025-10-30 22:29:34.868390: Epoch time: 19.21 s +2025-10-30 22:29:36.091444: +2025-10-30 22:29:36.095170: Epoch 245 +2025-10-30 22:29:36.098975: Current learning rate: 0.00777 +2025-10-30 22:29:56.484296: train_loss -0.9862 +2025-10-30 22:29:56.486719: val_loss -0.8931 +2025-10-30 22:29:56.488517: Pseudo dice [np.float32(0.9846), np.float32(0.9921), np.float32(0.9947), np.float32(0.7924)] +2025-10-30 22:29:56.490431: Epoch time: 20.4 s +2025-10-30 22:29:58.120793: +2025-10-30 22:29:58.122737: Epoch 246 +2025-10-30 22:29:58.124533: Current learning rate: 0.00776 +2025-10-30 22:30:18.743955: train_loss -0.9842 +2025-10-30 22:30:18.747419: val_loss -0.8957 +2025-10-30 22:30:18.749009: Pseudo dice [np.float32(0.9838), np.float32(0.9916), np.float32(0.9946), np.float32(0.7889)] +2025-10-30 22:30:18.750570: Epoch time: 20.62 s +2025-10-30 22:30:19.933108: +2025-10-30 22:30:19.935395: Epoch 247 +2025-10-30 22:30:19.937337: Current learning rate: 0.00775 +2025-10-30 22:30:39.260348: train_loss -0.9835 +2025-10-30 22:30:39.263622: val_loss -0.8961 +2025-10-30 22:30:39.265242: Pseudo dice [np.float32(0.985), np.float32(0.9916), np.float32(0.9942), np.float32(0.7953)] +2025-10-30 22:30:39.267177: Epoch time: 19.33 s +2025-10-30 22:30:40.365737: +2025-10-30 22:30:40.368565: Epoch 248 +2025-10-30 22:30:40.370769: Current learning rate: 0.00774 +2025-10-30 22:31:01.001792: train_loss -0.9847 +2025-10-30 22:31:01.004800: val_loss -0.8907 +2025-10-30 22:31:01.006560: Pseudo dice [np.float32(0.9851), np.float32(0.9917), np.float32(0.9942), np.float32(0.7819)] +2025-10-30 22:31:01.008110: Epoch time: 20.64 s +2025-10-30 22:31:02.213933: +2025-10-30 22:31:02.216644: Epoch 249 +2025-10-30 22:31:02.218498: Current learning rate: 0.00773 +2025-10-30 22:31:22.544907: train_loss -0.9846 +2025-10-30 22:31:22.547826: val_loss -0.8938 +2025-10-30 22:31:22.550807: Pseudo dice [np.float32(0.9853), np.float32(0.9921), np.float32(0.9944), np.float32(0.786)] +2025-10-30 22:31:22.553074: Epoch time: 20.33 s +2025-10-30 22:31:24.870662: +2025-10-30 22:31:24.873580: Epoch 250 +2025-10-30 22:31:24.875734: Current learning rate: 0.00772 +2025-10-30 22:31:44.946532: train_loss -0.9853 +2025-10-30 22:31:44.949107: val_loss -0.8915 +2025-10-30 22:31:44.951147: Pseudo dice [np.float32(0.9841), np.float32(0.9918), np.float32(0.9943), np.float32(0.7825)] +2025-10-30 22:31:44.953124: Epoch time: 20.08 s +2025-10-30 22:31:46.130190: +2025-10-30 22:31:46.132091: Epoch 251 +2025-10-30 22:31:46.134068: Current learning rate: 0.00771 +2025-10-30 22:32:06.746529: train_loss -0.9867 +2025-10-30 22:32:06.753142: val_loss -0.8991 +2025-10-30 22:32:06.754785: Pseudo dice [np.float32(0.9841), np.float32(0.9925), np.float32(0.9949), np.float32(0.8037)] +2025-10-30 22:32:06.756492: Epoch time: 20.62 s +2025-10-30 22:32:08.053169: +2025-10-30 22:32:08.055514: Epoch 252 +2025-10-30 22:32:08.057253: Current learning rate: 0.0077 +2025-10-30 22:32:28.633120: train_loss -0.9867 +2025-10-30 22:32:28.636465: val_loss -0.8923 +2025-10-30 22:32:28.638063: Pseudo dice [np.float32(0.9841), np.float32(0.992), np.float32(0.9946), np.float32(0.7952)] +2025-10-30 22:32:28.639691: Epoch time: 20.58 s +2025-10-30 22:32:29.836046: +2025-10-30 22:32:29.838318: Epoch 253 +2025-10-30 22:32:29.840128: Current learning rate: 0.00769 +2025-10-30 22:32:49.205555: train_loss -0.987 +2025-10-30 22:32:49.213790: val_loss -0.8844 +2025-10-30 22:32:49.217208: Pseudo dice [np.float32(0.9841), np.float32(0.9916), np.float32(0.994), np.float32(0.7631)] +2025-10-30 22:32:49.226590: Epoch time: 19.37 s +2025-10-30 22:32:50.447107: +2025-10-30 22:32:50.451695: Epoch 254 +2025-10-30 22:32:50.454888: Current learning rate: 0.00768 +2025-10-30 22:33:06.031712: train_loss -0.9867 +2025-10-30 22:33:06.037547: val_loss -0.8939 +2025-10-30 22:33:06.039263: Pseudo dice [np.float32(0.9854), np.float32(0.9923), np.float32(0.9945), np.float32(0.7929)] +2025-10-30 22:33:06.040870: Epoch time: 15.59 s +2025-10-30 22:33:07.171671: +2025-10-30 22:33:07.175180: Epoch 255 +2025-10-30 22:33:07.177772: Current learning rate: 0.00767 +2025-10-30 22:33:27.606407: train_loss -0.9865 +2025-10-30 22:33:27.608760: val_loss -0.8924 +2025-10-30 22:33:27.610415: Pseudo dice [np.float32(0.9838), np.float32(0.9919), np.float32(0.9952), np.float32(0.7999)] +2025-10-30 22:33:27.612089: Epoch time: 20.44 s +2025-10-30 22:33:28.600851: +2025-10-30 22:33:28.603010: Epoch 256 +2025-10-30 22:33:28.604547: Current learning rate: 0.00766 +2025-10-30 22:33:48.894524: train_loss -0.9865 +2025-10-30 22:33:48.897232: val_loss -0.8979 +2025-10-30 22:33:48.898892: Pseudo dice [np.float32(0.9854), np.float32(0.9919), np.float32(0.9951), np.float32(0.8073)] +2025-10-30 22:33:48.900814: Epoch time: 20.3 s +2025-10-30 22:33:50.016980: +2025-10-30 22:33:50.018743: Epoch 257 +2025-10-30 22:33:50.020406: Current learning rate: 0.00765 +2025-10-30 22:34:10.220725: train_loss -0.9874 +2025-10-30 22:34:10.222697: val_loss -0.8939 +2025-10-30 22:34:10.224315: Pseudo dice [np.float32(0.9834), np.float32(0.9923), np.float32(0.9948), np.float32(0.793)] +2025-10-30 22:34:10.225821: Epoch time: 20.21 s +2025-10-30 22:34:11.624143: +2025-10-30 22:34:11.626250: Epoch 258 +2025-10-30 22:34:11.628170: Current learning rate: 0.00764 +2025-10-30 22:34:32.119509: train_loss -0.9767 +2025-10-30 22:34:32.130059: val_loss -0.9054 +2025-10-30 22:34:32.136027: Pseudo dice [np.float32(0.9837), np.float32(0.9914), np.float32(0.9944), np.float32(0.8018)] +2025-10-30 22:34:32.138680: Epoch time: 20.5 s +2025-10-30 22:34:33.386592: +2025-10-30 22:34:33.391612: Epoch 259 +2025-10-30 22:34:33.393492: Current learning rate: 0.00764 +2025-10-30 22:34:53.760382: train_loss -0.9686 +2025-10-30 22:34:53.765516: val_loss -0.9012 +2025-10-30 22:34:53.767239: Pseudo dice [np.float32(0.9828), np.float32(0.9888), np.float32(0.9935), np.float32(0.7984)] +2025-10-30 22:34:53.768766: Epoch time: 20.38 s +2025-10-30 22:34:54.795576: +2025-10-30 22:34:54.797268: Epoch 260 +2025-10-30 22:34:54.798709: Current learning rate: 0.00763 +2025-10-30 22:35:15.280814: train_loss -0.9685 +2025-10-30 22:35:15.282991: val_loss -0.9056 +2025-10-30 22:35:15.284572: Pseudo dice [np.float32(0.9835), np.float32(0.9919), np.float32(0.9947), np.float32(0.7924)] +2025-10-30 22:35:15.285968: Epoch time: 20.49 s +2025-10-30 22:35:16.530304: +2025-10-30 22:35:16.532195: Epoch 261 +2025-10-30 22:35:16.533864: Current learning rate: 0.00762 +2025-10-30 22:35:35.869368: train_loss -0.9712 +2025-10-30 22:35:35.871921: val_loss -0.9073 +2025-10-30 22:35:35.873684: Pseudo dice [np.float32(0.9833), np.float32(0.9902), np.float32(0.9943), np.float32(0.8044)] +2025-10-30 22:35:35.875382: Epoch time: 19.34 s +2025-10-30 22:35:37.004243: +2025-10-30 22:35:37.005998: Epoch 262 +2025-10-30 22:35:37.007544: Current learning rate: 0.00761 +2025-10-30 22:35:57.232702: train_loss -0.9763 +2025-10-30 22:35:57.235836: val_loss -0.8945 +2025-10-30 22:35:57.237378: Pseudo dice [np.float32(0.9847), np.float32(0.9909), np.float32(0.9943), np.float32(0.7801)] +2025-10-30 22:35:57.239101: Epoch time: 20.23 s +2025-10-30 22:35:58.328635: +2025-10-30 22:35:58.330242: Epoch 263 +2025-10-30 22:35:58.332613: Current learning rate: 0.0076 +2025-10-30 22:36:17.577768: train_loss -0.9811 +2025-10-30 22:36:17.580676: val_loss -0.9018 +2025-10-30 22:36:17.582262: Pseudo dice [np.float32(0.9814), np.float32(0.991), np.float32(0.9948), np.float32(0.8026)] +2025-10-30 22:36:17.583785: Epoch time: 19.25 s +2025-10-30 22:36:18.691498: +2025-10-30 22:36:18.693583: Epoch 264 +2025-10-30 22:36:18.695402: Current learning rate: 0.00759 +2025-10-30 22:36:39.344280: train_loss -0.9827 +2025-10-30 22:36:39.346847: val_loss -0.9048 +2025-10-30 22:36:39.348705: Pseudo dice [np.float32(0.9831), np.float32(0.9911), np.float32(0.9947), np.float32(0.811)] +2025-10-30 22:36:39.351076: Epoch time: 20.65 s +2025-10-30 22:36:40.642490: +2025-10-30 22:36:40.645139: Epoch 265 +2025-10-30 22:36:40.647498: Current learning rate: 0.00758 +2025-10-30 22:37:01.177479: train_loss -0.9828 +2025-10-30 22:37:01.180063: val_loss -0.9054 +2025-10-30 22:37:01.182391: Pseudo dice [np.float32(0.985), np.float32(0.9916), np.float32(0.9946), np.float32(0.7981)] +2025-10-30 22:37:01.184420: Epoch time: 20.54 s +2025-10-30 22:37:02.373161: +2025-10-30 22:37:02.375087: Epoch 266 +2025-10-30 22:37:02.376894: Current learning rate: 0.00757 +2025-10-30 22:37:23.007671: train_loss -0.9849 +2025-10-30 22:37:23.009876: val_loss -0.9024 +2025-10-30 22:37:23.011454: Pseudo dice [np.float32(0.9853), np.float32(0.9921), np.float32(0.9944), np.float32(0.8034)] +2025-10-30 22:37:23.012872: Epoch time: 20.64 s +2025-10-30 22:37:24.008736: +2025-10-30 22:37:24.010592: Epoch 267 +2025-10-30 22:37:24.012106: Current learning rate: 0.00756 +2025-10-30 22:37:44.682775: train_loss -0.9854 +2025-10-30 22:37:44.686280: val_loss -0.9056 +2025-10-30 22:37:44.688101: Pseudo dice [np.float32(0.9853), np.float32(0.9922), np.float32(0.9949), np.float32(0.8051)] +2025-10-30 22:37:44.690100: Epoch time: 20.68 s +2025-10-30 22:37:45.805593: +2025-10-30 22:37:45.808349: Epoch 268 +2025-10-30 22:37:45.811066: Current learning rate: 0.00755 +2025-10-30 22:38:05.150050: train_loss -0.9839 +2025-10-30 22:38:05.160091: val_loss -0.9009 +2025-10-30 22:38:05.164545: Pseudo dice [np.float32(0.9861), np.float32(0.9929), np.float32(0.995), np.float32(0.7998)] +2025-10-30 22:38:05.169257: Epoch time: 19.35 s +2025-10-30 22:38:06.186697: +2025-10-30 22:38:06.190468: Epoch 269 +2025-10-30 22:38:06.193819: Current learning rate: 0.00754 +2025-10-30 22:38:26.099289: train_loss -0.9851 +2025-10-30 22:38:26.102527: val_loss -0.898 +2025-10-30 22:38:26.104127: Pseudo dice [np.float32(0.9843), np.float32(0.9919), np.float32(0.9943), np.float32(0.7951)] +2025-10-30 22:38:26.105848: Epoch time: 19.91 s +2025-10-30 22:38:27.590635: +2025-10-30 22:38:27.593103: Epoch 270 +2025-10-30 22:38:27.594949: Current learning rate: 0.00753 +2025-10-30 22:38:48.156827: train_loss -0.9848 +2025-10-30 22:38:48.159409: val_loss -0.8967 +2025-10-30 22:38:48.162118: Pseudo dice [np.float32(0.9833), np.float32(0.9915), np.float32(0.9943), np.float32(0.7944)] +2025-10-30 22:38:48.164344: Epoch time: 20.57 s +2025-10-30 22:38:49.184194: +2025-10-30 22:38:49.186337: Epoch 271 +2025-10-30 22:38:49.188451: Current learning rate: 0.00752 +2025-10-30 22:39:09.688412: train_loss -0.9858 +2025-10-30 22:39:09.692044: val_loss -0.8951 +2025-10-30 22:39:09.694015: Pseudo dice [np.float32(0.9829), np.float32(0.9919), np.float32(0.9946), np.float32(0.7994)] +2025-10-30 22:39:09.696566: Epoch time: 20.51 s +2025-10-30 22:39:10.823606: +2025-10-30 22:39:10.826403: Epoch 272 +2025-10-30 22:39:10.828255: Current learning rate: 0.00751 +2025-10-30 22:39:31.571789: train_loss -0.9855 +2025-10-30 22:39:31.574227: val_loss -0.8937 +2025-10-30 22:39:31.575987: Pseudo dice [np.float32(0.9839), np.float32(0.9918), np.float32(0.9943), np.float32(0.7904)] +2025-10-30 22:39:31.577705: Epoch time: 20.75 s +2025-10-30 22:39:32.819025: +2025-10-30 22:39:32.820834: Epoch 273 +2025-10-30 22:39:32.822478: Current learning rate: 0.00751 +2025-10-30 22:39:53.259148: train_loss -0.9856 +2025-10-30 22:39:53.261781: val_loss -0.9012 +2025-10-30 22:39:53.263506: Pseudo dice [np.float32(0.9861), np.float32(0.9927), np.float32(0.9945), np.float32(0.7978)] +2025-10-30 22:39:53.265379: Epoch time: 20.44 s +2025-10-30 22:39:54.431003: +2025-10-30 22:39:54.433117: Epoch 274 +2025-10-30 22:39:54.434826: Current learning rate: 0.0075 +2025-10-30 22:40:14.743603: train_loss -0.9872 +2025-10-30 22:40:14.746634: val_loss -0.8962 +2025-10-30 22:40:14.748322: Pseudo dice [np.float32(0.9855), np.float32(0.9933), np.float32(0.9946), np.float32(0.7992)] +2025-10-30 22:40:14.750046: Epoch time: 20.31 s +2025-10-30 22:40:15.805577: +2025-10-30 22:40:15.807820: Epoch 275 +2025-10-30 22:40:15.809591: Current learning rate: 0.00749 +2025-10-30 22:40:35.214142: train_loss -0.9866 +2025-10-30 22:40:35.217366: val_loss -0.8979 +2025-10-30 22:40:35.219059: Pseudo dice [np.float32(0.9863), np.float32(0.9928), np.float32(0.9943), np.float32(0.7927)] +2025-10-30 22:40:35.220680: Epoch time: 19.41 s +2025-10-30 22:40:36.223424: +2025-10-30 22:40:36.226211: Epoch 276 +2025-10-30 22:40:36.227898: Current learning rate: 0.00748 +2025-10-30 22:40:55.575849: train_loss -0.9854 +2025-10-30 22:40:55.581545: val_loss -0.8974 +2025-10-30 22:40:55.583025: Pseudo dice [np.float32(0.9852), np.float32(0.9923), np.float32(0.9948), np.float32(0.8047)] +2025-10-30 22:40:55.584464: Epoch time: 19.35 s +2025-10-30 22:40:56.778531: +2025-10-30 22:40:56.783775: Epoch 277 +2025-10-30 22:40:56.785685: Current learning rate: 0.00747 +2025-10-30 22:41:17.482024: train_loss -0.9852 +2025-10-30 22:41:17.485069: val_loss -0.8985 +2025-10-30 22:41:17.486677: Pseudo dice [np.float32(0.9849), np.float32(0.9928), np.float32(0.9949), np.float32(0.7935)] +2025-10-30 22:41:17.488214: Epoch time: 20.71 s +2025-10-30 22:41:18.673526: +2025-10-30 22:41:18.675317: Epoch 278 +2025-10-30 22:41:18.676856: Current learning rate: 0.00746 +2025-10-30 22:41:39.104054: train_loss -0.986 +2025-10-30 22:41:39.106279: val_loss -0.8981 +2025-10-30 22:41:39.108175: Pseudo dice [np.float32(0.9849), np.float32(0.9919), np.float32(0.9946), np.float32(0.797)] +2025-10-30 22:41:39.109953: Epoch time: 20.43 s +2025-10-30 22:41:40.100627: +2025-10-30 22:41:40.102989: Epoch 279 +2025-10-30 22:41:40.104900: Current learning rate: 0.00745 +2025-10-30 22:42:00.649104: train_loss -0.9865 +2025-10-30 22:42:00.652099: val_loss -0.8918 +2025-10-30 22:42:00.653903: Pseudo dice [np.float32(0.9844), np.float32(0.9924), np.float32(0.9941), np.float32(0.781)] +2025-10-30 22:42:00.655705: Epoch time: 20.55 s +2025-10-30 22:42:01.690780: +2025-10-30 22:42:01.692603: Epoch 280 +2025-10-30 22:42:01.694373: Current learning rate: 0.00744 +2025-10-30 22:42:22.733156: train_loss -0.9863 +2025-10-30 22:42:22.736630: val_loss -0.8824 +2025-10-30 22:42:22.738630: Pseudo dice [np.float32(0.9852), np.float32(0.9925), np.float32(0.9917), np.float32(0.7744)] +2025-10-30 22:42:22.740518: Epoch time: 21.04 s +2025-10-30 22:42:24.035270: +2025-10-30 22:42:24.037559: Epoch 281 +2025-10-30 22:42:24.039546: Current learning rate: 0.00743 +2025-10-30 22:42:43.999059: train_loss -0.9864 +2025-10-30 22:42:44.001504: val_loss -0.8677 +2025-10-30 22:42:44.003057: Pseudo dice [np.float32(0.9834), np.float32(0.9918), np.float32(0.9901), np.float32(0.7633)] +2025-10-30 22:42:44.004621: Epoch time: 19.97 s +2025-10-30 22:42:45.703638: +2025-10-30 22:42:45.705531: Epoch 282 +2025-10-30 22:42:45.707349: Current learning rate: 0.00742 +2025-10-30 22:43:04.657682: train_loss -0.9871 +2025-10-30 22:43:04.660708: val_loss -0.8792 +2025-10-30 22:43:04.662569: Pseudo dice [np.float32(0.9852), np.float32(0.9922), np.float32(0.9914), np.float32(0.7784)] +2025-10-30 22:43:04.664623: Epoch time: 18.96 s +2025-10-30 22:43:05.940211: +2025-10-30 22:43:05.942010: Epoch 283 +2025-10-30 22:43:05.943539: Current learning rate: 0.00741 +2025-10-30 22:43:26.408832: train_loss -0.9866 +2025-10-30 22:43:26.412017: val_loss -0.8913 +2025-10-30 22:43:26.413928: Pseudo dice [np.float32(0.9842), np.float32(0.9925), np.float32(0.993), np.float32(0.7942)] +2025-10-30 22:43:26.415650: Epoch time: 20.47 s +2025-10-30 22:43:27.415762: +2025-10-30 22:43:27.417901: Epoch 284 +2025-10-30 22:43:27.419535: Current learning rate: 0.0074 +2025-10-30 22:43:48.107069: train_loss -0.9866 +2025-10-30 22:43:48.113114: val_loss -0.884 +2025-10-30 22:43:48.114833: Pseudo dice [np.float32(0.9832), np.float32(0.9918), np.float32(0.9916), np.float32(0.7881)] +2025-10-30 22:43:48.116850: Epoch time: 20.69 s +2025-10-30 22:43:49.360953: +2025-10-30 22:43:49.362825: Epoch 285 +2025-10-30 22:43:49.364485: Current learning rate: 0.00739 +2025-10-30 22:44:09.647614: train_loss -0.9875 +2025-10-30 22:44:09.649985: val_loss -0.8913 +2025-10-30 22:44:09.652177: Pseudo dice [np.float32(0.9846), np.float32(0.9929), np.float32(0.9937), np.float32(0.79)] +2025-10-30 22:44:09.654218: Epoch time: 20.29 s +2025-10-30 22:44:10.864023: +2025-10-30 22:44:10.866057: Epoch 286 +2025-10-30 22:44:10.867804: Current learning rate: 0.00738 +2025-10-30 22:44:31.335377: train_loss -0.9869 +2025-10-30 22:44:31.337815: val_loss -0.8938 +2025-10-30 22:44:31.339418: Pseudo dice [np.float32(0.9848), np.float32(0.992), np.float32(0.9946), np.float32(0.8004)] +2025-10-30 22:44:31.341615: Epoch time: 20.47 s +2025-10-30 22:44:32.372566: +2025-10-30 22:44:32.374708: Epoch 287 +2025-10-30 22:44:32.376560: Current learning rate: 0.00738 +2025-10-30 22:44:52.830879: train_loss -0.9837 +2025-10-30 22:44:52.833361: val_loss -0.8954 +2025-10-30 22:44:52.835669: Pseudo dice [np.float32(0.9848), np.float32(0.9918), np.float32(0.9946), np.float32(0.7945)] +2025-10-30 22:44:52.837942: Epoch time: 20.46 s +2025-10-30 22:44:54.015573: +2025-10-30 22:44:54.017334: Epoch 288 +2025-10-30 22:44:54.019053: Current learning rate: 0.00737 +2025-10-30 22:45:13.356786: train_loss -0.9856 +2025-10-30 22:45:13.359023: val_loss -0.8882 +2025-10-30 22:45:13.360621: Pseudo dice [np.float32(0.9838), np.float32(0.9913), np.float32(0.9943), np.float32(0.7785)] +2025-10-30 22:45:13.362184: Epoch time: 19.34 s +2025-10-30 22:45:14.559160: +2025-10-30 22:45:14.561318: Epoch 289 +2025-10-30 22:45:14.562977: Current learning rate: 0.00736 +2025-10-30 22:45:34.027586: train_loss -0.9862 +2025-10-30 22:45:34.034291: val_loss -0.8851 +2025-10-30 22:45:34.036251: Pseudo dice [np.float32(0.9839), np.float32(0.9915), np.float32(0.9937), np.float32(0.7788)] +2025-10-30 22:45:34.037850: Epoch time: 19.47 s +2025-10-30 22:45:35.127903: +2025-10-30 22:45:35.130021: Epoch 290 +2025-10-30 22:45:35.131915: Current learning rate: 0.00735 +2025-10-30 22:45:55.667715: train_loss -0.9878 +2025-10-30 22:45:55.669853: val_loss -0.8843 +2025-10-30 22:45:55.671419: Pseudo dice [np.float32(0.983), np.float32(0.9914), np.float32(0.9939), np.float32(0.7773)] +2025-10-30 22:45:55.673033: Epoch time: 20.54 s +2025-10-30 22:45:56.687704: +2025-10-30 22:45:56.689406: Epoch 291 +2025-10-30 22:45:56.690871: Current learning rate: 0.00734 +2025-10-30 22:46:17.153138: train_loss -0.9879 +2025-10-30 22:46:17.155916: val_loss -0.8893 +2025-10-30 22:46:17.157944: Pseudo dice [np.float32(0.9848), np.float32(0.9911), np.float32(0.9939), np.float32(0.7865)] +2025-10-30 22:46:17.159862: Epoch time: 20.47 s +2025-10-30 22:46:18.224114: +2025-10-30 22:46:18.226331: Epoch 292 +2025-10-30 22:46:18.228209: Current learning rate: 0.00733 +2025-10-30 22:46:38.907107: train_loss -0.987 +2025-10-30 22:46:38.911027: val_loss -0.8992 +2025-10-30 22:46:38.913349: Pseudo dice [np.float32(0.9844), np.float32(0.992), np.float32(0.9948), np.float32(0.7996)] +2025-10-30 22:46:38.915521: Epoch time: 20.68 s +2025-10-30 22:46:39.868465: +2025-10-30 22:46:39.870779: Epoch 293 +2025-10-30 22:46:39.874113: Current learning rate: 0.00732 +2025-10-30 22:47:00.220239: train_loss -0.9866 +2025-10-30 22:47:00.223227: val_loss -0.8902 +2025-10-30 22:47:00.225874: Pseudo dice [np.float32(0.9826), np.float32(0.9911), np.float32(0.9946), np.float32(0.7913)] +2025-10-30 22:47:00.227961: Epoch time: 20.35 s +2025-10-30 22:47:01.442553: +2025-10-30 22:47:01.444517: Epoch 294 +2025-10-30 22:47:01.446806: Current learning rate: 0.00731 +2025-10-30 22:47:21.831432: train_loss -0.9868 +2025-10-30 22:47:21.834028: val_loss -0.8979 +2025-10-30 22:47:21.836257: Pseudo dice [np.float32(0.984), np.float32(0.9923), np.float32(0.995), np.float32(0.7975)] +2025-10-30 22:47:21.838139: Epoch time: 20.39 s +2025-10-30 22:47:23.427829: +2025-10-30 22:47:23.429807: Epoch 295 +2025-10-30 22:47:23.431825: Current learning rate: 0.0073 +2025-10-30 22:47:41.857721: train_loss -0.9863 +2025-10-30 22:47:41.860699: val_loss -0.8921 +2025-10-30 22:47:41.862397: Pseudo dice [np.float32(0.9842), np.float32(0.9927), np.float32(0.9946), np.float32(0.7885)] +2025-10-30 22:47:41.864209: Epoch time: 18.43 s +2025-10-30 22:47:43.077923: +2025-10-30 22:47:43.080397: Epoch 296 +2025-10-30 22:47:43.082711: Current learning rate: 0.00729 +2025-10-30 22:48:03.675789: train_loss -0.987 +2025-10-30 22:48:03.677894: val_loss -0.8971 +2025-10-30 22:48:03.680203: Pseudo dice [np.float32(0.9855), np.float32(0.9927), np.float32(0.9942), np.float32(0.796)] +2025-10-30 22:48:03.682480: Epoch time: 20.6 s +2025-10-30 22:48:04.572793: +2025-10-30 22:48:04.575215: Epoch 297 +2025-10-30 22:48:04.577322: Current learning rate: 0.00728 +2025-10-30 22:48:25.129380: train_loss -0.9873 +2025-10-30 22:48:25.131614: val_loss -0.8983 +2025-10-30 22:48:25.133284: Pseudo dice [np.float32(0.9839), np.float32(0.992), np.float32(0.9946), np.float32(0.8059)] +2025-10-30 22:48:25.135596: Epoch time: 20.56 s +2025-10-30 22:48:26.436675: +2025-10-30 22:48:26.438553: Epoch 298 +2025-10-30 22:48:26.440050: Current learning rate: 0.00727 +2025-10-30 22:48:46.805961: train_loss -0.9875 +2025-10-30 22:48:46.809099: val_loss -0.8939 +2025-10-30 22:48:46.811046: Pseudo dice [np.float32(0.9849), np.float32(0.9917), np.float32(0.9945), np.float32(0.7999)] +2025-10-30 22:48:46.812939: Epoch time: 20.37 s +2025-10-30 22:48:47.986083: +2025-10-30 22:48:47.987838: Epoch 299 +2025-10-30 22:48:47.989799: Current learning rate: 0.00726 +2025-10-30 22:49:08.661928: train_loss -0.9873 +2025-10-30 22:49:08.664118: val_loss -0.8971 +2025-10-30 22:49:08.665835: Pseudo dice [np.float32(0.9866), np.float32(0.9928), np.float32(0.9946), np.float32(0.7974)] +2025-10-30 22:49:08.667618: Epoch time: 20.68 s +2025-10-30 22:49:11.203932: +2025-10-30 22:49:11.206486: Epoch 300 +2025-10-30 22:49:11.208838: Current learning rate: 0.00725 +2025-10-30 22:49:31.720970: train_loss -0.9879 +2025-10-30 22:49:31.724219: val_loss -0.8871 +2025-10-30 22:49:31.725895: Pseudo dice [np.float32(0.9856), np.float32(0.9915), np.float32(0.9934), np.float32(0.7761)] +2025-10-30 22:49:31.728624: Epoch time: 20.52 s +2025-10-30 22:49:32.913274: +2025-10-30 22:49:32.915358: Epoch 301 +2025-10-30 22:49:32.917327: Current learning rate: 0.00724 +2025-10-30 22:49:52.792640: train_loss -0.9878 +2025-10-30 22:49:52.795794: val_loss -0.9029 +2025-10-30 22:49:52.798093: Pseudo dice [np.float32(0.9848), np.float32(0.9924), np.float32(0.995), np.float32(0.819)] +2025-10-30 22:49:52.800282: Epoch time: 19.88 s +2025-10-30 22:49:54.014565: +2025-10-30 22:49:54.020567: Epoch 302 +2025-10-30 22:49:54.022359: Current learning rate: 0.00724 +2025-10-30 22:50:12.907764: train_loss -0.9874 +2025-10-30 22:50:12.910058: val_loss -0.8844 +2025-10-30 22:50:12.911756: Pseudo dice [np.float32(0.9868), np.float32(0.9918), np.float32(0.9941), np.float32(0.7743)] +2025-10-30 22:50:12.913315: Epoch time: 18.9 s +2025-10-30 22:50:14.018672: +2025-10-30 22:50:14.020760: Epoch 303 +2025-10-30 22:50:14.022904: Current learning rate: 0.00723 +2025-10-30 22:50:34.333497: train_loss -0.9872 +2025-10-30 22:50:34.335948: val_loss -0.8945 +2025-10-30 22:50:34.337669: Pseudo dice [np.float32(0.984), np.float32(0.9913), np.float32(0.9946), np.float32(0.8021)] +2025-10-30 22:50:34.339350: Epoch time: 20.32 s +2025-10-30 22:50:35.533602: +2025-10-30 22:50:35.535350: Epoch 304 +2025-10-30 22:50:35.537007: Current learning rate: 0.00722 +2025-10-30 22:50:55.997121: train_loss -0.9874 +2025-10-30 22:50:55.999706: val_loss -0.8916 +2025-10-30 22:50:56.001301: Pseudo dice [np.float32(0.9853), np.float32(0.9912), np.float32(0.9941), np.float32(0.7939)] +2025-10-30 22:50:56.003030: Epoch time: 20.47 s +2025-10-30 22:50:57.188994: +2025-10-30 22:50:57.191025: Epoch 305 +2025-10-30 22:50:57.192877: Current learning rate: 0.00721 +2025-10-30 22:51:17.973475: train_loss -0.9835 +2025-10-30 22:51:17.976322: val_loss -0.9025 +2025-10-30 22:51:17.979012: Pseudo dice [np.float32(0.9862), np.float32(0.9924), np.float32(0.9944), np.float32(0.8074)] +2025-10-30 22:51:17.981436: Epoch time: 20.79 s +2025-10-30 22:51:19.258462: +2025-10-30 22:51:19.260659: Epoch 306 +2025-10-30 22:51:19.262688: Current learning rate: 0.0072 +2025-10-30 22:51:39.637336: train_loss -0.9675 +2025-10-30 22:51:39.640296: val_loss -0.8984 +2025-10-30 22:51:39.642589: Pseudo dice [np.float32(0.9838), np.float32(0.9923), np.float32(0.993), np.float32(0.7824)] +2025-10-30 22:51:39.644337: Epoch time: 20.38 s +2025-10-30 22:51:41.038154: +2025-10-30 22:51:41.040210: Epoch 307 +2025-10-30 22:51:41.042259: Current learning rate: 0.00719 +2025-10-30 22:52:01.420808: train_loss -0.9744 +2025-10-30 22:52:01.433365: val_loss -0.9015 +2025-10-30 22:52:01.436371: Pseudo dice [np.float32(0.9868), np.float32(0.9931), np.float32(0.9909), np.float32(0.8112)] +2025-10-30 22:52:01.442337: Epoch time: 20.38 s +2025-10-30 22:52:02.648715: +2025-10-30 22:52:02.652499: Epoch 308 +2025-10-30 22:52:02.655013: Current learning rate: 0.00718 +2025-10-30 22:52:21.931370: train_loss -0.9769 +2025-10-30 22:52:21.936919: val_loss -0.9105 +2025-10-30 22:52:21.938946: Pseudo dice [np.float32(0.9842), np.float32(0.9918), np.float32(0.9945), np.float32(0.8182)] +2025-10-30 22:52:21.940896: Epoch time: 19.28 s +2025-10-30 22:52:23.064634: +2025-10-30 22:52:23.066291: Epoch 309 +2025-10-30 22:52:23.068714: Current learning rate: 0.00717 +2025-10-30 22:52:42.018076: train_loss -0.9826 +2025-10-30 22:52:42.020657: val_loss -0.9006 +2025-10-30 22:52:42.022292: Pseudo dice [np.float32(0.9864), np.float32(0.9926), np.float32(0.9951), np.float32(0.7886)] +2025-10-30 22:52:42.023915: Epoch time: 18.95 s +2025-10-30 22:52:43.211460: +2025-10-30 22:52:43.214046: Epoch 310 +2025-10-30 22:52:43.216217: Current learning rate: 0.00716 +2025-10-30 22:53:03.647179: train_loss -0.9814 +2025-10-30 22:53:03.650472: val_loss -0.8958 +2025-10-30 22:53:03.652687: Pseudo dice [np.float32(0.9844), np.float32(0.9902), np.float32(0.9935), np.float32(0.7904)] +2025-10-30 22:53:03.656797: Epoch time: 20.44 s +2025-10-30 22:53:04.764132: +2025-10-30 22:53:04.766171: Epoch 311 +2025-10-30 22:53:04.767853: Current learning rate: 0.00715 +2025-10-30 22:53:25.223399: train_loss -0.9805 +2025-10-30 22:53:25.226593: val_loss -0.899 +2025-10-30 22:53:25.228562: Pseudo dice [np.float32(0.9851), np.float32(0.992), np.float32(0.9947), np.float32(0.7949)] +2025-10-30 22:53:25.230433: Epoch time: 20.46 s +2025-10-30 22:53:26.247989: +2025-10-30 22:53:26.250569: Epoch 312 +2025-10-30 22:53:26.252619: Current learning rate: 0.00714 +2025-10-30 22:53:46.484276: train_loss -0.9841 +2025-10-30 22:53:46.486835: val_loss -0.9013 +2025-10-30 22:53:46.489783: Pseudo dice [np.float32(0.9868), np.float32(0.9924), np.float32(0.9944), np.float32(0.7943)] +2025-10-30 22:53:46.491880: Epoch time: 20.24 s +2025-10-30 22:53:47.711932: +2025-10-30 22:53:47.714370: Epoch 313 +2025-10-30 22:53:47.716755: Current learning rate: 0.00713 +2025-10-30 22:54:08.120528: train_loss -0.9854 +2025-10-30 22:54:08.123522: val_loss -0.8973 +2025-10-30 22:54:08.125363: Pseudo dice [np.float32(0.9869), np.float32(0.9922), np.float32(0.9946), np.float32(0.7933)] +2025-10-30 22:54:08.128067: Epoch time: 20.41 s +2025-10-30 22:54:09.149699: +2025-10-30 22:54:09.152593: Epoch 314 +2025-10-30 22:54:09.154534: Current learning rate: 0.00712 +2025-10-30 22:54:28.171304: train_loss -0.9868 +2025-10-30 22:54:28.174829: val_loss -0.8868 +2025-10-30 22:54:28.177070: Pseudo dice [np.float32(0.9853), np.float32(0.9924), np.float32(0.9945), np.float32(0.7783)] +2025-10-30 22:54:28.180088: Epoch time: 19.02 s +2025-10-30 22:54:29.263495: +2025-10-30 22:54:29.265394: Epoch 315 +2025-10-30 22:54:29.267100: Current learning rate: 0.00711 +2025-10-30 22:54:49.787242: train_loss -0.9869 +2025-10-30 22:54:49.789589: val_loss -0.9025 +2025-10-30 22:54:49.791384: Pseudo dice [np.float32(0.9863), np.float32(0.9931), np.float32(0.9948), np.float32(0.8008)] +2025-10-30 22:54:49.793000: Epoch time: 20.53 s +2025-10-30 22:54:50.998611: +2025-10-30 22:54:51.000526: Epoch 316 +2025-10-30 22:54:51.002597: Current learning rate: 0.0071 +2025-10-30 22:55:10.797164: train_loss -0.9858 +2025-10-30 22:55:10.800591: val_loss -0.8923 +2025-10-30 22:55:10.802308: Pseudo dice [np.float32(0.9858), np.float32(0.9917), np.float32(0.9943), np.float32(0.7834)] +2025-10-30 22:55:10.804371: Epoch time: 19.8 s +2025-10-30 22:55:11.909864: +2025-10-30 22:55:11.912073: Epoch 317 +2025-10-30 22:55:11.914334: Current learning rate: 0.0071 +2025-10-30 22:55:32.409211: train_loss -0.9861 +2025-10-30 22:55:32.411830: val_loss -0.8929 +2025-10-30 22:55:32.413619: Pseudo dice [np.float32(0.9835), np.float32(0.9914), np.float32(0.9946), np.float32(0.7949)] +2025-10-30 22:55:32.415324: Epoch time: 20.5 s +2025-10-30 22:55:33.606188: +2025-10-30 22:55:33.608378: Epoch 318 +2025-10-30 22:55:33.610507: Current learning rate: 0.00709 +2025-10-30 22:55:54.116737: train_loss -0.987 +2025-10-30 22:55:54.118948: val_loss -0.9001 +2025-10-30 22:55:54.120704: Pseudo dice [np.float32(0.9855), np.float32(0.9932), np.float32(0.9949), np.float32(0.8085)] +2025-10-30 22:55:54.122316: Epoch time: 20.51 s +2025-10-30 22:55:55.733544: +2025-10-30 22:55:55.735873: Epoch 319 +2025-10-30 22:55:55.737913: Current learning rate: 0.00708 +2025-10-30 22:56:16.303535: train_loss -0.986 +2025-10-30 22:56:16.306530: val_loss -0.8942 +2025-10-30 22:56:16.308272: Pseudo dice [np.float32(0.9825), np.float32(0.9918), np.float32(0.9945), np.float32(0.8001)] +2025-10-30 22:56:16.310074: Epoch time: 20.57 s +2025-10-30 22:56:17.480590: +2025-10-30 22:56:17.482526: Epoch 320 +2025-10-30 22:56:17.484313: Current learning rate: 0.00707 +2025-10-30 22:56:38.183597: train_loss -0.9856 +2025-10-30 22:56:38.187686: val_loss -0.9001 +2025-10-30 22:56:38.192244: Pseudo dice [np.float32(0.9846), np.float32(0.9924), np.float32(0.995), np.float32(0.8122)] +2025-10-30 22:56:38.196888: Epoch time: 20.7 s +2025-10-30 22:56:39.343490: +2025-10-30 22:56:39.346174: Epoch 321 +2025-10-30 22:56:39.348258: Current learning rate: 0.00706 +2025-10-30 22:56:58.983973: train_loss -0.986 +2025-10-30 22:56:58.986789: val_loss -0.9025 +2025-10-30 22:56:58.988444: Pseudo dice [np.float32(0.9856), np.float32(0.9922), np.float32(0.9948), np.float32(0.812)] +2025-10-30 22:56:58.990088: Epoch time: 19.64 s +2025-10-30 22:57:00.219724: +2025-10-30 22:57:00.222872: Epoch 322 +2025-10-30 22:57:00.225410: Current learning rate: 0.00705 +2025-10-30 22:57:20.604575: train_loss -0.988 +2025-10-30 22:57:20.607992: val_loss -0.9048 +2025-10-30 22:57:20.610321: Pseudo dice [np.float32(0.9843), np.float32(0.9927), np.float32(0.9953), np.float32(0.8224)] +2025-10-30 22:57:20.612823: Epoch time: 20.39 s +2025-10-30 22:57:21.636178: +2025-10-30 22:57:21.638296: Epoch 323 +2025-10-30 22:57:21.640070: Current learning rate: 0.00704 +2025-10-30 22:57:39.526343: train_loss -0.9868 +2025-10-30 22:57:39.528517: val_loss -0.8995 +2025-10-30 22:57:39.530075: Pseudo dice [np.float32(0.985), np.float32(0.9926), np.float32(0.9949), np.float32(0.8028)] +2025-10-30 22:57:39.531619: Epoch time: 17.89 s +2025-10-30 22:57:40.644989: +2025-10-30 22:57:40.647172: Epoch 324 +2025-10-30 22:57:40.648911: Current learning rate: 0.00703 +2025-10-30 22:58:01.076658: train_loss -0.987 +2025-10-30 22:58:01.078796: val_loss -0.8912 +2025-10-30 22:58:01.080995: Pseudo dice [np.float32(0.9848), np.float32(0.9917), np.float32(0.9941), np.float32(0.7825)] +2025-10-30 22:58:01.083347: Epoch time: 20.43 s +2025-10-30 22:58:02.099754: +2025-10-30 22:58:02.101525: Epoch 325 +2025-10-30 22:58:02.103216: Current learning rate: 0.00702 +2025-10-30 22:58:22.562960: train_loss -0.9863 +2025-10-30 22:58:22.566288: val_loss -0.8979 +2025-10-30 22:58:22.568406: Pseudo dice [np.float32(0.987), np.float32(0.9928), np.float32(0.9943), np.float32(0.7893)] +2025-10-30 22:58:22.570330: Epoch time: 20.46 s +2025-10-30 22:58:23.817811: +2025-10-30 22:58:23.819808: Epoch 326 +2025-10-30 22:58:23.821750: Current learning rate: 0.00701 +2025-10-30 22:58:44.144124: train_loss -0.9881 +2025-10-30 22:58:44.146501: val_loss -0.8951 +2025-10-30 22:58:44.148041: Pseudo dice [np.float32(0.9855), np.float32(0.9941), np.float32(0.9951), np.float32(0.7937)] +2025-10-30 22:58:44.149446: Epoch time: 20.33 s +2025-10-30 22:58:45.375898: +2025-10-30 22:58:45.377659: Epoch 327 +2025-10-30 22:58:45.379346: Current learning rate: 0.007 +2025-10-30 22:59:04.826230: train_loss -0.988 +2025-10-30 22:59:04.829207: val_loss -0.8934 +2025-10-30 22:59:04.830878: Pseudo dice [np.float32(0.9844), np.float32(0.992), np.float32(0.9945), np.float32(0.7905)] +2025-10-30 22:59:04.832469: Epoch time: 19.45 s +2025-10-30 22:59:06.067492: +2025-10-30 22:59:06.069724: Epoch 328 +2025-10-30 22:59:06.071653: Current learning rate: 0.00699 +2025-10-30 22:59:26.434972: train_loss -0.9877 +2025-10-30 22:59:26.439612: val_loss -0.8862 +2025-10-30 22:59:26.441320: Pseudo dice [np.float32(0.9844), np.float32(0.9923), np.float32(0.9936), np.float32(0.7742)] +2025-10-30 22:59:26.442909: Epoch time: 20.37 s +2025-10-30 22:59:27.473165: +2025-10-30 22:59:27.475516: Epoch 329 +2025-10-30 22:59:27.477443: Current learning rate: 0.00698 +2025-10-30 22:59:48.303334: train_loss -0.9881 +2025-10-30 22:59:48.306761: val_loss -0.8957 +2025-10-30 22:59:48.308431: Pseudo dice [np.float32(0.9858), np.float32(0.992), np.float32(0.9945), np.float32(0.7984)] +2025-10-30 22:59:48.310264: Epoch time: 20.83 s +2025-10-30 22:59:49.562039: +2025-10-30 22:59:49.563843: Epoch 330 +2025-10-30 22:59:49.565521: Current learning rate: 0.00697 +2025-10-30 23:00:09.205845: train_loss -0.988 +2025-10-30 23:00:09.208325: val_loss -0.8919 +2025-10-30 23:00:09.209925: Pseudo dice [np.float32(0.984), np.float32(0.9924), np.float32(0.9943), np.float32(0.7919)] +2025-10-30 23:00:09.212331: Epoch time: 19.65 s +2025-10-30 23:00:10.801172: +2025-10-30 23:00:10.803683: Epoch 331 +2025-10-30 23:00:10.806793: Current learning rate: 0.00696 +2025-10-30 23:00:31.264051: train_loss -0.9865 +2025-10-30 23:00:31.266941: val_loss -0.8949 +2025-10-30 23:00:31.268812: Pseudo dice [np.float32(0.985), np.float32(0.992), np.float32(0.9943), np.float32(0.7988)] +2025-10-30 23:00:31.270426: Epoch time: 20.47 s +2025-10-30 23:00:32.490875: +2025-10-30 23:00:32.493317: Epoch 332 +2025-10-30 23:00:32.495243: Current learning rate: 0.00696 +2025-10-30 23:00:52.879349: train_loss -0.9855 +2025-10-30 23:00:52.881717: val_loss -0.8943 +2025-10-30 23:00:52.883512: Pseudo dice [np.float32(0.9857), np.float32(0.9923), np.float32(0.9948), np.float32(0.7879)] +2025-10-30 23:00:52.885295: Epoch time: 20.39 s +2025-10-30 23:00:53.903878: +2025-10-30 23:00:53.905769: Epoch 333 +2025-10-30 23:00:53.907424: Current learning rate: 0.00695 +2025-10-30 23:01:14.487110: train_loss -0.9879 +2025-10-30 23:01:14.490486: val_loss -0.8985 +2025-10-30 23:01:14.492126: Pseudo dice [np.float32(0.9846), np.float32(0.9928), np.float32(0.995), np.float32(0.8036)] +2025-10-30 23:01:14.493782: Epoch time: 20.58 s +2025-10-30 23:01:15.727931: +2025-10-30 23:01:15.730181: Epoch 334 +2025-10-30 23:01:15.732521: Current learning rate: 0.00694 +2025-10-30 23:01:35.397419: train_loss -0.9886 +2025-10-30 23:01:35.401451: val_loss -0.8927 +2025-10-30 23:01:35.404027: Pseudo dice [np.float32(0.9857), np.float32(0.9919), np.float32(0.9943), np.float32(0.791)] +2025-10-30 23:01:35.406351: Epoch time: 19.67 s +2025-10-30 23:01:36.458392: +2025-10-30 23:01:36.460473: Epoch 335 +2025-10-30 23:01:36.462220: Current learning rate: 0.00693 +2025-10-30 23:01:56.919466: train_loss -0.9885 +2025-10-30 23:01:56.923769: val_loss -0.8951 +2025-10-30 23:01:56.925603: Pseudo dice [np.float32(0.9855), np.float32(0.993), np.float32(0.9947), np.float32(0.7972)] +2025-10-30 23:01:56.927124: Epoch time: 20.46 s +2025-10-30 23:01:57.936905: +2025-10-30 23:01:57.938873: Epoch 336 +2025-10-30 23:01:57.940629: Current learning rate: 0.00692 +2025-10-30 23:02:18.040000: train_loss -0.9888 +2025-10-30 23:02:18.042418: val_loss -0.8985 +2025-10-30 23:02:18.044698: Pseudo dice [np.float32(0.9843), np.float32(0.9918), np.float32(0.9946), np.float32(0.8051)] +2025-10-30 23:02:18.046818: Epoch time: 20.1 s +2025-10-30 23:02:19.086135: +2025-10-30 23:02:19.088780: Epoch 337 +2025-10-30 23:02:19.090912: Current learning rate: 0.00691 +2025-10-30 23:02:38.985456: train_loss -0.9879 +2025-10-30 23:02:38.989283: val_loss -0.8865 +2025-10-30 23:02:38.991163: Pseudo dice [np.float32(0.9844), np.float32(0.992), np.float32(0.994), np.float32(0.7827)] +2025-10-30 23:02:38.993146: Epoch time: 19.9 s +2025-10-30 23:02:40.118534: +2025-10-30 23:02:40.120876: Epoch 338 +2025-10-30 23:02:40.122826: Current learning rate: 0.0069 +2025-10-30 23:03:00.462869: train_loss -0.987 +2025-10-30 23:03:00.465368: val_loss -0.8912 +2025-10-30 23:03:00.467214: Pseudo dice [np.float32(0.9864), np.float32(0.9924), np.float32(0.994), np.float32(0.7826)] +2025-10-30 23:03:00.469024: Epoch time: 20.35 s +2025-10-30 23:03:01.514658: +2025-10-30 23:03:01.516937: Epoch 339 +2025-10-30 23:03:01.518776: Current learning rate: 0.00689 +2025-10-30 23:03:22.123220: train_loss -0.9862 +2025-10-30 23:03:22.125918: val_loss -0.8907 +2025-10-30 23:03:22.127833: Pseudo dice [np.float32(0.9855), np.float32(0.9922), np.float32(0.9944), np.float32(0.7912)] +2025-10-30 23:03:22.129737: Epoch time: 20.61 s +2025-10-30 23:03:23.103239: +2025-10-30 23:03:23.105345: Epoch 340 +2025-10-30 23:03:23.107219: Current learning rate: 0.00688 +2025-10-30 23:03:42.055327: train_loss -0.9879 +2025-10-30 23:03:42.059459: val_loss -0.8928 +2025-10-30 23:03:42.062301: Pseudo dice [np.float32(0.9826), np.float32(0.9914), np.float32(0.9946), np.float32(0.7995)] +2025-10-30 23:03:42.065242: Epoch time: 18.95 s +2025-10-30 23:03:43.244738: +2025-10-30 23:03:43.247125: Epoch 341 +2025-10-30 23:03:43.250122: Current learning rate: 0.00687 +2025-10-30 23:04:03.744967: train_loss -0.9871 +2025-10-30 23:04:03.747443: val_loss -0.8943 +2025-10-30 23:04:03.749197: Pseudo dice [np.float32(0.9845), np.float32(0.9926), np.float32(0.9947), np.float32(0.7924)] +2025-10-30 23:04:03.751027: Epoch time: 20.5 s +2025-10-30 23:04:05.407614: +2025-10-30 23:04:05.409697: Epoch 342 +2025-10-30 23:04:05.411538: Current learning rate: 0.00686 +2025-10-30 23:04:25.810921: train_loss -0.9879 +2025-10-30 23:04:25.813336: val_loss -0.8918 +2025-10-30 23:04:25.815152: Pseudo dice [np.float32(0.9848), np.float32(0.992), np.float32(0.9942), np.float32(0.7835)] +2025-10-30 23:04:25.816808: Epoch time: 20.4 s +2025-10-30 23:04:27.045636: +2025-10-30 23:04:27.047530: Epoch 343 +2025-10-30 23:04:27.049301: Current learning rate: 0.00685 +2025-10-30 23:04:46.576393: train_loss -0.9867 +2025-10-30 23:04:46.580267: val_loss -0.8908 +2025-10-30 23:04:46.582443: Pseudo dice [np.float32(0.9848), np.float32(0.992), np.float32(0.9937), np.float32(0.7829)] +2025-10-30 23:04:46.584446: Epoch time: 19.53 s +2025-10-30 23:04:47.598798: +2025-10-30 23:04:47.600947: Epoch 344 +2025-10-30 23:04:47.602876: Current learning rate: 0.00684 +2025-10-30 23:05:08.147248: train_loss -0.9868 +2025-10-30 23:05:08.149226: val_loss -0.8907 +2025-10-30 23:05:08.151682: Pseudo dice [np.float32(0.9834), np.float32(0.9907), np.float32(0.9938), np.float32(0.7874)] +2025-10-30 23:05:08.153702: Epoch time: 20.55 s +2025-10-30 23:05:09.342689: +2025-10-30 23:05:09.344787: Epoch 345 +2025-10-30 23:05:09.346338: Current learning rate: 0.00683 +2025-10-30 23:05:29.942458: train_loss -0.985 +2025-10-30 23:05:29.944857: val_loss -0.8867 +2025-10-30 23:05:29.947154: Pseudo dice [np.float32(0.9842), np.float32(0.982), np.float32(0.9905), np.float32(0.8001)] +2025-10-30 23:05:29.948960: Epoch time: 20.6 s +2025-10-30 23:05:31.124615: +2025-10-30 23:05:31.126870: Epoch 346 +2025-10-30 23:05:31.128763: Current learning rate: 0.00682 +2025-10-30 23:05:51.400004: train_loss -0.9872 +2025-10-30 23:05:51.404600: val_loss -0.8957 +2025-10-30 23:05:51.406854: Pseudo dice [np.float32(0.9837), np.float32(0.9901), np.float32(0.9939), np.float32(0.8031)] +2025-10-30 23:05:51.408887: Epoch time: 20.28 s +2025-10-30 23:05:52.329007: +2025-10-30 23:05:52.331215: Epoch 347 +2025-10-30 23:05:52.333412: Current learning rate: 0.00681 +2025-10-30 23:06:12.220710: train_loss -0.9869 +2025-10-30 23:06:12.223027: val_loss -0.8968 +2025-10-30 23:06:12.224450: Pseudo dice [np.float32(0.9859), np.float32(0.9927), np.float32(0.9946), np.float32(0.7928)] +2025-10-30 23:06:12.225898: Epoch time: 19.89 s +2025-10-30 23:06:13.340082: +2025-10-30 23:06:13.342079: Epoch 348 +2025-10-30 23:06:13.343844: Current learning rate: 0.0068 +2025-10-30 23:06:33.785577: train_loss -0.9864 +2025-10-30 23:06:33.790494: val_loss -0.8989 +2025-10-30 23:06:33.792116: Pseudo dice [np.float32(0.9838), np.float32(0.9921), np.float32(0.9944), np.float32(0.8119)] +2025-10-30 23:06:33.793555: Epoch time: 20.45 s +2025-10-30 23:06:34.996289: +2025-10-30 23:06:34.998454: Epoch 349 +2025-10-30 23:06:35.000529: Current learning rate: 0.0068 +2025-10-30 23:06:55.406030: train_loss -0.9848 +2025-10-30 23:06:55.408952: val_loss -0.9036 +2025-10-30 23:06:55.410759: Pseudo dice [np.float32(0.9831), np.float32(0.9922), np.float32(0.9949), np.float32(0.8075)] +2025-10-30 23:06:55.412442: Epoch time: 20.41 s +2025-10-30 23:06:57.766479: +2025-10-30 23:06:57.768456: Epoch 350 +2025-10-30 23:06:57.770067: Current learning rate: 0.00679 +2025-10-30 23:07:17.188395: train_loss -0.9856 +2025-10-30 23:07:17.194105: val_loss -0.8992 +2025-10-30 23:07:17.196742: Pseudo dice [np.float32(0.9839), np.float32(0.991), np.float32(0.9948), np.float32(0.7995)] +2025-10-30 23:07:17.199067: Epoch time: 19.42 s +2025-10-30 23:07:18.228127: +2025-10-30 23:07:18.229978: Epoch 351 +2025-10-30 23:07:18.231853: Current learning rate: 0.00678 +2025-10-30 23:07:38.645415: train_loss -0.9859 +2025-10-30 23:07:38.649023: val_loss -0.8979 +2025-10-30 23:07:38.650877: Pseudo dice [np.float32(0.9834), np.float32(0.9909), np.float32(0.9944), np.float32(0.7948)] +2025-10-30 23:07:38.652496: Epoch time: 20.42 s +2025-10-30 23:07:39.992449: +2025-10-30 23:07:39.994487: Epoch 352 +2025-10-30 23:07:39.996275: Current learning rate: 0.00677 +2025-10-30 23:08:00.431171: train_loss -0.9878 +2025-10-30 23:08:00.434343: val_loss -0.8939 +2025-10-30 23:08:00.436105: Pseudo dice [np.float32(0.9849), np.float32(0.9921), np.float32(0.9941), np.float32(0.7919)] +2025-10-30 23:08:00.437797: Epoch time: 20.44 s +2025-10-30 23:08:01.479952: +2025-10-30 23:08:01.481942: Epoch 353 +2025-10-30 23:08:01.483600: Current learning rate: 0.00676 +2025-10-30 23:08:21.258344: train_loss -0.9876 +2025-10-30 23:08:21.260638: val_loss -0.8892 +2025-10-30 23:08:21.262233: Pseudo dice [np.float32(0.9858), np.float32(0.9917), np.float32(0.9943), np.float32(0.781)] +2025-10-30 23:08:21.263816: Epoch time: 19.78 s +2025-10-30 23:08:22.868642: +2025-10-30 23:08:22.870596: Epoch 354 +2025-10-30 23:08:22.872865: Current learning rate: 0.00675 +2025-10-30 23:08:43.737311: train_loss -0.9873 +2025-10-30 23:08:43.743098: val_loss -0.8969 +2025-10-30 23:08:43.745315: Pseudo dice [np.float32(0.9848), np.float32(0.9915), np.float32(0.9944), np.float32(0.803)] +2025-10-30 23:08:43.747149: Epoch time: 20.87 s +2025-10-30 23:08:44.967061: +2025-10-30 23:08:44.969342: Epoch 355 +2025-10-30 23:08:44.974603: Current learning rate: 0.00674 +2025-10-30 23:09:05.506052: train_loss -0.9877 +2025-10-30 23:09:05.509531: val_loss -0.8873 +2025-10-30 23:09:05.512224: Pseudo dice [np.float32(0.9843), np.float32(0.9917), np.float32(0.9939), np.float32(0.7784)] +2025-10-30 23:09:05.513996: Epoch time: 20.54 s +2025-10-30 23:09:06.634309: +2025-10-30 23:09:06.636463: Epoch 356 +2025-10-30 23:09:06.638721: Current learning rate: 0.00673 +2025-10-30 23:09:27.072432: train_loss -0.985 +2025-10-30 23:09:27.074703: val_loss -0.8974 +2025-10-30 23:09:27.076354: Pseudo dice [np.float32(0.983), np.float32(0.9912), np.float32(0.9949), np.float32(0.7933)] +2025-10-30 23:09:27.077833: Epoch time: 20.44 s +2025-10-30 23:09:28.340656: +2025-10-30 23:09:28.342517: Epoch 357 +2025-10-30 23:09:28.344088: Current learning rate: 0.00672 +2025-10-30 23:09:47.769024: train_loss -0.9868 +2025-10-30 23:09:47.771247: val_loss -0.8965 +2025-10-30 23:09:47.773140: Pseudo dice [np.float32(0.985), np.float32(0.9916), np.float32(0.9948), np.float32(0.7954)] +2025-10-30 23:09:47.774982: Epoch time: 19.43 s +2025-10-30 23:09:48.938714: +2025-10-30 23:09:48.941301: Epoch 358 +2025-10-30 23:09:48.943291: Current learning rate: 0.00671 +2025-10-30 23:10:09.323505: train_loss -0.9888 +2025-10-30 23:10:09.326619: val_loss -0.8961 +2025-10-30 23:10:09.328327: Pseudo dice [np.float32(0.9844), np.float32(0.9917), np.float32(0.9948), np.float32(0.7973)] +2025-10-30 23:10:09.330081: Epoch time: 20.39 s +2025-10-30 23:10:10.376368: +2025-10-30 23:10:10.378568: Epoch 359 +2025-10-30 23:10:10.380241: Current learning rate: 0.0067 +2025-10-30 23:10:30.012671: train_loss -0.9833 +2025-10-30 23:10:30.022797: val_loss -0.887 +2025-10-30 23:10:30.024927: Pseudo dice [np.float32(0.9816), np.float32(0.9859), np.float32(0.9925), np.float32(0.7904)] +2025-10-30 23:10:30.026554: Epoch time: 19.64 s +2025-10-30 23:10:31.198452: +2025-10-30 23:10:31.200282: Epoch 360 +2025-10-30 23:10:31.201915: Current learning rate: 0.00669 +2025-10-30 23:10:51.742476: train_loss -0.9508 +2025-10-30 23:10:51.744370: val_loss -0.901 +2025-10-30 23:10:51.746019: Pseudo dice [np.float32(0.984), np.float32(0.9917), np.float32(0.994), np.float32(0.7908)] +2025-10-30 23:10:51.747687: Epoch time: 20.55 s +2025-10-30 23:10:52.757014: +2025-10-30 23:10:52.759243: Epoch 361 +2025-10-30 23:10:52.761180: Current learning rate: 0.00668 +2025-10-30 23:11:13.026739: train_loss -0.9592 +2025-10-30 23:11:13.029926: val_loss -0.9046 +2025-10-30 23:11:13.031602: Pseudo dice [np.float32(0.9835), np.float32(0.991), np.float32(0.9936), np.float32(0.7882)] +2025-10-30 23:11:13.033399: Epoch time: 20.27 s +2025-10-30 23:11:14.058329: +2025-10-30 23:11:14.060444: Epoch 362 +2025-10-30 23:11:14.062505: Current learning rate: 0.00667 +2025-10-30 23:11:34.714751: train_loss -0.9713 +2025-10-30 23:11:34.717055: val_loss -0.9055 +2025-10-30 23:11:34.718630: Pseudo dice [np.float32(0.984), np.float32(0.9909), np.float32(0.9947), np.float32(0.8016)] +2025-10-30 23:11:34.720237: Epoch time: 20.66 s +2025-10-30 23:11:35.954151: +2025-10-30 23:11:35.956144: Epoch 363 +2025-10-30 23:11:35.958109: Current learning rate: 0.00666 +2025-10-30 23:11:56.478578: train_loss -0.9793 +2025-10-30 23:11:56.480770: val_loss -0.8857 +2025-10-30 23:11:56.482334: Pseudo dice [np.float32(0.9838), np.float32(0.9911), np.float32(0.9943), np.float32(0.7554)] +2025-10-30 23:11:56.483785: Epoch time: 20.53 s +2025-10-30 23:11:57.626812: +2025-10-30 23:11:57.628644: Epoch 364 +2025-10-30 23:11:57.630262: Current learning rate: 0.00665 +2025-10-30 23:12:16.787613: train_loss -0.9789 +2025-10-30 23:12:16.790145: val_loss -0.9048 +2025-10-30 23:12:16.791640: Pseudo dice [np.float32(0.9846), np.float32(0.9907), np.float32(0.9944), np.float32(0.8018)] +2025-10-30 23:12:16.793162: Epoch time: 19.16 s +2025-10-30 23:12:17.983229: +2025-10-30 23:12:17.985293: Epoch 365 +2025-10-30 23:12:17.986942: Current learning rate: 0.00665 +2025-10-30 23:12:38.288917: train_loss -0.9808 +2025-10-30 23:12:38.291595: val_loss -0.8993 +2025-10-30 23:12:38.294229: Pseudo dice [np.float32(0.9836), np.float32(0.9917), np.float32(0.9945), np.float32(0.7903)] +2025-10-30 23:12:38.296490: Epoch time: 20.31 s +2025-10-30 23:12:39.836506: +2025-10-30 23:12:39.838384: Epoch 366 +2025-10-30 23:12:39.839977: Current learning rate: 0.00664 +2025-10-30 23:12:59.328842: train_loss -0.9689 +2025-10-30 23:12:59.331337: val_loss -0.8947 +2025-10-30 23:12:59.332880: Pseudo dice [np.float32(0.9809), np.float32(0.9904), np.float32(0.9935), np.float32(0.7954)] +2025-10-30 23:12:59.335041: Epoch time: 19.49 s +2025-10-30 23:13:00.560349: +2025-10-30 23:13:00.562153: Epoch 367 +2025-10-30 23:13:00.563820: Current learning rate: 0.00663 +2025-10-30 23:13:20.981320: train_loss -0.9561 +2025-10-30 23:13:20.983886: val_loss -0.9042 +2025-10-30 23:13:20.985424: Pseudo dice [np.float32(0.9838), np.float32(0.9918), np.float32(0.9944), np.float32(0.7995)] +2025-10-30 23:13:20.987599: Epoch time: 20.42 s +2025-10-30 23:13:22.114708: +2025-10-30 23:13:22.116828: Epoch 368 +2025-10-30 23:13:22.118373: Current learning rate: 0.00662 +2025-10-30 23:13:42.542126: train_loss -0.9702 +2025-10-30 23:13:42.545714: val_loss -0.9065 +2025-10-30 23:13:42.548123: Pseudo dice [np.float32(0.9812), np.float32(0.9911), np.float32(0.9949), np.float32(0.8088)] +2025-10-30 23:13:42.549888: Epoch time: 20.43 s +2025-10-30 23:13:43.815778: +2025-10-30 23:13:43.817839: Epoch 369 +2025-10-30 23:13:43.819937: Current learning rate: 0.00661 +2025-10-30 23:14:04.118741: train_loss -0.9787 +2025-10-30 23:14:04.120856: val_loss -0.9006 +2025-10-30 23:14:04.123297: Pseudo dice [np.float32(0.9837), np.float32(0.9919), np.float32(0.9946), np.float32(0.7933)] +2025-10-30 23:14:04.125459: Epoch time: 20.3 s +2025-10-30 23:14:05.159271: +2025-10-30 23:14:05.160986: Epoch 370 +2025-10-30 23:14:05.162636: Current learning rate: 0.0066 +2025-10-30 23:14:25.677526: train_loss -0.983 +2025-10-30 23:14:25.681790: val_loss -0.8957 +2025-10-30 23:14:25.683643: Pseudo dice [np.float32(0.9824), np.float32(0.9905), np.float32(0.9942), np.float32(0.7879)] +2025-10-30 23:14:25.685204: Epoch time: 20.52 s +2025-10-30 23:14:27.002597: +2025-10-30 23:14:27.004798: Epoch 371 +2025-10-30 23:14:27.007090: Current learning rate: 0.00659 +2025-10-30 23:14:46.686761: train_loss -0.9842 +2025-10-30 23:14:46.692354: val_loss -0.8964 +2025-10-30 23:14:46.696911: Pseudo dice [np.float32(0.9843), np.float32(0.9914), np.float32(0.9948), np.float32(0.7944)] +2025-10-30 23:14:46.701592: Epoch time: 19.69 s +2025-10-30 23:14:47.929265: +2025-10-30 23:14:47.931033: Epoch 372 +2025-10-30 23:14:47.932669: Current learning rate: 0.00658 +2025-10-30 23:15:07.291925: train_loss -0.9844 +2025-10-30 23:15:07.294754: val_loss -0.898 +2025-10-30 23:15:07.296832: Pseudo dice [np.float32(0.984), np.float32(0.9912), np.float32(0.9946), np.float32(0.7977)] +2025-10-30 23:15:07.298995: Epoch time: 19.36 s +2025-10-30 23:15:08.391565: +2025-10-30 23:15:08.393465: Epoch 373 +2025-10-30 23:15:08.395448: Current learning rate: 0.00657 +2025-10-30 23:15:29.025522: train_loss -0.9858 +2025-10-30 23:15:29.028955: val_loss -0.8935 +2025-10-30 23:15:29.030631: Pseudo dice [np.float32(0.984), np.float32(0.991), np.float32(0.9944), np.float32(0.794)] +2025-10-30 23:15:29.032366: Epoch time: 20.64 s +2025-10-30 23:15:30.264088: +2025-10-30 23:15:30.265857: Epoch 374 +2025-10-30 23:15:30.267399: Current learning rate: 0.00656 +2025-10-30 23:15:51.090254: train_loss -0.986 +2025-10-30 23:15:51.092347: val_loss -0.8975 +2025-10-30 23:15:51.094498: Pseudo dice [np.float32(0.986), np.float32(0.9919), np.float32(0.9945), np.float32(0.7941)] +2025-10-30 23:15:51.096517: Epoch time: 20.83 s +2025-10-30 23:15:52.354453: +2025-10-30 23:15:52.356225: Epoch 375 +2025-10-30 23:15:52.358135: Current learning rate: 0.00655 +2025-10-30 23:16:12.975037: train_loss -0.9849 +2025-10-30 23:16:12.977340: val_loss -0.8928 +2025-10-30 23:16:12.980051: Pseudo dice [np.float32(0.9837), np.float32(0.9918), np.float32(0.9945), np.float32(0.7885)] +2025-10-30 23:16:12.982507: Epoch time: 20.62 s +2025-10-30 23:16:14.243310: +2025-10-30 23:16:14.246176: Epoch 376 +2025-10-30 23:16:14.248119: Current learning rate: 0.00654 +2025-10-30 23:16:34.710756: train_loss -0.9847 +2025-10-30 23:16:34.714139: val_loss -0.8908 +2025-10-30 23:16:34.716535: Pseudo dice [np.float32(0.9839), np.float32(0.9917), np.float32(0.994), np.float32(0.7768)] +2025-10-30 23:16:34.719064: Epoch time: 20.47 s +2025-10-30 23:16:35.747761: +2025-10-30 23:16:35.750034: Epoch 377 +2025-10-30 23:16:35.751817: Current learning rate: 0.00653 +2025-10-30 23:16:56.128601: train_loss -0.9841 +2025-10-30 23:16:56.131524: val_loss -0.895 +2025-10-30 23:16:56.134198: Pseudo dice [np.float32(0.9843), np.float32(0.9917), np.float32(0.9941), np.float32(0.7935)] +2025-10-30 23:16:56.136023: Epoch time: 20.38 s +2025-10-30 23:16:57.311291: +2025-10-30 23:16:57.313100: Epoch 378 +2025-10-30 23:16:57.315141: Current learning rate: 0.00652 +2025-10-30 23:17:16.999093: train_loss -0.9848 +2025-10-30 23:17:17.002742: val_loss -0.9013 +2025-10-30 23:17:17.005021: Pseudo dice [np.float32(0.9847), np.float32(0.9922), np.float32(0.9948), np.float32(0.8096)] +2025-10-30 23:17:17.007030: Epoch time: 19.69 s +2025-10-30 23:17:18.046848: +2025-10-30 23:17:18.048985: Epoch 379 +2025-10-30 23:17:18.050817: Current learning rate: 0.00651 +2025-10-30 23:17:38.390861: train_loss -0.9859 +2025-10-30 23:17:38.393755: val_loss -0.9006 +2025-10-30 23:17:38.396184: Pseudo dice [np.float32(0.983), np.float32(0.9916), np.float32(0.9945), np.float32(0.8073)] +2025-10-30 23:17:38.398015: Epoch time: 20.35 s +2025-10-30 23:17:39.440977: +2025-10-30 23:17:39.442798: Epoch 380 +2025-10-30 23:17:39.444422: Current learning rate: 0.0065 +2025-10-30 23:17:59.677932: train_loss -0.9869 +2025-10-30 23:17:59.680817: val_loss -0.8944 +2025-10-30 23:17:59.682522: Pseudo dice [np.float32(0.9835), np.float32(0.991), np.float32(0.9942), np.float32(0.7906)] +2025-10-30 23:17:59.684043: Epoch time: 20.24 s +2025-10-30 23:18:00.702427: +2025-10-30 23:18:00.704218: Epoch 381 +2025-10-30 23:18:00.705642: Current learning rate: 0.00649 +2025-10-30 23:18:21.145036: train_loss -0.9864 +2025-10-30 23:18:21.149308: val_loss -0.894 +2025-10-30 23:18:21.151158: Pseudo dice [np.float32(0.9836), np.float32(0.9915), np.float32(0.9945), np.float32(0.7977)] +2025-10-30 23:18:21.152803: Epoch time: 20.44 s +2025-10-30 23:18:22.209856: +2025-10-30 23:18:22.211957: Epoch 382 +2025-10-30 23:18:22.213746: Current learning rate: 0.00648 +2025-10-30 23:18:42.767525: train_loss -0.9875 +2025-10-30 23:18:42.772703: val_loss -0.8988 +2025-10-30 23:18:42.774424: Pseudo dice [np.float32(0.9822), np.float32(0.9906), np.float32(0.9943), np.float32(0.8036)] +2025-10-30 23:18:42.776026: Epoch time: 20.56 s +2025-10-30 23:18:43.997222: +2025-10-30 23:18:43.999845: Epoch 383 +2025-10-30 23:18:44.001604: Current learning rate: 0.00648 +2025-10-30 23:19:04.229163: train_loss -0.9856 +2025-10-30 23:19:04.231505: val_loss -0.8939 +2025-10-30 23:19:04.233079: Pseudo dice [np.float32(0.9842), np.float32(0.9916), np.float32(0.9944), np.float32(0.7888)] +2025-10-30 23:19:04.234879: Epoch time: 20.23 s +2025-10-30 23:19:05.363838: +2025-10-30 23:19:05.365752: Epoch 384 +2025-10-30 23:19:05.367720: Current learning rate: 0.00647 +2025-10-30 23:19:23.623793: train_loss -0.9883 +2025-10-30 23:19:23.625844: val_loss -0.8905 +2025-10-30 23:19:23.627425: Pseudo dice [np.float32(0.9849), np.float32(0.9913), np.float32(0.9941), np.float32(0.7905)] +2025-10-30 23:19:23.629104: Epoch time: 18.26 s +2025-10-30 23:19:24.814520: +2025-10-30 23:19:24.818106: Epoch 385 +2025-10-30 23:19:24.819857: Current learning rate: 0.00646 +2025-10-30 23:19:44.339325: train_loss -0.9878 +2025-10-30 23:19:44.342498: val_loss -0.8882 +2025-10-30 23:19:44.344032: Pseudo dice [np.float32(0.9841), np.float32(0.9912), np.float32(0.9945), np.float32(0.7838)] +2025-10-30 23:19:44.345559: Epoch time: 19.53 s +2025-10-30 23:19:45.461231: +2025-10-30 23:19:45.463257: Epoch 386 +2025-10-30 23:19:45.464971: Current learning rate: 0.00645 +2025-10-30 23:20:05.889391: train_loss -0.9877 +2025-10-30 23:20:05.892266: val_loss -0.8933 +2025-10-30 23:20:05.894541: Pseudo dice [np.float32(0.9831), np.float32(0.9911), np.float32(0.9941), np.float32(0.7949)] +2025-10-30 23:20:05.896683: Epoch time: 20.43 s +2025-10-30 23:20:07.010746: +2025-10-30 23:20:07.012702: Epoch 387 +2025-10-30 23:20:07.014917: Current learning rate: 0.00644 +2025-10-30 23:20:27.497257: train_loss -0.989 +2025-10-30 23:20:27.499300: val_loss -0.8988 +2025-10-30 23:20:27.500974: Pseudo dice [np.float32(0.9845), np.float32(0.9902), np.float32(0.9941), np.float32(0.8038)] +2025-10-30 23:20:27.502683: Epoch time: 20.49 s +2025-10-30 23:20:28.542356: +2025-10-30 23:20:28.544513: Epoch 388 +2025-10-30 23:20:28.546270: Current learning rate: 0.00643 +2025-10-30 23:20:48.887857: train_loss -0.9885 +2025-10-30 23:20:48.891834: val_loss -0.8937 +2025-10-30 23:20:48.894034: Pseudo dice [np.float32(0.9855), np.float32(0.9921), np.float32(0.9944), np.float32(0.792)] +2025-10-30 23:20:48.895870: Epoch time: 20.35 s +2025-10-30 23:20:50.317596: +2025-10-30 23:20:50.319410: Epoch 389 +2025-10-30 23:20:50.321164: Current learning rate: 0.00642 +2025-10-30 23:21:10.686912: train_loss -0.9881 +2025-10-30 23:21:10.692430: val_loss -0.8968 +2025-10-30 23:21:10.695019: Pseudo dice [np.float32(0.985), np.float32(0.9909), np.float32(0.9945), np.float32(0.8017)] +2025-10-30 23:21:10.697111: Epoch time: 20.37 s +2025-10-30 23:21:11.729859: +2025-10-30 23:21:11.731704: Epoch 390 +2025-10-30 23:21:11.733414: Current learning rate: 0.00641 +2025-10-30 23:21:32.074387: train_loss -0.9884 +2025-10-30 23:21:32.077988: val_loss -0.9014 +2025-10-30 23:21:32.079782: Pseudo dice [np.float32(0.9849), np.float32(0.9919), np.float32(0.9947), np.float32(0.811)] +2025-10-30 23:21:32.082044: Epoch time: 20.35 s +2025-10-30 23:21:33.372584: +2025-10-30 23:21:33.374686: Epoch 391 +2025-10-30 23:21:33.376356: Current learning rate: 0.0064 +2025-10-30 23:21:50.200464: train_loss -0.988 +2025-10-30 23:21:50.203403: val_loss -0.8953 +2025-10-30 23:21:50.205268: Pseudo dice [np.float32(0.9836), np.float32(0.9913), np.float32(0.9946), np.float32(0.8042)] +2025-10-30 23:21:50.206915: Epoch time: 16.83 s +2025-10-30 23:21:51.421796: +2025-10-30 23:21:51.423555: Epoch 392 +2025-10-30 23:21:51.425069: Current learning rate: 0.00639 +2025-10-30 23:22:12.048781: train_loss -0.9888 +2025-10-30 23:22:12.051449: val_loss -0.8957 +2025-10-30 23:22:12.053594: Pseudo dice [np.float32(0.9843), np.float32(0.9917), np.float32(0.9946), np.float32(0.7982)] +2025-10-30 23:22:12.055394: Epoch time: 20.63 s +2025-10-30 23:22:13.122127: +2025-10-30 23:22:13.124581: Epoch 393 +2025-10-30 23:22:13.126407: Current learning rate: 0.00638 +2025-10-30 23:22:33.705816: train_loss -0.9887 +2025-10-30 23:22:33.707927: val_loss -0.8862 +2025-10-30 23:22:33.709717: Pseudo dice [np.float32(0.9844), np.float32(0.9912), np.float32(0.9942), np.float32(0.7871)] +2025-10-30 23:22:33.711625: Epoch time: 20.59 s +2025-10-30 23:22:34.641423: +2025-10-30 23:22:34.644978: Epoch 394 +2025-10-30 23:22:34.646859: Current learning rate: 0.00637 +2025-10-30 23:22:55.150902: train_loss -0.988 +2025-10-30 23:22:55.155520: val_loss -0.8953 +2025-10-30 23:22:55.157223: Pseudo dice [np.float32(0.9857), np.float32(0.9916), np.float32(0.9944), np.float32(0.7976)] +2025-10-30 23:22:55.159276: Epoch time: 20.51 s +2025-10-30 23:22:56.451805: +2025-10-30 23:22:56.454301: Epoch 395 +2025-10-30 23:22:56.456742: Current learning rate: 0.00636 +2025-10-30 23:23:16.918171: train_loss -0.9874 +2025-10-30 23:23:16.920771: val_loss -0.886 +2025-10-30 23:23:16.922496: Pseudo dice [np.float32(0.9848), np.float32(0.9919), np.float32(0.9939), np.float32(0.7709)] +2025-10-30 23:23:16.924082: Epoch time: 20.47 s +2025-10-30 23:23:18.013322: +2025-10-30 23:23:18.015251: Epoch 396 +2025-10-30 23:23:18.017024: Current learning rate: 0.00635 +2025-10-30 23:23:38.379610: train_loss -0.9891 +2025-10-30 23:23:38.382025: val_loss -0.8902 +2025-10-30 23:23:38.383559: Pseudo dice [np.float32(0.9855), np.float32(0.9926), np.float32(0.9941), np.float32(0.7823)] +2025-10-30 23:23:38.385139: Epoch time: 20.37 s +2025-10-30 23:23:39.631647: +2025-10-30 23:23:39.633739: Epoch 397 +2025-10-30 23:23:39.635505: Current learning rate: 0.00634 +2025-10-30 23:24:00.144300: train_loss -0.9875 +2025-10-30 23:24:00.147205: val_loss -0.8947 +2025-10-30 23:24:00.149432: Pseudo dice [np.float32(0.9862), np.float32(0.9929), np.float32(0.9948), np.float32(0.7975)] +2025-10-30 23:24:00.151705: Epoch time: 20.51 s +2025-10-30 23:24:01.398833: +2025-10-30 23:24:01.400769: Epoch 398 +2025-10-30 23:24:01.402349: Current learning rate: 0.00633 +2025-10-30 23:24:19.875918: train_loss -0.9881 +2025-10-30 23:24:19.878962: val_loss -0.8929 +2025-10-30 23:24:19.880710: Pseudo dice [np.float32(0.9856), np.float32(0.9922), np.float32(0.9947), np.float32(0.7907)] +2025-10-30 23:24:19.882450: Epoch time: 18.48 s +2025-10-30 23:24:20.993644: +2025-10-30 23:24:20.995483: Epoch 399 +2025-10-30 23:24:20.997088: Current learning rate: 0.00632 +2025-10-30 23:24:41.369065: train_loss -0.9884 +2025-10-30 23:24:41.371342: val_loss -0.8848 +2025-10-30 23:24:41.373953: Pseudo dice [np.float32(0.9851), np.float32(0.9915), np.float32(0.9938), np.float32(0.7729)] +2025-10-30 23:24:41.376399: Epoch time: 20.38 s +2025-10-30 23:24:43.660306: +2025-10-30 23:24:43.663162: Epoch 400 +2025-10-30 23:24:43.666416: Current learning rate: 0.00631 +2025-10-30 23:25:04.390521: train_loss -0.9877 +2025-10-30 23:25:04.394249: val_loss -0.897 +2025-10-30 23:25:04.396300: Pseudo dice [np.float32(0.983), np.float32(0.9917), np.float32(0.9946), np.float32(0.8019)] +2025-10-30 23:25:04.398418: Epoch time: 20.73 s +2025-10-30 23:25:05.421136: +2025-10-30 23:25:05.423431: Epoch 401 +2025-10-30 23:25:05.425712: Current learning rate: 0.0063 +2025-10-30 23:25:25.616899: train_loss -0.9874 +2025-10-30 23:25:25.619704: val_loss -0.8941 +2025-10-30 23:25:25.621861: Pseudo dice [np.float32(0.984), np.float32(0.9921), np.float32(0.9942), np.float32(0.7963)] +2025-10-30 23:25:25.623645: Epoch time: 20.2 s +2025-10-30 23:25:26.667117: +2025-10-30 23:25:26.668859: Epoch 402 +2025-10-30 23:25:26.670360: Current learning rate: 0.0063 +2025-10-30 23:25:46.936450: train_loss -0.9884 +2025-10-30 23:25:46.938543: val_loss -0.8977 +2025-10-30 23:25:46.939979: Pseudo dice [np.float32(0.9839), np.float32(0.992), np.float32(0.9943), np.float32(0.8052)] +2025-10-30 23:25:46.941343: Epoch time: 20.27 s +2025-10-30 23:25:48.127712: +2025-10-30 23:25:48.129473: Epoch 403 +2025-10-30 23:25:48.131295: Current learning rate: 0.00629 +2025-10-30 23:26:08.770972: train_loss -0.9887 +2025-10-30 23:26:08.774815: val_loss -0.8899 +2025-10-30 23:26:08.776611: Pseudo dice [np.float32(0.9844), np.float32(0.9919), np.float32(0.9946), np.float32(0.7825)] +2025-10-30 23:26:08.778390: Epoch time: 20.64 s +2025-10-30 23:26:09.963233: +2025-10-30 23:26:09.965029: Epoch 404 +2025-10-30 23:26:09.966575: Current learning rate: 0.00628 +2025-10-30 23:26:29.321480: train_loss -0.9887 +2025-10-30 23:26:29.327757: val_loss -0.8891 +2025-10-30 23:26:29.329671: Pseudo dice [np.float32(0.9857), np.float32(0.9917), np.float32(0.9943), np.float32(0.7822)] +2025-10-30 23:26:29.331320: Epoch time: 19.36 s +2025-10-30 23:26:30.590261: +2025-10-30 23:26:30.592233: Epoch 405 +2025-10-30 23:26:30.593766: Current learning rate: 0.00627 +2025-10-30 23:26:49.511949: train_loss -0.9889 +2025-10-30 23:26:49.514114: val_loss -0.8912 +2025-10-30 23:26:49.515802: Pseudo dice [np.float32(0.9838), np.float32(0.9914), np.float32(0.9944), np.float32(0.7938)] +2025-10-30 23:26:49.517492: Epoch time: 18.92 s +2025-10-30 23:26:50.646468: +2025-10-30 23:26:50.648421: Epoch 406 +2025-10-30 23:26:50.650142: Current learning rate: 0.00626 +2025-10-30 23:27:10.912495: train_loss -0.9892 +2025-10-30 23:27:10.915199: val_loss -0.8912 +2025-10-30 23:27:10.916839: Pseudo dice [np.float32(0.9849), np.float32(0.9916), np.float32(0.9943), np.float32(0.7906)] +2025-10-30 23:27:10.918483: Epoch time: 20.27 s +2025-10-30 23:27:12.039860: +2025-10-30 23:27:12.041868: Epoch 407 +2025-10-30 23:27:12.043761: Current learning rate: 0.00625 +2025-10-30 23:27:32.496665: train_loss -0.9889 +2025-10-30 23:27:32.499284: val_loss -0.8935 +2025-10-30 23:27:32.501035: Pseudo dice [np.float32(0.9845), np.float32(0.9926), np.float32(0.9947), np.float32(0.7977)] +2025-10-30 23:27:32.503061: Epoch time: 20.46 s +2025-10-30 23:27:33.767276: +2025-10-30 23:27:33.769415: Epoch 408 +2025-10-30 23:27:33.771432: Current learning rate: 0.00624 +2025-10-30 23:27:54.565834: train_loss -0.9887 +2025-10-30 23:27:54.568405: val_loss -0.8985 +2025-10-30 23:27:54.570217: Pseudo dice [np.float32(0.986), np.float32(0.9925), np.float32(0.9947), np.float32(0.7995)] +2025-10-30 23:27:54.572088: Epoch time: 20.8 s +2025-10-30 23:27:55.828638: +2025-10-30 23:27:55.830655: Epoch 409 +2025-10-30 23:27:55.832396: Current learning rate: 0.00623 +2025-10-30 23:28:16.453143: train_loss -0.9886 +2025-10-30 23:28:16.455876: val_loss -0.8915 +2025-10-30 23:28:16.457284: Pseudo dice [np.float32(0.9871), np.float32(0.9921), np.float32(0.9942), np.float32(0.7844)] +2025-10-30 23:28:16.458717: Epoch time: 20.63 s +2025-10-30 23:28:17.627992: +2025-10-30 23:28:17.630030: Epoch 410 +2025-10-30 23:28:17.632542: Current learning rate: 0.00622 +2025-10-30 23:28:36.459902: train_loss -0.9884 +2025-10-30 23:28:36.468790: val_loss -0.8895 +2025-10-30 23:28:36.475286: Pseudo dice [np.float32(0.984), np.float32(0.9914), np.float32(0.9943), np.float32(0.7775)] +2025-10-30 23:28:36.481916: Epoch time: 18.83 s +2025-10-30 23:28:37.731037: +2025-10-30 23:28:37.739070: Epoch 411 +2025-10-30 23:28:37.741504: Current learning rate: 0.00621 +2025-10-30 23:28:57.150525: train_loss -0.9887 +2025-10-30 23:28:57.152255: val_loss -0.8982 +2025-10-30 23:28:57.153651: Pseudo dice [np.float32(0.9861), np.float32(0.9922), np.float32(0.9949), np.float32(0.8011)] +2025-10-30 23:28:57.155153: Epoch time: 19.42 s +2025-10-30 23:28:58.560759: +2025-10-30 23:28:58.562551: Epoch 412 +2025-10-30 23:28:58.564275: Current learning rate: 0.0062 +2025-10-30 23:29:18.697013: train_loss -0.9895 +2025-10-30 23:29:18.700215: val_loss -0.891 +2025-10-30 23:29:18.701971: Pseudo dice [np.float32(0.9849), np.float32(0.9919), np.float32(0.9944), np.float32(0.7893)] +2025-10-30 23:29:18.703712: Epoch time: 20.14 s +2025-10-30 23:29:19.922154: +2025-10-30 23:29:19.924223: Epoch 413 +2025-10-30 23:29:19.926120: Current learning rate: 0.00619 +2025-10-30 23:29:40.432653: train_loss -0.9861 +2025-10-30 23:29:40.435081: val_loss -0.8947 +2025-10-30 23:29:40.436848: Pseudo dice [np.float32(0.9837), np.float32(0.992), np.float32(0.9945), np.float32(0.7967)] +2025-10-30 23:29:40.438906: Epoch time: 20.51 s +2025-10-30 23:29:41.505736: +2025-10-30 23:29:41.507744: Epoch 414 +2025-10-30 23:29:41.509446: Current learning rate: 0.00618 +2025-10-30 23:30:02.061685: train_loss -0.9882 +2025-10-30 23:30:02.064975: val_loss -0.9036 +2025-10-30 23:30:02.067132: Pseudo dice [np.float32(0.9853), np.float32(0.9925), np.float32(0.995), np.float32(0.8121)] +2025-10-30 23:30:02.068679: Epoch time: 20.56 s +2025-10-30 23:30:03.084908: +2025-10-30 23:30:03.086787: Epoch 415 +2025-10-30 23:30:03.088510: Current learning rate: 0.00617 +2025-10-30 23:30:23.556937: train_loss -0.9894 +2025-10-30 23:30:23.559887: val_loss -0.9007 +2025-10-30 23:30:23.561544: Pseudo dice [np.float32(0.9846), np.float32(0.9916), np.float32(0.9945), np.float32(0.8101)] +2025-10-30 23:30:23.563398: Epoch time: 20.47 s +2025-10-30 23:30:24.572058: +2025-10-30 23:30:24.574140: Epoch 416 +2025-10-30 23:30:24.576021: Current learning rate: 0.00616 +2025-10-30 23:30:45.191450: train_loss -0.9886 +2025-10-30 23:30:45.194216: val_loss -0.9007 +2025-10-30 23:30:45.196042: Pseudo dice [np.float32(0.984), np.float32(0.9926), np.float32(0.9948), np.float32(0.8022)] +2025-10-30 23:30:45.197796: Epoch time: 20.62 s +2025-10-30 23:30:46.453063: +2025-10-30 23:30:46.455168: Epoch 417 +2025-10-30 23:30:46.456849: Current learning rate: 0.00615 +2025-10-30 23:31:05.819947: train_loss -0.9889 +2025-10-30 23:31:05.824389: val_loss -0.9011 +2025-10-30 23:31:05.826406: Pseudo dice [np.float32(0.9836), np.float32(0.9921), np.float32(0.9951), np.float32(0.819)] +2025-10-30 23:31:05.828331: Epoch time: 19.37 s +2025-10-30 23:31:06.994625: +2025-10-30 23:31:06.997535: Epoch 418 +2025-10-30 23:31:06.999644: Current learning rate: 0.00614 +2025-10-30 23:31:27.239432: train_loss -0.9897 +2025-10-30 23:31:27.242636: val_loss -0.8914 +2025-10-30 23:31:27.244190: Pseudo dice [np.float32(0.9845), np.float32(0.9916), np.float32(0.9945), np.float32(0.7885)] +2025-10-30 23:31:27.245997: Epoch time: 20.25 s +2025-10-30 23:31:28.331040: +2025-10-30 23:31:28.332949: Epoch 419 +2025-10-30 23:31:28.335130: Current learning rate: 0.00613 +2025-10-30 23:31:47.636614: train_loss -0.989 +2025-10-30 23:31:47.639503: val_loss -0.8923 +2025-10-30 23:31:47.641305: Pseudo dice [np.float32(0.985), np.float32(0.9924), np.float32(0.995), np.float32(0.7898)] +2025-10-30 23:31:47.642934: Epoch time: 19.31 s +2025-10-30 23:31:48.697126: +2025-10-30 23:31:48.699357: Epoch 420 +2025-10-30 23:31:48.701563: Current learning rate: 0.00612 +2025-10-30 23:32:08.956850: train_loss -0.9892 +2025-10-30 23:32:08.958593: val_loss -0.8938 +2025-10-30 23:32:08.960733: Pseudo dice [np.float32(0.9846), np.float32(0.9916), np.float32(0.9947), np.float32(0.7952)] +2025-10-30 23:32:08.962174: Epoch time: 20.26 s +2025-10-30 23:32:10.161262: +2025-10-30 23:32:10.163007: Epoch 421 +2025-10-30 23:32:10.164612: Current learning rate: 0.00612 +2025-10-30 23:32:30.650698: train_loss -0.9887 +2025-10-30 23:32:30.653677: val_loss -0.9008 +2025-10-30 23:32:30.655101: Pseudo dice [np.float32(0.9854), np.float32(0.9923), np.float32(0.995), np.float32(0.812)] +2025-10-30 23:32:30.657212: Epoch time: 20.49 s +2025-10-30 23:32:31.946695: +2025-10-30 23:32:31.949055: Epoch 422 +2025-10-30 23:32:31.951048: Current learning rate: 0.00611 +2025-10-30 23:32:52.685965: train_loss -0.9889 +2025-10-30 23:32:52.688205: val_loss -0.9013 +2025-10-30 23:32:52.690039: Pseudo dice [np.float32(0.9866), np.float32(0.9929), np.float32(0.9946), np.float32(0.8067)] +2025-10-30 23:32:52.691862: Epoch time: 20.74 s +2025-10-30 23:32:53.854949: +2025-10-30 23:32:53.857044: Epoch 423 +2025-10-30 23:32:53.858882: Current learning rate: 0.0061 +2025-10-30 23:33:14.336788: train_loss -0.989 +2025-10-30 23:33:14.339279: val_loss -0.899 +2025-10-30 23:33:14.341230: Pseudo dice [np.float32(0.9872), np.float32(0.9931), np.float32(0.9944), np.float32(0.7969)] +2025-10-30 23:33:14.347021: Epoch time: 20.48 s +2025-10-30 23:33:15.601071: +2025-10-30 23:33:15.602914: Epoch 424 +2025-10-30 23:33:15.604696: Current learning rate: 0.00609 +2025-10-30 23:33:35.402189: train_loss -0.989 +2025-10-30 23:33:35.405505: val_loss -0.8928 +2025-10-30 23:33:35.407269: Pseudo dice [np.float32(0.9855), np.float32(0.9921), np.float32(0.9944), np.float32(0.7888)] +2025-10-30 23:33:35.408923: Epoch time: 19.8 s +2025-10-30 23:33:37.391715: +2025-10-30 23:33:37.393654: Epoch 425 +2025-10-30 23:33:37.395393: Current learning rate: 0.00608 +2025-10-30 23:33:57.676405: train_loss -0.9898 +2025-10-30 23:33:57.678741: val_loss -0.8976 +2025-10-30 23:33:57.680328: Pseudo dice [np.float32(0.9828), np.float32(0.9919), np.float32(0.9949), np.float32(0.8135)] +2025-10-30 23:33:57.681820: Epoch time: 20.29 s +2025-10-30 23:33:58.897858: +2025-10-30 23:33:58.899800: Epoch 426 +2025-10-30 23:33:58.901597: Current learning rate: 0.00607 +2025-10-30 23:34:19.487023: train_loss -0.9895 +2025-10-30 23:34:19.489363: val_loss -0.8893 +2025-10-30 23:34:19.491017: Pseudo dice [np.float32(0.9844), np.float32(0.9917), np.float32(0.9943), np.float32(0.7819)] +2025-10-30 23:34:19.492978: Epoch time: 20.59 s +2025-10-30 23:34:20.751412: +2025-10-30 23:34:20.753440: Epoch 427 +2025-10-30 23:34:20.755247: Current learning rate: 0.00606 +2025-10-30 23:34:41.576180: train_loss -0.9888 +2025-10-30 23:34:41.579896: val_loss -0.8854 +2025-10-30 23:34:41.581863: Pseudo dice [np.float32(0.9844), np.float32(0.9925), np.float32(0.9945), np.float32(0.776)] +2025-10-30 23:34:41.586845: Epoch time: 20.83 s +2025-10-30 23:34:42.719431: +2025-10-30 23:34:42.721792: Epoch 428 +2025-10-30 23:34:42.723664: Current learning rate: 0.00605 +2025-10-30 23:35:03.436506: train_loss -0.9887 +2025-10-30 23:35:03.443455: val_loss -0.9001 +2025-10-30 23:35:03.445879: Pseudo dice [np.float32(0.9855), np.float32(0.9923), np.float32(0.9948), np.float32(0.8055)] +2025-10-30 23:35:03.448226: Epoch time: 20.72 s +2025-10-30 23:35:04.729063: +2025-10-30 23:35:04.731855: Epoch 429 +2025-10-30 23:35:04.733855: Current learning rate: 0.00604 +2025-10-30 23:35:24.784124: train_loss -0.9892 +2025-10-30 23:35:24.787137: val_loss -0.8907 +2025-10-30 23:35:24.788842: Pseudo dice [np.float32(0.985), np.float32(0.9925), np.float32(0.9946), np.float32(0.7866)] +2025-10-30 23:35:24.790420: Epoch time: 20.06 s +2025-10-30 23:35:25.861005: +2025-10-30 23:35:25.862945: Epoch 430 +2025-10-30 23:35:25.864752: Current learning rate: 0.00603 +2025-10-30 23:35:44.893328: train_loss -0.9891 +2025-10-30 23:35:44.896856: val_loss -0.8907 +2025-10-30 23:35:44.898741: Pseudo dice [np.float32(0.9859), np.float32(0.9926), np.float32(0.9944), np.float32(0.7828)] +2025-10-30 23:35:44.900517: Epoch time: 19.03 s +2025-10-30 23:35:45.933346: +2025-10-30 23:35:45.935779: Epoch 431 +2025-10-30 23:35:45.938113: Current learning rate: 0.00602 +2025-10-30 23:36:06.355300: train_loss -0.9892 +2025-10-30 23:36:06.360603: val_loss -0.8956 +2025-10-30 23:36:06.362293: Pseudo dice [np.float32(0.9849), np.float32(0.9928), np.float32(0.9949), np.float32(0.7989)] +2025-10-30 23:36:06.363886: Epoch time: 20.42 s +2025-10-30 23:36:07.554820: +2025-10-30 23:36:07.556832: Epoch 432 +2025-10-30 23:36:07.559317: Current learning rate: 0.00601 +2025-10-30 23:36:26.636352: train_loss -0.9901 +2025-10-30 23:36:26.638548: val_loss -0.8885 +2025-10-30 23:36:26.640507: Pseudo dice [np.float32(0.9843), np.float32(0.9917), np.float32(0.9943), np.float32(0.7819)] +2025-10-30 23:36:26.642424: Epoch time: 19.08 s +2025-10-30 23:36:27.781009: +2025-10-30 23:36:27.782756: Epoch 433 +2025-10-30 23:36:27.784481: Current learning rate: 0.006 +2025-10-30 23:36:48.069513: train_loss -0.9895 +2025-10-30 23:36:48.073458: val_loss -0.8925 +2025-10-30 23:36:48.075289: Pseudo dice [np.float32(0.9868), np.float32(0.9921), np.float32(0.9942), np.float32(0.7904)] +2025-10-30 23:36:48.076999: Epoch time: 20.29 s +2025-10-30 23:36:49.187924: +2025-10-30 23:36:49.190275: Epoch 434 +2025-10-30 23:36:49.192245: Current learning rate: 0.00599 +2025-10-30 23:37:09.545942: train_loss -0.9887 +2025-10-30 23:37:09.549258: val_loss -0.8788 +2025-10-30 23:37:09.551270: Pseudo dice [np.float32(0.9854), np.float32(0.9921), np.float32(0.9944), np.float32(0.7486)] +2025-10-30 23:37:09.555778: Epoch time: 20.36 s +2025-10-30 23:37:10.779948: +2025-10-30 23:37:10.782033: Epoch 435 +2025-10-30 23:37:10.784618: Current learning rate: 0.00598 +2025-10-30 23:37:31.034975: train_loss -0.9888 +2025-10-30 23:37:31.038249: val_loss -0.8932 +2025-10-30 23:37:31.040192: Pseudo dice [np.float32(0.9878), np.float32(0.9927), np.float32(0.9944), np.float32(0.7806)] +2025-10-30 23:37:31.043080: Epoch time: 20.26 s +2025-10-30 23:37:32.079193: +2025-10-30 23:37:32.081358: Epoch 436 +2025-10-30 23:37:32.083121: Current learning rate: 0.00597 +2025-10-30 23:37:51.448024: train_loss -0.9894 +2025-10-30 23:37:51.451247: val_loss -0.9011 +2025-10-30 23:37:51.452942: Pseudo dice [np.float32(0.9859), np.float32(0.9923), np.float32(0.995), np.float32(0.811)] +2025-10-30 23:37:51.454686: Epoch time: 19.37 s +2025-10-30 23:37:52.928135: +2025-10-30 23:37:52.930076: Epoch 437 +2025-10-30 23:37:52.931824: Current learning rate: 0.00596 +2025-10-30 23:38:13.606924: train_loss -0.9897 +2025-10-30 23:38:13.609345: val_loss -0.8978 +2025-10-30 23:38:13.611072: Pseudo dice [np.float32(0.9847), np.float32(0.9921), np.float32(0.9948), np.float32(0.8094)] +2025-10-30 23:38:13.612816: Epoch time: 20.68 s +2025-10-30 23:38:14.797948: +2025-10-30 23:38:14.800201: Epoch 438 +2025-10-30 23:38:14.802060: Current learning rate: 0.00595 +2025-10-30 23:38:35.335128: train_loss -0.9891 +2025-10-30 23:38:35.337418: val_loss -0.8852 +2025-10-30 23:38:35.339293: Pseudo dice [np.float32(0.9853), np.float32(0.9918), np.float32(0.9944), np.float32(0.775)] +2025-10-30 23:38:35.341171: Epoch time: 20.54 s +2025-10-30 23:38:36.401619: +2025-10-30 23:38:36.404430: Epoch 439 +2025-10-30 23:38:36.406457: Current learning rate: 0.00594 +2025-10-30 23:38:56.051470: train_loss -0.9895 +2025-10-30 23:38:56.056628: val_loss -0.8954 +2025-10-30 23:38:56.058288: Pseudo dice [np.float32(0.9844), np.float32(0.9912), np.float32(0.9945), np.float32(0.8069)] +2025-10-30 23:38:56.059935: Epoch time: 19.65 s +2025-10-30 23:38:57.298937: +2025-10-30 23:38:57.300998: Epoch 440 +2025-10-30 23:38:57.302943: Current learning rate: 0.00593 +2025-10-30 23:39:17.481806: train_loss -0.9898 +2025-10-30 23:39:17.484104: val_loss -0.8941 +2025-10-30 23:39:17.485815: Pseudo dice [np.float32(0.9847), np.float32(0.9924), np.float32(0.995), np.float32(0.7985)] +2025-10-30 23:39:17.487433: Epoch time: 20.18 s +2025-10-30 23:39:18.594641: +2025-10-30 23:39:18.596995: Epoch 441 +2025-10-30 23:39:18.599212: Current learning rate: 0.00592 +2025-10-30 23:39:38.676402: train_loss -0.9903 +2025-10-30 23:39:38.679701: val_loss -0.8963 +2025-10-30 23:39:38.682041: Pseudo dice [np.float32(0.9841), np.float32(0.9916), np.float32(0.995), np.float32(0.8055)] +2025-10-30 23:39:38.684666: Epoch time: 20.08 s +2025-10-30 23:39:39.769439: +2025-10-30 23:39:39.771416: Epoch 442 +2025-10-30 23:39:39.773207: Current learning rate: 0.00592 +2025-10-30 23:40:00.261066: train_loss -0.99 +2025-10-30 23:40:00.263834: val_loss -0.8892 +2025-10-30 23:40:00.265487: Pseudo dice [np.float32(0.9852), np.float32(0.9913), np.float32(0.9944), np.float32(0.7948)] +2025-10-30 23:40:00.267047: Epoch time: 20.49 s +2025-10-30 23:40:01.462890: +2025-10-30 23:40:01.465587: Epoch 443 +2025-10-30 23:40:01.468363: Current learning rate: 0.00591 +2025-10-30 23:40:20.893842: train_loss -0.9893 +2025-10-30 23:40:20.896431: val_loss -0.8934 +2025-10-30 23:40:20.898125: Pseudo dice [np.float32(0.9869), np.float32(0.9927), np.float32(0.9945), np.float32(0.7926)] +2025-10-30 23:40:20.899912: Epoch time: 19.43 s +2025-10-30 23:40:22.263908: +2025-10-30 23:40:22.276680: Epoch 444 +2025-10-30 23:40:22.278589: Current learning rate: 0.0059 +2025-10-30 23:40:42.464858: train_loss -0.9905 +2025-10-30 23:40:42.467209: val_loss -0.8897 +2025-10-30 23:40:42.470484: Pseudo dice [np.float32(0.9858), np.float32(0.9927), np.float32(0.9946), np.float32(0.7859)] +2025-10-30 23:40:42.472099: Epoch time: 20.2 s +2025-10-30 23:40:43.668969: +2025-10-30 23:40:43.671030: Epoch 445 +2025-10-30 23:40:43.672799: Current learning rate: 0.00589 +2025-10-30 23:41:03.994272: train_loss -0.9891 +2025-10-30 23:41:03.997337: val_loss -0.8899 +2025-10-30 23:41:03.998989: Pseudo dice [np.float32(0.9853), np.float32(0.9923), np.float32(0.9942), np.float32(0.7871)] +2025-10-30 23:41:04.001208: Epoch time: 20.33 s +2025-10-30 23:41:05.006954: +2025-10-30 23:41:05.008592: Epoch 446 +2025-10-30 23:41:05.010042: Current learning rate: 0.00588 +2025-10-30 23:41:22.901772: train_loss -0.9896 +2025-10-30 23:41:22.906183: val_loss -0.8959 +2025-10-30 23:41:22.908053: Pseudo dice [np.float32(0.986), np.float32(0.9917), np.float32(0.9945), np.float32(0.8069)] +2025-10-30 23:41:22.909809: Epoch time: 17.9 s +2025-10-30 23:41:24.099776: +2025-10-30 23:41:24.102739: Epoch 447 +2025-10-30 23:41:24.106420: Current learning rate: 0.00587 +2025-10-30 23:41:44.389376: train_loss -0.9895 +2025-10-30 23:41:44.394686: val_loss -0.8952 +2025-10-30 23:41:44.397079: Pseudo dice [np.float32(0.9869), np.float32(0.993), np.float32(0.9947), np.float32(0.7884)] +2025-10-30 23:41:44.400337: Epoch time: 20.29 s +2025-10-30 23:41:45.589867: +2025-10-30 23:41:45.592124: Epoch 448 +2025-10-30 23:41:45.594179: Current learning rate: 0.00586 +2025-10-30 23:42:06.067802: train_loss -0.9888 +2025-10-30 23:42:06.072206: val_loss -0.8976 +2025-10-30 23:42:06.074314: Pseudo dice [np.float32(0.984), np.float32(0.9917), np.float32(0.9951), np.float32(0.8052)] +2025-10-30 23:42:06.077036: Epoch time: 20.48 s +2025-10-30 23:42:07.597890: +2025-10-30 23:42:07.600197: Epoch 449 +2025-10-30 23:42:07.602325: Current learning rate: 0.00585 +2025-10-30 23:42:27.644203: train_loss -0.9894 +2025-10-30 23:42:27.646699: val_loss -0.8949 +2025-10-30 23:42:27.648522: Pseudo dice [np.float32(0.9847), np.float32(0.9925), np.float32(0.9947), np.float32(0.7954)] +2025-10-30 23:42:27.650591: Epoch time: 20.05 s +2025-10-30 23:42:29.839057: +2025-10-30 23:42:29.841071: Epoch 450 +2025-10-30 23:42:29.842814: Current learning rate: 0.00584 +2025-10-30 23:42:50.296282: train_loss -0.9909 +2025-10-30 23:42:50.298993: val_loss -0.8998 +2025-10-30 23:42:50.300958: Pseudo dice [np.float32(0.9861), np.float32(0.9925), np.float32(0.995), np.float32(0.8072)] +2025-10-30 23:42:50.303036: Epoch time: 20.46 s +2025-10-30 23:42:51.361909: +2025-10-30 23:42:51.363710: Epoch 451 +2025-10-30 23:42:51.365427: Current learning rate: 0.00583 +2025-10-30 23:43:11.987148: train_loss -0.9893 +2025-10-30 23:43:11.990721: val_loss -0.8926 +2025-10-30 23:43:11.992930: Pseudo dice [np.float32(0.9874), np.float32(0.9927), np.float32(0.9945), np.float32(0.7805)] +2025-10-30 23:43:11.995287: Epoch time: 20.63 s +2025-10-30 23:43:13.148250: +2025-10-30 23:43:13.151093: Epoch 452 +2025-10-30 23:43:13.153338: Current learning rate: 0.00582 +2025-10-30 23:43:33.489862: train_loss -0.9893 +2025-10-30 23:43:33.492693: val_loss -0.8976 +2025-10-30 23:43:33.495364: Pseudo dice [np.float32(0.9852), np.float32(0.9921), np.float32(0.9944), np.float32(0.8064)] +2025-10-30 23:43:33.498599: Epoch time: 20.34 s +2025-10-30 23:43:34.748373: +2025-10-30 23:43:34.750335: Epoch 453 +2025-10-30 23:43:34.752118: Current learning rate: 0.00581 +2025-10-30 23:43:53.875470: train_loss -0.9892 +2025-10-30 23:43:53.877848: val_loss -0.9016 +2025-10-30 23:43:53.879777: Pseudo dice [np.float32(0.9852), np.float32(0.9923), np.float32(0.9947), np.float32(0.8055)] +2025-10-30 23:43:53.881577: Epoch time: 19.13 s +2025-10-30 23:43:54.881168: +2025-10-30 23:43:54.883295: Epoch 454 +2025-10-30 23:43:54.885464: Current learning rate: 0.0058 +2025-10-30 23:44:15.378467: train_loss -0.9901 +2025-10-30 23:44:15.381633: val_loss -0.9021 +2025-10-30 23:44:15.383484: Pseudo dice [np.float32(0.987), np.float32(0.9933), np.float32(0.9946), np.float32(0.805)] +2025-10-30 23:44:15.385175: Epoch time: 20.5 s +2025-10-30 23:44:16.380048: +2025-10-30 23:44:16.382028: Epoch 455 +2025-10-30 23:44:16.384550: Current learning rate: 0.00579 +2025-10-30 23:44:36.922882: train_loss -0.9894 +2025-10-30 23:44:36.931855: val_loss -0.8839 +2025-10-30 23:44:36.933619: Pseudo dice [np.float32(0.9847), np.float32(0.9919), np.float32(0.9941), np.float32(0.7668)] +2025-10-30 23:44:36.935486: Epoch time: 20.54 s +2025-10-30 23:44:38.224412: +2025-10-30 23:44:38.226427: Epoch 456 +2025-10-30 23:44:38.228460: Current learning rate: 0.00578 +2025-10-30 23:44:57.480777: train_loss -0.9898 +2025-10-30 23:44:57.483262: val_loss -0.8933 +2025-10-30 23:44:57.484899: Pseudo dice [np.float32(0.983), np.float32(0.9919), np.float32(0.9948), np.float32(0.802)] +2025-10-30 23:44:57.486537: Epoch time: 19.26 s +2025-10-30 23:44:58.667691: +2025-10-30 23:44:58.669959: Epoch 457 +2025-10-30 23:44:58.671720: Current learning rate: 0.00577 +2025-10-30 23:45:19.227121: train_loss -0.9875 +2025-10-30 23:45:19.230236: val_loss -0.9033 +2025-10-30 23:45:19.232414: Pseudo dice [np.float32(0.9873), np.float32(0.9923), np.float32(0.9948), np.float32(0.8128)] +2025-10-30 23:45:19.235274: Epoch time: 20.56 s +2025-10-30 23:45:20.241635: +2025-10-30 23:45:20.243499: Epoch 458 +2025-10-30 23:45:20.245113: Current learning rate: 0.00576 +2025-10-30 23:45:40.684165: train_loss -0.9881 +2025-10-30 23:45:40.689605: val_loss -0.8953 +2025-10-30 23:45:40.691325: Pseudo dice [np.float32(0.9864), np.float32(0.9925), np.float32(0.9949), np.float32(0.7977)] +2025-10-30 23:45:40.693020: Epoch time: 20.44 s +2025-10-30 23:45:41.805089: +2025-10-30 23:45:41.807643: Epoch 459 +2025-10-30 23:45:41.809907: Current learning rate: 0.00575 +2025-10-30 23:46:02.452085: train_loss -0.9874 +2025-10-30 23:46:02.454483: val_loss -0.8935 +2025-10-30 23:46:02.456401: Pseudo dice [np.float32(0.9858), np.float32(0.992), np.float32(0.9946), np.float32(0.7913)] +2025-10-30 23:46:02.458485: Epoch time: 20.65 s +2025-10-30 23:46:03.624477: +2025-10-30 23:46:03.626453: Epoch 460 +2025-10-30 23:46:03.628330: Current learning rate: 0.00574 +2025-10-30 23:46:23.066779: train_loss -0.9899 +2025-10-30 23:46:23.069802: val_loss -0.8933 +2025-10-30 23:46:23.071541: Pseudo dice [np.float32(0.9856), np.float32(0.9929), np.float32(0.9944), np.float32(0.7887)] +2025-10-30 23:46:23.074315: Epoch time: 19.44 s +2025-10-30 23:46:24.258496: +2025-10-30 23:46:24.271099: Epoch 461 +2025-10-30 23:46:24.273055: Current learning rate: 0.00573 +2025-10-30 23:46:44.805042: train_loss -0.9897 +2025-10-30 23:46:44.809122: val_loss -0.8985 +2025-10-30 23:46:44.810625: Pseudo dice [np.float32(0.9848), np.float32(0.9924), np.float32(0.9949), np.float32(0.8115)] +2025-10-30 23:46:44.812444: Epoch time: 20.55 s +2025-10-30 23:46:46.745137: +2025-10-30 23:46:46.747840: Epoch 462 +2025-10-30 23:46:46.749812: Current learning rate: 0.00572 +2025-10-30 23:47:06.778421: train_loss -0.9867 +2025-10-30 23:47:06.782287: val_loss -0.8864 +2025-10-30 23:47:06.786811: Pseudo dice [np.float32(0.985), np.float32(0.9917), np.float32(0.9942), np.float32(0.768)] +2025-10-30 23:47:06.790679: Epoch time: 20.04 s +2025-10-30 23:47:07.787232: +2025-10-30 23:47:07.789538: Epoch 463 +2025-10-30 23:47:07.791335: Current learning rate: 0.00571 +2025-10-30 23:47:27.956973: train_loss -0.9856 +2025-10-30 23:47:27.959832: val_loss -0.9005 +2025-10-30 23:47:27.961366: Pseudo dice [np.float32(0.9858), np.float32(0.9922), np.float32(0.9948), np.float32(0.8043)] +2025-10-30 23:47:27.963202: Epoch time: 20.17 s +2025-10-30 23:47:29.173311: +2025-10-30 23:47:29.175640: Epoch 464 +2025-10-30 23:47:29.177830: Current learning rate: 0.0057 +2025-10-30 23:47:49.846651: train_loss -0.9868 +2025-10-30 23:47:49.848914: val_loss -0.8974 +2025-10-30 23:47:49.850625: Pseudo dice [np.float32(0.9851), np.float32(0.9919), np.float32(0.9944), np.float32(0.7972)] +2025-10-30 23:47:49.852553: Epoch time: 20.68 s +2025-10-30 23:47:51.051177: +2025-10-30 23:47:51.057128: Epoch 465 +2025-10-30 23:47:51.059120: Current learning rate: 0.0057 +2025-10-30 23:48:11.725147: train_loss -0.9887 +2025-10-30 23:48:11.728565: val_loss -0.8998 +2025-10-30 23:48:11.731280: Pseudo dice [np.float32(0.9867), np.float32(0.9926), np.float32(0.9943), np.float32(0.8019)] +2025-10-30 23:48:11.733101: Epoch time: 20.68 s +2025-10-30 23:48:12.757895: +2025-10-30 23:48:12.759962: Epoch 466 +2025-10-30 23:48:12.762165: Current learning rate: 0.00569 +2025-10-30 23:48:33.414950: train_loss -0.9883 +2025-10-30 23:48:33.418210: val_loss -0.8935 +2025-10-30 23:48:33.419831: Pseudo dice [np.float32(0.9853), np.float32(0.9919), np.float32(0.9943), np.float32(0.801)] +2025-10-30 23:48:33.421441: Epoch time: 20.66 s +2025-10-30 23:48:34.583734: +2025-10-30 23:48:34.588289: Epoch 467 +2025-10-30 23:48:34.590637: Current learning rate: 0.00568 +2025-10-30 23:48:54.361256: train_loss -0.9887 +2025-10-30 23:48:54.364303: val_loss -0.8927 +2025-10-30 23:48:54.366533: Pseudo dice [np.float32(0.985), np.float32(0.9919), np.float32(0.9942), np.float32(0.7899)] +2025-10-30 23:48:54.368548: Epoch time: 19.78 s +2025-10-30 23:48:55.371408: +2025-10-30 23:48:55.373561: Epoch 468 +2025-10-30 23:48:55.376211: Current learning rate: 0.00567 +2025-10-30 23:49:15.958787: train_loss -0.9894 +2025-10-30 23:49:15.961593: val_loss -0.8869 +2025-10-30 23:49:15.963398: Pseudo dice [np.float32(0.9855), np.float32(0.9912), np.float32(0.9945), np.float32(0.7804)] +2025-10-30 23:49:15.965037: Epoch time: 20.59 s +2025-10-30 23:49:17.152278: +2025-10-30 23:49:17.156422: Epoch 469 +2025-10-30 23:49:17.158321: Current learning rate: 0.00566 +2025-10-30 23:49:37.021634: train_loss -0.9903 +2025-10-30 23:49:37.027349: val_loss -0.8923 +2025-10-30 23:49:37.029881: Pseudo dice [np.float32(0.9857), np.float32(0.992), np.float32(0.9948), np.float32(0.7924)] +2025-10-30 23:49:37.031917: Epoch time: 19.87 s +2025-10-30 23:49:38.211010: +2025-10-30 23:49:38.213392: Epoch 470 +2025-10-30 23:49:38.215384: Current learning rate: 0.00565 +2025-10-30 23:49:59.063263: train_loss -0.9889 +2025-10-30 23:49:59.065885: val_loss -0.8938 +2025-10-30 23:49:59.067715: Pseudo dice [np.float32(0.9858), np.float32(0.9922), np.float32(0.9944), np.float32(0.7892)] +2025-10-30 23:49:59.070079: Epoch time: 20.85 s +2025-10-30 23:50:00.291754: +2025-10-30 23:50:00.294863: Epoch 471 +2025-10-30 23:50:00.296692: Current learning rate: 0.00564 +2025-10-30 23:50:21.297294: train_loss -0.9885 +2025-10-30 23:50:21.299497: val_loss -0.898 +2025-10-30 23:50:21.304734: Pseudo dice [np.float32(0.9846), np.float32(0.9918), np.float32(0.9944), np.float32(0.8075)] +2025-10-30 23:50:21.307017: Epoch time: 21.01 s +2025-10-30 23:50:22.594177: +2025-10-30 23:50:22.596041: Epoch 472 +2025-10-30 23:50:22.597700: Current learning rate: 0.00563 +2025-10-30 23:50:42.931409: train_loss -0.9886 +2025-10-30 23:50:42.934543: val_loss -0.902 +2025-10-30 23:50:42.936206: Pseudo dice [np.float32(0.9852), np.float32(0.9914), np.float32(0.9946), np.float32(0.8125)] +2025-10-30 23:50:42.937784: Epoch time: 20.34 s +2025-10-30 23:50:43.996963: +2025-10-30 23:50:43.999083: Epoch 473 +2025-10-30 23:50:44.001652: Current learning rate: 0.00562 +2025-10-30 23:51:04.268434: train_loss -0.9891 +2025-10-30 23:51:04.270359: val_loss -0.8995 +2025-10-30 23:51:04.272017: Pseudo dice [np.float32(0.9859), np.float32(0.9925), np.float32(0.9947), np.float32(0.8059)] +2025-10-30 23:51:04.273601: Epoch time: 20.27 s +2025-10-30 23:51:05.263982: +2025-10-30 23:51:05.266137: Epoch 474 +2025-10-30 23:51:05.267928: Current learning rate: 0.00561 +2025-10-30 23:51:25.429516: train_loss -0.9892 +2025-10-30 23:51:25.432563: val_loss -0.884 +2025-10-30 23:51:25.434399: Pseudo dice [np.float32(0.9839), np.float32(0.9914), np.float32(0.9944), np.float32(0.7795)] +2025-10-30 23:51:25.436181: Epoch time: 20.17 s +2025-10-30 23:51:27.286459: +2025-10-30 23:51:27.288644: Epoch 475 +2025-10-30 23:51:27.290900: Current learning rate: 0.0056 +2025-10-30 23:51:46.691712: train_loss -0.9898 +2025-10-30 23:51:46.694848: val_loss -0.8878 +2025-10-30 23:51:46.696756: Pseudo dice [np.float32(0.9846), np.float32(0.9914), np.float32(0.9942), np.float32(0.7878)] +2025-10-30 23:51:46.699009: Epoch time: 19.41 s +2025-10-30 23:51:47.818793: +2025-10-30 23:51:47.822134: Epoch 476 +2025-10-30 23:51:47.824006: Current learning rate: 0.00559 +2025-10-30 23:52:08.270826: train_loss -0.9896 +2025-10-30 23:52:08.273208: val_loss -0.8902 +2025-10-30 23:52:08.275112: Pseudo dice [np.float32(0.9866), np.float32(0.9924), np.float32(0.9949), np.float32(0.7853)] +2025-10-30 23:52:08.277184: Epoch time: 20.45 s +2025-10-30 23:52:09.367618: +2025-10-30 23:52:09.370255: Epoch 477 +2025-10-30 23:52:09.372050: Current learning rate: 0.00558 +2025-10-30 23:52:29.669864: train_loss -0.9888 +2025-10-30 23:52:29.672130: val_loss -0.884 +2025-10-30 23:52:29.673924: Pseudo dice [np.float32(0.9857), np.float32(0.9923), np.float32(0.9941), np.float32(0.7721)] +2025-10-30 23:52:29.675480: Epoch time: 20.3 s +2025-10-30 23:52:30.733220: +2025-10-30 23:52:30.735568: Epoch 478 +2025-10-30 23:52:30.737504: Current learning rate: 0.00557 +2025-10-30 23:52:50.965466: train_loss -0.9889 +2025-10-30 23:52:50.968590: val_loss -0.8848 +2025-10-30 23:52:50.970256: Pseudo dice [np.float32(0.9848), np.float32(0.9919), np.float32(0.9944), np.float32(0.7781)] +2025-10-30 23:52:50.971850: Epoch time: 20.23 s +2025-10-30 23:52:52.186579: +2025-10-30 23:52:52.189029: Epoch 479 +2025-10-30 23:52:52.190920: Current learning rate: 0.00556 +2025-10-30 23:53:12.657900: train_loss -0.9903 +2025-10-30 23:53:12.661116: val_loss -0.8896 +2025-10-30 23:53:12.663455: Pseudo dice [np.float32(0.9859), np.float32(0.9921), np.float32(0.9944), np.float32(0.7833)] +2025-10-30 23:53:12.665438: Epoch time: 20.47 s +2025-10-30 23:53:13.908788: +2025-10-30 23:53:13.910564: Epoch 480 +2025-10-30 23:53:13.912098: Current learning rate: 0.00555 +2025-10-30 23:53:33.216655: train_loss -0.9902 +2025-10-30 23:53:33.219616: val_loss -0.8885 +2025-10-30 23:53:33.222609: Pseudo dice [np.float32(0.9842), np.float32(0.9917), np.float32(0.9944), np.float32(0.7807)] +2025-10-30 23:53:33.225510: Epoch time: 19.31 s +2025-10-30 23:53:34.290179: +2025-10-30 23:53:34.291872: Epoch 481 +2025-10-30 23:53:34.293916: Current learning rate: 0.00554 +2025-10-30 23:53:54.971434: train_loss -0.9889 +2025-10-30 23:53:54.974180: val_loss -0.8956 +2025-10-30 23:53:54.975870: Pseudo dice [np.float32(0.9855), np.float32(0.9928), np.float32(0.9948), np.float32(0.7975)] +2025-10-30 23:53:54.977491: Epoch time: 20.68 s +2025-10-30 23:53:56.160862: +2025-10-30 23:53:56.162942: Epoch 482 +2025-10-30 23:53:56.165478: Current learning rate: 0.00553 +2025-10-30 23:54:16.364424: train_loss -0.9893 +2025-10-30 23:54:16.367485: val_loss -0.8873 +2025-10-30 23:54:16.369520: Pseudo dice [np.float32(0.9835), np.float32(0.9922), np.float32(0.9944), np.float32(0.7883)] +2025-10-30 23:54:16.371467: Epoch time: 20.21 s +2025-10-30 23:54:17.639926: +2025-10-30 23:54:17.641899: Epoch 483 +2025-10-30 23:54:17.643634: Current learning rate: 0.00552 +2025-10-30 23:54:38.211060: train_loss -0.9903 +2025-10-30 23:54:38.214038: val_loss -0.8918 +2025-10-30 23:54:38.215982: Pseudo dice [np.float32(0.9865), np.float32(0.9929), np.float32(0.9944), np.float32(0.7884)] +2025-10-30 23:54:38.217819: Epoch time: 20.57 s +2025-10-30 23:54:39.229345: +2025-10-30 23:54:39.231756: Epoch 484 +2025-10-30 23:54:39.234177: Current learning rate: 0.00551 +2025-10-30 23:54:59.658220: train_loss -0.9907 +2025-10-30 23:54:59.661944: val_loss -0.8823 +2025-10-30 23:54:59.664651: Pseudo dice [np.float32(0.9844), np.float32(0.9919), np.float32(0.9942), np.float32(0.7714)] +2025-10-30 23:54:59.666812: Epoch time: 20.43 s +2025-10-30 23:55:00.795296: +2025-10-30 23:55:00.797356: Epoch 485 +2025-10-30 23:55:00.799269: Current learning rate: 0.0055 +2025-10-30 23:55:21.348083: train_loss -0.9908 +2025-10-30 23:55:21.351110: val_loss -0.8897 +2025-10-30 23:55:21.353112: Pseudo dice [np.float32(0.9828), np.float32(0.9916), np.float32(0.9943), np.float32(0.7973)] +2025-10-30 23:55:21.355122: Epoch time: 20.55 s +2025-10-30 23:55:22.551883: +2025-10-30 23:55:22.554452: Epoch 486 +2025-10-30 23:55:22.556519: Current learning rate: 0.00549 +2025-10-30 23:55:43.000048: train_loss -0.9901 +2025-10-30 23:55:43.002571: val_loss -0.8899 +2025-10-30 23:55:43.004891: Pseudo dice [np.float32(0.9844), np.float32(0.9915), np.float32(0.9945), np.float32(0.7893)] +2025-10-30 23:55:43.007187: Epoch time: 20.45 s +2025-10-30 23:55:44.661039: +2025-10-30 23:55:44.663131: Epoch 487 +2025-10-30 23:55:44.665341: Current learning rate: 0.00548 +2025-10-30 23:56:04.060509: train_loss -0.9899 +2025-10-30 23:56:04.063919: val_loss -0.8898 +2025-10-30 23:56:04.065697: Pseudo dice [np.float32(0.9859), np.float32(0.9919), np.float32(0.9945), np.float32(0.7927)] +2025-10-30 23:56:04.067419: Epoch time: 19.4 s +2025-10-30 23:56:05.275749: +2025-10-30 23:56:05.279019: Epoch 488 +2025-10-30 23:56:05.280897: Current learning rate: 0.00547 +2025-10-30 23:56:24.776525: train_loss -0.9894 +2025-10-30 23:56:24.778672: val_loss -0.8852 +2025-10-30 23:56:24.780461: Pseudo dice [np.float32(0.9839), np.float32(0.992), np.float32(0.9939), np.float32(0.7814)] +2025-10-30 23:56:24.782000: Epoch time: 19.5 s +2025-10-30 23:56:25.957182: +2025-10-30 23:56:25.959262: Epoch 489 +2025-10-30 23:56:25.961224: Current learning rate: 0.00546 +2025-10-30 23:56:46.783561: train_loss -0.99 +2025-10-30 23:56:46.786633: val_loss -0.8809 +2025-10-30 23:56:46.788715: Pseudo dice [np.float32(0.9854), np.float32(0.9924), np.float32(0.994), np.float32(0.7716)] +2025-10-30 23:56:46.790817: Epoch time: 20.83 s +2025-10-30 23:56:47.957664: +2025-10-30 23:56:47.959847: Epoch 490 +2025-10-30 23:56:47.961753: Current learning rate: 0.00546 +2025-10-30 23:57:08.341567: train_loss -0.9895 +2025-10-30 23:57:08.344093: val_loss -0.891 +2025-10-30 23:57:08.345831: Pseudo dice [np.float32(0.9858), np.float32(0.9927), np.float32(0.9943), np.float32(0.7895)] +2025-10-30 23:57:08.347514: Epoch time: 20.39 s +2025-10-30 23:57:09.532461: +2025-10-30 23:57:09.534437: Epoch 491 +2025-10-30 23:57:09.535958: Current learning rate: 0.00545 +2025-10-30 23:57:30.030717: train_loss -0.9899 +2025-10-30 23:57:30.032978: val_loss -0.8893 +2025-10-30 23:57:30.034680: Pseudo dice [np.float32(0.9857), np.float32(0.9922), np.float32(0.9944), np.float32(0.7859)] +2025-10-30 23:57:30.036268: Epoch time: 20.5 s +2025-10-30 23:57:31.233436: +2025-10-30 23:57:31.235351: Epoch 492 +2025-10-30 23:57:31.237047: Current learning rate: 0.00544 +2025-10-30 23:57:51.799692: train_loss -0.9895 +2025-10-30 23:57:51.805830: val_loss -0.8948 +2025-10-30 23:57:51.808439: Pseudo dice [np.float32(0.9848), np.float32(0.9924), np.float32(0.9946), np.float32(0.7913)] +2025-10-30 23:57:51.810699: Epoch time: 20.57 s +2025-10-30 23:57:53.056877: +2025-10-30 23:57:53.058807: Epoch 493 +2025-10-30 23:57:53.060409: Current learning rate: 0.00543 +2025-10-30 23:58:13.521741: train_loss -0.9894 +2025-10-30 23:58:13.525305: val_loss -0.8982 +2025-10-30 23:58:13.527193: Pseudo dice [np.float32(0.9872), np.float32(0.9932), np.float32(0.995), np.float32(0.7983)] +2025-10-30 23:58:13.529332: Epoch time: 20.47 s +2025-10-30 23:58:14.592095: +2025-10-30 23:58:14.594223: Epoch 494 +2025-10-30 23:58:14.595957: Current learning rate: 0.00542 +2025-10-30 23:58:34.207433: train_loss -0.989 +2025-10-30 23:58:34.209849: val_loss -0.8973 +2025-10-30 23:58:34.212076: Pseudo dice [np.float32(0.9844), np.float32(0.9919), np.float32(0.9948), np.float32(0.8084)] +2025-10-30 23:58:34.214200: Epoch time: 19.62 s +2025-10-30 23:58:35.235697: +2025-10-30 23:58:35.237872: Epoch 495 +2025-10-30 23:58:35.240595: Current learning rate: 0.00541 +2025-10-30 23:58:55.008873: train_loss -0.9895 +2025-10-30 23:58:55.011299: val_loss -0.8972 +2025-10-30 23:58:55.012976: Pseudo dice [np.float32(0.9844), np.float32(0.9923), np.float32(0.9952), np.float32(0.8054)] +2025-10-30 23:58:55.014632: Epoch time: 19.77 s +2025-10-30 23:58:56.013140: +2025-10-30 23:58:56.015157: Epoch 496 +2025-10-30 23:58:56.017249: Current learning rate: 0.0054 +2025-10-30 23:59:16.549752: train_loss -0.9894 +2025-10-30 23:59:16.552413: val_loss -0.8923 +2025-10-30 23:59:16.554080: Pseudo dice [np.float32(0.9841), np.float32(0.9918), np.float32(0.9945), np.float32(0.7984)] +2025-10-30 23:59:16.556243: Epoch time: 20.54 s +2025-10-30 23:59:17.736338: +2025-10-30 23:59:17.738635: Epoch 497 +2025-10-30 23:59:17.740963: Current learning rate: 0.00539 +2025-10-30 23:59:38.179388: train_loss -0.99 +2025-10-30 23:59:38.181854: val_loss -0.8897 +2025-10-30 23:59:38.183521: Pseudo dice [np.float32(0.9862), np.float32(0.9932), np.float32(0.9948), np.float32(0.7797)] +2025-10-30 23:59:38.185259: Epoch time: 20.44 s +2025-10-30 23:59:39.232275: +2025-10-30 23:59:39.234239: Epoch 498 +2025-10-30 23:59:39.236224: Current learning rate: 0.00538 +2025-10-30 23:59:59.774393: train_loss -0.9901 +2025-10-30 23:59:59.776773: val_loss -0.8987 +2025-10-30 23:59:59.779023: Pseudo dice [np.float32(0.9864), np.float32(0.9926), np.float32(0.9949), np.float32(0.8071)] +2025-10-30 23:59:59.781888: Epoch time: 20.54 s +2025-10-31 00:00:01.319215: +2025-10-31 00:00:01.322541: Epoch 499 +2025-10-31 00:00:01.324248: Current learning rate: 0.00537 +2025-10-31 00:00:22.010672: train_loss -0.9905 +2025-10-31 00:00:22.013716: val_loss -0.8879 +2025-10-31 00:00:22.015998: Pseudo dice [np.float32(0.987), np.float32(0.9924), np.float32(0.9941), np.float32(0.7862)] +2025-10-31 00:00:22.019206: Epoch time: 20.69 s +2025-10-31 00:00:24.529682: +2025-10-31 00:00:24.534356: Epoch 500 +2025-10-31 00:00:24.536974: Current learning rate: 0.00536 +2025-10-31 00:00:44.969333: train_loss -0.9898 +2025-10-31 00:00:44.971460: val_loss -0.8915 +2025-10-31 00:00:44.973070: Pseudo dice [np.float32(0.9851), np.float32(0.9921), np.float32(0.9946), np.float32(0.7917)] +2025-10-31 00:00:44.974748: Epoch time: 20.44 s +2025-10-31 00:00:46.053071: +2025-10-31 00:00:46.055238: Epoch 501 +2025-10-31 00:00:46.057120: Current learning rate: 0.00535 +2025-10-31 00:01:04.125285: train_loss -0.9904 +2025-10-31 00:01:04.127166: val_loss -0.8927 +2025-10-31 00:01:04.129085: Pseudo dice [np.float32(0.9856), np.float32(0.9917), np.float32(0.9942), np.float32(0.7917)] +2025-10-31 00:01:04.133245: Epoch time: 18.07 s +2025-10-31 00:01:05.148737: +2025-10-31 00:01:05.150662: Epoch 502 +2025-10-31 00:01:05.152417: Current learning rate: 0.00534 +2025-10-31 00:01:25.702969: train_loss -0.9894 +2025-10-31 00:01:25.706466: val_loss -0.8868 +2025-10-31 00:01:25.708175: Pseudo dice [np.float32(0.9846), np.float32(0.9918), np.float32(0.9942), np.float32(0.7825)] +2025-10-31 00:01:25.709864: Epoch time: 20.56 s +2025-10-31 00:01:26.893387: +2025-10-31 00:01:26.895539: Epoch 503 +2025-10-31 00:01:26.897593: Current learning rate: 0.00533 +2025-10-31 00:01:47.576496: train_loss -0.9892 +2025-10-31 00:01:47.578988: val_loss -0.8941 +2025-10-31 00:01:47.580791: Pseudo dice [np.float32(0.9856), np.float32(0.9925), np.float32(0.9949), np.float32(0.7905)] +2025-10-31 00:01:47.586487: Epoch time: 20.68 s +2025-10-31 00:01:48.783226: +2025-10-31 00:01:48.785465: Epoch 504 +2025-10-31 00:01:48.787473: Current learning rate: 0.00532 +2025-10-31 00:02:09.422852: train_loss -0.991 +2025-10-31 00:02:09.428632: val_loss -0.8987 +2025-10-31 00:02:09.430241: Pseudo dice [np.float32(0.9864), np.float32(0.9927), np.float32(0.9949), np.float32(0.8069)] +2025-10-31 00:02:09.431635: Epoch time: 20.64 s +2025-10-31 00:02:10.556223: +2025-10-31 00:02:10.558325: Epoch 505 +2025-10-31 00:02:10.560247: Current learning rate: 0.00531 +2025-10-31 00:02:31.237893: train_loss -0.99 +2025-10-31 00:02:31.246224: val_loss -0.8897 +2025-10-31 00:02:31.249045: Pseudo dice [np.float32(0.9849), np.float32(0.9929), np.float32(0.9943), np.float32(0.7853)] +2025-10-31 00:02:31.251793: Epoch time: 20.68 s +2025-10-31 00:02:32.280926: +2025-10-31 00:02:32.285999: Epoch 506 +2025-10-31 00:02:32.287901: Current learning rate: 0.0053 +2025-10-31 00:02:52.964367: train_loss -0.9891 +2025-10-31 00:02:52.966717: val_loss -0.8874 +2025-10-31 00:02:52.968970: Pseudo dice [np.float32(0.9864), np.float32(0.9922), np.float32(0.9926), np.float32(0.782)] +2025-10-31 00:02:52.970671: Epoch time: 20.68 s +2025-10-31 00:02:53.980410: +2025-10-31 00:02:53.982502: Epoch 507 +2025-10-31 00:02:53.984040: Current learning rate: 0.00529 +2025-10-31 00:03:14.269276: train_loss -0.9875 +2025-10-31 00:03:14.271366: val_loss -0.8976 +2025-10-31 00:03:14.274130: Pseudo dice [np.float32(0.9854), np.float32(0.9933), np.float32(0.995), np.float32(0.8019)] +2025-10-31 00:03:14.276795: Epoch time: 20.29 s +2025-10-31 00:03:15.340914: +2025-10-31 00:03:15.342818: Epoch 508 +2025-10-31 00:03:15.345282: Current learning rate: 0.00528 +2025-10-31 00:03:35.100667: train_loss -0.9875 +2025-10-31 00:03:35.105096: val_loss -0.8926 +2025-10-31 00:03:35.107285: Pseudo dice [np.float32(0.9858), np.float32(0.9923), np.float32(0.9935), np.float32(0.7937)] +2025-10-31 00:03:35.109382: Epoch time: 19.76 s +2025-10-31 00:03:36.270949: +2025-10-31 00:03:36.273297: Epoch 509 +2025-10-31 00:03:36.275161: Current learning rate: 0.00527 +2025-10-31 00:03:57.074283: train_loss -0.9884 +2025-10-31 00:03:57.076922: val_loss -0.8923 +2025-10-31 00:03:57.078850: Pseudo dice [np.float32(0.9851), np.float32(0.9918), np.float32(0.9945), np.float32(0.7902)] +2025-10-31 00:03:57.080745: Epoch time: 20.81 s +2025-10-31 00:03:58.076185: +2025-10-31 00:03:58.078351: Epoch 510 +2025-10-31 00:03:58.080192: Current learning rate: 0.00526 +2025-10-31 00:04:18.695987: train_loss -0.9895 +2025-10-31 00:04:18.698828: val_loss -0.8838 +2025-10-31 00:04:18.701758: Pseudo dice [np.float32(0.9866), np.float32(0.9928), np.float32(0.9945), np.float32(0.7734)] +2025-10-31 00:04:18.705094: Epoch time: 20.62 s +2025-10-31 00:04:19.948973: +2025-10-31 00:04:19.950843: Epoch 511 +2025-10-31 00:04:19.952628: Current learning rate: 0.00525 +2025-10-31 00:04:40.497295: train_loss -0.989 +2025-10-31 00:04:40.500444: val_loss -0.8964 +2025-10-31 00:04:40.502524: Pseudo dice [np.float32(0.987), np.float32(0.993), np.float32(0.9944), np.float32(0.7963)] +2025-10-31 00:04:40.504639: Epoch time: 20.55 s +2025-10-31 00:04:41.968815: +2025-10-31 00:04:41.970741: Epoch 512 +2025-10-31 00:04:41.972382: Current learning rate: 0.00524 +2025-10-31 00:05:02.866707: train_loss -0.9898 +2025-10-31 00:05:02.868794: val_loss -0.8902 +2025-10-31 00:05:02.877843: Pseudo dice [np.float32(0.9858), np.float32(0.9928), np.float32(0.9942), np.float32(0.7844)] +2025-10-31 00:05:02.882936: Epoch time: 20.9 s +2025-10-31 00:05:03.885033: +2025-10-31 00:05:03.887382: Epoch 513 +2025-10-31 00:05:03.889544: Current learning rate: 0.00523 +2025-10-31 00:05:24.631577: train_loss -0.9896 +2025-10-31 00:05:24.633904: val_loss -0.8952 +2025-10-31 00:05:24.640490: Pseudo dice [np.float32(0.9854), np.float32(0.9932), np.float32(0.9947), np.float32(0.7945)] +2025-10-31 00:05:24.643109: Epoch time: 20.75 s +2025-10-31 00:05:25.636524: +2025-10-31 00:05:25.638375: Epoch 514 +2025-10-31 00:05:25.639959: Current learning rate: 0.00522 +2025-10-31 00:05:44.664914: train_loss -0.989 +2025-10-31 00:05:44.668246: val_loss -0.8979 +2025-10-31 00:05:44.671101: Pseudo dice [np.float32(0.9855), np.float32(0.9927), np.float32(0.9948), np.float32(0.8044)] +2025-10-31 00:05:44.673157: Epoch time: 19.03 s +2025-10-31 00:05:45.868252: +2025-10-31 00:05:45.870451: Epoch 515 +2025-10-31 00:05:45.872231: Current learning rate: 0.00521 +2025-10-31 00:06:06.652741: train_loss -0.9902 +2025-10-31 00:06:06.655706: val_loss -0.889 +2025-10-31 00:06:06.658103: Pseudo dice [np.float32(0.9842), np.float32(0.9924), np.float32(0.9943), np.float32(0.7835)] +2025-10-31 00:06:06.660199: Epoch time: 20.79 s +2025-10-31 00:06:07.828096: +2025-10-31 00:06:07.833607: Epoch 516 +2025-10-31 00:06:07.835645: Current learning rate: 0.0052 +2025-10-31 00:06:28.410663: train_loss -0.9907 +2025-10-31 00:06:28.412882: val_loss -0.8944 +2025-10-31 00:06:28.414631: Pseudo dice [np.float32(0.985), np.float32(0.9921), np.float32(0.9947), np.float32(0.8016)] +2025-10-31 00:06:28.416455: Epoch time: 20.58 s +2025-10-31 00:06:29.429326: +2025-10-31 00:06:29.431604: Epoch 517 +2025-10-31 00:06:29.433501: Current learning rate: 0.00519 +2025-10-31 00:06:50.227582: train_loss -0.991 +2025-10-31 00:06:50.231689: val_loss -0.8943 +2025-10-31 00:06:50.234054: Pseudo dice [np.float32(0.9831), np.float32(0.9927), np.float32(0.9948), np.float32(0.7977)] +2025-10-31 00:06:50.236981: Epoch time: 20.8 s +2025-10-31 00:06:51.541901: +2025-10-31 00:06:51.544556: Epoch 518 +2025-10-31 00:06:51.546500: Current learning rate: 0.00518 +2025-10-31 00:07:12.070981: train_loss -0.9914 +2025-10-31 00:07:12.073570: val_loss -0.8977 +2025-10-31 00:07:12.075230: Pseudo dice [np.float32(0.9851), np.float32(0.992), np.float32(0.9948), np.float32(0.8068)] +2025-10-31 00:07:12.076852: Epoch time: 20.53 s +2025-10-31 00:07:13.295618: +2025-10-31 00:07:13.297601: Epoch 519 +2025-10-31 00:07:13.300530: Current learning rate: 0.00518 +2025-10-31 00:07:34.067188: train_loss -0.9908 +2025-10-31 00:07:34.070252: val_loss -0.8902 +2025-10-31 00:07:34.073559: Pseudo dice [np.float32(0.9872), np.float32(0.9925), np.float32(0.9943), np.float32(0.7817)] +2025-10-31 00:07:34.076792: Epoch time: 20.77 s +2025-10-31 00:07:35.288872: +2025-10-31 00:07:35.291022: Epoch 520 +2025-10-31 00:07:35.293602: Current learning rate: 0.00517 +2025-10-31 00:07:55.623887: train_loss -0.9905 +2025-10-31 00:07:55.626822: val_loss -0.897 +2025-10-31 00:07:55.628975: Pseudo dice [np.float32(0.9865), np.float32(0.9927), np.float32(0.9949), np.float32(0.7985)] +2025-10-31 00:07:55.630779: Epoch time: 20.34 s +2025-10-31 00:07:56.813309: +2025-10-31 00:07:56.815440: Epoch 521 +2025-10-31 00:07:56.817389: Current learning rate: 0.00516 +2025-10-31 00:08:16.461866: train_loss -0.9905 +2025-10-31 00:08:16.464557: val_loss -0.8892 +2025-10-31 00:08:16.467221: Pseudo dice [np.float32(0.9857), np.float32(0.9921), np.float32(0.9944), np.float32(0.7851)] +2025-10-31 00:08:16.468887: Epoch time: 19.65 s +2025-10-31 00:08:17.596255: +2025-10-31 00:08:17.598186: Epoch 522 +2025-10-31 00:08:17.599815: Current learning rate: 0.00515 +2025-10-31 00:08:38.141422: train_loss -0.9908 +2025-10-31 00:08:38.143422: val_loss -0.8952 +2025-10-31 00:08:38.145226: Pseudo dice [np.float32(0.9836), np.float32(0.9926), np.float32(0.9952), np.float32(0.8062)] +2025-10-31 00:08:38.147197: Epoch time: 20.55 s +2025-10-31 00:08:39.176344: +2025-10-31 00:08:39.178142: Epoch 523 +2025-10-31 00:08:39.179755: Current learning rate: 0.00514 +2025-10-31 00:08:59.671527: train_loss -0.9897 +2025-10-31 00:08:59.674819: val_loss -0.8936 +2025-10-31 00:08:59.676842: Pseudo dice [np.float32(0.9856), np.float32(0.9925), np.float32(0.9946), np.float32(0.7976)] +2025-10-31 00:08:59.678505: Epoch time: 20.5 s +2025-10-31 00:09:01.242649: +2025-10-31 00:09:01.245077: Epoch 524 +2025-10-31 00:09:01.247452: Current learning rate: 0.00513 +2025-10-31 00:09:21.595996: train_loss -0.9899 +2025-10-31 00:09:21.598166: val_loss -0.8892 +2025-10-31 00:09:21.599710: Pseudo dice [np.float32(0.9861), np.float32(0.9919), np.float32(0.9945), np.float32(0.7835)] +2025-10-31 00:09:21.601118: Epoch time: 20.35 s +2025-10-31 00:09:22.612930: +2025-10-31 00:09:22.614655: Epoch 525 +2025-10-31 00:09:22.616229: Current learning rate: 0.00512 +2025-10-31 00:09:43.420180: train_loss -0.9897 +2025-10-31 00:09:43.422538: val_loss -0.8899 +2025-10-31 00:09:43.424211: Pseudo dice [np.float32(0.9842), np.float32(0.9917), np.float32(0.9944), np.float32(0.7839)] +2025-10-31 00:09:43.425898: Epoch time: 20.81 s +2025-10-31 00:09:44.424367: +2025-10-31 00:09:44.426571: Epoch 526 +2025-10-31 00:09:44.428173: Current learning rate: 0.00511 +2025-10-31 00:10:04.638495: train_loss -0.9889 +2025-10-31 00:10:04.641555: val_loss -0.8947 +2025-10-31 00:10:04.643267: Pseudo dice [np.float32(0.9848), np.float32(0.9919), np.float32(0.9946), np.float32(0.7985)] +2025-10-31 00:10:04.645097: Epoch time: 20.22 s +2025-10-31 00:10:05.798281: +2025-10-31 00:10:05.800524: Epoch 527 +2025-10-31 00:10:05.802284: Current learning rate: 0.0051 +2025-10-31 00:10:25.511238: train_loss -0.9893 +2025-10-31 00:10:25.513257: val_loss -0.877 +2025-10-31 00:10:25.514855: Pseudo dice [np.float32(0.9834), np.float32(0.9908), np.float32(0.9941), np.float32(0.7628)] +2025-10-31 00:10:25.516261: Epoch time: 19.71 s +2025-10-31 00:10:26.721985: +2025-10-31 00:10:26.724012: Epoch 528 +2025-10-31 00:10:26.726022: Current learning rate: 0.00509 +2025-10-31 00:10:45.853340: train_loss -0.9899 +2025-10-31 00:10:45.856719: val_loss -0.8963 +2025-10-31 00:10:45.858640: Pseudo dice [np.float32(0.9856), np.float32(0.992), np.float32(0.9946), np.float32(0.8067)] +2025-10-31 00:10:45.860410: Epoch time: 19.13 s +2025-10-31 00:10:46.854009: +2025-10-31 00:10:46.856055: Epoch 529 +2025-10-31 00:10:46.857772: Current learning rate: 0.00508 +2025-10-31 00:11:07.192637: train_loss -0.9912 +2025-10-31 00:11:07.195739: val_loss -0.8908 +2025-10-31 00:11:07.197453: Pseudo dice [np.float32(0.985), np.float32(0.9918), np.float32(0.9942), np.float32(0.7944)] +2025-10-31 00:11:07.199104: Epoch time: 20.34 s +2025-10-31 00:11:08.234793: +2025-10-31 00:11:08.236887: Epoch 530 +2025-10-31 00:11:08.239481: Current learning rate: 0.00507 +2025-10-31 00:11:29.044619: train_loss -0.9901 +2025-10-31 00:11:29.051625: val_loss -0.8782 +2025-10-31 00:11:29.055124: Pseudo dice [np.float32(0.987), np.float32(0.9922), np.float32(0.9939), np.float32(0.757)] +2025-10-31 00:11:29.056893: Epoch time: 20.81 s +2025-10-31 00:11:30.317242: +2025-10-31 00:11:30.319358: Epoch 531 +2025-10-31 00:11:30.321078: Current learning rate: 0.00506 +2025-10-31 00:11:50.822989: train_loss -0.9902 +2025-10-31 00:11:50.825548: val_loss -0.8941 +2025-10-31 00:11:50.827306: Pseudo dice [np.float32(0.9848), np.float32(0.9913), np.float32(0.9945), np.float32(0.8025)] +2025-10-31 00:11:50.828974: Epoch time: 20.51 s +2025-10-31 00:11:51.981694: +2025-10-31 00:11:51.983769: Epoch 532 +2025-10-31 00:11:51.985963: Current learning rate: 0.00505 +2025-10-31 00:12:12.545654: train_loss -0.9896 +2025-10-31 00:12:12.548532: val_loss -0.8897 +2025-10-31 00:12:12.550384: Pseudo dice [np.float32(0.9833), np.float32(0.9905), np.float32(0.994), np.float32(0.7944)] +2025-10-31 00:12:12.552457: Epoch time: 20.57 s +2025-10-31 00:12:13.827976: +2025-10-31 00:12:13.829829: Epoch 533 +2025-10-31 00:12:13.831603: Current learning rate: 0.00504 +2025-10-31 00:12:33.984697: train_loss -0.9894 +2025-10-31 00:12:33.987019: val_loss -0.8909 +2025-10-31 00:12:33.989485: Pseudo dice [np.float32(0.9852), np.float32(0.9911), np.float32(0.9944), np.float32(0.7931)] +2025-10-31 00:12:33.991779: Epoch time: 20.16 s +2025-10-31 00:12:35.251468: +2025-10-31 00:12:35.253533: Epoch 534 +2025-10-31 00:12:35.255507: Current learning rate: 0.00503 +2025-10-31 00:12:55.515371: train_loss -0.9895 +2025-10-31 00:12:55.517744: val_loss -0.8961 +2025-10-31 00:12:55.520062: Pseudo dice [np.float32(0.9851), np.float32(0.992), np.float32(0.9951), np.float32(0.8058)] +2025-10-31 00:12:55.522360: Epoch time: 20.27 s +2025-10-31 00:12:56.691485: +2025-10-31 00:12:56.693463: Epoch 535 +2025-10-31 00:12:56.695648: Current learning rate: 0.00502 +2025-10-31 00:13:15.823168: train_loss -0.9898 +2025-10-31 00:13:15.826602: val_loss -0.8909 +2025-10-31 00:13:15.829392: Pseudo dice [np.float32(0.9853), np.float32(0.9926), np.float32(0.9947), np.float32(0.7868)] +2025-10-31 00:13:15.831974: Epoch time: 19.13 s +2025-10-31 00:13:17.435307: +2025-10-31 00:13:17.437188: Epoch 536 +2025-10-31 00:13:17.439108: Current learning rate: 0.00501 +2025-10-31 00:13:37.952633: train_loss -0.9905 +2025-10-31 00:13:37.955138: val_loss -0.8912 +2025-10-31 00:13:37.957057: Pseudo dice [np.float32(0.9864), np.float32(0.9932), np.float32(0.9948), np.float32(0.781)] +2025-10-31 00:13:37.958935: Epoch time: 20.52 s +2025-10-31 00:13:38.970303: +2025-10-31 00:13:38.972181: Epoch 537 +2025-10-31 00:13:38.973900: Current learning rate: 0.005 +2025-10-31 00:13:59.695213: train_loss -0.9898 +2025-10-31 00:13:59.697895: val_loss -0.8985 +2025-10-31 00:13:59.699630: Pseudo dice [np.float32(0.9863), np.float32(0.9923), np.float32(0.995), np.float32(0.8067)] +2025-10-31 00:13:59.701331: Epoch time: 20.73 s +2025-10-31 00:14:00.934266: +2025-10-31 00:14:00.936553: Epoch 538 +2025-10-31 00:14:00.938498: Current learning rate: 0.00499 +2025-10-31 00:14:21.599205: train_loss -0.9892 +2025-10-31 00:14:21.603068: val_loss -0.9016 +2025-10-31 00:14:21.604580: Pseudo dice [np.float32(0.9838), np.float32(0.9935), np.float32(0.9953), np.float32(0.8095)] +2025-10-31 00:14:21.607267: Epoch time: 20.67 s +2025-10-31 00:14:22.615598: +2025-10-31 00:14:22.617692: Epoch 539 +2025-10-31 00:14:22.619591: Current learning rate: 0.00498 +2025-10-31 00:14:42.913824: train_loss -0.9899 +2025-10-31 00:14:42.916571: val_loss -0.8943 +2025-10-31 00:14:42.918932: Pseudo dice [np.float32(0.9843), np.float32(0.9925), np.float32(0.9947), np.float32(0.8061)] +2025-10-31 00:14:42.922525: Epoch time: 20.3 s +2025-10-31 00:14:43.927157: +2025-10-31 00:14:43.929407: Epoch 540 +2025-10-31 00:14:43.931472: Current learning rate: 0.00497 +2025-10-31 00:15:03.474529: train_loss -0.9903 +2025-10-31 00:15:03.477228: val_loss -0.8929 +2025-10-31 00:15:03.478760: Pseudo dice [np.float32(0.9849), np.float32(0.9919), np.float32(0.9945), np.float32(0.7947)] +2025-10-31 00:15:03.480279: Epoch time: 19.55 s +2025-10-31 00:15:04.323137: +2025-10-31 00:15:04.325001: Epoch 541 +2025-10-31 00:15:04.326966: Current learning rate: 0.00496 +2025-10-31 00:15:24.944105: train_loss -0.9905 +2025-10-31 00:15:24.947455: val_loss -0.8961 +2025-10-31 00:15:24.949370: Pseudo dice [np.float32(0.9857), np.float32(0.9925), np.float32(0.9946), np.float32(0.796)] +2025-10-31 00:15:24.950894: Epoch time: 20.62 s +2025-10-31 00:15:26.065546: +2025-10-31 00:15:26.067266: Epoch 542 +2025-10-31 00:15:26.069091: Current learning rate: 0.00495 +2025-10-31 00:15:45.721829: train_loss -0.9903 +2025-10-31 00:15:45.723999: val_loss -0.8994 +2025-10-31 00:15:45.726697: Pseudo dice [np.float32(0.9868), np.float32(0.9924), np.float32(0.9943), np.float32(0.8044)] +2025-10-31 00:15:45.729100: Epoch time: 19.66 s +2025-10-31 00:15:46.794400: +2025-10-31 00:15:46.796905: Epoch 543 +2025-10-31 00:15:46.799219: Current learning rate: 0.00494 +2025-10-31 00:16:07.610933: train_loss -0.9905 +2025-10-31 00:16:07.613620: val_loss -0.8905 +2025-10-31 00:16:07.615669: Pseudo dice [np.float32(0.9851), np.float32(0.9923), np.float32(0.9946), np.float32(0.7905)] +2025-10-31 00:16:07.617589: Epoch time: 20.82 s +2025-10-31 00:16:08.840904: +2025-10-31 00:16:08.842968: Epoch 544 +2025-10-31 00:16:08.844617: Current learning rate: 0.00493 +2025-10-31 00:16:29.432347: train_loss -0.9903 +2025-10-31 00:16:29.438316: val_loss -0.8934 +2025-10-31 00:16:29.439955: Pseudo dice [np.float32(0.9863), np.float32(0.9933), np.float32(0.9951), np.float32(0.7918)] +2025-10-31 00:16:29.442057: Epoch time: 20.59 s +2025-10-31 00:16:30.581464: +2025-10-31 00:16:30.583281: Epoch 545 +2025-10-31 00:16:30.584883: Current learning rate: 0.00492 +2025-10-31 00:16:50.946925: train_loss -0.9903 +2025-10-31 00:16:50.949276: val_loss -0.8956 +2025-10-31 00:16:50.952917: Pseudo dice [np.float32(0.9871), np.float32(0.992), np.float32(0.9945), np.float32(0.7993)] +2025-10-31 00:16:50.954598: Epoch time: 20.37 s +2025-10-31 00:16:52.107561: +2025-10-31 00:16:52.109500: Epoch 546 +2025-10-31 00:16:52.111043: Current learning rate: 0.00491 +2025-10-31 00:17:11.620355: train_loss -0.9906 +2025-10-31 00:17:11.623396: val_loss -0.8867 +2025-10-31 00:17:11.625148: Pseudo dice [np.float32(0.9851), np.float32(0.9925), np.float32(0.9946), np.float32(0.7858)] +2025-10-31 00:17:11.626865: Epoch time: 19.51 s +2025-10-31 00:17:12.654733: +2025-10-31 00:17:12.656720: Epoch 547 +2025-10-31 00:17:12.658999: Current learning rate: 0.0049 +2025-10-31 00:17:33.557172: train_loss -0.9905 +2025-10-31 00:17:33.561826: val_loss -0.8881 +2025-10-31 00:17:33.563422: Pseudo dice [np.float32(0.9856), np.float32(0.9921), np.float32(0.9947), np.float32(0.7745)] +2025-10-31 00:17:33.564877: Epoch time: 20.9 s +2025-10-31 00:17:34.753822: +2025-10-31 00:17:34.755639: Epoch 548 +2025-10-31 00:17:34.757264: Current learning rate: 0.00489 +2025-10-31 00:17:55.339989: train_loss -0.99 +2025-10-31 00:17:55.350101: val_loss -0.8913 +2025-10-31 00:17:55.352169: Pseudo dice [np.float32(0.9866), np.float32(0.9925), np.float32(0.9951), np.float32(0.7861)] +2025-10-31 00:17:55.354064: Epoch time: 20.59 s +2025-10-31 00:17:57.592854: +2025-10-31 00:17:57.594708: Epoch 549 +2025-10-31 00:17:57.597406: Current learning rate: 0.00488 +2025-10-31 00:18:17.818939: train_loss -0.9909 +2025-10-31 00:18:17.821395: val_loss -0.8932 +2025-10-31 00:18:17.823203: Pseudo dice [np.float32(0.985), np.float32(0.9926), np.float32(0.9949), np.float32(0.795)] +2025-10-31 00:18:17.824902: Epoch time: 20.23 s +2025-10-31 00:18:20.246181: +2025-10-31 00:18:20.248187: Epoch 550 +2025-10-31 00:18:20.250119: Current learning rate: 0.00487 +2025-10-31 00:18:40.842735: train_loss -0.9903 +2025-10-31 00:18:40.845656: val_loss -0.8951 +2025-10-31 00:18:40.847261: Pseudo dice [np.float32(0.9869), np.float32(0.9928), np.float32(0.9949), np.float32(0.7971)] +2025-10-31 00:18:40.848969: Epoch time: 20.6 s +2025-10-31 00:18:41.923788: +2025-10-31 00:18:41.926221: Epoch 551 +2025-10-31 00:18:41.928113: Current learning rate: 0.00486 +2025-10-31 00:19:02.446535: train_loss -0.9905 +2025-10-31 00:19:02.449378: val_loss -0.8982 +2025-10-31 00:19:02.451402: Pseudo dice [np.float32(0.9864), np.float32(0.9934), np.float32(0.9947), np.float32(0.8013)] +2025-10-31 00:19:02.452929: Epoch time: 20.52 s +2025-10-31 00:19:03.459895: +2025-10-31 00:19:03.462103: Epoch 552 +2025-10-31 00:19:03.463962: Current learning rate: 0.00485 +2025-10-31 00:19:23.610424: train_loss -0.9908 +2025-10-31 00:19:23.612509: val_loss -0.8989 +2025-10-31 00:19:23.614202: Pseudo dice [np.float32(0.9847), np.float32(0.9932), np.float32(0.9953), np.float32(0.8036)] +2025-10-31 00:19:23.615818: Epoch time: 20.15 s +2025-10-31 00:19:24.558148: +2025-10-31 00:19:24.560099: Epoch 553 +2025-10-31 00:19:24.562308: Current learning rate: 0.00484 +2025-10-31 00:19:45.029370: train_loss -0.9907 +2025-10-31 00:19:45.032665: val_loss -0.8978 +2025-10-31 00:19:45.034400: Pseudo dice [np.float32(0.986), np.float32(0.9919), np.float32(0.9945), np.float32(0.8087)] +2025-10-31 00:19:45.036210: Epoch time: 20.47 s +2025-10-31 00:19:46.106336: +2025-10-31 00:19:46.111872: Epoch 554 +2025-10-31 00:19:46.115454: Current learning rate: 0.00484 +2025-10-31 00:20:06.848421: train_loss -0.9896 +2025-10-31 00:20:06.850478: val_loss -0.8958 +2025-10-31 00:20:06.852876: Pseudo dice [np.float32(0.9853), np.float32(0.9926), np.float32(0.9948), np.float32(0.8025)] +2025-10-31 00:20:06.854627: Epoch time: 20.74 s +2025-10-31 00:20:07.879291: +2025-10-31 00:20:07.881307: Epoch 555 +2025-10-31 00:20:07.883329: Current learning rate: 0.00483 +2025-10-31 00:20:27.727703: train_loss -0.9901 +2025-10-31 00:20:27.730039: val_loss -0.8975 +2025-10-31 00:20:27.731920: Pseudo dice [np.float32(0.9858), np.float32(0.9926), np.float32(0.9948), np.float32(0.7995)] +2025-10-31 00:20:27.733634: Epoch time: 19.85 s +2025-10-31 00:20:28.945207: +2025-10-31 00:20:28.947762: Epoch 556 +2025-10-31 00:20:28.950140: Current learning rate: 0.00482 +2025-10-31 00:20:49.468432: train_loss -0.9904 +2025-10-31 00:20:49.471009: val_loss -0.8933 +2025-10-31 00:20:49.472678: Pseudo dice [np.float32(0.9865), np.float32(0.9929), np.float32(0.9942), np.float32(0.7913)] +2025-10-31 00:20:49.474885: Epoch time: 20.53 s +2025-10-31 00:20:50.446137: +2025-10-31 00:20:50.447939: Epoch 557 +2025-10-31 00:20:50.449491: Current learning rate: 0.00481 +2025-10-31 00:21:10.961488: train_loss -0.9895 +2025-10-31 00:21:10.963742: val_loss -0.8962 +2025-10-31 00:21:10.965473: Pseudo dice [np.float32(0.9856), np.float32(0.9921), np.float32(0.9946), np.float32(0.802)] +2025-10-31 00:21:10.967152: Epoch time: 20.52 s +2025-10-31 00:21:12.067115: +2025-10-31 00:21:12.069180: Epoch 558 +2025-10-31 00:21:12.070940: Current learning rate: 0.0048 +2025-10-31 00:21:32.422951: train_loss -0.9903 +2025-10-31 00:21:32.425498: val_loss -0.897 +2025-10-31 00:21:32.427496: Pseudo dice [np.float32(0.9865), np.float32(0.9928), np.float32(0.9949), np.float32(0.8009)] +2025-10-31 00:21:32.429529: Epoch time: 20.36 s +2025-10-31 00:21:33.647902: +2025-10-31 00:21:33.650143: Epoch 559 +2025-10-31 00:21:33.651898: Current learning rate: 0.00479 +2025-10-31 00:21:53.395118: train_loss -0.9905 +2025-10-31 00:21:53.398436: val_loss -0.8929 +2025-10-31 00:21:53.400529: Pseudo dice [np.float32(0.9856), np.float32(0.9922), np.float32(0.9949), np.float32(0.7967)] +2025-10-31 00:21:53.402542: Epoch time: 19.75 s +2025-10-31 00:21:54.436172: +2025-10-31 00:21:54.437994: Epoch 560 +2025-10-31 00:21:54.440243: Current learning rate: 0.00478 +2025-10-31 00:22:15.256812: train_loss -0.9908 +2025-10-31 00:22:15.259038: val_loss -0.9056 +2025-10-31 00:22:15.260602: Pseudo dice [np.float32(0.9865), np.float32(0.9932), np.float32(0.9954), np.float32(0.8191)] +2025-10-31 00:22:15.262083: Epoch time: 20.82 s +2025-10-31 00:22:17.086153: +2025-10-31 00:22:17.088002: Epoch 561 +2025-10-31 00:22:17.089781: Current learning rate: 0.00477 +2025-10-31 00:22:37.439789: train_loss -0.9909 +2025-10-31 00:22:37.442147: val_loss -0.8917 +2025-10-31 00:22:37.443843: Pseudo dice [np.float32(0.9838), np.float32(0.9921), np.float32(0.995), np.float32(0.7993)] +2025-10-31 00:22:37.445510: Epoch time: 20.35 s +2025-10-31 00:22:38.646830: +2025-10-31 00:22:38.648838: Epoch 562 +2025-10-31 00:22:38.650880: Current learning rate: 0.00476 +2025-10-31 00:22:58.215654: train_loss -0.9914 +2025-10-31 00:22:58.218611: val_loss -0.8905 +2025-10-31 00:22:58.220475: Pseudo dice [np.float32(0.9849), np.float32(0.9917), np.float32(0.9946), np.float32(0.7922)] +2025-10-31 00:22:58.222217: Epoch time: 19.57 s +2025-10-31 00:22:59.216609: +2025-10-31 00:22:59.218616: Epoch 563 +2025-10-31 00:22:59.221357: Current learning rate: 0.00475 +2025-10-31 00:23:19.791463: train_loss -0.9915 +2025-10-31 00:23:19.794820: val_loss -0.9016 +2025-10-31 00:23:19.796942: Pseudo dice [np.float32(0.9861), np.float32(0.9927), np.float32(0.995), np.float32(0.8106)] +2025-10-31 00:23:19.798811: Epoch time: 20.58 s +2025-10-31 00:23:20.901573: +2025-10-31 00:23:20.903692: Epoch 564 +2025-10-31 00:23:20.905542: Current learning rate: 0.00474 +2025-10-31 00:23:41.639056: train_loss -0.9902 +2025-10-31 00:23:41.643163: val_loss -0.8904 +2025-10-31 00:23:41.645473: Pseudo dice [np.float32(0.9845), np.float32(0.9913), np.float32(0.9942), np.float32(0.7888)] +2025-10-31 00:23:41.647291: Epoch time: 20.74 s +2025-10-31 00:23:42.927714: +2025-10-31 00:23:42.929819: Epoch 565 +2025-10-31 00:23:42.931780: Current learning rate: 0.00473 +2025-10-31 00:24:02.105905: train_loss -0.9905 +2025-10-31 00:24:02.108766: val_loss -0.8949 +2025-10-31 00:24:02.110449: Pseudo dice [np.float32(0.9838), np.float32(0.9905), np.float32(0.9944), np.float32(0.8056)] +2025-10-31 00:24:02.112143: Epoch time: 19.18 s +2025-10-31 00:24:03.238067: +2025-10-31 00:24:03.240100: Epoch 566 +2025-10-31 00:24:03.241955: Current learning rate: 0.00472 +2025-10-31 00:24:23.693801: train_loss -0.9898 +2025-10-31 00:24:23.696027: val_loss -0.8973 +2025-10-31 00:24:23.697997: Pseudo dice [np.float32(0.984), np.float32(0.9933), np.float32(0.9952), np.float32(0.806)] +2025-10-31 00:24:23.699831: Epoch time: 20.46 s +2025-10-31 00:24:24.711700: +2025-10-31 00:24:24.714235: Epoch 567 +2025-10-31 00:24:24.716184: Current learning rate: 0.00471 +2025-10-31 00:24:45.562128: train_loss -0.9905 +2025-10-31 00:24:45.564050: val_loss -0.8906 +2025-10-31 00:24:45.565491: Pseudo dice [np.float32(0.9862), np.float32(0.9933), np.float32(0.9946), np.float32(0.7906)] +2025-10-31 00:24:45.567075: Epoch time: 20.85 s +2025-10-31 00:24:46.859450: +2025-10-31 00:24:46.864808: Epoch 568 +2025-10-31 00:24:46.866807: Current learning rate: 0.0047 +2025-10-31 00:25:07.594573: train_loss -0.9902 +2025-10-31 00:25:07.601593: val_loss -0.8981 +2025-10-31 00:25:07.603328: Pseudo dice [np.float32(0.9857), np.float32(0.9925), np.float32(0.9953), np.float32(0.7985)] +2025-10-31 00:25:07.604846: Epoch time: 20.74 s +2025-10-31 00:25:08.665817: +2025-10-31 00:25:08.667636: Epoch 569 +2025-10-31 00:25:08.669347: Current learning rate: 0.00469 +2025-10-31 00:25:28.287853: train_loss -0.9909 +2025-10-31 00:25:28.290443: val_loss -0.896 +2025-10-31 00:25:28.291832: Pseudo dice [np.float32(0.985), np.float32(0.9923), np.float32(0.9949), np.float32(0.8065)] +2025-10-31 00:25:28.293316: Epoch time: 19.62 s +2025-10-31 00:25:29.621799: +2025-10-31 00:25:29.623657: Epoch 570 +2025-10-31 00:25:29.625348: Current learning rate: 0.00468 +2025-10-31 00:25:50.131502: train_loss -0.9905 +2025-10-31 00:25:50.135398: val_loss -0.8904 +2025-10-31 00:25:50.138900: Pseudo dice [np.float32(0.9855), np.float32(0.9921), np.float32(0.9946), np.float32(0.7873)] +2025-10-31 00:25:50.142100: Epoch time: 20.51 s +2025-10-31 00:25:51.225921: +2025-10-31 00:25:51.227646: Epoch 571 +2025-10-31 00:25:51.229263: Current learning rate: 0.00467 +2025-10-31 00:26:11.389223: train_loss -0.9911 +2025-10-31 00:26:11.392127: val_loss -0.8876 +2025-10-31 00:26:11.394392: Pseudo dice [np.float32(0.9863), np.float32(0.9927), np.float32(0.9944), np.float32(0.776)] +2025-10-31 00:26:11.396112: Epoch time: 20.16 s +2025-10-31 00:26:12.523154: +2025-10-31 00:26:12.525071: Epoch 572 +2025-10-31 00:26:12.526860: Current learning rate: 0.00466 +2025-10-31 00:26:32.152589: train_loss -0.9897 +2025-10-31 00:26:32.155704: val_loss -0.896 +2025-10-31 00:26:32.157391: Pseudo dice [np.float32(0.9849), np.float32(0.9924), np.float32(0.9948), np.float32(0.8006)] +2025-10-31 00:26:32.158910: Epoch time: 19.63 s +2025-10-31 00:26:33.795692: +2025-10-31 00:26:33.797773: Epoch 573 +2025-10-31 00:26:33.799609: Current learning rate: 0.00465 +2025-10-31 00:26:54.351938: train_loss -0.9907 +2025-10-31 00:26:54.354340: val_loss -0.8928 +2025-10-31 00:26:54.356036: Pseudo dice [np.float32(0.984), np.float32(0.992), np.float32(0.9947), np.float32(0.7977)] +2025-10-31 00:26:54.357761: Epoch time: 20.56 s +2025-10-31 00:26:55.616405: +2025-10-31 00:26:55.618972: Epoch 574 +2025-10-31 00:26:55.620852: Current learning rate: 0.00464 +2025-10-31 00:27:16.021371: train_loss -0.9899 +2025-10-31 00:27:16.024389: val_loss -0.8908 +2025-10-31 00:27:16.026076: Pseudo dice [np.float32(0.9858), np.float32(0.9932), np.float32(0.9944), np.float32(0.7892)] +2025-10-31 00:27:16.027532: Epoch time: 20.41 s +2025-10-31 00:27:17.099981: +2025-10-31 00:27:17.102261: Epoch 575 +2025-10-31 00:27:17.109283: Current learning rate: 0.00463 +2025-10-31 00:27:37.438394: train_loss -0.99 +2025-10-31 00:27:37.440603: val_loss -0.8994 +2025-10-31 00:27:37.442368: Pseudo dice [np.float32(0.9847), np.float32(0.9922), np.float32(0.9948), np.float32(0.8096)] +2025-10-31 00:27:37.443823: Epoch time: 20.34 s +2025-10-31 00:27:38.467370: +2025-10-31 00:27:38.469328: Epoch 576 +2025-10-31 00:27:38.470985: Current learning rate: 0.00462 +2025-10-31 00:27:58.402452: train_loss -0.9903 +2025-10-31 00:27:58.404844: val_loss -0.899 +2025-10-31 00:27:58.406435: Pseudo dice [np.float32(0.9859), np.float32(0.9928), np.float32(0.9952), np.float32(0.8092)] +2025-10-31 00:27:58.408055: Epoch time: 19.94 s +2025-10-31 00:27:59.421719: +2025-10-31 00:27:59.423680: Epoch 577 +2025-10-31 00:27:59.425233: Current learning rate: 0.00461 +2025-10-31 00:28:20.140251: train_loss -0.9906 +2025-10-31 00:28:20.143363: val_loss -0.8991 +2025-10-31 00:28:20.145092: Pseudo dice [np.float32(0.9866), np.float32(0.9926), np.float32(0.9947), np.float32(0.8017)] +2025-10-31 00:28:20.149893: Epoch time: 20.72 s +2025-10-31 00:28:21.403913: +2025-10-31 00:28:21.406106: Epoch 578 +2025-10-31 00:28:21.408105: Current learning rate: 0.0046 +2025-10-31 00:28:41.235598: train_loss -0.9904 +2025-10-31 00:28:41.238038: val_loss -0.8982 +2025-10-31 00:28:41.240554: Pseudo dice [np.float32(0.9864), np.float32(0.9929), np.float32(0.9951), np.float32(0.8078)] +2025-10-31 00:28:41.242899: Epoch time: 19.83 s +2025-10-31 00:28:42.469846: +2025-10-31 00:28:42.471806: Epoch 579 +2025-10-31 00:28:42.473605: Current learning rate: 0.00459 +2025-10-31 00:29:02.976290: train_loss -0.9908 +2025-10-31 00:29:02.978588: val_loss -0.8926 +2025-10-31 00:29:02.980218: Pseudo dice [np.float32(0.9874), np.float32(0.9928), np.float32(0.9947), np.float32(0.7922)] +2025-10-31 00:29:02.982012: Epoch time: 20.51 s +2025-10-31 00:29:04.221889: +2025-10-31 00:29:04.223866: Epoch 580 +2025-10-31 00:29:04.226582: Current learning rate: 0.00458 +2025-10-31 00:29:25.027720: train_loss -0.9907 +2025-10-31 00:29:25.030613: val_loss -0.8918 +2025-10-31 00:29:25.032319: Pseudo dice [np.float32(0.987), np.float32(0.9937), np.float32(0.9949), np.float32(0.7863)] +2025-10-31 00:29:25.034324: Epoch time: 20.81 s +2025-10-31 00:29:26.116005: +2025-10-31 00:29:26.118070: Epoch 581 +2025-10-31 00:29:26.119697: Current learning rate: 0.00457 +2025-10-31 00:29:46.806471: train_loss -0.9907 +2025-10-31 00:29:46.809108: val_loss -0.8964 +2025-10-31 00:29:46.810790: Pseudo dice [np.float32(0.9873), np.float32(0.9935), np.float32(0.995), np.float32(0.7971)] +2025-10-31 00:29:46.812379: Epoch time: 20.69 s +2025-10-31 00:29:48.050990: +2025-10-31 00:29:48.053121: Epoch 582 +2025-10-31 00:29:48.055007: Current learning rate: 0.00456 +2025-10-31 00:30:08.267935: train_loss -0.9909 +2025-10-31 00:30:08.270457: val_loss -0.8999 +2025-10-31 00:30:08.272408: Pseudo dice [np.float32(0.9871), np.float32(0.9935), np.float32(0.9949), np.float32(0.8035)] +2025-10-31 00:30:08.274297: Epoch time: 20.22 s +2025-10-31 00:30:09.482989: +2025-10-31 00:30:09.484825: Epoch 583 +2025-10-31 00:30:09.486888: Current learning rate: 0.00455 +2025-10-31 00:30:29.311062: train_loss -0.9911 +2025-10-31 00:30:29.314100: val_loss -0.8971 +2025-10-31 00:30:29.315939: Pseudo dice [np.float32(0.9862), np.float32(0.9932), np.float32(0.995), np.float32(0.7969)] +2025-10-31 00:30:29.317562: Epoch time: 19.83 s +2025-10-31 00:30:30.364786: +2025-10-31 00:30:30.366853: Epoch 584 +2025-10-31 00:30:30.368857: Current learning rate: 0.00454 +2025-10-31 00:30:51.066870: train_loss -0.9907 +2025-10-31 00:30:51.071697: val_loss -0.8898 +2025-10-31 00:30:51.074827: Pseudo dice [np.float32(0.9843), np.float32(0.9918), np.float32(0.9947), np.float32(0.7903)] +2025-10-31 00:30:51.077937: Epoch time: 20.7 s +2025-10-31 00:30:52.567902: +2025-10-31 00:30:52.569894: Epoch 585 +2025-10-31 00:30:52.571467: Current learning rate: 0.00453 +2025-10-31 00:31:12.414055: train_loss -0.991 +2025-10-31 00:31:12.417037: val_loss -0.8846 +2025-10-31 00:31:12.418832: Pseudo dice [np.float32(0.9863), np.float32(0.9925), np.float32(0.9943), np.float32(0.7843)] +2025-10-31 00:31:12.420382: Epoch time: 19.85 s +2025-10-31 00:31:13.754284: +2025-10-31 00:31:13.756395: Epoch 586 +2025-10-31 00:31:13.758045: Current learning rate: 0.00452 +2025-10-31 00:31:34.424378: train_loss -0.9914 +2025-10-31 00:31:34.427236: val_loss -0.8868 +2025-10-31 00:31:34.428795: Pseudo dice [np.float32(0.9857), np.float32(0.9921), np.float32(0.9944), np.float32(0.7837)] +2025-10-31 00:31:34.430342: Epoch time: 20.67 s +2025-10-31 00:31:35.650424: +2025-10-31 00:31:35.652184: Epoch 587 +2025-10-31 00:31:35.653736: Current learning rate: 0.00451 +2025-10-31 00:31:56.294941: train_loss -0.991 +2025-10-31 00:31:56.297705: val_loss -0.8839 +2025-10-31 00:31:56.300010: Pseudo dice [np.float32(0.9859), np.float32(0.9927), np.float32(0.9946), np.float32(0.7669)] +2025-10-31 00:31:56.301913: Epoch time: 20.65 s +2025-10-31 00:31:57.407135: +2025-10-31 00:31:57.409488: Epoch 588 +2025-10-31 00:31:57.411140: Current learning rate: 0.0045 +2025-10-31 00:32:18.038641: train_loss -0.9907 +2025-10-31 00:32:18.040809: val_loss -0.8914 +2025-10-31 00:32:18.042571: Pseudo dice [np.float32(0.9844), np.float32(0.9929), np.float32(0.9947), np.float32(0.7937)] +2025-10-31 00:32:18.044234: Epoch time: 20.63 s +2025-10-31 00:32:19.355501: +2025-10-31 00:32:19.357561: Epoch 589 +2025-10-31 00:32:19.359239: Current learning rate: 0.00449 +2025-10-31 00:32:38.546030: train_loss -0.9894 +2025-10-31 00:32:38.549705: val_loss -0.8849 +2025-10-31 00:32:38.552058: Pseudo dice [np.float32(0.9852), np.float32(0.9933), np.float32(0.995), np.float32(0.7726)] +2025-10-31 00:32:38.554536: Epoch time: 19.19 s +2025-10-31 00:32:39.728615: +2025-10-31 00:32:39.730595: Epoch 590 +2025-10-31 00:32:39.732378: Current learning rate: 0.00448 +2025-10-31 00:33:00.289696: train_loss -0.9906 +2025-10-31 00:33:00.291964: val_loss -0.8924 +2025-10-31 00:33:00.293643: Pseudo dice [np.float32(0.9846), np.float32(0.9923), np.float32(0.9946), np.float32(0.7886)] +2025-10-31 00:33:00.295379: Epoch time: 20.56 s +2025-10-31 00:33:01.489613: +2025-10-31 00:33:01.491670: Epoch 591 +2025-10-31 00:33:01.493443: Current learning rate: 0.00447 +2025-10-31 00:33:21.245970: train_loss -0.9911 +2025-10-31 00:33:21.248222: val_loss -0.8941 +2025-10-31 00:33:21.249648: Pseudo dice [np.float32(0.9861), np.float32(0.9926), np.float32(0.9951), np.float32(0.7981)] +2025-10-31 00:33:21.251664: Epoch time: 19.76 s +2025-10-31 00:33:22.274805: +2025-10-31 00:33:22.276941: Epoch 592 +2025-10-31 00:33:22.280700: Current learning rate: 0.00446 +2025-10-31 00:33:42.696917: train_loss -0.9911 +2025-10-31 00:33:42.700422: val_loss -0.8926 +2025-10-31 00:33:42.702215: Pseudo dice [np.float32(0.9854), np.float32(0.9935), np.float32(0.995), np.float32(0.7985)] +2025-10-31 00:33:42.703964: Epoch time: 20.42 s +2025-10-31 00:33:43.915930: +2025-10-31 00:33:43.918260: Epoch 593 +2025-10-31 00:33:43.921033: Current learning rate: 0.00445 +2025-10-31 00:34:04.532418: train_loss -0.9907 +2025-10-31 00:34:04.535112: val_loss -0.8878 +2025-10-31 00:34:04.537442: Pseudo dice [np.float32(0.985), np.float32(0.9922), np.float32(0.9948), np.float32(0.7892)] +2025-10-31 00:34:04.539176: Epoch time: 20.62 s +2025-10-31 00:34:05.569700: +2025-10-31 00:34:05.572322: Epoch 594 +2025-10-31 00:34:05.575334: Current learning rate: 0.00444 +2025-10-31 00:34:26.056539: train_loss -0.9885 +2025-10-31 00:34:26.059257: val_loss -0.892 +2025-10-31 00:34:26.061829: Pseudo dice [np.float32(0.9837), np.float32(0.9912), np.float32(0.9943), np.float32(0.7913)] +2025-10-31 00:34:26.063710: Epoch time: 20.49 s +2025-10-31 00:34:27.078937: +2025-10-31 00:34:27.081389: Epoch 595 +2025-10-31 00:34:27.083173: Current learning rate: 0.00443 +2025-10-31 00:34:47.814801: train_loss -0.9907 +2025-10-31 00:34:47.817488: val_loss -0.8908 +2025-10-31 00:34:47.819130: Pseudo dice [np.float32(0.9863), np.float32(0.9922), np.float32(0.9943), np.float32(0.7855)] +2025-10-31 00:34:47.820754: Epoch time: 20.74 s +2025-10-31 00:34:49.028821: +2025-10-31 00:34:49.030637: Epoch 596 +2025-10-31 00:34:49.032277: Current learning rate: 0.00442 +2025-10-31 00:35:09.080086: train_loss -0.9902 +2025-10-31 00:35:09.082360: val_loss -0.8931 +2025-10-31 00:35:09.084278: Pseudo dice [np.float32(0.9849), np.float32(0.9915), np.float32(0.9948), np.float32(0.7955)] +2025-10-31 00:35:09.086057: Epoch time: 20.05 s +2025-10-31 00:35:10.643407: +2025-10-31 00:35:10.645794: Epoch 597 +2025-10-31 00:35:10.647591: Current learning rate: 0.00441 +2025-10-31 00:35:30.488837: train_loss -0.9892 +2025-10-31 00:35:30.491272: val_loss -0.8976 +2025-10-31 00:35:30.493630: Pseudo dice [np.float32(0.9836), np.float32(0.9912), np.float32(0.995), np.float32(0.8038)] +2025-10-31 00:35:30.495646: Epoch time: 19.85 s +2025-10-31 00:35:31.541962: +2025-10-31 00:35:31.543986: Epoch 598 +2025-10-31 00:35:31.545616: Current learning rate: 0.0044 +2025-10-31 00:35:52.119456: train_loss -0.989 +2025-10-31 00:35:52.121991: val_loss -0.898 +2025-10-31 00:35:52.123611: Pseudo dice [np.float32(0.9866), np.float32(0.9925), np.float32(0.9944), np.float32(0.7999)] +2025-10-31 00:35:52.125223: Epoch time: 20.58 s +2025-10-31 00:35:53.140682: +2025-10-31 00:35:53.142720: Epoch 599 +2025-10-31 00:35:53.144300: Current learning rate: 0.00439 +2025-10-31 00:36:13.752930: train_loss -0.9903 +2025-10-31 00:36:13.772076: val_loss -0.8962 +2025-10-31 00:36:13.773901: Pseudo dice [np.float32(0.9839), np.float32(0.9915), np.float32(0.9949), np.float32(0.8047)] +2025-10-31 00:36:13.775711: Epoch time: 20.61 s +2025-10-31 00:36:16.199184: +2025-10-31 00:36:16.201354: Epoch 600 +2025-10-31 00:36:16.203246: Current learning rate: 0.00438 +2025-10-31 00:36:36.912469: train_loss -0.9909 +2025-10-31 00:36:36.914573: val_loss -0.8991 +2025-10-31 00:36:36.916304: Pseudo dice [np.float32(0.9852), np.float32(0.9927), np.float32(0.995), np.float32(0.81)] +2025-10-31 00:36:36.918145: Epoch time: 20.72 s +2025-10-31 00:36:37.955421: +2025-10-31 00:36:37.957208: Epoch 601 +2025-10-31 00:36:37.958874: Current learning rate: 0.00437 +2025-10-31 00:36:58.676800: train_loss -0.9906 +2025-10-31 00:36:58.679575: val_loss -0.8941 +2025-10-31 00:36:58.681188: Pseudo dice [np.float32(0.9838), np.float32(0.9916), np.float32(0.9946), np.float32(0.8027)] +2025-10-31 00:36:58.682902: Epoch time: 20.72 s +2025-10-31 00:36:59.872637: +2025-10-31 00:36:59.875151: Epoch 602 +2025-10-31 00:36:59.876970: Current learning rate: 0.00436 +2025-10-31 00:37:20.403458: train_loss -0.9909 +2025-10-31 00:37:20.405915: val_loss -0.8961 +2025-10-31 00:37:20.408411: Pseudo dice [np.float32(0.9861), np.float32(0.9931), np.float32(0.9948), np.float32(0.8047)] +2025-10-31 00:37:20.410464: Epoch time: 20.53 s +2025-10-31 00:37:21.632246: +2025-10-31 00:37:21.634573: Epoch 603 +2025-10-31 00:37:21.636536: Current learning rate: 0.00435 +2025-10-31 00:37:41.252633: train_loss -0.9911 +2025-10-31 00:37:41.254528: val_loss -0.8958 +2025-10-31 00:37:41.256255: Pseudo dice [np.float32(0.9861), np.float32(0.9928), np.float32(0.995), np.float32(0.7869)] +2025-10-31 00:37:41.257820: Epoch time: 19.62 s +2025-10-31 00:37:42.278415: +2025-10-31 00:37:42.280308: Epoch 604 +2025-10-31 00:37:42.282044: Current learning rate: 0.00434 +2025-10-31 00:38:02.469563: train_loss -0.9909 +2025-10-31 00:38:02.473711: val_loss -0.8913 +2025-10-31 00:38:02.475778: Pseudo dice [np.float32(0.9858), np.float32(0.9926), np.float32(0.9948), np.float32(0.7896)] +2025-10-31 00:38:02.478080: Epoch time: 20.19 s +2025-10-31 00:38:03.393693: +2025-10-31 00:38:03.395467: Epoch 605 +2025-10-31 00:38:03.397063: Current learning rate: 0.00433 +2025-10-31 00:38:24.007332: train_loss -0.9909 +2025-10-31 00:38:24.009351: val_loss -0.8957 +2025-10-31 00:38:24.011272: Pseudo dice [np.float32(0.9842), np.float32(0.9923), np.float32(0.9949), np.float32(0.8014)] +2025-10-31 00:38:24.012898: Epoch time: 20.61 s +2025-10-31 00:38:25.060625: +2025-10-31 00:38:25.062777: Epoch 606 +2025-10-31 00:38:25.064534: Current learning rate: 0.00432 +2025-10-31 00:38:45.733844: train_loss -0.9905 +2025-10-31 00:38:45.736505: val_loss -0.8898 +2025-10-31 00:38:45.738145: Pseudo dice [np.float32(0.9862), np.float32(0.9918), np.float32(0.9942), np.float32(0.7929)] +2025-10-31 00:38:45.739850: Epoch time: 20.67 s +2025-10-31 00:38:46.951345: +2025-10-31 00:38:46.953460: Epoch 607 +2025-10-31 00:38:46.955394: Current learning rate: 0.00431 +2025-10-31 00:39:07.795410: train_loss -0.9908 +2025-10-31 00:39:07.798875: val_loss -0.8933 +2025-10-31 00:39:07.800426: Pseudo dice [np.float32(0.9864), np.float32(0.9927), np.float32(0.9948), np.float32(0.796)] +2025-10-31 00:39:07.802100: Epoch time: 20.85 s +2025-10-31 00:39:09.003548: +2025-10-31 00:39:09.005297: Epoch 608 +2025-10-31 00:39:09.006803: Current learning rate: 0.0043 +2025-10-31 00:39:29.779101: train_loss -0.9912 +2025-10-31 00:39:29.782689: val_loss -0.8934 +2025-10-31 00:39:29.784198: Pseudo dice [np.float32(0.9853), np.float32(0.9921), np.float32(0.9945), np.float32(0.7917)] +2025-10-31 00:39:29.786478: Epoch time: 20.78 s +2025-10-31 00:39:31.284307: +2025-10-31 00:39:31.286334: Epoch 609 +2025-10-31 00:39:31.287930: Current learning rate: 0.00429 +2025-10-31 00:39:51.765628: train_loss -0.9907 +2025-10-31 00:39:51.768076: val_loss -0.9027 +2025-10-31 00:39:51.769626: Pseudo dice [np.float32(0.9847), np.float32(0.9931), np.float32(0.9952), np.float32(0.8132)] +2025-10-31 00:39:51.771164: Epoch time: 20.48 s +2025-10-31 00:39:52.799787: +2025-10-31 00:39:52.802005: Epoch 610 +2025-10-31 00:39:52.804051: Current learning rate: 0.00429 +2025-10-31 00:40:11.412365: train_loss -0.9909 +2025-10-31 00:40:11.418452: val_loss -0.9002 +2025-10-31 00:40:11.420361: Pseudo dice [np.float32(0.9855), np.float32(0.9927), np.float32(0.9946), np.float32(0.8028)] +2025-10-31 00:40:11.422329: Epoch time: 18.61 s +2025-10-31 00:40:12.724496: +2025-10-31 00:40:12.726423: Epoch 611 +2025-10-31 00:40:12.728045: Current learning rate: 0.00428 +2025-10-31 00:40:33.346934: train_loss -0.9915 +2025-10-31 00:40:33.351225: val_loss -0.8921 +2025-10-31 00:40:33.352836: Pseudo dice [np.float32(0.9863), np.float32(0.9937), np.float32(0.9948), np.float32(0.7865)] +2025-10-31 00:40:33.354286: Epoch time: 20.62 s +2025-10-31 00:40:34.381192: +2025-10-31 00:40:34.382856: Epoch 612 +2025-10-31 00:40:34.384801: Current learning rate: 0.00427 +2025-10-31 00:40:54.957626: train_loss -0.9913 +2025-10-31 00:40:54.960122: val_loss -0.8911 +2025-10-31 00:40:54.961767: Pseudo dice [np.float32(0.9854), np.float32(0.9922), np.float32(0.9945), np.float32(0.7889)] +2025-10-31 00:40:54.964336: Epoch time: 20.58 s +2025-10-31 00:40:56.045884: +2025-10-31 00:40:56.047802: Epoch 613 +2025-10-31 00:40:56.049484: Current learning rate: 0.00426 +2025-10-31 00:41:16.731392: train_loss -0.991 +2025-10-31 00:41:16.734338: val_loss -0.8987 +2025-10-31 00:41:16.736117: Pseudo dice [np.float32(0.9854), np.float32(0.9925), np.float32(0.9948), np.float32(0.8045)] +2025-10-31 00:41:16.737746: Epoch time: 20.69 s +2025-10-31 00:41:17.959097: +2025-10-31 00:41:17.961198: Epoch 614 +2025-10-31 00:41:17.962868: Current learning rate: 0.00425 +2025-10-31 00:41:38.714460: train_loss -0.9918 +2025-10-31 00:41:38.716959: val_loss -0.8985 +2025-10-31 00:41:38.718788: Pseudo dice [np.float32(0.9861), np.float32(0.9927), np.float32(0.9946), np.float32(0.8046)] +2025-10-31 00:41:38.721179: Epoch time: 20.76 s +2025-10-31 00:41:39.870325: +2025-10-31 00:41:39.872199: Epoch 615 +2025-10-31 00:41:39.874352: Current learning rate: 0.00424 +2025-10-31 00:42:00.481850: train_loss -0.9903 +2025-10-31 00:42:00.485124: val_loss -0.8908 +2025-10-31 00:42:00.487024: Pseudo dice [np.float32(0.9863), np.float32(0.9929), np.float32(0.9951), np.float32(0.7796)] +2025-10-31 00:42:00.488798: Epoch time: 20.61 s +2025-10-31 00:42:01.510974: +2025-10-31 00:42:01.513325: Epoch 616 +2025-10-31 00:42:01.515106: Current learning rate: 0.00423 +2025-10-31 00:42:21.044459: train_loss -0.9902 +2025-10-31 00:42:21.048174: val_loss -0.8963 +2025-10-31 00:42:21.050356: Pseudo dice [np.float32(0.9864), np.float32(0.9935), np.float32(0.9946), np.float32(0.7918)] +2025-10-31 00:42:21.053144: Epoch time: 19.53 s +2025-10-31 00:42:22.459470: +2025-10-31 00:42:22.461676: Epoch 617 +2025-10-31 00:42:22.463734: Current learning rate: 0.00422 +2025-10-31 00:42:43.104266: train_loss -0.9909 +2025-10-31 00:42:43.106387: val_loss -0.8883 +2025-10-31 00:42:43.108577: Pseudo dice [np.float32(0.9859), np.float32(0.9928), np.float32(0.9947), np.float32(0.7836)] +2025-10-31 00:42:43.110740: Epoch time: 20.65 s +2025-10-31 00:42:44.214617: +2025-10-31 00:42:44.216606: Epoch 618 +2025-10-31 00:42:44.218700: Current learning rate: 0.00421 +2025-10-31 00:43:04.925232: train_loss -0.9912 +2025-10-31 00:43:04.928233: val_loss -0.8921 +2025-10-31 00:43:04.930151: Pseudo dice [np.float32(0.9851), np.float32(0.9926), np.float32(0.9946), np.float32(0.7895)] +2025-10-31 00:43:04.931704: Epoch time: 20.71 s +2025-10-31 00:43:06.119720: +2025-10-31 00:43:06.121739: Epoch 619 +2025-10-31 00:43:06.123588: Current learning rate: 0.0042 +2025-10-31 00:43:26.897483: train_loss -0.9904 +2025-10-31 00:43:26.902050: val_loss -0.8955 +2025-10-31 00:43:26.903904: Pseudo dice [np.float32(0.9849), np.float32(0.9926), np.float32(0.9946), np.float32(0.8009)] +2025-10-31 00:43:26.905763: Epoch time: 20.78 s +2025-10-31 00:43:28.197904: +2025-10-31 00:43:28.200024: Epoch 620 +2025-10-31 00:43:28.202059: Current learning rate: 0.00419 +2025-10-31 00:43:48.998150: train_loss -0.9906 +2025-10-31 00:43:49.001092: val_loss -0.8994 +2025-10-31 00:43:49.002803: Pseudo dice [np.float32(0.9868), np.float32(0.9933), np.float32(0.9946), np.float32(0.8079)] +2025-10-31 00:43:49.005161: Epoch time: 20.8 s +2025-10-31 00:43:50.650236: +2025-10-31 00:43:50.652124: Epoch 621 +2025-10-31 00:43:50.653842: Current learning rate: 0.00418 +2025-10-31 00:44:11.194348: train_loss -0.9905 +2025-10-31 00:44:11.196199: val_loss -0.896 +2025-10-31 00:44:11.197656: Pseudo dice [np.float32(0.9849), np.float32(0.9926), np.float32(0.9946), np.float32(0.8036)] +2025-10-31 00:44:11.199014: Epoch time: 20.55 s +2025-10-31 00:44:12.209939: +2025-10-31 00:44:12.211826: Epoch 622 +2025-10-31 00:44:12.213717: Current learning rate: 0.00417 +2025-10-31 00:44:32.868888: train_loss -0.9909 +2025-10-31 00:44:32.873658: val_loss -0.8978 +2025-10-31 00:44:32.875571: Pseudo dice [np.float32(0.9863), np.float32(0.9931), np.float32(0.995), np.float32(0.7966)] +2025-10-31 00:44:32.877297: Epoch time: 20.66 s +2025-10-31 00:44:33.813536: +2025-10-31 00:44:33.815403: Epoch 623 +2025-10-31 00:44:33.817118: Current learning rate: 0.00416 +2025-10-31 00:44:52.062342: train_loss -0.9913 +2025-10-31 00:44:52.065231: val_loss -0.8955 +2025-10-31 00:44:52.067919: Pseudo dice [np.float32(0.986), np.float32(0.9933), np.float32(0.9948), np.float32(0.8001)] +2025-10-31 00:44:52.070038: Epoch time: 18.25 s +2025-10-31 00:44:53.209581: +2025-10-31 00:44:53.211975: Epoch 624 +2025-10-31 00:44:53.214626: Current learning rate: 0.00415 +2025-10-31 00:45:13.658324: train_loss -0.9913 +2025-10-31 00:45:13.661122: val_loss -0.8977 +2025-10-31 00:45:13.663082: Pseudo dice [np.float32(0.984), np.float32(0.9922), np.float32(0.9951), np.float32(0.8047)] +2025-10-31 00:45:13.665005: Epoch time: 20.45 s +2025-10-31 00:45:14.695676: +2025-10-31 00:45:14.697814: Epoch 625 +2025-10-31 00:45:14.699507: Current learning rate: 0.00414 +2025-10-31 00:45:35.339459: train_loss -0.9908 +2025-10-31 00:45:35.343978: val_loss -0.8938 +2025-10-31 00:45:35.346566: Pseudo dice [np.float32(0.9852), np.float32(0.9927), np.float32(0.9948), np.float32(0.8007)] +2025-10-31 00:45:35.349090: Epoch time: 20.65 s +2025-10-31 00:45:36.383364: +2025-10-31 00:45:36.385258: Epoch 626 +2025-10-31 00:45:36.387608: Current learning rate: 0.00413 +2025-10-31 00:45:57.154892: train_loss -0.9913 +2025-10-31 00:45:57.157233: val_loss -0.8843 +2025-10-31 00:45:57.158786: Pseudo dice [np.float32(0.9856), np.float32(0.9929), np.float32(0.9942), np.float32(0.7623)] +2025-10-31 00:45:57.160338: Epoch time: 20.77 s +2025-10-31 00:45:58.372078: +2025-10-31 00:45:58.373766: Epoch 627 +2025-10-31 00:45:58.375923: Current learning rate: 0.00412 +2025-10-31 00:46:18.933995: train_loss -0.9911 +2025-10-31 00:46:18.935865: val_loss -0.8995 +2025-10-31 00:46:18.937441: Pseudo dice [np.float32(0.9846), np.float32(0.9922), np.float32(0.9947), np.float32(0.8135)] +2025-10-31 00:46:18.942796: Epoch time: 20.56 s +2025-10-31 00:46:19.988859: +2025-10-31 00:46:19.990769: Epoch 628 +2025-10-31 00:46:19.992271: Current learning rate: 0.00411 +2025-10-31 00:46:40.758866: train_loss -0.9901 +2025-10-31 00:46:40.762210: val_loss -0.8827 +2025-10-31 00:46:40.764555: Pseudo dice [np.float32(0.9857), np.float32(0.9929), np.float32(0.9941), np.float32(0.7696)] +2025-10-31 00:46:40.766647: Epoch time: 20.77 s +2025-10-31 00:46:41.909547: +2025-10-31 00:46:41.911447: Epoch 629 +2025-10-31 00:46:41.919950: Current learning rate: 0.0041 +2025-10-31 00:47:01.081261: train_loss -0.9908 +2025-10-31 00:47:01.083675: val_loss -0.8892 +2025-10-31 00:47:01.085910: Pseudo dice [np.float32(0.9858), np.float32(0.9926), np.float32(0.9949), np.float32(0.7818)] +2025-10-31 00:47:01.087693: Epoch time: 19.17 s +2025-10-31 00:47:02.174149: +2025-10-31 00:47:02.176714: Epoch 630 +2025-10-31 00:47:02.178869: Current learning rate: 0.00409 +2025-10-31 00:47:21.965164: train_loss -0.9898 +2025-10-31 00:47:21.967212: val_loss -0.8931 +2025-10-31 00:47:21.969630: Pseudo dice [np.float32(0.9845), np.float32(0.9919), np.float32(0.9945), np.float32(0.7924)] +2025-10-31 00:47:21.972057: Epoch time: 19.79 s +2025-10-31 00:47:23.162587: +2025-10-31 00:47:23.166433: Epoch 631 +2025-10-31 00:47:23.168004: Current learning rate: 0.00408 +2025-10-31 00:47:43.899521: train_loss -0.99 +2025-10-31 00:47:43.903084: val_loss -0.896 +2025-10-31 00:47:43.905179: Pseudo dice [np.float32(0.9846), np.float32(0.9925), np.float32(0.9947), np.float32(0.8016)] +2025-10-31 00:47:43.908369: Epoch time: 20.74 s +2025-10-31 00:47:45.143071: +2025-10-31 00:47:45.145034: Epoch 632 +2025-10-31 00:47:45.147435: Current learning rate: 0.00407 +2025-10-31 00:48:05.731401: train_loss -0.986 +2025-10-31 00:48:05.733608: val_loss -0.8832 +2025-10-31 00:48:05.735073: Pseudo dice [np.float32(0.9847), np.float32(0.9915), np.float32(0.9936), np.float32(0.7576)] +2025-10-31 00:48:05.736588: Epoch time: 20.59 s +2025-10-31 00:48:07.261635: +2025-10-31 00:48:07.263343: Epoch 633 +2025-10-31 00:48:07.265121: Current learning rate: 0.00406 +2025-10-31 00:48:27.823399: train_loss -0.9637 +2025-10-31 00:48:27.825750: val_loss -0.8986 +2025-10-31 00:48:27.828086: Pseudo dice [np.float32(0.9805), np.float32(0.9907), np.float32(0.9926), np.float32(0.7924)] +2025-10-31 00:48:27.830269: Epoch time: 20.56 s +2025-10-31 00:48:29.005136: +2025-10-31 00:48:29.006987: Epoch 634 +2025-10-31 00:48:29.008545: Current learning rate: 0.00405 +2025-10-31 00:48:49.766788: train_loss -0.929 +2025-10-31 00:48:49.769734: val_loss -0.9105 +2025-10-31 00:48:49.771832: Pseudo dice [np.float32(0.9843), np.float32(0.9912), np.float32(0.9946), np.float32(0.8085)] +2025-10-31 00:48:49.773628: Epoch time: 20.76 s +2025-10-31 00:48:50.719007: +2025-10-31 00:48:50.721103: Epoch 635 +2025-10-31 00:48:50.723543: Current learning rate: 0.00404 +2025-10-31 00:49:11.071220: train_loss -0.9501 +2025-10-31 00:49:11.073903: val_loss -0.8985 +2025-10-31 00:49:11.076059: Pseudo dice [np.float32(0.9845), np.float32(0.9907), np.float32(0.9932), np.float32(0.7755)] +2025-10-31 00:49:11.078178: Epoch time: 20.35 s +2025-10-31 00:49:12.256351: +2025-10-31 00:49:12.258504: Epoch 636 +2025-10-31 00:49:12.261045: Current learning rate: 0.00403 +2025-10-31 00:49:32.240822: train_loss -0.9706 +2025-10-31 00:49:32.243036: val_loss -0.8976 +2025-10-31 00:49:32.245045: Pseudo dice [np.float32(0.9833), np.float32(0.99), np.float32(0.9934), np.float32(0.7705)] +2025-10-31 00:49:32.246609: Epoch time: 19.99 s +2025-10-31 00:49:33.386473: +2025-10-31 00:49:33.388290: Epoch 637 +2025-10-31 00:49:33.391169: Current learning rate: 0.00402 +2025-10-31 00:49:53.417634: train_loss -0.9784 +2025-10-31 00:49:53.420428: val_loss -0.8955 +2025-10-31 00:49:53.422525: Pseudo dice [np.float32(0.9831), np.float32(0.991), np.float32(0.9941), np.float32(0.7807)] +2025-10-31 00:49:53.424483: Epoch time: 20.03 s +2025-10-31 00:49:54.376228: +2025-10-31 00:49:54.378201: Epoch 638 +2025-10-31 00:49:54.379843: Current learning rate: 0.00401 +2025-10-31 00:50:14.932789: train_loss -0.9818 +2025-10-31 00:50:14.935266: val_loss -0.8893 +2025-10-31 00:50:14.937560: Pseudo dice [np.float32(0.9839), np.float32(0.9912), np.float32(0.9941), np.float32(0.7569)] +2025-10-31 00:50:14.940004: Epoch time: 20.56 s +2025-10-31 00:50:16.078519: +2025-10-31 00:50:16.080860: Epoch 639 +2025-10-31 00:50:16.083314: Current learning rate: 0.004 +2025-10-31 00:50:36.799332: train_loss -0.9831 +2025-10-31 00:50:36.802698: val_loss -0.8973 +2025-10-31 00:50:36.805021: Pseudo dice [np.float32(0.985), np.float32(0.9918), np.float32(0.9943), np.float32(0.7877)] +2025-10-31 00:50:36.807238: Epoch time: 20.72 s +2025-10-31 00:50:37.849010: +2025-10-31 00:50:37.851193: Epoch 640 +2025-10-31 00:50:37.853158: Current learning rate: 0.00399 +2025-10-31 00:50:58.559940: train_loss -0.9843 +2025-10-31 00:50:58.566774: val_loss -0.9011 +2025-10-31 00:50:58.569123: Pseudo dice [np.float32(0.985), np.float32(0.9918), np.float32(0.9946), np.float32(0.7996)] +2025-10-31 00:50:58.571442: Epoch time: 20.71 s +2025-10-31 00:50:59.868356: +2025-10-31 00:50:59.870399: Epoch 641 +2025-10-31 00:50:59.872292: Current learning rate: 0.00398 +2025-10-31 00:51:20.315522: train_loss -0.9856 +2025-10-31 00:51:20.317683: val_loss -0.8984 +2025-10-31 00:51:20.319433: Pseudo dice [np.float32(0.9845), np.float32(0.9916), np.float32(0.9944), np.float32(0.7884)] +2025-10-31 00:51:20.320963: Epoch time: 20.45 s +2025-10-31 00:51:21.565800: +2025-10-31 00:51:21.567758: Epoch 642 +2025-10-31 00:51:21.569528: Current learning rate: 0.00397 +2025-10-31 00:51:40.603716: train_loss -0.9867 +2025-10-31 00:51:40.605616: val_loss -0.8941 +2025-10-31 00:51:40.607239: Pseudo dice [np.float32(0.9858), np.float32(0.9909), np.float32(0.9935), np.float32(0.7863)] +2025-10-31 00:51:40.608817: Epoch time: 19.04 s +2025-10-31 00:51:41.658244: +2025-10-31 00:51:41.660285: Epoch 643 +2025-10-31 00:51:41.661922: Current learning rate: 0.00396 +2025-10-31 00:52:02.453876: train_loss -0.9859 +2025-10-31 00:52:02.468594: val_loss -0.892 +2025-10-31 00:52:02.470211: Pseudo dice [np.float32(0.9845), np.float32(0.9912), np.float32(0.9943), np.float32(0.7896)] +2025-10-31 00:52:02.471852: Epoch time: 20.8 s +2025-10-31 00:52:03.868981: +2025-10-31 00:52:03.871047: Epoch 644 +2025-10-31 00:52:03.872860: Current learning rate: 0.00395 +2025-10-31 00:52:23.606158: train_loss -0.9875 +2025-10-31 00:52:23.608350: val_loss -0.8931 +2025-10-31 00:52:23.609892: Pseudo dice [np.float32(0.9856), np.float32(0.9915), np.float32(0.9944), np.float32(0.7931)] +2025-10-31 00:52:23.611571: Epoch time: 19.74 s +2025-10-31 00:52:25.217061: +2025-10-31 00:52:25.219217: Epoch 645 +2025-10-31 00:52:25.221011: Current learning rate: 0.00394 +2025-10-31 00:52:45.880062: train_loss -0.9888 +2025-10-31 00:52:45.882225: val_loss -0.8928 +2025-10-31 00:52:45.883850: Pseudo dice [np.float32(0.9865), np.float32(0.9919), np.float32(0.9941), np.float32(0.7789)] +2025-10-31 00:52:45.885466: Epoch time: 20.67 s +2025-10-31 00:52:46.913660: +2025-10-31 00:52:46.916032: Epoch 646 +2025-10-31 00:52:46.919230: Current learning rate: 0.00393 +2025-10-31 00:53:07.791567: train_loss -0.9889 +2025-10-31 00:53:07.794338: val_loss -0.8935 +2025-10-31 00:53:07.795778: Pseudo dice [np.float32(0.9855), np.float32(0.992), np.float32(0.9944), np.float32(0.7935)] +2025-10-31 00:53:07.797227: Epoch time: 20.88 s +2025-10-31 00:53:09.051964: +2025-10-31 00:53:09.053835: Epoch 647 +2025-10-31 00:53:09.055338: Current learning rate: 0.00392 +2025-10-31 00:53:29.559487: train_loss -0.989 +2025-10-31 00:53:29.563361: val_loss -0.8943 +2025-10-31 00:53:29.564911: Pseudo dice [np.float32(0.9861), np.float32(0.9925), np.float32(0.9944), np.float32(0.7845)] +2025-10-31 00:53:29.566214: Epoch time: 20.51 s +2025-10-31 00:53:30.650259: +2025-10-31 00:53:30.653132: Epoch 648 +2025-10-31 00:53:30.666521: Current learning rate: 0.00391 +2025-10-31 00:53:50.143451: train_loss -0.9893 +2025-10-31 00:53:50.145583: val_loss -0.8935 +2025-10-31 00:53:50.146974: Pseudo dice [np.float32(0.9825), np.float32(0.9912), np.float32(0.9943), np.float32(0.8031)] +2025-10-31 00:53:50.148525: Epoch time: 19.49 s +2025-10-31 00:53:51.170929: +2025-10-31 00:53:51.172885: Epoch 649 +2025-10-31 00:53:51.174756: Current learning rate: 0.0039 +2025-10-31 00:54:11.826262: train_loss -0.9885 +2025-10-31 00:54:11.829304: val_loss -0.891 +2025-10-31 00:54:11.831028: Pseudo dice [np.float32(0.9846), np.float32(0.9923), np.float32(0.995), np.float32(0.7837)] +2025-10-31 00:54:11.832860: Epoch time: 20.66 s +2025-10-31 00:54:14.343553: +2025-10-31 00:54:14.345504: Epoch 650 +2025-10-31 00:54:14.348048: Current learning rate: 0.00389 +2025-10-31 00:54:33.885755: train_loss -0.9894 +2025-10-31 00:54:33.887888: val_loss -0.9023 +2025-10-31 00:54:33.889687: Pseudo dice [np.float32(0.985), np.float32(0.9917), np.float32(0.9947), np.float32(0.8083)] +2025-10-31 00:54:33.891592: Epoch time: 19.54 s +2025-10-31 00:54:34.993953: +2025-10-31 00:54:34.995704: Epoch 651 +2025-10-31 00:54:34.997317: Current learning rate: 0.00388 +2025-10-31 00:54:55.430837: train_loss -0.9898 +2025-10-31 00:54:55.433036: val_loss -0.8925 +2025-10-31 00:54:55.435494: Pseudo dice [np.float32(0.9846), np.float32(0.9918), np.float32(0.9941), np.float32(0.7914)] +2025-10-31 00:54:55.437077: Epoch time: 20.44 s +2025-10-31 00:54:56.449260: +2025-10-31 00:54:56.450935: Epoch 652 +2025-10-31 00:54:56.452663: Current learning rate: 0.00387 +2025-10-31 00:55:17.198339: train_loss -0.9899 +2025-10-31 00:55:17.202243: val_loss -0.8927 +2025-10-31 00:55:17.204845: Pseudo dice [np.float32(0.9859), np.float32(0.9924), np.float32(0.9941), np.float32(0.7922)] +2025-10-31 00:55:17.207413: Epoch time: 20.75 s +2025-10-31 00:55:18.559361: +2025-10-31 00:55:18.561713: Epoch 653 +2025-10-31 00:55:18.563860: Current learning rate: 0.00386 +2025-10-31 00:55:39.211927: train_loss -0.99 +2025-10-31 00:55:39.214588: val_loss -0.8943 +2025-10-31 00:55:39.216461: Pseudo dice [np.float32(0.985), np.float32(0.9921), np.float32(0.9945), np.float32(0.7937)] +2025-10-31 00:55:39.218358: Epoch time: 20.65 s +2025-10-31 00:55:40.279511: +2025-10-31 00:55:40.281909: Epoch 654 +2025-10-31 00:55:40.284254: Current learning rate: 0.00385 +2025-10-31 00:56:00.724425: train_loss -0.9899 +2025-10-31 00:56:00.727176: val_loss -0.8901 +2025-10-31 00:56:00.729922: Pseudo dice [np.float32(0.9851), np.float32(0.9919), np.float32(0.9943), np.float32(0.7927)] +2025-10-31 00:56:00.732257: Epoch time: 20.45 s +2025-10-31 00:56:01.938970: +2025-10-31 00:56:01.940847: Epoch 655 +2025-10-31 00:56:01.942540: Current learning rate: 0.00384 +2025-10-31 00:56:22.034095: train_loss -0.9901 +2025-10-31 00:56:22.037625: val_loss -0.8883 +2025-10-31 00:56:22.039632: Pseudo dice [np.float32(0.9861), np.float32(0.9929), np.float32(0.9945), np.float32(0.781)] +2025-10-31 00:56:22.041440: Epoch time: 20.1 s +2025-10-31 00:56:23.365771: +2025-10-31 00:56:23.367790: Epoch 656 +2025-10-31 00:56:23.369633: Current learning rate: 0.00383 +2025-10-31 00:56:43.803904: train_loss -0.9902 +2025-10-31 00:56:43.806185: val_loss -0.8938 +2025-10-31 00:56:43.808523: Pseudo dice [np.float32(0.9853), np.float32(0.992), np.float32(0.9946), np.float32(0.7963)] +2025-10-31 00:56:43.811043: Epoch time: 20.44 s +2025-10-31 00:56:45.327306: +2025-10-31 00:56:45.329201: Epoch 657 +2025-10-31 00:56:45.330809: Current learning rate: 0.00382 +2025-10-31 00:57:04.723592: train_loss -0.9905 +2025-10-31 00:57:04.725633: val_loss -0.8944 +2025-10-31 00:57:04.727329: Pseudo dice [np.float32(0.9855), np.float32(0.9923), np.float32(0.9946), np.float32(0.8014)] +2025-10-31 00:57:04.729206: Epoch time: 19.4 s +2025-10-31 00:57:05.819589: +2025-10-31 00:57:05.821562: Epoch 658 +2025-10-31 00:57:05.823846: Current learning rate: 0.00381 +2025-10-31 00:57:26.606456: train_loss -0.9908 +2025-10-31 00:57:26.609271: val_loss -0.8922 +2025-10-31 00:57:26.610744: Pseudo dice [np.float32(0.9857), np.float32(0.992), np.float32(0.9944), np.float32(0.7913)] +2025-10-31 00:57:26.612231: Epoch time: 20.79 s +2025-10-31 00:57:27.967603: +2025-10-31 00:57:27.970135: Epoch 659 +2025-10-31 00:57:27.972258: Current learning rate: 0.0038 +2025-10-31 00:57:48.652944: train_loss -0.9904 +2025-10-31 00:57:48.655711: val_loss -0.8885 +2025-10-31 00:57:48.658372: Pseudo dice [np.float32(0.987), np.float32(0.9918), np.float32(0.9941), np.float32(0.7819)] +2025-10-31 00:57:48.661435: Epoch time: 20.69 s +2025-10-31 00:57:49.766214: +2025-10-31 00:57:49.768226: Epoch 660 +2025-10-31 00:57:49.770043: Current learning rate: 0.00379 +2025-10-31 00:58:10.545628: train_loss -0.9911 +2025-10-31 00:58:10.547868: val_loss -0.896 +2025-10-31 00:58:10.549644: Pseudo dice [np.float32(0.9866), np.float32(0.9931), np.float32(0.9947), np.float32(0.7954)] +2025-10-31 00:58:10.551257: Epoch time: 20.78 s +2025-10-31 00:58:11.786741: +2025-10-31 00:58:11.788634: Epoch 661 +2025-10-31 00:58:11.790696: Current learning rate: 0.00378 +2025-10-31 00:58:31.861658: train_loss -0.9903 +2025-10-31 00:58:31.864985: val_loss -0.8953 +2025-10-31 00:58:31.866549: Pseudo dice [np.float32(0.9857), np.float32(0.9925), np.float32(0.9948), np.float32(0.792)] +2025-10-31 00:58:31.868101: Epoch time: 20.08 s +2025-10-31 00:58:32.970262: +2025-10-31 00:58:32.972303: Epoch 662 +2025-10-31 00:58:32.974143: Current learning rate: 0.00377 +2025-10-31 00:58:53.761769: train_loss -0.9901 +2025-10-31 00:58:53.764092: val_loss -0.8931 +2025-10-31 00:58:53.765680: Pseudo dice [np.float32(0.9858), np.float32(0.9927), np.float32(0.9945), np.float32(0.7933)] +2025-10-31 00:58:53.767255: Epoch time: 20.79 s +2025-10-31 00:58:54.801492: +2025-10-31 00:58:54.803491: Epoch 663 +2025-10-31 00:58:54.805734: Current learning rate: 0.00376 +2025-10-31 00:59:15.279803: train_loss -0.9908 +2025-10-31 00:59:15.282226: val_loss -0.9003 +2025-10-31 00:59:15.284274: Pseudo dice [np.float32(0.9843), np.float32(0.9923), np.float32(0.9948), np.float32(0.8102)] +2025-10-31 00:59:15.285932: Epoch time: 20.48 s +2025-10-31 00:59:16.431302: +2025-10-31 00:59:16.433779: Epoch 664 +2025-10-31 00:59:16.436178: Current learning rate: 0.00375 +2025-10-31 00:59:36.691113: train_loss -0.9908 +2025-10-31 00:59:36.693980: val_loss -0.8963 +2025-10-31 00:59:36.695932: Pseudo dice [np.float32(0.9863), np.float32(0.9921), np.float32(0.9943), np.float32(0.798)] +2025-10-31 00:59:36.697629: Epoch time: 20.26 s +2025-10-31 00:59:37.778494: +2025-10-31 00:59:37.780389: Epoch 665 +2025-10-31 00:59:37.782541: Current learning rate: 0.00374 +2025-10-31 00:59:58.076892: train_loss -0.9905 +2025-10-31 00:59:58.079426: val_loss -0.8992 +2025-10-31 00:59:58.081367: Pseudo dice [np.float32(0.9847), np.float32(0.9919), np.float32(0.9946), np.float32(0.8112)] +2025-10-31 00:59:58.083812: Epoch time: 20.3 s +2025-10-31 00:59:59.284422: +2025-10-31 00:59:59.286616: Epoch 666 +2025-10-31 00:59:59.288737: Current learning rate: 0.00373 +2025-10-31 01:00:19.874280: train_loss -0.9907 +2025-10-31 01:00:19.877176: val_loss -0.9024 +2025-10-31 01:00:19.879484: Pseudo dice [np.float32(0.9875), np.float32(0.9924), np.float32(0.9946), np.float32(0.8147)] +2025-10-31 01:00:19.881395: Epoch time: 20.59 s +2025-10-31 01:00:21.068951: +2025-10-31 01:00:21.071132: Epoch 667 +2025-10-31 01:00:21.073091: Current learning rate: 0.00372 +2025-10-31 01:00:41.006379: train_loss -0.9909 +2025-10-31 01:00:41.010014: val_loss -0.8913 +2025-10-31 01:00:41.011859: Pseudo dice [np.float32(0.9855), np.float32(0.9922), np.float32(0.9945), np.float32(0.7911)] +2025-10-31 01:00:41.013697: Epoch time: 19.94 s +2025-10-31 01:00:42.343987: +2025-10-31 01:00:42.345721: Epoch 668 +2025-10-31 01:00:42.347232: Current learning rate: 0.00371 +2025-10-31 01:01:02.707163: train_loss -0.9914 +2025-10-31 01:01:02.709432: val_loss -0.8896 +2025-10-31 01:01:02.711806: Pseudo dice [np.float32(0.9856), np.float32(0.9921), np.float32(0.9942), np.float32(0.7923)] +2025-10-31 01:01:02.713416: Epoch time: 20.37 s +2025-10-31 01:01:04.191501: +2025-10-31 01:01:04.193241: Epoch 669 +2025-10-31 01:01:04.194830: Current learning rate: 0.0037 +2025-10-31 01:01:24.759938: train_loss -0.9911 +2025-10-31 01:01:24.761658: val_loss -0.8971 +2025-10-31 01:01:24.762920: Pseudo dice [np.float32(0.9863), np.float32(0.9929), np.float32(0.9949), np.float32(0.7954)] +2025-10-31 01:01:24.764815: Epoch time: 20.57 s +2025-10-31 01:01:25.984550: +2025-10-31 01:01:25.986925: Epoch 670 +2025-10-31 01:01:25.989481: Current learning rate: 0.00369 +2025-10-31 01:01:45.724097: train_loss -0.9912 +2025-10-31 01:01:45.727114: val_loss -0.8998 +2025-10-31 01:01:45.729316: Pseudo dice [np.float32(0.9848), np.float32(0.9921), np.float32(0.9951), np.float32(0.8136)] +2025-10-31 01:01:45.730825: Epoch time: 19.74 s +2025-10-31 01:01:46.983411: +2025-10-31 01:01:46.985379: Epoch 671 +2025-10-31 01:01:46.987349: Current learning rate: 0.00368 +2025-10-31 01:02:07.556241: train_loss -0.9903 +2025-10-31 01:02:07.574481: val_loss -0.8908 +2025-10-31 01:02:07.576427: Pseudo dice [np.float32(0.9861), np.float32(0.9918), np.float32(0.9942), np.float32(0.7957)] +2025-10-31 01:02:07.578492: Epoch time: 20.58 s +2025-10-31 01:02:08.712374: +2025-10-31 01:02:08.714581: Epoch 672 +2025-10-31 01:02:08.717328: Current learning rate: 0.00367 +2025-10-31 01:02:29.682293: train_loss -0.9913 +2025-10-31 01:02:29.686063: val_loss -0.8925 +2025-10-31 01:02:29.687999: Pseudo dice [np.float32(0.9863), np.float32(0.9927), np.float32(0.9946), np.float32(0.7922)] +2025-10-31 01:02:29.690049: Epoch time: 20.97 s +2025-10-31 01:02:31.125021: +2025-10-31 01:02:31.127264: Epoch 673 +2025-10-31 01:02:31.129278: Current learning rate: 0.00366 +2025-10-31 01:02:51.730363: train_loss -0.9907 +2025-10-31 01:02:51.735969: val_loss -0.8937 +2025-10-31 01:02:51.738212: Pseudo dice [np.float32(0.9865), np.float32(0.9937), np.float32(0.9945), np.float32(0.7925)] +2025-10-31 01:02:51.739592: Epoch time: 20.61 s +2025-10-31 01:02:52.892861: +2025-10-31 01:02:52.895528: Epoch 674 +2025-10-31 01:02:52.898294: Current learning rate: 0.00365 +2025-10-31 01:03:13.725532: train_loss -0.9912 +2025-10-31 01:03:13.733265: val_loss -0.8991 +2025-10-31 01:03:13.734922: Pseudo dice [np.float32(0.9853), np.float32(0.9928), np.float32(0.9949), np.float32(0.8107)] +2025-10-31 01:03:13.736700: Epoch time: 20.83 s +2025-10-31 01:03:14.964518: +2025-10-31 01:03:14.968021: Epoch 675 +2025-10-31 01:03:14.970280: Current learning rate: 0.00364 +2025-10-31 01:03:35.486700: train_loss -0.9914 +2025-10-31 01:03:35.494467: val_loss -0.8997 +2025-10-31 01:03:35.496257: Pseudo dice [np.float32(0.9859), np.float32(0.9926), np.float32(0.9948), np.float32(0.8105)] +2025-10-31 01:03:35.498108: Epoch time: 20.52 s +2025-10-31 01:03:36.740128: +2025-10-31 01:03:36.741964: Epoch 676 +2025-10-31 01:03:36.743623: Current learning rate: 0.00363 +2025-10-31 01:03:57.398764: train_loss -0.9904 +2025-10-31 01:03:57.410132: val_loss -0.8939 +2025-10-31 01:03:57.413765: Pseudo dice [np.float32(0.9853), np.float32(0.9923), np.float32(0.9947), np.float32(0.789)] +2025-10-31 01:03:57.418516: Epoch time: 20.66 s +2025-10-31 01:03:58.530323: +2025-10-31 01:03:58.532760: Epoch 677 +2025-10-31 01:03:58.534721: Current learning rate: 0.00362 +2025-10-31 01:04:18.358328: train_loss -0.9911 +2025-10-31 01:04:18.361016: val_loss -0.8905 +2025-10-31 01:04:18.362479: Pseudo dice [np.float32(0.9853), np.float32(0.9925), np.float32(0.9945), np.float32(0.7881)] +2025-10-31 01:04:18.364521: Epoch time: 19.83 s +2025-10-31 01:04:19.659335: +2025-10-31 01:04:19.663149: Epoch 678 +2025-10-31 01:04:19.666503: Current learning rate: 0.00361 +2025-10-31 01:04:40.236690: train_loss -0.991 +2025-10-31 01:04:40.239931: val_loss -0.9002 +2025-10-31 01:04:40.244038: Pseudo dice [np.float32(0.9854), np.float32(0.9931), np.float32(0.9951), np.float32(0.8037)] +2025-10-31 01:04:40.245520: Epoch time: 20.58 s +2025-10-31 01:04:41.446454: +2025-10-31 01:04:41.450232: Epoch 679 +2025-10-31 01:04:41.452091: Current learning rate: 0.0036 +2025-10-31 01:05:02.170317: train_loss -0.9903 +2025-10-31 01:05:02.184906: val_loss -0.8962 +2025-10-31 01:05:02.187624: Pseudo dice [np.float32(0.9871), np.float32(0.993), np.float32(0.9944), np.float32(0.7936)] +2025-10-31 01:05:02.190491: Epoch time: 20.73 s +2025-10-31 01:05:03.259333: +2025-10-31 01:05:03.261780: Epoch 680 +2025-10-31 01:05:03.264801: Current learning rate: 0.00359 +2025-10-31 01:05:22.930548: train_loss -0.9894 +2025-10-31 01:05:22.936563: val_loss -0.8955 +2025-10-31 01:05:22.938741: Pseudo dice [np.float32(0.9872), np.float32(0.9935), np.float32(0.9945), np.float32(0.7858)] +2025-10-31 01:05:22.940536: Epoch time: 19.67 s +2025-10-31 01:05:24.700481: +2025-10-31 01:05:24.703468: Epoch 681 +2025-10-31 01:05:24.710976: Current learning rate: 0.00358 +2025-10-31 01:05:45.331131: train_loss -0.9913 +2025-10-31 01:05:45.334070: val_loss -0.9008 +2025-10-31 01:05:45.336532: Pseudo dice [np.float32(0.9854), np.float32(0.9924), np.float32(0.9946), np.float32(0.8102)] +2025-10-31 01:05:45.338833: Epoch time: 20.63 s +2025-10-31 01:05:46.459984: +2025-10-31 01:05:46.467160: Epoch 682 +2025-10-31 01:05:46.472166: Current learning rate: 0.00357 +2025-10-31 01:06:07.037229: train_loss -0.9907 +2025-10-31 01:06:07.043826: val_loss -0.8952 +2025-10-31 01:06:07.046082: Pseudo dice [np.float32(0.9856), np.float32(0.9925), np.float32(0.9946), np.float32(0.7949)] +2025-10-31 01:06:07.047781: Epoch time: 20.58 s +2025-10-31 01:06:08.268400: +2025-10-31 01:06:08.270733: Epoch 683 +2025-10-31 01:06:08.272821: Current learning rate: 0.00356 +2025-10-31 01:06:28.949447: train_loss -0.9905 +2025-10-31 01:06:28.952552: val_loss -0.8974 +2025-10-31 01:06:28.954383: Pseudo dice [np.float32(0.9861), np.float32(0.9924), np.float32(0.9943), np.float32(0.7955)] +2025-10-31 01:06:28.955898: Epoch time: 20.68 s +2025-10-31 01:06:29.976767: +2025-10-31 01:06:29.978461: Epoch 684 +2025-10-31 01:06:29.980488: Current learning rate: 0.00355 +2025-10-31 01:06:49.934573: train_loss -0.9913 +2025-10-31 01:06:49.941067: val_loss -0.8981 +2025-10-31 01:06:49.942646: Pseudo dice [np.float32(0.9853), np.float32(0.9927), np.float32(0.9951), np.float32(0.8067)] +2025-10-31 01:06:49.944300: Epoch time: 19.96 s +2025-10-31 01:06:51.166912: +2025-10-31 01:06:51.168818: Epoch 685 +2025-10-31 01:06:51.170392: Current learning rate: 0.00354 +2025-10-31 01:07:11.735725: train_loss -0.9915 +2025-10-31 01:07:11.739189: val_loss -0.9 +2025-10-31 01:07:11.742577: Pseudo dice [np.float32(0.9846), np.float32(0.9927), np.float32(0.995), np.float32(0.8105)] +2025-10-31 01:07:11.745042: Epoch time: 20.57 s +2025-10-31 01:07:12.996488: +2025-10-31 01:07:12.999826: Epoch 686 +2025-10-31 01:07:13.002049: Current learning rate: 0.00353 +2025-10-31 01:07:32.779627: train_loss -0.9915 +2025-10-31 01:07:32.792443: val_loss -0.8982 +2025-10-31 01:07:32.795327: Pseudo dice [np.float32(0.986), np.float32(0.9925), np.float32(0.9945), np.float32(0.8048)] +2025-10-31 01:07:32.797569: Epoch time: 19.78 s +2025-10-31 01:07:33.968054: +2025-10-31 01:07:33.970029: Epoch 687 +2025-10-31 01:07:33.971614: Current learning rate: 0.00352 +2025-10-31 01:07:54.898101: train_loss -0.9918 +2025-10-31 01:07:54.901904: val_loss -0.9022 +2025-10-31 01:07:54.904130: Pseudo dice [np.float32(0.9868), np.float32(0.9929), np.float32(0.9947), np.float32(0.8156)] +2025-10-31 01:07:54.906190: Epoch time: 20.93 s +2025-10-31 01:07:56.192475: +2025-10-31 01:07:56.199203: Epoch 688 +2025-10-31 01:07:56.204813: Current learning rate: 0.00351 +2025-10-31 01:08:16.780858: train_loss -0.9915 +2025-10-31 01:08:16.791947: val_loss -0.906 +2025-10-31 01:08:16.793490: Pseudo dice [np.float32(0.9862), np.float32(0.992), np.float32(0.9947), np.float32(0.8228)] +2025-10-31 01:08:16.795266: Epoch time: 20.59 s +2025-10-31 01:08:16.797274: Yayy! New best EMA pseudo Dice: 0.9441999793052673 +2025-10-31 01:08:19.122569: +2025-10-31 01:08:19.125598: Epoch 689 +2025-10-31 01:08:19.128244: Current learning rate: 0.0035 +2025-10-31 01:08:39.663452: train_loss -0.9921 +2025-10-31 01:08:39.672279: val_loss -0.8928 +2025-10-31 01:08:39.674454: Pseudo dice [np.float32(0.9856), np.float32(0.9927), np.float32(0.9946), np.float32(0.7872)] +2025-10-31 01:08:39.678393: Epoch time: 20.54 s +2025-10-31 01:08:40.757086: +2025-10-31 01:08:40.759751: Epoch 690 +2025-10-31 01:08:40.762369: Current learning rate: 0.00349 +2025-10-31 01:09:00.043424: train_loss -0.9912 +2025-10-31 01:09:00.049877: val_loss -0.8935 +2025-10-31 01:09:00.052778: Pseudo dice [np.float32(0.9866), np.float32(0.9925), np.float32(0.9948), np.float32(0.7882)] +2025-10-31 01:09:00.054850: Epoch time: 19.29 s +2025-10-31 01:09:01.293962: +2025-10-31 01:09:01.295872: Epoch 691 +2025-10-31 01:09:01.297666: Current learning rate: 0.00348 +2025-10-31 01:09:21.832033: train_loss -0.9913 +2025-10-31 01:09:21.836458: val_loss -0.89 +2025-10-31 01:09:21.838286: Pseudo dice [np.float32(0.9856), np.float32(0.9921), np.float32(0.9943), np.float32(0.7911)] +2025-10-31 01:09:21.839717: Epoch time: 20.54 s +2025-10-31 01:09:23.099297: +2025-10-31 01:09:23.101570: Epoch 692 +2025-10-31 01:09:23.104426: Current learning rate: 0.00346 +2025-10-31 01:09:42.775105: train_loss -0.9917 +2025-10-31 01:09:42.781508: val_loss -0.8894 +2025-10-31 01:09:42.783765: Pseudo dice [np.float32(0.9865), np.float32(0.9928), np.float32(0.9943), np.float32(0.7876)] +2025-10-31 01:09:42.785564: Epoch time: 19.68 s +2025-10-31 01:09:43.823291: +2025-10-31 01:09:43.825644: Epoch 693 +2025-10-31 01:09:43.827770: Current learning rate: 0.00345 +2025-10-31 01:10:04.555822: train_loss -0.9913 +2025-10-31 01:10:04.560143: val_loss -0.9034 +2025-10-31 01:10:04.563132: Pseudo dice [np.float32(0.9869), np.float32(0.9926), np.float32(0.9948), np.float32(0.8153)] +2025-10-31 01:10:04.565263: Epoch time: 20.73 s +2025-10-31 01:10:05.603616: +2025-10-31 01:10:05.605526: Epoch 694 +2025-10-31 01:10:05.607398: Current learning rate: 0.00344 +2025-10-31 01:10:26.230608: train_loss -0.992 +2025-10-31 01:10:26.234209: val_loss -0.8927 +2025-10-31 01:10:26.235987: Pseudo dice [np.float32(0.9865), np.float32(0.9925), np.float32(0.9949), np.float32(0.7933)] +2025-10-31 01:10:26.237657: Epoch time: 20.63 s +2025-10-31 01:10:27.651284: +2025-10-31 01:10:27.653492: Epoch 695 +2025-10-31 01:10:27.655030: Current learning rate: 0.00343 +2025-10-31 01:10:48.339304: train_loss -0.9904 +2025-10-31 01:10:48.342978: val_loss -0.9019 +2025-10-31 01:10:48.344801: Pseudo dice [np.float32(0.9866), np.float32(0.9932), np.float32(0.9948), np.float32(0.807)] +2025-10-31 01:10:48.346741: Epoch time: 20.69 s +2025-10-31 01:10:49.458751: +2025-10-31 01:10:49.471303: Epoch 696 +2025-10-31 01:10:49.472867: Current learning rate: 0.00342 +2025-10-31 01:11:10.275471: train_loss -0.9904 +2025-10-31 01:11:10.279886: val_loss -0.9027 +2025-10-31 01:11:10.281278: Pseudo dice [np.float32(0.9867), np.float32(0.9933), np.float32(0.995), np.float32(0.8159)] +2025-10-31 01:11:10.282702: Epoch time: 20.82 s +2025-10-31 01:11:11.517278: +2025-10-31 01:11:11.519355: Epoch 697 +2025-10-31 01:11:11.521400: Current learning rate: 0.00341 +2025-10-31 01:11:31.231115: train_loss -0.9911 +2025-10-31 01:11:31.239164: val_loss -0.9063 +2025-10-31 01:11:31.240770: Pseudo dice [np.float32(0.9866), np.float32(0.9928), np.float32(0.9951), np.float32(0.8121)] +2025-10-31 01:11:31.242236: Epoch time: 19.72 s +2025-10-31 01:11:32.522318: +2025-10-31 01:11:32.524097: Epoch 698 +2025-10-31 01:11:32.533309: Current learning rate: 0.0034 +2025-10-31 01:11:52.962252: train_loss -0.9914 +2025-10-31 01:11:52.969797: val_loss -0.891 +2025-10-31 01:11:52.971851: Pseudo dice [np.float32(0.9844), np.float32(0.9925), np.float32(0.9947), np.float32(0.7919)] +2025-10-31 01:11:52.974577: Epoch time: 20.44 s +2025-10-31 01:11:54.005413: +2025-10-31 01:11:54.027961: Epoch 699 +2025-10-31 01:11:54.047985: Current learning rate: 0.00339 +2025-10-31 01:12:13.815599: train_loss -0.9918 +2025-10-31 01:12:13.819110: val_loss -0.8923 +2025-10-31 01:12:13.821198: Pseudo dice [np.float32(0.9844), np.float32(0.9921), np.float32(0.9944), np.float32(0.7946)] +2025-10-31 01:12:13.823312: Epoch time: 19.81 s +2025-10-31 01:12:16.160784: +2025-10-31 01:12:16.162646: Epoch 700 +2025-10-31 01:12:16.164151: Current learning rate: 0.00338 +2025-10-31 01:12:36.918068: train_loss -0.9912 +2025-10-31 01:12:36.927052: val_loss -0.9 +2025-10-31 01:12:36.928570: Pseudo dice [np.float32(0.9865), np.float32(0.9928), np.float32(0.9951), np.float32(0.8066)] +2025-10-31 01:12:36.930436: Epoch time: 20.76 s +2025-10-31 01:12:38.189743: +2025-10-31 01:12:38.191781: Epoch 701 +2025-10-31 01:12:38.193359: Current learning rate: 0.00337 +2025-10-31 01:12:58.546118: train_loss -0.9909 +2025-10-31 01:12:58.550348: val_loss -0.899 +2025-10-31 01:12:58.551639: Pseudo dice [np.float32(0.9863), np.float32(0.9931), np.float32(0.9948), np.float32(0.8001)] +2025-10-31 01:12:58.552994: Epoch time: 20.36 s +2025-10-31 01:12:59.594924: +2025-10-31 01:12:59.596578: Epoch 702 +2025-10-31 01:12:59.598896: Current learning rate: 0.00336 +2025-10-31 01:13:20.678130: train_loss -0.9916 +2025-10-31 01:13:20.680939: val_loss -0.9031 +2025-10-31 01:13:20.682398: Pseudo dice [np.float32(0.9851), np.float32(0.9925), np.float32(0.9949), np.float32(0.8157)] +2025-10-31 01:13:20.684368: Epoch time: 21.08 s +2025-10-31 01:13:21.999263: +2025-10-31 01:13:22.001388: Epoch 703 +2025-10-31 01:13:22.003673: Current learning rate: 0.00335 +2025-10-31 01:13:42.619695: train_loss -0.9913 +2025-10-31 01:13:42.628553: val_loss -0.9034 +2025-10-31 01:13:42.630827: Pseudo dice [np.float32(0.9866), np.float32(0.9932), np.float32(0.995), np.float32(0.8107)] +2025-10-31 01:13:42.632561: Epoch time: 20.62 s +2025-10-31 01:13:42.636422: Yayy! New best EMA pseudo Dice: 0.9442999958992004 +2025-10-31 01:13:45.359948: +2025-10-31 01:13:45.361975: Epoch 704 +2025-10-31 01:13:45.363669: Current learning rate: 0.00334 +2025-10-31 01:14:04.937657: train_loss -0.9918 +2025-10-31 01:14:04.942757: val_loss -0.8965 +2025-10-31 01:14:04.946417: Pseudo dice [np.float32(0.9854), np.float32(0.9923), np.float32(0.9945), np.float32(0.7983)] +2025-10-31 01:14:04.949106: Epoch time: 19.58 s +2025-10-31 01:14:06.043332: +2025-10-31 01:14:06.049042: Epoch 705 +2025-10-31 01:14:06.051585: Current learning rate: 0.00333 +2025-10-31 01:14:25.276093: train_loss -0.9914 +2025-10-31 01:14:25.279123: val_loss -0.9032 +2025-10-31 01:14:25.280636: Pseudo dice [np.float32(0.9875), np.float32(0.9929), np.float32(0.9945), np.float32(0.8115)] +2025-10-31 01:14:25.282363: Epoch time: 19.23 s +2025-10-31 01:14:25.284354: Yayy! New best EMA pseudo Dice: 0.9444000124931335 +2025-10-31 01:14:28.061562: +2025-10-31 01:14:28.065542: Epoch 706 +2025-10-31 01:14:28.068439: Current learning rate: 0.00332 +2025-10-31 01:14:48.641650: train_loss -0.9914 +2025-10-31 01:14:48.645287: val_loss -0.901 +2025-10-31 01:14:48.646846: Pseudo dice [np.float32(0.986), np.float32(0.9927), np.float32(0.9949), np.float32(0.8124)] +2025-10-31 01:14:48.648773: Epoch time: 20.58 s +2025-10-31 01:14:48.650421: Yayy! New best EMA pseudo Dice: 0.944599986076355 +2025-10-31 01:14:50.917165: +2025-10-31 01:14:50.920042: Epoch 707 +2025-10-31 01:14:50.922375: Current learning rate: 0.00331 +2025-10-31 01:15:11.568889: train_loss -0.9918 +2025-10-31 01:15:11.571707: val_loss -0.896 +2025-10-31 01:15:11.573805: Pseudo dice [np.float32(0.9854), np.float32(0.9925), np.float32(0.9948), np.float32(0.8047)] +2025-10-31 01:15:11.575624: Epoch time: 20.65 s +2025-10-31 01:15:12.774010: +2025-10-31 01:15:12.775812: Epoch 708 +2025-10-31 01:15:12.777611: Current learning rate: 0.0033 +2025-10-31 01:15:33.344845: train_loss -0.9919 +2025-10-31 01:15:33.356457: val_loss -0.9052 +2025-10-31 01:15:33.358122: Pseudo dice [np.float32(0.9858), np.float32(0.9929), np.float32(0.9952), np.float32(0.8179)] +2025-10-31 01:15:33.359753: Epoch time: 20.57 s +2025-10-31 01:15:33.361227: Yayy! New best EMA pseudo Dice: 0.9448999762535095 +2025-10-31 01:15:35.767560: +2025-10-31 01:15:35.769642: Epoch 709 +2025-10-31 01:15:35.771188: Current learning rate: 0.00329 +2025-10-31 01:15:56.647695: train_loss -0.9921 +2025-10-31 01:15:56.651742: val_loss -0.8928 +2025-10-31 01:15:56.655898: Pseudo dice [np.float32(0.985), np.float32(0.9925), np.float32(0.9944), np.float32(0.7976)] +2025-10-31 01:15:56.657490: Epoch time: 20.88 s +2025-10-31 01:15:57.902515: +2025-10-31 01:15:57.904618: Epoch 710 +2025-10-31 01:15:57.906295: Current learning rate: 0.00328 +2025-10-31 01:16:17.673773: train_loss -0.9915 +2025-10-31 01:16:17.678992: val_loss -0.8988 +2025-10-31 01:16:17.680910: Pseudo dice [np.float32(0.9867), np.float32(0.9924), np.float32(0.9948), np.float32(0.804)] +2025-10-31 01:16:17.682491: Epoch time: 19.77 s +2025-10-31 01:16:18.813637: +2025-10-31 01:16:18.815397: Epoch 711 +2025-10-31 01:16:18.817233: Current learning rate: 0.00327 +2025-10-31 01:16:38.500066: train_loss -0.9923 +2025-10-31 01:16:38.505164: val_loss -0.8905 +2025-10-31 01:16:38.506824: Pseudo dice [np.float32(0.9864), np.float32(0.9929), np.float32(0.9943), np.float32(0.7833)] +2025-10-31 01:16:38.508357: Epoch time: 19.69 s +2025-10-31 01:16:39.758796: +2025-10-31 01:16:39.760361: Epoch 712 +2025-10-31 01:16:39.762547: Current learning rate: 0.00326 +2025-10-31 01:17:00.609428: train_loss -0.9922 +2025-10-31 01:17:00.615291: val_loss -0.8883 +2025-10-31 01:17:00.617926: Pseudo dice [np.float32(0.9853), np.float32(0.9929), np.float32(0.9945), np.float32(0.7821)] +2025-10-31 01:17:00.620124: Epoch time: 20.85 s +2025-10-31 01:17:01.914276: +2025-10-31 01:17:01.916157: Epoch 713 +2025-10-31 01:17:01.917860: Current learning rate: 0.00325 +2025-10-31 01:17:22.674891: train_loss -0.9912 +2025-10-31 01:17:22.677333: val_loss -0.8873 +2025-10-31 01:17:22.678988: Pseudo dice [np.float32(0.9861), np.float32(0.993), np.float32(0.9938), np.float32(0.7782)] +2025-10-31 01:17:22.681149: Epoch time: 20.76 s +2025-10-31 01:17:23.757324: +2025-10-31 01:17:23.759064: Epoch 714 +2025-10-31 01:17:23.760752: Current learning rate: 0.00324 +2025-10-31 01:17:44.650807: train_loss -0.9915 +2025-10-31 01:17:44.655125: val_loss -0.8966 +2025-10-31 01:17:44.656712: Pseudo dice [np.float32(0.9857), np.float32(0.9931), np.float32(0.9948), np.float32(0.802)] +2025-10-31 01:17:44.658409: Epoch time: 20.9 s +2025-10-31 01:17:46.198532: +2025-10-31 01:17:46.200297: Epoch 715 +2025-10-31 01:17:46.201675: Current learning rate: 0.00323 +2025-10-31 01:18:06.931898: train_loss -0.9919 +2025-10-31 01:18:06.937348: val_loss -0.8986 +2025-10-31 01:18:06.938834: Pseudo dice [np.float32(0.9858), np.float32(0.9927), np.float32(0.9947), np.float32(0.7999)] +2025-10-31 01:18:06.940168: Epoch time: 20.74 s +2025-10-31 01:18:08.200273: +2025-10-31 01:18:08.202300: Epoch 716 +2025-10-31 01:18:08.203946: Current learning rate: 0.00322 +2025-10-31 01:18:28.669306: train_loss -0.9922 +2025-10-31 01:18:28.672278: val_loss -0.8928 +2025-10-31 01:18:28.673944: Pseudo dice [np.float32(0.9869), np.float32(0.993), np.float32(0.9946), np.float32(0.7939)] +2025-10-31 01:18:28.675784: Epoch time: 20.47 s +2025-10-31 01:18:29.903117: +2025-10-31 01:18:29.904848: Epoch 717 +2025-10-31 01:18:29.906498: Current learning rate: 0.00321 +2025-10-31 01:18:47.965984: train_loss -0.9923 +2025-10-31 01:18:47.967774: val_loss -0.8965 +2025-10-31 01:18:47.969266: Pseudo dice [np.float32(0.9853), np.float32(0.9928), np.float32(0.9945), np.float32(0.7994)] +2025-10-31 01:18:47.971075: Epoch time: 18.06 s +2025-10-31 01:18:49.172663: +2025-10-31 01:18:49.174523: Epoch 718 +2025-10-31 01:18:49.176044: Current learning rate: 0.0032 +2025-10-31 01:19:09.736125: train_loss -0.9926 +2025-10-31 01:19:09.739262: val_loss -0.8994 +2025-10-31 01:19:09.740946: Pseudo dice [np.float32(0.9867), np.float32(0.993), np.float32(0.9943), np.float32(0.8067)] +2025-10-31 01:19:09.744228: Epoch time: 20.57 s +2025-10-31 01:19:11.056247: +2025-10-31 01:19:11.059653: Epoch 719 +2025-10-31 01:19:11.061328: Current learning rate: 0.00319 +2025-10-31 01:19:31.712680: train_loss -0.9916 +2025-10-31 01:19:31.714564: val_loss -0.8974 +2025-10-31 01:19:31.716560: Pseudo dice [np.float32(0.9843), np.float32(0.9915), np.float32(0.9944), np.float32(0.8137)] +2025-10-31 01:19:31.718233: Epoch time: 20.66 s +2025-10-31 01:19:32.947092: +2025-10-31 01:19:32.949434: Epoch 720 +2025-10-31 01:19:32.951597: Current learning rate: 0.00318 +2025-10-31 01:19:53.688591: train_loss -0.9922 +2025-10-31 01:19:53.691986: val_loss -0.8946 +2025-10-31 01:19:53.693482: Pseudo dice [np.float32(0.9872), np.float32(0.9931), np.float32(0.9947), np.float32(0.7888)] +2025-10-31 01:19:53.695816: Epoch time: 20.74 s +2025-10-31 01:19:54.867953: +2025-10-31 01:19:54.869989: Epoch 721 +2025-10-31 01:19:54.871660: Current learning rate: 0.00317 +2025-10-31 01:20:15.629476: train_loss -0.9922 +2025-10-31 01:20:15.638558: val_loss -0.8924 +2025-10-31 01:20:15.641453: Pseudo dice [np.float32(0.986), np.float32(0.9927), np.float32(0.9944), np.float32(0.7881)] +2025-10-31 01:20:15.644557: Epoch time: 20.76 s +2025-10-31 01:20:16.880995: +2025-10-31 01:20:16.883214: Epoch 722 +2025-10-31 01:20:16.886332: Current learning rate: 0.00316 +2025-10-31 01:20:37.480147: train_loss -0.9918 +2025-10-31 01:20:37.484843: val_loss -0.8919 +2025-10-31 01:20:37.486742: Pseudo dice [np.float32(0.9854), np.float32(0.9925), np.float32(0.9942), np.float32(0.7949)] +2025-10-31 01:20:37.488501: Epoch time: 20.6 s +2025-10-31 01:20:38.538629: +2025-10-31 01:20:38.540925: Epoch 723 +2025-10-31 01:20:38.543158: Current learning rate: 0.00315 +2025-10-31 01:20:59.247110: train_loss -0.9925 +2025-10-31 01:20:59.249812: val_loss -0.9008 +2025-10-31 01:20:59.251496: Pseudo dice [np.float32(0.9866), np.float32(0.9935), np.float32(0.995), np.float32(0.8047)] +2025-10-31 01:20:59.253573: Epoch time: 20.71 s +2025-10-31 01:21:00.383754: +2025-10-31 01:21:00.385666: Epoch 724 +2025-10-31 01:21:00.387438: Current learning rate: 0.00314 +2025-10-31 01:21:18.510011: train_loss -0.9918 +2025-10-31 01:21:18.513261: val_loss -0.8998 +2025-10-31 01:21:18.514689: Pseudo dice [np.float32(0.9858), np.float32(0.9928), np.float32(0.9949), np.float32(0.8115)] +2025-10-31 01:21:18.516137: Epoch time: 18.13 s +2025-10-31 01:21:19.487355: +2025-10-31 01:21:19.489015: Epoch 725 +2025-10-31 01:21:19.491074: Current learning rate: 0.00313 +2025-10-31 01:21:40.125111: train_loss -0.9926 +2025-10-31 01:21:40.129055: val_loss -0.8919 +2025-10-31 01:21:40.130804: Pseudo dice [np.float32(0.9866), np.float32(0.9933), np.float32(0.9944), np.float32(0.7907)] +2025-10-31 01:21:40.132408: Epoch time: 20.64 s +2025-10-31 01:21:41.240209: +2025-10-31 01:21:41.242107: Epoch 726 +2025-10-31 01:21:41.244319: Current learning rate: 0.00312 +2025-10-31 01:22:01.993090: train_loss -0.9916 +2025-10-31 01:22:01.996178: val_loss -0.8953 +2025-10-31 01:22:01.997722: Pseudo dice [np.float32(0.9847), np.float32(0.9917), np.float32(0.9945), np.float32(0.8107)] +2025-10-31 01:22:01.999257: Epoch time: 20.75 s +2025-10-31 01:22:03.648118: +2025-10-31 01:22:03.649746: Epoch 727 +2025-10-31 01:22:03.652560: Current learning rate: 0.00311 +2025-10-31 01:22:24.440893: train_loss -0.9926 +2025-10-31 01:22:24.453471: val_loss -0.8949 +2025-10-31 01:22:24.460463: Pseudo dice [np.float32(0.9866), np.float32(0.9927), np.float32(0.9942), np.float32(0.7968)] +2025-10-31 01:22:24.467690: Epoch time: 20.79 s +2025-10-31 01:22:25.603697: +2025-10-31 01:22:25.606188: Epoch 728 +2025-10-31 01:22:25.608618: Current learning rate: 0.0031 +2025-10-31 01:22:46.375527: train_loss -0.9925 +2025-10-31 01:22:46.379590: val_loss -0.8898 +2025-10-31 01:22:46.381013: Pseudo dice [np.float32(0.985), np.float32(0.9923), np.float32(0.9945), np.float32(0.796)] +2025-10-31 01:22:46.382588: Epoch time: 20.77 s +2025-10-31 01:22:47.525957: +2025-10-31 01:22:47.528675: Epoch 729 +2025-10-31 01:22:47.530276: Current learning rate: 0.00309 +2025-10-31 01:23:08.170242: train_loss -0.9923 +2025-10-31 01:23:08.172472: val_loss -0.8991 +2025-10-31 01:23:08.174429: Pseudo dice [np.float32(0.9869), np.float32(0.9927), np.float32(0.9945), np.float32(0.7993)] +2025-10-31 01:23:08.176505: Epoch time: 20.65 s +2025-10-31 01:23:09.411286: +2025-10-31 01:23:09.413217: Epoch 730 +2025-10-31 01:23:09.414787: Current learning rate: 0.00308 +2025-10-31 01:23:28.467588: train_loss -0.9923 +2025-10-31 01:23:28.475177: val_loss -0.8926 +2025-10-31 01:23:28.476783: Pseudo dice [np.float32(0.9874), np.float32(0.9928), np.float32(0.9942), np.float32(0.7916)] +2025-10-31 01:23:28.479090: Epoch time: 19.06 s +2025-10-31 01:23:29.510175: +2025-10-31 01:23:29.512471: Epoch 731 +2025-10-31 01:23:29.515897: Current learning rate: 0.00307 +2025-10-31 01:23:50.294074: train_loss -0.9923 +2025-10-31 01:23:50.306061: val_loss -0.8968 +2025-10-31 01:23:50.308304: Pseudo dice [np.float32(0.9868), np.float32(0.9927), np.float32(0.9944), np.float32(0.802)] +2025-10-31 01:23:50.310486: Epoch time: 20.79 s +2025-10-31 01:23:51.454378: +2025-10-31 01:23:51.460147: Epoch 732 +2025-10-31 01:23:51.466346: Current learning rate: 0.00306 +2025-10-31 01:24:12.217331: train_loss -0.9911 +2025-10-31 01:24:12.220279: val_loss -0.897 +2025-10-31 01:24:12.221772: Pseudo dice [np.float32(0.9869), np.float32(0.9928), np.float32(0.9946), np.float32(0.8009)] +2025-10-31 01:24:12.223233: Epoch time: 20.76 s +2025-10-31 01:24:13.453233: +2025-10-31 01:24:13.455283: Epoch 733 +2025-10-31 01:24:13.457583: Current learning rate: 0.00305 +2025-10-31 01:24:34.208649: train_loss -0.9922 +2025-10-31 01:24:34.216020: val_loss -0.8989 +2025-10-31 01:24:34.218022: Pseudo dice [np.float32(0.9878), np.float32(0.993), np.float32(0.9945), np.float32(0.8023)] +2025-10-31 01:24:34.219995: Epoch time: 20.76 s +2025-10-31 01:24:35.416631: +2025-10-31 01:24:35.419805: Epoch 734 +2025-10-31 01:24:35.421985: Current learning rate: 0.00304 +2025-10-31 01:24:56.236868: train_loss -0.9917 +2025-10-31 01:24:56.251651: val_loss -0.8974 +2025-10-31 01:24:56.255435: Pseudo dice [np.float32(0.9863), np.float32(0.9926), np.float32(0.9944), np.float32(0.8004)] +2025-10-31 01:24:56.258698: Epoch time: 20.82 s +2025-10-31 01:24:57.430116: +2025-10-31 01:24:57.433170: Epoch 735 +2025-10-31 01:24:57.435961: Current learning rate: 0.00303 +2025-10-31 01:25:18.115923: train_loss -0.9927 +2025-10-31 01:25:18.122380: val_loss -0.8986 +2025-10-31 01:25:18.124505: Pseudo dice [np.float32(0.987), np.float32(0.993), np.float32(0.9949), np.float32(0.8072)] +2025-10-31 01:25:18.126752: Epoch time: 20.69 s +2025-10-31 01:25:19.306922: +2025-10-31 01:25:19.308991: Epoch 736 +2025-10-31 01:25:19.310559: Current learning rate: 0.00302 +2025-10-31 01:25:39.784629: train_loss -0.9922 +2025-10-31 01:25:39.788680: val_loss -0.9011 +2025-10-31 01:25:39.790348: Pseudo dice [np.float32(0.9867), np.float32(0.9931), np.float32(0.995), np.float32(0.812)] +2025-10-31 01:25:39.791956: Epoch time: 20.48 s +2025-10-31 01:25:40.934364: +2025-10-31 01:25:40.937026: Epoch 737 +2025-10-31 01:25:40.940346: Current learning rate: 0.00301 +2025-10-31 01:25:59.976600: train_loss -0.9921 +2025-10-31 01:25:59.980342: val_loss -0.895 +2025-10-31 01:25:59.981833: Pseudo dice [np.float32(0.9842), np.float32(0.9927), np.float32(0.9948), np.float32(0.802)] +2025-10-31 01:25:59.983253: Epoch time: 19.04 s +2025-10-31 01:26:01.014626: +2025-10-31 01:26:01.016497: Epoch 738 +2025-10-31 01:26:01.018491: Current learning rate: 0.003 +2025-10-31 01:26:21.722675: train_loss -0.9924 +2025-10-31 01:26:21.727684: val_loss -0.8993 +2025-10-31 01:26:21.729174: Pseudo dice [np.float32(0.9871), np.float32(0.9929), np.float32(0.995), np.float32(0.8119)] +2025-10-31 01:26:21.730711: Epoch time: 20.71 s +2025-10-31 01:26:23.308290: +2025-10-31 01:26:23.310413: Epoch 739 +2025-10-31 01:26:23.312011: Current learning rate: 0.00299 +2025-10-31 01:26:44.029330: train_loss -0.9922 +2025-10-31 01:26:44.034867: val_loss -0.8902 +2025-10-31 01:26:44.036400: Pseudo dice [np.float32(0.9868), np.float32(0.9924), np.float32(0.994), np.float32(0.7852)] +2025-10-31 01:26:44.039035: Epoch time: 20.72 s +2025-10-31 01:26:44.961900: +2025-10-31 01:26:44.964653: Epoch 740 +2025-10-31 01:26:44.966913: Current learning rate: 0.00297 +2025-10-31 01:27:05.578164: train_loss -0.9924 +2025-10-31 01:27:05.580772: val_loss -0.8878 +2025-10-31 01:27:05.582308: Pseudo dice [np.float32(0.9858), np.float32(0.9924), np.float32(0.9945), np.float32(0.7806)] +2025-10-31 01:27:05.583975: Epoch time: 20.62 s +2025-10-31 01:27:06.682422: +2025-10-31 01:27:06.684454: Epoch 741 +2025-10-31 01:27:06.686334: Current learning rate: 0.00296 +2025-10-31 01:27:27.623054: train_loss -0.9924 +2025-10-31 01:27:27.632702: val_loss -0.8926 +2025-10-31 01:27:27.634280: Pseudo dice [np.float32(0.9869), np.float32(0.9931), np.float32(0.9945), np.float32(0.7869)] +2025-10-31 01:27:27.635736: Epoch time: 20.94 s +2025-10-31 01:27:28.704550: +2025-10-31 01:27:28.708854: Epoch 742 +2025-10-31 01:27:28.711533: Current learning rate: 0.00295 +2025-10-31 01:27:49.516757: train_loss -0.9924 +2025-10-31 01:27:49.521318: val_loss -0.8953 +2025-10-31 01:27:49.523426: Pseudo dice [np.float32(0.9867), np.float32(0.9929), np.float32(0.9949), np.float32(0.796)] +2025-10-31 01:27:49.525429: Epoch time: 20.81 s +2025-10-31 01:27:50.435765: +2025-10-31 01:27:50.437858: Epoch 743 +2025-10-31 01:27:50.439798: Current learning rate: 0.00294 +2025-10-31 01:28:10.441701: train_loss -0.9929 +2025-10-31 01:28:10.453439: val_loss -0.8956 +2025-10-31 01:28:10.455696: Pseudo dice [np.float32(0.9853), np.float32(0.9929), np.float32(0.9948), np.float32(0.8006)] +2025-10-31 01:28:10.457597: Epoch time: 20.01 s +2025-10-31 01:28:11.652618: +2025-10-31 01:28:11.665941: Epoch 744 +2025-10-31 01:28:11.667883: Current learning rate: 0.00293 +2025-10-31 01:28:31.497652: train_loss -0.9924 +2025-10-31 01:28:31.500699: val_loss -0.8942 +2025-10-31 01:28:31.502828: Pseudo dice [np.float32(0.9868), np.float32(0.9929), np.float32(0.9945), np.float32(0.7977)] +2025-10-31 01:28:31.504570: Epoch time: 19.85 s +2025-10-31 01:28:32.534261: +2025-10-31 01:28:32.537242: Epoch 745 +2025-10-31 01:28:32.539582: Current learning rate: 0.00292 +2025-10-31 01:28:53.260080: train_loss -0.9924 +2025-10-31 01:28:53.263628: val_loss -0.895 +2025-10-31 01:28:53.265572: Pseudo dice [np.float32(0.9861), np.float32(0.9928), np.float32(0.9946), np.float32(0.8013)] +2025-10-31 01:28:53.267201: Epoch time: 20.73 s +2025-10-31 01:28:54.315758: +2025-10-31 01:28:54.319567: Epoch 746 +2025-10-31 01:28:54.322545: Current learning rate: 0.00291 +2025-10-31 01:29:15.250472: train_loss -0.9921 +2025-10-31 01:29:15.254310: val_loss -0.8937 +2025-10-31 01:29:15.256424: Pseudo dice [np.float32(0.9863), np.float32(0.9932), np.float32(0.9946), np.float32(0.7973)] +2025-10-31 01:29:15.258356: Epoch time: 20.94 s +2025-10-31 01:29:16.625088: +2025-10-31 01:29:16.627788: Epoch 747 +2025-10-31 01:29:16.630753: Current learning rate: 0.0029 +2025-10-31 01:29:37.248880: train_loss -0.9918 +2025-10-31 01:29:37.263976: val_loss -0.8966 +2025-10-31 01:29:37.266100: Pseudo dice [np.float32(0.9879), np.float32(0.9934), np.float32(0.9945), np.float32(0.7932)] +2025-10-31 01:29:37.268086: Epoch time: 20.63 s +2025-10-31 01:29:38.369468: +2025-10-31 01:29:38.371700: Epoch 748 +2025-10-31 01:29:38.374083: Current learning rate: 0.00289 +2025-10-31 01:29:59.112171: train_loss -0.9917 +2025-10-31 01:29:59.121516: val_loss -0.8996 +2025-10-31 01:29:59.123523: Pseudo dice [np.float32(0.9872), np.float32(0.9933), np.float32(0.9946), np.float32(0.8055)] +2025-10-31 01:29:59.126201: Epoch time: 20.74 s +2025-10-31 01:30:00.310456: +2025-10-31 01:30:00.312055: Epoch 749 +2025-10-31 01:30:00.314513: Current learning rate: 0.00288 +2025-10-31 01:30:19.933482: train_loss -0.9925 +2025-10-31 01:30:19.936735: val_loss -0.8942 +2025-10-31 01:30:19.939844: Pseudo dice [np.float32(0.9877), np.float32(0.994), np.float32(0.9946), np.float32(0.7878)] +2025-10-31 01:30:19.941893: Epoch time: 19.62 s +2025-10-31 01:30:22.477774: +2025-10-31 01:30:22.480623: Epoch 750 +2025-10-31 01:30:22.482717: Current learning rate: 0.00287 +2025-10-31 01:30:43.186605: train_loss -0.9923 +2025-10-31 01:30:43.192118: val_loss -0.897 +2025-10-31 01:30:43.193964: Pseudo dice [np.float32(0.9875), np.float32(0.9937), np.float32(0.995), np.float32(0.7971)] +2025-10-31 01:30:43.195620: Epoch time: 20.71 s +2025-10-31 01:30:44.321642: +2025-10-31 01:30:44.325244: Epoch 751 +2025-10-31 01:30:44.327040: Current learning rate: 0.00286 +2025-10-31 01:31:04.130867: train_loss -0.9925 +2025-10-31 01:31:04.136676: val_loss -0.8905 +2025-10-31 01:31:04.145840: Pseudo dice [np.float32(0.9857), np.float32(0.9926), np.float32(0.9947), np.float32(0.7868)] +2025-10-31 01:31:04.147584: Epoch time: 19.81 s +2025-10-31 01:31:05.219513: +2025-10-31 01:31:05.221601: Epoch 752 +2025-10-31 01:31:05.223190: Current learning rate: 0.00285 +2025-10-31 01:31:26.115513: train_loss -0.9923 +2025-10-31 01:31:26.124883: val_loss -0.8956 +2025-10-31 01:31:26.127991: Pseudo dice [np.float32(0.9879), np.float32(0.9934), np.float32(0.9947), np.float32(0.7972)] +2025-10-31 01:31:26.130867: Epoch time: 20.9 s +2025-10-31 01:31:27.175971: +2025-10-31 01:31:27.179056: Epoch 753 +2025-10-31 01:31:27.180868: Current learning rate: 0.00284 +2025-10-31 01:31:48.283065: train_loss -0.9916 +2025-10-31 01:31:48.294523: val_loss -0.896 +2025-10-31 01:31:48.296301: Pseudo dice [np.float32(0.987), np.float32(0.9935), np.float32(0.9942), np.float32(0.7969)] +2025-10-31 01:31:48.298028: Epoch time: 21.11 s +2025-10-31 01:31:49.682887: +2025-10-31 01:31:49.684922: Epoch 754 +2025-10-31 01:31:49.686742: Current learning rate: 0.00283 +2025-10-31 01:32:10.384767: train_loss -0.9917 +2025-10-31 01:32:10.389246: val_loss -0.8988 +2025-10-31 01:32:10.392510: Pseudo dice [np.float32(0.9856), np.float32(0.9924), np.float32(0.9947), np.float32(0.8117)] +2025-10-31 01:32:10.396001: Epoch time: 20.7 s +2025-10-31 01:32:11.546918: +2025-10-31 01:32:11.551093: Epoch 755 +2025-10-31 01:32:11.552724: Current learning rate: 0.00282 +2025-10-31 01:32:32.189318: train_loss -0.9917 +2025-10-31 01:32:32.197076: val_loss -0.8991 +2025-10-31 01:32:32.200158: Pseudo dice [np.float32(0.9855), np.float32(0.9927), np.float32(0.9947), np.float32(0.8051)] +2025-10-31 01:32:32.203343: Epoch time: 20.64 s +2025-10-31 01:32:33.527593: +2025-10-31 01:32:33.529562: Epoch 756 +2025-10-31 01:32:33.531382: Current learning rate: 0.00281 +2025-10-31 01:32:53.636213: train_loss -0.9924 +2025-10-31 01:32:53.639830: val_loss -0.8916 +2025-10-31 01:32:53.641531: Pseudo dice [np.float32(0.9846), np.float32(0.992), np.float32(0.9943), np.float32(0.7986)] +2025-10-31 01:32:53.642999: Epoch time: 20.11 s +2025-10-31 01:32:54.862841: +2025-10-31 01:32:54.868378: Epoch 757 +2025-10-31 01:32:54.872290: Current learning rate: 0.0028 +2025-10-31 01:33:14.702276: train_loss -0.9921 +2025-10-31 01:33:14.706571: val_loss -0.9025 +2025-10-31 01:33:14.708879: Pseudo dice [np.float32(0.9868), np.float32(0.9927), np.float32(0.9947), np.float32(0.8107)] +2025-10-31 01:33:14.711554: Epoch time: 19.84 s +2025-10-31 01:33:15.825474: +2025-10-31 01:33:15.827890: Epoch 758 +2025-10-31 01:33:15.829630: Current learning rate: 0.00279 +2025-10-31 01:33:36.642951: train_loss -0.9924 +2025-10-31 01:33:36.660455: val_loss -0.9006 +2025-10-31 01:33:36.663011: Pseudo dice [np.float32(0.9865), np.float32(0.9925), np.float32(0.9947), np.float32(0.8136)] +2025-10-31 01:33:36.666095: Epoch time: 20.82 s +2025-10-31 01:33:37.766252: +2025-10-31 01:33:37.768410: Epoch 759 +2025-10-31 01:33:37.770033: Current learning rate: 0.00278 +2025-10-31 01:33:58.761039: train_loss -0.9923 +2025-10-31 01:33:58.767002: val_loss -0.8935 +2025-10-31 01:33:58.770410: Pseudo dice [np.float32(0.9856), np.float32(0.9922), np.float32(0.9941), np.float32(0.7945)] +2025-10-31 01:33:58.774772: Epoch time: 21.0 s +2025-10-31 01:34:00.198685: +2025-10-31 01:34:00.201144: Epoch 760 +2025-10-31 01:34:00.204316: Current learning rate: 0.00277 +2025-10-31 01:34:20.684579: train_loss -0.9919 +2025-10-31 01:34:20.688055: val_loss -0.8913 +2025-10-31 01:34:20.692223: Pseudo dice [np.float32(0.9859), np.float32(0.9926), np.float32(0.9944), np.float32(0.7847)] +2025-10-31 01:34:20.693973: Epoch time: 20.49 s +2025-10-31 01:34:22.170397: +2025-10-31 01:34:22.172467: Epoch 761 +2025-10-31 01:34:22.175438: Current learning rate: 0.00276 +2025-10-31 01:34:42.826144: train_loss -0.9919 +2025-10-31 01:34:42.828884: val_loss -0.8971 +2025-10-31 01:34:42.830787: Pseudo dice [np.float32(0.9856), np.float32(0.9929), np.float32(0.9952), np.float32(0.8018)] +2025-10-31 01:34:42.832841: Epoch time: 20.66 s +2025-10-31 01:34:44.070320: +2025-10-31 01:34:44.072071: Epoch 762 +2025-10-31 01:34:44.073506: Current learning rate: 0.00275 +2025-10-31 01:35:03.922120: train_loss -0.9923 +2025-10-31 01:35:03.926817: val_loss -0.8907 +2025-10-31 01:35:03.929018: Pseudo dice [np.float32(0.9864), np.float32(0.9927), np.float32(0.9947), np.float32(0.789)] +2025-10-31 01:35:03.930524: Epoch time: 19.85 s +2025-10-31 01:35:04.963545: +2025-10-31 01:35:04.965663: Epoch 763 +2025-10-31 01:35:04.967428: Current learning rate: 0.00274 +2025-10-31 01:35:25.594007: train_loss -0.9919 +2025-10-31 01:35:25.597999: val_loss -0.8893 +2025-10-31 01:35:25.599815: Pseudo dice [np.float32(0.9869), np.float32(0.9935), np.float32(0.9945), np.float32(0.7903)] +2025-10-31 01:35:25.601579: Epoch time: 20.63 s +2025-10-31 01:35:26.682263: +2025-10-31 01:35:26.684639: Epoch 764 +2025-10-31 01:35:26.686946: Current learning rate: 0.00273 +2025-10-31 01:35:46.400495: train_loss -0.992 +2025-10-31 01:35:46.404030: val_loss -0.8933 +2025-10-31 01:35:46.406249: Pseudo dice [np.float32(0.9861), np.float32(0.9935), np.float32(0.9948), np.float32(0.7942)] +2025-10-31 01:35:46.408433: Epoch time: 19.72 s +2025-10-31 01:35:47.484464: +2025-10-31 01:35:47.486531: Epoch 765 +2025-10-31 01:35:47.488225: Current learning rate: 0.00272 +2025-10-31 01:36:08.315843: train_loss -0.992 +2025-10-31 01:36:08.319909: val_loss -0.9003 +2025-10-31 01:36:08.322954: Pseudo dice [np.float32(0.986), np.float32(0.9933), np.float32(0.9949), np.float32(0.8122)] +2025-10-31 01:36:08.324901: Epoch time: 20.83 s +2025-10-31 01:36:09.480759: +2025-10-31 01:36:09.482584: Epoch 766 +2025-10-31 01:36:09.484533: Current learning rate: 0.00271 +2025-10-31 01:36:30.455089: train_loss -0.9918 +2025-10-31 01:36:30.459017: val_loss -0.8934 +2025-10-31 01:36:30.460562: Pseudo dice [np.float32(0.9874), np.float32(0.9933), np.float32(0.9945), np.float32(0.7886)] +2025-10-31 01:36:30.462080: Epoch time: 20.98 s +2025-10-31 01:36:31.724846: +2025-10-31 01:36:31.727180: Epoch 767 +2025-10-31 01:36:31.728902: Current learning rate: 0.0027 +2025-10-31 01:36:52.504889: train_loss -0.992 +2025-10-31 01:36:52.511162: val_loss -0.8926 +2025-10-31 01:36:52.512601: Pseudo dice [np.float32(0.9853), np.float32(0.9927), np.float32(0.995), np.float32(0.7978)] +2025-10-31 01:36:52.513967: Epoch time: 20.78 s +2025-10-31 01:36:53.646437: +2025-10-31 01:36:53.648099: Epoch 768 +2025-10-31 01:36:53.649520: Current learning rate: 0.00268 +2025-10-31 01:37:12.876602: train_loss -0.9916 +2025-10-31 01:37:12.879091: val_loss -0.9019 +2025-10-31 01:37:12.882126: Pseudo dice [np.float32(0.9865), np.float32(0.9929), np.float32(0.9951), np.float32(0.8138)] +2025-10-31 01:37:12.884563: Epoch time: 19.23 s +2025-10-31 01:37:13.987481: +2025-10-31 01:37:13.989509: Epoch 769 +2025-10-31 01:37:13.991310: Current learning rate: 0.00267 +2025-10-31 01:37:34.938200: train_loss -0.9927 +2025-10-31 01:37:34.945298: val_loss -0.8986 +2025-10-31 01:37:34.948190: Pseudo dice [np.float32(0.9854), np.float32(0.9925), np.float32(0.9947), np.float32(0.81)] +2025-10-31 01:37:34.953698: Epoch time: 20.95 s +2025-10-31 01:37:36.255853: +2025-10-31 01:37:36.261079: Epoch 770 +2025-10-31 01:37:36.264736: Current learning rate: 0.00266 +2025-10-31 01:37:56.579525: train_loss -0.9928 +2025-10-31 01:37:56.582983: val_loss -0.8974 +2025-10-31 01:37:56.584938: Pseudo dice [np.float32(0.985), np.float32(0.9922), np.float32(0.9946), np.float32(0.8104)] +2025-10-31 01:37:56.587013: Epoch time: 20.33 s +2025-10-31 01:37:57.707506: +2025-10-31 01:37:57.710052: Epoch 771 +2025-10-31 01:37:57.711792: Current learning rate: 0.00265 +2025-10-31 01:38:17.394711: train_loss -0.9927 +2025-10-31 01:38:17.400846: val_loss -0.8973 +2025-10-31 01:38:17.404248: Pseudo dice [np.float32(0.9864), np.float32(0.9921), np.float32(0.9948), np.float32(0.8078)] +2025-10-31 01:38:17.405719: Epoch time: 19.69 s +2025-10-31 01:38:18.528364: +2025-10-31 01:38:18.530169: Epoch 772 +2025-10-31 01:38:18.535282: Current learning rate: 0.00264 +2025-10-31 01:38:39.212633: train_loss -0.9924 +2025-10-31 01:38:39.216664: val_loss -0.8944 +2025-10-31 01:38:39.218959: Pseudo dice [np.float32(0.9863), np.float32(0.9929), np.float32(0.9947), np.float32(0.7985)] +2025-10-31 01:38:39.220785: Epoch time: 20.69 s +2025-10-31 01:38:40.744469: +2025-10-31 01:38:40.747381: Epoch 773 +2025-10-31 01:38:40.749290: Current learning rate: 0.00263 +2025-10-31 01:39:01.116440: train_loss -0.9928 +2025-10-31 01:39:01.120220: val_loss -0.8914 +2025-10-31 01:39:01.123362: Pseudo dice [np.float32(0.9856), np.float32(0.9921), np.float32(0.9946), np.float32(0.7987)] +2025-10-31 01:39:01.124932: Epoch time: 20.37 s +2025-10-31 01:39:02.389004: +2025-10-31 01:39:02.391148: Epoch 774 +2025-10-31 01:39:02.392805: Current learning rate: 0.00262 +2025-10-31 01:39:22.919977: train_loss -0.9926 +2025-10-31 01:39:22.923491: val_loss -0.8931 +2025-10-31 01:39:22.925267: Pseudo dice [np.float32(0.9851), np.float32(0.9917), np.float32(0.9945), np.float32(0.8012)] +2025-10-31 01:39:22.926961: Epoch time: 20.53 s +2025-10-31 01:39:24.240410: +2025-10-31 01:39:24.242576: Epoch 775 +2025-10-31 01:39:24.244958: Current learning rate: 0.00261 +2025-10-31 01:39:43.880654: train_loss -0.9921 +2025-10-31 01:39:43.884151: val_loss -0.8975 +2025-10-31 01:39:43.886248: Pseudo dice [np.float32(0.986), np.float32(0.9922), np.float32(0.9947), np.float32(0.8025)] +2025-10-31 01:39:43.888395: Epoch time: 19.64 s +2025-10-31 01:39:44.903112: +2025-10-31 01:39:44.905531: Epoch 776 +2025-10-31 01:39:44.908172: Current learning rate: 0.0026 +2025-10-31 01:40:05.325343: train_loss -0.9928 +2025-10-31 01:40:05.333984: val_loss -0.8949 +2025-10-31 01:40:05.339954: Pseudo dice [np.float32(0.986), np.float32(0.9925), np.float32(0.9944), np.float32(0.8032)] +2025-10-31 01:40:05.346087: Epoch time: 20.42 s +2025-10-31 01:40:06.415631: +2025-10-31 01:40:06.417420: Epoch 777 +2025-10-31 01:40:06.419324: Current learning rate: 0.00259 +2025-10-31 01:40:26.818811: train_loss -0.9926 +2025-10-31 01:40:26.821656: val_loss -0.8946 +2025-10-31 01:40:26.823290: Pseudo dice [np.float32(0.9854), np.float32(0.9924), np.float32(0.9945), np.float32(0.8042)] +2025-10-31 01:40:26.825499: Epoch time: 20.4 s +2025-10-31 01:40:28.059646: +2025-10-31 01:40:28.063119: Epoch 778 +2025-10-31 01:40:28.064869: Current learning rate: 0.00258 +2025-10-31 01:40:48.068439: train_loss -0.9927 +2025-10-31 01:40:48.073906: val_loss -0.8951 +2025-10-31 01:40:48.075547: Pseudo dice [np.float32(0.9856), np.float32(0.9926), np.float32(0.9945), np.float32(0.8026)] +2025-10-31 01:40:48.077636: Epoch time: 20.01 s +2025-10-31 01:40:49.128946: +2025-10-31 01:40:49.130681: Epoch 779 +2025-10-31 01:40:49.132302: Current learning rate: 0.00257 +2025-10-31 01:41:09.647468: train_loss -0.9924 +2025-10-31 01:41:09.652973: val_loss -0.9017 +2025-10-31 01:41:09.655749: Pseudo dice [np.float32(0.9862), np.float32(0.9936), np.float32(0.995), np.float32(0.8142)] +2025-10-31 01:41:09.657916: Epoch time: 20.52 s +2025-10-31 01:41:10.871219: +2025-10-31 01:41:10.873109: Epoch 780 +2025-10-31 01:41:10.876127: Current learning rate: 0.00256 +2025-10-31 01:41:31.455619: train_loss -0.9924 +2025-10-31 01:41:31.458138: val_loss -0.8997 +2025-10-31 01:41:31.460446: Pseudo dice [np.float32(0.9867), np.float32(0.993), np.float32(0.9946), np.float32(0.8106)] +2025-10-31 01:41:31.462830: Epoch time: 20.59 s +2025-10-31 01:41:32.561656: +2025-10-31 01:41:32.563522: Epoch 781 +2025-10-31 01:41:32.564998: Current learning rate: 0.00255 +2025-10-31 01:41:51.210892: train_loss -0.9931 +2025-10-31 01:41:51.216538: val_loss -0.8956 +2025-10-31 01:41:51.219337: Pseudo dice [np.float32(0.9872), np.float32(0.9933), np.float32(0.9948), np.float32(0.798)] +2025-10-31 01:41:51.222225: Epoch time: 18.65 s +2025-10-31 01:41:52.397071: +2025-10-31 01:41:52.398864: Epoch 782 +2025-10-31 01:41:52.400720: Current learning rate: 0.00254 +2025-10-31 01:42:13.383300: train_loss -0.9927 +2025-10-31 01:42:13.387117: val_loss -0.8987 +2025-10-31 01:42:13.388856: Pseudo dice [np.float32(0.9854), np.float32(0.993), np.float32(0.9949), np.float32(0.815)] +2025-10-31 01:42:13.391294: Epoch time: 20.99 s +2025-10-31 01:42:14.750783: +2025-10-31 01:42:14.752812: Epoch 783 +2025-10-31 01:42:14.754454: Current learning rate: 0.00253 +2025-10-31 01:42:35.151552: train_loss -0.9928 +2025-10-31 01:42:35.155942: val_loss -0.8911 +2025-10-31 01:42:35.157358: Pseudo dice [np.float32(0.9867), np.float32(0.9927), np.float32(0.9942), np.float32(0.7964)] +2025-10-31 01:42:35.158846: Epoch time: 20.4 s +2025-10-31 01:42:36.591127: +2025-10-31 01:42:36.594021: Epoch 784 +2025-10-31 01:42:36.595566: Current learning rate: 0.00252 +2025-10-31 01:42:56.565557: train_loss -0.9926 +2025-10-31 01:42:56.573817: val_loss -0.8965 +2025-10-31 01:42:56.575895: Pseudo dice [np.float32(0.9857), np.float32(0.993), np.float32(0.9949), np.float32(0.8058)] +2025-10-31 01:42:56.577961: Epoch time: 19.98 s +2025-10-31 01:42:57.639702: +2025-10-31 01:42:57.641382: Epoch 785 +2025-10-31 01:42:57.642965: Current learning rate: 0.00251 +2025-10-31 01:43:18.364810: train_loss -0.9927 +2025-10-31 01:43:18.367197: val_loss -0.8938 +2025-10-31 01:43:18.369283: Pseudo dice [np.float32(0.986), np.float32(0.9925), np.float32(0.9944), np.float32(0.7965)] +2025-10-31 01:43:18.371485: Epoch time: 20.73 s +2025-10-31 01:43:19.575023: +2025-10-31 01:43:19.577038: Epoch 786 +2025-10-31 01:43:19.578831: Current learning rate: 0.0025 +2025-10-31 01:43:39.783380: train_loss -0.9932 +2025-10-31 01:43:39.790465: val_loss -0.894 +2025-10-31 01:43:39.795066: Pseudo dice [np.float32(0.986), np.float32(0.9929), np.float32(0.9947), np.float32(0.7984)] +2025-10-31 01:43:39.800735: Epoch time: 20.21 s +2025-10-31 01:43:40.919322: +2025-10-31 01:43:40.921000: Epoch 787 +2025-10-31 01:43:40.922542: Current learning rate: 0.00249 +2025-10-31 01:44:01.290750: train_loss -0.9929 +2025-10-31 01:44:01.295933: val_loss -0.8992 +2025-10-31 01:44:01.300575: Pseudo dice [np.float32(0.9862), np.float32(0.993), np.float32(0.9947), np.float32(0.8027)] +2025-10-31 01:44:01.302243: Epoch time: 20.37 s +2025-10-31 01:44:02.356411: +2025-10-31 01:44:02.358886: Epoch 788 +2025-10-31 01:44:02.360720: Current learning rate: 0.00248 +2025-10-31 01:44:21.610002: train_loss -0.9925 +2025-10-31 01:44:21.613292: val_loss -0.8953 +2025-10-31 01:44:21.614841: Pseudo dice [np.float32(0.9865), np.float32(0.9933), np.float32(0.9947), np.float32(0.795)] +2025-10-31 01:44:21.616299: Epoch time: 19.26 s +2025-10-31 01:44:22.650423: +2025-10-31 01:44:22.652402: Epoch 789 +2025-10-31 01:44:22.653945: Current learning rate: 0.00247 +2025-10-31 01:44:43.183103: train_loss -0.9933 +2025-10-31 01:44:43.188173: val_loss -0.8893 +2025-10-31 01:44:43.189686: Pseudo dice [np.float32(0.9872), np.float32(0.9938), np.float32(0.9943), np.float32(0.7824)] +2025-10-31 01:44:43.191444: Epoch time: 20.53 s +2025-10-31 01:44:44.389136: +2025-10-31 01:44:44.391768: Epoch 790 +2025-10-31 01:44:44.394625: Current learning rate: 0.00245 +2025-10-31 01:45:05.148959: train_loss -0.9931 +2025-10-31 01:45:05.153604: val_loss -0.8928 +2025-10-31 01:45:05.155333: Pseudo dice [np.float32(0.9865), np.float32(0.9932), np.float32(0.9948), np.float32(0.7885)] +2025-10-31 01:45:05.156985: Epoch time: 20.76 s +2025-10-31 01:45:06.421656: +2025-10-31 01:45:06.423605: Epoch 791 +2025-10-31 01:45:06.425387: Current learning rate: 0.00244 +2025-10-31 01:45:26.069602: train_loss -0.9929 +2025-10-31 01:45:26.071485: val_loss -0.8961 +2025-10-31 01:45:26.073003: Pseudo dice [np.float32(0.9866), np.float32(0.993), np.float32(0.9949), np.float32(0.7954)] +2025-10-31 01:45:26.074615: Epoch time: 19.65 s +2025-10-31 01:45:27.152274: +2025-10-31 01:45:27.154473: Epoch 792 +2025-10-31 01:45:27.156338: Current learning rate: 0.00243 +2025-10-31 01:45:47.542507: train_loss -0.9926 +2025-10-31 01:45:47.546514: val_loss -0.8927 +2025-10-31 01:45:47.548332: Pseudo dice [np.float32(0.9861), np.float32(0.9927), np.float32(0.9945), np.float32(0.7961)] +2025-10-31 01:45:47.549828: Epoch time: 20.39 s +2025-10-31 01:45:48.599184: +2025-10-31 01:45:48.607018: Epoch 793 +2025-10-31 01:45:48.617601: Current learning rate: 0.00242 +2025-10-31 01:46:09.085695: train_loss -0.9933 +2025-10-31 01:46:09.097615: val_loss -0.8926 +2025-10-31 01:46:09.102004: Pseudo dice [np.float32(0.9867), np.float32(0.9933), np.float32(0.9945), np.float32(0.7959)] +2025-10-31 01:46:09.106453: Epoch time: 20.49 s +2025-10-31 01:46:10.338756: +2025-10-31 01:46:10.340560: Epoch 794 +2025-10-31 01:46:10.342220: Current learning rate: 0.00241 +2025-10-31 01:46:28.554724: train_loss -0.9925 +2025-10-31 01:46:28.557742: val_loss -0.8903 +2025-10-31 01:46:28.560213: Pseudo dice [np.float32(0.9872), np.float32(0.994), np.float32(0.9947), np.float32(0.7868)] +2025-10-31 01:46:28.563141: Epoch time: 18.22 s +2025-10-31 01:46:29.794230: +2025-10-31 01:46:29.796400: Epoch 795 +2025-10-31 01:46:29.798800: Current learning rate: 0.0024 +2025-10-31 01:46:50.384765: train_loss -0.9928 +2025-10-31 01:46:50.389975: val_loss -0.8981 +2025-10-31 01:46:50.392306: Pseudo dice [np.float32(0.9874), np.float32(0.9933), np.float32(0.9944), np.float32(0.7973)] +2025-10-31 01:46:50.394684: Epoch time: 20.59 s +2025-10-31 01:46:51.896300: +2025-10-31 01:46:51.898630: Epoch 796 +2025-10-31 01:46:51.900691: Current learning rate: 0.00239 +2025-10-31 01:47:12.460105: train_loss -0.9929 +2025-10-31 01:47:12.464194: val_loss -0.8956 +2025-10-31 01:47:12.466108: Pseudo dice [np.float32(0.9871), np.float32(0.9934), np.float32(0.9946), np.float32(0.8001)] +2025-10-31 01:47:12.467694: Epoch time: 20.57 s +2025-10-31 01:47:13.730332: +2025-10-31 01:47:13.732688: Epoch 797 +2025-10-31 01:47:13.735014: Current learning rate: 0.00238 +2025-10-31 01:47:34.102156: train_loss -0.9924 +2025-10-31 01:47:34.112559: val_loss -0.8977 +2025-10-31 01:47:34.115649: Pseudo dice [np.float32(0.9874), np.float32(0.992), np.float32(0.9946), np.float32(0.802)] +2025-10-31 01:47:34.118325: Epoch time: 20.37 s +2025-10-31 01:47:35.278097: +2025-10-31 01:47:35.280416: Epoch 798 +2025-10-31 01:47:35.281919: Current learning rate: 0.00237 +2025-10-31 01:47:54.730396: train_loss -0.9929 +2025-10-31 01:47:54.733412: val_loss -0.895 +2025-10-31 01:47:54.735290: Pseudo dice [np.float32(0.9863), np.float32(0.9928), np.float32(0.9947), np.float32(0.8047)] +2025-10-31 01:47:54.736836: Epoch time: 19.45 s +2025-10-31 01:47:55.844702: +2025-10-31 01:47:55.846767: Epoch 799 +2025-10-31 01:47:55.850490: Current learning rate: 0.00236 +2025-10-31 01:48:16.474121: train_loss -0.993 +2025-10-31 01:48:16.477582: val_loss -0.8953 +2025-10-31 01:48:16.479517: Pseudo dice [np.float32(0.9865), np.float32(0.9926), np.float32(0.9945), np.float32(0.804)] +2025-10-31 01:48:16.481183: Epoch time: 20.63 s +2025-10-31 01:48:19.250760: +2025-10-31 01:48:19.253161: Epoch 800 +2025-10-31 01:48:19.255282: Current learning rate: 0.00235 +2025-10-31 01:48:39.398479: train_loss -0.9933 +2025-10-31 01:48:39.402550: val_loss -0.8949 +2025-10-31 01:48:39.406199: Pseudo dice [np.float32(0.988), np.float32(0.9931), np.float32(0.9946), np.float32(0.8013)] +2025-10-31 01:48:39.410209: Epoch time: 20.15 s +2025-10-31 01:48:40.573486: +2025-10-31 01:48:40.575824: Epoch 801 +2025-10-31 01:48:40.578573: Current learning rate: 0.00234 +2025-10-31 01:49:00.878209: train_loss -0.993 +2025-10-31 01:49:00.882174: val_loss -0.8938 +2025-10-31 01:49:00.884147: Pseudo dice [np.float32(0.9859), np.float32(0.9927), np.float32(0.9941), np.float32(0.7973)] +2025-10-31 01:49:00.885864: Epoch time: 20.31 s +2025-10-31 01:49:02.038525: +2025-10-31 01:49:02.041804: Epoch 802 +2025-10-31 01:49:02.043281: Current learning rate: 0.00233 +2025-10-31 01:49:22.512463: train_loss -0.9932 +2025-10-31 01:49:22.516701: val_loss -0.8923 +2025-10-31 01:49:22.518446: Pseudo dice [np.float32(0.9859), np.float32(0.9926), np.float32(0.9945), np.float32(0.7965)] +2025-10-31 01:49:22.519913: Epoch time: 20.48 s +2025-10-31 01:49:23.747285: +2025-10-31 01:49:23.748828: Epoch 803 +2025-10-31 01:49:23.751015: Current learning rate: 0.00232 +2025-10-31 01:49:44.341715: train_loss -0.9934 +2025-10-31 01:49:44.344916: val_loss -0.9007 +2025-10-31 01:49:44.346453: Pseudo dice [np.float32(0.9879), np.float32(0.9928), np.float32(0.9947), np.float32(0.8174)] +2025-10-31 01:49:44.347954: Epoch time: 20.6 s +2025-10-31 01:49:45.502787: +2025-10-31 01:49:45.504887: Epoch 804 +2025-10-31 01:49:45.507185: Current learning rate: 0.00231 +2025-10-31 01:50:05.815387: train_loss -0.9928 +2025-10-31 01:50:05.818656: val_loss -0.8998 +2025-10-31 01:50:05.820460: Pseudo dice [np.float32(0.9862), np.float32(0.9926), np.float32(0.9949), np.float32(0.8176)] +2025-10-31 01:50:05.822969: Epoch time: 20.31 s +2025-10-31 01:50:07.012797: +2025-10-31 01:50:07.015067: Epoch 805 +2025-10-31 01:50:07.016884: Current learning rate: 0.0023 +2025-10-31 01:50:26.838336: train_loss -0.9928 +2025-10-31 01:50:26.842148: val_loss -0.8999 +2025-10-31 01:50:26.844407: Pseudo dice [np.float32(0.9863), np.float32(0.9928), np.float32(0.9951), np.float32(0.8116)] +2025-10-31 01:50:26.847219: Epoch time: 19.83 s +2025-10-31 01:50:28.114200: +2025-10-31 01:50:28.119152: Epoch 806 +2025-10-31 01:50:28.124058: Current learning rate: 0.00229 +2025-10-31 01:50:48.674708: train_loss -0.9927 +2025-10-31 01:50:48.676600: val_loss -0.8961 +2025-10-31 01:50:48.678526: Pseudo dice [np.float32(0.9866), np.float32(0.9932), np.float32(0.995), np.float32(0.806)] +2025-10-31 01:50:48.680311: Epoch time: 20.56 s +2025-10-31 01:50:50.137568: +2025-10-31 01:50:50.139640: Epoch 807 +2025-10-31 01:50:50.141257: Current learning rate: 0.00228 +2025-10-31 01:51:09.606173: train_loss -0.9935 +2025-10-31 01:51:09.608873: val_loss -0.8903 +2025-10-31 01:51:09.610851: Pseudo dice [np.float32(0.9872), np.float32(0.9923), np.float32(0.9941), np.float32(0.7893)] +2025-10-31 01:51:09.612812: Epoch time: 19.47 s +2025-10-31 01:51:10.691426: +2025-10-31 01:51:10.693912: Epoch 808 +2025-10-31 01:51:10.696960: Current learning rate: 0.00226 +2025-10-31 01:51:31.439944: train_loss -0.9935 +2025-10-31 01:51:31.448330: val_loss -0.8919 +2025-10-31 01:51:31.451657: Pseudo dice [np.float32(0.986), np.float32(0.9932), np.float32(0.9949), np.float32(0.7951)] +2025-10-31 01:51:31.455544: Epoch time: 20.75 s +2025-10-31 01:51:32.727539: +2025-10-31 01:51:32.729829: Epoch 809 +2025-10-31 01:51:32.733085: Current learning rate: 0.00225 +2025-10-31 01:51:53.192970: train_loss -0.9934 +2025-10-31 01:51:53.196157: val_loss -0.8954 +2025-10-31 01:51:53.197761: Pseudo dice [np.float32(0.9863), np.float32(0.9919), np.float32(0.9946), np.float32(0.8023)] +2025-10-31 01:51:53.199283: Epoch time: 20.47 s +2025-10-31 01:51:54.480872: +2025-10-31 01:51:54.483185: Epoch 810 +2025-10-31 01:51:54.485518: Current learning rate: 0.00224 +2025-10-31 01:52:15.201311: train_loss -0.9928 +2025-10-31 01:52:15.206322: val_loss -0.8921 +2025-10-31 01:52:15.207918: Pseudo dice [np.float32(0.9867), np.float32(0.9922), np.float32(0.9944), np.float32(0.7964)] +2025-10-31 01:52:15.209615: Epoch time: 20.72 s +2025-10-31 01:52:16.416457: +2025-10-31 01:52:16.418363: Epoch 811 +2025-10-31 01:52:16.420021: Current learning rate: 0.00223 +2025-10-31 01:52:35.676253: train_loss -0.9926 +2025-10-31 01:52:35.680452: val_loss -0.8941 +2025-10-31 01:52:35.682382: Pseudo dice [np.float32(0.9871), np.float32(0.9935), np.float32(0.9944), np.float32(0.792)] +2025-10-31 01:52:35.684176: Epoch time: 19.26 s +2025-10-31 01:52:36.851670: +2025-10-31 01:52:36.853535: Epoch 812 +2025-10-31 01:52:36.855115: Current learning rate: 0.00222 +2025-10-31 01:52:57.725468: train_loss -0.9927 +2025-10-31 01:52:57.727882: val_loss -0.8955 +2025-10-31 01:52:57.729467: Pseudo dice [np.float32(0.9865), np.float32(0.9929), np.float32(0.9946), np.float32(0.8027)] +2025-10-31 01:52:57.734094: Epoch time: 20.88 s +2025-10-31 01:52:58.798002: +2025-10-31 01:52:58.799830: Epoch 813 +2025-10-31 01:52:58.801615: Current learning rate: 0.00221 +2025-10-31 01:53:18.795060: train_loss -0.9932 +2025-10-31 01:53:18.799371: val_loss -0.897 +2025-10-31 01:53:18.802177: Pseudo dice [np.float32(0.9865), np.float32(0.9932), np.float32(0.995), np.float32(0.8105)] +2025-10-31 01:53:18.805556: Epoch time: 20.0 s +2025-10-31 01:53:20.037784: +2025-10-31 01:53:20.039951: Epoch 814 +2025-10-31 01:53:20.041677: Current learning rate: 0.0022 +2025-10-31 01:53:40.707746: train_loss -0.9932 +2025-10-31 01:53:40.711503: val_loss -0.895 +2025-10-31 01:53:40.713046: Pseudo dice [np.float32(0.9863), np.float32(0.9928), np.float32(0.9943), np.float32(0.797)] +2025-10-31 01:53:40.714717: Epoch time: 20.67 s +2025-10-31 01:53:41.820323: +2025-10-31 01:53:41.822345: Epoch 815 +2025-10-31 01:53:41.823970: Current learning rate: 0.00219 +2025-10-31 01:54:02.579009: train_loss -0.9935 +2025-10-31 01:54:02.581086: val_loss -0.8993 +2025-10-31 01:54:02.582845: Pseudo dice [np.float32(0.9865), np.float32(0.9934), np.float32(0.9947), np.float32(0.8096)] +2025-10-31 01:54:02.584434: Epoch time: 20.76 s +2025-10-31 01:54:03.724324: +2025-10-31 01:54:03.727746: Epoch 816 +2025-10-31 01:54:03.729938: Current learning rate: 0.00218 +2025-10-31 01:54:24.416266: train_loss -0.9928 +2025-10-31 01:54:24.423243: val_loss -0.8965 +2025-10-31 01:54:24.424986: Pseudo dice [np.float32(0.9859), np.float32(0.9928), np.float32(0.9949), np.float32(0.7994)] +2025-10-31 01:54:24.426736: Epoch time: 20.69 s +2025-10-31 01:54:25.643099: +2025-10-31 01:54:25.645527: Epoch 817 +2025-10-31 01:54:25.647257: Current learning rate: 0.00217 +2025-10-31 01:54:46.218144: train_loss -0.9924 +2025-10-31 01:54:46.222707: val_loss -0.8955 +2025-10-31 01:54:46.224735: Pseudo dice [np.float32(0.9857), np.float32(0.9928), np.float32(0.9951), np.float32(0.8052)] +2025-10-31 01:54:46.226613: Epoch time: 20.58 s +2025-10-31 01:54:47.754761: +2025-10-31 01:54:47.756634: Epoch 818 +2025-10-31 01:54:47.758232: Current learning rate: 0.00216 +2025-10-31 01:55:07.367158: train_loss -0.9923 +2025-10-31 01:55:07.370260: val_loss -0.8933 +2025-10-31 01:55:07.372029: Pseudo dice [np.float32(0.9863), np.float32(0.9931), np.float32(0.9946), np.float32(0.7978)] +2025-10-31 01:55:07.374137: Epoch time: 19.61 s +2025-10-31 01:55:08.440373: +2025-10-31 01:55:08.443010: Epoch 819 +2025-10-31 01:55:08.446418: Current learning rate: 0.00215 +2025-10-31 01:55:28.958689: train_loss -0.9928 +2025-10-31 01:55:28.964267: val_loss -0.8906 +2025-10-31 01:55:28.965864: Pseudo dice [np.float32(0.988), np.float32(0.9931), np.float32(0.9946), np.float32(0.7899)] +2025-10-31 01:55:28.967290: Epoch time: 20.52 s +2025-10-31 01:55:30.099550: +2025-10-31 01:55:30.101882: Epoch 820 +2025-10-31 01:55:30.103812: Current learning rate: 0.00214 +2025-10-31 01:55:49.439914: train_loss -0.9931 +2025-10-31 01:55:49.445164: val_loss -0.889 +2025-10-31 01:55:49.446920: Pseudo dice [np.float32(0.9868), np.float32(0.993), np.float32(0.9942), np.float32(0.7887)] +2025-10-31 01:55:49.448861: Epoch time: 19.34 s +2025-10-31 01:55:50.696259: +2025-10-31 01:55:50.698276: Epoch 821 +2025-10-31 01:55:50.699985: Current learning rate: 0.00213 +2025-10-31 01:56:11.073138: train_loss -0.9934 +2025-10-31 01:56:11.078107: val_loss -0.8977 +2025-10-31 01:56:11.080162: Pseudo dice [np.float32(0.9871), np.float32(0.9932), np.float32(0.9945), np.float32(0.8046)] +2025-10-31 01:56:11.082201: Epoch time: 20.38 s +2025-10-31 01:56:12.125170: +2025-10-31 01:56:12.127218: Epoch 822 +2025-10-31 01:56:12.131774: Current learning rate: 0.00212 +2025-10-31 01:56:32.747766: train_loss -0.9937 +2025-10-31 01:56:32.751170: val_loss -0.8906 +2025-10-31 01:56:32.752676: Pseudo dice [np.float32(0.9872), np.float32(0.9933), np.float32(0.9943), np.float32(0.7919)] +2025-10-31 01:56:32.754200: Epoch time: 20.62 s +2025-10-31 01:56:33.777187: +2025-10-31 01:56:33.781125: Epoch 823 +2025-10-31 01:56:33.784333: Current learning rate: 0.0021 +2025-10-31 01:56:54.603318: train_loss -0.9932 +2025-10-31 01:56:54.607627: val_loss -0.8925 +2025-10-31 01:56:54.609508: Pseudo dice [np.float32(0.986), np.float32(0.9923), np.float32(0.9944), np.float32(0.7985)] +2025-10-31 01:56:54.611061: Epoch time: 20.83 s +2025-10-31 01:56:55.658989: +2025-10-31 01:56:55.661017: Epoch 824 +2025-10-31 01:56:55.663345: Current learning rate: 0.00209 +2025-10-31 01:57:16.236638: train_loss -0.9931 +2025-10-31 01:57:16.239606: val_loss -0.8928 +2025-10-31 01:57:16.242116: Pseudo dice [np.float32(0.9876), np.float32(0.9927), np.float32(0.9943), np.float32(0.8018)] +2025-10-31 01:57:16.244864: Epoch time: 20.58 s +2025-10-31 01:57:17.428273: +2025-10-31 01:57:17.435386: Epoch 825 +2025-10-31 01:57:17.442760: Current learning rate: 0.00208 +2025-10-31 01:57:36.643862: train_loss -0.9928 +2025-10-31 01:57:36.648070: val_loss -0.8891 +2025-10-31 01:57:36.650036: Pseudo dice [np.float32(0.985), np.float32(0.9927), np.float32(0.9945), np.float32(0.7918)] +2025-10-31 01:57:36.651736: Epoch time: 19.22 s +2025-10-31 01:57:37.674294: +2025-10-31 01:57:37.676116: Epoch 826 +2025-10-31 01:57:37.677933: Current learning rate: 0.00207 +2025-10-31 01:57:56.997760: train_loss -0.9936 +2025-10-31 01:57:57.004270: val_loss -0.8873 +2025-10-31 01:57:57.006309: Pseudo dice [np.float32(0.9858), np.float32(0.9926), np.float32(0.9942), np.float32(0.7821)] +2025-10-31 01:57:57.008633: Epoch time: 19.32 s +2025-10-31 01:57:58.019083: +2025-10-31 01:57:58.021162: Epoch 827 +2025-10-31 01:57:58.022911: Current learning rate: 0.00206 +2025-10-31 01:58:18.924366: train_loss -0.9927 +2025-10-31 01:58:18.927282: val_loss -0.8963 +2025-10-31 01:58:18.929650: Pseudo dice [np.float32(0.9862), np.float32(0.9933), np.float32(0.9949), np.float32(0.8057)] +2025-10-31 01:58:18.931763: Epoch time: 20.91 s +2025-10-31 01:58:20.136572: +2025-10-31 01:58:20.138973: Epoch 828 +2025-10-31 01:58:20.140799: Current learning rate: 0.00205 +2025-10-31 01:58:40.828099: train_loss -0.9931 +2025-10-31 01:58:40.832862: val_loss -0.8916 +2025-10-31 01:58:40.834908: Pseudo dice [np.float32(0.9868), np.float32(0.9935), np.float32(0.9943), np.float32(0.7931)] +2025-10-31 01:58:40.838070: Epoch time: 20.69 s +2025-10-31 01:58:41.838587: +2025-10-31 01:58:41.840632: Epoch 829 +2025-10-31 01:58:41.842396: Current learning rate: 0.00204 +2025-10-31 01:59:02.509669: train_loss -0.9937 +2025-10-31 01:59:02.513991: val_loss -0.8877 +2025-10-31 01:59:02.515646: Pseudo dice [np.float32(0.9858), np.float32(0.9923), np.float32(0.9945), np.float32(0.786)] +2025-10-31 01:59:02.517357: Epoch time: 20.67 s +2025-10-31 01:59:03.538508: +2025-10-31 01:59:03.541012: Epoch 830 +2025-10-31 01:59:03.542784: Current learning rate: 0.00203 +2025-10-31 01:59:24.347883: train_loss -0.9937 +2025-10-31 01:59:24.353260: val_loss -0.8861 +2025-10-31 01:59:24.355259: Pseudo dice [np.float32(0.9859), np.float32(0.993), np.float32(0.9942), np.float32(0.781)] +2025-10-31 01:59:24.357411: Epoch time: 20.81 s +2025-10-31 01:59:25.994954: +2025-10-31 01:59:25.997394: Epoch 831 +2025-10-31 01:59:25.999256: Current learning rate: 0.00202 +2025-10-31 01:59:46.254783: train_loss -0.993 +2025-10-31 01:59:46.258983: val_loss -0.8889 +2025-10-31 01:59:46.261224: Pseudo dice [np.float32(0.9866), np.float32(0.9924), np.float32(0.9945), np.float32(0.7875)] +2025-10-31 01:59:46.263374: Epoch time: 20.26 s +2025-10-31 01:59:47.389104: +2025-10-31 01:59:47.391465: Epoch 832 +2025-10-31 01:59:47.393724: Current learning rate: 0.00201 +2025-10-31 02:00:06.120524: train_loss -0.9933 +2025-10-31 02:00:06.127939: val_loss -0.8885 +2025-10-31 02:00:06.131886: Pseudo dice [np.float32(0.9861), np.float32(0.9928), np.float32(0.9945), np.float32(0.7892)] +2025-10-31 02:00:06.138612: Epoch time: 18.73 s +2025-10-31 02:00:07.274085: +2025-10-31 02:00:07.277154: Epoch 833 +2025-10-31 02:00:07.279889: Current learning rate: 0.002 +2025-10-31 02:00:27.828290: train_loss -0.9933 +2025-10-31 02:00:27.830625: val_loss -0.9038 +2025-10-31 02:00:27.832219: Pseudo dice [np.float32(0.9875), np.float32(0.9937), np.float32(0.9951), np.float32(0.811)] +2025-10-31 02:00:27.833803: Epoch time: 20.56 s +2025-10-31 02:00:28.953130: +2025-10-31 02:00:28.955223: Epoch 834 +2025-10-31 02:00:28.957640: Current learning rate: 0.00199 +2025-10-31 02:00:49.447010: train_loss -0.9937 +2025-10-31 02:00:49.450200: val_loss -0.8909 +2025-10-31 02:00:49.451899: Pseudo dice [np.float32(0.987), np.float32(0.9933), np.float32(0.995), np.float32(0.7934)] +2025-10-31 02:00:49.453418: Epoch time: 20.5 s +2025-10-31 02:00:50.475219: +2025-10-31 02:00:50.477057: Epoch 835 +2025-10-31 02:00:50.479431: Current learning rate: 0.00198 +2025-10-31 02:01:10.676778: train_loss -0.9934 +2025-10-31 02:01:10.682300: val_loss -0.8919 +2025-10-31 02:01:10.683850: Pseudo dice [np.float32(0.9876), np.float32(0.9933), np.float32(0.9947), np.float32(0.7868)] +2025-10-31 02:01:10.685416: Epoch time: 20.2 s +2025-10-31 02:01:11.733477: +2025-10-31 02:01:11.737212: Epoch 836 +2025-10-31 02:01:11.740172: Current learning rate: 0.00196 +2025-10-31 02:01:32.417681: train_loss -0.9933 +2025-10-31 02:01:32.420062: val_loss -0.8999 +2025-10-31 02:01:32.422674: Pseudo dice [np.float32(0.9877), np.float32(0.9932), np.float32(0.9948), np.float32(0.8132)] +2025-10-31 02:01:32.424093: Epoch time: 20.69 s +2025-10-31 02:01:33.651258: +2025-10-31 02:01:33.653924: Epoch 837 +2025-10-31 02:01:33.656354: Current learning rate: 0.00195 +2025-10-31 02:01:54.142299: train_loss -0.9932 +2025-10-31 02:01:54.148782: val_loss -0.8942 +2025-10-31 02:01:54.150195: Pseudo dice [np.float32(0.9865), np.float32(0.9934), np.float32(0.9948), np.float32(0.7987)] +2025-10-31 02:01:54.151689: Epoch time: 20.49 s +2025-10-31 02:01:55.336304: +2025-10-31 02:01:55.344713: Epoch 838 +2025-10-31 02:01:55.353896: Current learning rate: 0.00194 +2025-10-31 02:02:15.659520: train_loss -0.9934 +2025-10-31 02:02:15.662499: val_loss -0.8924 +2025-10-31 02:02:15.664522: Pseudo dice [np.float32(0.9866), np.float32(0.9929), np.float32(0.9946), np.float32(0.7971)] +2025-10-31 02:02:15.666091: Epoch time: 20.33 s +2025-10-31 02:02:16.718547: +2025-10-31 02:02:16.721665: Epoch 839 +2025-10-31 02:02:16.724028: Current learning rate: 0.00193 +2025-10-31 02:02:35.653367: train_loss -0.9935 +2025-10-31 02:02:35.659514: val_loss -0.893 +2025-10-31 02:02:35.663285: Pseudo dice [np.float32(0.9864), np.float32(0.9931), np.float32(0.9944), np.float32(0.7945)] +2025-10-31 02:02:35.665838: Epoch time: 18.94 s +2025-10-31 02:02:37.005468: +2025-10-31 02:02:37.007394: Epoch 840 +2025-10-31 02:02:37.009008: Current learning rate: 0.00192 +2025-10-31 02:02:57.374057: train_loss -0.9929 +2025-10-31 02:02:57.379530: val_loss -0.8939 +2025-10-31 02:02:57.381180: Pseudo dice [np.float32(0.9864), np.float32(0.9935), np.float32(0.9949), np.float32(0.7978)] +2025-10-31 02:02:57.382601: Epoch time: 20.37 s +2025-10-31 02:02:58.538654: +2025-10-31 02:02:58.540639: Epoch 841 +2025-10-31 02:02:58.542489: Current learning rate: 0.00191 +2025-10-31 02:03:19.374356: train_loss -0.9936 +2025-10-31 02:03:19.381223: val_loss -0.8885 +2025-10-31 02:03:19.382859: Pseudo dice [np.float32(0.9874), np.float32(0.9933), np.float32(0.9949), np.float32(0.7802)] +2025-10-31 02:03:19.384613: Epoch time: 20.84 s +2025-10-31 02:03:20.519354: +2025-10-31 02:03:20.521262: Epoch 842 +2025-10-31 02:03:20.522887: Current learning rate: 0.0019 +2025-10-31 02:03:41.056736: train_loss -0.9933 +2025-10-31 02:03:41.059356: val_loss -0.8965 +2025-10-31 02:03:41.061741: Pseudo dice [np.float32(0.9862), np.float32(0.9935), np.float32(0.9947), np.float32(0.8055)] +2025-10-31 02:03:41.064381: Epoch time: 20.54 s +2025-10-31 02:03:42.515772: +2025-10-31 02:03:42.517722: Epoch 843 +2025-10-31 02:03:42.519638: Current learning rate: 0.00189 +2025-10-31 02:04:03.178385: train_loss -0.9928 +2025-10-31 02:04:03.183232: val_loss -0.9009 +2025-10-31 02:04:03.185639: Pseudo dice [np.float32(0.9861), np.float32(0.9929), np.float32(0.9949), np.float32(0.8183)] +2025-10-31 02:04:03.187537: Epoch time: 20.66 s +2025-10-31 02:04:04.471790: +2025-10-31 02:04:04.477984: Epoch 844 +2025-10-31 02:04:04.482580: Current learning rate: 0.00188 +2025-10-31 02:04:24.703086: train_loss -0.993 +2025-10-31 02:04:24.711167: val_loss -0.8966 +2025-10-31 02:04:24.712795: Pseudo dice [np.float32(0.988), np.float32(0.9932), np.float32(0.9947), np.float32(0.8016)] +2025-10-31 02:04:24.717109: Epoch time: 20.23 s +2025-10-31 02:04:25.879041: +2025-10-31 02:04:25.883503: Epoch 845 +2025-10-31 02:04:25.887900: Current learning rate: 0.00187 +2025-10-31 02:04:43.053191: train_loss -0.9929 +2025-10-31 02:04:43.055696: val_loss -0.8924 +2025-10-31 02:04:43.058264: Pseudo dice [np.float32(0.9873), np.float32(0.9929), np.float32(0.9944), np.float32(0.7905)] +2025-10-31 02:04:43.060356: Epoch time: 17.18 s +2025-10-31 02:04:44.101828: +2025-10-31 02:04:44.103780: Epoch 846 +2025-10-31 02:04:44.105623: Current learning rate: 0.00186 +2025-10-31 02:05:04.892408: train_loss -0.9937 +2025-10-31 02:05:04.895949: val_loss -0.8949 +2025-10-31 02:05:04.899991: Pseudo dice [np.float32(0.9867), np.float32(0.9934), np.float32(0.9947), np.float32(0.7987)] +2025-10-31 02:05:04.904306: Epoch time: 20.79 s +2025-10-31 02:05:06.059746: +2025-10-31 02:05:06.062795: Epoch 847 +2025-10-31 02:05:06.064509: Current learning rate: 0.00185 +2025-10-31 02:05:26.579720: train_loss -0.9934 +2025-10-31 02:05:26.583017: val_loss -0.8849 +2025-10-31 02:05:26.585358: Pseudo dice [np.float32(0.987), np.float32(0.9932), np.float32(0.9943), np.float32(0.7815)] +2025-10-31 02:05:26.587318: Epoch time: 20.52 s +2025-10-31 02:05:27.652951: +2025-10-31 02:05:27.654787: Epoch 848 +2025-10-31 02:05:27.656846: Current learning rate: 0.00184 +2025-10-31 02:05:47.993057: train_loss -0.9931 +2025-10-31 02:05:47.996929: val_loss -0.8953 +2025-10-31 02:05:47.998921: Pseudo dice [np.float32(0.987), np.float32(0.9936), np.float32(0.9947), np.float32(0.801)] +2025-10-31 02:05:48.000621: Epoch time: 20.34 s +2025-10-31 02:05:49.029850: +2025-10-31 02:05:49.031715: Epoch 849 +2025-10-31 02:05:49.033971: Current learning rate: 0.00182 +2025-10-31 02:06:09.642917: train_loss -0.9938 +2025-10-31 02:06:09.646540: val_loss -0.8942 +2025-10-31 02:06:09.648843: Pseudo dice [np.float32(0.9875), np.float32(0.9932), np.float32(0.9946), np.float32(0.8022)] +2025-10-31 02:06:09.652020: Epoch time: 20.61 s +2025-10-31 02:06:12.255950: +2025-10-31 02:06:12.258205: Epoch 850 +2025-10-31 02:06:12.260581: Current learning rate: 0.00181 +2025-10-31 02:06:32.913044: train_loss -0.9931 +2025-10-31 02:06:32.925128: val_loss -0.8955 +2025-10-31 02:06:32.932013: Pseudo dice [np.float32(0.9872), np.float32(0.9939), np.float32(0.9952), np.float32(0.8038)] +2025-10-31 02:06:32.937859: Epoch time: 20.66 s +2025-10-31 02:06:33.968040: +2025-10-31 02:06:33.969843: Epoch 851 +2025-10-31 02:06:33.972036: Current learning rate: 0.0018 +2025-10-31 02:06:54.405969: train_loss -0.9932 +2025-10-31 02:06:54.415235: val_loss -0.8946 +2025-10-31 02:06:54.423686: Pseudo dice [np.float32(0.9874), np.float32(0.9934), np.float32(0.9946), np.float32(0.8022)] +2025-10-31 02:06:54.430419: Epoch time: 20.44 s +2025-10-31 02:06:55.681224: +2025-10-31 02:06:55.683298: Epoch 852 +2025-10-31 02:06:55.686519: Current learning rate: 0.00179 +2025-10-31 02:07:14.067884: train_loss -0.9931 +2025-10-31 02:07:14.072740: val_loss -0.8925 +2025-10-31 02:07:14.074305: Pseudo dice [np.float32(0.9881), np.float32(0.9936), np.float32(0.9948), np.float32(0.7922)] +2025-10-31 02:07:14.075752: Epoch time: 18.39 s +2025-10-31 02:07:15.154652: +2025-10-31 02:07:15.156794: Epoch 853 +2025-10-31 02:07:15.158227: Current learning rate: 0.00178 +2025-10-31 02:07:35.858148: train_loss -0.9934 +2025-10-31 02:07:35.862082: val_loss -0.8902 +2025-10-31 02:07:35.864401: Pseudo dice [np.float32(0.9874), np.float32(0.9933), np.float32(0.9942), np.float32(0.7888)] +2025-10-31 02:07:35.867272: Epoch time: 20.71 s +2025-10-31 02:07:36.924066: +2025-10-31 02:07:36.925801: Epoch 854 +2025-10-31 02:07:36.927675: Current learning rate: 0.00177 +2025-10-31 02:07:57.622674: train_loss -0.9931 +2025-10-31 02:07:57.625249: val_loss -0.9011 +2025-10-31 02:07:57.626911: Pseudo dice [np.float32(0.9867), np.float32(0.994), np.float32(0.9952), np.float32(0.8216)] +2025-10-31 02:07:57.629048: Epoch time: 20.7 s +2025-10-31 02:07:58.929483: +2025-10-31 02:07:58.931765: Epoch 855 +2025-10-31 02:07:58.933534: Current learning rate: 0.00176 +2025-10-31 02:08:19.418350: train_loss -0.9936 +2025-10-31 02:08:19.423430: val_loss -0.8917 +2025-10-31 02:08:19.426067: Pseudo dice [np.float32(0.9875), np.float32(0.9943), np.float32(0.9949), np.float32(0.7882)] +2025-10-31 02:08:19.427886: Epoch time: 20.49 s +2025-10-31 02:08:20.626525: +2025-10-31 02:08:20.629302: Epoch 856 +2025-10-31 02:08:20.631684: Current learning rate: 0.00175 +2025-10-31 02:08:41.189964: train_loss -0.9933 +2025-10-31 02:08:41.192299: val_loss -0.8963 +2025-10-31 02:08:41.193936: Pseudo dice [np.float32(0.9868), np.float32(0.9929), np.float32(0.9946), np.float32(0.8087)] +2025-10-31 02:08:41.195494: Epoch time: 20.56 s +2025-10-31 02:08:42.438675: +2025-10-31 02:08:42.441604: Epoch 857 +2025-10-31 02:08:42.444052: Current learning rate: 0.00174 +2025-10-31 02:09:03.279074: train_loss -0.9933 +2025-10-31 02:09:03.284557: val_loss -0.8971 +2025-10-31 02:09:03.286505: Pseudo dice [np.float32(0.986), np.float32(0.9932), np.float32(0.9949), np.float32(0.7965)] +2025-10-31 02:09:03.288042: Epoch time: 20.84 s +2025-10-31 02:09:04.318830: +2025-10-31 02:09:04.320650: Epoch 858 +2025-10-31 02:09:04.322357: Current learning rate: 0.00173 +2025-10-31 02:09:24.098506: train_loss -0.9905 +2025-10-31 02:09:24.104133: val_loss -0.8949 +2025-10-31 02:09:24.107833: Pseudo dice [np.float32(0.9855), np.float32(0.9924), np.float32(0.9945), np.float32(0.8021)] +2025-10-31 02:09:24.111926: Epoch time: 19.78 s +2025-10-31 02:09:25.321327: +2025-10-31 02:09:25.324020: Epoch 859 +2025-10-31 02:09:25.325822: Current learning rate: 0.00172 +2025-10-31 02:09:44.938648: train_loss -0.9921 +2025-10-31 02:09:44.942784: val_loss -0.8922 +2025-10-31 02:09:44.944470: Pseudo dice [np.float32(0.985), np.float32(0.9929), np.float32(0.9947), np.float32(0.8007)] +2025-10-31 02:09:44.946093: Epoch time: 19.62 s +2025-10-31 02:09:46.168133: +2025-10-31 02:09:46.171021: Epoch 860 +2025-10-31 02:09:46.173259: Current learning rate: 0.0017 +2025-10-31 02:10:07.159996: train_loss -0.9927 +2025-10-31 02:10:07.163927: val_loss -0.8935 +2025-10-31 02:10:07.166058: Pseudo dice [np.float32(0.9873), np.float32(0.9929), np.float32(0.9943), np.float32(0.7903)] +2025-10-31 02:10:07.169717: Epoch time: 20.99 s +2025-10-31 02:10:08.172670: +2025-10-31 02:10:08.178021: Epoch 861 +2025-10-31 02:10:08.182169: Current learning rate: 0.00169 +2025-10-31 02:10:28.849611: train_loss -0.9931 +2025-10-31 02:10:28.855760: val_loss -0.9014 +2025-10-31 02:10:28.857478: Pseudo dice [np.float32(0.9866), np.float32(0.9932), np.float32(0.9948), np.float32(0.8141)] +2025-10-31 02:10:28.859303: Epoch time: 20.68 s +2025-10-31 02:10:29.880560: +2025-10-31 02:10:29.883123: Epoch 862 +2025-10-31 02:10:29.884922: Current learning rate: 0.00168 +2025-10-31 02:10:50.500579: train_loss -0.9928 +2025-10-31 02:10:50.514214: val_loss -0.892 +2025-10-31 02:10:50.522251: Pseudo dice [np.float32(0.9874), np.float32(0.9939), np.float32(0.9946), np.float32(0.7904)] +2025-10-31 02:10:50.528335: Epoch time: 20.62 s +2025-10-31 02:10:51.548636: +2025-10-31 02:10:51.551331: Epoch 863 +2025-10-31 02:10:51.554063: Current learning rate: 0.00167 +2025-10-31 02:11:12.221826: train_loss -0.9935 +2025-10-31 02:11:12.223712: val_loss -0.8905 +2025-10-31 02:11:12.226025: Pseudo dice [np.float32(0.987), np.float32(0.9934), np.float32(0.9944), np.float32(0.7881)] +2025-10-31 02:11:12.228188: Epoch time: 20.67 s +2025-10-31 02:11:13.382129: +2025-10-31 02:11:13.383922: Epoch 864 +2025-10-31 02:11:13.385541: Current learning rate: 0.00166 +2025-10-31 02:11:33.805114: train_loss -0.9936 +2025-10-31 02:11:33.807495: val_loss -0.8932 +2025-10-31 02:11:33.810587: Pseudo dice [np.float32(0.9865), np.float32(0.993), np.float32(0.9946), np.float32(0.7965)] +2025-10-31 02:11:33.812859: Epoch time: 20.42 s +2025-10-31 02:11:34.920546: +2025-10-31 02:11:34.922189: Epoch 865 +2025-10-31 02:11:34.923989: Current learning rate: 0.00165 +2025-10-31 02:11:54.555564: train_loss -0.9936 +2025-10-31 02:11:54.560235: val_loss -0.9029 +2025-10-31 02:11:54.562956: Pseudo dice [np.float32(0.9866), np.float32(0.9938), np.float32(0.995), np.float32(0.8171)] +2025-10-31 02:11:54.565996: Epoch time: 19.64 s +2025-10-31 02:11:55.661022: +2025-10-31 02:11:55.664832: Epoch 866 +2025-10-31 02:11:55.667520: Current learning rate: 0.00164 +2025-10-31 02:12:16.172637: train_loss -0.9935 +2025-10-31 02:12:16.175968: val_loss -0.8912 +2025-10-31 02:12:16.177678: Pseudo dice [np.float32(0.9861), np.float32(0.9927), np.float32(0.9944), np.float32(0.7925)] +2025-10-31 02:12:16.179674: Epoch time: 20.51 s +2025-10-31 02:12:17.349872: +2025-10-31 02:12:17.352041: Epoch 867 +2025-10-31 02:12:17.353754: Current learning rate: 0.00163 +2025-10-31 02:12:38.091940: train_loss -0.9928 +2025-10-31 02:12:38.096299: val_loss -0.8939 +2025-10-31 02:12:38.098432: Pseudo dice [np.float32(0.9871), np.float32(0.9931), np.float32(0.9944), np.float32(0.7959)] +2025-10-31 02:12:38.100305: Epoch time: 20.74 s +2025-10-31 02:12:39.941307: +2025-10-31 02:12:39.943670: Epoch 868 +2025-10-31 02:12:39.945543: Current learning rate: 0.00162 +2025-10-31 02:13:00.377300: train_loss -0.9933 +2025-10-31 02:13:00.379999: val_loss -0.896 +2025-10-31 02:13:00.382029: Pseudo dice [np.float32(0.9874), np.float32(0.9938), np.float32(0.9948), np.float32(0.8066)] +2025-10-31 02:13:00.384074: Epoch time: 20.44 s +2025-10-31 02:13:01.386481: +2025-10-31 02:13:01.388589: Epoch 869 +2025-10-31 02:13:01.390421: Current learning rate: 0.00161 +2025-10-31 02:13:21.818871: train_loss -0.9934 +2025-10-31 02:13:21.822278: val_loss -0.8906 +2025-10-31 02:13:21.825157: Pseudo dice [np.float32(0.9868), np.float32(0.9934), np.float32(0.9944), np.float32(0.7882)] +2025-10-31 02:13:21.827090: Epoch time: 20.43 s +2025-10-31 02:13:22.863499: +2025-10-31 02:13:22.865480: Epoch 870 +2025-10-31 02:13:22.867303: Current learning rate: 0.00159 +2025-10-31 02:13:43.572013: train_loss -0.9934 +2025-10-31 02:13:43.576581: val_loss -0.8994 +2025-10-31 02:13:43.578585: Pseudo dice [np.float32(0.9868), np.float32(0.9934), np.float32(0.9949), np.float32(0.8093)] +2025-10-31 02:13:43.580333: Epoch time: 20.71 s +2025-10-31 02:13:44.948062: +2025-10-31 02:13:44.950085: Epoch 871 +2025-10-31 02:13:44.951645: Current learning rate: 0.00158 +2025-10-31 02:14:04.486130: train_loss -0.9932 +2025-10-31 02:14:04.495489: val_loss -0.8926 +2025-10-31 02:14:04.497475: Pseudo dice [np.float32(0.9858), np.float32(0.9928), np.float32(0.9948), np.float32(0.7941)] +2025-10-31 02:14:04.499391: Epoch time: 19.54 s +2025-10-31 02:14:05.577696: +2025-10-31 02:14:05.580268: Epoch 872 +2025-10-31 02:14:05.582916: Current learning rate: 0.00157 +2025-10-31 02:14:25.073526: train_loss -0.9929 +2025-10-31 02:14:25.078589: val_loss -0.8982 +2025-10-31 02:14:25.081458: Pseudo dice [np.float32(0.9882), np.float32(0.9941), np.float32(0.9948), np.float32(0.8018)] +2025-10-31 02:14:25.083199: Epoch time: 19.5 s +2025-10-31 02:14:26.127639: +2025-10-31 02:14:26.129539: Epoch 873 +2025-10-31 02:14:26.131487: Current learning rate: 0.00156 +2025-10-31 02:14:46.633069: train_loss -0.9934 +2025-10-31 02:14:46.637604: val_loss -0.8929 +2025-10-31 02:14:46.640271: Pseudo dice [np.float32(0.9875), np.float32(0.9934), np.float32(0.9945), np.float32(0.7921)] +2025-10-31 02:14:46.642833: Epoch time: 20.51 s +2025-10-31 02:14:47.766817: +2025-10-31 02:14:47.769922: Epoch 874 +2025-10-31 02:14:47.772052: Current learning rate: 0.00155 +2025-10-31 02:15:08.386910: train_loss -0.9933 +2025-10-31 02:15:08.389850: val_loss -0.892 +2025-10-31 02:15:08.391766: Pseudo dice [np.float32(0.9868), np.float32(0.9932), np.float32(0.9948), np.float32(0.7933)] +2025-10-31 02:15:08.396947: Epoch time: 20.62 s +2025-10-31 02:15:09.705486: +2025-10-31 02:15:09.707718: Epoch 875 +2025-10-31 02:15:09.709853: Current learning rate: 0.00154 +2025-10-31 02:15:30.443108: train_loss -0.9929 +2025-10-31 02:15:30.446171: val_loss -0.8928 +2025-10-31 02:15:30.447875: Pseudo dice [np.float32(0.986), np.float32(0.9925), np.float32(0.9945), np.float32(0.7995)] +2025-10-31 02:15:30.449526: Epoch time: 20.74 s +2025-10-31 02:15:31.633137: +2025-10-31 02:15:31.635678: Epoch 876 +2025-10-31 02:15:31.637300: Current learning rate: 0.00153 +2025-10-31 02:15:52.217978: train_loss -0.9934 +2025-10-31 02:15:52.222953: val_loss -0.893 +2025-10-31 02:15:52.225028: Pseudo dice [np.float32(0.9868), np.float32(0.9942), np.float32(0.9949), np.float32(0.7923)] +2025-10-31 02:15:52.226623: Epoch time: 20.59 s +2025-10-31 02:15:53.239310: +2025-10-31 02:15:53.241333: Epoch 877 +2025-10-31 02:15:53.242965: Current learning rate: 0.00152 +2025-10-31 02:16:12.665689: train_loss -0.9933 +2025-10-31 02:16:12.669972: val_loss -0.89 +2025-10-31 02:16:12.671737: Pseudo dice [np.float32(0.987), np.float32(0.9938), np.float32(0.9944), np.float32(0.7905)] +2025-10-31 02:16:12.673589: Epoch time: 19.43 s +2025-10-31 02:16:13.847203: +2025-10-31 02:16:13.849216: Epoch 878 +2025-10-31 02:16:13.851876: Current learning rate: 0.00151 +2025-10-31 02:16:34.398781: train_loss -0.9937 +2025-10-31 02:16:34.402307: val_loss -0.8969 +2025-10-31 02:16:34.404254: Pseudo dice [np.float32(0.9868), np.float32(0.9937), np.float32(0.9949), np.float32(0.8072)] +2025-10-31 02:16:34.405955: Epoch time: 20.55 s +2025-10-31 02:16:35.495685: +2025-10-31 02:16:35.497462: Epoch 879 +2025-10-31 02:16:35.499055: Current learning rate: 0.00149 +2025-10-31 02:16:55.136489: train_loss -0.9937 +2025-10-31 02:16:55.140370: val_loss -0.8908 +2025-10-31 02:16:55.142699: Pseudo dice [np.float32(0.9877), np.float32(0.9936), np.float32(0.9947), np.float32(0.7933)] +2025-10-31 02:16:55.144450: Epoch time: 19.64 s +2025-10-31 02:16:56.509265: +2025-10-31 02:16:56.511580: Epoch 880 +2025-10-31 02:16:56.513395: Current learning rate: 0.00148 +2025-10-31 02:17:16.921042: train_loss -0.9937 +2025-10-31 02:17:16.924320: val_loss -0.8926 +2025-10-31 02:17:16.926007: Pseudo dice [np.float32(0.9866), np.float32(0.9933), np.float32(0.9944), np.float32(0.7985)] +2025-10-31 02:17:16.927540: Epoch time: 20.41 s +2025-10-31 02:17:18.021321: +2025-10-31 02:17:18.023306: Epoch 881 +2025-10-31 02:17:18.025284: Current learning rate: 0.00147 +2025-10-31 02:17:38.630186: train_loss -0.9936 +2025-10-31 02:17:38.635180: val_loss -0.8882 +2025-10-31 02:17:38.637519: Pseudo dice [np.float32(0.9861), np.float32(0.9935), np.float32(0.9947), np.float32(0.7917)] +2025-10-31 02:17:38.639629: Epoch time: 20.61 s +2025-10-31 02:17:39.891388: +2025-10-31 02:17:39.893233: Epoch 882 +2025-10-31 02:17:39.895071: Current learning rate: 0.00146 +2025-10-31 02:17:59.881659: train_loss -0.9937 +2025-10-31 02:17:59.886602: val_loss -0.8988 +2025-10-31 02:17:59.888329: Pseudo dice [np.float32(0.9873), np.float32(0.9937), np.float32(0.9949), np.float32(0.8097)] +2025-10-31 02:17:59.890290: Epoch time: 19.99 s +2025-10-31 02:18:01.003481: +2025-10-31 02:18:01.007045: Epoch 883 +2025-10-31 02:18:01.009090: Current learning rate: 0.00145 +2025-10-31 02:18:20.277018: train_loss -0.9936 +2025-10-31 02:18:20.290268: val_loss -0.8988 +2025-10-31 02:18:20.295926: Pseudo dice [np.float32(0.9867), np.float32(0.9943), np.float32(0.9954), np.float32(0.811)] +2025-10-31 02:18:20.299668: Epoch time: 19.28 s +2025-10-31 02:18:21.482447: +2025-10-31 02:18:21.485152: Epoch 884 +2025-10-31 02:18:21.487016: Current learning rate: 0.00144 +2025-10-31 02:18:39.790476: train_loss -0.9932 +2025-10-31 02:18:39.794406: val_loss -0.8986 +2025-10-31 02:18:39.796430: Pseudo dice [np.float32(0.9872), np.float32(0.994), np.float32(0.995), np.float32(0.8042)] +2025-10-31 02:18:39.798133: Epoch time: 18.31 s +2025-10-31 02:18:40.833360: +2025-10-31 02:18:40.835200: Epoch 885 +2025-10-31 02:18:40.836769: Current learning rate: 0.00143 +2025-10-31 02:19:01.364014: train_loss -0.9935 +2025-10-31 02:19:01.368443: val_loss -0.8872 +2025-10-31 02:19:01.373195: Pseudo dice [np.float32(0.9864), np.float32(0.9927), np.float32(0.9942), np.float32(0.7844)] +2025-10-31 02:19:01.374782: Epoch time: 20.53 s +2025-10-31 02:19:02.461469: +2025-10-31 02:19:02.463523: Epoch 886 +2025-10-31 02:19:02.466311: Current learning rate: 0.00142 +2025-10-31 02:19:22.666977: train_loss -0.9938 +2025-10-31 02:19:22.672418: val_loss -0.8934 +2025-10-31 02:19:22.674163: Pseudo dice [np.float32(0.9863), np.float32(0.9932), np.float32(0.9943), np.float32(0.802)] +2025-10-31 02:19:22.675822: Epoch time: 20.21 s +2025-10-31 02:19:23.894794: +2025-10-31 02:19:23.897007: Epoch 887 +2025-10-31 02:19:23.898750: Current learning rate: 0.00141 +2025-10-31 02:19:44.511056: train_loss -0.994 +2025-10-31 02:19:44.513767: val_loss -0.8933 +2025-10-31 02:19:44.516182: Pseudo dice [np.float32(0.9869), np.float32(0.9939), np.float32(0.9947), np.float32(0.7945)] +2025-10-31 02:19:44.518950: Epoch time: 20.62 s +2025-10-31 02:19:45.613582: +2025-10-31 02:19:45.615765: Epoch 888 +2025-10-31 02:19:45.617334: Current learning rate: 0.00139 +2025-10-31 02:20:06.057462: train_loss -0.9943 +2025-10-31 02:20:06.062083: val_loss -0.8924 +2025-10-31 02:20:06.064415: Pseudo dice [np.float32(0.9874), np.float32(0.9936), np.float32(0.9947), np.float32(0.7956)] +2025-10-31 02:20:06.066275: Epoch time: 20.45 s +2025-10-31 02:20:07.201064: +2025-10-31 02:20:07.202994: Epoch 889 +2025-10-31 02:20:07.205768: Current learning rate: 0.00138 +2025-10-31 02:20:27.918303: train_loss -0.9936 +2025-10-31 02:20:27.921827: val_loss -0.8947 +2025-10-31 02:20:27.925889: Pseudo dice [np.float32(0.9869), np.float32(0.9933), np.float32(0.9948), np.float32(0.8045)] +2025-10-31 02:20:27.929284: Epoch time: 20.72 s +2025-10-31 02:20:29.100572: +2025-10-31 02:20:29.102835: Epoch 890 +2025-10-31 02:20:29.105265: Current learning rate: 0.00137 +2025-10-31 02:20:48.762939: train_loss -0.9939 +2025-10-31 02:20:48.765280: val_loss -0.8958 +2025-10-31 02:20:48.767035: Pseudo dice [np.float32(0.9865), np.float32(0.993), np.float32(0.9949), np.float32(0.8065)] +2025-10-31 02:20:48.769934: Epoch time: 19.66 s +2025-10-31 02:20:49.841393: +2025-10-31 02:20:49.843766: Epoch 891 +2025-10-31 02:20:49.847076: Current learning rate: 0.00136 +2025-10-31 02:21:10.609357: train_loss -0.9939 +2025-10-31 02:21:10.616778: val_loss -0.8939 +2025-10-31 02:21:10.620394: Pseudo dice [np.float32(0.9867), np.float32(0.9937), np.float32(0.9946), np.float32(0.8011)] +2025-10-31 02:21:10.622322: Epoch time: 20.77 s +2025-10-31 02:21:11.636466: +2025-10-31 02:21:11.638561: Epoch 892 +2025-10-31 02:21:11.640497: Current learning rate: 0.00135 +2025-10-31 02:21:32.465683: train_loss -0.9941 +2025-10-31 02:21:32.470053: val_loss -0.8991 +2025-10-31 02:21:32.471863: Pseudo dice [np.float32(0.9878), np.float32(0.9933), np.float32(0.9944), np.float32(0.8094)] +2025-10-31 02:21:32.473388: Epoch time: 20.83 s +2025-10-31 02:21:33.959654: +2025-10-31 02:21:33.962988: Epoch 893 +2025-10-31 02:21:33.966653: Current learning rate: 0.00134 +2025-10-31 02:21:53.964690: train_loss -0.9937 +2025-10-31 02:21:53.968992: val_loss -0.8903 +2025-10-31 02:21:53.971127: Pseudo dice [np.float32(0.9869), np.float32(0.9933), np.float32(0.9946), np.float32(0.7917)] +2025-10-31 02:21:53.973551: Epoch time: 20.01 s +2025-10-31 02:21:55.274322: +2025-10-31 02:21:55.276384: Epoch 894 +2025-10-31 02:21:55.278036: Current learning rate: 0.00133 +2025-10-31 02:22:15.703932: train_loss -0.994 +2025-10-31 02:22:15.710196: val_loss -0.8941 +2025-10-31 02:22:15.713012: Pseudo dice [np.float32(0.9869), np.float32(0.9942), np.float32(0.995), np.float32(0.8015)] +2025-10-31 02:22:15.716187: Epoch time: 20.43 s +2025-10-31 02:22:16.880449: +2025-10-31 02:22:16.883483: Epoch 895 +2025-10-31 02:22:16.886309: Current learning rate: 0.00132 +2025-10-31 02:22:37.687578: train_loss -0.9937 +2025-10-31 02:22:37.693299: val_loss -0.8927 +2025-10-31 02:22:37.695161: Pseudo dice [np.float32(0.9867), np.float32(0.9936), np.float32(0.9949), np.float32(0.8004)] +2025-10-31 02:22:37.696713: Epoch time: 20.81 s +2025-10-31 02:22:38.855904: +2025-10-31 02:22:38.861638: Epoch 896 +2025-10-31 02:22:38.865671: Current learning rate: 0.0013 +2025-10-31 02:22:59.476466: train_loss -0.9939 +2025-10-31 02:22:59.479156: val_loss -0.8876 +2025-10-31 02:22:59.480856: Pseudo dice [np.float32(0.9864), np.float32(0.9933), np.float32(0.9946), np.float32(0.7881)] +2025-10-31 02:22:59.482550: Epoch time: 20.62 s +2025-10-31 02:23:00.750334: +2025-10-31 02:23:00.753155: Epoch 897 +2025-10-31 02:23:00.754968: Current learning rate: 0.00129 +2025-10-31 02:23:20.764960: train_loss -0.9945 +2025-10-31 02:23:20.769862: val_loss -0.8984 +2025-10-31 02:23:20.772807: Pseudo dice [np.float32(0.9861), np.float32(0.9936), np.float32(0.9954), np.float32(0.8092)] +2025-10-31 02:23:20.775487: Epoch time: 20.02 s +2025-10-31 02:23:21.822782: +2025-10-31 02:23:21.825538: Epoch 898 +2025-10-31 02:23:21.827485: Current learning rate: 0.00128 +2025-10-31 02:23:42.577384: train_loss -0.994 +2025-10-31 02:23:42.594536: val_loss -0.8919 +2025-10-31 02:23:42.602476: Pseudo dice [np.float32(0.9876), np.float32(0.9934), np.float32(0.9945), np.float32(0.7979)] +2025-10-31 02:23:42.608824: Epoch time: 20.76 s +2025-10-31 02:23:43.783446: +2025-10-31 02:23:43.785296: Epoch 899 +2025-10-31 02:23:43.786937: Current learning rate: 0.00127 +2025-10-31 02:24:03.700856: train_loss -0.9937 +2025-10-31 02:24:03.703274: val_loss -0.8955 +2025-10-31 02:24:03.705535: Pseudo dice [np.float32(0.9859), np.float32(0.9931), np.float32(0.9949), np.float32(0.8076)] +2025-10-31 02:24:03.707459: Epoch time: 19.92 s +2025-10-31 02:24:06.312170: +2025-10-31 02:24:06.314002: Epoch 900 +2025-10-31 02:24:06.315412: Current learning rate: 0.00126 +2025-10-31 02:24:26.855834: train_loss -0.9939 +2025-10-31 02:24:26.859992: val_loss -0.8968 +2025-10-31 02:24:26.863110: Pseudo dice [np.float32(0.9873), np.float32(0.9933), np.float32(0.9948), np.float32(0.8084)] +2025-10-31 02:24:26.865911: Epoch time: 20.55 s +2025-10-31 02:24:27.939649: +2025-10-31 02:24:27.942567: Epoch 901 +2025-10-31 02:24:27.944993: Current learning rate: 0.00125 +2025-10-31 02:24:48.535951: train_loss -0.9944 +2025-10-31 02:24:48.540144: val_loss -0.8989 +2025-10-31 02:24:48.542291: Pseudo dice [np.float32(0.9873), np.float32(0.9934), np.float32(0.9946), np.float32(0.8129)] +2025-10-31 02:24:48.544522: Epoch time: 20.6 s +2025-10-31 02:24:49.566550: +2025-10-31 02:24:49.568473: Epoch 902 +2025-10-31 02:24:49.570082: Current learning rate: 0.00124 +2025-10-31 02:25:10.080466: train_loss -0.9936 +2025-10-31 02:25:10.084523: val_loss -0.8938 +2025-10-31 02:25:10.086386: Pseudo dice [np.float32(0.9875), np.float32(0.9934), np.float32(0.9949), np.float32(0.8024)] +2025-10-31 02:25:10.088939: Epoch time: 20.52 s +2025-10-31 02:25:11.312131: +2025-10-31 02:25:11.314014: Epoch 903 +2025-10-31 02:25:11.316031: Current learning rate: 0.00122 +2025-10-31 02:25:31.747779: train_loss -0.9939 +2025-10-31 02:25:31.753392: val_loss -0.8968 +2025-10-31 02:25:31.755324: Pseudo dice [np.float32(0.9876), np.float32(0.9939), np.float32(0.9949), np.float32(0.8064)] +2025-10-31 02:25:31.757209: Epoch time: 20.44 s +2025-10-31 02:25:32.956376: +2025-10-31 02:25:32.958856: Epoch 904 +2025-10-31 02:25:32.960841: Current learning rate: 0.00121 +2025-10-31 02:25:53.557383: train_loss -0.9944 +2025-10-31 02:25:53.559805: val_loss -0.8969 +2025-10-31 02:25:53.561144: Pseudo dice [np.float32(0.9861), np.float32(0.993), np.float32(0.9949), np.float32(0.8102)] +2025-10-31 02:25:53.562544: Epoch time: 20.6 s +2025-10-31 02:25:54.744294: +2025-10-31 02:25:54.746413: Epoch 905 +2025-10-31 02:25:54.748472: Current learning rate: 0.0012 +2025-10-31 02:26:15.485580: train_loss -0.9939 +2025-10-31 02:26:15.489872: val_loss -0.895 +2025-10-31 02:26:15.492252: Pseudo dice [np.float32(0.9874), np.float32(0.9938), np.float32(0.9948), np.float32(0.805)] +2025-10-31 02:26:15.493830: Epoch time: 20.74 s +2025-10-31 02:26:17.539778: +2025-10-31 02:26:17.541874: Epoch 906 +2025-10-31 02:26:17.543371: Current learning rate: 0.00119 +2025-10-31 02:26:36.784074: train_loss -0.9943 +2025-10-31 02:26:36.790568: val_loss -0.893 +2025-10-31 02:26:36.794204: Pseudo dice [np.float32(0.9875), np.float32(0.9933), np.float32(0.9948), np.float32(0.7955)] +2025-10-31 02:26:36.797529: Epoch time: 19.25 s +2025-10-31 02:26:38.134829: +2025-10-31 02:26:38.142652: Epoch 907 +2025-10-31 02:26:38.150608: Current learning rate: 0.00118 +2025-10-31 02:26:59.359146: train_loss -0.9938 +2025-10-31 02:26:59.365333: val_loss -0.888 +2025-10-31 02:26:59.368665: Pseudo dice [np.float32(0.9864), np.float32(0.9934), np.float32(0.9948), np.float32(0.7888)] +2025-10-31 02:26:59.371329: Epoch time: 21.23 s +2025-10-31 02:27:00.603137: +2025-10-31 02:27:00.605338: Epoch 908 +2025-10-31 02:27:00.607219: Current learning rate: 0.00117 +2025-10-31 02:27:21.520166: train_loss -0.9933 +2025-10-31 02:27:21.523059: val_loss -0.8961 +2025-10-31 02:27:21.525245: Pseudo dice [np.float32(0.9869), np.float32(0.9936), np.float32(0.9949), np.float32(0.8097)] +2025-10-31 02:27:21.527991: Epoch time: 20.92 s +2025-10-31 02:27:22.724460: +2025-10-31 02:27:22.726639: Epoch 909 +2025-10-31 02:27:22.728301: Current learning rate: 0.00116 +2025-10-31 02:27:43.117827: train_loss -0.9942 +2025-10-31 02:27:43.121812: val_loss -0.8922 +2025-10-31 02:27:43.124720: Pseudo dice [np.float32(0.9866), np.float32(0.9933), np.float32(0.9946), np.float32(0.7966)] +2025-10-31 02:27:43.128304: Epoch time: 20.4 s +2025-10-31 02:27:44.374815: +2025-10-31 02:27:44.377184: Epoch 910 +2025-10-31 02:27:44.381853: Current learning rate: 0.00115 +2025-10-31 02:28:04.982836: train_loss -0.994 +2025-10-31 02:28:04.989596: val_loss -0.8901 +2025-10-31 02:28:04.992813: Pseudo dice [np.float32(0.9874), np.float32(0.9934), np.float32(0.9945), np.float32(0.7977)] +2025-10-31 02:28:04.995595: Epoch time: 20.61 s +2025-10-31 02:28:05.985124: +2025-10-31 02:28:05.987449: Epoch 911 +2025-10-31 02:28:05.990164: Current learning rate: 0.00113 +2025-10-31 02:28:26.942462: train_loss -0.9946 +2025-10-31 02:28:26.945314: val_loss -0.8942 +2025-10-31 02:28:26.946847: Pseudo dice [np.float32(0.9877), np.float32(0.994), np.float32(0.9949), np.float32(0.7971)] +2025-10-31 02:28:26.948444: Epoch time: 20.96 s +2025-10-31 02:28:28.146240: +2025-10-31 02:28:28.148497: Epoch 912 +2025-10-31 02:28:28.150381: Current learning rate: 0.00112 +2025-10-31 02:28:49.102925: train_loss -0.9946 +2025-10-31 02:28:49.107544: val_loss -0.8909 +2025-10-31 02:28:49.109779: Pseudo dice [np.float32(0.9872), np.float32(0.9934), np.float32(0.9946), np.float32(0.7936)] +2025-10-31 02:28:49.111828: Epoch time: 20.96 s +2025-10-31 02:28:50.363501: +2025-10-31 02:28:50.365932: Epoch 913 +2025-10-31 02:28:50.371835: Current learning rate: 0.00111 +2025-10-31 02:29:10.498011: train_loss -0.9943 +2025-10-31 02:29:10.501620: val_loss -0.8894 +2025-10-31 02:29:10.503208: Pseudo dice [np.float32(0.9882), np.float32(0.9937), np.float32(0.9947), np.float32(0.7947)] +2025-10-31 02:29:10.505132: Epoch time: 20.14 s +2025-10-31 02:29:11.716345: +2025-10-31 02:29:11.718306: Epoch 914 +2025-10-31 02:29:11.720350: Current learning rate: 0.0011 +2025-10-31 02:29:32.789910: train_loss -0.9943 +2025-10-31 02:29:32.794038: val_loss -0.9036 +2025-10-31 02:29:32.795748: Pseudo dice [np.float32(0.988), np.float32(0.9942), np.float32(0.9951), np.float32(0.814)] +2025-10-31 02:29:32.797524: Epoch time: 21.08 s +2025-10-31 02:29:34.036693: +2025-10-31 02:29:34.038585: Epoch 915 +2025-10-31 02:29:34.040429: Current learning rate: 0.00109 +2025-10-31 02:29:54.008221: train_loss -0.9937 +2025-10-31 02:29:54.011141: val_loss -0.8967 +2025-10-31 02:29:54.012828: Pseudo dice [np.float32(0.987), np.float32(0.9932), np.float32(0.9948), np.float32(0.8044)] +2025-10-31 02:29:54.014373: Epoch time: 19.97 s +2025-10-31 02:29:55.215695: +2025-10-31 02:29:55.219095: Epoch 916 +2025-10-31 02:29:55.220750: Current learning rate: 0.00108 +2025-10-31 02:30:16.357489: train_loss -0.9942 +2025-10-31 02:30:16.361116: val_loss -0.8958 +2025-10-31 02:30:16.363719: Pseudo dice [np.float32(0.9877), np.float32(0.9937), np.float32(0.9947), np.float32(0.8036)] +2025-10-31 02:30:16.367108: Epoch time: 21.14 s +2025-10-31 02:30:17.767660: +2025-10-31 02:30:17.770431: Epoch 917 +2025-10-31 02:30:17.772688: Current learning rate: 0.00106 +2025-10-31 02:30:38.792944: train_loss -0.9941 +2025-10-31 02:30:38.801995: val_loss -0.8932 +2025-10-31 02:30:38.804197: Pseudo dice [np.float32(0.9872), np.float32(0.9937), np.float32(0.9946), np.float32(0.8014)] +2025-10-31 02:30:38.806654: Epoch time: 21.03 s +2025-10-31 02:30:39.912057: +2025-10-31 02:30:39.914311: Epoch 918 +2025-10-31 02:30:39.916208: Current learning rate: 0.00105 +2025-10-31 02:31:01.465427: train_loss -0.9937 +2025-10-31 02:31:01.469661: val_loss -0.8952 +2025-10-31 02:31:01.471474: Pseudo dice [np.float32(0.9871), np.float32(0.9935), np.float32(0.9945), np.float32(0.8018)] +2025-10-31 02:31:01.473326: Epoch time: 21.56 s +2025-10-31 02:31:02.644253: +2025-10-31 02:31:02.649230: Epoch 919 +2025-10-31 02:31:02.652772: Current learning rate: 0.00104 +2025-10-31 02:31:21.823207: train_loss -0.9942 +2025-10-31 02:31:21.828189: val_loss -0.8904 +2025-10-31 02:31:21.830880: Pseudo dice [np.float32(0.9875), np.float32(0.9932), np.float32(0.9946), np.float32(0.7917)] +2025-10-31 02:31:21.832888: Epoch time: 19.18 s +2025-10-31 02:31:23.044155: +2025-10-31 02:31:23.048646: Epoch 920 +2025-10-31 02:31:23.053117: Current learning rate: 0.00103 +2025-10-31 02:31:43.841688: train_loss -0.9945 +2025-10-31 02:31:43.848919: val_loss -0.8903 +2025-10-31 02:31:43.850851: Pseudo dice [np.float32(0.9873), np.float32(0.9939), np.float32(0.9949), np.float32(0.7931)] +2025-10-31 02:31:43.852858: Epoch time: 20.8 s +2025-10-31 02:31:44.989427: +2025-10-31 02:31:44.991906: Epoch 921 +2025-10-31 02:31:44.994365: Current learning rate: 0.00102 +2025-10-31 02:32:04.565806: train_loss -0.9941 +2025-10-31 02:32:04.576041: val_loss -0.894 +2025-10-31 02:32:04.583534: Pseudo dice [np.float32(0.988), np.float32(0.9937), np.float32(0.9947), np.float32(0.7974)] +2025-10-31 02:32:04.591780: Epoch time: 19.58 s +2025-10-31 02:32:05.480375: +2025-10-31 02:32:05.482684: Epoch 922 +2025-10-31 02:32:05.484766: Current learning rate: 0.00101 +2025-10-31 02:32:26.098890: train_loss -0.9942 +2025-10-31 02:32:26.102865: val_loss -0.892 +2025-10-31 02:32:26.104858: Pseudo dice [np.float32(0.9862), np.float32(0.9937), np.float32(0.9947), np.float32(0.798)] +2025-10-31 02:32:26.106835: Epoch time: 20.62 s +2025-10-31 02:32:27.219578: +2025-10-31 02:32:27.221690: Epoch 923 +2025-10-31 02:32:27.223316: Current learning rate: 0.001 +2025-10-31 02:32:47.659317: train_loss -0.9943 +2025-10-31 02:32:47.663420: val_loss -0.8949 +2025-10-31 02:32:47.666714: Pseudo dice [np.float32(0.9873), np.float32(0.9933), np.float32(0.9945), np.float32(0.8003)] +2025-10-31 02:32:47.670567: Epoch time: 20.44 s +2025-10-31 02:32:48.722866: +2025-10-31 02:32:48.725008: Epoch 924 +2025-10-31 02:32:48.727423: Current learning rate: 0.00098 +2025-10-31 02:33:09.050394: train_loss -0.9948 +2025-10-31 02:33:09.054598: val_loss -0.9054 +2025-10-31 02:33:09.057604: Pseudo dice [np.float32(0.9868), np.float32(0.9936), np.float32(0.9951), np.float32(0.8217)] +2025-10-31 02:33:09.060453: Epoch time: 20.33 s +2025-10-31 02:33:10.254656: +2025-10-31 02:33:10.256975: Epoch 925 +2025-10-31 02:33:10.259034: Current learning rate: 0.00097 +2025-10-31 02:33:30.764600: train_loss -0.9943 +2025-10-31 02:33:30.768756: val_loss -0.8963 +2025-10-31 02:33:30.770813: Pseudo dice [np.float32(0.988), np.float32(0.9938), np.float32(0.9948), np.float32(0.8052)] +2025-10-31 02:33:30.772567: Epoch time: 20.51 s +2025-10-31 02:33:31.885164: +2025-10-31 02:33:31.890523: Epoch 926 +2025-10-31 02:33:31.892993: Current learning rate: 0.00096 +2025-10-31 02:33:51.587431: train_loss -0.9944 +2025-10-31 02:33:51.593292: val_loss -0.8933 +2025-10-31 02:33:51.597354: Pseudo dice [np.float32(0.987), np.float32(0.9933), np.float32(0.9948), np.float32(0.8009)] +2025-10-31 02:33:51.601254: Epoch time: 19.7 s +2025-10-31 02:33:52.618071: +2025-10-31 02:33:52.621287: Epoch 927 +2025-10-31 02:33:52.623301: Current learning rate: 0.00095 +2025-10-31 02:34:13.064524: train_loss -0.9942 +2025-10-31 02:34:13.072475: val_loss -0.8969 +2025-10-31 02:34:13.075781: Pseudo dice [np.float32(0.988), np.float32(0.9932), np.float32(0.9947), np.float32(0.8051)] +2025-10-31 02:34:13.077928: Epoch time: 20.45 s +2025-10-31 02:34:14.148537: +2025-10-31 02:34:14.150445: Epoch 928 +2025-10-31 02:34:14.152821: Current learning rate: 0.00094 +2025-10-31 02:34:33.807185: train_loss -0.9947 +2025-10-31 02:34:33.811022: val_loss -0.892 +2025-10-31 02:34:33.812893: Pseudo dice [np.float32(0.9867), np.float32(0.9929), np.float32(0.9944), np.float32(0.8023)] +2025-10-31 02:34:33.814707: Epoch time: 19.66 s +2025-10-31 02:34:35.124387: +2025-10-31 02:34:35.126679: Epoch 929 +2025-10-31 02:34:35.129624: Current learning rate: 0.00092 +2025-10-31 02:34:55.566656: train_loss -0.9943 +2025-10-31 02:34:55.569236: val_loss -0.8996 +2025-10-31 02:34:55.571552: Pseudo dice [np.float32(0.9879), np.float32(0.9933), np.float32(0.9949), np.float32(0.8138)] +2025-10-31 02:34:55.573871: Epoch time: 20.44 s +2025-10-31 02:34:56.616282: +2025-10-31 02:34:56.618416: Epoch 930 +2025-10-31 02:34:56.620742: Current learning rate: 0.00091 +2025-10-31 02:35:17.379073: train_loss -0.9945 +2025-10-31 02:35:17.386095: val_loss -0.8975 +2025-10-31 02:35:17.387814: Pseudo dice [np.float32(0.9869), np.float32(0.9936), np.float32(0.9948), np.float32(0.8124)] +2025-10-31 02:35:17.390214: Epoch time: 20.76 s +2025-10-31 02:35:17.392318: Yayy! New best EMA pseudo Dice: 0.9449999928474426 +2025-10-31 02:35:20.116352: +2025-10-31 02:35:20.118758: Epoch 931 +2025-10-31 02:35:20.120660: Current learning rate: 0.0009 +2025-10-31 02:35:40.704531: train_loss -0.9945 +2025-10-31 02:35:40.713338: val_loss -0.8985 +2025-10-31 02:35:40.715630: Pseudo dice [np.float32(0.9879), np.float32(0.9939), np.float32(0.9948), np.float32(0.8035)] +2025-10-31 02:35:40.717448: Epoch time: 20.59 s +2025-10-31 02:35:40.719065: Yayy! New best EMA pseudo Dice: 0.9449999928474426 +2025-10-31 02:35:43.291497: +2025-10-31 02:35:43.293890: Epoch 932 +2025-10-31 02:35:43.296559: Current learning rate: 0.00089 +2025-10-31 02:36:03.957937: train_loss -0.9941 +2025-10-31 02:36:03.965487: val_loss -0.8949 +2025-10-31 02:36:03.971333: Pseudo dice [np.float32(0.9882), np.float32(0.9937), np.float32(0.9945), np.float32(0.7989)] +2025-10-31 02:36:03.977161: Epoch time: 20.67 s +2025-10-31 02:36:05.175474: +2025-10-31 02:36:05.177855: Epoch 933 +2025-10-31 02:36:05.180216: Current learning rate: 0.00088 +2025-10-31 02:36:24.716310: train_loss -0.9945 +2025-10-31 02:36:24.719386: val_loss -0.8928 +2025-10-31 02:36:24.722920: Pseudo dice [np.float32(0.9872), np.float32(0.9931), np.float32(0.9947), np.float32(0.8014)] +2025-10-31 02:36:24.727087: Epoch time: 19.54 s +2025-10-31 02:36:25.799791: +2025-10-31 02:36:25.804654: Epoch 934 +2025-10-31 02:36:25.806612: Current learning rate: 0.00087 +2025-10-31 02:36:45.103980: train_loss -0.9944 +2025-10-31 02:36:45.107277: val_loss -0.8933 +2025-10-31 02:36:45.109657: Pseudo dice [np.float32(0.9863), np.float32(0.9931), np.float32(0.9948), np.float32(0.8032)] +2025-10-31 02:36:45.111954: Epoch time: 19.31 s +2025-10-31 02:36:46.153269: +2025-10-31 02:36:46.155820: Epoch 935 +2025-10-31 02:36:46.157969: Current learning rate: 0.00085 +2025-10-31 02:37:06.683501: train_loss -0.9945 +2025-10-31 02:37:06.688207: val_loss -0.8962 +2025-10-31 02:37:06.690342: Pseudo dice [np.float32(0.9872), np.float32(0.9936), np.float32(0.9949), np.float32(0.8075)] +2025-10-31 02:37:06.692309: Epoch time: 20.53 s +2025-10-31 02:37:07.692429: +2025-10-31 02:37:07.694503: Epoch 936 +2025-10-31 02:37:07.696568: Current learning rate: 0.00084 +2025-10-31 02:37:28.344460: train_loss -0.9947 +2025-10-31 02:37:28.351930: val_loss -0.9004 +2025-10-31 02:37:28.354075: Pseudo dice [np.float32(0.9872), np.float32(0.9935), np.float32(0.995), np.float32(0.8156)] +2025-10-31 02:37:28.357065: Epoch time: 20.65 s +2025-10-31 02:37:28.359282: Yayy! New best EMA pseudo Dice: 0.9451000094413757 +2025-10-31 02:37:31.201345: +2025-10-31 02:37:31.204396: Epoch 937 +2025-10-31 02:37:31.206664: Current learning rate: 0.00083 +2025-10-31 02:37:51.714207: train_loss -0.9946 +2025-10-31 02:37:51.718302: val_loss -0.8968 +2025-10-31 02:37:51.719937: Pseudo dice [np.float32(0.9875), np.float32(0.9932), np.float32(0.9947), np.float32(0.8065)] +2025-10-31 02:37:51.721520: Epoch time: 20.51 s +2025-10-31 02:37:51.723082: Yayy! New best EMA pseudo Dice: 0.9452000260353088 +2025-10-31 02:37:54.233393: +2025-10-31 02:37:54.235651: Epoch 938 +2025-10-31 02:37:54.237529: Current learning rate: 0.00082 +2025-10-31 02:38:14.970783: train_loss -0.9944 +2025-10-31 02:38:14.975515: val_loss -0.8995 +2025-10-31 02:38:14.978688: Pseudo dice [np.float32(0.9876), np.float32(0.9937), np.float32(0.9949), np.float32(0.8093)] +2025-10-31 02:38:14.981326: Epoch time: 20.74 s +2025-10-31 02:38:14.983289: Yayy! New best EMA pseudo Dice: 0.9452999830245972 +2025-10-31 02:38:17.630090: +2025-10-31 02:38:17.632016: Epoch 939 +2025-10-31 02:38:17.634088: Current learning rate: 0.00081 +2025-10-31 02:38:37.467833: train_loss -0.9945 +2025-10-31 02:38:37.486720: val_loss -0.8967 +2025-10-31 02:38:37.489028: Pseudo dice [np.float32(0.9865), np.float32(0.9936), np.float32(0.9949), np.float32(0.8092)] +2025-10-31 02:38:37.491480: Epoch time: 19.84 s +2025-10-31 02:38:37.493841: Yayy! New best EMA pseudo Dice: 0.9453999996185303 +2025-10-31 02:38:40.102761: +2025-10-31 02:38:40.105021: Epoch 940 +2025-10-31 02:38:40.107005: Current learning rate: 0.00079 +2025-10-31 02:38:59.980572: train_loss -0.9945 +2025-10-31 02:38:59.985147: val_loss -0.8943 +2025-10-31 02:38:59.987225: Pseudo dice [np.float32(0.9875), np.float32(0.9932), np.float32(0.9946), np.float32(0.7979)] +2025-10-31 02:38:59.989145: Epoch time: 19.88 s +2025-10-31 02:39:01.145567: +2025-10-31 02:39:01.147715: Epoch 941 +2025-10-31 02:39:01.149615: Current learning rate: 0.00078 +2025-10-31 02:39:21.656285: train_loss -0.9948 +2025-10-31 02:39:21.662455: val_loss -0.8993 +2025-10-31 02:39:21.664149: Pseudo dice [np.float32(0.9874), np.float32(0.9936), np.float32(0.9948), np.float32(0.8084)] +2025-10-31 02:39:21.666232: Epoch time: 20.51 s +2025-10-31 02:39:22.715343: +2025-10-31 02:39:22.717266: Epoch 942 +2025-10-31 02:39:22.718915: Current learning rate: 0.00077 +2025-10-31 02:39:43.351052: train_loss -0.9947 +2025-10-31 02:39:43.355092: val_loss -0.8921 +2025-10-31 02:39:43.358034: Pseudo dice [np.float32(0.9871), np.float32(0.9934), np.float32(0.9948), np.float32(0.7958)] +2025-10-31 02:39:43.359828: Epoch time: 20.64 s +2025-10-31 02:39:44.743952: +2025-10-31 02:39:44.746241: Epoch 943 +2025-10-31 02:39:44.749779: Current learning rate: 0.00076 +2025-10-31 02:40:05.454064: train_loss -0.9949 +2025-10-31 02:40:05.463387: val_loss -0.8936 +2025-10-31 02:40:05.468465: Pseudo dice [np.float32(0.9875), np.float32(0.9941), np.float32(0.9947), np.float32(0.801)] +2025-10-31 02:40:05.474667: Epoch time: 20.71 s +2025-10-31 02:40:06.520560: +2025-10-31 02:40:06.527722: Epoch 944 +2025-10-31 02:40:06.534636: Current learning rate: 0.00075 +2025-10-31 02:40:27.189744: train_loss -0.9946 +2025-10-31 02:40:27.194053: val_loss -0.8949 +2025-10-31 02:40:27.196373: Pseudo dice [np.float32(0.9872), np.float32(0.993), np.float32(0.9946), np.float32(0.801)] +2025-10-31 02:40:27.197967: Epoch time: 20.67 s +2025-10-31 02:40:28.337357: +2025-10-31 02:40:28.339127: Epoch 945 +2025-10-31 02:40:28.340879: Current learning rate: 0.00074 +2025-10-31 02:40:48.792524: train_loss -0.995 +2025-10-31 02:40:48.799152: val_loss -0.8985 +2025-10-31 02:40:48.802689: Pseudo dice [np.float32(0.9867), np.float32(0.9936), np.float32(0.9948), np.float32(0.8107)] +2025-10-31 02:40:48.805584: Epoch time: 20.46 s +2025-10-31 02:40:49.956696: +2025-10-31 02:40:49.959404: Epoch 946 +2025-10-31 02:40:49.961685: Current learning rate: 0.00072 +2025-10-31 02:41:09.950460: train_loss -0.9947 +2025-10-31 02:41:09.954105: val_loss -0.8913 +2025-10-31 02:41:09.955907: Pseudo dice [np.float32(0.987), np.float32(0.9932), np.float32(0.9946), np.float32(0.8007)] +2025-10-31 02:41:09.957826: Epoch time: 20.0 s +2025-10-31 02:41:11.039965: +2025-10-31 02:41:11.042163: Epoch 947 +2025-10-31 02:41:11.045925: Current learning rate: 0.00071 +2025-10-31 02:41:32.019974: train_loss -0.9947 +2025-10-31 02:41:32.024806: val_loss -0.8941 +2025-10-31 02:41:32.026553: Pseudo dice [np.float32(0.9873), np.float32(0.9938), np.float32(0.9949), np.float32(0.7992)] +2025-10-31 02:41:32.028859: Epoch time: 20.98 s +2025-10-31 02:41:33.360074: +2025-10-31 02:41:33.362426: Epoch 948 +2025-10-31 02:41:33.364498: Current learning rate: 0.0007 +2025-10-31 02:41:53.699769: train_loss -0.9949 +2025-10-31 02:41:53.704082: val_loss -0.896 +2025-10-31 02:41:53.705653: Pseudo dice [np.float32(0.9882), np.float32(0.9943), np.float32(0.995), np.float32(0.799)] +2025-10-31 02:41:53.707653: Epoch time: 20.34 s +2025-10-31 02:41:54.840112: +2025-10-31 02:41:54.842523: Epoch 949 +2025-10-31 02:41:54.846292: Current learning rate: 0.00069 +2025-10-31 02:42:15.326809: train_loss -0.9947 +2025-10-31 02:42:15.330803: val_loss -0.8968 +2025-10-31 02:42:15.333013: Pseudo dice [np.float32(0.9871), np.float32(0.9938), np.float32(0.9949), np.float32(0.8032)] +2025-10-31 02:42:15.334985: Epoch time: 20.49 s +2025-10-31 02:42:17.935126: +2025-10-31 02:42:17.937597: Epoch 950 +2025-10-31 02:42:17.939831: Current learning rate: 0.00067 +2025-10-31 02:42:38.574282: train_loss -0.9949 +2025-10-31 02:42:38.578634: val_loss -0.8989 +2025-10-31 02:42:38.580645: Pseudo dice [np.float32(0.9876), np.float32(0.9938), np.float32(0.9949), np.float32(0.8095)] +2025-10-31 02:42:38.582673: Epoch time: 20.64 s +2025-10-31 02:42:39.645767: +2025-10-31 02:42:39.647813: Epoch 951 +2025-10-31 02:42:39.650193: Current learning rate: 0.00066 +2025-10-31 02:43:00.258495: train_loss -0.9947 +2025-10-31 02:43:00.261141: val_loss -0.8962 +2025-10-31 02:43:00.262795: Pseudo dice [np.float32(0.987), np.float32(0.994), np.float32(0.995), np.float32(0.8021)] +2025-10-31 02:43:00.264628: Epoch time: 20.61 s +2025-10-31 02:43:01.508220: +2025-10-31 02:43:01.510185: Epoch 952 +2025-10-31 02:43:01.512202: Current learning rate: 0.00065 +2025-10-31 02:43:21.969930: train_loss -0.9953 +2025-10-31 02:43:21.973202: val_loss -0.8946 +2025-10-31 02:43:21.974962: Pseudo dice [np.float32(0.9876), np.float32(0.9935), np.float32(0.9948), np.float32(0.8013)] +2025-10-31 02:43:21.976717: Epoch time: 20.46 s +2025-10-31 02:43:23.045676: +2025-10-31 02:43:23.047928: Epoch 953 +2025-10-31 02:43:23.049834: Current learning rate: 0.00064 +2025-10-31 02:43:41.472471: train_loss -0.9945 +2025-10-31 02:43:41.476346: val_loss -0.8924 +2025-10-31 02:43:41.477970: Pseudo dice [np.float32(0.9871), np.float32(0.9935), np.float32(0.9947), np.float32(0.7977)] +2025-10-31 02:43:41.480219: Epoch time: 18.43 s +2025-10-31 02:43:42.507370: +2025-10-31 02:43:42.509229: Epoch 954 +2025-10-31 02:43:42.510975: Current learning rate: 0.00063 +2025-10-31 02:44:03.087263: train_loss -0.9949 +2025-10-31 02:44:03.091748: val_loss -0.892 +2025-10-31 02:44:03.093249: Pseudo dice [np.float32(0.9877), np.float32(0.9935), np.float32(0.9947), np.float32(0.794)] +2025-10-31 02:44:03.094759: Epoch time: 20.58 s +2025-10-31 02:44:04.117381: +2025-10-31 02:44:04.123040: Epoch 955 +2025-10-31 02:44:04.128533: Current learning rate: 0.00061 +2025-10-31 02:44:24.830648: train_loss -0.995 +2025-10-31 02:44:24.839052: val_loss -0.8896 +2025-10-31 02:44:24.841702: Pseudo dice [np.float32(0.9866), np.float32(0.9933), np.float32(0.9944), np.float32(0.7958)] +2025-10-31 02:44:24.844166: Epoch time: 20.71 s +2025-10-31 02:44:26.720820: +2025-10-31 02:44:26.726640: Epoch 956 +2025-10-31 02:44:26.728542: Current learning rate: 0.0006 +2025-10-31 02:44:47.238994: train_loss -0.9948 +2025-10-31 02:44:47.241950: val_loss -0.8917 +2025-10-31 02:44:47.244202: Pseudo dice [np.float32(0.9869), np.float32(0.9937), np.float32(0.9947), np.float32(0.8033)] +2025-10-31 02:44:47.246867: Epoch time: 20.52 s +2025-10-31 02:44:48.395874: +2025-10-31 02:44:48.397829: Epoch 957 +2025-10-31 02:44:48.399600: Current learning rate: 0.00059 +2025-10-31 02:45:09.087036: train_loss -0.9949 +2025-10-31 02:45:09.091648: val_loss -0.8925 +2025-10-31 02:45:09.093361: Pseudo dice [np.float32(0.9867), np.float32(0.9934), np.float32(0.9946), np.float32(0.7984)] +2025-10-31 02:45:09.094970: Epoch time: 20.69 s +2025-10-31 02:45:10.124672: +2025-10-31 02:45:10.126395: Epoch 958 +2025-10-31 02:45:10.129056: Current learning rate: 0.00058 +2025-10-31 02:45:30.960431: train_loss -0.9947 +2025-10-31 02:45:30.963223: val_loss -0.894 +2025-10-31 02:45:30.965755: Pseudo dice [np.float32(0.9871), np.float32(0.994), np.float32(0.9949), np.float32(0.8003)] +2025-10-31 02:45:30.967357: Epoch time: 20.84 s +2025-10-31 02:45:32.086617: +2025-10-31 02:45:32.089123: Epoch 959 +2025-10-31 02:45:32.091368: Current learning rate: 0.00056 +2025-10-31 02:45:51.063977: train_loss -0.9948 +2025-10-31 02:45:51.066280: val_loss -0.8929 +2025-10-31 02:45:51.068105: Pseudo dice [np.float32(0.9871), np.float32(0.9939), np.float32(0.995), np.float32(0.7951)] +2025-10-31 02:45:51.069710: Epoch time: 18.98 s +2025-10-31 02:45:52.281097: +2025-10-31 02:45:52.283718: Epoch 960 +2025-10-31 02:45:52.286218: Current learning rate: 0.00055 +2025-10-31 02:46:12.700765: train_loss -0.9945 +2025-10-31 02:46:12.705751: val_loss -0.8924 +2025-10-31 02:46:12.709065: Pseudo dice [np.float32(0.9877), np.float32(0.9941), np.float32(0.995), np.float32(0.7945)] +2025-10-31 02:46:12.712682: Epoch time: 20.42 s +2025-10-31 02:46:13.809419: +2025-10-31 02:46:13.811448: Epoch 961 +2025-10-31 02:46:13.813372: Current learning rate: 0.00054 +2025-10-31 02:46:34.273708: train_loss -0.9948 +2025-10-31 02:46:34.279633: val_loss -0.9004 +2025-10-31 02:46:34.282132: Pseudo dice [np.float32(0.9877), np.float32(0.9945), np.float32(0.9952), np.float32(0.8143)] +2025-10-31 02:46:34.283919: Epoch time: 20.47 s +2025-10-31 02:46:35.505234: +2025-10-31 02:46:35.507403: Epoch 962 +2025-10-31 02:46:35.509341: Current learning rate: 0.00053 +2025-10-31 02:46:56.138318: train_loss -0.9952 +2025-10-31 02:46:56.141283: val_loss -0.8934 +2025-10-31 02:46:56.143787: Pseudo dice [np.float32(0.987), np.float32(0.9933), np.float32(0.9947), np.float32(0.8067)] +2025-10-31 02:46:56.145836: Epoch time: 20.63 s +2025-10-31 02:46:57.160633: +2025-10-31 02:46:57.162776: Epoch 963 +2025-10-31 02:46:57.164796: Current learning rate: 0.00051 +2025-10-31 02:47:17.722550: train_loss -0.9951 +2025-10-31 02:47:17.726317: val_loss -0.8945 +2025-10-31 02:47:17.727985: Pseudo dice [np.float32(0.9882), np.float32(0.9937), np.float32(0.9947), np.float32(0.7998)] +2025-10-31 02:47:17.729669: Epoch time: 20.56 s +2025-10-31 02:47:18.982494: +2025-10-31 02:47:18.984526: Epoch 964 +2025-10-31 02:47:18.986252: Current learning rate: 0.0005 +2025-10-31 02:47:39.734978: train_loss -0.9951 +2025-10-31 02:47:39.739597: val_loss -0.8971 +2025-10-31 02:47:39.741405: Pseudo dice [np.float32(0.9873), np.float32(0.9935), np.float32(0.9948), np.float32(0.8084)] +2025-10-31 02:47:39.743131: Epoch time: 20.75 s +2025-10-31 02:47:40.750808: +2025-10-31 02:47:40.752856: Epoch 965 +2025-10-31 02:47:40.757234: Current learning rate: 0.00049 +2025-10-31 02:48:00.909356: train_loss -0.9948 +2025-10-31 02:48:00.912545: val_loss -0.8974 +2025-10-31 02:48:00.914491: Pseudo dice [np.float32(0.9874), np.float32(0.9939), np.float32(0.9951), np.float32(0.8053)] +2025-10-31 02:48:00.916242: Epoch time: 20.16 s +2025-10-31 02:48:01.911719: +2025-10-31 02:48:01.914464: Epoch 966 +2025-10-31 02:48:01.916577: Current learning rate: 0.00048 +2025-10-31 02:48:21.312367: train_loss -0.995 +2025-10-31 02:48:21.316399: val_loss -0.8923 +2025-10-31 02:48:21.318116: Pseudo dice [np.float32(0.9874), np.float32(0.9933), np.float32(0.9947), np.float32(0.8007)] +2025-10-31 02:48:21.319815: Epoch time: 19.4 s +2025-10-31 02:48:22.615978: +2025-10-31 02:48:22.619959: Epoch 967 +2025-10-31 02:48:22.622646: Current learning rate: 0.00046 +2025-10-31 02:48:42.952575: train_loss -0.9952 +2025-10-31 02:48:42.955943: val_loss -0.8949 +2025-10-31 02:48:42.958584: Pseudo dice [np.float32(0.9876), np.float32(0.9933), np.float32(0.9947), np.float32(0.8079)] +2025-10-31 02:48:42.963169: Epoch time: 20.34 s +2025-10-31 02:48:44.548582: +2025-10-31 02:48:44.550530: Epoch 968 +2025-10-31 02:48:44.552071: Current learning rate: 0.00045 +2025-10-31 02:49:05.328665: train_loss -0.9949 +2025-10-31 02:49:05.332741: val_loss -0.8941 +2025-10-31 02:49:05.334448: Pseudo dice [np.float32(0.9888), np.float32(0.9942), np.float32(0.9949), np.float32(0.7957)] +2025-10-31 02:49:05.336211: Epoch time: 20.78 s +2025-10-31 02:49:06.398518: +2025-10-31 02:49:06.400438: Epoch 969 +2025-10-31 02:49:06.402129: Current learning rate: 0.00044 +2025-10-31 02:49:27.203828: train_loss -0.9948 +2025-10-31 02:49:27.209359: val_loss -0.8946 +2025-10-31 02:49:27.213864: Pseudo dice [np.float32(0.9876), np.float32(0.9939), np.float32(0.9951), np.float32(0.7984)] +2025-10-31 02:49:27.216110: Epoch time: 20.81 s +2025-10-31 02:49:28.455084: +2025-10-31 02:49:28.457040: Epoch 970 +2025-10-31 02:49:28.458666: Current learning rate: 0.00043 +2025-10-31 02:49:49.188861: train_loss -0.9948 +2025-10-31 02:49:49.193703: val_loss -0.8973 +2025-10-31 02:49:49.196618: Pseudo dice [np.float32(0.9882), np.float32(0.9939), np.float32(0.9951), np.float32(0.8084)] +2025-10-31 02:49:49.198428: Epoch time: 20.74 s +2025-10-31 02:49:50.269495: +2025-10-31 02:49:50.271217: Epoch 971 +2025-10-31 02:49:50.272541: Current learning rate: 0.00041 +2025-10-31 02:50:10.773971: train_loss -0.9952 +2025-10-31 02:50:10.778841: val_loss -0.8924 +2025-10-31 02:50:10.780439: Pseudo dice [np.float32(0.9877), np.float32(0.9934), np.float32(0.9948), np.float32(0.7985)] +2025-10-31 02:50:10.782154: Epoch time: 20.51 s +2025-10-31 02:50:11.802809: +2025-10-31 02:50:11.804838: Epoch 972 +2025-10-31 02:50:11.806696: Current learning rate: 0.0004 +2025-10-31 02:50:31.785399: train_loss -0.9947 +2025-10-31 02:50:31.789881: val_loss -0.8944 +2025-10-31 02:50:31.792233: Pseudo dice [np.float32(0.9871), np.float32(0.9937), np.float32(0.9949), np.float32(0.8088)] +2025-10-31 02:50:31.794243: Epoch time: 19.98 s +2025-10-31 02:50:32.849101: +2025-10-31 02:50:32.851513: Epoch 973 +2025-10-31 02:50:32.853617: Current learning rate: 0.00039 +2025-10-31 02:50:52.759376: train_loss -0.9951 +2025-10-31 02:50:52.764668: val_loss -0.8906 +2025-10-31 02:50:52.766382: Pseudo dice [np.float32(0.988), np.float32(0.9937), np.float32(0.9949), np.float32(0.788)] +2025-10-31 02:50:52.767897: Epoch time: 19.91 s +2025-10-31 02:50:53.981472: +2025-10-31 02:50:53.983402: Epoch 974 +2025-10-31 02:50:53.985079: Current learning rate: 0.00037 +2025-10-31 02:51:14.382618: train_loss -0.9951 +2025-10-31 02:51:14.385437: val_loss -0.8939 +2025-10-31 02:51:14.387251: Pseudo dice [np.float32(0.9872), np.float32(0.9942), np.float32(0.9951), np.float32(0.8017)] +2025-10-31 02:51:14.389119: Epoch time: 20.4 s +2025-10-31 02:51:15.517787: +2025-10-31 02:51:15.519656: Epoch 975 +2025-10-31 02:51:15.521277: Current learning rate: 0.00036 +2025-10-31 02:51:35.984342: train_loss -0.9949 +2025-10-31 02:51:35.988774: val_loss -0.8946 +2025-10-31 02:51:35.990430: Pseudo dice [np.float32(0.9873), np.float32(0.994), np.float32(0.9952), np.float32(0.7984)] +2025-10-31 02:51:35.992169: Epoch time: 20.47 s +2025-10-31 02:51:37.041933: +2025-10-31 02:51:37.044006: Epoch 976 +2025-10-31 02:51:37.045709: Current learning rate: 0.00035 +2025-10-31 02:51:57.188917: train_loss -0.995 +2025-10-31 02:51:57.191317: val_loss -0.8913 +2025-10-31 02:51:57.192800: Pseudo dice [np.float32(0.9873), np.float32(0.9936), np.float32(0.9946), np.float32(0.8002)] +2025-10-31 02:51:57.196950: Epoch time: 20.15 s +2025-10-31 02:51:58.289897: +2025-10-31 02:51:58.291965: Epoch 977 +2025-10-31 02:51:58.293687: Current learning rate: 0.00034 +2025-10-31 02:52:18.640070: train_loss -0.9952 +2025-10-31 02:52:18.644674: val_loss -0.8926 +2025-10-31 02:52:18.646331: Pseudo dice [np.float32(0.9878), np.float32(0.9944), np.float32(0.995), np.float32(0.8002)] +2025-10-31 02:52:18.647961: Epoch time: 20.35 s +2025-10-31 02:52:19.901254: +2025-10-31 02:52:19.906830: Epoch 978 +2025-10-31 02:52:19.908714: Current learning rate: 0.00032 +2025-10-31 02:52:39.393678: train_loss -0.9954 +2025-10-31 02:52:39.399911: val_loss -0.8924 +2025-10-31 02:52:39.401581: Pseudo dice [np.float32(0.9873), np.float32(0.9943), np.float32(0.995), np.float32(0.797)] +2025-10-31 02:52:39.403447: Epoch time: 19.49 s +2025-10-31 02:52:40.688469: +2025-10-31 02:52:40.690627: Epoch 979 +2025-10-31 02:52:40.692930: Current learning rate: 0.00031 +2025-10-31 02:53:01.573011: train_loss -0.9955 +2025-10-31 02:53:01.576256: val_loss -0.8926 +2025-10-31 02:53:01.577987: Pseudo dice [np.float32(0.9884), np.float32(0.9943), np.float32(0.9947), np.float32(0.7962)] +2025-10-31 02:53:01.579767: Epoch time: 20.89 s +2025-10-31 02:53:02.989380: +2025-10-31 02:53:02.991518: Epoch 980 +2025-10-31 02:53:02.993181: Current learning rate: 0.0003 +2025-10-31 02:53:22.854171: train_loss -0.9953 +2025-10-31 02:53:22.857787: val_loss -0.8943 +2025-10-31 02:53:22.859359: Pseudo dice [np.float32(0.988), np.float32(0.9939), np.float32(0.9947), np.float32(0.8)] +2025-10-31 02:53:22.860872: Epoch time: 19.87 s +2025-10-31 02:53:24.079731: +2025-10-31 02:53:24.082037: Epoch 981 +2025-10-31 02:53:24.084677: Current learning rate: 0.00028 +2025-10-31 02:53:44.494245: train_loss -0.9948 +2025-10-31 02:53:44.500486: val_loss -0.8922 +2025-10-31 02:53:44.502656: Pseudo dice [np.float32(0.9877), np.float32(0.9938), np.float32(0.9947), np.float32(0.801)] +2025-10-31 02:53:44.508121: Epoch time: 20.42 s +2025-10-31 02:53:45.594363: +2025-10-31 02:53:45.596427: Epoch 982 +2025-10-31 02:53:45.598045: Current learning rate: 0.00027 +2025-10-31 02:54:06.143610: train_loss -0.9954 +2025-10-31 02:54:06.147013: val_loss -0.8976 +2025-10-31 02:54:06.171489: Pseudo dice [np.float32(0.9875), np.float32(0.9941), np.float32(0.9952), np.float32(0.8036)] +2025-10-31 02:54:06.173121: Epoch time: 20.55 s +2025-10-31 02:54:07.411940: +2025-10-31 02:54:07.414486: Epoch 983 +2025-10-31 02:54:07.416528: Current learning rate: 0.00026 +2025-10-31 02:54:28.120562: train_loss -0.9953 +2025-10-31 02:54:28.125008: val_loss -0.8992 +2025-10-31 02:54:28.126613: Pseudo dice [np.float32(0.9881), np.float32(0.994), np.float32(0.995), np.float32(0.8099)] +2025-10-31 02:54:28.128293: Epoch time: 20.71 s +2025-10-31 02:54:29.163361: +2025-10-31 02:54:29.165246: Epoch 984 +2025-10-31 02:54:29.167134: Current learning rate: 0.00024 +2025-10-31 02:54:49.632948: train_loss -0.9952 +2025-10-31 02:54:49.636400: val_loss -0.8989 +2025-10-31 02:54:49.638077: Pseudo dice [np.float32(0.988), np.float32(0.9941), np.float32(0.995), np.float32(0.8118)] +2025-10-31 02:54:49.640167: Epoch time: 20.47 s +2025-10-31 02:54:50.760589: +2025-10-31 02:54:50.762955: Epoch 985 +2025-10-31 02:54:50.765090: Current learning rate: 0.00023 +2025-10-31 02:55:10.769949: train_loss -0.9954 +2025-10-31 02:55:10.773585: val_loss -0.8902 +2025-10-31 02:55:10.776574: Pseudo dice [np.float32(0.9893), np.float32(0.9944), np.float32(0.9947), np.float32(0.7882)] +2025-10-31 02:55:10.779234: Epoch time: 20.01 s +2025-10-31 02:55:11.791749: +2025-10-31 02:55:11.793808: Epoch 986 +2025-10-31 02:55:11.795483: Current learning rate: 0.00021 +2025-10-31 02:55:32.501402: train_loss -0.9952 +2025-10-31 02:55:32.504716: val_loss -0.8921 +2025-10-31 02:55:32.506929: Pseudo dice [np.float32(0.9879), np.float32(0.9942), np.float32(0.9949), np.float32(0.797)] +2025-10-31 02:55:32.509019: Epoch time: 20.71 s +2025-10-31 02:55:33.723160: +2025-10-31 02:55:33.725606: Epoch 987 +2025-10-31 02:55:33.727679: Current learning rate: 0.0002 +2025-10-31 02:55:52.910176: train_loss -0.995 +2025-10-31 02:55:52.920189: val_loss -0.8911 +2025-10-31 02:55:52.922431: Pseudo dice [np.float32(0.9876), np.float32(0.9935), np.float32(0.9946), np.float32(0.8006)] +2025-10-31 02:55:52.924466: Epoch time: 19.19 s +2025-10-31 02:55:54.042162: +2025-10-31 02:55:54.048146: Epoch 988 +2025-10-31 02:55:54.050446: Current learning rate: 0.00019 +2025-10-31 02:56:14.639346: train_loss -0.9956 +2025-10-31 02:56:14.642317: val_loss -0.8942 +2025-10-31 02:56:14.644298: Pseudo dice [np.float32(0.9881), np.float32(0.994), np.float32(0.9949), np.float32(0.8031)] +2025-10-31 02:56:14.646446: Epoch time: 20.6 s +2025-10-31 02:56:15.683978: +2025-10-31 02:56:15.685879: Epoch 989 +2025-10-31 02:56:15.687759: Current learning rate: 0.00017 +2025-10-31 02:56:36.277665: train_loss -0.9954 +2025-10-31 02:56:36.280471: val_loss -0.8884 +2025-10-31 02:56:36.283121: Pseudo dice [np.float32(0.9874), np.float32(0.9938), np.float32(0.9946), np.float32(0.7967)] +2025-10-31 02:56:36.285621: Epoch time: 20.6 s +2025-10-31 02:56:37.304405: +2025-10-31 02:56:37.306083: Epoch 990 +2025-10-31 02:56:37.307803: Current learning rate: 0.00016 +2025-10-31 02:56:57.957900: train_loss -0.9953 +2025-10-31 02:56:57.962075: val_loss -0.8926 +2025-10-31 02:56:57.964200: Pseudo dice [np.float32(0.989), np.float32(0.9939), np.float32(0.9947), np.float32(0.7969)] +2025-10-31 02:56:57.965937: Epoch time: 20.65 s +2025-10-31 02:56:59.254985: +2025-10-31 02:56:59.256994: Epoch 991 +2025-10-31 02:56:59.259351: Current learning rate: 0.00014 +2025-10-31 02:57:18.918535: train_loss -0.9954 +2025-10-31 02:57:18.922444: val_loss -0.8933 +2025-10-31 02:57:18.924096: Pseudo dice [np.float32(0.9873), np.float32(0.9939), np.float32(0.9949), np.float32(0.8052)] +2025-10-31 02:57:18.925684: Epoch time: 19.67 s +2025-10-31 02:57:20.049181: +2025-10-31 02:57:20.051313: Epoch 992 +2025-10-31 02:57:20.053061: Current learning rate: 0.00013 +2025-10-31 02:57:40.803272: train_loss -0.9955 +2025-10-31 02:57:40.807351: val_loss -0.8914 +2025-10-31 02:57:40.808931: Pseudo dice [np.float32(0.9882), np.float32(0.9944), np.float32(0.9949), np.float32(0.7911)] +2025-10-31 02:57:40.810578: Epoch time: 20.76 s +2025-10-31 02:57:42.365877: +2025-10-31 02:57:42.368212: Epoch 993 +2025-10-31 02:57:42.370385: Current learning rate: 0.00011 +2025-10-31 02:58:02.986091: train_loss -0.9955 +2025-10-31 02:58:02.990594: val_loss -0.8964 +2025-10-31 02:58:02.992791: Pseudo dice [np.float32(0.9881), np.float32(0.994), np.float32(0.995), np.float32(0.8083)] +2025-10-31 02:58:02.995055: Epoch time: 20.62 s +2025-10-31 02:58:04.077464: +2025-10-31 02:58:04.080198: Epoch 994 +2025-10-31 02:58:04.084591: Current learning rate: 0.0001 +2025-10-31 02:58:23.951692: train_loss -0.9956 +2025-10-31 02:58:23.954633: val_loss -0.8969 +2025-10-31 02:58:23.957088: Pseudo dice [np.float32(0.9882), np.float32(0.9944), np.float32(0.995), np.float32(0.8059)] +2025-10-31 02:58:23.958771: Epoch time: 19.88 s +2025-10-31 02:58:25.071854: +2025-10-31 02:58:25.073600: Epoch 995 +2025-10-31 02:58:25.075285: Current learning rate: 8e-05 +2025-10-31 02:58:45.644559: train_loss -0.9954 +2025-10-31 02:58:45.648118: val_loss -0.8929 +2025-10-31 02:58:45.650363: Pseudo dice [np.float32(0.9875), np.float32(0.9941), np.float32(0.9949), np.float32(0.8005)] +2025-10-31 02:58:45.653303: Epoch time: 20.57 s +2025-10-31 02:58:46.864182: +2025-10-31 02:58:46.866397: Epoch 996 +2025-10-31 02:58:46.868139: Current learning rate: 7e-05 +2025-10-31 02:59:07.654910: train_loss -0.9958 +2025-10-31 02:59:07.659697: val_loss -0.8905 +2025-10-31 02:59:07.661983: Pseudo dice [np.float32(0.9871), np.float32(0.994), np.float32(0.9947), np.float32(0.8012)] +2025-10-31 02:59:07.664306: Epoch time: 20.79 s +2025-10-31 02:59:08.678619: +2025-10-31 02:59:08.680827: Epoch 997 +2025-10-31 02:59:08.682769: Current learning rate: 5e-05 +2025-10-31 02:59:28.932262: train_loss -0.9957 +2025-10-31 02:59:28.935229: val_loss -0.8957 +2025-10-31 02:59:28.936806: Pseudo dice [np.float32(0.9873), np.float32(0.9937), np.float32(0.9948), np.float32(0.8123)] +2025-10-31 02:59:28.938351: Epoch time: 20.26 s +2025-10-31 02:59:30.003883: +2025-10-31 02:59:30.005875: Epoch 998 +2025-10-31 02:59:30.007736: Current learning rate: 4e-05 +2025-10-31 02:59:50.230789: train_loss -0.996 +2025-10-31 02:59:50.237092: val_loss -0.8939 +2025-10-31 02:59:50.239363: Pseudo dice [np.float32(0.9878), np.float32(0.9939), np.float32(0.995), np.float32(0.8047)] +2025-10-31 02:59:50.241242: Epoch time: 20.23 s +2025-10-31 02:59:51.464990: +2025-10-31 02:59:51.467224: Epoch 999 +2025-10-31 02:59:51.468952: Current learning rate: 2e-05 +2025-10-31 03:00:12.111485: train_loss -0.9956 +2025-10-31 03:00:12.116348: val_loss -0.8933 +2025-10-31 03:00:12.118731: Pseudo dice [np.float32(0.9877), np.float32(0.9939), np.float32(0.9948), np.float32(0.8031)] +2025-10-31 03:00:12.120857: Epoch time: 20.65 s +2025-10-31 03:00:14.511660: Training done. +2025-10-31 03:00:14.589931: Using splits from existing split file: /hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/splits_final.json +2025-10-31 03:00:14.598306: The split file contains 5 splits. +2025-10-31 03:00:14.600821: Desired fold for training: 2 +2025-10-31 03:00:14.603062: This split has 86 training and 22 validation cases. +2025-10-31 03:00:14.605817: predicting fish0000 +2025-10-31 03:00:14.610818: fish0000, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 03:00:25.492502: predicting fish0017 +2025-10-31 03:00:25.506556: fish0017, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 03:00:25.555531: predicting fish0018 +2025-10-31 03:00:25.560012: fish0018, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 03:00:25.597774: predicting fish0021 +2025-10-31 03:00:25.601938: fish0021, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 03:00:25.666522: predicting fish0022 +2025-10-31 03:00:25.671600: fish0022, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 03:00:25.759808: predicting fish0024 +2025-10-31 03:00:25.773959: fish0024, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 03:00:25.839247: predicting fish0026 +2025-10-31 03:00:25.843331: fish0026, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 03:00:25.900808: predicting fish0027 +2025-10-31 03:00:25.912819: fish0027, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 03:00:25.958820: predicting fish0032 +2025-10-31 03:00:25.963274: fish0032, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 03:00:26.030637: predicting fish0046 +2025-10-31 03:00:26.036028: fish0046, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 03:00:26.107871: predicting fish0050 +2025-10-31 03:00:26.117770: fish0050, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 03:00:26.169049: predicting fish0057 +2025-10-31 03:00:26.173869: fish0057, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 03:00:26.226638: predicting fish0066 +2025-10-31 03:00:26.263045: fish0066, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 03:00:26.307696: predicting fish0068 +2025-10-31 03:00:26.312207: fish0068, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 03:00:26.344248: predicting fish0070 +2025-10-31 03:00:26.349235: fish0070, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 03:00:26.382598: predicting fish0084 +2025-10-31 03:00:26.386548: fish0084, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 03:00:26.424686: predicting fish0085 +2025-10-31 03:00:26.428174: fish0085, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 03:00:26.482884: predicting fish0086 +2025-10-31 03:00:26.486780: fish0086, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 03:00:26.517985: predicting fish0087 +2025-10-31 03:00:26.521750: fish0087, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 03:00:26.546907: predicting fish0090 +2025-10-31 03:00:26.550549: fish0090, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 03:00:26.591214: predicting fish0093 +2025-10-31 03:00:26.595457: fish0093, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 03:00:26.637952: predicting fish0102 +2025-10-31 03:00:26.642178: fish0102, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 03:00:35.316775: Validation complete +2025-10-31 03:00:35.319004: Mean Validation Dice: 0.9437516455461267 diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0000.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0000.png new file mode 100644 index 0000000000000000000000000000000000000000..1ef8504fe9937899a1bdc1b831623c005383a189 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0000.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0017.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0017.png new file mode 100644 index 0000000000000000000000000000000000000000..97dfb63faeca745de3abfee1d41382051b3efee9 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0017.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0018.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0018.png new file mode 100644 index 0000000000000000000000000000000000000000..87ce49d00af964e6cd7d7eb74706f60ce81878d9 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0018.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0021.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0021.png new file mode 100644 index 0000000000000000000000000000000000000000..ccfbf873163d2249573d1a5d69f2c08bd4a113fb Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0021.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0022.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0022.png new file mode 100644 index 0000000000000000000000000000000000000000..d4c620a5d5143f485c8c981d1c16ed2a3a2d06ce Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0022.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0024.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0024.png new file mode 100644 index 0000000000000000000000000000000000000000..90b6a72ddfe2c8277aaa3e52e75d35f44f47c5a2 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0024.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0026.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0026.png new file mode 100644 index 0000000000000000000000000000000000000000..7179fd926e79985914660cfc2813beae35b6aee4 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0026.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0027.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0027.png new file mode 100644 index 0000000000000000000000000000000000000000..df672eb60912f5ec594635392ef42f80c6e9dc0a Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0027.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0032.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0032.png new file mode 100644 index 0000000000000000000000000000000000000000..c885404ac2fb9cce6aea6829d7b3979b7356bb67 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0032.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0046.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0046.png new file mode 100644 index 0000000000000000000000000000000000000000..6cb2ab127c2e85bb98efc62360b882c1fba43fa0 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0046.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0050.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0050.png new file mode 100644 index 0000000000000000000000000000000000000000..810b0d91a72d715287a7476dfa6d18f67fdb975b Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0050.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0057.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0057.png new file mode 100644 index 0000000000000000000000000000000000000000..644baf737273d932712c96ff968255f662d6e0f4 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0057.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0066.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0066.png new file mode 100644 index 0000000000000000000000000000000000000000..120a92c43f12e8bcaf64f94b352bbb0392d9f291 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0066.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0068.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0068.png new file mode 100644 index 0000000000000000000000000000000000000000..ca5cf1a2da35b86423aece1f546b4014788e1f7a Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0068.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0070.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0070.png new file mode 100644 index 0000000000000000000000000000000000000000..83566730b3b5e5b68cf1a9234515d293a29b623f Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0070.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0084.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0084.png new file mode 100644 index 0000000000000000000000000000000000000000..b65e00f4c230fd8b8c54adb42570d3fb5e9c1507 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0084.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0085.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0085.png new file mode 100644 index 0000000000000000000000000000000000000000..5575c117b6bc92b50dd307de435e0fcae931cfbe Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0085.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0086.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0086.png new file mode 100644 index 0000000000000000000000000000000000000000..1f2a969621707491275101b87627f132067c1ab6 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0086.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0087.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0087.png new file mode 100644 index 0000000000000000000000000000000000000000..3a6b6d7969809fef863f5d2294ef218f1fa11c1a Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0087.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0090.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0090.png new file mode 100644 index 0000000000000000000000000000000000000000..044aa8ea12584ab2d32801a694f34af6c33428ed Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0090.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0093.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0093.png new file mode 100644 index 0000000000000000000000000000000000000000..ad907be170ca044430dabcd9972f845b3143f5a6 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0093.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0102.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0102.png new file mode 100644 index 0000000000000000000000000000000000000000..1b1cd69c0c587f1ac3a197d0ca4f96bc08bdf7b7 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0102.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/summary.json b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/summary.json new file mode 100644 index 0000000000000000000000000000000000000000..e5ef9e20db625b08fc5fd3b9d29b8760359fba19 --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/summary.json @@ -0,0 +1,1068 @@ +{ + "foreground_mean": { + "Dice": 0.9437516455461267, + "FN": 107.77272727272728, + "FP": 116.81818181818184, + "IoU": 0.9077986454923727, + "TN": 92550.18181818181, + "TP": 11673.227272727274, + "n_pred": 11790.045454545454, + "n_ref": 11781.0 + }, + "mean": { + "1": { + "Dice": 0.9874707143212667, + "FN": 66.0909090909091, + "FP": 90.0, + "IoU": 0.9753434303183252, + "TN": 98191.63636363637, + "TP": 6100.272727272727, + "n_pred": 6190.272727272727, + "n_ref": 6166.363636363636 + }, + "2": { + "Dice": 0.9938292776241296, + "FN": 70.4090909090909, + "FP": 64.22727272727273, + "IoU": 0.9877739761172211, + "TN": 93154.5, + "TP": 11158.863636363636, + "n_pred": 11223.09090909091, + "n_ref": 11229.272727272728 + }, + "3": { + "Dice": 0.9949291641052628, + "FN": 112.18181818181819, + "FP": 180.45454545454547, + "IoU": 0.9899251259017476, + "TN": 75364.45454545454, + "TP": 28790.909090909092, + "n_pred": 28971.363636363636, + "n_ref": 28903.090909090908 + }, + "4": { + "Dice": 0.7987774261338476, + "FN": 182.4090909090909, + "FP": 132.5909090909091, + "IoU": 0.6781520496321969, + "TN": 103490.13636363637, + "TP": 642.8636363636364, + "n_pred": 775.4545454545455, + "n_ref": 825.2727272727273 + } + }, + "metric_per_case": [ + { + "metrics": { + "1": { + "Dice": 0.9888114155991568, + "FN": 22, + "FP": 116, + "IoU": 0.9778704297626684, + "TN": 98212, + "TP": 6098, + "n_pred": 6214, + "n_ref": 6120 + }, + "2": { + "Dice": 0.9935723951285521, + "FN": 63, + "FP": 51, + "IoU": 0.9872268907563025, + "TN": 95523, + "TP": 8811, + "n_pred": 8862, + "n_ref": 8874 + }, + "3": { + "Dice": 0.9969604863221885, + "FN": 48, + "FP": 96, + "IoU": 0.9939393939393939, + "TN": 80688, + "TP": 23616, + "n_pred": 23712, + "n_ref": 23664 + }, + "4": { + "Dice": 0.5804274465691789, + "FN": 48, + "FP": 325, + "IoU": 0.40887480190174325, + "TN": 103817, + "TP": 258, + "n_pred": 583, + "n_ref": 306 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0000.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0000.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9850582805288274, + "FN": 28, + "FP": 163, + "IoU": 0.9705564976106058, + "TN": 97961, + "TP": 6296, + "n_pred": 6459, + "n_ref": 6324 + }, + "2": { + "Dice": 0.9892547064385799, + "FN": 222, + "FP": 28, + "IoU": 0.9787378805919374, + "TN": 92690, + "TP": 11508, + "n_pred": 11536, + "n_ref": 11730 + }, + "3": { + "Dice": 0.9897430887955456, + "FN": 0, + "FP": 630, + "IoU": 0.9796944498162831, + "TN": 73422, + "TP": 30396, + "n_pred": 31026, + "n_ref": 30396 + }, + "4": { + "Dice": 0.8, + "FN": 408, + "FP": 102, + "IoU": 0.6666666666666666, + "TN": 102918, + "TP": 1020, + "n_pred": 1122, + "n_ref": 1428 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0017.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0017.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9869046626073901, + "FN": 102, + "FP": 55, + "IoU": 0.974147867610736, + "TN": 98375, + "TP": 5916, + "n_pred": 5971, + "n_ref": 6018 + }, + "2": { + "Dice": 0.9937304075235109, + "FN": 136, + "FP": 0, + "IoU": 0.9875389408099688, + "TN": 93534, + "TP": 10778, + "n_pred": 10778, + "n_ref": 10914 + }, + "3": { + "Dice": 0.994735967196764, + "FN": 204, + "FP": 81, + "IoU": 0.989527064270753, + "TN": 77235, + "TP": 26928, + "n_pred": 27009, + "n_ref": 27132 + }, + "4": { + "Dice": 0.8563419761737912, + "FN": 1, + "FP": 204, + "IoU": 0.7487745098039216, + "TN": 103632, + "TP": 611, + "n_pred": 815, + "n_ref": 612 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0018.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0018.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9957122439256789, + "FN": 54, + "FP": 0, + "IoU": 0.99146110056926, + "TN": 98124, + "TP": 6270, + "n_pred": 6270, + "n_ref": 6324 + }, + "2": { + "Dice": 0.9974825716498839, + "FN": 0, + "FP": 52, + "IoU": 0.9949777863627584, + "TN": 94094, + "TP": 10302, + "n_pred": 10354, + "n_ref": 10302 + }, + "3": { + "Dice": 0.9901543519956161, + "FN": 539, + "FP": 0, + "IoU": 0.9805006873598148, + "TN": 76806, + "TP": 27103, + "n_pred": 27103, + "n_ref": 27642 + }, + "4": { + "Dice": 0.5234124438742784, + "FN": 0, + "FP": 743, + "IoU": 0.35447437011294525, + "TN": 103297, + "TP": 408, + "n_pred": 1151, + "n_ref": 408 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0021.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0021.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9833333333333333, + "FN": 59, + "FP": 143, + "IoU": 0.9672131147540983, + "TN": 98287, + "TP": 5959, + "n_pred": 6102, + "n_ref": 6018 + }, + "2": { + "Dice": 0.9966422589910595, + "FN": 24, + "FP": 59, + "IoU": 0.9933069913716636, + "TN": 92047, + "TP": 12318, + "n_pred": 12377, + "n_ref": 12342 + }, + "3": { + "Dice": 0.9979986657771848, + "FN": 0, + "FP": 126, + "IoU": 0.996005326231691, + "TN": 72906, + "TP": 31416, + "n_pred": 31542, + "n_ref": 31416 + }, + "4": { + "Dice": 0.9058995611896635, + "FN": 193, + "FP": 0, + "IoU": 0.8279857397504456, + "TN": 103326, + "TP": 929, + "n_pred": 929, + "n_ref": 1122 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0022.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0022.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9872871561753602, + "FN": 19, + "FP": 146, + "IoU": 0.9748934875228241, + "TN": 97876, + "TP": 6407, + "n_pred": 6553, + "n_ref": 6426 + }, + "2": { + "Dice": 0.999194576817236, + "FN": 5, + "FP": 19, + "IoU": 0.9983904500033532, + "TN": 89537, + "TP": 14887, + "n_pred": 14906, + "n_ref": 14892 + }, + "3": { + "Dice": 0.9984907257211368, + "FN": 102, + "FP": 5, + "IoU": 0.9969860003943551, + "TN": 68947, + "TP": 35394, + "n_pred": 35399, + "n_ref": 35496 + }, + "4": { + "Dice": 0.875, + "FN": 0, + "FP": 204, + "IoU": 0.7777777777777778, + "TN": 103530, + "TP": 714, + "n_pred": 918, + "n_ref": 714 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0024.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0024.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9830949284785435, + "FN": 102, + "FP": 119, + "IoU": 0.9667519181585678, + "TN": 97801, + "TP": 6426, + "n_pred": 6545, + "n_ref": 6528 + }, + "2": { + "Dice": 0.9903846153846154, + "FN": 102, + "FP": 102, + "IoU": 0.9809523809523809, + "TN": 93738, + "TP": 10506, + "n_pred": 10608, + "n_ref": 10608 + }, + "3": { + "Dice": 0.9934789359279578, + "FN": 276, + "FP": 102, + "IoU": 0.9870423693953105, + "TN": 75276, + "TP": 28794, + "n_pred": 28896, + "n_ref": 29070 + }, + "4": { + "Dice": 0.7346465816917729, + "FN": 182, + "FP": 276, + "IoU": 0.5805860805860806, + "TN": 103356, + "TP": 634, + "n_pred": 910, + "n_ref": 816 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0026.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0026.png" + }, + { + "metrics": { + "1": { + "Dice": 0.984809721778062, + "FN": 63, + "FP": 127, + "IoU": 0.9700740274058907, + "TN": 98099, + "TP": 6159, + "n_pred": 6286, + "n_ref": 6222 + }, + "2": { + "Dice": 0.9932712795783335, + "FN": 17, + "FP": 103, + "IoU": 0.9866325052913, + "TN": 95471, + "TP": 8857, + "n_pred": 8960, + "n_ref": 8874 + }, + "3": { + "Dice": 0.9938835965304861, + "FN": 40, + "FP": 247, + "IoU": 0.9878415589917391, + "TN": 80843, + "TP": 23318, + "n_pred": 23565, + "n_ref": 23358 + }, + "4": { + "Dice": 0.7936132465996452, + "FN": 349, + "FP": 0, + "IoU": 0.657843137254902, + "TN": 103428, + "TP": 671, + "n_pred": 671, + "n_ref": 1020 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0027.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0027.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9667715447778374, + "FN": 433, + "FP": 0, + "IoU": 0.9356803327391563, + "TN": 97716, + "TP": 6299, + "n_pred": 6299, + "n_ref": 6732 + }, + "2": { + "Dice": 0.985656047108561, + "FN": 0, + "FP": 285, + "IoU": 0.9717177731467699, + "TN": 94371, + "TP": 9792, + "n_pred": 10077, + "n_ref": 9792 + }, + "3": { + "Dice": 0.9952036599763873, + "FN": 158, + "FP": 102, + "IoU": 0.9904531100829845, + "TN": 77214, + "TP": 26974, + "n_pred": 27076, + "n_ref": 27132 + }, + "4": { + "Dice": 0.7527675276752768, + "FN": 102, + "FP": 166, + "IoU": 0.6035502958579881, + "TN": 103772, + "TP": 408, + "n_pred": 574, + "n_ref": 510 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0032.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0032.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9806949806949807, + "FN": 74, + "FP": 156, + "IoU": 0.9621212121212122, + "TN": 98376, + "TP": 5842, + "n_pred": 5998, + "n_ref": 5916 + }, + "2": { + "Dice": 0.9884867058726083, + "FN": 204, + "FP": 74, + "IoU": 0.9772355060596135, + "TN": 92236, + "TP": 11934, + "n_pred": 12008, + "n_ref": 12138 + }, + "3": { + "Dice": 0.9907722195240408, + "FN": 0, + "FP": 551, + "IoU": 0.9817131857555341, + "TN": 74317, + "TP": 29580, + "n_pred": 30131, + "n_ref": 29580 + }, + "4": { + "Dice": 0.7850568489442339, + "FN": 397, + "FP": 0, + "IoU": 0.6461675579322638, + "TN": 103326, + "TP": 725, + "n_pred": 725, + "n_ref": 1122 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0046.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0046.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9806795469686875, + "FN": 28, + "FP": 204, + "IoU": 0.9620915032679739, + "TN": 98328, + "TP": 5888, + "n_pred": 6092, + "n_ref": 5916 + }, + "2": { + "Dice": 0.9961342828077314, + "FN": 0, + "FP": 114, + "IoU": 0.992298338062424, + "TN": 89646, + "TP": 14688, + "n_pred": 14802, + "n_ref": 14688 + }, + "3": { + "Dice": 0.9985401459854014, + "FN": 102, + "FP": 0, + "IoU": 0.9970845481049563, + "TN": 69462, + "TP": 34884, + "n_pred": 34884, + "n_ref": 34986 + }, + "4": { + "Dice": 0.8613406795224977, + "FN": 286, + "FP": 16, + "IoU": 0.7564516129032258, + "TN": 103208, + "TP": 938, + "n_pred": 954, + "n_ref": 1224 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0050.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0050.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9950288646568313, + "FN": 17, + "FP": 45, + "IoU": 0.9901069092069571, + "TN": 98181, + "TP": 6205, + "n_pred": 6250, + "n_ref": 6222 + }, + "2": { + "Dice": 0.9865319865319865, + "FN": 45, + "FP": 171, + "IoU": 0.973421926910299, + "TN": 96321, + "TP": 7911, + "n_pred": 8082, + "n_ref": 7956 + }, + "3": { + "Dice": 0.9945078158005914, + "FN": 171, + "FP": 102, + "IoU": 0.9890756302521009, + "TN": 79458, + "TP": 24717, + "n_pred": 24819, + "n_ref": 24888 + }, + "4": { + "Dice": 0.81, + "FN": 228, + "FP": 0, + "IoU": 0.680672268907563, + "TN": 103734, + "TP": 486, + "n_pred": 486, + "n_ref": 714 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0057.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0057.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9967733013736517, + "FN": 0, + "FP": 35, + "IoU": 0.993567358941371, + "TN": 99007, + "TP": 5406, + "n_pred": 5441, + "n_ref": 5406 + }, + "2": { + "Dice": 0.9997384937238494, + "FN": 4, + "FP": 0, + "IoU": 0.9994771241830065, + "TN": 96798, + "TP": 7646, + "n_pred": 7646, + "n_ref": 7650 + }, + "3": { + "Dice": 0.9993610223642172, + "FN": 0, + "FP": 30, + "IoU": 0.9987228607918263, + "TN": 80958, + "TP": 23460, + "n_pred": 23490, + "n_ref": 23460 + }, + "4": { + "Dice": 0.9622331691297209, + "FN": 26, + "FP": 20, + "IoU": 0.9272151898734177, + "TN": 103816, + "TP": 586, + "n_pred": 606, + "n_ref": 612 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0066.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0066.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9875602550147722, + "FN": 75, + "FP": 85, + "IoU": 0.9754262018123177, + "TN": 97937, + "TP": 6351, + "n_pred": 6436, + "n_ref": 6426 + }, + "2": { + "Dice": 0.99148470577042, + "FN": 85, + "FP": 94, + "IoU": 0.9831132075471698, + "TN": 93848, + "TP": 10421, + "n_pred": 10515, + "n_ref": 10506 + }, + "3": { + "Dice": 0.9935508835289565, + "FN": 94, + "FP": 306, + "IoU": 0.9871844162501602, + "TN": 73236, + "TP": 30812, + "n_pred": 31118, + "n_ref": 30906 + }, + "4": { + "Dice": 0.8571428571428571, + "FN": 306, + "FP": 0, + "IoU": 0.75, + "TN": 103224, + "TP": 918, + "n_pred": 918, + "n_ref": 1224 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0068.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0068.png" + }, + { + "metrics": { + "1": { + "Dice": 1.0, + "FN": 0, + "FP": 0, + "IoU": 1.0, + "TN": 98328, + "TP": 6120, + "n_pred": 6120, + "n_ref": 6120 + }, + "2": { + "Dice": 0.9959183673469387, + "FN": 102, + "FP": 0, + "IoU": 0.991869918699187, + "TN": 91902, + "TP": 12444, + "n_pred": 12444, + "n_ref": 12546 + }, + "3": { + "Dice": 0.9918433931484503, + "FN": 0, + "FP": 510, + "IoU": 0.9838187702265372, + "TN": 72930, + "TP": 31008, + "n_pred": 31518, + "n_ref": 31008 + }, + "4": { + "Dice": 0.6915254237288135, + "FN": 408, + "FP": 138, + "IoU": 0.5284974093264249, + "TN": 103290, + "TP": 612, + "n_pred": 750, + "n_ref": 1020 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0070.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0070.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9873498799039231, + "FN": 158, + "FP": 0, + "IoU": 0.9750158127767236, + "TN": 98124, + "TP": 6166, + "n_pred": 6166, + "n_ref": 6324 + }, + "2": { + "Dice": 0.9965191447041273, + "FN": 12, + "FP": 72, + "IoU": 0.9930624380574826, + "TN": 92340, + "TP": 12024, + "n_pred": 12096, + "n_ref": 12036 + }, + "3": { + "Dice": 0.9976036302452455, + "FN": 129, + "FP": 12, + "IoU": 0.9952187182095625, + "TN": 74958, + "TP": 29349, + "n_pred": 29361, + "n_ref": 29478 + }, + "4": { + "Dice": 0.9230769230769231, + "FN": 0, + "FP": 102, + "IoU": 0.8571428571428571, + "TN": 103734, + "TP": 612, + "n_pred": 714, + "n_ref": 612 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0084.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0084.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9908173332321469, + "FN": 0, + "FP": 121, + "IoU": 0.9818017747029628, + "TN": 97799, + "TP": 6528, + "n_pred": 6649, + "n_ref": 6528 + }, + "2": { + "Dice": 0.9973534971644612, + "FN": 77, + "FP": 0, + "IoU": 0.9947209653092006, + "TN": 89862, + "TP": 14509, + "n_pred": 14509, + "n_ref": 14586 + }, + "3": { + "Dice": 0.9976631314039187, + "FN": 156, + "FP": 0, + "IoU": 0.9953371592539455, + "TN": 70992, + "TP": 33300, + "n_pred": 33300, + "n_ref": 33456 + }, + "4": { + "Dice": 0.8662420382165605, + "FN": 0, + "FP": 189, + "IoU": 0.7640449438202247, + "TN": 103647, + "TP": 612, + "n_pred": 801, + "n_ref": 612 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0085.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0085.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9859250466338816, + "FN": 0, + "FP": 166, + "IoU": 0.9722408026755853, + "TN": 98468, + "TP": 5814, + "n_pred": 5980, + "n_ref": 5814 + }, + "2": { + "Dice": 0.9854816716130584, + "FN": 362, + "FP": 0, + "IoU": 0.9713788741302973, + "TN": 91800, + "TP": 12286, + "n_pred": 12286, + "n_ref": 12648 + }, + "3": { + "Dice": 0.9917937841585773, + "FN": 0, + "FP": 503, + "IoU": 0.9837211560244669, + "TN": 73549, + "TP": 30396, + "n_pred": 30899, + "n_ref": 30396 + }, + "4": { + "Dice": 0.75, + "FN": 306, + "FP": 102, + "IoU": 0.6, + "TN": 103428, + "TP": 612, + "n_pred": 714, + "n_ref": 918 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0086.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0086.png" + }, + { + "metrics": { + "1": { + "Dice": 0.991304347826087, + "FN": 0, + "FP": 102, + "IoU": 0.9827586206896551, + "TN": 98532, + "TP": 5814, + "n_pred": 5916, + "n_ref": 5814 + }, + "2": { + "Dice": 0.9999429972068631, + "FN": 1, + "FP": 0, + "IoU": 0.9998860009119928, + "TN": 95676, + "TP": 8771, + "n_pred": 8771, + "n_ref": 8772 + }, + "3": { + "Dice": 0.9958475966699751, + "FN": 0, + "FP": 205, + "IoU": 0.9917295356436842, + "TN": 79661, + "TP": 24582, + "n_pred": 24787, + "n_ref": 24582 + }, + "4": { + "Dice": 0.7727272727272727, + "FN": 340, + "FP": 0, + "IoU": 0.6296296296296297, + "TN": 103530, + "TP": 578, + "n_pred": 578, + "n_ref": 918 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0087.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0087.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9875406713752877, + "FN": 0, + "FP": 157, + "IoU": 0.9753879918482521, + "TN": 98069, + "TP": 6222, + "n_pred": 6379, + "n_ref": 6222 + }, + "2": { + "Dice": 0.9968413496051687, + "FN": 88, + "FP": 0, + "IoU": 0.9937025905252612, + "TN": 90474, + "TP": 13886, + "n_pred": 13886, + "n_ref": 13974 + }, + "3": { + "Dice": 0.9945529507358031, + "FN": 0, + "FP": 362, + "IoU": 0.9891649206824304, + "TN": 71038, + "TP": 33048, + "n_pred": 33410, + "n_ref": 33048 + }, + "4": { + "Dice": 0.7609055770292656, + "FN": 433, + "FP": 0, + "IoU": 0.6140819964349377, + "TN": 103326, + "TP": 689, + "n_pred": 689, + "n_ref": 1122 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0090.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0090.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9957001939128235, + "FN": 11, + "FP": 40, + "IoU": 0.9914372061786434, + "TN": 98492, + "TP": 5905, + "n_pred": 5945, + "n_ref": 5916 + }, + "2": { + "Dice": 0.9987760097919217, + "FN": 0, + "FP": 28, + "IoU": 0.9975550122249389, + "TN": 92996, + "TP": 11424, + "n_pred": 11452, + "n_ref": 11424 + }, + "3": { + "Dice": 0.9940569283703472, + "FN": 323, + "FP": 0, + "IoU": 0.9881840796019901, + "TN": 77112, + "TP": 27013, + "n_pred": 27013, + "n_ref": 27336 + }, + "4": { + "Dice": 0.7272727272727273, + "FN": 0, + "FP": 306, + "IoU": 0.5714285714285714, + "TN": 103734, + "TP": 408, + "n_pred": 714, + "n_ref": 408 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0093.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0093.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9831980062706005, + "FN": 209, + "FP": 0, + "IoU": 0.9669512966476913, + "TN": 98124, + "TP": 6115, + "n_pred": 6115, + "n_ref": 6324 + }, + "2": { + "Dice": 0.9918460369713852, + "FN": 0, + "FP": 161, + "IoU": 0.9838239726715563, + "TN": 94495, + "TP": 9792, + "n_pred": 9953, + "n_ref": 9792 + }, + "3": { + "Dice": 0.9976986301369863, + "FN": 126, + "FP": 0, + "IoU": 0.9954078285589328, + "TN": 77010, + "TP": 27312, + "n_pred": 27312, + "n_ref": 27438 + }, + "4": { + "Dice": 0.9834710743801653, + "FN": 0, + "FP": 24, + "IoU": 0.967479674796748, + "TN": 103710, + "TP": 714, + "n_pred": 738, + "n_ref": 714 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_2/validation/fish0102.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0102.png" + } + ] +} \ No newline at end of file diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/checkpoint_best.pth b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/checkpoint_best.pth new file mode 100644 index 0000000000000000000000000000000000000000..b2fc0bd4b775ef143c5148e6621d3b0b6e639122 --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/checkpoint_best.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbfa96e44ecda37103531608332ba0a93616c13fa1bb9fdd41f258c73c51a517 +size 358694786 diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/checkpoint_final.pth b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/checkpoint_final.pth new file mode 100644 index 0000000000000000000000000000000000000000..85f3e55f41a3e4163eb5b457464d25cc5a47122b --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/checkpoint_final.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce69713051c12fdcf9f5d78b56c8442d23d58067457299ce282e586002a636ac +size 358731822 diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/debug.json b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/debug.json new file mode 100644 index 0000000000000000000000000000000000000000..062b988391cc54b1658a3884f8c54bf262d0da97 --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/debug.json @@ -0,0 +1,53 @@ +{ + "_best_ema": "None", + "batch_size": "5", + "configuration_manager": "{'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 5, 'patch_size': [1024, 112], 'median_image_size_in_voxels': [1024.0, 102.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['ZScoreNormalization'], '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': 8, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 1], [2, 1], [2, 1]], 'n_conv_per_stage': [2, 2, 2, 2, 2, 2, 2, 2], 'n_conv_per_stage_decoder': [2, 2, 2, 2, 2, 2, 2], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}", + "configuration_name": "2d", + "cudnn_version": 90100, + "current_epoch": "0", + "dataloader_train": "", + "dataloader_train.generator": "", + "dataloader_train.num_processes": "12", + "dataloader_train.transform": "None", + "dataloader_val": "", + "dataloader_val.generator": "", + "dataloader_val.num_processes": "6", + "dataloader_val.transform": "None", + "dataset_json": "{'channel_names': {'0': '\u00b5OCT'}, 'labels': {'background': 0, 'Retina': 1, 'VCD': 2, 'lens': 3, 'cornea': 4}, 'numTraining': 108, 'file_ending': '.png'}", + "device": "cuda:0", + "disable_checkpointing": "False", + "enable_deep_supervision": "True", + "fold": "3", + "folder_with_segs_from_previous_stage": "None", + "gpu_name": "NVIDIA A100 80GB PCIe", + "grad_scaler": "", + "hostname": "hpc5", + "inference_allowed_mirroring_axes": "(0, 1)", + "initial_lr": "0.01", + "is_cascaded": "False", + "is_ddp": "False", + "label_manager": "", + "local_rank": "0", + "log_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/training_log_2025_10_31_03_00_44.txt", + "logger": "", + "loss": "DeepSupervisionWrapper(\n (loss): DC_and_CE_loss(\n (ce): RobustCrossEntropyLoss()\n (dc): OptimizedModule(\n (_orig_mod): MemoryEfficientSoftDiceLoss()\n )\n )\n)", + "lr_scheduler": "", + "my_init_kwargs": "{'plans': {'dataset_name': 'Dataset001_zebrafish', 'plans_name': 'nnUNetPlans', 'original_median_spacing_after_transp': [999.0, 1.0, 1.0], 'original_median_shape_after_transp': [1, 1024, 102], 'image_reader_writer': 'NaturalImage2DIO', 'transpose_forward': [0, 1, 2], 'transpose_backward': [0, 1, 2], 'configurations': {'2d': {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 5, 'patch_size': [1024, 112], 'median_image_size_in_voxels': [1024.0, 102.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['ZScoreNormalization'], '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': 8, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 1], [2, 1], [2, 1]], 'n_conv_per_stage': [2, 2, 2, 2, 2, 2, 2, 2], 'n_conv_per_stage_decoder': [2, 2, 2, 2, 2, 2, 2], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}}, 'experiment_planner_used': 'ExperimentPlanner', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 255.0, 'mean': 49.659568786621094, 'median': 45.0, 'min': 0.0, 'percentile_00_5': 10.0, 'percentile_99_5': 163.0, 'std': 24.689043045043945}}}, 'configuration': '2d', 'fold': 3, 'dataset_json': {'channel_names': {'0': '\u00b5OCT'}, 'labels': {'background': 0, 'Retina': 1, 'VCD': 2, 'lens': 3, 'cornea': 4}, 'numTraining': 108, 'file_ending': '.png'}, 'device': device(type='cuda')}", + "network": "OptimizedModule", + "num_epochs": "1000", + "num_input_channels": "1", + "num_iterations_per_epoch": "250", + "num_val_iterations_per_epoch": "50", + "optimizer": "SGD (\nParameter Group 0\n dampening: 0\n differentiable: False\n foreach: None\n fused: None\n initial_lr: 0.01\n lr: 0.01\n maximize: False\n momentum: 0.99\n nesterov: True\n weight_decay: 3e-05\n)", + "output_folder": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3", + "output_folder_base": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d", + "oversample_foreground_percent": "0.33", + "plans_manager": "{'dataset_name': 'Dataset001_zebrafish', 'plans_name': 'nnUNetPlans', 'original_median_spacing_after_transp': [999.0, 1.0, 1.0], 'original_median_shape_after_transp': [1, 1024, 102], 'image_reader_writer': 'NaturalImage2DIO', 'transpose_forward': [0, 1, 2], 'transpose_backward': [0, 1, 2], 'configurations': {'2d': {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 5, 'patch_size': [1024, 112], 'median_image_size_in_voxels': [1024.0, 102.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['ZScoreNormalization'], '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': 8, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 1], [2, 1], [2, 1]], 'n_conv_per_stage': [2, 2, 2, 2, 2, 2, 2, 2], 'n_conv_per_stage_decoder': [2, 2, 2, 2, 2, 2, 2], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}}, 'experiment_planner_used': 'ExperimentPlanner', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 255.0, 'mean': 49.659568786621094, 'median': 45.0, 'min': 0.0, 'percentile_00_5': 10.0, 'percentile_99_5': 163.0, 'std': 24.689043045043945}}}", + "preprocessed_dataset_folder": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/nnUNetPlans_2d", + "preprocessed_dataset_folder_base": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish", + "probabilistic_oversampling": "False", + "save_every": "50", + "torch_version": "2.5.1+cu121", + "was_initialized": "True", + "weight_decay": "3e-05" +} \ No newline at end of file diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/progress.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/progress.png new file mode 100644 index 0000000000000000000000000000000000000000..49092f6eca38fa8f3f1e27eb6dc695a621207075 --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/progress.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:573c635e40f58956dd0c728a72fcda05e60d1a3e9a5d43c0929de3956f8af53d +size 1047872 diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/training_log_2025_10_30_12_32_05.txt b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/training_log_2025_10_30_12_32_05.txt new file mode 100644 index 0000000000000000000000000000000000000000..53f363c337907507406a24d6073c9129b2a5f575 --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/training_log_2025_10_30_12_32_05.txt @@ -0,0 +1,24 @@ + +####################################################################### +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. +####################################################################### + +2025-10-30 12:32:07.455136: Using torch.compile... +2025-10-30 12:32:09.286134: do_dummy_2d_data_aug: False +2025-10-30 12:32:09.290186: Using splits from existing split file: /hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/splits_final.json +2025-10-30 12:32:09.294169: The split file contains 5 splits. +2025-10-30 12:32:09.296050: Desired fold for training: 3 +2025-10-30 12:32:09.297687: This split has 87 training and 21 validation cases. + +This is the configuration used by this training: +Configuration name: 2d + {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 5, 'patch_size': [1024, 112], 'median_image_size_in_voxels': [1024.0, 102.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['ZScoreNormalization'], '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': 8, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 1], [2, 1], [2, 1]], 'n_conv_per_stage': [2, 2, 2, 2, 2, 2, 2, 2], 'n_conv_per_stage_decoder': [2, 2, 2, 2, 2, 2, 2], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True} + +These are the global plan.json settings: + {'dataset_name': 'Dataset001_zebrafish', 'plans_name': 'nnUNetPlans', 'original_median_spacing_after_transp': [999.0, 1.0, 1.0], 'original_median_shape_after_transp': [1, 1024, 102], 'image_reader_writer': 'NaturalImage2DIO', 'transpose_forward': [0, 1, 2], 'transpose_backward': [0, 1, 2], 'experiment_planner_used': 'ExperimentPlanner', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 255.0, 'mean': 49.659568786621094, 'median': 45.0, 'min': 0.0, 'percentile_00_5': 10.0, 'percentile_99_5': 163.0, 'std': 24.689043045043945}}} + +2025-10-30 12:32:10.767526: Unable to plot network architecture: nnUNet_compile is enabled! +2025-10-30 12:32:10.839905: +2025-10-30 12:32:10.842110: Epoch 0 +2025-10-30 12:32:10.844226: Current learning rate: 0.01 diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/training_log_2025_10_31_03_00_44.txt b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/training_log_2025_10_31_03_00_44.txt new file mode 100644 index 0000000000000000000000000000000000000000..6ef202680f1a3a6fa5e98590357c826a5be6dced --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/training_log_2025_10_31_03_00_44.txt @@ -0,0 +1,7145 @@ + +####################################################################### +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. +####################################################################### + +2025-10-31 03:00:47.179034: Using torch.compile... +2025-10-31 03:00:48.503361: do_dummy_2d_data_aug: False +2025-10-31 03:00:48.506001: Using splits from existing split file: /hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/splits_final.json +2025-10-31 03:00:48.507953: The split file contains 5 splits. +2025-10-31 03:00:48.509335: Desired fold for training: 3 +2025-10-31 03:00:48.510627: This split has 87 training and 21 validation cases. + +This is the configuration used by this training: +Configuration name: 2d + {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 5, 'patch_size': [1024, 112], 'median_image_size_in_voxels': [1024.0, 102.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['ZScoreNormalization'], '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': 8, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 1], [2, 1], [2, 1]], 'n_conv_per_stage': [2, 2, 2, 2, 2, 2, 2, 2], 'n_conv_per_stage_decoder': [2, 2, 2, 2, 2, 2, 2], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True} + +These are the global plan.json settings: + {'dataset_name': 'Dataset001_zebrafish', 'plans_name': 'nnUNetPlans', 'original_median_spacing_after_transp': [999.0, 1.0, 1.0], 'original_median_shape_after_transp': [1, 1024, 102], 'image_reader_writer': 'NaturalImage2DIO', 'transpose_forward': [0, 1, 2], 'transpose_backward': [0, 1, 2], 'experiment_planner_used': 'ExperimentPlanner', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 255.0, 'mean': 49.659568786621094, 'median': 45.0, 'min': 0.0, 'percentile_00_5': 10.0, 'percentile_99_5': 163.0, 'std': 24.689043045043945}}} + +2025-10-31 03:00:50.480118: Unable to plot network architecture: nnUNet_compile is enabled! +2025-10-31 03:00:50.498480: +2025-10-31 03:00:50.500539: Epoch 0 +2025-10-31 03:00:50.502172: Current learning rate: 0.01 +2025-10-31 03:01:49.541226: train_loss -0.2092 +2025-10-31 03:01:49.545582: val_loss -0.8295 +2025-10-31 03:01:49.547401: Pseudo dice [np.float32(0.9675), np.float32(0.9716), np.float32(0.9797), np.float32(0.7102)] +2025-10-31 03:01:49.549512: Epoch time: 59.04 s +2025-10-31 03:01:49.552398: Yayy! New best EMA pseudo Dice: 0.9072999954223633 +2025-10-31 03:01:51.647938: +2025-10-31 03:01:51.649985: Epoch 1 +2025-10-31 03:01:51.652015: Current learning rate: 0.00999 +2025-10-31 03:02:13.446621: train_loss -0.8504 +2025-10-31 03:02:13.453984: val_loss -0.8804 +2025-10-31 03:02:13.455687: Pseudo dice [np.float32(0.9785), np.float32(0.9847), np.float32(0.9886), np.float32(0.7638)] +2025-10-31 03:02:13.457586: Epoch time: 21.8 s +2025-10-31 03:02:13.459264: Yayy! New best EMA pseudo Dice: 0.9093999862670898 +2025-10-31 03:02:15.698380: +2025-10-31 03:02:15.702482: Epoch 2 +2025-10-31 03:02:15.704394: Current learning rate: 0.00998 +2025-10-31 03:02:37.109049: train_loss -0.8835 +2025-10-31 03:02:37.113472: val_loss -0.886 +2025-10-31 03:02:37.115243: Pseudo dice [np.float32(0.98), np.float32(0.9871), np.float32(0.9889), np.float32(0.7728)] +2025-10-31 03:02:37.117063: Epoch time: 21.41 s +2025-10-31 03:02:37.118637: Yayy! New best EMA pseudo Dice: 0.9117000102996826 +2025-10-31 03:02:39.568900: +2025-10-31 03:02:39.573221: Epoch 3 +2025-10-31 03:02:39.576014: Current learning rate: 0.00997 +2025-10-31 03:03:02.039837: train_loss -0.9017 +2025-10-31 03:03:02.043699: val_loss -0.897 +2025-10-31 03:03:02.045143: Pseudo dice [np.float32(0.9775), np.float32(0.9891), np.float32(0.9926), np.float32(0.7848)] +2025-10-31 03:03:02.046548: Epoch time: 22.47 s +2025-10-31 03:03:02.047965: Yayy! New best EMA pseudo Dice: 0.9140999913215637 +2025-10-31 03:03:04.429435: +2025-10-31 03:03:04.431792: Epoch 4 +2025-10-31 03:03:04.433457: Current learning rate: 0.00996 +2025-10-31 03:03:26.378296: train_loss -0.9066 +2025-10-31 03:03:26.381034: val_loss -0.9023 +2025-10-31 03:03:26.383582: Pseudo dice [np.float32(0.9808), np.float32(0.9874), np.float32(0.9926), np.float32(0.7908)] +2025-10-31 03:03:26.385464: Epoch time: 21.95 s +2025-10-31 03:03:26.386911: Yayy! New best EMA pseudo Dice: 0.9164999723434448 +2025-10-31 03:03:29.121591: +2025-10-31 03:03:29.123375: Epoch 5 +2025-10-31 03:03:29.126132: Current learning rate: 0.00995 +2025-10-31 03:03:51.574395: train_loss -0.9125 +2025-10-31 03:03:51.576985: val_loss -0.9002 +2025-10-31 03:03:51.578569: Pseudo dice [np.float32(0.9837), np.float32(0.9884), np.float32(0.9927), np.float32(0.7803)] +2025-10-31 03:03:51.580130: Epoch time: 22.45 s +2025-10-31 03:03:51.581768: Yayy! New best EMA pseudo Dice: 0.9185000061988831 +2025-10-31 03:03:54.751835: +2025-10-31 03:03:54.754207: Epoch 6 +2025-10-31 03:03:54.756013: Current learning rate: 0.00995 +2025-10-31 03:04:16.756572: train_loss -0.8861 +2025-10-31 03:04:16.762307: val_loss -0.8705 +2025-10-31 03:04:16.764006: Pseudo dice [np.float32(0.9773), np.float32(0.9754), np.float32(0.9863), np.float32(0.7747)] +2025-10-31 03:04:16.765795: Epoch time: 22.01 s +2025-10-31 03:04:16.768051: Yayy! New best EMA pseudo Dice: 0.9194999933242798 +2025-10-31 03:04:19.186003: +2025-10-31 03:04:19.187824: Epoch 7 +2025-10-31 03:04:19.189466: Current learning rate: 0.00994 +2025-10-31 03:04:41.561021: train_loss -0.8936 +2025-10-31 03:04:41.565687: val_loss -0.9039 +2025-10-31 03:04:41.570690: Pseudo dice [np.float32(0.9842), np.float32(0.9899), np.float32(0.9922), np.float32(0.8021)] +2025-10-31 03:04:41.573752: Epoch time: 22.38 s +2025-10-31 03:04:41.575833: Yayy! New best EMA pseudo Dice: 0.9217000007629395 +2025-10-31 03:04:43.807411: +2025-10-31 03:04:43.809573: Epoch 8 +2025-10-31 03:04:43.811711: Current learning rate: 0.00993 +2025-10-31 03:05:05.139363: train_loss -0.9132 +2025-10-31 03:05:05.143147: val_loss -0.9029 +2025-10-31 03:05:05.145415: Pseudo dice [np.float32(0.9845), np.float32(0.9881), np.float32(0.9927), np.float32(0.782)] +2025-10-31 03:05:05.147136: Epoch time: 21.33 s +2025-10-31 03:05:05.148862: Yayy! New best EMA pseudo Dice: 0.92330002784729 +2025-10-31 03:05:07.333427: +2025-10-31 03:05:07.336367: Epoch 9 +2025-10-31 03:05:07.338131: Current learning rate: 0.00992 +2025-10-31 03:05:28.815603: train_loss -0.9212 +2025-10-31 03:05:28.818753: val_loss -0.9106 +2025-10-31 03:05:28.820453: Pseudo dice [np.float32(0.985), np.float32(0.9905), np.float32(0.9932), np.float32(0.7903)] +2025-10-31 03:05:28.822222: Epoch time: 21.48 s +2025-10-31 03:05:28.824012: Yayy! New best EMA pseudo Dice: 0.9248999953269958 +2025-10-31 03:05:31.246343: +2025-10-31 03:05:31.248505: Epoch 10 +2025-10-31 03:05:31.250220: Current learning rate: 0.00991 +2025-10-31 03:05:52.731899: train_loss -0.9232 +2025-10-31 03:05:52.735502: val_loss -0.9 +2025-10-31 03:05:52.737113: Pseudo dice [np.float32(0.9852), np.float32(0.9904), np.float32(0.9908), np.float32(0.7696)] +2025-10-31 03:05:52.739014: Epoch time: 21.49 s +2025-10-31 03:05:52.740584: Yayy! New best EMA pseudo Dice: 0.9258000254631042 +2025-10-31 03:05:55.004147: +2025-10-31 03:05:55.006383: Epoch 11 +2025-10-31 03:05:55.008221: Current learning rate: 0.0099 +2025-10-31 03:06:17.397160: train_loss -0.9319 +2025-10-31 03:06:17.399861: val_loss -0.9044 +2025-10-31 03:06:17.402005: Pseudo dice [np.float32(0.9843), np.float32(0.9903), np.float32(0.993), np.float32(0.7702)] +2025-10-31 03:06:17.403967: Epoch time: 22.39 s +2025-10-31 03:06:17.405542: Yayy! New best EMA pseudo Dice: 0.9266999959945679 +2025-10-31 03:06:19.773108: +2025-10-31 03:06:19.775641: Epoch 12 +2025-10-31 03:06:19.777799: Current learning rate: 0.00989 +2025-10-31 03:06:41.638715: train_loss -0.9326 +2025-10-31 03:06:41.642088: val_loss -0.9035 +2025-10-31 03:06:41.643879: Pseudo dice [np.float32(0.9841), np.float32(0.9898), np.float32(0.9921), np.float32(0.7728)] +2025-10-31 03:06:41.645784: Epoch time: 21.87 s +2025-10-31 03:06:41.647589: Yayy! New best EMA pseudo Dice: 0.9275000095367432 +2025-10-31 03:06:43.995403: +2025-10-31 03:06:43.997935: Epoch 13 +2025-10-31 03:06:43.999930: Current learning rate: 0.00988 +2025-10-31 03:07:06.780907: train_loss -0.9344 +2025-10-31 03:07:06.783051: val_loss -0.9052 +2025-10-31 03:07:06.788027: Pseudo dice [np.float32(0.9854), np.float32(0.9898), np.float32(0.9929), np.float32(0.7793)] +2025-10-31 03:07:06.789886: Epoch time: 22.79 s +2025-10-31 03:07:06.791882: Yayy! New best EMA pseudo Dice: 0.9283999800682068 +2025-10-31 03:07:09.365111: +2025-10-31 03:07:09.369560: Epoch 14 +2025-10-31 03:07:09.374390: Current learning rate: 0.00987 +2025-10-31 03:07:29.951970: train_loss -0.9331 +2025-10-31 03:07:29.954676: val_loss -0.9067 +2025-10-31 03:07:29.956559: Pseudo dice [np.float32(0.9863), np.float32(0.9905), np.float32(0.9925), np.float32(0.7913)] +2025-10-31 03:07:29.958419: Epoch time: 20.59 s +2025-10-31 03:07:29.961086: Yayy! New best EMA pseudo Dice: 0.9296000003814697 +2025-10-31 03:07:32.402650: +2025-10-31 03:07:32.405097: Epoch 15 +2025-10-31 03:07:32.407146: Current learning rate: 0.00986 +2025-10-31 03:07:54.975938: train_loss -0.9345 +2025-10-31 03:07:54.979402: val_loss -0.9035 +2025-10-31 03:07:54.981489: Pseudo dice [np.float32(0.9851), np.float32(0.99), np.float32(0.9932), np.float32(0.7717)] +2025-10-31 03:07:54.983400: Epoch time: 22.58 s +2025-10-31 03:07:55.002197: Yayy! New best EMA pseudo Dice: 0.9301000237464905 +2025-10-31 03:07:57.467499: +2025-10-31 03:07:57.469350: Epoch 16 +2025-10-31 03:07:57.471255: Current learning rate: 0.00986 +2025-10-31 03:08:18.775167: train_loss -0.9364 +2025-10-31 03:08:18.778069: val_loss -0.9012 +2025-10-31 03:08:18.780625: Pseudo dice [np.float32(0.9834), np.float32(0.9893), np.float32(0.992), np.float32(0.7792)] +2025-10-31 03:08:18.782236: Epoch time: 21.31 s +2025-10-31 03:08:18.783846: Yayy! New best EMA pseudo Dice: 0.9307000041007996 +2025-10-31 03:08:21.326547: +2025-10-31 03:08:21.329269: Epoch 17 +2025-10-31 03:08:21.331488: Current learning rate: 0.00985 +2025-10-31 03:08:43.539121: train_loss -0.9413 +2025-10-31 03:08:43.542231: val_loss -0.8905 +2025-10-31 03:08:43.543992: Pseudo dice [np.float32(0.9839), np.float32(0.9847), np.float32(0.9903), np.float32(0.768)] +2025-10-31 03:08:43.545662: Epoch time: 22.22 s +2025-10-31 03:08:43.547174: Yayy! New best EMA pseudo Dice: 0.9308000206947327 +2025-10-31 03:08:47.042980: +2025-10-31 03:08:47.045743: Epoch 18 +2025-10-31 03:08:47.047949: Current learning rate: 0.00984 +2025-10-31 03:09:09.924872: train_loss -0.9419 +2025-10-31 03:09:09.931359: val_loss -0.9061 +2025-10-31 03:09:09.933155: Pseudo dice [np.float32(0.9826), np.float32(0.9905), np.float32(0.9938), np.float32(0.7765)] +2025-10-31 03:09:09.934802: Epoch time: 22.89 s +2025-10-31 03:09:09.936503: Yayy! New best EMA pseudo Dice: 0.9312999844551086 +2025-10-31 03:09:12.500048: +2025-10-31 03:09:12.503108: Epoch 19 +2025-10-31 03:09:12.505021: Current learning rate: 0.00983 +2025-10-31 03:09:34.741026: train_loss -0.9481 +2025-10-31 03:09:34.743546: val_loss -0.8928 +2025-10-31 03:09:34.745149: Pseudo dice [np.float32(0.9838), np.float32(0.9903), np.float32(0.993), np.float32(0.7465)] +2025-10-31 03:09:34.746823: Epoch time: 22.24 s +2025-10-31 03:09:35.980827: +2025-10-31 03:09:35.983073: Epoch 20 +2025-10-31 03:09:35.985094: Current learning rate: 0.00982 +2025-10-31 03:09:57.453509: train_loss -0.9425 +2025-10-31 03:09:57.457143: val_loss -0.8985 +2025-10-31 03:09:57.461461: Pseudo dice [np.float32(0.9856), np.float32(0.9904), np.float32(0.9928), np.float32(0.758)] +2025-10-31 03:09:57.464134: Epoch time: 21.48 s +2025-10-31 03:09:58.462337: +2025-10-31 03:09:58.464270: Epoch 21 +2025-10-31 03:09:58.465979: Current learning rate: 0.00981 +2025-10-31 03:10:20.766056: train_loss -0.9416 +2025-10-31 03:10:20.769309: val_loss -0.9017 +2025-10-31 03:10:20.771846: Pseudo dice [np.float32(0.9849), np.float32(0.9886), np.float32(0.9928), np.float32(0.7637)] +2025-10-31 03:10:20.775012: Epoch time: 22.31 s +2025-10-31 03:10:21.846286: +2025-10-31 03:10:21.848937: Epoch 22 +2025-10-31 03:10:21.850608: Current learning rate: 0.0098 +2025-10-31 03:10:42.952961: train_loss -0.9452 +2025-10-31 03:10:42.958883: val_loss -0.9048 +2025-10-31 03:10:42.962708: Pseudo dice [np.float32(0.9846), np.float32(0.9909), np.float32(0.9936), np.float32(0.783)] +2025-10-31 03:10:42.966597: Epoch time: 21.11 s +2025-10-31 03:10:42.970783: Yayy! New best EMA pseudo Dice: 0.9319000244140625 +2025-10-31 03:10:45.290647: +2025-10-31 03:10:45.296633: Epoch 23 +2025-10-31 03:10:45.302377: Current learning rate: 0.00979 +2025-10-31 03:11:07.645502: train_loss -0.9494 +2025-10-31 03:11:07.650752: val_loss -0.9033 +2025-10-31 03:11:07.653744: Pseudo dice [np.float32(0.9837), np.float32(0.9908), np.float32(0.9936), np.float32(0.7721)] +2025-10-31 03:11:07.655448: Epoch time: 22.36 s +2025-10-31 03:11:07.657246: Yayy! New best EMA pseudo Dice: 0.932200014591217 +2025-10-31 03:11:09.843256: +2025-10-31 03:11:09.847115: Epoch 24 +2025-10-31 03:11:09.849074: Current learning rate: 0.00978 +2025-10-31 03:11:31.319828: train_loss -0.9539 +2025-10-31 03:11:31.337893: val_loss -0.9028 +2025-10-31 03:11:31.345607: Pseudo dice [np.float32(0.9845), np.float32(0.9905), np.float32(0.9938), np.float32(0.7758)] +2025-10-31 03:11:31.354176: Epoch time: 21.48 s +2025-10-31 03:11:31.361055: Yayy! New best EMA pseudo Dice: 0.9326000213623047 +2025-10-31 03:11:34.276315: +2025-10-31 03:11:34.287880: Epoch 25 +2025-10-31 03:11:34.293901: Current learning rate: 0.00977 +2025-10-31 03:11:56.747808: train_loss -0.952 +2025-10-31 03:11:56.750510: val_loss -0.9053 +2025-10-31 03:11:56.754047: Pseudo dice [np.float32(0.9847), np.float32(0.9909), np.float32(0.9927), np.float32(0.7937)] +2025-10-31 03:11:56.755651: Epoch time: 22.47 s +2025-10-31 03:11:56.757104: Yayy! New best EMA pseudo Dice: 0.9333999752998352 +2025-10-31 03:11:59.308022: +2025-10-31 03:11:59.310543: Epoch 26 +2025-10-31 03:11:59.312176: Current learning rate: 0.00977 +2025-10-31 03:12:20.248977: train_loss -0.9547 +2025-10-31 03:12:20.252669: val_loss -0.9015 +2025-10-31 03:12:20.254206: Pseudo dice [np.float32(0.9809), np.float32(0.9899), np.float32(0.9937), np.float32(0.7873)] +2025-10-31 03:12:20.255898: Epoch time: 20.94 s +2025-10-31 03:12:20.257341: Yayy! New best EMA pseudo Dice: 0.933899998664856 +2025-10-31 03:12:22.540200: +2025-10-31 03:12:22.542298: Epoch 27 +2025-10-31 03:12:22.544194: Current learning rate: 0.00976 +2025-10-31 03:12:43.452518: train_loss -0.9556 +2025-10-31 03:12:43.456381: val_loss -0.9011 +2025-10-31 03:12:43.458012: Pseudo dice [np.float32(0.9835), np.float32(0.9893), np.float32(0.9928), np.float32(0.7766)] +2025-10-31 03:12:43.459663: Epoch time: 20.91 s +2025-10-31 03:12:43.461330: Yayy! New best EMA pseudo Dice: 0.9340000152587891 +2025-10-31 03:12:45.692191: +2025-10-31 03:12:45.694840: Epoch 28 +2025-10-31 03:12:45.697584: Current learning rate: 0.00975 +2025-10-31 03:13:07.727664: train_loss -0.9593 +2025-10-31 03:13:07.731448: val_loss -0.9102 +2025-10-31 03:13:07.733481: Pseudo dice [np.float32(0.9842), np.float32(0.9904), np.float32(0.9948), np.float32(0.7917)] +2025-10-31 03:13:07.735488: Epoch time: 22.04 s +2025-10-31 03:13:07.737272: Yayy! New best EMA pseudo Dice: 0.9347000122070312 +2025-10-31 03:13:10.254963: +2025-10-31 03:13:10.257153: Epoch 29 +2025-10-31 03:13:10.258667: Current learning rate: 0.00974 +2025-10-31 03:13:32.543941: train_loss -0.9581 +2025-10-31 03:13:32.547898: val_loss -0.9008 +2025-10-31 03:13:32.549431: Pseudo dice [np.float32(0.9841), np.float32(0.9901), np.float32(0.9943), np.float32(0.7769)] +2025-10-31 03:13:32.551526: Epoch time: 22.29 s +2025-10-31 03:13:32.553090: Yayy! New best EMA pseudo Dice: 0.9348000288009644 +2025-10-31 03:13:35.391653: +2025-10-31 03:13:35.393819: Epoch 30 +2025-10-31 03:13:35.395671: Current learning rate: 0.00973 +2025-10-31 03:13:58.466553: train_loss -0.9592 +2025-10-31 03:13:58.471051: val_loss -0.9025 +2025-10-31 03:13:58.473144: Pseudo dice [np.float32(0.9841), np.float32(0.9905), np.float32(0.9935), np.float32(0.7806)] +2025-10-31 03:13:58.474789: Epoch time: 23.08 s +2025-10-31 03:13:58.476365: Yayy! New best EMA pseudo Dice: 0.9351000189781189 +2025-10-31 03:14:01.087013: +2025-10-31 03:14:01.089086: Epoch 31 +2025-10-31 03:14:01.092173: Current learning rate: 0.00972 +2025-10-31 03:14:23.995833: train_loss -0.964 +2025-10-31 03:14:24.001485: val_loss -0.8851 +2025-10-31 03:14:24.003960: Pseudo dice [np.float32(0.9852), np.float32(0.9905), np.float32(0.9911), np.float32(0.7497)] +2025-10-31 03:14:24.006419: Epoch time: 22.91 s +2025-10-31 03:14:25.237675: +2025-10-31 03:14:25.241326: Epoch 32 +2025-10-31 03:14:25.243867: Current learning rate: 0.00971 +2025-10-31 03:14:46.152898: train_loss -0.963 +2025-10-31 03:14:46.157218: val_loss -0.9106 +2025-10-31 03:14:46.158841: Pseudo dice [np.float32(0.9837), np.float32(0.9886), np.float32(0.9939), np.float32(0.8129)] +2025-10-31 03:14:46.160801: Epoch time: 20.92 s +2025-10-31 03:14:46.162462: Yayy! New best EMA pseudo Dice: 0.9355000257492065 +2025-10-31 03:14:48.505234: +2025-10-31 03:14:48.507052: Epoch 33 +2025-10-31 03:14:48.509349: Current learning rate: 0.0097 +2025-10-31 03:15:10.438348: train_loss -0.96 +2025-10-31 03:15:10.441157: val_loss -0.9027 +2025-10-31 03:15:10.443110: Pseudo dice [np.float32(0.9828), np.float32(0.9905), np.float32(0.9942), np.float32(0.7901)] +2025-10-31 03:15:10.444746: Epoch time: 21.93 s +2025-10-31 03:15:10.446378: Yayy! New best EMA pseudo Dice: 0.9358999729156494 +2025-10-31 03:15:12.907874: +2025-10-31 03:15:12.910818: Epoch 34 +2025-10-31 03:15:12.912798: Current learning rate: 0.00969 +2025-10-31 03:15:35.503942: train_loss -0.9643 +2025-10-31 03:15:35.509134: val_loss -0.9018 +2025-10-31 03:15:35.511372: Pseudo dice [np.float32(0.9835), np.float32(0.9902), np.float32(0.9931), np.float32(0.7828)] +2025-10-31 03:15:35.512870: Epoch time: 22.6 s +2025-10-31 03:15:35.515058: Yayy! New best EMA pseudo Dice: 0.9359999895095825 +2025-10-31 03:15:37.984895: +2025-10-31 03:15:37.987104: Epoch 35 +2025-10-31 03:15:37.988998: Current learning rate: 0.00968 +2025-10-31 03:15:59.814053: train_loss -0.9628 +2025-10-31 03:15:59.818051: val_loss -0.9 +2025-10-31 03:15:59.819845: Pseudo dice [np.float32(0.9842), np.float32(0.9909), np.float32(0.9932), np.float32(0.7796)] +2025-10-31 03:15:59.821746: Epoch time: 21.83 s +2025-10-31 03:15:59.823439: Yayy! New best EMA pseudo Dice: 0.9361000061035156 +2025-10-31 03:16:02.526984: +2025-10-31 03:16:02.530415: Epoch 36 +2025-10-31 03:16:02.534577: Current learning rate: 0.00968 +2025-10-31 03:16:24.518785: train_loss -0.9633 +2025-10-31 03:16:24.524333: val_loss -0.9018 +2025-10-31 03:16:24.526387: Pseudo dice [np.float32(0.9854), np.float32(0.9905), np.float32(0.9936), np.float32(0.7879)] +2025-10-31 03:16:24.528013: Epoch time: 21.99 s +2025-10-31 03:16:24.529944: Yayy! New best EMA pseudo Dice: 0.9365000128746033 +2025-10-31 03:16:26.785605: +2025-10-31 03:16:26.787861: Epoch 37 +2025-10-31 03:16:26.789945: Current learning rate: 0.00967 +2025-10-31 03:16:49.325446: train_loss -0.9636 +2025-10-31 03:16:49.330002: val_loss -0.8999 +2025-10-31 03:16:49.332799: Pseudo dice [np.float32(0.9824), np.float32(0.9879), np.float32(0.9933), np.float32(0.7865)] +2025-10-31 03:16:49.336263: Epoch time: 22.54 s +2025-10-31 03:16:49.341317: Yayy! New best EMA pseudo Dice: 0.9366000294685364 +2025-10-31 03:16:51.845561: +2025-10-31 03:16:51.847337: Epoch 38 +2025-10-31 03:16:51.848830: Current learning rate: 0.00966 +2025-10-31 03:17:12.706507: train_loss -0.9563 +2025-10-31 03:17:12.711418: val_loss -0.903 +2025-10-31 03:17:12.713023: Pseudo dice [np.float32(0.9857), np.float32(0.9904), np.float32(0.9937), np.float32(0.7784)] +2025-10-31 03:17:12.714987: Epoch time: 20.86 s +2025-10-31 03:17:12.716575: Yayy! New best EMA pseudo Dice: 0.9366000294685364 +2025-10-31 03:17:15.145969: +2025-10-31 03:17:15.148839: Epoch 39 +2025-10-31 03:17:15.152052: Current learning rate: 0.00965 +2025-10-31 03:17:36.741607: train_loss -0.9609 +2025-10-31 03:17:36.747679: val_loss -0.8928 +2025-10-31 03:17:36.751968: Pseudo dice [np.float32(0.9827), np.float32(0.9891), np.float32(0.9924), np.float32(0.7662)] +2025-10-31 03:17:36.753500: Epoch time: 21.6 s +2025-10-31 03:17:37.849930: +2025-10-31 03:17:37.851796: Epoch 40 +2025-10-31 03:17:37.853560: Current learning rate: 0.00964 +2025-10-31 03:17:59.875216: train_loss -0.9654 +2025-10-31 03:17:59.879239: val_loss -0.8954 +2025-10-31 03:17:59.880952: Pseudo dice [np.float32(0.9851), np.float32(0.9905), np.float32(0.9924), np.float32(0.7718)] +2025-10-31 03:17:59.882478: Epoch time: 22.03 s +2025-10-31 03:18:01.493458: +2025-10-31 03:18:01.496111: Epoch 41 +2025-10-31 03:18:01.497833: Current learning rate: 0.00963 +2025-10-31 03:18:23.972210: train_loss -0.9679 +2025-10-31 03:18:23.978818: val_loss -0.8663 +2025-10-31 03:18:23.983193: Pseudo dice [np.float32(0.9857), np.float32(0.9916), np.float32(0.9865), np.float32(0.7816)] +2025-10-31 03:18:23.985416: Epoch time: 22.48 s +2025-10-31 03:18:25.037861: +2025-10-31 03:18:25.039996: Epoch 42 +2025-10-31 03:18:25.041500: Current learning rate: 0.00962 +2025-10-31 03:18:47.734563: train_loss -0.9677 +2025-10-31 03:18:47.736850: val_loss -0.8931 +2025-10-31 03:18:47.738639: Pseudo dice [np.float32(0.985), np.float32(0.9905), np.float32(0.9914), np.float32(0.7773)] +2025-10-31 03:18:47.740248: Epoch time: 22.7 s +2025-10-31 03:18:48.835624: +2025-10-31 03:18:48.839067: Epoch 43 +2025-10-31 03:18:48.841235: Current learning rate: 0.00961 +2025-10-31 03:19:10.590944: train_loss -0.9699 +2025-10-31 03:19:10.596669: val_loss -0.9004 +2025-10-31 03:19:10.599194: Pseudo dice [np.float32(0.9846), np.float32(0.9907), np.float32(0.9939), np.float32(0.7823)] +2025-10-31 03:19:10.602278: Epoch time: 21.76 s +2025-10-31 03:19:11.809406: +2025-10-31 03:19:11.811239: Epoch 44 +2025-10-31 03:19:11.813566: Current learning rate: 0.0096 +2025-10-31 03:19:32.375027: train_loss -0.9714 +2025-10-31 03:19:32.380327: val_loss -0.8877 +2025-10-31 03:19:32.383786: Pseudo dice [np.float32(0.9842), np.float32(0.9905), np.float32(0.9909), np.float32(0.7724)] +2025-10-31 03:19:32.385702: Epoch time: 20.57 s +2025-10-31 03:19:33.557134: +2025-10-31 03:19:33.559478: Epoch 45 +2025-10-31 03:19:33.561261: Current learning rate: 0.00959 +2025-10-31 03:19:56.144680: train_loss -0.965 +2025-10-31 03:19:56.151602: val_loss -0.8953 +2025-10-31 03:19:56.154222: Pseudo dice [np.float32(0.9849), np.float32(0.9893), np.float32(0.9922), np.float32(0.7704)] +2025-10-31 03:19:56.156455: Epoch time: 22.59 s +2025-10-31 03:19:57.298391: +2025-10-31 03:19:57.300133: Epoch 46 +2025-10-31 03:19:57.301691: Current learning rate: 0.00959 +2025-10-31 03:20:19.679801: train_loss -0.9661 +2025-10-31 03:20:19.684002: val_loss -0.897 +2025-10-31 03:20:19.686404: Pseudo dice [np.float32(0.9819), np.float32(0.9902), np.float32(0.9937), np.float32(0.786)] +2025-10-31 03:20:19.688610: Epoch time: 22.38 s +2025-10-31 03:20:20.710020: +2025-10-31 03:20:20.713163: Epoch 47 +2025-10-31 03:20:20.715250: Current learning rate: 0.00958 +2025-10-31 03:20:42.710783: train_loss -0.9681 +2025-10-31 03:20:42.713433: val_loss -0.8872 +2025-10-31 03:20:42.716235: Pseudo dice [np.float32(0.9841), np.float32(0.9905), np.float32(0.9906), np.float32(0.7699)] +2025-10-31 03:20:42.718721: Epoch time: 22.0 s +2025-10-31 03:20:43.886564: +2025-10-31 03:20:43.890458: Epoch 48 +2025-10-31 03:20:43.894836: Current learning rate: 0.00957 +2025-10-31 03:21:05.667787: train_loss -0.9656 +2025-10-31 03:21:05.672332: val_loss -0.8949 +2025-10-31 03:21:05.674791: Pseudo dice [np.float32(0.9844), np.float32(0.9919), np.float32(0.9916), np.float32(0.7766)] +2025-10-31 03:21:05.676559: Epoch time: 21.78 s +2025-10-31 03:21:06.761843: +2025-10-31 03:21:06.764306: Epoch 49 +2025-10-31 03:21:06.768249: Current learning rate: 0.00956 +2025-10-31 03:21:28.955827: train_loss -0.9654 +2025-10-31 03:21:28.962348: val_loss -0.9016 +2025-10-31 03:21:28.964325: Pseudo dice [np.float32(0.9864), np.float32(0.9913), np.float32(0.992), np.float32(0.799)] +2025-10-31 03:21:28.967808: Epoch time: 22.2 s +2025-10-31 03:21:31.473640: +2025-10-31 03:21:31.475552: Epoch 50 +2025-10-31 03:21:31.477189: Current learning rate: 0.00955 +2025-10-31 03:21:52.427819: train_loss -0.9644 +2025-10-31 03:21:52.432218: val_loss -0.8928 +2025-10-31 03:21:52.435914: Pseudo dice [np.float32(0.9832), np.float32(0.9894), np.float32(0.9928), np.float32(0.77)] +2025-10-31 03:21:52.437967: Epoch time: 20.96 s +2025-10-31 03:21:53.428507: +2025-10-31 03:21:53.431327: Epoch 51 +2025-10-31 03:21:53.433268: Current learning rate: 0.00954 +2025-10-31 03:22:15.213582: train_loss -0.9679 +2025-10-31 03:22:15.221839: val_loss -0.8874 +2025-10-31 03:22:15.224833: Pseudo dice [np.float32(0.9827), np.float32(0.99), np.float32(0.9914), np.float32(0.7627)] +2025-10-31 03:22:15.227757: Epoch time: 21.79 s +2025-10-31 03:22:16.436466: +2025-10-31 03:22:16.439302: Epoch 52 +2025-10-31 03:22:16.442399: Current learning rate: 0.00953 +2025-10-31 03:22:38.818326: train_loss -0.9712 +2025-10-31 03:22:38.823887: val_loss -0.8843 +2025-10-31 03:22:38.825519: Pseudo dice [np.float32(0.9848), np.float32(0.9904), np.float32(0.991), np.float32(0.772)] +2025-10-31 03:22:38.826959: Epoch time: 22.38 s +2025-10-31 03:22:40.478159: +2025-10-31 03:22:40.480983: Epoch 53 +2025-10-31 03:22:40.482846: Current learning rate: 0.00952 +2025-10-31 03:23:02.552186: train_loss -0.9696 +2025-10-31 03:23:02.558623: val_loss -0.8819 +2025-10-31 03:23:02.560237: Pseudo dice [np.float32(0.9848), np.float32(0.9909), np.float32(0.9892), np.float32(0.7704)] +2025-10-31 03:23:02.562080: Epoch time: 22.08 s +2025-10-31 03:23:03.561220: +2025-10-31 03:23:03.563430: Epoch 54 +2025-10-31 03:23:03.565220: Current learning rate: 0.00951 +2025-10-31 03:23:25.464456: train_loss -0.9671 +2025-10-31 03:23:25.467963: val_loss -0.8916 +2025-10-31 03:23:25.469927: Pseudo dice [np.float32(0.9824), np.float32(0.9898), np.float32(0.9932), np.float32(0.77)] +2025-10-31 03:23:25.473164: Epoch time: 21.91 s +2025-10-31 03:23:26.640721: +2025-10-31 03:23:26.643386: Epoch 55 +2025-10-31 03:23:26.645112: Current learning rate: 0.0095 +2025-10-31 03:23:48.657346: train_loss -0.9654 +2025-10-31 03:23:48.668197: val_loss -0.8849 +2025-10-31 03:23:48.677090: Pseudo dice [np.float32(0.982), np.float32(0.9894), np.float32(0.9917), np.float32(0.7669)] +2025-10-31 03:23:48.681834: Epoch time: 22.02 s +2025-10-31 03:23:49.787139: +2025-10-31 03:23:49.789201: Epoch 56 +2025-10-31 03:23:49.790952: Current learning rate: 0.00949 +2025-10-31 03:24:11.700937: train_loss -0.9629 +2025-10-31 03:24:11.703621: val_loss -0.8993 +2025-10-31 03:24:11.705306: Pseudo dice [np.float32(0.9855), np.float32(0.9911), np.float32(0.9928), np.float32(0.7829)] +2025-10-31 03:24:11.707053: Epoch time: 21.92 s +2025-10-31 03:24:12.894677: +2025-10-31 03:24:12.896594: Epoch 57 +2025-10-31 03:24:12.898334: Current learning rate: 0.00949 +2025-10-31 03:24:33.267637: train_loss -0.9713 +2025-10-31 03:24:33.272783: val_loss -0.8922 +2025-10-31 03:24:33.275880: Pseudo dice [np.float32(0.9857), np.float32(0.9914), np.float32(0.99), np.float32(0.7855)] +2025-10-31 03:24:33.278556: Epoch time: 20.37 s +2025-10-31 03:24:34.457318: +2025-10-31 03:24:34.459217: Epoch 58 +2025-10-31 03:24:34.462351: Current learning rate: 0.00948 +2025-10-31 03:24:56.936713: train_loss -0.97 +2025-10-31 03:24:56.941486: val_loss -0.8871 +2025-10-31 03:24:56.943466: Pseudo dice [np.float32(0.9824), np.float32(0.9902), np.float32(0.9918), np.float32(0.7625)] +2025-10-31 03:24:56.945403: Epoch time: 22.48 s +2025-10-31 03:24:57.942886: +2025-10-31 03:24:57.944975: Epoch 59 +2025-10-31 03:24:57.947814: Current learning rate: 0.00947 +2025-10-31 03:25:19.834018: train_loss -0.9693 +2025-10-31 03:25:19.836243: val_loss -0.8943 +2025-10-31 03:25:19.837823: Pseudo dice [np.float32(0.9847), np.float32(0.9905), np.float32(0.9917), np.float32(0.7792)] +2025-10-31 03:25:19.839660: Epoch time: 21.89 s +2025-10-31 03:25:21.123362: +2025-10-31 03:25:21.129437: Epoch 60 +2025-10-31 03:25:21.135666: Current learning rate: 0.00946 +2025-10-31 03:25:43.072334: train_loss -0.9674 +2025-10-31 03:25:43.075379: val_loss -0.8878 +2025-10-31 03:25:43.077457: Pseudo dice [np.float32(0.9842), np.float32(0.991), np.float32(0.9906), np.float32(0.786)] +2025-10-31 03:25:43.081853: Epoch time: 21.95 s +2025-10-31 03:25:44.193483: +2025-10-31 03:25:44.195374: Epoch 61 +2025-10-31 03:25:44.197065: Current learning rate: 0.00945 +2025-10-31 03:26:06.355422: train_loss -0.9687 +2025-10-31 03:26:06.362850: val_loss -0.8959 +2025-10-31 03:26:06.366076: Pseudo dice [np.float32(0.9844), np.float32(0.9903), np.float32(0.9923), np.float32(0.7864)] +2025-10-31 03:26:06.368227: Epoch time: 22.16 s +2025-10-31 03:26:07.489053: +2025-10-31 03:26:07.493330: Epoch 62 +2025-10-31 03:26:07.498815: Current learning rate: 0.00944 +2025-10-31 03:26:29.521540: train_loss -0.9735 +2025-10-31 03:26:29.525589: val_loss -0.8547 +2025-10-31 03:26:29.527808: Pseudo dice [np.float32(0.9836), np.float32(0.9909), np.float32(0.9857), np.float32(0.7642)] +2025-10-31 03:26:29.529533: Epoch time: 22.03 s +2025-10-31 03:26:30.728712: +2025-10-31 03:26:30.730811: Epoch 63 +2025-10-31 03:26:30.732579: Current learning rate: 0.00943 +2025-10-31 03:26:50.593884: train_loss -0.9589 +2025-10-31 03:26:50.599147: val_loss -0.9072 +2025-10-31 03:26:50.600978: Pseudo dice [np.float32(0.9841), np.float32(0.9904), np.float32(0.9925), np.float32(0.8061)] +2025-10-31 03:26:50.602580: Epoch time: 19.87 s +2025-10-31 03:26:51.734047: +2025-10-31 03:26:51.736450: Epoch 64 +2025-10-31 03:26:51.738108: Current learning rate: 0.00942 +2025-10-31 03:27:13.445995: train_loss -0.9674 +2025-10-31 03:27:13.450540: val_loss -0.9015 +2025-10-31 03:27:13.453254: Pseudo dice [np.float32(0.9834), np.float32(0.9912), np.float32(0.9914), np.float32(0.7947)] +2025-10-31 03:27:13.456568: Epoch time: 21.71 s +2025-10-31 03:27:15.038718: +2025-10-31 03:27:15.041270: Epoch 65 +2025-10-31 03:27:15.043721: Current learning rate: 0.00941 +2025-10-31 03:27:37.359930: train_loss -0.9703 +2025-10-31 03:27:37.364014: val_loss -0.9065 +2025-10-31 03:27:37.365745: Pseudo dice [np.float32(0.9842), np.float32(0.9904), np.float32(0.9938), np.float32(0.8082)] +2025-10-31 03:27:37.367438: Epoch time: 22.32 s +2025-10-31 03:27:37.369012: Yayy! New best EMA pseudo Dice: 0.9373999834060669 +2025-10-31 03:27:40.078627: +2025-10-31 03:27:40.080683: Epoch 66 +2025-10-31 03:27:40.083565: Current learning rate: 0.0094 +2025-10-31 03:28:02.550543: train_loss -0.9702 +2025-10-31 03:28:02.562635: val_loss -0.9041 +2025-10-31 03:28:02.565149: Pseudo dice [np.float32(0.9815), np.float32(0.9884), np.float32(0.9941), np.float32(0.8002)] +2025-10-31 03:28:02.566756: Epoch time: 22.47 s +2025-10-31 03:28:02.568460: Yayy! New best EMA pseudo Dice: 0.9376999735832214 +2025-10-31 03:28:05.443285: +2025-10-31 03:28:05.445299: Epoch 67 +2025-10-31 03:28:05.447152: Current learning rate: 0.00939 +2025-10-31 03:28:28.035408: train_loss -0.9712 +2025-10-31 03:28:28.042791: val_loss -0.906 +2025-10-31 03:28:28.044867: Pseudo dice [np.float32(0.9831), np.float32(0.9898), np.float32(0.9945), np.float32(0.8017)] +2025-10-31 03:28:28.047491: Epoch time: 22.59 s +2025-10-31 03:28:28.049489: Yayy! New best EMA pseudo Dice: 0.9381999969482422 +2025-10-31 03:28:30.769719: +2025-10-31 03:28:30.772202: Epoch 68 +2025-10-31 03:28:30.774225: Current learning rate: 0.00939 +2025-10-31 03:28:52.738069: train_loss -0.9748 +2025-10-31 03:28:52.741006: val_loss -0.904 +2025-10-31 03:28:52.742753: Pseudo dice [np.float32(0.9827), np.float32(0.9898), np.float32(0.9942), np.float32(0.8035)] +2025-10-31 03:28:52.744429: Epoch time: 21.97 s +2025-10-31 03:28:52.745945: Yayy! New best EMA pseudo Dice: 0.9386000037193298 +2025-10-31 03:28:55.509904: +2025-10-31 03:28:55.512748: Epoch 69 +2025-10-31 03:28:55.514717: Current learning rate: 0.00938 +2025-10-31 03:29:16.036493: train_loss -0.9736 +2025-10-31 03:29:16.041095: val_loss -0.8952 +2025-10-31 03:29:16.044388: Pseudo dice [np.float32(0.9839), np.float32(0.9895), np.float32(0.9933), np.float32(0.7814)] +2025-10-31 03:29:16.046399: Epoch time: 20.53 s +2025-10-31 03:29:17.307221: +2025-10-31 03:29:17.309325: Epoch 70 +2025-10-31 03:29:17.311723: Current learning rate: 0.00937 +2025-10-31 03:29:39.299499: train_loss -0.9715 +2025-10-31 03:29:39.301885: val_loss -0.9033 +2025-10-31 03:29:39.304389: Pseudo dice [np.float32(0.9843), np.float32(0.9907), np.float32(0.9943), np.float32(0.7981)] +2025-10-31 03:29:39.306471: Epoch time: 21.99 s +2025-10-31 03:29:39.308009: Yayy! New best EMA pseudo Dice: 0.9387999773025513 +2025-10-31 03:29:41.827147: +2025-10-31 03:29:41.829479: Epoch 71 +2025-10-31 03:29:41.831563: Current learning rate: 0.00936 +2025-10-31 03:30:04.584250: train_loss -0.975 +2025-10-31 03:30:04.586955: val_loss -0.8952 +2025-10-31 03:30:04.588724: Pseudo dice [np.float32(0.9845), np.float32(0.9902), np.float32(0.9921), np.float32(0.7879)] +2025-10-31 03:30:04.591197: Epoch time: 22.76 s +2025-10-31 03:30:05.788097: +2025-10-31 03:30:05.792385: Epoch 72 +2025-10-31 03:30:05.795459: Current learning rate: 0.00935 +2025-10-31 03:30:28.359928: train_loss -0.9694 +2025-10-31 03:30:28.365353: val_loss -0.8901 +2025-10-31 03:30:28.367875: Pseudo dice [np.float32(0.9835), np.float32(0.9881), np.float32(0.99), np.float32(0.7819)] +2025-10-31 03:30:28.369373: Epoch time: 22.57 s +2025-10-31 03:30:29.665393: +2025-10-31 03:30:29.668047: Epoch 73 +2025-10-31 03:30:29.670686: Current learning rate: 0.00934 +2025-10-31 03:30:51.796798: train_loss -0.9701 +2025-10-31 03:30:51.800067: val_loss -0.8917 +2025-10-31 03:30:51.801713: Pseudo dice [np.float32(0.9821), np.float32(0.9902), np.float32(0.9918), np.float32(0.7738)] +2025-10-31 03:30:51.803193: Epoch time: 22.13 s +2025-10-31 03:30:52.953575: +2025-10-31 03:30:52.955613: Epoch 74 +2025-10-31 03:30:52.957512: Current learning rate: 0.00933 +2025-10-31 03:31:15.178540: train_loss -0.9707 +2025-10-31 03:31:15.181045: val_loss -0.9056 +2025-10-31 03:31:15.182874: Pseudo dice [np.float32(0.9847), np.float32(0.9908), np.float32(0.9941), np.float32(0.7898)] +2025-10-31 03:31:15.184624: Epoch time: 22.23 s +2025-10-31 03:31:16.323593: +2025-10-31 03:31:16.325636: Epoch 75 +2025-10-31 03:31:16.327523: Current learning rate: 0.00932 +2025-10-31 03:31:37.572688: train_loss -0.9705 +2025-10-31 03:31:37.576298: val_loss -0.897 +2025-10-31 03:31:37.578248: Pseudo dice [np.float32(0.9847), np.float32(0.991), np.float32(0.9925), np.float32(0.8051)] +2025-10-31 03:31:37.580312: Epoch time: 21.25 s +2025-10-31 03:31:38.823753: +2025-10-31 03:31:38.826012: Epoch 76 +2025-10-31 03:31:38.828006: Current learning rate: 0.00931 +2025-10-31 03:32:00.987902: train_loss -0.9729 +2025-10-31 03:32:00.991969: val_loss -0.9027 +2025-10-31 03:32:00.996418: Pseudo dice [np.float32(0.9844), np.float32(0.9906), np.float32(0.9941), np.float32(0.7982)] +2025-10-31 03:32:01.000769: Epoch time: 22.17 s +2025-10-31 03:32:01.004750: Yayy! New best EMA pseudo Dice: 0.9391000270843506 +2025-10-31 03:32:03.818759: +2025-10-31 03:32:03.820615: Epoch 77 +2025-10-31 03:32:03.822784: Current learning rate: 0.0093 +2025-10-31 03:32:25.879706: train_loss -0.9754 +2025-10-31 03:32:25.885646: val_loss -0.8959 +2025-10-31 03:32:25.887524: Pseudo dice [np.float32(0.984), np.float32(0.9907), np.float32(0.9917), np.float32(0.7969)] +2025-10-31 03:32:25.890082: Epoch time: 22.06 s +2025-10-31 03:32:25.892229: Yayy! New best EMA pseudo Dice: 0.939300000667572 +2025-10-31 03:32:28.656912: +2025-10-31 03:32:28.660486: Epoch 78 +2025-10-31 03:32:28.662508: Current learning rate: 0.0093 +2025-10-31 03:32:51.187885: train_loss -0.9772 +2025-10-31 03:32:51.191352: val_loss -0.8986 +2025-10-31 03:32:51.193638: Pseudo dice [np.float32(0.9851), np.float32(0.9915), np.float32(0.9933), np.float32(0.7979)] +2025-10-31 03:32:51.196049: Epoch time: 22.53 s +2025-10-31 03:32:51.198198: Yayy! New best EMA pseudo Dice: 0.9394999742507935 +2025-10-31 03:32:54.001761: +2025-10-31 03:32:54.004002: Epoch 79 +2025-10-31 03:32:54.006922: Current learning rate: 0.00929 +2025-10-31 03:33:15.696151: train_loss -0.9769 +2025-10-31 03:33:15.705981: val_loss -0.8972 +2025-10-31 03:33:15.708295: Pseudo dice [np.float32(0.9827), np.float32(0.9904), np.float32(0.994), np.float32(0.7877)] +2025-10-31 03:33:15.710682: Epoch time: 21.7 s +2025-10-31 03:33:16.906368: +2025-10-31 03:33:16.908087: Epoch 80 +2025-10-31 03:33:16.910353: Current learning rate: 0.00928 +2025-10-31 03:33:38.403392: train_loss -0.9762 +2025-10-31 03:33:38.405870: val_loss -0.8951 +2025-10-31 03:33:38.407625: Pseudo dice [np.float32(0.9837), np.float32(0.99), np.float32(0.9935), np.float32(0.7859)] +2025-10-31 03:33:38.409379: Epoch time: 21.5 s +2025-10-31 03:33:39.424695: +2025-10-31 03:33:39.427417: Epoch 81 +2025-10-31 03:33:39.429547: Current learning rate: 0.00927 +2025-10-31 03:34:01.495242: train_loss -0.9765 +2025-10-31 03:34:01.504508: val_loss -0.9086 +2025-10-31 03:34:01.506258: Pseudo dice [np.float32(0.9841), np.float32(0.9908), np.float32(0.9949), np.float32(0.8188)] +2025-10-31 03:34:01.508432: Epoch time: 22.07 s +2025-10-31 03:34:01.510049: Yayy! New best EMA pseudo Dice: 0.9401000142097473 +2025-10-31 03:34:04.555201: +2025-10-31 03:34:04.558725: Epoch 82 +2025-10-31 03:34:04.565075: Current learning rate: 0.00926 +2025-10-31 03:34:26.153805: train_loss -0.9788 +2025-10-31 03:34:26.158020: val_loss -0.9013 +2025-10-31 03:34:26.162960: Pseudo dice [np.float32(0.9833), np.float32(0.9899), np.float32(0.9935), np.float32(0.8099)] +2025-10-31 03:34:26.164962: Epoch time: 21.6 s +2025-10-31 03:34:26.167042: Yayy! New best EMA pseudo Dice: 0.940500020980835 +2025-10-31 03:34:28.639783: +2025-10-31 03:34:28.641995: Epoch 83 +2025-10-31 03:34:28.644154: Current learning rate: 0.00925 +2025-10-31 03:34:51.202604: train_loss -0.9771 +2025-10-31 03:34:51.205322: val_loss -0.8924 +2025-10-31 03:34:51.207819: Pseudo dice [np.float32(0.9843), np.float32(0.9901), np.float32(0.9936), np.float32(0.7733)] +2025-10-31 03:34:51.209919: Epoch time: 22.56 s +2025-10-31 03:34:52.287399: +2025-10-31 03:34:52.289977: Epoch 84 +2025-10-31 03:34:52.291476: Current learning rate: 0.00924 +2025-10-31 03:35:14.317021: train_loss -0.9777 +2025-10-31 03:35:14.324434: val_loss -0.8946 +2025-10-31 03:35:14.327556: Pseudo dice [np.float32(0.9832), np.float32(0.9899), np.float32(0.9932), np.float32(0.7836)] +2025-10-31 03:35:14.331048: Epoch time: 22.03 s +2025-10-31 03:35:15.383768: +2025-10-31 03:35:15.385622: Epoch 85 +2025-10-31 03:35:15.388690: Current learning rate: 0.00923 +2025-10-31 03:35:37.631931: train_loss -0.9776 +2025-10-31 03:35:37.636564: val_loss -0.8942 +2025-10-31 03:35:37.639148: Pseudo dice [np.float32(0.9844), np.float32(0.9914), np.float32(0.9937), np.float32(0.78)] +2025-10-31 03:35:37.640738: Epoch time: 22.25 s +2025-10-31 03:35:38.661917: +2025-10-31 03:35:38.667181: Epoch 86 +2025-10-31 03:35:38.669439: Current learning rate: 0.00922 +2025-10-31 03:35:59.764923: train_loss -0.9796 +2025-10-31 03:35:59.768667: val_loss -0.8999 +2025-10-31 03:35:59.771186: Pseudo dice [np.float32(0.9841), np.float32(0.9913), np.float32(0.9945), np.float32(0.7891)] +2025-10-31 03:35:59.775086: Epoch time: 21.11 s +2025-10-31 03:36:00.775792: +2025-10-31 03:36:00.778494: Epoch 87 +2025-10-31 03:36:00.780612: Current learning rate: 0.00921 +2025-10-31 03:36:22.669346: train_loss -0.9775 +2025-10-31 03:36:22.673143: val_loss -0.8864 +2025-10-31 03:36:22.674818: Pseudo dice [np.float32(0.9836), np.float32(0.9908), np.float32(0.9918), np.float32(0.7749)] +2025-10-31 03:36:22.676468: Epoch time: 21.89 s +2025-10-31 03:36:24.150765: +2025-10-31 03:36:24.152753: Epoch 88 +2025-10-31 03:36:24.156587: Current learning rate: 0.0092 +2025-10-31 03:36:45.403247: train_loss -0.9773 +2025-10-31 03:36:45.407523: val_loss -0.8909 +2025-10-31 03:36:45.409111: Pseudo dice [np.float32(0.982), np.float32(0.9896), np.float32(0.9935), np.float32(0.7788)] +2025-10-31 03:36:45.410714: Epoch time: 21.25 s +2025-10-31 03:36:46.594419: +2025-10-31 03:36:46.604347: Epoch 89 +2025-10-31 03:36:46.606323: Current learning rate: 0.0092 +2025-10-31 03:37:09.518118: train_loss -0.9783 +2025-10-31 03:37:09.525217: val_loss -0.8732 +2025-10-31 03:37:09.528131: Pseudo dice [np.float32(0.9844), np.float32(0.991), np.float32(0.9885), np.float32(0.7577)] +2025-10-31 03:37:09.529668: Epoch time: 22.93 s +2025-10-31 03:37:10.742087: +2025-10-31 03:37:10.748124: Epoch 90 +2025-10-31 03:37:10.750681: Current learning rate: 0.00919 +2025-10-31 03:37:33.326819: train_loss -0.9782 +2025-10-31 03:37:33.331335: val_loss -0.8696 +2025-10-31 03:37:33.332986: Pseudo dice [np.float32(0.9826), np.float32(0.9904), np.float32(0.9902), np.float32(0.7505)] +2025-10-31 03:37:33.334591: Epoch time: 22.59 s +2025-10-31 03:37:34.435507: +2025-10-31 03:37:34.437943: Epoch 91 +2025-10-31 03:37:34.440238: Current learning rate: 0.00918 +2025-10-31 03:37:56.442664: train_loss -0.9797 +2025-10-31 03:37:56.445892: val_loss -0.8942 +2025-10-31 03:37:56.448493: Pseudo dice [np.float32(0.9841), np.float32(0.9912), np.float32(0.9931), np.float32(0.7786)] +2025-10-31 03:37:56.450608: Epoch time: 22.01 s +2025-10-31 03:37:57.470120: +2025-10-31 03:37:57.474457: Epoch 92 +2025-10-31 03:37:57.477241: Current learning rate: 0.00917 +2025-10-31 03:38:18.931406: train_loss -0.9772 +2025-10-31 03:38:18.933847: val_loss -0.8941 +2025-10-31 03:38:18.937922: Pseudo dice [np.float32(0.9841), np.float32(0.9919), np.float32(0.9927), np.float32(0.7757)] +2025-10-31 03:38:18.940282: Epoch time: 21.46 s +2025-10-31 03:38:20.104037: +2025-10-31 03:38:20.106303: Epoch 93 +2025-10-31 03:38:20.108117: Current learning rate: 0.00916 +2025-10-31 03:38:41.799413: train_loss -0.9786 +2025-10-31 03:38:41.803429: val_loss -0.8795 +2025-10-31 03:38:41.805400: Pseudo dice [np.float32(0.9843), np.float32(0.9906), np.float32(0.9895), np.float32(0.7691)] +2025-10-31 03:38:41.807101: Epoch time: 21.7 s +2025-10-31 03:38:42.857555: +2025-10-31 03:38:42.861609: Epoch 94 +2025-10-31 03:38:42.863248: Current learning rate: 0.00915 +2025-10-31 03:39:04.163903: train_loss -0.9773 +2025-10-31 03:39:04.169781: val_loss -0.896 +2025-10-31 03:39:04.177688: Pseudo dice [np.float32(0.9855), np.float32(0.9909), np.float32(0.9933), np.float32(0.7851)] +2025-10-31 03:39:04.179789: Epoch time: 21.31 s +2025-10-31 03:39:05.396046: +2025-10-31 03:39:05.398474: Epoch 95 +2025-10-31 03:39:05.400915: Current learning rate: 0.00914 +2025-10-31 03:39:27.724581: train_loss -0.9763 +2025-10-31 03:39:27.728369: val_loss -0.8919 +2025-10-31 03:39:27.731796: Pseudo dice [np.float32(0.9833), np.float32(0.9905), np.float32(0.9925), np.float32(0.7756)] +2025-10-31 03:39:27.736358: Epoch time: 22.33 s +2025-10-31 03:39:28.667223: +2025-10-31 03:39:28.669062: Epoch 96 +2025-10-31 03:39:28.670512: Current learning rate: 0.00913 +2025-10-31 03:39:50.435754: train_loss -0.9758 +2025-10-31 03:39:50.446818: val_loss -0.8865 +2025-10-31 03:39:50.448802: Pseudo dice [np.float32(0.9839), np.float32(0.9893), np.float32(0.9914), np.float32(0.7619)] +2025-10-31 03:39:50.450432: Epoch time: 21.77 s +2025-10-31 03:39:51.476524: +2025-10-31 03:39:51.478627: Epoch 97 +2025-10-31 03:39:51.481079: Current learning rate: 0.00912 +2025-10-31 03:40:13.826556: train_loss -0.9764 +2025-10-31 03:40:13.832513: val_loss -0.8967 +2025-10-31 03:40:13.836301: Pseudo dice [np.float32(0.9844), np.float32(0.9911), np.float32(0.9941), np.float32(0.7792)] +2025-10-31 03:40:13.839770: Epoch time: 22.35 s +2025-10-31 03:40:15.029745: +2025-10-31 03:40:15.033503: Epoch 98 +2025-10-31 03:40:15.039233: Current learning rate: 0.00911 +2025-10-31 03:40:36.573496: train_loss -0.976 +2025-10-31 03:40:36.576569: val_loss -0.8889 +2025-10-31 03:40:36.579141: Pseudo dice [np.float32(0.9849), np.float32(0.9915), np.float32(0.9927), np.float32(0.7713)] +2025-10-31 03:40:36.581597: Epoch time: 21.55 s +2025-10-31 03:40:37.860702: +2025-10-31 03:40:37.867895: Epoch 99 +2025-10-31 03:40:37.875287: Current learning rate: 0.0091 +2025-10-31 03:40:59.884130: train_loss -0.9794 +2025-10-31 03:40:59.892103: val_loss -0.8947 +2025-10-31 03:40:59.895004: Pseudo dice [np.float32(0.9836), np.float32(0.9911), np.float32(0.9934), np.float32(0.7812)] +2025-10-31 03:40:59.898903: Epoch time: 22.03 s +2025-10-31 03:41:02.914171: +2025-10-31 03:41:02.918602: Epoch 100 +2025-10-31 03:41:02.920494: Current learning rate: 0.0091 +2025-10-31 03:41:25.696900: train_loss -0.9792 +2025-10-31 03:41:25.701414: val_loss -0.9006 +2025-10-31 03:41:25.703447: Pseudo dice [np.float32(0.9843), np.float32(0.9916), np.float32(0.994), np.float32(0.7897)] +2025-10-31 03:41:25.705816: Epoch time: 22.78 s +2025-10-31 03:41:26.692077: +2025-10-31 03:41:26.695820: Epoch 101 +2025-10-31 03:41:26.699519: Current learning rate: 0.00909 +2025-10-31 03:41:47.055635: train_loss -0.9784 +2025-10-31 03:41:47.059444: val_loss -0.8931 +2025-10-31 03:41:47.061321: Pseudo dice [np.float32(0.9829), np.float32(0.9906), np.float32(0.9931), np.float32(0.7818)] +2025-10-31 03:41:47.063334: Epoch time: 20.37 s +2025-10-31 03:41:48.059882: +2025-10-31 03:41:48.062101: Epoch 102 +2025-10-31 03:41:48.064457: Current learning rate: 0.00908 +2025-10-31 03:42:10.042573: train_loss -0.9798 +2025-10-31 03:42:10.056940: val_loss -0.8888 +2025-10-31 03:42:10.059014: Pseudo dice [np.float32(0.9817), np.float32(0.9902), np.float32(0.9914), np.float32(0.7923)] +2025-10-31 03:42:10.061252: Epoch time: 21.98 s +2025-10-31 03:42:11.415410: +2025-10-31 03:42:11.417668: Epoch 103 +2025-10-31 03:42:11.419581: Current learning rate: 0.00907 +2025-10-31 03:42:33.116551: train_loss -0.9706 +2025-10-31 03:42:33.123552: val_loss -0.9008 +2025-10-31 03:42:33.128518: Pseudo dice [np.float32(0.9826), np.float32(0.99), np.float32(0.9941), np.float32(0.784)] +2025-10-31 03:42:33.132025: Epoch time: 21.7 s +2025-10-31 03:42:34.180151: +2025-10-31 03:42:34.182244: Epoch 104 +2025-10-31 03:42:34.184354: Current learning rate: 0.00906 +2025-10-31 03:42:55.255694: train_loss -0.9704 +2025-10-31 03:42:55.259773: val_loss -0.8976 +2025-10-31 03:42:55.262498: Pseudo dice [np.float32(0.9864), np.float32(0.9911), np.float32(0.9933), np.float32(0.7801)] +2025-10-31 03:42:55.265096: Epoch time: 21.08 s +2025-10-31 03:42:56.270197: +2025-10-31 03:42:56.272593: Epoch 105 +2025-10-31 03:42:56.274856: Current learning rate: 0.00905 +2025-10-31 03:43:18.791779: train_loss -0.9738 +2025-10-31 03:43:18.799919: val_loss -0.9037 +2025-10-31 03:43:18.802346: Pseudo dice [np.float32(0.9839), np.float32(0.9908), np.float32(0.9948), np.float32(0.802)] +2025-10-31 03:43:18.804600: Epoch time: 22.52 s +2025-10-31 03:43:19.978261: +2025-10-31 03:43:19.979944: Epoch 106 +2025-10-31 03:43:19.981543: Current learning rate: 0.00904 +2025-10-31 03:43:42.089186: train_loss -0.9771 +2025-10-31 03:43:42.097525: val_loss -0.9048 +2025-10-31 03:43:42.099484: Pseudo dice [np.float32(0.9859), np.float32(0.9919), np.float32(0.9944), np.float32(0.7979)] +2025-10-31 03:43:42.101201: Epoch time: 22.11 s +2025-10-31 03:43:43.373863: +2025-10-31 03:43:43.376275: Epoch 107 +2025-10-31 03:43:43.379150: Current learning rate: 0.00903 +2025-10-31 03:44:03.487319: train_loss -0.9752 +2025-10-31 03:44:03.494267: val_loss -0.9101 +2025-10-31 03:44:03.499926: Pseudo dice [np.float32(0.985), np.float32(0.9914), np.float32(0.9951), np.float32(0.8181)] +2025-10-31 03:44:03.503177: Epoch time: 20.12 s +2025-10-31 03:44:04.546502: +2025-10-31 03:44:04.548410: Epoch 108 +2025-10-31 03:44:04.550208: Current learning rate: 0.00902 +2025-10-31 03:44:26.934644: train_loss -0.9794 +2025-10-31 03:44:26.953596: val_loss -0.8998 +2025-10-31 03:44:26.955292: Pseudo dice [np.float32(0.9848), np.float32(0.9911), np.float32(0.9942), np.float32(0.7922)] +2025-10-31 03:44:26.956756: Epoch time: 22.39 s +2025-10-31 03:44:28.144249: +2025-10-31 03:44:28.146878: Epoch 109 +2025-10-31 03:44:28.149760: Current learning rate: 0.00901 +2025-10-31 03:44:48.939159: train_loss -0.9775 +2025-10-31 03:44:48.957036: val_loss -0.8993 +2025-10-31 03:44:48.961281: Pseudo dice [np.float32(0.9856), np.float32(0.9916), np.float32(0.9942), np.float32(0.7887)] +2025-10-31 03:44:48.964173: Epoch time: 20.8 s +2025-10-31 03:44:50.254332: +2025-10-31 03:44:50.265887: Epoch 110 +2025-10-31 03:44:50.272493: Current learning rate: 0.009 +2025-10-31 03:45:10.673544: train_loss -0.9785 +2025-10-31 03:45:10.677741: val_loss -0.8991 +2025-10-31 03:45:10.680759: Pseudo dice [np.float32(0.984), np.float32(0.9911), np.float32(0.9942), np.float32(0.7918)] +2025-10-31 03:45:10.685155: Epoch time: 20.42 s +2025-10-31 03:45:11.837581: +2025-10-31 03:45:11.839706: Epoch 111 +2025-10-31 03:45:11.841575: Current learning rate: 0.009 +2025-10-31 03:45:33.972575: train_loss -0.978 +2025-10-31 03:45:33.976180: val_loss -0.8872 +2025-10-31 03:45:33.977863: Pseudo dice [np.float32(0.9837), np.float32(0.9903), np.float32(0.9934), np.float32(0.7571)] +2025-10-31 03:45:33.980001: Epoch time: 22.14 s +2025-10-31 03:45:34.998777: +2025-10-31 03:45:35.000808: Epoch 112 +2025-10-31 03:45:35.002632: Current learning rate: 0.00899 +2025-10-31 03:45:57.313258: train_loss -0.9802 +2025-10-31 03:45:57.320676: val_loss -0.8936 +2025-10-31 03:45:57.322664: Pseudo dice [np.float32(0.9848), np.float32(0.9915), np.float32(0.994), np.float32(0.7816)] +2025-10-31 03:45:57.324434: Epoch time: 22.32 s +2025-10-31 03:45:58.974275: +2025-10-31 03:45:58.976711: Epoch 113 +2025-10-31 03:45:58.979089: Current learning rate: 0.00898 +2025-10-31 03:46:20.869156: train_loss -0.9797 +2025-10-31 03:46:20.876804: val_loss -0.8972 +2025-10-31 03:46:20.882035: Pseudo dice [np.float32(0.9852), np.float32(0.9923), np.float32(0.9943), np.float32(0.7853)] +2025-10-31 03:46:20.888978: Epoch time: 21.9 s +2025-10-31 03:46:21.939501: +2025-10-31 03:46:21.941543: Epoch 114 +2025-10-31 03:46:21.943240: Current learning rate: 0.00897 +2025-10-31 03:46:42.174004: train_loss -0.9801 +2025-10-31 03:46:42.177089: val_loss -0.9028 +2025-10-31 03:46:42.179559: Pseudo dice [np.float32(0.9849), np.float32(0.9915), np.float32(0.9948), np.float32(0.8018)] +2025-10-31 03:46:42.181582: Epoch time: 20.24 s +2025-10-31 03:46:43.362172: +2025-10-31 03:46:43.364285: Epoch 115 +2025-10-31 03:46:43.366178: Current learning rate: 0.00896 +2025-10-31 03:47:05.968634: train_loss -0.9797 +2025-10-31 03:47:05.972881: val_loss -0.891 +2025-10-31 03:47:05.974772: Pseudo dice [np.float32(0.9833), np.float32(0.9913), np.float32(0.9939), np.float32(0.768)] +2025-10-31 03:47:05.976361: Epoch time: 22.61 s +2025-10-31 03:47:06.991258: +2025-10-31 03:47:06.993174: Epoch 116 +2025-10-31 03:47:06.995751: Current learning rate: 0.00895 +2025-10-31 03:47:28.725976: train_loss -0.9798 +2025-10-31 03:47:28.728381: val_loss -0.8959 +2025-10-31 03:47:28.730448: Pseudo dice [np.float32(0.9829), np.float32(0.9908), np.float32(0.9943), np.float32(0.7853)] +2025-10-31 03:47:28.732028: Epoch time: 21.74 s +2025-10-31 03:47:30.037982: +2025-10-31 03:47:30.043473: Epoch 117 +2025-10-31 03:47:30.045251: Current learning rate: 0.00894 +2025-10-31 03:47:51.682180: train_loss -0.9808 +2025-10-31 03:47:51.870298: val_loss -0.9063 +2025-10-31 03:47:51.879319: Pseudo dice [np.float32(0.9854), np.float32(0.9919), np.float32(0.9946), np.float32(0.805)] +2025-10-31 03:47:51.883880: Epoch time: 21.65 s +2025-10-31 03:47:53.170873: +2025-10-31 03:47:53.173045: Epoch 118 +2025-10-31 03:47:53.176537: Current learning rate: 0.00893 +2025-10-31 03:48:15.553910: train_loss -0.98 +2025-10-31 03:48:15.559739: val_loss -0.8925 +2025-10-31 03:48:15.562482: Pseudo dice [np.float32(0.9851), np.float32(0.9909), np.float32(0.9928), np.float32(0.775)] +2025-10-31 03:48:15.565775: Epoch time: 22.38 s +2025-10-31 03:48:16.580821: +2025-10-31 03:48:16.583722: Epoch 119 +2025-10-31 03:48:16.585690: Current learning rate: 0.00892 +2025-10-31 03:48:38.600131: train_loss -0.9802 +2025-10-31 03:48:38.603025: val_loss -0.9021 +2025-10-31 03:48:38.605199: Pseudo dice [np.float32(0.9863), np.float32(0.9921), np.float32(0.994), np.float32(0.8015)] +2025-10-31 03:48:38.607205: Epoch time: 22.02 s +2025-10-31 03:48:39.772430: +2025-10-31 03:48:39.774293: Epoch 120 +2025-10-31 03:48:39.776076: Current learning rate: 0.00891 +2025-10-31 03:49:01.108876: train_loss -0.981 +2025-10-31 03:49:01.115377: val_loss -0.8898 +2025-10-31 03:49:01.117504: Pseudo dice [np.float32(0.9844), np.float32(0.9912), np.float32(0.9929), np.float32(0.7727)] +2025-10-31 03:49:01.119415: Epoch time: 21.34 s +2025-10-31 03:49:02.313658: +2025-10-31 03:49:02.315695: Epoch 121 +2025-10-31 03:49:02.317258: Current learning rate: 0.0089 +2025-10-31 03:49:24.241027: train_loss -0.981 +2025-10-31 03:49:24.254303: val_loss -0.8936 +2025-10-31 03:49:24.256564: Pseudo dice [np.float32(0.9846), np.float32(0.9909), np.float32(0.9941), np.float32(0.7888)] +2025-10-31 03:49:24.258647: Epoch time: 21.93 s +2025-10-31 03:49:25.335154: +2025-10-31 03:49:25.337101: Epoch 122 +2025-10-31 03:49:25.338811: Current learning rate: 0.00889 +2025-10-31 03:49:46.249432: train_loss -0.9796 +2025-10-31 03:49:46.255686: val_loss -0.8865 +2025-10-31 03:49:46.257795: Pseudo dice [np.float32(0.9835), np.float32(0.991), np.float32(0.9923), np.float32(0.7752)] +2025-10-31 03:49:46.259881: Epoch time: 20.92 s +2025-10-31 03:49:47.474102: +2025-10-31 03:49:47.476604: Epoch 123 +2025-10-31 03:49:47.478717: Current learning rate: 0.00889 +2025-10-31 03:50:09.778022: train_loss -0.9796 +2025-10-31 03:50:09.783278: val_loss -0.8853 +2025-10-31 03:50:09.786582: Pseudo dice [np.float32(0.9858), np.float32(0.9919), np.float32(0.9927), np.float32(0.7605)] +2025-10-31 03:50:09.790148: Epoch time: 22.31 s +2025-10-31 03:50:10.783981: +2025-10-31 03:50:10.786165: Epoch 124 +2025-10-31 03:50:10.787872: Current learning rate: 0.00888 +2025-10-31 03:50:33.085678: train_loss -0.981 +2025-10-31 03:50:33.088287: val_loss -0.9037 +2025-10-31 03:50:33.090256: Pseudo dice [np.float32(0.9861), np.float32(0.9925), np.float32(0.9946), np.float32(0.7926)] +2025-10-31 03:50:33.094746: Epoch time: 22.3 s +2025-10-31 03:50:34.240814: +2025-10-31 03:50:34.247441: Epoch 125 +2025-10-31 03:50:34.253903: Current learning rate: 0.00887 +2025-10-31 03:50:56.705541: train_loss -0.9777 +2025-10-31 03:50:56.723907: val_loss -0.9022 +2025-10-31 03:50:56.728225: Pseudo dice [np.float32(0.9845), np.float32(0.9912), np.float32(0.9948), np.float32(0.7985)] +2025-10-31 03:50:56.730665: Epoch time: 22.47 s +2025-10-31 03:50:57.743053: +2025-10-31 03:50:57.746269: Epoch 126 +2025-10-31 03:50:57.747911: Current learning rate: 0.00886 +2025-10-31 03:51:20.333881: train_loss -0.9801 +2025-10-31 03:51:20.337503: val_loss -0.8917 +2025-10-31 03:51:20.339295: Pseudo dice [np.float32(0.9852), np.float32(0.9911), np.float32(0.9928), np.float32(0.7688)] +2025-10-31 03:51:20.341764: Epoch time: 22.59 s +2025-10-31 03:51:21.650167: +2025-10-31 03:51:21.653034: Epoch 127 +2025-10-31 03:51:21.657066: Current learning rate: 0.00885 +2025-10-31 03:51:42.101087: train_loss -0.9808 +2025-10-31 03:51:42.103811: val_loss -0.891 +2025-10-31 03:51:42.106895: Pseudo dice [np.float32(0.9862), np.float32(0.9913), np.float32(0.9935), np.float32(0.7697)] +2025-10-31 03:51:42.108885: Epoch time: 20.45 s +2025-10-31 03:51:43.362577: +2025-10-31 03:51:43.364363: Epoch 128 +2025-10-31 03:51:43.366010: Current learning rate: 0.00884 +2025-10-31 03:52:04.712367: train_loss -0.98 +2025-10-31 03:52:04.714547: val_loss -0.8985 +2025-10-31 03:52:04.716871: Pseudo dice [np.float32(0.9836), np.float32(0.9901), np.float32(0.9939), np.float32(0.7944)] +2025-10-31 03:52:04.719311: Epoch time: 21.35 s +2025-10-31 03:52:05.775551: +2025-10-31 03:52:05.777648: Epoch 129 +2025-10-31 03:52:05.783280: Current learning rate: 0.00883 +2025-10-31 03:52:27.886406: train_loss -0.9754 +2025-10-31 03:52:27.897389: val_loss -0.8962 +2025-10-31 03:52:27.899956: Pseudo dice [np.float32(0.9837), np.float32(0.9908), np.float32(0.9938), np.float32(0.7772)] +2025-10-31 03:52:27.902137: Epoch time: 22.11 s +2025-10-31 03:52:28.920784: +2025-10-31 03:52:28.922962: Epoch 130 +2025-10-31 03:52:28.926660: Current learning rate: 0.00882 +2025-10-31 03:52:50.989247: train_loss -0.9778 +2025-10-31 03:52:50.993306: val_loss -0.9055 +2025-10-31 03:52:50.995441: Pseudo dice [np.float32(0.9853), np.float32(0.9915), np.float32(0.9942), np.float32(0.7984)] +2025-10-31 03:52:50.996981: Epoch time: 22.07 s +2025-10-31 03:52:52.274901: +2025-10-31 03:52:52.277917: Epoch 131 +2025-10-31 03:52:52.279715: Current learning rate: 0.00881 +2025-10-31 03:53:14.099644: train_loss -0.9799 +2025-10-31 03:53:14.111175: val_loss -0.9043 +2025-10-31 03:53:14.113872: Pseudo dice [np.float32(0.9847), np.float32(0.9905), np.float32(0.9947), np.float32(0.8049)] +2025-10-31 03:53:14.116008: Epoch time: 21.83 s +2025-10-31 03:53:15.325491: +2025-10-31 03:53:15.331760: Epoch 132 +2025-10-31 03:53:15.336228: Current learning rate: 0.0088 +2025-10-31 03:53:37.279540: train_loss -0.9812 +2025-10-31 03:53:37.283345: val_loss -0.8984 +2025-10-31 03:53:37.286677: Pseudo dice [np.float32(0.9838), np.float32(0.9913), np.float32(0.9938), np.float32(0.7992)] +2025-10-31 03:53:37.289461: Epoch time: 21.96 s +2025-10-31 03:53:38.302237: +2025-10-31 03:53:38.304486: Epoch 133 +2025-10-31 03:53:38.306671: Current learning rate: 0.00879 +2025-10-31 03:54:00.034414: train_loss -0.98 +2025-10-31 03:54:00.039995: val_loss -0.8973 +2025-10-31 03:54:00.042477: Pseudo dice [np.float32(0.9831), np.float32(0.9895), np.float32(0.994), np.float32(0.7905)] +2025-10-31 03:54:00.044031: Epoch time: 21.73 s +2025-10-31 03:54:01.267952: +2025-10-31 03:54:01.271262: Epoch 134 +2025-10-31 03:54:01.273154: Current learning rate: 0.00879 +2025-10-31 03:54:22.594222: train_loss -0.9802 +2025-10-31 03:54:22.598344: val_loss -0.9094 +2025-10-31 03:54:22.601077: Pseudo dice [np.float32(0.9855), np.float32(0.9919), np.float32(0.9947), np.float32(0.8161)] +2025-10-31 03:54:22.603785: Epoch time: 21.33 s +2025-10-31 03:54:23.851549: +2025-10-31 03:54:23.853406: Epoch 135 +2025-10-31 03:54:23.855032: Current learning rate: 0.00878 +2025-10-31 03:54:45.787966: train_loss -0.9814 +2025-10-31 03:54:45.792761: val_loss -0.8891 +2025-10-31 03:54:45.794884: Pseudo dice [np.float32(0.984), np.float32(0.9911), np.float32(0.9935), np.float32(0.7679)] +2025-10-31 03:54:45.797538: Epoch time: 21.94 s +2025-10-31 03:54:47.199722: +2025-10-31 03:54:47.201888: Epoch 136 +2025-10-31 03:54:47.204273: Current learning rate: 0.00877 +2025-10-31 03:55:09.945819: train_loss -0.9757 +2025-10-31 03:55:09.948789: val_loss -0.8781 +2025-10-31 03:55:09.950688: Pseudo dice [np.float32(0.9834), np.float32(0.9899), np.float32(0.9897), np.float32(0.7794)] +2025-10-31 03:55:09.952914: Epoch time: 22.75 s +2025-10-31 03:55:10.975936: +2025-10-31 03:55:10.978637: Epoch 137 +2025-10-31 03:55:10.981164: Current learning rate: 0.00876 +2025-10-31 03:55:32.883780: train_loss -0.9669 +2025-10-31 03:55:32.889815: val_loss -0.9142 +2025-10-31 03:55:32.891584: Pseudo dice [np.float32(0.9855), np.float32(0.9915), np.float32(0.9942), np.float32(0.8209)] +2025-10-31 03:55:32.893180: Epoch time: 21.91 s +2025-10-31 03:55:34.203488: +2025-10-31 03:55:34.205586: Epoch 138 +2025-10-31 03:55:34.207581: Current learning rate: 0.00875 +2025-10-31 03:55:56.124967: train_loss -0.9737 +2025-10-31 03:55:56.131724: val_loss -0.9019 +2025-10-31 03:55:56.133418: Pseudo dice [np.float32(0.9846), np.float32(0.9913), np.float32(0.9941), np.float32(0.7857)] +2025-10-31 03:55:56.137423: Epoch time: 21.92 s +2025-10-31 03:55:57.382869: +2025-10-31 03:55:57.387520: Epoch 139 +2025-10-31 03:55:57.392547: Current learning rate: 0.00874 +2025-10-31 03:56:19.765048: train_loss -0.9781 +2025-10-31 03:56:19.767152: val_loss -0.9006 +2025-10-31 03:56:19.768851: Pseudo dice [np.float32(0.9846), np.float32(0.9913), np.float32(0.9944), np.float32(0.7924)] +2025-10-31 03:56:19.770200: Epoch time: 22.38 s +2025-10-31 03:56:21.014714: +2025-10-31 03:56:21.016969: Epoch 140 +2025-10-31 03:56:21.018808: Current learning rate: 0.00873 +2025-10-31 03:56:41.448885: train_loss -0.9814 +2025-10-31 03:56:41.451663: val_loss -0.8995 +2025-10-31 03:56:41.453686: Pseudo dice [np.float32(0.9854), np.float32(0.992), np.float32(0.9946), np.float32(0.7862)] +2025-10-31 03:56:41.455600: Epoch time: 20.44 s +2025-10-31 03:56:42.741081: +2025-10-31 03:56:42.744315: Epoch 141 +2025-10-31 03:56:42.746278: Current learning rate: 0.00872 +2025-10-31 03:57:04.260470: train_loss -0.9815 +2025-10-31 03:57:04.294004: val_loss -0.8891 +2025-10-31 03:57:04.296553: Pseudo dice [np.float32(0.9855), np.float32(0.9907), np.float32(0.9935), np.float32(0.7729)] +2025-10-31 03:57:04.298124: Epoch time: 21.52 s +2025-10-31 03:57:05.510209: +2025-10-31 03:57:05.512125: Epoch 142 +2025-10-31 03:57:05.514948: Current learning rate: 0.00871 +2025-10-31 03:57:27.620087: train_loss -0.9801 +2025-10-31 03:57:27.625296: val_loss -0.9028 +2025-10-31 03:57:27.627069: Pseudo dice [np.float32(0.9855), np.float32(0.991), np.float32(0.9941), np.float32(0.8056)] +2025-10-31 03:57:27.628765: Epoch time: 22.11 s +2025-10-31 03:57:28.775573: +2025-10-31 03:57:28.780771: Epoch 143 +2025-10-31 03:57:28.782472: Current learning rate: 0.0087 +2025-10-31 03:57:51.001481: train_loss -0.9814 +2025-10-31 03:57:51.005841: val_loss -0.8926 +2025-10-31 03:57:51.007469: Pseudo dice [np.float32(0.9834), np.float32(0.9908), np.float32(0.9945), np.float32(0.7796)] +2025-10-31 03:57:51.009054: Epoch time: 22.23 s +2025-10-31 03:57:52.047242: +2025-10-31 03:57:52.049830: Epoch 144 +2025-10-31 03:57:52.052348: Current learning rate: 0.00869 +2025-10-31 03:58:14.480780: train_loss -0.9792 +2025-10-31 03:58:14.487717: val_loss -0.8946 +2025-10-31 03:58:14.489536: Pseudo dice [np.float32(0.9851), np.float32(0.9918), np.float32(0.9941), np.float32(0.777)] +2025-10-31 03:58:14.491229: Epoch time: 22.44 s +2025-10-31 03:58:15.742026: +2025-10-31 03:58:15.743864: Epoch 145 +2025-10-31 03:58:15.745304: Current learning rate: 0.00868 +2025-10-31 03:58:37.988493: train_loss -0.9682 +2025-10-31 03:58:37.992353: val_loss -0.8773 +2025-10-31 03:58:37.994001: Pseudo dice [np.float32(0.9825), np.float32(0.9894), np.float32(0.9911), np.float32(0.7497)] +2025-10-31 03:58:37.995746: Epoch time: 22.25 s +2025-10-31 03:58:39.234719: +2025-10-31 03:58:39.236929: Epoch 146 +2025-10-31 03:58:39.239199: Current learning rate: 0.00868 +2025-10-31 03:58:58.800844: train_loss -0.9559 +2025-10-31 03:58:58.805254: val_loss -0.9015 +2025-10-31 03:58:58.808949: Pseudo dice [np.float32(0.9837), np.float32(0.9895), np.float32(0.9929), np.float32(0.7866)] +2025-10-31 03:58:58.812871: Epoch time: 19.57 s +2025-10-31 03:58:59.843081: +2025-10-31 03:58:59.845364: Epoch 147 +2025-10-31 03:58:59.847898: Current learning rate: 0.00867 +2025-10-31 03:59:21.581159: train_loss -0.9605 +2025-10-31 03:59:21.591309: val_loss -0.9088 +2025-10-31 03:59:21.593107: Pseudo dice [np.float32(0.985), np.float32(0.9902), np.float32(0.9941), np.float32(0.7967)] +2025-10-31 03:59:21.595334: Epoch time: 21.74 s +2025-10-31 03:59:23.290433: +2025-10-31 03:59:23.292878: Epoch 148 +2025-10-31 03:59:23.295527: Current learning rate: 0.00866 +2025-10-31 03:59:45.045784: train_loss -0.9615 +2025-10-31 03:59:45.048480: val_loss -0.9063 +2025-10-31 03:59:45.051123: Pseudo dice [np.float32(0.9844), np.float32(0.9902), np.float32(0.994), np.float32(0.7958)] +2025-10-31 03:59:45.054154: Epoch time: 21.76 s +2025-10-31 03:59:46.285584: +2025-10-31 03:59:46.289147: Epoch 149 +2025-10-31 03:59:46.292950: Current learning rate: 0.00865 +2025-10-31 04:00:08.527857: train_loss -0.9688 +2025-10-31 04:00:08.531574: val_loss -0.9078 +2025-10-31 04:00:08.533482: Pseudo dice [np.float32(0.9847), np.float32(0.9901), np.float32(0.9944), np.float32(0.7991)] +2025-10-31 04:00:08.539586: Epoch time: 22.24 s +2025-10-31 04:00:11.239233: +2025-10-31 04:00:11.243641: Epoch 150 +2025-10-31 04:00:11.245471: Current learning rate: 0.00864 +2025-10-31 04:00:33.926374: train_loss -0.9754 +2025-10-31 04:00:33.944081: val_loss -0.9023 +2025-10-31 04:00:33.950423: Pseudo dice [np.float32(0.9851), np.float32(0.9906), np.float32(0.9941), np.float32(0.7877)] +2025-10-31 04:00:33.956512: Epoch time: 22.69 s +2025-10-31 04:00:35.012185: +2025-10-31 04:00:35.014570: Epoch 151 +2025-10-31 04:00:35.017413: Current learning rate: 0.00863 +2025-10-31 04:00:57.530443: train_loss -0.9786 +2025-10-31 04:00:57.539916: val_loss -0.9032 +2025-10-31 04:00:57.548778: Pseudo dice [np.float32(0.9845), np.float32(0.991), np.float32(0.9942), np.float32(0.8039)] +2025-10-31 04:00:57.558334: Epoch time: 22.52 s +2025-10-31 04:00:58.613795: +2025-10-31 04:00:58.620916: Epoch 152 +2025-10-31 04:00:58.627075: Current learning rate: 0.00862 +2025-10-31 04:01:19.338676: train_loss -0.9547 +2025-10-31 04:01:19.341395: val_loss -0.8847 +2025-10-31 04:01:19.343053: Pseudo dice [np.float32(0.9829), np.float32(0.9885), np.float32(0.9919), np.float32(0.7447)] +2025-10-31 04:01:19.345347: Epoch time: 20.73 s +2025-10-31 04:01:20.624060: +2025-10-31 04:01:20.625750: Epoch 153 +2025-10-31 04:01:20.628955: Current learning rate: 0.00861 +2025-10-31 04:01:42.141046: train_loss -0.9477 +2025-10-31 04:01:42.157882: val_loss -0.9025 +2025-10-31 04:01:42.164705: Pseudo dice [np.float32(0.9837), np.float32(0.9902), np.float32(0.9937), np.float32(0.7803)] +2025-10-31 04:01:42.175303: Epoch time: 21.52 s +2025-10-31 04:01:43.427439: +2025-10-31 04:01:43.432747: Epoch 154 +2025-10-31 04:01:43.438258: Current learning rate: 0.0086 +2025-10-31 04:02:06.105456: train_loss -0.9612 +2025-10-31 04:02:06.114771: val_loss -0.9073 +2025-10-31 04:02:06.121742: Pseudo dice [np.float32(0.9846), np.float32(0.9911), np.float32(0.9941), np.float32(0.7913)] +2025-10-31 04:02:06.125326: Epoch time: 22.68 s +2025-10-31 04:02:07.299907: +2025-10-31 04:02:07.304431: Epoch 155 +2025-10-31 04:02:07.307600: Current learning rate: 0.00859 +2025-10-31 04:02:29.945925: train_loss -0.9672 +2025-10-31 04:02:29.949947: val_loss -0.9017 +2025-10-31 04:02:29.952990: Pseudo dice [np.float32(0.9836), np.float32(0.9898), np.float32(0.9935), np.float32(0.7936)] +2025-10-31 04:02:29.955936: Epoch time: 22.65 s +2025-10-31 04:02:31.209951: +2025-10-31 04:02:31.212934: Epoch 156 +2025-10-31 04:02:31.215272: Current learning rate: 0.00858 +2025-10-31 04:02:52.823992: train_loss -0.9728 +2025-10-31 04:02:52.833891: val_loss -0.8979 +2025-10-31 04:02:52.836207: Pseudo dice [np.float32(0.9837), np.float32(0.9904), np.float32(0.9928), np.float32(0.7859)] +2025-10-31 04:02:52.839095: Epoch time: 21.62 s +2025-10-31 04:02:53.981121: +2025-10-31 04:02:53.983524: Epoch 157 +2025-10-31 04:02:53.985847: Current learning rate: 0.00858 +2025-10-31 04:03:16.410209: train_loss -0.9757 +2025-10-31 04:03:16.412708: val_loss -0.8932 +2025-10-31 04:03:16.414421: Pseudo dice [np.float32(0.9839), np.float32(0.9908), np.float32(0.9934), np.float32(0.7836)] +2025-10-31 04:03:16.417031: Epoch time: 22.43 s +2025-10-31 04:03:17.637035: +2025-10-31 04:03:17.639680: Epoch 158 +2025-10-31 04:03:17.641511: Current learning rate: 0.00857 +2025-10-31 04:03:39.401277: train_loss -0.9764 +2025-10-31 04:03:39.403921: val_loss -0.8971 +2025-10-31 04:03:39.406263: Pseudo dice [np.float32(0.9831), np.float32(0.9911), np.float32(0.9938), np.float32(0.7754)] +2025-10-31 04:03:39.408323: Epoch time: 21.77 s +2025-10-31 04:03:40.873362: +2025-10-31 04:03:40.875839: Epoch 159 +2025-10-31 04:03:40.877894: Current learning rate: 0.00856 +2025-10-31 04:04:01.968826: train_loss -0.9785 +2025-10-31 04:04:01.975800: val_loss -0.9045 +2025-10-31 04:04:01.977689: Pseudo dice [np.float32(0.9833), np.float32(0.9902), np.float32(0.9946), np.float32(0.8)] +2025-10-31 04:04:01.979324: Epoch time: 21.1 s +2025-10-31 04:04:03.221262: +2025-10-31 04:04:03.224013: Epoch 160 +2025-10-31 04:04:03.226665: Current learning rate: 0.00855 +2025-10-31 04:04:25.008341: train_loss -0.9787 +2025-10-31 04:04:25.010804: val_loss -0.9045 +2025-10-31 04:04:25.012571: Pseudo dice [np.float32(0.9849), np.float32(0.9907), np.float32(0.9942), np.float32(0.798)] +2025-10-31 04:04:25.014363: Epoch time: 21.79 s +2025-10-31 04:04:26.166694: +2025-10-31 04:04:26.169176: Epoch 161 +2025-10-31 04:04:26.170983: Current learning rate: 0.00854 +2025-10-31 04:04:48.570715: train_loss -0.9775 +2025-10-31 04:04:48.573077: val_loss -0.9005 +2025-10-31 04:04:48.574575: Pseudo dice [np.float32(0.9841), np.float32(0.9911), np.float32(0.9944), np.float32(0.7835)] +2025-10-31 04:04:48.576131: Epoch time: 22.41 s +2025-10-31 04:04:49.795739: +2025-10-31 04:04:49.798285: Epoch 162 +2025-10-31 04:04:49.800256: Current learning rate: 0.00853 +2025-10-31 04:05:12.591999: train_loss -0.9789 +2025-10-31 04:05:12.620190: val_loss -0.9018 +2025-10-31 04:05:12.631684: Pseudo dice [np.float32(0.9831), np.float32(0.9911), np.float32(0.9948), np.float32(0.7905)] +2025-10-31 04:05:12.642001: Epoch time: 22.8 s +2025-10-31 04:05:13.882653: +2025-10-31 04:05:13.894150: Epoch 163 +2025-10-31 04:05:13.909421: Current learning rate: 0.00852 +2025-10-31 04:05:36.572686: train_loss -0.9799 +2025-10-31 04:05:36.578305: val_loss -0.9066 +2025-10-31 04:05:36.585935: Pseudo dice [np.float32(0.9844), np.float32(0.9917), np.float32(0.9949), np.float32(0.802)] +2025-10-31 04:05:36.593209: Epoch time: 22.69 s +2025-10-31 04:05:37.580431: +2025-10-31 04:05:37.585148: Epoch 164 +2025-10-31 04:05:37.587311: Current learning rate: 0.00851 +2025-10-31 04:05:58.679668: train_loss -0.9809 +2025-10-31 04:05:58.685000: val_loss -0.9027 +2025-10-31 04:05:58.691069: Pseudo dice [np.float32(0.9847), np.float32(0.9921), np.float32(0.9945), np.float32(0.7931)] +2025-10-31 04:05:58.695614: Epoch time: 21.1 s +2025-10-31 04:05:59.723250: +2025-10-31 04:05:59.725051: Epoch 165 +2025-10-31 04:05:59.726569: Current learning rate: 0.0085 +2025-10-31 04:06:21.354454: train_loss -0.982 +2025-10-31 04:06:21.360111: val_loss -0.8994 +2025-10-31 04:06:21.363290: Pseudo dice [np.float32(0.9845), np.float32(0.9909), np.float32(0.9942), np.float32(0.7978)] +2025-10-31 04:06:21.365955: Epoch time: 21.63 s +2025-10-31 04:06:22.529676: +2025-10-31 04:06:22.532063: Epoch 166 +2025-10-31 04:06:22.534074: Current learning rate: 0.00849 +2025-10-31 04:06:44.919040: train_loss -0.9801 +2025-10-31 04:06:44.921390: val_loss -0.9006 +2025-10-31 04:06:44.923568: Pseudo dice [np.float32(0.9835), np.float32(0.991), np.float32(0.9943), np.float32(0.7977)] +2025-10-31 04:06:44.925336: Epoch time: 22.39 s +2025-10-31 04:06:46.171060: +2025-10-31 04:06:46.174224: Epoch 167 +2025-10-31 04:06:46.176752: Current learning rate: 0.00848 +2025-10-31 04:07:08.716668: train_loss -0.9824 +2025-10-31 04:07:08.721826: val_loss -0.8972 +2025-10-31 04:07:08.724105: Pseudo dice [np.float32(0.9849), np.float32(0.991), np.float32(0.9943), np.float32(0.7911)] +2025-10-31 04:07:08.725982: Epoch time: 22.55 s +2025-10-31 04:07:10.031206: +2025-10-31 04:07:10.033283: Epoch 168 +2025-10-31 04:07:10.034902: Current learning rate: 0.00847 +2025-10-31 04:07:31.858949: train_loss -0.9806 +2025-10-31 04:07:31.863119: val_loss -0.9004 +2025-10-31 04:07:31.865597: Pseudo dice [np.float32(0.9856), np.float32(0.9911), np.float32(0.9942), np.float32(0.7993)] +2025-10-31 04:07:31.867395: Epoch time: 21.83 s +2025-10-31 04:07:33.001850: +2025-10-31 04:07:33.004066: Epoch 169 +2025-10-31 04:07:33.005581: Current learning rate: 0.00847 +2025-10-31 04:07:55.353712: train_loss -0.9792 +2025-10-31 04:07:55.359525: val_loss -0.9018 +2025-10-31 04:07:55.362857: Pseudo dice [np.float32(0.9846), np.float32(0.9909), np.float32(0.9944), np.float32(0.792)] +2025-10-31 04:07:55.365267: Epoch time: 22.35 s +2025-10-31 04:07:57.095527: +2025-10-31 04:07:57.097358: Epoch 170 +2025-10-31 04:07:57.100106: Current learning rate: 0.00846 +2025-10-31 04:08:18.865580: train_loss -0.9749 +2025-10-31 04:08:18.868356: val_loss -0.9007 +2025-10-31 04:08:18.870070: Pseudo dice [np.float32(0.9844), np.float32(0.9924), np.float32(0.9942), np.float32(0.7917)] +2025-10-31 04:08:18.872794: Epoch time: 21.77 s +2025-10-31 04:08:19.961810: +2025-10-31 04:08:19.963884: Epoch 171 +2025-10-31 04:08:19.965920: Current learning rate: 0.00845 +2025-10-31 04:08:41.914581: train_loss -0.9777 +2025-10-31 04:08:41.917521: val_loss -0.8994 +2025-10-31 04:08:41.919485: Pseudo dice [np.float32(0.9827), np.float32(0.99), np.float32(0.9938), np.float32(0.7972)] +2025-10-31 04:08:41.921015: Epoch time: 21.95 s +2025-10-31 04:08:43.247865: +2025-10-31 04:08:43.249790: Epoch 172 +2025-10-31 04:08:43.251508: Current learning rate: 0.00844 +2025-10-31 04:09:04.587357: train_loss -0.9789 +2025-10-31 04:09:04.589489: val_loss -0.9013 +2025-10-31 04:09:04.591081: Pseudo dice [np.float32(0.9826), np.float32(0.9898), np.float32(0.9937), np.float32(0.7991)] +2025-10-31 04:09:04.592676: Epoch time: 21.34 s +2025-10-31 04:09:05.658201: +2025-10-31 04:09:05.659975: Epoch 173 +2025-10-31 04:09:05.661365: Current learning rate: 0.00843 +2025-10-31 04:09:28.091437: train_loss -0.9804 +2025-10-31 04:09:28.093673: val_loss -0.9072 +2025-10-31 04:09:28.096175: Pseudo dice [np.float32(0.9863), np.float32(0.9923), np.float32(0.9947), np.float32(0.8111)] +2025-10-31 04:09:28.098562: Epoch time: 22.43 s +2025-10-31 04:09:28.100597: Yayy! New best EMA pseudo Dice: 0.9409999847412109 +2025-10-31 04:09:30.520678: +2025-10-31 04:09:30.522895: Epoch 174 +2025-10-31 04:09:30.526012: Current learning rate: 0.00842 +2025-10-31 04:09:52.698123: train_loss -0.9814 +2025-10-31 04:09:52.702103: val_loss -0.9037 +2025-10-31 04:09:52.704418: Pseudo dice [np.float32(0.984), np.float32(0.9918), np.float32(0.9949), np.float32(0.7999)] +2025-10-31 04:09:52.706372: Epoch time: 22.18 s +2025-10-31 04:09:52.708041: Yayy! New best EMA pseudo Dice: 0.9412000179290771 +2025-10-31 04:09:55.349506: +2025-10-31 04:09:55.351265: Epoch 175 +2025-10-31 04:09:55.352900: Current learning rate: 0.00841 +2025-10-31 04:10:17.489086: train_loss -0.9814 +2025-10-31 04:10:17.491247: val_loss -0.8974 +2025-10-31 04:10:17.493170: Pseudo dice [np.float32(0.985), np.float32(0.9913), np.float32(0.9943), np.float32(0.791)] +2025-10-31 04:10:17.494885: Epoch time: 22.14 s +2025-10-31 04:10:18.737576: +2025-10-31 04:10:18.739714: Epoch 176 +2025-10-31 04:10:18.742144: Current learning rate: 0.0084 +2025-10-31 04:10:40.484365: train_loss -0.9826 +2025-10-31 04:10:40.487377: val_loss -0.887 +2025-10-31 04:10:40.489703: Pseudo dice [np.float32(0.9852), np.float32(0.9912), np.float32(0.9926), np.float32(0.7694)] +2025-10-31 04:10:40.492096: Epoch time: 21.75 s +2025-10-31 04:10:41.620109: +2025-10-31 04:10:41.621920: Epoch 177 +2025-10-31 04:10:41.623567: Current learning rate: 0.00839 +2025-10-31 04:11:03.345417: train_loss -0.9831 +2025-10-31 04:11:03.355873: val_loss -0.897 +2025-10-31 04:11:03.358806: Pseudo dice [np.float32(0.9853), np.float32(0.9918), np.float32(0.994), np.float32(0.7949)] +2025-10-31 04:11:03.361398: Epoch time: 21.73 s +2025-10-31 04:11:04.474962: +2025-10-31 04:11:04.481615: Epoch 178 +2025-10-31 04:11:04.486159: Current learning rate: 0.00838 +2025-10-31 04:11:25.811475: train_loss -0.982 +2025-10-31 04:11:25.814093: val_loss -0.9011 +2025-10-31 04:11:25.815570: Pseudo dice [np.float32(0.9861), np.float32(0.9912), np.float32(0.9941), np.float32(0.8024)] +2025-10-31 04:11:25.817133: Epoch time: 21.34 s +2025-10-31 04:11:27.127705: +2025-10-31 04:11:27.130440: Epoch 179 +2025-10-31 04:11:27.132353: Current learning rate: 0.00837 +2025-10-31 04:11:48.431326: train_loss -0.9833 +2025-10-31 04:11:48.433311: val_loss -0.8919 +2025-10-31 04:11:48.435519: Pseudo dice [np.float32(0.9842), np.float32(0.9909), np.float32(0.9946), np.float32(0.7836)] +2025-10-31 04:11:48.437181: Epoch time: 21.31 s +2025-10-31 04:11:49.707342: +2025-10-31 04:11:49.709945: Epoch 180 +2025-10-31 04:11:49.712207: Current learning rate: 0.00836 +2025-10-31 04:12:10.755264: train_loss -0.983 +2025-10-31 04:12:10.758526: val_loss -0.8931 +2025-10-31 04:12:10.760306: Pseudo dice [np.float32(0.9844), np.float32(0.9914), np.float32(0.9935), np.float32(0.7736)] +2025-10-31 04:12:10.762499: Epoch time: 21.05 s +2025-10-31 04:12:12.363328: +2025-10-31 04:12:12.366904: Epoch 181 +2025-10-31 04:12:12.369485: Current learning rate: 0.00836 +2025-10-31 04:12:34.687207: train_loss -0.9832 +2025-10-31 04:12:34.691166: val_loss -0.9018 +2025-10-31 04:12:34.693164: Pseudo dice [np.float32(0.9856), np.float32(0.9913), np.float32(0.9943), np.float32(0.811)] +2025-10-31 04:12:34.694753: Epoch time: 22.33 s +2025-10-31 04:12:35.712347: +2025-10-31 04:12:35.714192: Epoch 182 +2025-10-31 04:12:35.716307: Current learning rate: 0.00835 +2025-10-31 04:12:58.291592: train_loss -0.984 +2025-10-31 04:12:58.309493: val_loss -0.8965 +2025-10-31 04:12:58.311535: Pseudo dice [np.float32(0.985), np.float32(0.9912), np.float32(0.9943), np.float32(0.7875)] +2025-10-31 04:12:58.313009: Epoch time: 22.58 s +2025-10-31 04:12:59.509428: +2025-10-31 04:12:59.511179: Epoch 183 +2025-10-31 04:12:59.512577: Current learning rate: 0.00834 +2025-10-31 04:13:21.222479: train_loss -0.9842 +2025-10-31 04:13:21.233250: val_loss -0.898 +2025-10-31 04:13:21.236894: Pseudo dice [np.float32(0.9846), np.float32(0.9922), np.float32(0.9949), np.float32(0.7863)] +2025-10-31 04:13:21.239209: Epoch time: 21.71 s +2025-10-31 04:13:22.554481: +2025-10-31 04:13:22.556705: Epoch 184 +2025-10-31 04:13:22.558585: Current learning rate: 0.00833 +2025-10-31 04:13:44.006444: train_loss -0.9834 +2025-10-31 04:13:44.009697: val_loss -0.8969 +2025-10-31 04:13:44.011253: Pseudo dice [np.float32(0.9845), np.float32(0.9922), np.float32(0.9945), np.float32(0.7875)] +2025-10-31 04:13:44.012588: Epoch time: 21.45 s +2025-10-31 04:13:45.211850: +2025-10-31 04:13:45.214120: Epoch 185 +2025-10-31 04:13:45.215608: Current learning rate: 0.00832 +2025-10-31 04:14:08.521174: train_loss -0.9836 +2025-10-31 04:14:08.532306: val_loss -0.8926 +2025-10-31 04:14:08.534107: Pseudo dice [np.float32(0.9858), np.float32(0.9923), np.float32(0.9937), np.float32(0.7831)] +2025-10-31 04:14:08.536435: Epoch time: 23.31 s +2025-10-31 04:14:09.636313: +2025-10-31 04:14:09.638966: Epoch 186 +2025-10-31 04:14:09.641050: Current learning rate: 0.00831 +2025-10-31 04:14:32.703514: train_loss -0.9831 +2025-10-31 04:14:32.711768: val_loss -0.8965 +2025-10-31 04:14:32.713680: Pseudo dice [np.float32(0.9848), np.float32(0.9912), np.float32(0.9941), np.float32(0.7919)] +2025-10-31 04:14:32.716185: Epoch time: 23.07 s +2025-10-31 04:14:34.057498: +2025-10-31 04:14:34.060196: Epoch 187 +2025-10-31 04:14:34.063358: Current learning rate: 0.0083 +2025-10-31 04:14:56.889200: train_loss -0.9832 +2025-10-31 04:14:56.893545: val_loss -0.8938 +2025-10-31 04:14:56.895723: Pseudo dice [np.float32(0.9847), np.float32(0.9911), np.float32(0.9942), np.float32(0.782)] +2025-10-31 04:14:56.898135: Epoch time: 22.83 s +2025-10-31 04:14:58.157026: +2025-10-31 04:14:58.158940: Epoch 188 +2025-10-31 04:14:58.160860: Current learning rate: 0.00829 +2025-10-31 04:15:20.303423: train_loss -0.9829 +2025-10-31 04:15:20.308125: val_loss -0.8957 +2025-10-31 04:15:20.310888: Pseudo dice [np.float32(0.9833), np.float32(0.9908), np.float32(0.9943), np.float32(0.7873)] +2025-10-31 04:15:20.312440: Epoch time: 22.15 s +2025-10-31 04:15:21.424114: +2025-10-31 04:15:21.426171: Epoch 189 +2025-10-31 04:15:21.428071: Current learning rate: 0.00828 +2025-10-31 04:15:43.330921: train_loss -0.9814 +2025-10-31 04:15:43.336697: val_loss -0.8926 +2025-10-31 04:15:43.338579: Pseudo dice [np.float32(0.9858), np.float32(0.9913), np.float32(0.9939), np.float32(0.7716)] +2025-10-31 04:15:43.340631: Epoch time: 21.91 s +2025-10-31 04:15:44.433360: +2025-10-31 04:15:44.436009: Epoch 190 +2025-10-31 04:15:44.437699: Current learning rate: 0.00827 +2025-10-31 04:16:06.559252: train_loss -0.9824 +2025-10-31 04:16:06.590168: val_loss -0.8916 +2025-10-31 04:16:06.597188: Pseudo dice [np.float32(0.9858), np.float32(0.9925), np.float32(0.9939), np.float32(0.768)] +2025-10-31 04:16:06.600954: Epoch time: 22.13 s +2025-10-31 04:16:07.787113: +2025-10-31 04:16:07.788860: Epoch 191 +2025-10-31 04:16:07.790795: Current learning rate: 0.00826 +2025-10-31 04:16:29.350634: train_loss -0.9825 +2025-10-31 04:16:29.355013: val_loss -0.8961 +2025-10-31 04:16:29.356438: Pseudo dice [np.float32(0.9839), np.float32(0.9914), np.float32(0.9941), np.float32(0.786)] +2025-10-31 04:16:29.357848: Epoch time: 21.56 s +2025-10-31 04:16:30.433256: +2025-10-31 04:16:30.436203: Epoch 192 +2025-10-31 04:16:30.438053: Current learning rate: 0.00825 +2025-10-31 04:16:52.792649: train_loss -0.9846 +2025-10-31 04:16:52.796396: val_loss -0.9005 +2025-10-31 04:16:52.798074: Pseudo dice [np.float32(0.9854), np.float32(0.9917), np.float32(0.9946), np.float32(0.796)] +2025-10-31 04:16:52.799999: Epoch time: 22.36 s +2025-10-31 04:16:54.661427: +2025-10-31 04:16:54.665076: Epoch 193 +2025-10-31 04:16:54.667951: Current learning rate: 0.00824 +2025-10-31 04:17:16.904226: train_loss -0.984 +2025-10-31 04:17:16.916036: val_loss -0.9055 +2025-10-31 04:17:16.921896: Pseudo dice [np.float32(0.9849), np.float32(0.9921), np.float32(0.9952), np.float32(0.8128)] +2025-10-31 04:17:16.927148: Epoch time: 22.24 s +2025-10-31 04:17:18.059928: +2025-10-31 04:17:18.067827: Epoch 194 +2025-10-31 04:17:18.076509: Current learning rate: 0.00824 +2025-10-31 04:17:40.504321: train_loss -0.9845 +2025-10-31 04:17:40.511188: val_loss -0.8879 +2025-10-31 04:17:40.513651: Pseudo dice [np.float32(0.9831), np.float32(0.9904), np.float32(0.9944), np.float32(0.775)] +2025-10-31 04:17:40.518148: Epoch time: 22.45 s +2025-10-31 04:17:41.793687: +2025-10-31 04:17:41.795481: Epoch 195 +2025-10-31 04:17:41.798054: Current learning rate: 0.00823 +2025-10-31 04:18:02.490571: train_loss -0.9844 +2025-10-31 04:18:02.501473: val_loss -0.8955 +2025-10-31 04:18:02.504048: Pseudo dice [np.float32(0.985), np.float32(0.9911), np.float32(0.9941), np.float32(0.7912)] +2025-10-31 04:18:02.505547: Epoch time: 20.7 s +2025-10-31 04:18:03.551480: +2025-10-31 04:18:03.554477: Epoch 196 +2025-10-31 04:18:03.556453: Current learning rate: 0.00822 +2025-10-31 04:18:25.456116: train_loss -0.9853 +2025-10-31 04:18:25.458955: val_loss -0.8922 +2025-10-31 04:18:25.460791: Pseudo dice [np.float32(0.9841), np.float32(0.9912), np.float32(0.9942), np.float32(0.7802)] +2025-10-31 04:18:25.463101: Epoch time: 21.91 s +2025-10-31 04:18:26.693342: +2025-10-31 04:18:26.699085: Epoch 197 +2025-10-31 04:18:26.704022: Current learning rate: 0.00821 +2025-10-31 04:18:47.881638: train_loss -0.9843 +2025-10-31 04:18:47.884528: val_loss -0.8957 +2025-10-31 04:18:47.886224: Pseudo dice [np.float32(0.9849), np.float32(0.9919), np.float32(0.9945), np.float32(0.7892)] +2025-10-31 04:18:47.888391: Epoch time: 21.19 s +2025-10-31 04:18:48.973308: +2025-10-31 04:18:48.975532: Epoch 198 +2025-10-31 04:18:48.978825: Current learning rate: 0.0082 +2025-10-31 04:19:11.597895: train_loss -0.9832 +2025-10-31 04:19:11.601270: val_loss -0.8942 +2025-10-31 04:19:11.603789: Pseudo dice [np.float32(0.9835), np.float32(0.9904), np.float32(0.9943), np.float32(0.795)] +2025-10-31 04:19:11.605827: Epoch time: 22.63 s +2025-10-31 04:19:12.647552: +2025-10-31 04:19:12.649443: Epoch 199 +2025-10-31 04:19:12.651438: Current learning rate: 0.00819 +2025-10-31 04:19:34.891573: train_loss -0.9844 +2025-10-31 04:19:34.896869: val_loss -0.8952 +2025-10-31 04:19:34.899498: Pseudo dice [np.float32(0.9826), np.float32(0.991), np.float32(0.9936), np.float32(0.7945)] +2025-10-31 04:19:34.902450: Epoch time: 22.25 s +2025-10-31 04:19:37.365289: +2025-10-31 04:19:37.368769: Epoch 200 +2025-10-31 04:19:37.371052: Current learning rate: 0.00818 +2025-10-31 04:19:59.583760: train_loss -0.9818 +2025-10-31 04:19:59.591661: val_loss -0.901 +2025-10-31 04:19:59.595224: Pseudo dice [np.float32(0.986), np.float32(0.9926), np.float32(0.9943), np.float32(0.7999)] +2025-10-31 04:19:59.597909: Epoch time: 22.22 s +2025-10-31 04:20:00.928346: +2025-10-31 04:20:00.930233: Epoch 201 +2025-10-31 04:20:00.931871: Current learning rate: 0.00817 +2025-10-31 04:20:21.109465: train_loss -0.9793 +2025-10-31 04:20:21.112287: val_loss -0.8919 +2025-10-31 04:20:21.113961: Pseudo dice [np.float32(0.9833), np.float32(0.9913), np.float32(0.9938), np.float32(0.7743)] +2025-10-31 04:20:21.115717: Epoch time: 20.18 s +2025-10-31 04:20:22.235484: +2025-10-31 04:20:22.237571: Epoch 202 +2025-10-31 04:20:22.239408: Current learning rate: 0.00816 +2025-10-31 04:20:44.576972: train_loss -0.9813 +2025-10-31 04:20:44.637105: val_loss -0.8966 +2025-10-31 04:20:44.640922: Pseudo dice [np.float32(0.9833), np.float32(0.9904), np.float32(0.9944), np.float32(0.7977)] +2025-10-31 04:20:44.645456: Epoch time: 22.34 s +2025-10-31 04:20:45.732907: +2025-10-31 04:20:45.736830: Epoch 203 +2025-10-31 04:20:45.738524: Current learning rate: 0.00815 +2025-10-31 04:21:07.742266: train_loss -0.9812 +2025-10-31 04:21:07.744959: val_loss -0.8951 +2025-10-31 04:21:07.746766: Pseudo dice [np.float32(0.9852), np.float32(0.9915), np.float32(0.9935), np.float32(0.7739)] +2025-10-31 04:21:07.748415: Epoch time: 22.01 s +2025-10-31 04:21:09.876041: +2025-10-31 04:21:09.878461: Epoch 204 +2025-10-31 04:21:09.880693: Current learning rate: 0.00814 +2025-10-31 04:21:31.759820: train_loss -0.9834 +2025-10-31 04:21:31.765956: val_loss -0.9118 +2025-10-31 04:21:31.768224: Pseudo dice [np.float32(0.9852), np.float32(0.9918), np.float32(0.9949), np.float32(0.821)] +2025-10-31 04:21:31.770804: Epoch time: 21.89 s +2025-10-31 04:21:32.871131: +2025-10-31 04:21:32.873143: Epoch 205 +2025-10-31 04:21:32.874951: Current learning rate: 0.00813 +2025-10-31 04:21:55.201345: train_loss -0.9847 +2025-10-31 04:21:55.206430: val_loss -0.8973 +2025-10-31 04:21:55.208258: Pseudo dice [np.float32(0.9842), np.float32(0.9912), np.float32(0.9943), np.float32(0.7957)] +2025-10-31 04:21:55.209994: Epoch time: 22.33 s +2025-10-31 04:21:56.291015: +2025-10-31 04:21:56.293221: Epoch 206 +2025-10-31 04:21:56.296517: Current learning rate: 0.00813 +2025-10-31 04:22:18.544012: train_loss -0.9836 +2025-10-31 04:22:18.546778: val_loss -0.9005 +2025-10-31 04:22:18.549467: Pseudo dice [np.float32(0.9859), np.float32(0.9921), np.float32(0.994), np.float32(0.7901)] +2025-10-31 04:22:18.553124: Epoch time: 22.25 s +2025-10-31 04:22:19.818924: +2025-10-31 04:22:19.822877: Epoch 207 +2025-10-31 04:22:19.827140: Current learning rate: 0.00812 +2025-10-31 04:22:40.008708: train_loss -0.9838 +2025-10-31 04:22:40.044897: val_loss -0.9011 +2025-10-31 04:22:40.048210: Pseudo dice [np.float32(0.9848), np.float32(0.9911), np.float32(0.9946), np.float32(0.8065)] +2025-10-31 04:22:40.051970: Epoch time: 20.19 s +2025-10-31 04:22:41.210682: +2025-10-31 04:22:41.214458: Epoch 208 +2025-10-31 04:22:41.217765: Current learning rate: 0.00811 +2025-10-31 04:23:03.784543: train_loss -0.9851 +2025-10-31 04:23:03.789214: val_loss -0.8987 +2025-10-31 04:23:03.791178: Pseudo dice [np.float32(0.9841), np.float32(0.9914), np.float32(0.9944), np.float32(0.795)] +2025-10-31 04:23:03.792933: Epoch time: 22.58 s +2025-10-31 04:23:04.811076: +2025-10-31 04:23:04.817334: Epoch 209 +2025-10-31 04:23:04.823130: Current learning rate: 0.0081 +2025-10-31 04:23:27.032031: train_loss -0.9858 +2025-10-31 04:23:27.037851: val_loss -0.8878 +2025-10-31 04:23:27.039621: Pseudo dice [np.float32(0.9846), np.float32(0.9904), np.float32(0.9939), np.float32(0.7715)] +2025-10-31 04:23:27.041535: Epoch time: 22.22 s +2025-10-31 04:23:28.229777: +2025-10-31 04:23:28.234037: Epoch 210 +2025-10-31 04:23:28.238005: Current learning rate: 0.00809 +2025-10-31 04:23:48.778801: train_loss -0.9854 +2025-10-31 04:23:48.785796: val_loss -0.8998 +2025-10-31 04:23:48.788634: Pseudo dice [np.float32(0.9856), np.float32(0.991), np.float32(0.9945), np.float32(0.7977)] +2025-10-31 04:23:48.790442: Epoch time: 20.55 s +2025-10-31 04:23:50.095785: +2025-10-31 04:23:50.098131: Epoch 211 +2025-10-31 04:23:50.100870: Current learning rate: 0.00808 +2025-10-31 04:24:12.597663: train_loss -0.9846 +2025-10-31 04:24:12.600953: val_loss -0.891 +2025-10-31 04:24:12.603289: Pseudo dice [np.float32(0.9844), np.float32(0.9912), np.float32(0.9936), np.float32(0.7856)] +2025-10-31 04:24:12.604831: Epoch time: 22.5 s +2025-10-31 04:24:13.674177: +2025-10-31 04:24:13.676253: Epoch 212 +2025-10-31 04:24:13.677846: Current learning rate: 0.00807 +2025-10-31 04:24:35.707491: train_loss -0.9844 +2025-10-31 04:24:35.711912: val_loss -0.902 +2025-10-31 04:24:35.714359: Pseudo dice [np.float32(0.9852), np.float32(0.9923), np.float32(0.995), np.float32(0.8056)] +2025-10-31 04:24:35.716379: Epoch time: 22.04 s +2025-10-31 04:24:36.790178: +2025-10-31 04:24:36.793596: Epoch 213 +2025-10-31 04:24:36.796304: Current learning rate: 0.00806 +2025-10-31 04:24:57.547797: train_loss -0.9847 +2025-10-31 04:24:57.562173: val_loss -0.8917 +2025-10-31 04:24:57.564526: Pseudo dice [np.float32(0.9853), np.float32(0.9912), np.float32(0.9938), np.float32(0.777)] +2025-10-31 04:24:57.566860: Epoch time: 20.76 s +2025-10-31 04:24:58.654597: +2025-10-31 04:24:58.656332: Epoch 214 +2025-10-31 04:24:58.658287: Current learning rate: 0.00805 +2025-10-31 04:25:21.219327: train_loss -0.9844 +2025-10-31 04:25:21.222375: val_loss -0.9003 +2025-10-31 04:25:21.224262: Pseudo dice [np.float32(0.9844), np.float32(0.9905), np.float32(0.9948), np.float32(0.8057)] +2025-10-31 04:25:21.225743: Epoch time: 22.57 s +2025-10-31 04:25:22.385311: +2025-10-31 04:25:22.390429: Epoch 215 +2025-10-31 04:25:22.396365: Current learning rate: 0.00804 +2025-10-31 04:25:44.454954: train_loss -0.9842 +2025-10-31 04:25:44.459024: val_loss -0.8961 +2025-10-31 04:25:44.461683: Pseudo dice [np.float32(0.9829), np.float32(0.991), np.float32(0.9949), np.float32(0.8034)] +2025-10-31 04:25:44.464486: Epoch time: 22.07 s +2025-10-31 04:25:46.274259: +2025-10-31 04:25:46.276770: Epoch 216 +2025-10-31 04:25:46.279144: Current learning rate: 0.00803 +2025-10-31 04:26:07.370868: train_loss -0.9851 +2025-10-31 04:26:07.376792: val_loss -0.8941 +2025-10-31 04:26:07.380410: Pseudo dice [np.float32(0.9851), np.float32(0.9905), np.float32(0.9942), np.float32(0.7902)] +2025-10-31 04:26:07.384691: Epoch time: 21.1 s +2025-10-31 04:26:08.417843: +2025-10-31 04:26:08.427271: Epoch 217 +2025-10-31 04:26:08.438630: Current learning rate: 0.00802 +2025-10-31 04:26:30.949388: train_loss -0.9851 +2025-10-31 04:26:30.970736: val_loss -0.8904 +2025-10-31 04:26:30.974026: Pseudo dice [np.float32(0.986), np.float32(0.9921), np.float32(0.9945), np.float32(0.7733)] +2025-10-31 04:26:30.975700: Epoch time: 22.53 s +2025-10-31 04:26:31.995800: +2025-10-31 04:26:31.998084: Epoch 218 +2025-10-31 04:26:31.999918: Current learning rate: 0.00801 +2025-10-31 04:26:54.407993: train_loss -0.9857 +2025-10-31 04:26:54.413835: val_loss -0.8922 +2025-10-31 04:26:54.416373: Pseudo dice [np.float32(0.9846), np.float32(0.9915), np.float32(0.9942), np.float32(0.7801)] +2025-10-31 04:26:54.419141: Epoch time: 22.41 s +2025-10-31 04:26:55.640174: +2025-10-31 04:26:55.642088: Epoch 219 +2025-10-31 04:26:55.643698: Current learning rate: 0.00801 +2025-10-31 04:27:15.271925: train_loss -0.9856 +2025-10-31 04:27:15.276674: val_loss -0.8997 +2025-10-31 04:27:15.279060: Pseudo dice [np.float32(0.9842), np.float32(0.9903), np.float32(0.9947), np.float32(0.8037)] +2025-10-31 04:27:15.281376: Epoch time: 19.63 s +2025-10-31 04:27:16.410650: +2025-10-31 04:27:16.412758: Epoch 220 +2025-10-31 04:27:16.414497: Current learning rate: 0.008 +2025-10-31 04:27:38.709692: train_loss -0.9849 +2025-10-31 04:27:38.720321: val_loss -0.8981 +2025-10-31 04:27:38.722500: Pseudo dice [np.float32(0.9861), np.float32(0.9922), np.float32(0.9942), np.float32(0.7903)] +2025-10-31 04:27:38.724441: Epoch time: 22.3 s +2025-10-31 04:27:40.006149: +2025-10-31 04:27:40.008604: Epoch 221 +2025-10-31 04:27:40.010890: Current learning rate: 0.00799 +2025-10-31 04:28:02.503931: train_loss -0.9857 +2025-10-31 04:28:02.507038: val_loss -0.893 +2025-10-31 04:28:02.508903: Pseudo dice [np.float32(0.9851), np.float32(0.9913), np.float32(0.9942), np.float32(0.7844)] +2025-10-31 04:28:02.511497: Epoch time: 22.5 s +2025-10-31 04:28:03.545833: +2025-10-31 04:28:03.549157: Epoch 222 +2025-10-31 04:28:03.551348: Current learning rate: 0.00798 +2025-10-31 04:28:25.833812: train_loss -0.9849 +2025-10-31 04:28:25.837337: val_loss -0.8948 +2025-10-31 04:28:25.839353: Pseudo dice [np.float32(0.983), np.float32(0.991), np.float32(0.9936), np.float32(0.8051)] +2025-10-31 04:28:25.841224: Epoch time: 22.29 s +2025-10-31 04:28:27.028813: +2025-10-31 04:28:27.031478: Epoch 223 +2025-10-31 04:28:27.033330: Current learning rate: 0.00797 +2025-10-31 04:28:48.168085: train_loss -0.9845 +2025-10-31 04:28:48.173223: val_loss -0.8984 +2025-10-31 04:28:48.175871: Pseudo dice [np.float32(0.9847), np.float32(0.9905), np.float32(0.9937), np.float32(0.8004)] +2025-10-31 04:28:48.177834: Epoch time: 21.14 s +2025-10-31 04:28:49.321132: +2025-10-31 04:28:49.323597: Epoch 224 +2025-10-31 04:28:49.326405: Current learning rate: 0.00796 +2025-10-31 04:29:11.803896: train_loss -0.9856 +2025-10-31 04:29:11.806636: val_loss -0.8955 +2025-10-31 04:29:11.808576: Pseudo dice [np.float32(0.9841), np.float32(0.9918), np.float32(0.9948), np.float32(0.7942)] +2025-10-31 04:29:11.810067: Epoch time: 22.48 s +2025-10-31 04:29:12.808527: +2025-10-31 04:29:12.810782: Epoch 225 +2025-10-31 04:29:12.813518: Current learning rate: 0.00795 +2025-10-31 04:29:33.638036: train_loss -0.9863 +2025-10-31 04:29:33.642507: val_loss -0.8965 +2025-10-31 04:29:33.644810: Pseudo dice [np.float32(0.9847), np.float32(0.9915), np.float32(0.9945), np.float32(0.794)] +2025-10-31 04:29:33.646888: Epoch time: 20.83 s +2025-10-31 04:29:34.630408: +2025-10-31 04:29:34.633016: Epoch 226 +2025-10-31 04:29:34.634498: Current learning rate: 0.00794 +2025-10-31 04:29:56.917877: train_loss -0.9849 +2025-10-31 04:29:56.924643: val_loss -0.9 +2025-10-31 04:29:56.926268: Pseudo dice [np.float32(0.9849), np.float32(0.9915), np.float32(0.9945), np.float32(0.8008)] +2025-10-31 04:29:56.928174: Epoch time: 22.29 s +2025-10-31 04:29:58.178868: +2025-10-31 04:29:58.180941: Epoch 227 +2025-10-31 04:29:58.184088: Current learning rate: 0.00793 +2025-10-31 04:30:20.403323: train_loss -0.9858 +2025-10-31 04:30:20.405807: val_loss -0.8913 +2025-10-31 04:30:20.407467: Pseudo dice [np.float32(0.9838), np.float32(0.9911), np.float32(0.9939), np.float32(0.7837)] +2025-10-31 04:30:20.409840: Epoch time: 22.23 s +2025-10-31 04:30:21.483932: +2025-10-31 04:30:21.488082: Epoch 228 +2025-10-31 04:30:21.491185: Current learning rate: 0.00792 +2025-10-31 04:30:43.949279: train_loss -0.9847 +2025-10-31 04:30:43.952652: val_loss -0.8979 +2025-10-31 04:30:43.954845: Pseudo dice [np.float32(0.9853), np.float32(0.9916), np.float32(0.9939), np.float32(0.7953)] +2025-10-31 04:30:43.956529: Epoch time: 22.47 s +2025-10-31 04:30:45.750691: +2025-10-31 04:30:45.761301: Epoch 229 +2025-10-31 04:30:45.771270: Current learning rate: 0.00791 +2025-10-31 04:31:07.006770: train_loss -0.9844 +2025-10-31 04:31:07.009954: val_loss -0.8991 +2025-10-31 04:31:07.012084: Pseudo dice [np.float32(0.9845), np.float32(0.9915), np.float32(0.9939), np.float32(0.7975)] +2025-10-31 04:31:07.014160: Epoch time: 21.26 s +2025-10-31 04:31:08.185999: +2025-10-31 04:31:08.188811: Epoch 230 +2025-10-31 04:31:08.191686: Current learning rate: 0.0079 +2025-10-31 04:31:30.570341: train_loss -0.9857 +2025-10-31 04:31:30.572825: val_loss -0.8784 +2025-10-31 04:31:30.574684: Pseudo dice [np.float32(0.9842), np.float32(0.9919), np.float32(0.9916), np.float32(0.7615)] +2025-10-31 04:31:30.576519: Epoch time: 22.39 s +2025-10-31 04:31:31.829483: +2025-10-31 04:31:31.831564: Epoch 231 +2025-10-31 04:31:31.833547: Current learning rate: 0.00789 +2025-10-31 04:31:53.421650: train_loss -0.985 +2025-10-31 04:31:53.428099: val_loss -0.8944 +2025-10-31 04:31:53.429617: Pseudo dice [np.float32(0.9844), np.float32(0.991), np.float32(0.9943), np.float32(0.7904)] +2025-10-31 04:31:53.431218: Epoch time: 21.59 s +2025-10-31 04:31:54.431895: +2025-10-31 04:31:54.433854: Epoch 232 +2025-10-31 04:31:54.436659: Current learning rate: 0.00789 +2025-10-31 04:32:15.688250: train_loss -0.9859 +2025-10-31 04:32:15.692425: val_loss -0.9026 +2025-10-31 04:32:15.699897: Pseudo dice [np.float32(0.9836), np.float32(0.9908), np.float32(0.9946), np.float32(0.8046)] +2025-10-31 04:32:15.704900: Epoch time: 21.26 s +2025-10-31 04:32:16.697063: +2025-10-31 04:32:16.699309: Epoch 233 +2025-10-31 04:32:16.703522: Current learning rate: 0.00788 +2025-10-31 04:32:39.543476: train_loss -0.986 +2025-10-31 04:32:39.547576: val_loss -0.898 +2025-10-31 04:32:39.549362: Pseudo dice [np.float32(0.9837), np.float32(0.9921), np.float32(0.9944), np.float32(0.7966)] +2025-10-31 04:32:39.551146: Epoch time: 22.85 s +2025-10-31 04:32:40.773632: +2025-10-31 04:32:40.777494: Epoch 234 +2025-10-31 04:32:40.781494: Current learning rate: 0.00787 +2025-10-31 04:33:02.587863: train_loss -0.9866 +2025-10-31 04:33:02.592088: val_loss -0.8896 +2025-10-31 04:33:02.596396: Pseudo dice [np.float32(0.9853), np.float32(0.9907), np.float32(0.9931), np.float32(0.7695)] +2025-10-31 04:33:02.599281: Epoch time: 21.82 s +2025-10-31 04:33:03.686007: +2025-10-31 04:33:03.687803: Epoch 235 +2025-10-31 04:33:03.689329: Current learning rate: 0.00786 +2025-10-31 04:33:25.449022: train_loss -0.9858 +2025-10-31 04:33:25.452138: val_loss -0.894 +2025-10-31 04:33:25.454792: Pseudo dice [np.float32(0.9839), np.float32(0.9912), np.float32(0.9946), np.float32(0.791)] +2025-10-31 04:33:25.457256: Epoch time: 21.76 s +2025-10-31 04:33:26.651658: +2025-10-31 04:33:26.654049: Epoch 236 +2025-10-31 04:33:26.655960: Current learning rate: 0.00785 +2025-10-31 04:33:48.460658: train_loss -0.9857 +2025-10-31 04:33:48.466560: val_loss -0.8924 +2025-10-31 04:33:48.471431: Pseudo dice [np.float32(0.9852), np.float32(0.9912), np.float32(0.9942), np.float32(0.7851)] +2025-10-31 04:33:48.477164: Epoch time: 21.81 s +2025-10-31 04:33:49.717790: +2025-10-31 04:33:49.720238: Epoch 237 +2025-10-31 04:33:49.722027: Current learning rate: 0.00784 +2025-10-31 04:34:12.192142: train_loss -0.9849 +2025-10-31 04:34:12.200828: val_loss -0.8925 +2025-10-31 04:34:12.204698: Pseudo dice [np.float32(0.986), np.float32(0.9921), np.float32(0.993), np.float32(0.7902)] +2025-10-31 04:34:12.207101: Epoch time: 22.48 s +2025-10-31 04:34:13.495508: +2025-10-31 04:34:13.499637: Epoch 238 +2025-10-31 04:34:13.501407: Current learning rate: 0.00783 +2025-10-31 04:34:34.818396: train_loss -0.986 +2025-10-31 04:34:34.829053: val_loss -0.8981 +2025-10-31 04:34:34.833238: Pseudo dice [np.float32(0.9862), np.float32(0.9921), np.float32(0.9941), np.float32(0.794)] +2025-10-31 04:34:34.834849: Epoch time: 21.32 s +2025-10-31 04:34:36.090463: +2025-10-31 04:34:36.092490: Epoch 239 +2025-10-31 04:34:36.094263: Current learning rate: 0.00782 +2025-10-31 04:34:58.538854: train_loss -0.9866 +2025-10-31 04:34:58.543931: val_loss -0.896 +2025-10-31 04:34:58.548126: Pseudo dice [np.float32(0.9852), np.float32(0.9915), np.float32(0.9944), np.float32(0.7899)] +2025-10-31 04:34:58.553255: Epoch time: 22.45 s +2025-10-31 04:34:59.581048: +2025-10-31 04:34:59.589184: Epoch 240 +2025-10-31 04:34:59.595057: Current learning rate: 0.00781 +2025-10-31 04:35:22.195002: train_loss -0.9865 +2025-10-31 04:35:22.199603: val_loss -0.9004 +2025-10-31 04:35:22.201339: Pseudo dice [np.float32(0.9858), np.float32(0.9921), np.float32(0.9945), np.float32(0.7949)] +2025-10-31 04:35:22.204006: Epoch time: 22.62 s +2025-10-31 04:35:23.238379: +2025-10-31 04:35:23.243138: Epoch 241 +2025-10-31 04:35:23.245165: Current learning rate: 0.0078 +2025-10-31 04:35:46.179881: train_loss -0.9856 +2025-10-31 04:35:46.183685: val_loss -0.8999 +2025-10-31 04:35:46.186314: Pseudo dice [np.float32(0.9856), np.float32(0.9917), np.float32(0.9946), np.float32(0.8041)] +2025-10-31 04:35:46.189682: Epoch time: 22.94 s +2025-10-31 04:35:47.895420: +2025-10-31 04:35:47.897452: Epoch 242 +2025-10-31 04:35:47.899618: Current learning rate: 0.00779 +2025-10-31 04:36:08.638131: train_loss -0.9862 +2025-10-31 04:36:08.641213: val_loss -0.8941 +2025-10-31 04:36:08.642828: Pseudo dice [np.float32(0.9854), np.float32(0.9922), np.float32(0.9947), np.float32(0.7839)] +2025-10-31 04:36:08.644800: Epoch time: 20.74 s +2025-10-31 04:36:09.721655: +2025-10-31 04:36:09.724505: Epoch 243 +2025-10-31 04:36:09.727506: Current learning rate: 0.00778 +2025-10-31 04:36:31.945266: train_loss -0.9832 +2025-10-31 04:36:31.948941: val_loss -0.8985 +2025-10-31 04:36:31.951863: Pseudo dice [np.float32(0.984), np.float32(0.9921), np.float32(0.9946), np.float32(0.7993)] +2025-10-31 04:36:31.953357: Epoch time: 22.23 s +2025-10-31 04:36:33.150855: +2025-10-31 04:36:33.156166: Epoch 244 +2025-10-31 04:36:33.158620: Current learning rate: 0.00777 +2025-10-31 04:36:55.036420: train_loss -0.9854 +2025-10-31 04:36:55.039436: val_loss -0.9023 +2025-10-31 04:36:55.042226: Pseudo dice [np.float32(0.9858), np.float32(0.992), np.float32(0.9946), np.float32(0.8002)] +2025-10-31 04:36:55.045674: Epoch time: 21.89 s +2025-10-31 04:36:56.256121: +2025-10-31 04:36:56.258001: Epoch 245 +2025-10-31 04:36:56.259779: Current learning rate: 0.00777 +2025-10-31 04:37:18.811250: train_loss -0.9854 +2025-10-31 04:37:18.818128: val_loss -0.9021 +2025-10-31 04:37:18.822531: Pseudo dice [np.float32(0.9852), np.float32(0.9921), np.float32(0.9944), np.float32(0.8054)] +2025-10-31 04:37:18.828646: Epoch time: 22.56 s +2025-10-31 04:37:18.836035: Yayy! New best EMA pseudo Dice: 0.9412999749183655 +2025-10-31 04:37:21.784865: +2025-10-31 04:37:21.786939: Epoch 246 +2025-10-31 04:37:21.788627: Current learning rate: 0.00776 +2025-10-31 04:37:43.718202: train_loss -0.9856 +2025-10-31 04:37:43.722931: val_loss -0.8966 +2025-10-31 04:37:43.724954: Pseudo dice [np.float32(0.9848), np.float32(0.9915), np.float32(0.9942), np.float32(0.7913)] +2025-10-31 04:37:43.727087: Epoch time: 21.94 s +2025-10-31 04:37:44.803970: +2025-10-31 04:37:44.808021: Epoch 247 +2025-10-31 04:37:44.810254: Current learning rate: 0.00775 +2025-10-31 04:38:07.524455: train_loss -0.9852 +2025-10-31 04:38:07.530137: val_loss -0.8923 +2025-10-31 04:38:07.533181: Pseudo dice [np.float32(0.985), np.float32(0.9917), np.float32(0.9923), np.float32(0.8056)] +2025-10-31 04:38:07.538280: Epoch time: 22.72 s +2025-10-31 04:38:07.543133: Yayy! New best EMA pseudo Dice: 0.9413999915122986 +2025-10-31 04:38:10.213082: +2025-10-31 04:38:10.216556: Epoch 248 +2025-10-31 04:38:10.220388: Current learning rate: 0.00774 +2025-10-31 04:38:31.606900: train_loss -0.9746 +2025-10-31 04:38:31.613670: val_loss -0.8987 +2025-10-31 04:38:31.615597: Pseudo dice [np.float32(0.9851), np.float32(0.9911), np.float32(0.9939), np.float32(0.7923)] +2025-10-31 04:38:31.617283: Epoch time: 21.4 s +2025-10-31 04:38:32.911898: +2025-10-31 04:38:32.918463: Epoch 249 +2025-10-31 04:38:32.922605: Current learning rate: 0.00773 +2025-10-31 04:38:54.424456: train_loss -0.9793 +2025-10-31 04:38:54.427746: val_loss -0.8533 +2025-10-31 04:38:54.429342: Pseudo dice [np.float32(0.9858), np.float32(0.9922), np.float32(0.985), np.float32(0.7514)] +2025-10-31 04:38:54.432144: Epoch time: 21.51 s +2025-10-31 04:38:56.855248: +2025-10-31 04:38:56.861645: Epoch 250 +2025-10-31 04:38:56.869491: Current learning rate: 0.00772 +2025-10-31 04:39:19.186771: train_loss -0.9834 +2025-10-31 04:39:19.194299: val_loss -0.9006 +2025-10-31 04:39:19.200583: Pseudo dice [np.float32(0.9851), np.float32(0.9919), np.float32(0.9943), np.float32(0.7923)] +2025-10-31 04:39:19.208503: Epoch time: 22.33 s +2025-10-31 04:39:20.285549: +2025-10-31 04:39:20.288232: Epoch 251 +2025-10-31 04:39:20.292652: Current learning rate: 0.00771 +2025-10-31 04:39:42.477664: train_loss -0.9835 +2025-10-31 04:39:42.480538: val_loss -0.8978 +2025-10-31 04:39:42.482636: Pseudo dice [np.float32(0.9849), np.float32(0.9917), np.float32(0.9943), np.float32(0.7966)] +2025-10-31 04:39:42.484481: Epoch time: 22.19 s +2025-10-31 04:39:43.656390: +2025-10-31 04:39:43.662050: Epoch 252 +2025-10-31 04:39:43.666332: Current learning rate: 0.0077 +2025-10-31 04:40:05.872131: train_loss -0.9854 +2025-10-31 04:40:05.882546: val_loss -0.8977 +2025-10-31 04:40:05.887578: Pseudo dice [np.float32(0.9849), np.float32(0.9912), np.float32(0.9942), np.float32(0.7989)] +2025-10-31 04:40:05.892749: Epoch time: 22.22 s +2025-10-31 04:40:07.130750: +2025-10-31 04:40:07.140959: Epoch 253 +2025-10-31 04:40:07.144220: Current learning rate: 0.00769 +2025-10-31 04:40:28.685036: train_loss -0.9849 +2025-10-31 04:40:28.689309: val_loss -0.8908 +2025-10-31 04:40:28.692749: Pseudo dice [np.float32(0.986), np.float32(0.9908), np.float32(0.9941), np.float32(0.7756)] +2025-10-31 04:40:28.695387: Epoch time: 21.56 s +2025-10-31 04:40:30.307482: +2025-10-31 04:40:30.309922: Epoch 254 +2025-10-31 04:40:30.312760: Current learning rate: 0.00768 +2025-10-31 04:40:51.739198: train_loss -0.9852 +2025-10-31 04:40:51.741296: val_loss -0.8917 +2025-10-31 04:40:51.743139: Pseudo dice [np.float32(0.9851), np.float32(0.9914), np.float32(0.9945), np.float32(0.7829)] +2025-10-31 04:40:51.744969: Epoch time: 21.43 s +2025-10-31 04:40:52.935307: +2025-10-31 04:40:52.937845: Epoch 255 +2025-10-31 04:40:52.940917: Current learning rate: 0.00767 +2025-10-31 04:41:14.839419: train_loss -0.9855 +2025-10-31 04:41:14.859076: val_loss -0.8998 +2025-10-31 04:41:14.864280: Pseudo dice [np.float32(0.9851), np.float32(0.9914), np.float32(0.9942), np.float32(0.7989)] +2025-10-31 04:41:14.869841: Epoch time: 21.91 s +2025-10-31 04:41:15.931724: +2025-10-31 04:41:15.934823: Epoch 256 +2025-10-31 04:41:15.937087: Current learning rate: 0.00766 +2025-10-31 04:41:37.368966: train_loss -0.9859 +2025-10-31 04:41:37.372995: val_loss -0.8946 +2025-10-31 04:41:37.377121: Pseudo dice [np.float32(0.9845), np.float32(0.9909), np.float32(0.9945), np.float32(0.7874)] +2025-10-31 04:41:37.380363: Epoch time: 21.44 s +2025-10-31 04:41:38.404276: +2025-10-31 04:41:38.406532: Epoch 257 +2025-10-31 04:41:38.408130: Current learning rate: 0.00765 +2025-10-31 04:42:00.085032: train_loss -0.9853 +2025-10-31 04:42:00.089283: val_loss -0.8956 +2025-10-31 04:42:00.093549: Pseudo dice [np.float32(0.9845), np.float32(0.9908), np.float32(0.9944), np.float32(0.8018)] +2025-10-31 04:42:00.098493: Epoch time: 21.68 s +2025-10-31 04:42:01.177714: +2025-10-31 04:42:01.180377: Epoch 258 +2025-10-31 04:42:01.182354: Current learning rate: 0.00764 +2025-10-31 04:42:22.852199: train_loss -0.9853 +2025-10-31 04:42:22.854970: val_loss -0.8977 +2025-10-31 04:42:22.856707: Pseudo dice [np.float32(0.9858), np.float32(0.9919), np.float32(0.9944), np.float32(0.7976)] +2025-10-31 04:42:22.859100: Epoch time: 21.68 s +2025-10-31 04:42:23.829296: +2025-10-31 04:42:23.831292: Epoch 259 +2025-10-31 04:42:23.833294: Current learning rate: 0.00764 +2025-10-31 04:42:45.722462: train_loss -0.9857 +2025-10-31 04:42:45.724885: val_loss -0.9028 +2025-10-31 04:42:45.726405: Pseudo dice [np.float32(0.9858), np.float32(0.9923), np.float32(0.9948), np.float32(0.8063)] +2025-10-31 04:42:45.727901: Epoch time: 21.89 s +2025-10-31 04:42:46.904552: +2025-10-31 04:42:46.907135: Epoch 260 +2025-10-31 04:42:46.909154: Current learning rate: 0.00763 +2025-10-31 04:43:09.151534: train_loss -0.9871 +2025-10-31 04:43:09.154245: val_loss -0.8759 +2025-10-31 04:43:09.158120: Pseudo dice [np.float32(0.9858), np.float32(0.9912), np.float32(0.9893), np.float32(0.7838)] +2025-10-31 04:43:09.160101: Epoch time: 22.25 s +2025-10-31 04:43:10.401422: +2025-10-31 04:43:10.403705: Epoch 261 +2025-10-31 04:43:10.405808: Current learning rate: 0.00762 +2025-10-31 04:43:30.724835: train_loss -0.9865 +2025-10-31 04:43:30.731282: val_loss -0.897 +2025-10-31 04:43:30.734456: Pseudo dice [np.float32(0.9863), np.float32(0.9919), np.float32(0.9942), np.float32(0.7948)] +2025-10-31 04:43:30.738448: Epoch time: 20.33 s +2025-10-31 04:43:31.811518: +2025-10-31 04:43:31.813424: Epoch 262 +2025-10-31 04:43:31.815144: Current learning rate: 0.00761 +2025-10-31 04:43:53.040599: train_loss -0.9831 +2025-10-31 04:43:53.046655: val_loss -0.9025 +2025-10-31 04:43:53.052386: Pseudo dice [np.float32(0.9855), np.float32(0.9914), np.float32(0.9945), np.float32(0.797)] +2025-10-31 04:43:53.056400: Epoch time: 21.23 s +2025-10-31 04:43:54.090700: +2025-10-31 04:43:54.092389: Epoch 263 +2025-10-31 04:43:54.093869: Current learning rate: 0.0076 +2025-10-31 04:44:16.269155: train_loss -0.9839 +2025-10-31 04:44:16.276539: val_loss -0.8938 +2025-10-31 04:44:16.278543: Pseudo dice [np.float32(0.9847), np.float32(0.9909), np.float32(0.9946), np.float32(0.7863)] +2025-10-31 04:44:16.280622: Epoch time: 22.18 s +2025-10-31 04:44:17.462060: +2025-10-31 04:44:17.464128: Epoch 264 +2025-10-31 04:44:17.467099: Current learning rate: 0.00759 +2025-10-31 04:44:39.754354: train_loss -0.9848 +2025-10-31 04:44:39.759040: val_loss -0.8883 +2025-10-31 04:44:39.761879: Pseudo dice [np.float32(0.9837), np.float32(0.9906), np.float32(0.9932), np.float32(0.7752)] +2025-10-31 04:44:39.764566: Epoch time: 22.29 s +2025-10-31 04:44:40.994869: +2025-10-31 04:44:40.998121: Epoch 265 +2025-10-31 04:44:41.000869: Current learning rate: 0.00758 +2025-10-31 04:45:03.196883: train_loss -0.9855 +2025-10-31 04:45:03.202590: val_loss -0.8846 +2025-10-31 04:45:03.206509: Pseudo dice [np.float32(0.984), np.float32(0.9904), np.float32(0.9936), np.float32(0.7677)] +2025-10-31 04:45:03.212433: Epoch time: 22.2 s +2025-10-31 04:45:04.320443: +2025-10-31 04:45:04.322649: Epoch 266 +2025-10-31 04:45:04.324921: Current learning rate: 0.00757 +2025-10-31 04:45:26.692229: train_loss -0.9857 +2025-10-31 04:45:26.695382: val_loss -0.8855 +2025-10-31 04:45:26.699700: Pseudo dice [np.float32(0.9852), np.float32(0.9915), np.float32(0.9935), np.float32(0.7767)] +2025-10-31 04:45:26.702653: Epoch time: 22.37 s +2025-10-31 04:45:28.317641: +2025-10-31 04:45:28.320720: Epoch 267 +2025-10-31 04:45:28.324852: Current learning rate: 0.00756 +2025-10-31 04:45:49.116710: train_loss -0.9863 +2025-10-31 04:45:49.120803: val_loss -0.8906 +2025-10-31 04:45:49.123557: Pseudo dice [np.float32(0.9841), np.float32(0.9914), np.float32(0.9939), np.float32(0.7792)] +2025-10-31 04:45:49.126125: Epoch time: 20.8 s +2025-10-31 04:45:50.347500: +2025-10-31 04:45:50.349513: Epoch 268 +2025-10-31 04:45:50.351546: Current learning rate: 0.00755 +2025-10-31 04:46:11.140235: train_loss -0.9862 +2025-10-31 04:46:11.149735: val_loss -0.8929 +2025-10-31 04:46:11.161313: Pseudo dice [np.float32(0.9858), np.float32(0.9912), np.float32(0.9937), np.float32(0.7879)] +2025-10-31 04:46:11.170486: Epoch time: 20.79 s +2025-10-31 04:46:12.402480: +2025-10-31 04:46:12.405071: Epoch 269 +2025-10-31 04:46:12.407320: Current learning rate: 0.00754 +2025-10-31 04:46:34.385522: train_loss -0.986 +2025-10-31 04:46:34.388108: val_loss -0.8973 +2025-10-31 04:46:34.390195: Pseudo dice [np.float32(0.9858), np.float32(0.9922), np.float32(0.995), np.float32(0.7913)] +2025-10-31 04:46:34.392526: Epoch time: 21.98 s +2025-10-31 04:46:35.393356: +2025-10-31 04:46:35.395374: Epoch 270 +2025-10-31 04:46:35.397083: Current learning rate: 0.00753 +2025-10-31 04:46:57.918075: train_loss -0.9861 +2025-10-31 04:46:57.922405: val_loss -0.9042 +2025-10-31 04:46:57.924839: Pseudo dice [np.float32(0.9849), np.float32(0.9921), np.float32(0.9949), np.float32(0.8122)] +2025-10-31 04:46:57.927769: Epoch time: 22.53 s +2025-10-31 04:46:59.157384: +2025-10-31 04:46:59.160489: Epoch 271 +2025-10-31 04:46:59.162273: Current learning rate: 0.00752 +2025-10-31 04:47:20.980149: train_loss -0.9865 +2025-10-31 04:47:20.985492: val_loss -0.8943 +2025-10-31 04:47:20.990322: Pseudo dice [np.float32(0.9859), np.float32(0.9904), np.float32(0.9943), np.float32(0.7942)] +2025-10-31 04:47:20.995291: Epoch time: 21.82 s +2025-10-31 04:47:22.205523: +2025-10-31 04:47:22.207735: Epoch 272 +2025-10-31 04:47:22.209816: Current learning rate: 0.00751 +2025-10-31 04:47:44.409948: train_loss -0.9866 +2025-10-31 04:47:44.415464: val_loss -0.8957 +2025-10-31 04:47:44.419369: Pseudo dice [np.float32(0.9849), np.float32(0.9912), np.float32(0.9945), np.float32(0.7929)] +2025-10-31 04:47:44.424725: Epoch time: 22.21 s +2025-10-31 04:47:45.423404: +2025-10-31 04:47:45.426045: Epoch 273 +2025-10-31 04:47:45.428204: Current learning rate: 0.00751 +2025-10-31 04:48:08.026062: train_loss -0.9864 +2025-10-31 04:48:08.030535: val_loss -0.8952 +2025-10-31 04:48:08.033593: Pseudo dice [np.float32(0.9841), np.float32(0.991), np.float32(0.9943), np.float32(0.8005)] +2025-10-31 04:48:08.039572: Epoch time: 22.6 s +2025-10-31 04:48:09.062747: +2025-10-31 04:48:09.072666: Epoch 274 +2025-10-31 04:48:09.077454: Current learning rate: 0.0075 +2025-10-31 04:48:27.798261: train_loss -0.975 +2025-10-31 04:48:27.801011: val_loss -0.8953 +2025-10-31 04:48:27.802932: Pseudo dice [np.float32(0.984), np.float32(0.9902), np.float32(0.9934), np.float32(0.7808)] +2025-10-31 04:48:27.804638: Epoch time: 18.74 s +2025-10-31 04:48:28.984860: +2025-10-31 04:48:28.987958: Epoch 275 +2025-10-31 04:48:28.990651: Current learning rate: 0.00749 +2025-10-31 04:48:50.979996: train_loss -0.9728 +2025-10-31 04:48:50.982832: val_loss -0.905 +2025-10-31 04:48:50.984900: Pseudo dice [np.float32(0.9861), np.float32(0.992), np.float32(0.9942), np.float32(0.798)] +2025-10-31 04:48:50.987470: Epoch time: 22.0 s +2025-10-31 04:48:52.146574: +2025-10-31 04:48:52.148448: Epoch 276 +2025-10-31 04:48:52.150573: Current learning rate: 0.00748 +2025-10-31 04:49:14.878121: train_loss -0.9779 +2025-10-31 04:49:14.892432: val_loss -0.8981 +2025-10-31 04:49:14.894156: Pseudo dice [np.float32(0.9865), np.float32(0.9915), np.float32(0.9944), np.float32(0.7869)] +2025-10-31 04:49:14.895607: Epoch time: 22.73 s +2025-10-31 04:49:16.145442: +2025-10-31 04:49:16.147744: Epoch 277 +2025-10-31 04:49:16.150301: Current learning rate: 0.00747 +2025-10-31 04:49:39.329821: train_loss -0.9799 +2025-10-31 04:49:39.332999: val_loss -0.8977 +2025-10-31 04:49:39.335740: Pseudo dice [np.float32(0.9861), np.float32(0.9915), np.float32(0.9944), np.float32(0.7883)] +2025-10-31 04:49:39.339190: Epoch time: 23.19 s +2025-10-31 04:49:40.585043: +2025-10-31 04:49:40.591787: Epoch 278 +2025-10-31 04:49:40.594048: Current learning rate: 0.00746 +2025-10-31 04:50:02.651116: train_loss -0.9827 +2025-10-31 04:50:02.654483: val_loss -0.9045 +2025-10-31 04:50:02.663059: Pseudo dice [np.float32(0.9855), np.float32(0.9922), np.float32(0.9945), np.float32(0.8029)] +2025-10-31 04:50:02.673100: Epoch time: 22.07 s +2025-10-31 04:50:04.463622: +2025-10-31 04:50:04.465699: Epoch 279 +2025-10-31 04:50:04.467622: Current learning rate: 0.00745 +2025-10-31 04:50:26.605312: train_loss -0.9695 +2025-10-31 04:50:26.608757: val_loss -0.8922 +2025-10-31 04:50:26.611063: Pseudo dice [np.float32(0.984), np.float32(0.9914), np.float32(0.9921), np.float32(0.7807)] +2025-10-31 04:50:26.612532: Epoch time: 22.14 s +2025-10-31 04:50:27.668247: +2025-10-31 04:50:27.672180: Epoch 280 +2025-10-31 04:50:27.675970: Current learning rate: 0.00744 +2025-10-31 04:50:47.757408: train_loss -0.9663 +2025-10-31 04:50:47.761193: val_loss -0.9048 +2025-10-31 04:50:47.762855: Pseudo dice [np.float32(0.986), np.float32(0.991), np.float32(0.9942), np.float32(0.7969)] +2025-10-31 04:50:47.764683: Epoch time: 20.09 s +2025-10-31 04:50:48.772721: +2025-10-31 04:50:48.776712: Epoch 281 +2025-10-31 04:50:48.778411: Current learning rate: 0.00743 +2025-10-31 04:51:11.474385: train_loss -0.9688 +2025-10-31 04:51:11.478216: val_loss -0.9092 +2025-10-31 04:51:11.481803: Pseudo dice [np.float32(0.9843), np.float32(0.9922), np.float32(0.9943), np.float32(0.803)] +2025-10-31 04:51:11.486023: Epoch time: 22.7 s +2025-10-31 04:51:12.521430: +2025-10-31 04:51:12.523609: Epoch 282 +2025-10-31 04:51:12.525549: Current learning rate: 0.00742 +2025-10-31 04:51:34.358958: train_loss -0.9753 +2025-10-31 04:51:34.364325: val_loss -0.8865 +2025-10-31 04:51:34.366311: Pseudo dice [np.float32(0.9838), np.float32(0.9908), np.float32(0.9941), np.float32(0.7547)] +2025-10-31 04:51:34.368545: Epoch time: 21.84 s +2025-10-31 04:51:35.429970: +2025-10-31 04:51:35.434260: Epoch 283 +2025-10-31 04:51:35.436336: Current learning rate: 0.00741 +2025-10-31 04:51:57.865138: train_loss -0.9775 +2025-10-31 04:51:57.868666: val_loss -0.8911 +2025-10-31 04:51:57.870438: Pseudo dice [np.float32(0.9847), np.float32(0.9911), np.float32(0.9935), np.float32(0.7655)] +2025-10-31 04:51:57.872719: Epoch time: 22.44 s +2025-10-31 04:51:59.001884: +2025-10-31 04:51:59.004325: Epoch 284 +2025-10-31 04:51:59.006300: Current learning rate: 0.0074 +2025-10-31 04:52:21.310851: train_loss -0.9652 +2025-10-31 04:52:21.313841: val_loss -0.8995 +2025-10-31 04:52:21.317668: Pseudo dice [np.float32(0.985), np.float32(0.9913), np.float32(0.9934), np.float32(0.7868)] +2025-10-31 04:52:21.319434: Epoch time: 22.31 s +2025-10-31 04:52:22.347652: +2025-10-31 04:52:22.354183: Epoch 285 +2025-10-31 04:52:22.360585: Current learning rate: 0.00739 +2025-10-31 04:52:45.334494: train_loss -0.9663 +2025-10-31 04:52:45.340691: val_loss -0.8942 +2025-10-31 04:52:45.345706: Pseudo dice [np.float32(0.9859), np.float32(0.9918), np.float32(0.9932), np.float32(0.766)] +2025-10-31 04:52:45.349594: Epoch time: 22.99 s +2025-10-31 04:52:46.577738: +2025-10-31 04:52:46.580341: Epoch 286 +2025-10-31 04:52:46.582572: Current learning rate: 0.00738 +2025-10-31 04:53:07.371306: train_loss -0.978 +2025-10-31 04:53:07.373497: val_loss -0.8941 +2025-10-31 04:53:07.375320: Pseudo dice [np.float32(0.9848), np.float32(0.9919), np.float32(0.9938), np.float32(0.7782)] +2025-10-31 04:53:07.376950: Epoch time: 20.8 s +2025-10-31 04:53:08.408000: +2025-10-31 04:53:08.412440: Epoch 287 +2025-10-31 04:53:08.416734: Current learning rate: 0.00738 +2025-10-31 04:53:29.396036: train_loss -0.9776 +2025-10-31 04:53:29.399029: val_loss -0.8743 +2025-10-31 04:53:29.401630: Pseudo dice [np.float32(0.9832), np.float32(0.9903), np.float32(0.9888), np.float32(0.7646)] +2025-10-31 04:53:29.406557: Epoch time: 20.99 s +2025-10-31 04:53:30.428608: +2025-10-31 04:53:30.430982: Epoch 288 +2025-10-31 04:53:30.432699: Current learning rate: 0.00737 +2025-10-31 04:53:53.588290: train_loss -0.9573 +2025-10-31 04:53:53.596146: val_loss -0.8939 +2025-10-31 04:53:53.600053: Pseudo dice [np.float32(0.9832), np.float32(0.9895), np.float32(0.9933), np.float32(0.7644)] +2025-10-31 04:53:53.604603: Epoch time: 23.16 s +2025-10-31 04:53:54.625873: +2025-10-31 04:53:54.627804: Epoch 289 +2025-10-31 04:53:54.629486: Current learning rate: 0.00736 +2025-10-31 04:54:16.360461: train_loss -0.9478 +2025-10-31 04:54:16.363505: val_loss -0.9005 +2025-10-31 04:54:16.365519: Pseudo dice [np.float32(0.9835), np.float32(0.9885), np.float32(0.9927), np.float32(0.7955)] +2025-10-31 04:54:16.368049: Epoch time: 21.74 s +2025-10-31 04:54:17.597155: +2025-10-31 04:54:17.599193: Epoch 290 +2025-10-31 04:54:17.601029: Current learning rate: 0.00735 +2025-10-31 04:54:39.927851: train_loss -0.9419 +2025-10-31 04:54:39.930381: val_loss -0.9048 +2025-10-31 04:54:39.932386: Pseudo dice [np.float32(0.9874), np.float32(0.9915), np.float32(0.9938), np.float32(0.7836)] +2025-10-31 04:54:39.934134: Epoch time: 22.33 s +2025-10-31 04:54:41.124831: +2025-10-31 04:54:41.127346: Epoch 291 +2025-10-31 04:54:41.129357: Current learning rate: 0.00734 +2025-10-31 04:55:03.457356: train_loss -0.9636 +2025-10-31 04:55:03.460868: val_loss -0.9055 +2025-10-31 04:55:03.462873: Pseudo dice [np.float32(0.9855), np.float32(0.9911), np.float32(0.9947), np.float32(0.7857)] +2025-10-31 04:55:03.464989: Epoch time: 22.33 s +2025-10-31 04:55:04.992990: +2025-10-31 04:55:04.995617: Epoch 292 +2025-10-31 04:55:05.001345: Current learning rate: 0.00733 +2025-10-31 04:55:26.763443: train_loss -0.97 +2025-10-31 04:55:26.765432: val_loss -0.9081 +2025-10-31 04:55:26.766834: Pseudo dice [np.float32(0.9835), np.float32(0.9912), np.float32(0.9948), np.float32(0.802)] +2025-10-31 04:55:26.768367: Epoch time: 21.77 s +2025-10-31 04:55:27.764249: +2025-10-31 04:55:27.767088: Epoch 293 +2025-10-31 04:55:27.769020: Current learning rate: 0.00732 +2025-10-31 04:55:47.611696: train_loss -0.973 +2025-10-31 04:55:47.627124: val_loss -0.9035 +2025-10-31 04:55:47.643452: Pseudo dice [np.float32(0.9851), np.float32(0.9918), np.float32(0.9942), np.float32(0.7854)] +2025-10-31 04:55:47.654742: Epoch time: 19.85 s +2025-10-31 04:55:49.041010: +2025-10-31 04:55:49.070480: Epoch 294 +2025-10-31 04:55:49.078793: Current learning rate: 0.00731 +2025-10-31 04:56:10.319718: train_loss -0.9757 +2025-10-31 04:56:10.323376: val_loss -0.9001 +2025-10-31 04:56:10.325370: Pseudo dice [np.float32(0.9849), np.float32(0.9909), np.float32(0.9936), np.float32(0.7855)] +2025-10-31 04:56:10.327686: Epoch time: 21.28 s +2025-10-31 04:56:11.560913: +2025-10-31 04:56:11.562782: Epoch 295 +2025-10-31 04:56:11.564720: Current learning rate: 0.0073 +2025-10-31 04:56:33.693189: train_loss -0.9807 +2025-10-31 04:56:33.698209: val_loss -0.9012 +2025-10-31 04:56:33.700756: Pseudo dice [np.float32(0.9864), np.float32(0.9924), np.float32(0.9946), np.float32(0.7857)] +2025-10-31 04:56:33.702650: Epoch time: 22.13 s +2025-10-31 04:56:34.817503: +2025-10-31 04:56:34.819834: Epoch 296 +2025-10-31 04:56:34.821707: Current learning rate: 0.00729 +2025-10-31 04:56:57.115371: train_loss -0.9814 +2025-10-31 04:56:57.118982: val_loss -0.9009 +2025-10-31 04:56:57.120395: Pseudo dice [np.float32(0.9843), np.float32(0.9915), np.float32(0.9942), np.float32(0.7927)] +2025-10-31 04:56:57.121919: Epoch time: 22.3 s +2025-10-31 04:56:58.166035: +2025-10-31 04:56:58.167809: Epoch 297 +2025-10-31 04:56:58.169941: Current learning rate: 0.00728 +2025-10-31 04:57:20.326942: train_loss -0.9818 +2025-10-31 04:57:20.330509: val_loss -0.9037 +2025-10-31 04:57:20.332837: Pseudo dice [np.float32(0.9866), np.float32(0.9926), np.float32(0.9948), np.float32(0.7956)] +2025-10-31 04:57:20.335008: Epoch time: 22.16 s +2025-10-31 04:57:21.562387: +2025-10-31 04:57:21.568176: Epoch 298 +2025-10-31 04:57:21.573211: Current learning rate: 0.00727 +2025-10-31 04:57:42.595850: train_loss -0.9826 +2025-10-31 04:57:42.598198: val_loss -0.8921 +2025-10-31 04:57:42.600062: Pseudo dice [np.float32(0.9841), np.float32(0.9908), np.float32(0.9941), np.float32(0.7729)] +2025-10-31 04:57:42.601697: Epoch time: 21.04 s +2025-10-31 04:57:43.729738: +2025-10-31 04:57:43.732911: Epoch 299 +2025-10-31 04:57:43.735362: Current learning rate: 0.00726 +2025-10-31 04:58:05.886714: train_loss -0.982 +2025-10-31 04:58:05.893856: val_loss -0.9005 +2025-10-31 04:58:05.900615: Pseudo dice [np.float32(0.9844), np.float32(0.9913), np.float32(0.995), np.float32(0.7903)] +2025-10-31 04:58:05.904946: Epoch time: 22.16 s +2025-10-31 04:58:08.734714: +2025-10-31 04:58:08.737190: Epoch 300 +2025-10-31 04:58:08.739259: Current learning rate: 0.00725 +2025-10-31 04:58:29.148092: train_loss -0.9815 +2025-10-31 04:58:29.158216: val_loss -0.8931 +2025-10-31 04:58:29.160674: Pseudo dice [np.float32(0.985), np.float32(0.9913), np.float32(0.9939), np.float32(0.775)] +2025-10-31 04:58:29.163002: Epoch time: 20.42 s +2025-10-31 04:58:30.195020: +2025-10-31 04:58:30.197849: Epoch 301 +2025-10-31 04:58:30.200502: Current learning rate: 0.00724 +2025-10-31 04:58:52.107288: train_loss -0.9836 +2025-10-31 04:58:52.110840: val_loss -0.8985 +2025-10-31 04:58:52.112552: Pseudo dice [np.float32(0.9856), np.float32(0.9917), np.float32(0.9943), np.float32(0.7898)] +2025-10-31 04:58:52.114470: Epoch time: 21.91 s +2025-10-31 04:58:53.473301: +2025-10-31 04:58:53.477962: Epoch 302 +2025-10-31 04:58:53.482353: Current learning rate: 0.00724 +2025-10-31 04:59:15.100689: train_loss -0.9838 +2025-10-31 04:59:15.103351: val_loss -0.8953 +2025-10-31 04:59:15.105474: Pseudo dice [np.float32(0.9844), np.float32(0.9918), np.float32(0.9941), np.float32(0.7787)] +2025-10-31 04:59:15.107825: Epoch time: 21.63 s +2025-10-31 04:59:16.223806: +2025-10-31 04:59:16.225597: Epoch 303 +2025-10-31 04:59:16.227175: Current learning rate: 0.00723 +2025-10-31 04:59:38.594590: train_loss -0.9848 +2025-10-31 04:59:38.598072: val_loss -0.8946 +2025-10-31 04:59:38.599847: Pseudo dice [np.float32(0.9844), np.float32(0.9907), np.float32(0.9942), np.float32(0.7936)] +2025-10-31 04:59:38.602283: Epoch time: 22.37 s +2025-10-31 04:59:40.178781: +2025-10-31 04:59:40.181596: Epoch 304 +2025-10-31 04:59:40.184147: Current learning rate: 0.00722 +2025-10-31 05:00:02.292647: train_loss -0.9838 +2025-10-31 05:00:02.304714: val_loss -0.8931 +2025-10-31 05:00:02.323832: Pseudo dice [np.float32(0.9847), np.float32(0.992), np.float32(0.9941), np.float32(0.7773)] +2025-10-31 05:00:02.342710: Epoch time: 22.12 s +2025-10-31 05:00:03.432867: +2025-10-31 05:00:03.450665: Epoch 305 +2025-10-31 05:00:03.462867: Current learning rate: 0.00721 +2025-10-31 05:00:25.362053: train_loss -0.9835 +2025-10-31 05:00:25.371328: val_loss -0.8993 +2025-10-31 05:00:25.380177: Pseudo dice [np.float32(0.9847), np.float32(0.9914), np.float32(0.9945), np.float32(0.7944)] +2025-10-31 05:00:25.388864: Epoch time: 21.93 s +2025-10-31 05:00:26.513071: +2025-10-31 05:00:26.524819: Epoch 306 +2025-10-31 05:00:26.531358: Current learning rate: 0.0072 +2025-10-31 05:00:47.534189: train_loss -0.9848 +2025-10-31 05:00:47.547060: val_loss -0.8954 +2025-10-31 05:00:47.549032: Pseudo dice [np.float32(0.9839), np.float32(0.992), np.float32(0.9945), np.float32(0.7872)] +2025-10-31 05:00:47.551647: Epoch time: 21.02 s +2025-10-31 05:00:48.636684: +2025-10-31 05:00:48.649588: Epoch 307 +2025-10-31 05:00:48.667346: Current learning rate: 0.00719 +2025-10-31 05:01:11.223830: train_loss -0.9849 +2025-10-31 05:01:11.229958: val_loss -0.8982 +2025-10-31 05:01:11.236037: Pseudo dice [np.float32(0.9835), np.float32(0.9916), np.float32(0.9951), np.float32(0.7935)] +2025-10-31 05:01:11.244003: Epoch time: 22.59 s +2025-10-31 05:01:12.459254: +2025-10-31 05:01:12.468821: Epoch 308 +2025-10-31 05:01:12.479240: Current learning rate: 0.00718 +2025-10-31 05:01:34.829283: train_loss -0.9857 +2025-10-31 05:01:34.847439: val_loss -0.9007 +2025-10-31 05:01:34.863921: Pseudo dice [np.float32(0.9844), np.float32(0.9919), np.float32(0.9946), np.float32(0.8006)] +2025-10-31 05:01:34.879337: Epoch time: 22.37 s +2025-10-31 05:01:36.147808: +2025-10-31 05:01:36.158784: Epoch 309 +2025-10-31 05:01:36.168597: Current learning rate: 0.00717 +2025-10-31 05:01:57.898993: train_loss -0.9861 +2025-10-31 05:01:57.907272: val_loss -0.8908 +2025-10-31 05:01:57.910836: Pseudo dice [np.float32(0.9848), np.float32(0.9918), np.float32(0.9942), np.float32(0.7781)] +2025-10-31 05:01:57.913970: Epoch time: 21.75 s +2025-10-31 05:01:59.086679: +2025-10-31 05:01:59.089091: Epoch 310 +2025-10-31 05:01:59.091207: Current learning rate: 0.00716 +2025-10-31 05:02:19.873566: train_loss -0.9853 +2025-10-31 05:02:19.883826: val_loss -0.8952 +2025-10-31 05:02:19.893153: Pseudo dice [np.float32(0.9839), np.float32(0.9917), np.float32(0.9944), np.float32(0.7891)] +2025-10-31 05:02:19.904526: Epoch time: 20.79 s +2025-10-31 05:02:21.083756: +2025-10-31 05:02:21.093682: Epoch 311 +2025-10-31 05:02:21.103863: Current learning rate: 0.00715 +2025-10-31 05:02:43.587039: train_loss -0.9858 +2025-10-31 05:02:43.589755: val_loss -0.8993 +2025-10-31 05:02:43.591597: Pseudo dice [np.float32(0.9853), np.float32(0.9911), np.float32(0.9943), np.float32(0.8012)] +2025-10-31 05:02:43.593344: Epoch time: 22.5 s +2025-10-31 05:02:44.670130: +2025-10-31 05:02:44.672615: Epoch 312 +2025-10-31 05:02:44.675109: Current learning rate: 0.00714 +2025-10-31 05:03:07.164159: train_loss -0.986 +2025-10-31 05:03:07.188397: val_loss -0.8958 +2025-10-31 05:03:07.195287: Pseudo dice [np.float32(0.9844), np.float32(0.9917), np.float32(0.9946), np.float32(0.7929)] +2025-10-31 05:03:07.206082: Epoch time: 22.5 s +2025-10-31 05:03:08.345129: +2025-10-31 05:03:08.348037: Epoch 313 +2025-10-31 05:03:08.353529: Current learning rate: 0.00713 +2025-10-31 05:03:29.515717: train_loss -0.9854 +2025-10-31 05:03:29.525616: val_loss -0.8988 +2025-10-31 05:03:29.532442: Pseudo dice [np.float32(0.9842), np.float32(0.991), np.float32(0.9947), np.float32(0.8012)] +2025-10-31 05:03:29.542103: Epoch time: 21.17 s +2025-10-31 05:03:30.806419: +2025-10-31 05:03:30.814316: Epoch 314 +2025-10-31 05:03:30.819336: Current learning rate: 0.00712 +2025-10-31 05:03:53.036236: train_loss -0.9851 +2025-10-31 05:03:53.041435: val_loss -0.8982 +2025-10-31 05:03:53.045451: Pseudo dice [np.float32(0.9854), np.float32(0.9917), np.float32(0.9941), np.float32(0.79)] +2025-10-31 05:03:53.049361: Epoch time: 22.23 s +2025-10-31 05:03:54.265616: +2025-10-31 05:03:54.268378: Epoch 315 +2025-10-31 05:03:54.270766: Current learning rate: 0.00711 +2025-10-31 05:04:16.828748: train_loss -0.9857 +2025-10-31 05:04:16.834331: val_loss -0.8989 +2025-10-31 05:04:16.836711: Pseudo dice [np.float32(0.9855), np.float32(0.9918), np.float32(0.9946), np.float32(0.7972)] +2025-10-31 05:04:16.838864: Epoch time: 22.56 s +2025-10-31 05:04:18.253561: +2025-10-31 05:04:18.255965: Epoch 316 +2025-10-31 05:04:18.258188: Current learning rate: 0.0071 +2025-10-31 05:04:39.720819: train_loss -0.9866 +2025-10-31 05:04:39.728792: val_loss -0.8938 +2025-10-31 05:04:39.732527: Pseudo dice [np.float32(0.9845), np.float32(0.9917), np.float32(0.9947), np.float32(0.7845)] +2025-10-31 05:04:39.734295: Epoch time: 21.47 s +2025-10-31 05:04:40.714839: +2025-10-31 05:04:40.717115: Epoch 317 +2025-10-31 05:04:40.719039: Current learning rate: 0.0071 +2025-10-31 05:05:02.239026: train_loss -0.9856 +2025-10-31 05:05:02.245248: val_loss -0.893 +2025-10-31 05:05:02.251658: Pseudo dice [np.float32(0.9833), np.float32(0.9909), np.float32(0.9942), np.float32(0.7858)] +2025-10-31 05:05:02.260209: Epoch time: 21.53 s +2025-10-31 05:05:03.526075: +2025-10-31 05:05:03.528332: Epoch 318 +2025-10-31 05:05:03.530251: Current learning rate: 0.00709 +2025-10-31 05:05:25.698616: train_loss -0.9868 +2025-10-31 05:05:25.709818: val_loss -0.8997 +2025-10-31 05:05:25.712848: Pseudo dice [np.float32(0.9864), np.float32(0.9923), np.float32(0.9947), np.float32(0.8019)] +2025-10-31 05:05:25.715943: Epoch time: 22.17 s +2025-10-31 05:05:26.927877: +2025-10-31 05:05:26.934556: Epoch 319 +2025-10-31 05:05:26.936325: Current learning rate: 0.00708 +2025-10-31 05:05:48.305310: train_loss -0.9868 +2025-10-31 05:05:48.308628: val_loss -0.8877 +2025-10-31 05:05:48.310913: Pseudo dice [np.float32(0.984), np.float32(0.9912), np.float32(0.9944), np.float32(0.7733)] +2025-10-31 05:05:48.312525: Epoch time: 21.38 s +2025-10-31 05:05:49.465367: +2025-10-31 05:05:49.467380: Epoch 320 +2025-10-31 05:05:49.469468: Current learning rate: 0.00707 +2025-10-31 05:06:11.515626: train_loss -0.9862 +2025-10-31 05:06:11.522089: val_loss -0.8994 +2025-10-31 05:06:11.525312: Pseudo dice [np.float32(0.9856), np.float32(0.9914), np.float32(0.9948), np.float32(0.8023)] +2025-10-31 05:06:11.527667: Epoch time: 22.05 s +2025-10-31 05:06:12.828360: +2025-10-31 05:06:12.831779: Epoch 321 +2025-10-31 05:06:12.834340: Current learning rate: 0.00706 +2025-10-31 05:06:34.953956: train_loss -0.9867 +2025-10-31 05:06:34.958661: val_loss -0.8901 +2025-10-31 05:06:34.959911: Pseudo dice [np.float32(0.9844), np.float32(0.9915), np.float32(0.9942), np.float32(0.7828)] +2025-10-31 05:06:34.961288: Epoch time: 22.13 s +2025-10-31 05:06:36.221094: +2025-10-31 05:06:36.224444: Epoch 322 +2025-10-31 05:06:36.226264: Current learning rate: 0.00705 +2025-10-31 05:06:56.778179: train_loss -0.9869 +2025-10-31 05:06:56.781147: val_loss -0.9064 +2025-10-31 05:06:56.783974: Pseudo dice [np.float32(0.9852), np.float32(0.9921), np.float32(0.995), np.float32(0.8148)] +2025-10-31 05:06:56.786989: Epoch time: 20.56 s +2025-10-31 05:06:58.004814: +2025-10-31 05:06:58.007065: Epoch 323 +2025-10-31 05:06:58.008943: Current learning rate: 0.00704 +2025-10-31 05:07:19.927248: train_loss -0.9869 +2025-10-31 05:07:19.933243: val_loss -0.8953 +2025-10-31 05:07:19.934772: Pseudo dice [np.float32(0.985), np.float32(0.9922), np.float32(0.9947), np.float32(0.7898)] +2025-10-31 05:07:19.936280: Epoch time: 21.92 s +2025-10-31 05:07:20.960577: +2025-10-31 05:07:20.963263: Epoch 324 +2025-10-31 05:07:20.965818: Current learning rate: 0.00703 +2025-10-31 05:07:43.476437: train_loss -0.9871 +2025-10-31 05:07:43.481714: val_loss -0.897 +2025-10-31 05:07:43.483503: Pseudo dice [np.float32(0.9848), np.float32(0.9911), np.float32(0.9943), np.float32(0.8017)] +2025-10-31 05:07:43.485333: Epoch time: 22.52 s +2025-10-31 05:07:44.543539: +2025-10-31 05:07:44.545953: Epoch 325 +2025-10-31 05:07:44.548039: Current learning rate: 0.00702 +2025-10-31 05:08:06.176888: train_loss -0.9875 +2025-10-31 05:08:06.182875: val_loss -0.9 +2025-10-31 05:08:06.188339: Pseudo dice [np.float32(0.985), np.float32(0.9917), np.float32(0.9947), np.float32(0.8036)] +2025-10-31 05:08:06.192161: Epoch time: 21.64 s +2025-10-31 05:08:07.395124: +2025-10-31 05:08:07.397766: Epoch 326 +2025-10-31 05:08:07.399999: Current learning rate: 0.00701 +2025-10-31 05:08:28.770885: train_loss -0.9863 +2025-10-31 05:08:28.781878: val_loss -0.9012 +2025-10-31 05:08:28.792054: Pseudo dice [np.float32(0.9857), np.float32(0.9924), np.float32(0.995), np.float32(0.8089)] +2025-10-31 05:08:28.801922: Epoch time: 21.38 s +2025-10-31 05:08:28.806633: Yayy! New best EMA pseudo Dice: 0.9416999816894531 +2025-10-31 05:08:31.567259: +2025-10-31 05:08:31.571870: Epoch 327 +2025-10-31 05:08:31.574763: Current learning rate: 0.007 +2025-10-31 05:08:54.098968: train_loss -0.9875 +2025-10-31 05:08:54.112340: val_loss -0.901 +2025-10-31 05:08:54.115854: Pseudo dice [np.float32(0.9868), np.float32(0.9927), np.float32(0.9946), np.float32(0.7926)] +2025-10-31 05:08:54.119592: Epoch time: 22.53 s +2025-10-31 05:08:55.581578: +2025-10-31 05:08:55.589803: Epoch 328 +2025-10-31 05:08:55.595760: Current learning rate: 0.00699 +2025-10-31 05:09:17.215169: train_loss -0.9863 +2025-10-31 05:09:17.224880: val_loss -0.8868 +2025-10-31 05:09:17.228122: Pseudo dice [np.float32(0.9849), np.float32(0.9916), np.float32(0.9945), np.float32(0.7696)] +2025-10-31 05:09:17.230541: Epoch time: 21.64 s +2025-10-31 05:09:18.346610: +2025-10-31 05:09:18.349878: Epoch 329 +2025-10-31 05:09:18.351924: Current learning rate: 0.00698 +2025-10-31 05:09:39.869568: train_loss -0.9866 +2025-10-31 05:09:39.876509: val_loss -0.902 +2025-10-31 05:09:39.881581: Pseudo dice [np.float32(0.9864), np.float32(0.9919), np.float32(0.9947), np.float32(0.8025)] +2025-10-31 05:09:39.885306: Epoch time: 21.52 s +2025-10-31 05:09:40.964649: +2025-10-31 05:09:40.968338: Epoch 330 +2025-10-31 05:09:40.970921: Current learning rate: 0.00697 +2025-10-31 05:10:03.151868: train_loss -0.9874 +2025-10-31 05:10:03.159148: val_loss -0.9006 +2025-10-31 05:10:03.160756: Pseudo dice [np.float32(0.9856), np.float32(0.9916), np.float32(0.9945), np.float32(0.8087)] +2025-10-31 05:10:03.162333: Epoch time: 22.19 s +2025-10-31 05:10:03.163867: Yayy! New best EMA pseudo Dice: 0.9416999816894531 +2025-10-31 05:10:05.576117: +2025-10-31 05:10:05.578946: Epoch 331 +2025-10-31 05:10:05.582319: Current learning rate: 0.00696 +2025-10-31 05:10:27.976259: train_loss -0.987 +2025-10-31 05:10:27.978259: val_loss -0.8942 +2025-10-31 05:10:27.980357: Pseudo dice [np.float32(0.9854), np.float32(0.9919), np.float32(0.9943), np.float32(0.7953)] +2025-10-31 05:10:27.982052: Epoch time: 22.4 s +2025-10-31 05:10:27.983707: Yayy! New best EMA pseudo Dice: 0.9416999816894531 +2025-10-31 05:10:30.979943: +2025-10-31 05:10:30.984424: Epoch 332 +2025-10-31 05:10:30.986384: Current learning rate: 0.00696 +2025-10-31 05:10:52.580559: train_loss -0.987 +2025-10-31 05:10:52.584572: val_loss -0.8952 +2025-10-31 05:10:52.586715: Pseudo dice [np.float32(0.9862), np.float32(0.9922), np.float32(0.9946), np.float32(0.7882)] +2025-10-31 05:10:52.588743: Epoch time: 21.6 s +2025-10-31 05:10:53.933129: +2025-10-31 05:10:53.936657: Epoch 333 +2025-10-31 05:10:53.938429: Current learning rate: 0.00695 +2025-10-31 05:11:15.920635: train_loss -0.9868 +2025-10-31 05:11:15.924806: val_loss -0.8958 +2025-10-31 05:11:15.926600: Pseudo dice [np.float32(0.9863), np.float32(0.9917), np.float32(0.9943), np.float32(0.7914)] +2025-10-31 05:11:15.928452: Epoch time: 21.99 s +2025-10-31 05:11:16.940863: +2025-10-31 05:11:16.942925: Epoch 334 +2025-10-31 05:11:16.945178: Current learning rate: 0.00694 +2025-10-31 05:11:38.630546: train_loss -0.9876 +2025-10-31 05:11:38.635123: val_loss -0.901 +2025-10-31 05:11:38.637310: Pseudo dice [np.float32(0.9855), np.float32(0.9925), np.float32(0.9946), np.float32(0.8026)] +2025-10-31 05:11:38.639595: Epoch time: 21.69 s +2025-10-31 05:11:38.641767: Yayy! New best EMA pseudo Dice: 0.9416999816894531 +2025-10-31 05:11:41.182984: +2025-10-31 05:11:41.187176: Epoch 335 +2025-10-31 05:11:41.190103: Current learning rate: 0.00693 +2025-10-31 05:12:03.686186: train_loss -0.9861 +2025-10-31 05:12:03.689058: val_loss -0.8962 +2025-10-31 05:12:03.691003: Pseudo dice [np.float32(0.9861), np.float32(0.9932), np.float32(0.9945), np.float32(0.7881)] +2025-10-31 05:12:03.692825: Epoch time: 22.5 s +2025-10-31 05:12:04.979042: +2025-10-31 05:12:04.981618: Epoch 336 +2025-10-31 05:12:04.983290: Current learning rate: 0.00692 +2025-10-31 05:12:27.193169: train_loss -0.9863 +2025-10-31 05:12:27.196487: val_loss -0.9042 +2025-10-31 05:12:27.198483: Pseudo dice [np.float32(0.9866), np.float32(0.9925), np.float32(0.9947), np.float32(0.81)] +2025-10-31 05:12:27.200007: Epoch time: 22.22 s +2025-10-31 05:12:27.201699: Yayy! New best EMA pseudo Dice: 0.9419999718666077 +2025-10-31 05:12:29.792508: +2025-10-31 05:12:29.794281: Epoch 337 +2025-10-31 05:12:29.796195: Current learning rate: 0.00691 +2025-10-31 05:12:52.575020: train_loss -0.9871 +2025-10-31 05:12:52.582513: val_loss -0.8974 +2025-10-31 05:12:52.586623: Pseudo dice [np.float32(0.9854), np.float32(0.9917), np.float32(0.9947), np.float32(0.7948)] +2025-10-31 05:12:52.591975: Epoch time: 22.78 s +2025-10-31 05:12:53.619796: +2025-10-31 05:12:53.622194: Epoch 338 +2025-10-31 05:12:53.624520: Current learning rate: 0.0069 +2025-10-31 05:13:15.621150: train_loss -0.9867 +2025-10-31 05:13:15.625382: val_loss -0.8924 +2025-10-31 05:13:15.628106: Pseudo dice [np.float32(0.9855), np.float32(0.9903), np.float32(0.994), np.float32(0.7841)] +2025-10-31 05:13:15.629998: Epoch time: 22.0 s +2025-10-31 05:13:17.063037: +2025-10-31 05:13:17.069002: Epoch 339 +2025-10-31 05:13:17.073770: Current learning rate: 0.00689 +2025-10-31 05:13:39.126708: train_loss -0.9876 +2025-10-31 05:13:39.130302: val_loss -0.8907 +2025-10-31 05:13:39.131666: Pseudo dice [np.float32(0.9847), np.float32(0.9917), np.float32(0.994), np.float32(0.7804)] +2025-10-31 05:13:39.133348: Epoch time: 22.06 s +2025-10-31 05:13:40.241161: +2025-10-31 05:13:40.246583: Epoch 340 +2025-10-31 05:13:40.251638: Current learning rate: 0.00688 +2025-10-31 05:14:01.717071: train_loss -0.9868 +2025-10-31 05:14:01.722992: val_loss -0.8869 +2025-10-31 05:14:01.724824: Pseudo dice [np.float32(0.9847), np.float32(0.9906), np.float32(0.9937), np.float32(0.7705)] +2025-10-31 05:14:01.726485: Epoch time: 21.48 s +2025-10-31 05:14:02.779130: +2025-10-31 05:14:02.781348: Epoch 341 +2025-10-31 05:14:02.783166: Current learning rate: 0.00687 +2025-10-31 05:14:24.838505: train_loss -0.9874 +2025-10-31 05:14:24.847331: val_loss -0.8908 +2025-10-31 05:14:24.854081: Pseudo dice [np.float32(0.9851), np.float32(0.9913), np.float32(0.994), np.float32(0.7821)] +2025-10-31 05:14:24.861389: Epoch time: 22.06 s +2025-10-31 05:14:25.975781: +2025-10-31 05:14:25.979278: Epoch 342 +2025-10-31 05:14:25.981121: Current learning rate: 0.00686 +2025-10-31 05:14:48.642379: train_loss -0.9875 +2025-10-31 05:14:48.647202: val_loss -0.8953 +2025-10-31 05:14:48.649450: Pseudo dice [np.float32(0.9855), np.float32(0.9911), np.float32(0.9937), np.float32(0.7999)] +2025-10-31 05:14:48.651108: Epoch time: 22.67 s +2025-10-31 05:14:49.832877: +2025-10-31 05:14:49.835324: Epoch 343 +2025-10-31 05:14:49.836924: Current learning rate: 0.00685 +2025-10-31 05:15:11.888645: train_loss -0.9877 +2025-10-31 05:15:11.892794: val_loss -0.8985 +2025-10-31 05:15:11.894857: Pseudo dice [np.float32(0.9853), np.float32(0.9916), np.float32(0.9945), np.float32(0.8004)] +2025-10-31 05:15:11.896959: Epoch time: 22.06 s +2025-10-31 05:15:13.254358: +2025-10-31 05:15:13.256746: Epoch 344 +2025-10-31 05:15:13.259041: Current learning rate: 0.00684 +2025-10-31 05:15:35.170002: train_loss -0.987 +2025-10-31 05:15:35.173430: val_loss -0.8941 +2025-10-31 05:15:35.175206: Pseudo dice [np.float32(0.9852), np.float32(0.9915), np.float32(0.9941), np.float32(0.792)] +2025-10-31 05:15:35.176954: Epoch time: 21.92 s +2025-10-31 05:15:36.344088: +2025-10-31 05:15:36.346017: Epoch 345 +2025-10-31 05:15:36.348438: Current learning rate: 0.00683 +2025-10-31 05:15:57.669182: train_loss -0.987 +2025-10-31 05:15:57.738663: val_loss -0.8955 +2025-10-31 05:15:57.772263: Pseudo dice [np.float32(0.9859), np.float32(0.9923), np.float32(0.9947), np.float32(0.7926)] +2025-10-31 05:15:57.794527: Epoch time: 21.33 s +2025-10-31 05:15:58.995343: +2025-10-31 05:15:59.004859: Epoch 346 +2025-10-31 05:15:59.020922: Current learning rate: 0.00682 +2025-10-31 05:16:20.230725: train_loss -0.9868 +2025-10-31 05:16:20.235331: val_loss -0.8993 +2025-10-31 05:16:20.237121: Pseudo dice [np.float32(0.9856), np.float32(0.9922), np.float32(0.9947), np.float32(0.8002)] +2025-10-31 05:16:20.238927: Epoch time: 21.24 s +2025-10-31 05:16:21.280093: +2025-10-31 05:16:21.282531: Epoch 347 +2025-10-31 05:16:21.284350: Current learning rate: 0.00681 +2025-10-31 05:16:44.007014: train_loss -0.9867 +2025-10-31 05:16:44.010389: val_loss -0.9054 +2025-10-31 05:16:44.012611: Pseudo dice [np.float32(0.9856), np.float32(0.9922), np.float32(0.9948), np.float32(0.815)] +2025-10-31 05:16:44.014606: Epoch time: 22.73 s +2025-10-31 05:16:45.048603: +2025-10-31 05:16:45.051150: Epoch 348 +2025-10-31 05:16:45.053184: Current learning rate: 0.0068 +2025-10-31 05:17:06.973719: train_loss -0.9852 +2025-10-31 05:17:06.978149: val_loss -0.9026 +2025-10-31 05:17:06.980154: Pseudo dice [np.float32(0.9849), np.float32(0.9923), np.float32(0.995), np.float32(0.8062)] +2025-10-31 05:17:06.982195: Epoch time: 21.93 s +2025-10-31 05:17:08.198900: +2025-10-31 05:17:08.200773: Epoch 349 +2025-10-31 05:17:08.202401: Current learning rate: 0.0068 +2025-10-31 05:17:30.556025: train_loss -0.9859 +2025-10-31 05:17:30.559373: val_loss -0.9035 +2025-10-31 05:17:30.560955: Pseudo dice [np.float32(0.9848), np.float32(0.9916), np.float32(0.995), np.float32(0.8089)] +2025-10-31 05:17:30.562812: Epoch time: 22.36 s +2025-10-31 05:17:32.130270: Yayy! New best EMA pseudo Dice: 0.942300021648407 +2025-10-31 05:17:34.681442: +2025-10-31 05:17:34.683428: Epoch 350 +2025-10-31 05:17:34.685367: Current learning rate: 0.00679 +2025-10-31 05:17:57.147388: train_loss -0.9868 +2025-10-31 05:17:57.151402: val_loss -0.8936 +2025-10-31 05:17:57.153899: Pseudo dice [np.float32(0.9829), np.float32(0.9907), np.float32(0.9946), np.float32(0.7944)] +2025-10-31 05:17:57.156114: Epoch time: 22.47 s +2025-10-31 05:17:58.613558: +2025-10-31 05:17:58.615962: Epoch 351 +2025-10-31 05:17:58.621016: Current learning rate: 0.00678 +2025-10-31 05:18:20.033486: train_loss -0.9871 +2025-10-31 05:18:20.039580: val_loss -0.8959 +2025-10-31 05:18:20.042504: Pseudo dice [np.float32(0.9854), np.float32(0.9918), np.float32(0.9938), np.float32(0.7904)] +2025-10-31 05:18:20.044457: Epoch time: 21.42 s +2025-10-31 05:18:21.133890: +2025-10-31 05:18:21.135911: Epoch 352 +2025-10-31 05:18:21.139669: Current learning rate: 0.00677 +2025-10-31 05:18:42.507552: train_loss -0.9875 +2025-10-31 05:18:42.510184: val_loss -0.9033 +2025-10-31 05:18:42.512472: Pseudo dice [np.float32(0.9856), np.float32(0.9916), np.float32(0.9944), np.float32(0.8137)] +2025-10-31 05:18:42.514535: Epoch time: 21.38 s +2025-10-31 05:18:42.516593: Yayy! New best EMA pseudo Dice: 0.9423999786376953 +2025-10-31 05:18:45.111622: +2025-10-31 05:18:45.114476: Epoch 353 +2025-10-31 05:18:45.117023: Current learning rate: 0.00676 +2025-10-31 05:19:07.350432: train_loss -0.9882 +2025-10-31 05:19:07.353461: val_loss -0.9021 +2025-10-31 05:19:07.355977: Pseudo dice [np.float32(0.9855), np.float32(0.9917), np.float32(0.9947), np.float32(0.8113)] +2025-10-31 05:19:07.357803: Epoch time: 22.24 s +2025-10-31 05:19:07.360186: Yayy! New best EMA pseudo Dice: 0.9427000284194946 +2025-10-31 05:19:10.109439: +2025-10-31 05:19:10.114865: Epoch 354 +2025-10-31 05:19:10.117416: Current learning rate: 0.00675 +2025-10-31 05:19:32.474244: train_loss -0.9871 +2025-10-31 05:19:32.478081: val_loss -0.896 +2025-10-31 05:19:32.479949: Pseudo dice [np.float32(0.9844), np.float32(0.9912), np.float32(0.9944), np.float32(0.801)] +2025-10-31 05:19:32.482273: Epoch time: 22.37 s +2025-10-31 05:19:32.484707: Yayy! New best EMA pseudo Dice: 0.9427000284194946 +2025-10-31 05:19:34.978336: +2025-10-31 05:19:34.980814: Epoch 355 +2025-10-31 05:19:34.984756: Current learning rate: 0.00674 +2025-10-31 05:19:57.289269: train_loss -0.988 +2025-10-31 05:19:57.293195: val_loss -0.895 +2025-10-31 05:19:57.294888: Pseudo dice [np.float32(0.986), np.float32(0.991), np.float32(0.9941), np.float32(0.7969)] +2025-10-31 05:19:57.296711: Epoch time: 22.31 s +2025-10-31 05:19:58.403150: +2025-10-31 05:19:58.406733: Epoch 356 +2025-10-31 05:19:58.412911: Current learning rate: 0.00673 +2025-10-31 05:20:20.562417: train_loss -0.9871 +2025-10-31 05:20:20.567387: val_loss -0.8897 +2025-10-31 05:20:20.569261: Pseudo dice [np.float32(0.9834), np.float32(0.9906), np.float32(0.994), np.float32(0.7844)] +2025-10-31 05:20:20.571234: Epoch time: 22.16 s +2025-10-31 05:20:21.802511: +2025-10-31 05:20:21.806808: Epoch 357 +2025-10-31 05:20:21.810430: Current learning rate: 0.00672 +2025-10-31 05:20:42.850980: train_loss -0.988 +2025-10-31 05:20:42.858513: val_loss -0.8892 +2025-10-31 05:20:42.860252: Pseudo dice [np.float32(0.9848), np.float32(0.9914), np.float32(0.994), np.float32(0.7769)] +2025-10-31 05:20:42.862342: Epoch time: 21.05 s +2025-10-31 05:20:44.187815: +2025-10-31 05:20:44.189531: Epoch 358 +2025-10-31 05:20:44.195840: Current learning rate: 0.00671 +2025-10-31 05:21:05.275090: train_loss -0.9855 +2025-10-31 05:21:05.278502: val_loss -0.8986 +2025-10-31 05:21:05.280618: Pseudo dice [np.float32(0.9851), np.float32(0.9913), np.float32(0.9945), np.float32(0.8058)] +2025-10-31 05:21:05.282540: Epoch time: 21.09 s +2025-10-31 05:21:06.298225: +2025-10-31 05:21:06.300099: Epoch 359 +2025-10-31 05:21:06.301808: Current learning rate: 0.0067 +2025-10-31 05:21:28.222333: train_loss -0.9864 +2025-10-31 05:21:28.228088: val_loss -0.8937 +2025-10-31 05:21:28.231211: Pseudo dice [np.float32(0.9851), np.float32(0.9908), np.float32(0.9941), np.float32(0.7911)] +2025-10-31 05:21:28.233274: Epoch time: 21.93 s +2025-10-31 05:21:29.361369: +2025-10-31 05:21:29.364545: Epoch 360 +2025-10-31 05:21:29.366574: Current learning rate: 0.00669 +2025-10-31 05:21:51.417703: train_loss -0.9865 +2025-10-31 05:21:51.421520: val_loss -0.9003 +2025-10-31 05:21:51.423250: Pseudo dice [np.float32(0.987), np.float32(0.9921), np.float32(0.9943), np.float32(0.7972)] +2025-10-31 05:21:51.425597: Epoch time: 22.06 s +2025-10-31 05:21:52.634637: +2025-10-31 05:21:52.636622: Epoch 361 +2025-10-31 05:21:52.640864: Current learning rate: 0.00668 +2025-10-31 05:22:14.817992: train_loss -0.9871 +2025-10-31 05:22:14.822443: val_loss -0.899 +2025-10-31 05:22:14.824409: Pseudo dice [np.float32(0.9865), np.float32(0.992), np.float32(0.9945), np.float32(0.7977)] +2025-10-31 05:22:14.826514: Epoch time: 22.18 s +2025-10-31 05:22:16.049029: +2025-10-31 05:22:16.051952: Epoch 362 +2025-10-31 05:22:16.053832: Current learning rate: 0.00667 +2025-10-31 05:22:37.659614: train_loss -0.9835 +2025-10-31 05:22:37.662503: val_loss -0.8924 +2025-10-31 05:22:37.664036: Pseudo dice [np.float32(0.9861), np.float32(0.9906), np.float32(0.9939), np.float32(0.7792)] +2025-10-31 05:22:37.665660: Epoch time: 21.61 s +2025-10-31 05:22:39.467246: +2025-10-31 05:22:39.469987: Epoch 363 +2025-10-31 05:22:39.471950: Current learning rate: 0.00666 +2025-10-31 05:23:00.815219: train_loss -0.9835 +2025-10-31 05:23:00.820025: val_loss -0.8941 +2025-10-31 05:23:00.822443: Pseudo dice [np.float32(0.9851), np.float32(0.992), np.float32(0.9943), np.float32(0.7785)] +2025-10-31 05:23:00.824393: Epoch time: 21.35 s +2025-10-31 05:23:01.946633: +2025-10-31 05:23:01.952890: Epoch 364 +2025-10-31 05:23:01.960589: Current learning rate: 0.00665 +2025-10-31 05:23:21.858777: train_loss -0.9858 +2025-10-31 05:23:21.863759: val_loss -0.898 +2025-10-31 05:23:21.865612: Pseudo dice [np.float32(0.9843), np.float32(0.9922), np.float32(0.9944), np.float32(0.7987)] +2025-10-31 05:23:21.868240: Epoch time: 19.91 s +2025-10-31 05:23:22.940604: +2025-10-31 05:23:22.949886: Epoch 365 +2025-10-31 05:23:22.958528: Current learning rate: 0.00665 +2025-10-31 05:23:44.351770: train_loss -0.9865 +2025-10-31 05:23:44.355376: val_loss -0.8912 +2025-10-31 05:23:44.358583: Pseudo dice [np.float32(0.9852), np.float32(0.9914), np.float32(0.994), np.float32(0.7957)] +2025-10-31 05:23:44.361491: Epoch time: 21.41 s +2025-10-31 05:23:45.447706: +2025-10-31 05:23:45.449816: Epoch 366 +2025-10-31 05:23:45.452755: Current learning rate: 0.00664 +2025-10-31 05:24:07.619574: train_loss -0.9873 +2025-10-31 05:24:07.624627: val_loss -0.8891 +2025-10-31 05:24:07.626637: Pseudo dice [np.float32(0.9846), np.float32(0.9912), np.float32(0.9944), np.float32(0.7802)] +2025-10-31 05:24:07.631999: Epoch time: 22.17 s +2025-10-31 05:24:08.836022: +2025-10-31 05:24:08.839305: Epoch 367 +2025-10-31 05:24:08.840976: Current learning rate: 0.00663 +2025-10-31 05:24:31.578417: train_loss -0.9867 +2025-10-31 05:24:31.582659: val_loss -0.893 +2025-10-31 05:24:31.584831: Pseudo dice [np.float32(0.9863), np.float32(0.9918), np.float32(0.9945), np.float32(0.7797)] +2025-10-31 05:24:31.588787: Epoch time: 22.74 s +2025-10-31 05:24:32.643177: +2025-10-31 05:24:32.649228: Epoch 368 +2025-10-31 05:24:32.651161: Current learning rate: 0.00662 +2025-10-31 05:24:54.832830: train_loss -0.987 +2025-10-31 05:24:54.835229: val_loss -0.8974 +2025-10-31 05:24:54.838656: Pseudo dice [np.float32(0.9836), np.float32(0.9909), np.float32(0.9944), np.float32(0.7961)] +2025-10-31 05:24:54.841907: Epoch time: 22.19 s +2025-10-31 05:24:56.200963: +2025-10-31 05:24:56.203496: Epoch 369 +2025-10-31 05:24:56.205890: Current learning rate: 0.00661 +2025-10-31 05:25:18.132522: train_loss -0.9877 +2025-10-31 05:25:18.141012: val_loss -0.894 +2025-10-31 05:25:18.142433: Pseudo dice [np.float32(0.9852), np.float32(0.9909), np.float32(0.9943), np.float32(0.791)] +2025-10-31 05:25:18.144004: Epoch time: 21.93 s +2025-10-31 05:25:19.394055: +2025-10-31 05:25:19.396060: Epoch 370 +2025-10-31 05:25:19.397871: Current learning rate: 0.0066 +2025-10-31 05:25:38.318341: train_loss -0.9874 +2025-10-31 05:25:38.326233: val_loss -0.8932 +2025-10-31 05:25:38.330122: Pseudo dice [np.float32(0.9868), np.float32(0.9917), np.float32(0.994), np.float32(0.7882)] +2025-10-31 05:25:38.334791: Epoch time: 18.93 s +2025-10-31 05:25:39.562950: +2025-10-31 05:25:39.565355: Epoch 371 +2025-10-31 05:25:39.567328: Current learning rate: 0.00659 +2025-10-31 05:26:01.719319: train_loss -0.9883 +2025-10-31 05:26:01.724240: val_loss -0.8913 +2025-10-31 05:26:01.726829: Pseudo dice [np.float32(0.9853), np.float32(0.9917), np.float32(0.994), np.float32(0.7827)] +2025-10-31 05:26:01.728964: Epoch time: 22.16 s +2025-10-31 05:26:02.994659: +2025-10-31 05:26:02.998459: Epoch 372 +2025-10-31 05:26:03.001115: Current learning rate: 0.00658 +2025-10-31 05:26:24.939155: train_loss -0.9878 +2025-10-31 05:26:24.944775: val_loss -0.8947 +2025-10-31 05:26:24.951477: Pseudo dice [np.float32(0.9854), np.float32(0.9916), np.float32(0.9942), np.float32(0.7986)] +2025-10-31 05:26:24.955223: Epoch time: 21.95 s +2025-10-31 05:26:26.021168: +2025-10-31 05:26:26.024883: Epoch 373 +2025-10-31 05:26:26.030953: Current learning rate: 0.00657 +2025-10-31 05:26:48.019743: train_loss -0.9875 +2025-10-31 05:26:48.025143: val_loss -0.8975 +2025-10-31 05:26:48.028846: Pseudo dice [np.float32(0.9831), np.float32(0.9911), np.float32(0.9945), np.float32(0.8012)] +2025-10-31 05:26:48.032084: Epoch time: 22.0 s +2025-10-31 05:26:49.320916: +2025-10-31 05:26:49.323026: Epoch 374 +2025-10-31 05:26:49.325443: Current learning rate: 0.00656 +2025-10-31 05:27:11.023864: train_loss -0.9879 +2025-10-31 05:27:11.027699: val_loss -0.8976 +2025-10-31 05:27:11.030966: Pseudo dice [np.float32(0.9851), np.float32(0.9913), np.float32(0.9947), np.float32(0.7971)] +2025-10-31 05:27:11.034036: Epoch time: 21.71 s +2025-10-31 05:27:12.645910: +2025-10-31 05:27:12.648265: Epoch 375 +2025-10-31 05:27:12.650539: Current learning rate: 0.00655 +2025-10-31 05:27:35.175629: train_loss -0.9876 +2025-10-31 05:27:35.178643: val_loss -0.899 +2025-10-31 05:27:35.180293: Pseudo dice [np.float32(0.9847), np.float32(0.9913), np.float32(0.9947), np.float32(0.8031)] +2025-10-31 05:27:35.182096: Epoch time: 22.53 s +2025-10-31 05:27:36.410174: +2025-10-31 05:27:36.412801: Epoch 376 +2025-10-31 05:27:36.415532: Current learning rate: 0.00654 +2025-10-31 05:27:57.670149: train_loss -0.9883 +2025-10-31 05:27:57.673663: val_loss -0.89 +2025-10-31 05:27:57.677693: Pseudo dice [np.float32(0.985), np.float32(0.991), np.float32(0.9938), np.float32(0.7838)] +2025-10-31 05:27:57.680362: Epoch time: 21.26 s +2025-10-31 05:27:58.922906: +2025-10-31 05:27:58.926680: Epoch 377 +2025-10-31 05:27:58.931014: Current learning rate: 0.00653 +2025-10-31 05:28:19.939523: train_loss -0.988 +2025-10-31 05:28:19.945776: val_loss -0.9064 +2025-10-31 05:28:19.947983: Pseudo dice [np.float32(0.9868), np.float32(0.9926), np.float32(0.9949), np.float32(0.8139)] +2025-10-31 05:28:19.950418: Epoch time: 21.02 s +2025-10-31 05:28:20.901528: +2025-10-31 05:28:20.906357: Epoch 378 +2025-10-31 05:28:20.908577: Current learning rate: 0.00652 +2025-10-31 05:28:43.061051: train_loss -0.9881 +2025-10-31 05:28:43.066638: val_loss -0.8864 +2025-10-31 05:28:43.068345: Pseudo dice [np.float32(0.985), np.float32(0.991), np.float32(0.9939), np.float32(0.7714)] +2025-10-31 05:28:43.069988: Epoch time: 22.16 s +2025-10-31 05:28:44.392925: +2025-10-31 05:28:44.395220: Epoch 379 +2025-10-31 05:28:44.397417: Current learning rate: 0.00651 +2025-10-31 05:29:06.702738: train_loss -0.9875 +2025-10-31 05:29:06.706944: val_loss -0.893 +2025-10-31 05:29:06.710662: Pseudo dice [np.float32(0.9846), np.float32(0.9917), np.float32(0.9945), np.float32(0.7891)] +2025-10-31 05:29:06.713697: Epoch time: 22.31 s +2025-10-31 05:29:07.755698: +2025-10-31 05:29:07.760969: Epoch 380 +2025-10-31 05:29:07.766911: Current learning rate: 0.0065 +2025-10-31 05:29:29.983440: train_loss -0.9878 +2025-10-31 05:29:29.988387: val_loss -0.8835 +2025-10-31 05:29:29.990691: Pseudo dice [np.float32(0.9847), np.float32(0.9911), np.float32(0.994), np.float32(0.7727)] +2025-10-31 05:29:29.993300: Epoch time: 22.23 s +2025-10-31 05:29:31.188822: +2025-10-31 05:29:31.191114: Epoch 381 +2025-10-31 05:29:31.193060: Current learning rate: 0.00649 +2025-10-31 05:29:53.231337: train_loss -0.9876 +2025-10-31 05:29:53.240756: val_loss -0.906 +2025-10-31 05:29:53.243329: Pseudo dice [np.float32(0.9875), np.float32(0.9925), np.float32(0.9944), np.float32(0.8152)] +2025-10-31 05:29:53.246312: Epoch time: 22.04 s +2025-10-31 05:29:54.298353: +2025-10-31 05:29:54.300995: Epoch 382 +2025-10-31 05:29:54.303082: Current learning rate: 0.00648 +2025-10-31 05:30:16.136701: train_loss -0.9884 +2025-10-31 05:30:16.140676: val_loss -0.8959 +2025-10-31 05:30:16.142848: Pseudo dice [np.float32(0.9848), np.float32(0.991), np.float32(0.9942), np.float32(0.8045)] +2025-10-31 05:30:16.144745: Epoch time: 21.84 s +2025-10-31 05:30:17.353972: +2025-10-31 05:30:17.357055: Epoch 383 +2025-10-31 05:30:17.359444: Current learning rate: 0.00648 +2025-10-31 05:30:37.449636: train_loss -0.9878 +2025-10-31 05:30:37.452941: val_loss -0.9007 +2025-10-31 05:30:37.456165: Pseudo dice [np.float32(0.9869), np.float32(0.9927), np.float32(0.9949), np.float32(0.8046)] +2025-10-31 05:30:37.458132: Epoch time: 20.1 s +2025-10-31 05:30:38.662148: +2025-10-31 05:30:38.663961: Epoch 384 +2025-10-31 05:30:38.665976: Current learning rate: 0.00647 +2025-10-31 05:31:00.879893: train_loss -0.9879 +2025-10-31 05:31:00.884282: val_loss -0.8999 +2025-10-31 05:31:00.886723: Pseudo dice [np.float32(0.986), np.float32(0.9921), np.float32(0.9946), np.float32(0.8007)] +2025-10-31 05:31:00.889615: Epoch time: 22.22 s +2025-10-31 05:31:02.212155: +2025-10-31 05:31:02.214088: Epoch 385 +2025-10-31 05:31:02.215863: Current learning rate: 0.00646 +2025-10-31 05:31:25.009841: train_loss -0.9874 +2025-10-31 05:31:25.013810: val_loss -0.8951 +2025-10-31 05:31:25.016926: Pseudo dice [np.float32(0.9862), np.float32(0.9911), np.float32(0.9941), np.float32(0.7876)] +2025-10-31 05:31:25.019181: Epoch time: 22.8 s +2025-10-31 05:31:26.158485: +2025-10-31 05:31:26.160637: Epoch 386 +2025-10-31 05:31:26.162184: Current learning rate: 0.00645 +2025-10-31 05:31:48.693198: train_loss -0.9876 +2025-10-31 05:31:48.697062: val_loss -0.8974 +2025-10-31 05:31:48.699062: Pseudo dice [np.float32(0.9862), np.float32(0.9919), np.float32(0.9946), np.float32(0.7993)] +2025-10-31 05:31:48.701014: Epoch time: 22.54 s +2025-10-31 05:31:50.053243: +2025-10-31 05:31:50.055139: Epoch 387 +2025-10-31 05:31:50.057117: Current learning rate: 0.00644 +2025-10-31 05:32:11.904908: train_loss -0.9872 +2025-10-31 05:32:11.912708: val_loss -0.8949 +2025-10-31 05:32:11.915065: Pseudo dice [np.float32(0.9849), np.float32(0.9906), np.float32(0.9942), np.float32(0.7966)] +2025-10-31 05:32:11.916764: Epoch time: 21.85 s +2025-10-31 05:32:13.003551: +2025-10-31 05:32:13.006023: Epoch 388 +2025-10-31 05:32:13.008856: Current learning rate: 0.00643 +2025-10-31 05:32:34.918308: train_loss -0.9887 +2025-10-31 05:32:34.921698: val_loss -0.8991 +2025-10-31 05:32:34.923465: Pseudo dice [np.float32(0.9861), np.float32(0.9919), np.float32(0.9945), np.float32(0.7979)] +2025-10-31 05:32:34.925333: Epoch time: 21.92 s +2025-10-31 05:32:35.986178: +2025-10-31 05:32:35.988024: Epoch 389 +2025-10-31 05:32:35.989788: Current learning rate: 0.00642 +2025-10-31 05:32:56.258875: train_loss -0.9878 +2025-10-31 05:32:56.260935: val_loss -0.8869 +2025-10-31 05:32:56.263182: Pseudo dice [np.float32(0.9854), np.float32(0.992), np.float32(0.9946), np.float32(0.7676)] +2025-10-31 05:32:56.266130: Epoch time: 20.27 s +2025-10-31 05:32:57.495538: +2025-10-31 05:32:57.497287: Epoch 390 +2025-10-31 05:32:57.499452: Current learning rate: 0.00641 +2025-10-31 05:33:18.487652: train_loss -0.9876 +2025-10-31 05:33:18.490848: val_loss -0.8949 +2025-10-31 05:33:18.493223: Pseudo dice [np.float32(0.9855), np.float32(0.9918), np.float32(0.9943), np.float32(0.7885)] +2025-10-31 05:33:18.495354: Epoch time: 20.99 s +2025-10-31 05:33:19.667530: +2025-10-31 05:33:19.669821: Epoch 391 +2025-10-31 05:33:19.671531: Current learning rate: 0.0064 +2025-10-31 05:33:41.758923: train_loss -0.9883 +2025-10-31 05:33:41.761461: val_loss -0.8849 +2025-10-31 05:33:41.763119: Pseudo dice [np.float32(0.9838), np.float32(0.9906), np.float32(0.9938), np.float32(0.7826)] +2025-10-31 05:33:41.764955: Epoch time: 22.09 s +2025-10-31 05:33:42.850738: +2025-10-31 05:33:42.856885: Epoch 392 +2025-10-31 05:33:42.860180: Current learning rate: 0.00639 +2025-10-31 05:34:05.433893: train_loss -0.9884 +2025-10-31 05:34:05.443011: val_loss -0.8951 +2025-10-31 05:34:05.446009: Pseudo dice [np.float32(0.9845), np.float32(0.9911), np.float32(0.9942), np.float32(0.8072)] +2025-10-31 05:34:05.448168: Epoch time: 22.58 s +2025-10-31 05:34:06.683740: +2025-10-31 05:34:06.686306: Epoch 393 +2025-10-31 05:34:06.689035: Current learning rate: 0.00638 +2025-10-31 05:34:29.022781: train_loss -0.988 +2025-10-31 05:34:29.026967: val_loss -0.8903 +2025-10-31 05:34:29.028995: Pseudo dice [np.float32(0.9845), np.float32(0.9931), np.float32(0.9944), np.float32(0.7825)] +2025-10-31 05:34:29.031089: Epoch time: 22.34 s +2025-10-31 05:34:30.235060: +2025-10-31 05:34:30.237571: Epoch 394 +2025-10-31 05:34:30.240144: Current learning rate: 0.00637 +2025-10-31 05:34:52.799792: train_loss -0.9883 +2025-10-31 05:34:52.810112: val_loss -0.8916 +2025-10-31 05:34:52.812610: Pseudo dice [np.float32(0.986), np.float32(0.9916), np.float32(0.994), np.float32(0.7854)] +2025-10-31 05:34:52.814682: Epoch time: 22.57 s +2025-10-31 05:34:54.104155: +2025-10-31 05:34:54.105875: Epoch 395 +2025-10-31 05:34:54.107324: Current learning rate: 0.00636 +2025-10-31 05:35:15.132236: train_loss -0.9845 +2025-10-31 05:35:15.136356: val_loss -0.8851 +2025-10-31 05:35:15.138737: Pseudo dice [np.float32(0.9847), np.float32(0.991), np.float32(0.9928), np.float32(0.7763)] +2025-10-31 05:35:15.141068: Epoch time: 21.03 s +2025-10-31 05:35:16.311460: +2025-10-31 05:35:16.313650: Epoch 396 +2025-10-31 05:35:16.315343: Current learning rate: 0.00635 +2025-10-31 05:35:37.975986: train_loss -0.9847 +2025-10-31 05:35:37.982317: val_loss -0.8965 +2025-10-31 05:35:37.984531: Pseudo dice [np.float32(0.9856), np.float32(0.9905), np.float32(0.9934), np.float32(0.7942)] +2025-10-31 05:35:37.989850: Epoch time: 21.67 s +2025-10-31 05:35:39.075539: +2025-10-31 05:35:39.078825: Epoch 397 +2025-10-31 05:35:39.081255: Current learning rate: 0.00634 +2025-10-31 05:36:00.824598: train_loss -0.9867 +2025-10-31 05:36:00.827043: val_loss -0.8924 +2025-10-31 05:36:00.828809: Pseudo dice [np.float32(0.9852), np.float32(0.9905), np.float32(0.9936), np.float32(0.7922)] +2025-10-31 05:36:00.830636: Epoch time: 21.75 s +2025-10-31 05:36:02.505741: +2025-10-31 05:36:02.510844: Epoch 398 +2025-10-31 05:36:02.518660: Current learning rate: 0.00633 +2025-10-31 05:36:25.031907: train_loss -0.987 +2025-10-31 05:36:25.052705: val_loss -0.8947 +2025-10-31 05:36:25.068033: Pseudo dice [np.float32(0.9816), np.float32(0.9907), np.float32(0.9948), np.float32(0.8066)] +2025-10-31 05:36:25.074001: Epoch time: 22.53 s +2025-10-31 05:36:26.268513: +2025-10-31 05:36:26.275379: Epoch 399 +2025-10-31 05:36:26.282309: Current learning rate: 0.00632 +2025-10-31 05:36:48.594836: train_loss -0.9872 +2025-10-31 05:36:48.600307: val_loss -0.899 +2025-10-31 05:36:48.602064: Pseudo dice [np.float32(0.9857), np.float32(0.9915), np.float32(0.9946), np.float32(0.7986)] +2025-10-31 05:36:48.603971: Epoch time: 22.33 s +2025-10-31 05:36:51.282049: +2025-10-31 05:36:51.284841: Epoch 400 +2025-10-31 05:36:51.286593: Current learning rate: 0.00631 +2025-10-31 05:37:13.374632: train_loss -0.988 +2025-10-31 05:37:13.378356: val_loss -0.911 +2025-10-31 05:37:13.380903: Pseudo dice [np.float32(0.9865), np.float32(0.9922), np.float32(0.9954), np.float32(0.8219)] +2025-10-31 05:37:13.383320: Epoch time: 22.09 s +2025-10-31 05:37:14.687934: +2025-10-31 05:37:14.695518: Epoch 401 +2025-10-31 05:37:14.702245: Current learning rate: 0.0063 +2025-10-31 05:37:35.138263: train_loss -0.9883 +2025-10-31 05:37:35.141528: val_loss -0.899 +2025-10-31 05:37:35.143243: Pseudo dice [np.float32(0.9841), np.float32(0.9908), np.float32(0.9945), np.float32(0.8122)] +2025-10-31 05:37:35.144832: Epoch time: 20.45 s +2025-10-31 05:37:36.292138: +2025-10-31 05:37:36.295439: Epoch 402 +2025-10-31 05:37:36.298757: Current learning rate: 0.0063 +2025-10-31 05:37:57.846511: train_loss -0.9886 +2025-10-31 05:37:57.853622: val_loss -0.9031 +2025-10-31 05:37:57.856668: Pseudo dice [np.float32(0.9839), np.float32(0.9915), np.float32(0.9952), np.float32(0.819)] +2025-10-31 05:37:57.860225: Epoch time: 21.56 s +2025-10-31 05:37:59.093779: +2025-10-31 05:37:59.095750: Epoch 403 +2025-10-31 05:37:59.097692: Current learning rate: 0.00629 +2025-10-31 05:38:21.523169: train_loss -0.9882 +2025-10-31 05:38:21.525850: val_loss -0.8961 +2025-10-31 05:38:21.527652: Pseudo dice [np.float32(0.9851), np.float32(0.9915), np.float32(0.9942), np.float32(0.7983)] +2025-10-31 05:38:21.529661: Epoch time: 22.43 s +2025-10-31 05:38:22.729040: +2025-10-31 05:38:22.734033: Epoch 404 +2025-10-31 05:38:22.737108: Current learning rate: 0.00628 +2025-10-31 05:38:44.373198: train_loss -0.9875 +2025-10-31 05:38:44.376201: val_loss -0.9141 +2025-10-31 05:38:44.378843: Pseudo dice [np.float32(0.9857), np.float32(0.9921), np.float32(0.9958), np.float32(0.8319)] +2025-10-31 05:38:44.381934: Epoch time: 21.65 s +2025-10-31 05:38:44.384174: Yayy! New best EMA pseudo Dice: 0.9434000253677368 +2025-10-31 05:38:47.163445: +2025-10-31 05:38:47.165486: Epoch 405 +2025-10-31 05:38:47.167172: Current learning rate: 0.00627 +2025-10-31 05:39:09.449857: train_loss -0.9875 +2025-10-31 05:39:09.454225: val_loss -0.8945 +2025-10-31 05:39:09.457905: Pseudo dice [np.float32(0.9841), np.float32(0.9908), np.float32(0.9943), np.float32(0.7997)] +2025-10-31 05:39:09.463036: Epoch time: 22.29 s +2025-10-31 05:39:10.681394: +2025-10-31 05:39:10.683632: Epoch 406 +2025-10-31 05:39:10.685467: Current learning rate: 0.00626 +2025-10-31 05:39:33.516847: train_loss -0.9858 +2025-10-31 05:39:33.520931: val_loss -0.8938 +2025-10-31 05:39:33.522732: Pseudo dice [np.float32(0.986), np.float32(0.9921), np.float32(0.9945), np.float32(0.7764)] +2025-10-31 05:39:33.524834: Epoch time: 22.84 s +2025-10-31 05:39:34.781821: +2025-10-31 05:39:34.786345: Epoch 407 +2025-10-31 05:39:34.791342: Current learning rate: 0.00625 +2025-10-31 05:39:56.538658: train_loss -0.9866 +2025-10-31 05:39:56.543235: val_loss -0.898 +2025-10-31 05:39:56.545291: Pseudo dice [np.float32(0.9847), np.float32(0.9907), np.float32(0.9949), np.float32(0.8015)] +2025-10-31 05:39:56.547323: Epoch time: 21.76 s +2025-10-31 05:39:57.865889: +2025-10-31 05:39:57.868616: Epoch 408 +2025-10-31 05:39:57.871391: Current learning rate: 0.00624 +2025-10-31 05:40:19.594765: train_loss -0.9877 +2025-10-31 05:40:19.598815: val_loss -0.9041 +2025-10-31 05:40:19.601161: Pseudo dice [np.float32(0.9865), np.float32(0.9913), np.float32(0.9944), np.float32(0.8039)] +2025-10-31 05:40:19.603344: Epoch time: 21.73 s +2025-10-31 05:40:21.141297: +2025-10-31 05:40:21.143417: Epoch 409 +2025-10-31 05:40:21.145602: Current learning rate: 0.00623 +2025-10-31 05:40:42.705870: train_loss -0.9874 +2025-10-31 05:40:42.708852: val_loss -0.9035 +2025-10-31 05:40:42.711140: Pseudo dice [np.float32(0.9858), np.float32(0.9914), np.float32(0.9946), np.float32(0.8136)] +2025-10-31 05:40:42.713624: Epoch time: 21.57 s +2025-10-31 05:40:43.765676: +2025-10-31 05:40:43.767984: Epoch 410 +2025-10-31 05:40:43.769751: Current learning rate: 0.00622 +2025-10-31 05:41:06.281388: train_loss -0.9874 +2025-10-31 05:41:06.288244: val_loss -0.8961 +2025-10-31 05:41:06.291622: Pseudo dice [np.float32(0.9854), np.float32(0.9915), np.float32(0.9945), np.float32(0.7893)] +2025-10-31 05:41:06.293187: Epoch time: 22.52 s +2025-10-31 05:41:07.301244: +2025-10-31 05:41:07.306090: Epoch 411 +2025-10-31 05:41:07.308053: Current learning rate: 0.00621 +2025-10-31 05:41:29.379317: train_loss -0.9871 +2025-10-31 05:41:29.387273: val_loss -0.9005 +2025-10-31 05:41:29.389509: Pseudo dice [np.float32(0.9866), np.float32(0.9921), np.float32(0.9943), np.float32(0.7969)] +2025-10-31 05:41:29.392322: Epoch time: 22.08 s +2025-10-31 05:41:30.640362: +2025-10-31 05:41:30.643292: Epoch 412 +2025-10-31 05:41:30.645273: Current learning rate: 0.0062 +2025-10-31 05:41:52.784529: train_loss -0.9879 +2025-10-31 05:41:52.790083: val_loss -0.8945 +2025-10-31 05:41:52.794139: Pseudo dice [np.float32(0.9854), np.float32(0.9909), np.float32(0.9939), np.float32(0.7995)] +2025-10-31 05:41:52.796744: Epoch time: 22.15 s +2025-10-31 05:41:54.011421: +2025-10-31 05:41:54.013488: Epoch 413 +2025-10-31 05:41:54.015441: Current learning rate: 0.00619 +2025-10-31 05:42:16.214564: train_loss -0.9881 +2025-10-31 05:42:16.218775: val_loss -0.904 +2025-10-31 05:42:16.220541: Pseudo dice [np.float32(0.9857), np.float32(0.9928), np.float32(0.9951), np.float32(0.8111)] +2025-10-31 05:42:16.222454: Epoch time: 22.21 s +2025-10-31 05:42:17.324722: +2025-10-31 05:42:17.327664: Epoch 414 +2025-10-31 05:42:17.329802: Current learning rate: 0.00618 +2025-10-31 05:42:40.514764: train_loss -0.9881 +2025-10-31 05:42:40.518662: val_loss -0.9002 +2025-10-31 05:42:40.520543: Pseudo dice [np.float32(0.9864), np.float32(0.9919), np.float32(0.9945), np.float32(0.808)] +2025-10-31 05:42:40.522465: Epoch time: 23.19 s +2025-10-31 05:42:41.560516: +2025-10-31 05:42:41.562917: Epoch 415 +2025-10-31 05:42:41.564737: Current learning rate: 0.00617 +2025-10-31 05:43:02.428849: train_loss -0.9896 +2025-10-31 05:43:02.431211: val_loss -0.8979 +2025-10-31 05:43:02.432980: Pseudo dice [np.float32(0.9867), np.float32(0.9923), np.float32(0.9944), np.float32(0.7883)] +2025-10-31 05:43:02.434554: Epoch time: 20.87 s +2025-10-31 05:43:03.799155: +2025-10-31 05:43:03.801489: Epoch 416 +2025-10-31 05:43:03.803265: Current learning rate: 0.00616 +2025-10-31 05:43:26.897330: train_loss -0.9881 +2025-10-31 05:43:26.900661: val_loss -0.9006 +2025-10-31 05:43:26.902236: Pseudo dice [np.float32(0.9872), np.float32(0.9924), np.float32(0.9946), np.float32(0.8023)] +2025-10-31 05:43:26.903594: Epoch time: 23.1 s +2025-10-31 05:43:27.916516: +2025-10-31 05:43:27.918398: Epoch 417 +2025-10-31 05:43:27.920134: Current learning rate: 0.00615 +2025-10-31 05:43:50.827363: train_loss -0.9882 +2025-10-31 05:43:50.833187: val_loss -0.8938 +2025-10-31 05:43:50.836076: Pseudo dice [np.float32(0.9862), np.float32(0.9912), np.float32(0.9942), np.float32(0.7937)] +2025-10-31 05:43:50.839308: Epoch time: 22.91 s +2025-10-31 05:43:51.868079: +2025-10-31 05:43:51.870090: Epoch 418 +2025-10-31 05:43:51.871571: Current learning rate: 0.00614 +2025-10-31 05:44:13.793194: train_loss -0.9887 +2025-10-31 05:44:13.797234: val_loss -0.8903 +2025-10-31 05:44:13.798946: Pseudo dice [np.float32(0.9837), np.float32(0.9913), np.float32(0.9946), np.float32(0.7917)] +2025-10-31 05:44:13.800579: Epoch time: 21.93 s +2025-10-31 05:44:14.862978: +2025-10-31 05:44:14.865602: Epoch 419 +2025-10-31 05:44:14.867471: Current learning rate: 0.00613 +2025-10-31 05:44:36.207766: train_loss -0.9887 +2025-10-31 05:44:36.212167: val_loss -0.8959 +2025-10-31 05:44:36.214750: Pseudo dice [np.float32(0.9852), np.float32(0.991), np.float32(0.994), np.float32(0.8048)] +2025-10-31 05:44:36.217036: Epoch time: 21.35 s +2025-10-31 05:44:37.284367: +2025-10-31 05:44:37.287139: Epoch 420 +2025-10-31 05:44:37.289573: Current learning rate: 0.00612 +2025-10-31 05:44:59.587054: train_loss -0.9861 +2025-10-31 05:44:59.591561: val_loss -0.8902 +2025-10-31 05:44:59.593297: Pseudo dice [np.float32(0.9845), np.float32(0.9909), np.float32(0.9937), np.float32(0.7746)] +2025-10-31 05:44:59.594902: Epoch time: 22.3 s +2025-10-31 05:45:00.820051: +2025-10-31 05:45:00.821967: Epoch 421 +2025-10-31 05:45:00.823780: Current learning rate: 0.00612 +2025-10-31 05:45:22.739753: train_loss -0.9856 +2025-10-31 05:45:22.743061: val_loss -0.9009 +2025-10-31 05:45:22.745315: Pseudo dice [np.float32(0.9862), np.float32(0.9928), np.float32(0.9939), np.float32(0.7956)] +2025-10-31 05:45:22.747453: Epoch time: 21.92 s +2025-10-31 05:45:24.479291: +2025-10-31 05:45:24.482555: Epoch 422 +2025-10-31 05:45:24.485343: Current learning rate: 0.00611 +2025-10-31 05:45:46.463228: train_loss -0.9863 +2025-10-31 05:45:46.467811: val_loss -0.8983 +2025-10-31 05:45:46.469517: Pseudo dice [np.float32(0.9865), np.float32(0.9926), np.float32(0.9948), np.float32(0.7873)] +2025-10-31 05:45:46.471220: Epoch time: 21.99 s +2025-10-31 05:45:47.647768: +2025-10-31 05:45:47.651811: Epoch 423 +2025-10-31 05:45:47.653760: Current learning rate: 0.0061 +2025-10-31 05:46:09.826020: train_loss -0.9838 +2025-10-31 05:46:09.829403: val_loss -0.8867 +2025-10-31 05:46:09.831113: Pseudo dice [np.float32(0.9854), np.float32(0.9901), np.float32(0.9939), np.float32(0.7584)] +2025-10-31 05:46:09.832860: Epoch time: 22.18 s +2025-10-31 05:46:10.881345: +2025-10-31 05:46:10.883200: Epoch 424 +2025-10-31 05:46:10.885181: Current learning rate: 0.00609 +2025-10-31 05:46:33.075065: train_loss -0.9862 +2025-10-31 05:46:33.078087: val_loss -0.8968 +2025-10-31 05:46:33.079658: Pseudo dice [np.float32(0.9857), np.float32(0.9925), np.float32(0.9943), np.float32(0.7901)] +2025-10-31 05:46:33.081184: Epoch time: 22.2 s +2025-10-31 05:46:34.271327: +2025-10-31 05:46:34.273355: Epoch 425 +2025-10-31 05:46:34.275149: Current learning rate: 0.00608 +2025-10-31 05:46:54.973888: train_loss -0.9867 +2025-10-31 05:46:54.976566: val_loss -0.8951 +2025-10-31 05:46:54.978281: Pseudo dice [np.float32(0.9843), np.float32(0.9919), np.float32(0.9947), np.float32(0.7915)] +2025-10-31 05:46:54.979953: Epoch time: 20.7 s +2025-10-31 05:46:56.075456: +2025-10-31 05:46:56.077615: Epoch 426 +2025-10-31 05:46:56.079889: Current learning rate: 0.00607 +2025-10-31 05:47:17.863156: train_loss -0.9876 +2025-10-31 05:47:17.867884: val_loss -0.8986 +2025-10-31 05:47:17.869483: Pseudo dice [np.float32(0.9855), np.float32(0.9923), np.float32(0.9945), np.float32(0.798)] +2025-10-31 05:47:17.871185: Epoch time: 21.79 s +2025-10-31 05:47:18.965482: +2025-10-31 05:47:18.967831: Epoch 427 +2025-10-31 05:47:18.969755: Current learning rate: 0.00606 +2025-10-31 05:47:41.154259: train_loss -0.9882 +2025-10-31 05:47:41.157137: val_loss -0.8949 +2025-10-31 05:47:41.158828: Pseudo dice [np.float32(0.9851), np.float32(0.9921), np.float32(0.995), np.float32(0.7954)] +2025-10-31 05:47:41.160313: Epoch time: 22.19 s +2025-10-31 05:47:42.301662: +2025-10-31 05:47:42.303787: Epoch 428 +2025-10-31 05:47:42.305372: Current learning rate: 0.00605 +2025-10-31 05:48:03.707419: train_loss -0.9881 +2025-10-31 05:48:03.711220: val_loss -0.9089 +2025-10-31 05:48:03.712900: Pseudo dice [np.float32(0.9848), np.float32(0.9922), np.float32(0.995), np.float32(0.8307)] +2025-10-31 05:48:03.714539: Epoch time: 21.41 s +2025-10-31 05:48:04.762733: +2025-10-31 05:48:04.764562: Epoch 429 +2025-10-31 05:48:04.766267: Current learning rate: 0.00604 +2025-10-31 05:48:26.525988: train_loss -0.9889 +2025-10-31 05:48:26.540438: val_loss -0.8953 +2025-10-31 05:48:26.542163: Pseudo dice [np.float32(0.9834), np.float32(0.9918), np.float32(0.9944), np.float32(0.7875)] +2025-10-31 05:48:26.543778: Epoch time: 21.77 s +2025-10-31 05:48:27.787402: +2025-10-31 05:48:27.789335: Epoch 430 +2025-10-31 05:48:27.790959: Current learning rate: 0.00603 +2025-10-31 05:48:49.715543: train_loss -0.9883 +2025-10-31 05:48:49.719002: val_loss -0.8985 +2025-10-31 05:48:49.721180: Pseudo dice [np.float32(0.9865), np.float32(0.9921), np.float32(0.9945), np.float32(0.7982)] +2025-10-31 05:48:49.723263: Epoch time: 21.93 s +2025-10-31 05:48:50.988933: +2025-10-31 05:48:50.990956: Epoch 431 +2025-10-31 05:48:50.992460: Current learning rate: 0.00602 +2025-10-31 05:49:11.381942: train_loss -0.9886 +2025-10-31 05:49:11.386259: val_loss -0.9076 +2025-10-31 05:49:11.387943: Pseudo dice [np.float32(0.9863), np.float32(0.9919), np.float32(0.9947), np.float32(0.8238)] +2025-10-31 05:49:11.389623: Epoch time: 20.39 s +2025-10-31 05:49:12.589557: +2025-10-31 05:49:12.591374: Epoch 432 +2025-10-31 05:49:12.593019: Current learning rate: 0.00601 +2025-10-31 05:49:34.480319: train_loss -0.9875 +2025-10-31 05:49:34.483824: val_loss -0.901 +2025-10-31 05:49:34.485400: Pseudo dice [np.float32(0.9866), np.float32(0.9927), np.float32(0.9949), np.float32(0.7973)] +2025-10-31 05:49:34.487079: Epoch time: 21.89 s +2025-10-31 05:49:35.907608: +2025-10-31 05:49:35.929154: Epoch 433 +2025-10-31 05:49:35.963231: Current learning rate: 0.006 +2025-10-31 05:49:56.517085: train_loss -0.9886 +2025-10-31 05:49:56.520867: val_loss -0.8884 +2025-10-31 05:49:56.522703: Pseudo dice [np.float32(0.9847), np.float32(0.9912), np.float32(0.9942), np.float32(0.7889)] +2025-10-31 05:49:56.524828: Epoch time: 20.61 s +2025-10-31 05:49:58.262388: +2025-10-31 05:49:58.266912: Epoch 434 +2025-10-31 05:49:58.271696: Current learning rate: 0.00599 +2025-10-31 05:50:19.477809: train_loss -0.988 +2025-10-31 05:50:19.479988: val_loss -0.902 +2025-10-31 05:50:19.481558: Pseudo dice [np.float32(0.9844), np.float32(0.9907), np.float32(0.9945), np.float32(0.8214)] +2025-10-31 05:50:19.483126: Epoch time: 21.22 s +2025-10-31 05:50:20.579783: +2025-10-31 05:50:20.581586: Epoch 435 +2025-10-31 05:50:20.583187: Current learning rate: 0.00598 +2025-10-31 05:50:42.496617: train_loss -0.9891 +2025-10-31 05:50:42.500413: val_loss -0.8977 +2025-10-31 05:50:42.501850: Pseudo dice [np.float32(0.9858), np.float32(0.9917), np.float32(0.9948), np.float32(0.8006)] +2025-10-31 05:50:42.503638: Epoch time: 21.92 s +2025-10-31 05:50:43.540602: +2025-10-31 05:50:43.543135: Epoch 436 +2025-10-31 05:50:43.545408: Current learning rate: 0.00597 +2025-10-31 05:51:05.377934: train_loss -0.9885 +2025-10-31 05:51:05.383123: val_loss -0.9025 +2025-10-31 05:51:05.385077: Pseudo dice [np.float32(0.9864), np.float32(0.9924), np.float32(0.9948), np.float32(0.8133)] +2025-10-31 05:51:05.386967: Epoch time: 21.84 s +2025-10-31 05:51:06.655200: +2025-10-31 05:51:06.657814: Epoch 437 +2025-10-31 05:51:06.659682: Current learning rate: 0.00596 +2025-10-31 05:51:27.543998: train_loss -0.9878 +2025-10-31 05:51:27.546466: val_loss -0.9049 +2025-10-31 05:51:27.548181: Pseudo dice [np.float32(0.9864), np.float32(0.9926), np.float32(0.9952), np.float32(0.8005)] +2025-10-31 05:51:27.549917: Epoch time: 20.89 s +2025-10-31 05:51:28.770840: +2025-10-31 05:51:28.772875: Epoch 438 +2025-10-31 05:51:28.774652: Current learning rate: 0.00595 +2025-10-31 05:51:51.124535: train_loss -0.9888 +2025-10-31 05:51:51.128965: val_loss -0.9004 +2025-10-31 05:51:51.130566: Pseudo dice [np.float32(0.9872), np.float32(0.9935), np.float32(0.9949), np.float32(0.7972)] +2025-10-31 05:51:51.132201: Epoch time: 22.36 s +2025-10-31 05:51:52.309358: +2025-10-31 05:51:52.311307: Epoch 439 +2025-10-31 05:51:52.312959: Current learning rate: 0.00594 +2025-10-31 05:52:14.250568: train_loss -0.989 +2025-10-31 05:52:14.256674: val_loss -0.8895 +2025-10-31 05:52:14.258424: Pseudo dice [np.float32(0.9843), np.float32(0.9906), np.float32(0.9944), np.float32(0.791)] +2025-10-31 05:52:14.260132: Epoch time: 21.94 s +2025-10-31 05:52:15.503168: +2025-10-31 05:52:15.504998: Epoch 440 +2025-10-31 05:52:15.507298: Current learning rate: 0.00593 +2025-10-31 05:52:37.474921: train_loss -0.9892 +2025-10-31 05:52:37.478745: val_loss -0.8977 +2025-10-31 05:52:37.480436: Pseudo dice [np.float32(0.9868), np.float32(0.9924), np.float32(0.9946), np.float32(0.7989)] +2025-10-31 05:52:37.481842: Epoch time: 21.97 s +2025-10-31 05:52:38.698087: +2025-10-31 05:52:38.700540: Epoch 441 +2025-10-31 05:52:38.702293: Current learning rate: 0.00592 +2025-10-31 05:53:00.601291: train_loss -0.9887 +2025-10-31 05:53:00.604635: val_loss -0.9012 +2025-10-31 05:53:00.606458: Pseudo dice [np.float32(0.9849), np.float32(0.9918), np.float32(0.9945), np.float32(0.8107)] +2025-10-31 05:53:00.608264: Epoch time: 21.91 s +2025-10-31 05:53:01.597021: +2025-10-31 05:53:01.598949: Epoch 442 +2025-10-31 05:53:01.600694: Current learning rate: 0.00592 +2025-10-31 05:53:24.048372: train_loss -0.9902 +2025-10-31 05:53:24.052775: val_loss -0.9033 +2025-10-31 05:53:24.054518: Pseudo dice [np.float32(0.9873), np.float32(0.9929), np.float32(0.9947), np.float32(0.809)] +2025-10-31 05:53:24.056167: Epoch time: 22.45 s +2025-10-31 05:53:24.057824: Yayy! New best EMA pseudo Dice: 0.9434999823570251 +2025-10-31 05:53:26.555535: +2025-10-31 05:53:26.557579: Epoch 443 +2025-10-31 05:53:26.559131: Current learning rate: 0.00591 +2025-10-31 05:53:47.470854: train_loss -0.9886 +2025-10-31 05:53:47.475193: val_loss -0.881 +2025-10-31 05:53:47.477422: Pseudo dice [np.float32(0.9825), np.float32(0.9908), np.float32(0.9937), np.float32(0.7657)] +2025-10-31 05:53:47.479420: Epoch time: 20.92 s +2025-10-31 05:53:48.531837: +2025-10-31 05:53:48.533810: Epoch 444 +2025-10-31 05:53:48.535422: Current learning rate: 0.0059 +2025-10-31 05:54:10.506568: train_loss -0.9886 +2025-10-31 05:54:10.509989: val_loss -0.8991 +2025-10-31 05:54:10.511610: Pseudo dice [np.float32(0.9847), np.float32(0.9914), np.float32(0.9947), np.float32(0.8084)] +2025-10-31 05:54:10.513245: Epoch time: 21.98 s +2025-10-31 05:54:11.546405: +2025-10-31 05:54:11.548241: Epoch 445 +2025-10-31 05:54:11.549811: Current learning rate: 0.00589 +2025-10-31 05:54:33.326679: train_loss -0.9898 +2025-10-31 05:54:33.330505: val_loss -0.8966 +2025-10-31 05:54:33.332333: Pseudo dice [np.float32(0.9856), np.float32(0.9923), np.float32(0.9947), np.float32(0.7947)] +2025-10-31 05:54:33.334230: Epoch time: 21.78 s +2025-10-31 05:54:34.579575: +2025-10-31 05:54:34.581417: Epoch 446 +2025-10-31 05:54:34.582938: Current learning rate: 0.00588 +2025-10-31 05:54:56.383779: train_loss -0.9896 +2025-10-31 05:54:56.389712: val_loss -0.8875 +2025-10-31 05:54:56.394771: Pseudo dice [np.float32(0.9847), np.float32(0.9903), np.float32(0.9942), np.float32(0.7782)] +2025-10-31 05:54:56.396401: Epoch time: 21.81 s +2025-10-31 05:54:57.890095: +2025-10-31 05:54:57.892517: Epoch 447 +2025-10-31 05:54:57.894282: Current learning rate: 0.00587 +2025-10-31 05:55:18.494872: train_loss -0.9899 +2025-10-31 05:55:18.498247: val_loss -0.893 +2025-10-31 05:55:18.500050: Pseudo dice [np.float32(0.9848), np.float32(0.9919), np.float32(0.9944), np.float32(0.7956)] +2025-10-31 05:55:18.501485: Epoch time: 20.61 s +2025-10-31 05:55:19.513510: +2025-10-31 05:55:19.515768: Epoch 448 +2025-10-31 05:55:19.517557: Current learning rate: 0.00586 +2025-10-31 05:55:42.044916: train_loss -0.989 +2025-10-31 05:55:42.047665: val_loss -0.9 +2025-10-31 05:55:42.049605: Pseudo dice [np.float32(0.9851), np.float32(0.9918), np.float32(0.9949), np.float32(0.8135)] +2025-10-31 05:55:42.051511: Epoch time: 22.53 s +2025-10-31 05:55:43.071458: +2025-10-31 05:55:43.073368: Epoch 449 +2025-10-31 05:55:43.075396: Current learning rate: 0.00585 +2025-10-31 05:56:05.006816: train_loss -0.9887 +2025-10-31 05:56:05.010590: val_loss -0.8947 +2025-10-31 05:56:05.012907: Pseudo dice [np.float32(0.9833), np.float32(0.991), np.float32(0.9942), np.float32(0.8004)] +2025-10-31 05:56:05.014360: Epoch time: 21.94 s +2025-10-31 05:56:07.219771: +2025-10-31 05:56:07.221842: Epoch 450 +2025-10-31 05:56:07.223444: Current learning rate: 0.00584 +2025-10-31 05:56:28.846177: train_loss -0.9896 +2025-10-31 05:56:28.851733: val_loss -0.9023 +2025-10-31 05:56:28.853719: Pseudo dice [np.float32(0.9848), np.float32(0.9913), np.float32(0.9941), np.float32(0.8141)] +2025-10-31 05:56:28.855513: Epoch time: 21.63 s +2025-10-31 05:56:29.909253: +2025-10-31 05:56:29.911023: Epoch 451 +2025-10-31 05:56:29.912527: Current learning rate: 0.00583 +2025-10-31 05:56:52.240724: train_loss -0.9896 +2025-10-31 05:56:52.244858: val_loss -0.894 +2025-10-31 05:56:52.246805: Pseudo dice [np.float32(0.9853), np.float32(0.9911), np.float32(0.9944), np.float32(0.7968)] +2025-10-31 05:56:52.248449: Epoch time: 22.33 s +2025-10-31 05:56:53.261879: +2025-10-31 05:56:53.263661: Epoch 452 +2025-10-31 05:56:53.265316: Current learning rate: 0.00582 +2025-10-31 05:57:15.987568: train_loss -0.9892 +2025-10-31 05:57:15.989767: val_loss -0.8997 +2025-10-31 05:57:15.992275: Pseudo dice [np.float32(0.9853), np.float32(0.9911), np.float32(0.9947), np.float32(0.8034)] +2025-10-31 05:57:15.994501: Epoch time: 22.73 s +2025-10-31 05:57:17.225595: +2025-10-31 05:57:17.227626: Epoch 453 +2025-10-31 05:57:17.229430: Current learning rate: 0.00581 +2025-10-31 05:57:38.906366: train_loss -0.9899 +2025-10-31 05:57:38.909778: val_loss -0.8968 +2025-10-31 05:57:38.911466: Pseudo dice [np.float32(0.9856), np.float32(0.9916), np.float32(0.9946), np.float32(0.7971)] +2025-10-31 05:57:38.913059: Epoch time: 21.68 s +2025-10-31 05:57:40.099852: +2025-10-31 05:57:40.102046: Epoch 454 +2025-10-31 05:57:40.104289: Current learning rate: 0.0058 +2025-10-31 05:58:01.524419: train_loss -0.9887 +2025-10-31 05:58:01.526935: val_loss -0.9 +2025-10-31 05:58:01.528534: Pseudo dice [np.float32(0.9869), np.float32(0.9921), np.float32(0.9947), np.float32(0.8049)] +2025-10-31 05:58:01.530217: Epoch time: 21.43 s +2025-10-31 05:58:02.669127: +2025-10-31 05:58:02.671281: Epoch 455 +2025-10-31 05:58:02.673166: Current learning rate: 0.00579 +2025-10-31 05:58:23.828972: train_loss -0.9889 +2025-10-31 05:58:23.832331: val_loss -0.8936 +2025-10-31 05:58:23.834013: Pseudo dice [np.float32(0.9862), np.float32(0.9916), np.float32(0.9948), np.float32(0.7817)] +2025-10-31 05:58:23.835638: Epoch time: 21.16 s +2025-10-31 05:58:25.010789: +2025-10-31 05:58:25.012715: Epoch 456 +2025-10-31 05:58:25.014536: Current learning rate: 0.00578 +2025-10-31 05:58:47.083737: train_loss -0.989 +2025-10-31 05:58:47.088675: val_loss -0.8962 +2025-10-31 05:58:47.090836: Pseudo dice [np.float32(0.9868), np.float32(0.9925), np.float32(0.9946), np.float32(0.7892)] +2025-10-31 05:58:47.092890: Epoch time: 22.07 s +2025-10-31 05:58:48.091275: +2025-10-31 05:58:48.093229: Epoch 457 +2025-10-31 05:58:48.095562: Current learning rate: 0.00577 +2025-10-31 05:59:09.468633: train_loss -0.9897 +2025-10-31 05:59:09.470996: val_loss -0.89 +2025-10-31 05:59:09.472856: Pseudo dice [np.float32(0.9855), np.float32(0.9916), np.float32(0.9944), np.float32(0.7818)] +2025-10-31 05:59:09.474534: Epoch time: 21.38 s +2025-10-31 05:59:10.622164: +2025-10-31 05:59:10.624275: Epoch 458 +2025-10-31 05:59:10.625971: Current learning rate: 0.00576 +2025-10-31 05:59:33.274784: train_loss -0.9892 +2025-10-31 05:59:33.277165: val_loss -0.8948 +2025-10-31 05:59:33.279355: Pseudo dice [np.float32(0.9859), np.float32(0.9918), np.float32(0.9945), np.float32(0.7972)] +2025-10-31 05:59:33.282019: Epoch time: 22.65 s +2025-10-31 05:59:34.676491: +2025-10-31 05:59:34.678373: Epoch 459 +2025-10-31 05:59:34.680674: Current learning rate: 0.00575 +2025-10-31 05:59:57.507773: train_loss -0.9877 +2025-10-31 05:59:57.510721: val_loss -0.8937 +2025-10-31 05:59:57.512589: Pseudo dice [np.float32(0.9846), np.float32(0.99), np.float32(0.9943), np.float32(0.8074)] +2025-10-31 05:59:57.514477: Epoch time: 22.83 s +2025-10-31 05:59:58.628449: +2025-10-31 05:59:58.630098: Epoch 460 +2025-10-31 05:59:58.631933: Current learning rate: 0.00574 +2025-10-31 06:00:19.510990: train_loss -0.9889 +2025-10-31 06:00:19.513317: val_loss -0.8841 +2025-10-31 06:00:19.515189: Pseudo dice [np.float32(0.9849), np.float32(0.9913), np.float32(0.9939), np.float32(0.7746)] +2025-10-31 06:00:19.516997: Epoch time: 20.88 s +2025-10-31 06:00:20.699239: +2025-10-31 06:00:20.701904: Epoch 461 +2025-10-31 06:00:20.704000: Current learning rate: 0.00573 +2025-10-31 06:00:41.900862: train_loss -0.9901 +2025-10-31 06:00:41.903403: val_loss -0.9017 +2025-10-31 06:00:41.904967: Pseudo dice [np.float32(0.9868), np.float32(0.9925), np.float32(0.9947), np.float32(0.8015)] +2025-10-31 06:00:41.907059: Epoch time: 21.2 s +2025-10-31 06:00:42.905321: +2025-10-31 06:00:42.907204: Epoch 462 +2025-10-31 06:00:42.909592: Current learning rate: 0.00572 +2025-10-31 06:01:05.471203: train_loss -0.9899 +2025-10-31 06:01:05.475984: val_loss -0.896 +2025-10-31 06:01:05.478906: Pseudo dice [np.float32(0.9858), np.float32(0.9917), np.float32(0.9948), np.float32(0.7977)] +2025-10-31 06:01:05.481109: Epoch time: 22.57 s +2025-10-31 06:01:06.664873: +2025-10-31 06:01:06.668178: Epoch 463 +2025-10-31 06:01:06.669967: Current learning rate: 0.00571 +2025-10-31 06:01:29.154060: train_loss -0.9887 +2025-10-31 06:01:29.156769: val_loss -0.8906 +2025-10-31 06:01:29.158513: Pseudo dice [np.float32(0.9848), np.float32(0.9915), np.float32(0.9943), np.float32(0.7816)] +2025-10-31 06:01:29.160381: Epoch time: 22.49 s +2025-10-31 06:01:30.481403: +2025-10-31 06:01:30.483384: Epoch 464 +2025-10-31 06:01:30.484962: Current learning rate: 0.0057 +2025-10-31 06:01:52.233939: train_loss -0.9894 +2025-10-31 06:01:52.236128: val_loss -0.8923 +2025-10-31 06:01:52.237886: Pseudo dice [np.float32(0.9861), np.float32(0.9922), np.float32(0.9939), np.float32(0.7893)] +2025-10-31 06:01:52.239501: Epoch time: 21.75 s +2025-10-31 06:01:53.288116: +2025-10-31 06:01:53.289883: Epoch 465 +2025-10-31 06:01:53.291787: Current learning rate: 0.0057 +2025-10-31 06:02:15.622456: train_loss -0.9899 +2025-10-31 06:02:15.625648: val_loss -0.8936 +2025-10-31 06:02:15.627672: Pseudo dice [np.float32(0.9858), np.float32(0.9913), np.float32(0.9943), np.float32(0.7968)] +2025-10-31 06:02:15.629425: Epoch time: 22.34 s +2025-10-31 06:02:16.649446: +2025-10-31 06:02:16.651294: Epoch 466 +2025-10-31 06:02:16.653198: Current learning rate: 0.00569 +2025-10-31 06:02:39.292634: train_loss -0.9892 +2025-10-31 06:02:39.298177: val_loss -0.8902 +2025-10-31 06:02:39.300158: Pseudo dice [np.float32(0.9863), np.float32(0.9921), np.float32(0.9944), np.float32(0.7767)] +2025-10-31 06:02:39.301955: Epoch time: 22.64 s +2025-10-31 06:02:40.691361: +2025-10-31 06:02:40.693745: Epoch 467 +2025-10-31 06:02:40.695464: Current learning rate: 0.00568 +2025-10-31 06:03:01.476824: train_loss -0.9899 +2025-10-31 06:03:01.479055: val_loss -0.8929 +2025-10-31 06:03:01.481628: Pseudo dice [np.float32(0.984), np.float32(0.9912), np.float32(0.9943), np.float32(0.8009)] +2025-10-31 06:03:01.483328: Epoch time: 20.79 s +2025-10-31 06:03:02.581215: +2025-10-31 06:03:02.583769: Epoch 468 +2025-10-31 06:03:02.585901: Current learning rate: 0.00567 +2025-10-31 06:03:24.731643: train_loss -0.9896 +2025-10-31 06:03:24.734436: val_loss -0.8946 +2025-10-31 06:03:24.736219: Pseudo dice [np.float32(0.9844), np.float32(0.9907), np.float32(0.9946), np.float32(0.8061)] +2025-10-31 06:03:24.737929: Epoch time: 22.15 s +2025-10-31 06:03:25.807584: +2025-10-31 06:03:25.809799: Epoch 469 +2025-10-31 06:03:25.811893: Current learning rate: 0.00566 +2025-10-31 06:03:48.528912: train_loss -0.9897 +2025-10-31 06:03:48.531853: val_loss -0.8997 +2025-10-31 06:03:48.533800: Pseudo dice [np.float32(0.986), np.float32(0.992), np.float32(0.9949), np.float32(0.7987)] +2025-10-31 06:03:48.536701: Epoch time: 22.72 s +2025-10-31 06:03:49.771948: +2025-10-31 06:03:49.773794: Epoch 470 +2025-10-31 06:03:49.775373: Current learning rate: 0.00565 +2025-10-31 06:04:11.990134: train_loss -0.9895 +2025-10-31 06:04:11.992537: val_loss -0.8999 +2025-10-31 06:04:11.994135: Pseudo dice [np.float32(0.9856), np.float32(0.9917), np.float32(0.9947), np.float32(0.8031)] +2025-10-31 06:04:11.996091: Epoch time: 22.22 s +2025-10-31 06:04:13.221210: +2025-10-31 06:04:13.223192: Epoch 471 +2025-10-31 06:04:13.224988: Current learning rate: 0.00564 +2025-10-31 06:04:35.497588: train_loss -0.9887 +2025-10-31 06:04:35.500854: val_loss -0.8937 +2025-10-31 06:04:35.502704: Pseudo dice [np.float32(0.9842), np.float32(0.991), np.float32(0.9945), np.float32(0.793)] +2025-10-31 06:04:35.504526: Epoch time: 22.28 s +2025-10-31 06:04:37.044446: +2025-10-31 06:04:37.047544: Epoch 472 +2025-10-31 06:04:37.049245: Current learning rate: 0.00563 +2025-10-31 06:04:59.375212: train_loss -0.9885 +2025-10-31 06:04:59.377670: val_loss -0.9011 +2025-10-31 06:04:59.379397: Pseudo dice [np.float32(0.9855), np.float32(0.9915), np.float32(0.9946), np.float32(0.8049)] +2025-10-31 06:04:59.380893: Epoch time: 22.33 s +2025-10-31 06:05:00.501147: +2025-10-31 06:05:00.503515: Epoch 473 +2025-10-31 06:05:00.506623: Current learning rate: 0.00562 +2025-10-31 06:05:21.594872: train_loss -0.9886 +2025-10-31 06:05:21.597132: val_loss -0.8939 +2025-10-31 06:05:21.598712: Pseudo dice [np.float32(0.9858), np.float32(0.9919), np.float32(0.9945), np.float32(0.7981)] +2025-10-31 06:05:21.600318: Epoch time: 21.1 s +2025-10-31 06:05:22.939676: +2025-10-31 06:05:22.941848: Epoch 474 +2025-10-31 06:05:22.943573: Current learning rate: 0.00561 +2025-10-31 06:05:44.452602: train_loss -0.9892 +2025-10-31 06:05:44.456078: val_loss -0.8971 +2025-10-31 06:05:44.457531: Pseudo dice [np.float32(0.9858), np.float32(0.9921), np.float32(0.9948), np.float32(0.7951)] +2025-10-31 06:05:44.459307: Epoch time: 21.52 s +2025-10-31 06:05:45.716615: +2025-10-31 06:05:45.718564: Epoch 475 +2025-10-31 06:05:45.720286: Current learning rate: 0.0056 +2025-10-31 06:06:08.132261: train_loss -0.9888 +2025-10-31 06:06:08.135569: val_loss -0.8964 +2025-10-31 06:06:08.137348: Pseudo dice [np.float32(0.9864), np.float32(0.9921), np.float32(0.9947), np.float32(0.7932)] +2025-10-31 06:06:08.140024: Epoch time: 22.42 s +2025-10-31 06:06:09.216820: +2025-10-31 06:06:09.218611: Epoch 476 +2025-10-31 06:06:09.220130: Current learning rate: 0.00559 +2025-10-31 06:06:31.659749: train_loss -0.9891 +2025-10-31 06:06:31.664207: val_loss -0.8868 +2025-10-31 06:06:31.665857: Pseudo dice [np.float32(0.9853), np.float32(0.9907), np.float32(0.9946), np.float32(0.7807)] +2025-10-31 06:06:31.667440: Epoch time: 22.45 s +2025-10-31 06:06:32.713827: +2025-10-31 06:06:32.716040: Epoch 477 +2025-10-31 06:06:32.717817: Current learning rate: 0.00558 +2025-10-31 06:06:55.199188: train_loss -0.9891 +2025-10-31 06:06:55.202336: val_loss -0.8856 +2025-10-31 06:06:55.203943: Pseudo dice [np.float32(0.9842), np.float32(0.9911), np.float32(0.9944), np.float32(0.7805)] +2025-10-31 06:06:55.205800: Epoch time: 22.49 s +2025-10-31 06:06:56.526033: +2025-10-31 06:06:56.528013: Epoch 478 +2025-10-31 06:06:56.530503: Current learning rate: 0.00557 +2025-10-31 06:07:18.595618: train_loss -0.9888 +2025-10-31 06:07:18.599415: val_loss -0.8998 +2025-10-31 06:07:18.601324: Pseudo dice [np.float32(0.9859), np.float32(0.9919), np.float32(0.9948), np.float32(0.804)] +2025-10-31 06:07:18.603139: Epoch time: 22.07 s +2025-10-31 06:07:19.672086: +2025-10-31 06:07:19.677518: Epoch 479 +2025-10-31 06:07:19.679412: Current learning rate: 0.00556 +2025-10-31 06:07:40.975637: train_loss -0.9884 +2025-10-31 06:07:40.977923: val_loss -0.8962 +2025-10-31 06:07:40.979649: Pseudo dice [np.float32(0.9856), np.float32(0.9917), np.float32(0.9945), np.float32(0.7973)] +2025-10-31 06:07:40.981508: Epoch time: 21.31 s +2025-10-31 06:07:42.183204: +2025-10-31 06:07:42.185690: Epoch 480 +2025-10-31 06:07:42.187541: Current learning rate: 0.00555 +2025-10-31 06:08:03.893475: train_loss -0.9901 +2025-10-31 06:08:03.897134: val_loss -0.9023 +2025-10-31 06:08:03.900044: Pseudo dice [np.float32(0.9863), np.float32(0.9922), np.float32(0.9952), np.float32(0.8099)] +2025-10-31 06:08:03.902739: Epoch time: 21.71 s +2025-10-31 06:08:05.111930: +2025-10-31 06:08:05.115584: Epoch 481 +2025-10-31 06:08:05.118520: Current learning rate: 0.00554 +2025-10-31 06:08:26.981972: train_loss -0.9895 +2025-10-31 06:08:26.984976: val_loss -0.8959 +2025-10-31 06:08:26.986989: Pseudo dice [np.float32(0.9873), np.float32(0.9919), np.float32(0.9946), np.float32(0.7906)] +2025-10-31 06:08:26.988711: Epoch time: 21.87 s +2025-10-31 06:08:28.058611: +2025-10-31 06:08:28.060576: Epoch 482 +2025-10-31 06:08:28.062411: Current learning rate: 0.00553 +2025-10-31 06:08:50.432753: train_loss -0.9898 +2025-10-31 06:08:50.435651: val_loss -0.8851 +2025-10-31 06:08:50.437968: Pseudo dice [np.float32(0.9855), np.float32(0.9914), np.float32(0.9939), np.float32(0.7734)] +2025-10-31 06:08:50.440797: Epoch time: 22.38 s +2025-10-31 06:08:51.651102: +2025-10-31 06:08:51.653167: Epoch 483 +2025-10-31 06:08:51.655620: Current learning rate: 0.00552 +2025-10-31 06:09:14.652610: train_loss -0.9895 +2025-10-31 06:09:14.655599: val_loss -0.9014 +2025-10-31 06:09:14.657205: Pseudo dice [np.float32(0.9866), np.float32(0.9921), np.float32(0.9945), np.float32(0.8083)] +2025-10-31 06:09:14.658858: Epoch time: 23.0 s +2025-10-31 06:09:15.731568: +2025-10-31 06:09:15.733385: Epoch 484 +2025-10-31 06:09:15.734959: Current learning rate: 0.00551 +2025-10-31 06:09:38.429492: train_loss -0.9888 +2025-10-31 06:09:38.431757: val_loss -0.8891 +2025-10-31 06:09:38.433464: Pseudo dice [np.float32(0.9866), np.float32(0.9915), np.float32(0.9943), np.float32(0.7774)] +2025-10-31 06:09:38.435072: Epoch time: 22.7 s +2025-10-31 06:09:40.320500: +2025-10-31 06:09:40.322630: Epoch 485 +2025-10-31 06:09:40.324334: Current learning rate: 0.0055 +2025-10-31 06:10:02.758441: train_loss -0.9892 +2025-10-31 06:10:02.762172: val_loss -0.8997 +2025-10-31 06:10:02.763822: Pseudo dice [np.float32(0.9869), np.float32(0.9919), np.float32(0.9948), np.float32(0.8038)] +2025-10-31 06:10:02.765260: Epoch time: 22.44 s +2025-10-31 06:10:03.933608: +2025-10-31 06:10:03.936589: Epoch 486 +2025-10-31 06:10:03.938480: Current learning rate: 0.00549 +2025-10-31 06:10:25.401676: train_loss -0.9893 +2025-10-31 06:10:25.404657: val_loss -0.8946 +2025-10-31 06:10:25.406288: Pseudo dice [np.float32(0.9856), np.float32(0.9919), np.float32(0.9949), np.float32(0.7962)] +2025-10-31 06:10:25.407764: Epoch time: 21.47 s +2025-10-31 06:10:26.468954: +2025-10-31 06:10:26.470748: Epoch 487 +2025-10-31 06:10:26.472888: Current learning rate: 0.00548 +2025-10-31 06:10:48.679608: train_loss -0.9891 +2025-10-31 06:10:48.682206: val_loss -0.8899 +2025-10-31 06:10:48.683968: Pseudo dice [np.float32(0.9863), np.float32(0.9919), np.float32(0.9943), np.float32(0.7855)] +2025-10-31 06:10:48.685506: Epoch time: 22.21 s +2025-10-31 06:10:49.965441: +2025-10-31 06:10:49.967431: Epoch 488 +2025-10-31 06:10:49.969141: Current learning rate: 0.00547 +2025-10-31 06:11:12.511950: train_loss -0.9876 +2025-10-31 06:11:12.515913: val_loss -0.8894 +2025-10-31 06:11:12.518664: Pseudo dice [np.float32(0.9855), np.float32(0.9911), np.float32(0.994), np.float32(0.7772)] +2025-10-31 06:11:12.520658: Epoch time: 22.55 s +2025-10-31 06:11:13.629655: +2025-10-31 06:11:13.631515: Epoch 489 +2025-10-31 06:11:13.633047: Current learning rate: 0.00546 +2025-10-31 06:11:36.176941: train_loss -0.9849 +2025-10-31 06:11:36.180050: val_loss -0.8964 +2025-10-31 06:11:36.181791: Pseudo dice [np.float32(0.9855), np.float32(0.9913), np.float32(0.9945), np.float32(0.7941)] +2025-10-31 06:11:36.183366: Epoch time: 22.55 s +2025-10-31 06:11:37.279299: +2025-10-31 06:11:37.280908: Epoch 490 +2025-10-31 06:11:37.282685: Current learning rate: 0.00546 +2025-10-31 06:12:00.022942: train_loss -0.9785 +2025-10-31 06:12:00.027281: val_loss -0.8987 +2025-10-31 06:12:00.028952: Pseudo dice [np.float32(0.9837), np.float32(0.99), np.float32(0.9941), np.float32(0.7838)] +2025-10-31 06:12:00.031394: Epoch time: 22.75 s +2025-10-31 06:12:01.190872: +2025-10-31 06:12:01.193222: Epoch 491 +2025-10-31 06:12:01.197339: Current learning rate: 0.00545 +2025-10-31 06:12:23.212709: train_loss -0.9561 +2025-10-31 06:12:23.217145: val_loss -0.898 +2025-10-31 06:12:23.218969: Pseudo dice [np.float32(0.9851), np.float32(0.9886), np.float32(0.9922), np.float32(0.7907)] +2025-10-31 06:12:23.220925: Epoch time: 22.02 s +2025-10-31 06:12:24.442150: +2025-10-31 06:12:24.444383: Epoch 492 +2025-10-31 06:12:24.446451: Current learning rate: 0.00544 +2025-10-31 06:12:45.226566: train_loss -0.9407 +2025-10-31 06:12:45.230623: val_loss -0.9074 +2025-10-31 06:12:45.232415: Pseudo dice [np.float32(0.9834), np.float32(0.9907), np.float32(0.9932), np.float32(0.8074)] +2025-10-31 06:12:45.234183: Epoch time: 20.79 s +2025-10-31 06:12:46.379694: +2025-10-31 06:12:46.384551: Epoch 493 +2025-10-31 06:12:46.386359: Current learning rate: 0.00543 +2025-10-31 06:13:08.336325: train_loss -0.954 +2025-10-31 06:13:08.342229: val_loss -0.9057 +2025-10-31 06:13:08.344267: Pseudo dice [np.float32(0.9843), np.float32(0.9909), np.float32(0.9933), np.float32(0.7824)] +2025-10-31 06:13:08.346209: Epoch time: 21.96 s +2025-10-31 06:13:09.641428: +2025-10-31 06:13:09.643471: Epoch 494 +2025-10-31 06:13:09.645195: Current learning rate: 0.00542 +2025-10-31 06:13:31.916435: train_loss -0.9689 +2025-10-31 06:13:31.919297: val_loss -0.9054 +2025-10-31 06:13:31.920941: Pseudo dice [np.float32(0.9872), np.float32(0.9922), np.float32(0.9948), np.float32(0.7734)] +2025-10-31 06:13:31.922659: Epoch time: 22.28 s +2025-10-31 06:13:33.111261: +2025-10-31 06:13:33.113348: Epoch 495 +2025-10-31 06:13:33.115146: Current learning rate: 0.00541 +2025-10-31 06:13:55.644735: train_loss -0.9755 +2025-10-31 06:13:55.648011: val_loss -0.9093 +2025-10-31 06:13:55.649657: Pseudo dice [np.float32(0.9859), np.float32(0.9919), np.float32(0.9942), np.float32(0.7979)] +2025-10-31 06:13:55.651270: Epoch time: 22.53 s +2025-10-31 06:13:56.569748: +2025-10-31 06:13:56.571537: Epoch 496 +2025-10-31 06:13:56.573274: Current learning rate: 0.0054 +2025-10-31 06:14:18.217555: train_loss -0.9784 +2025-10-31 06:14:18.220437: val_loss -0.8933 +2025-10-31 06:14:18.222002: Pseudo dice [np.float32(0.9857), np.float32(0.9919), np.float32(0.9934), np.float32(0.7677)] +2025-10-31 06:14:18.223523: Epoch time: 21.65 s +2025-10-31 06:14:19.340972: +2025-10-31 06:14:19.342887: Epoch 497 +2025-10-31 06:14:19.344737: Current learning rate: 0.00539 +2025-10-31 06:14:41.343017: train_loss -0.9824 +2025-10-31 06:14:41.345075: val_loss -0.896 +2025-10-31 06:14:41.346724: Pseudo dice [np.float32(0.9859), np.float32(0.9924), np.float32(0.9933), np.float32(0.7723)] +2025-10-31 06:14:41.348233: Epoch time: 22.0 s +2025-10-31 06:14:42.804598: +2025-10-31 06:14:42.806351: Epoch 498 +2025-10-31 06:14:42.807869: Current learning rate: 0.00538 +2025-10-31 06:15:03.751462: train_loss -0.9673 +2025-10-31 06:15:03.755937: val_loss -0.8992 +2025-10-31 06:15:03.758194: Pseudo dice [np.float32(0.9844), np.float32(0.987), np.float32(0.9923), np.float32(0.7903)] +2025-10-31 06:15:03.760257: Epoch time: 20.95 s +2025-10-31 06:15:04.980672: +2025-10-31 06:15:04.982435: Epoch 499 +2025-10-31 06:15:04.984042: Current learning rate: 0.00537 +2025-10-31 06:15:25.704759: train_loss -0.9357 +2025-10-31 06:15:25.707652: val_loss -0.9081 +2025-10-31 06:15:25.709503: Pseudo dice [np.float32(0.9859), np.float32(0.9911), np.float32(0.9938), np.float32(0.7982)] +2025-10-31 06:15:25.711212: Epoch time: 20.73 s +2025-10-31 06:15:28.190982: +2025-10-31 06:15:28.193075: Epoch 500 +2025-10-31 06:15:28.195825: Current learning rate: 0.00536 +2025-10-31 06:15:50.531585: train_loss -0.9577 +2025-10-31 06:15:50.534962: val_loss -0.9065 +2025-10-31 06:15:50.536600: Pseudo dice [np.float32(0.9862), np.float32(0.9914), np.float32(0.9944), np.float32(0.7908)] +2025-10-31 06:15:50.538326: Epoch time: 22.34 s +2025-10-31 06:15:51.625868: +2025-10-31 06:15:51.627594: Epoch 501 +2025-10-31 06:15:51.629243: Current learning rate: 0.00535 +2025-10-31 06:16:14.073754: train_loss -0.973 +2025-10-31 06:16:14.078302: val_loss -0.9125 +2025-10-31 06:16:14.079684: Pseudo dice [np.float32(0.9864), np.float32(0.9922), np.float32(0.9947), np.float32(0.8065)] +2025-10-31 06:16:14.081303: Epoch time: 22.45 s +2025-10-31 06:16:15.103340: +2025-10-31 06:16:15.105354: Epoch 502 +2025-10-31 06:16:15.107112: Current learning rate: 0.00534 +2025-10-31 06:16:37.419882: train_loss -0.9766 +2025-10-31 06:16:37.422192: val_loss -0.9111 +2025-10-31 06:16:37.423785: Pseudo dice [np.float32(0.9854), np.float32(0.9915), np.float32(0.9943), np.float32(0.806)] +2025-10-31 06:16:37.425230: Epoch time: 22.32 s +2025-10-31 06:16:38.655625: +2025-10-31 06:16:38.657834: Epoch 503 +2025-10-31 06:16:38.660347: Current learning rate: 0.00533 +2025-10-31 06:17:00.664106: train_loss -0.9779 +2025-10-31 06:17:00.669720: val_loss -0.9081 +2025-10-31 06:17:00.671583: Pseudo dice [np.float32(0.9863), np.float32(0.9926), np.float32(0.9943), np.float32(0.8036)] +2025-10-31 06:17:00.673272: Epoch time: 22.01 s +2025-10-31 06:17:01.894735: +2025-10-31 06:17:01.897575: Epoch 504 +2025-10-31 06:17:01.900272: Current learning rate: 0.00532 +2025-10-31 06:17:23.348223: train_loss -0.9805 +2025-10-31 06:17:23.351923: val_loss -0.9148 +2025-10-31 06:17:23.353674: Pseudo dice [np.float32(0.9867), np.float32(0.9914), np.float32(0.9945), np.float32(0.8239)] +2025-10-31 06:17:23.355284: Epoch time: 21.46 s +2025-10-31 06:17:24.370466: +2025-10-31 06:17:24.372475: Epoch 505 +2025-10-31 06:17:24.374885: Current learning rate: 0.00531 +2025-10-31 06:17:45.322738: train_loss -0.9778 +2025-10-31 06:17:45.326321: val_loss -0.8999 +2025-10-31 06:17:45.327984: Pseudo dice [np.float32(0.985), np.float32(0.9898), np.float32(0.9935), np.float32(0.7909)] +2025-10-31 06:17:45.329746: Epoch time: 20.95 s +2025-10-31 06:17:46.374622: +2025-10-31 06:17:46.376684: Epoch 506 +2025-10-31 06:17:46.378309: Current learning rate: 0.0053 +2025-10-31 06:18:08.680104: train_loss -0.9752 +2025-10-31 06:18:08.686774: val_loss -0.8981 +2025-10-31 06:18:08.688972: Pseudo dice [np.float32(0.9844), np.float32(0.9911), np.float32(0.9938), np.float32(0.7874)] +2025-10-31 06:18:08.691175: Epoch time: 22.31 s +2025-10-31 06:18:09.881712: +2025-10-31 06:18:09.883636: Epoch 507 +2025-10-31 06:18:09.885685: Current learning rate: 0.00529 +2025-10-31 06:18:31.821471: train_loss -0.9791 +2025-10-31 06:18:31.826120: val_loss -0.8965 +2025-10-31 06:18:31.827929: Pseudo dice [np.float32(0.9842), np.float32(0.9918), np.float32(0.994), np.float32(0.776)] +2025-10-31 06:18:31.829602: Epoch time: 21.94 s +2025-10-31 06:18:33.056879: +2025-10-31 06:18:33.058669: Epoch 508 +2025-10-31 06:18:33.060261: Current learning rate: 0.00528 +2025-10-31 06:18:55.300367: train_loss -0.9825 +2025-10-31 06:18:55.303861: val_loss -0.8892 +2025-10-31 06:18:55.305703: Pseudo dice [np.float32(0.9828), np.float32(0.9906), np.float32(0.994), np.float32(0.7665)] +2025-10-31 06:18:55.307624: Epoch time: 22.24 s +2025-10-31 06:18:56.315426: +2025-10-31 06:18:56.317252: Epoch 509 +2025-10-31 06:18:56.318854: Current learning rate: 0.00527 +2025-10-31 06:19:18.735783: train_loss -0.9837 +2025-10-31 06:19:18.739096: val_loss -0.8971 +2025-10-31 06:19:18.740951: Pseudo dice [np.float32(0.9842), np.float32(0.9905), np.float32(0.9942), np.float32(0.7955)] +2025-10-31 06:19:18.742771: Epoch time: 22.42 s +2025-10-31 06:19:20.535796: +2025-10-31 06:19:20.537853: Epoch 510 +2025-10-31 06:19:20.539677: Current learning rate: 0.00526 +2025-10-31 06:19:41.545065: train_loss -0.9841 +2025-10-31 06:19:41.550699: val_loss -0.8924 +2025-10-31 06:19:41.552471: Pseudo dice [np.float32(0.9837), np.float32(0.9908), np.float32(0.9941), np.float32(0.7831)] +2025-10-31 06:19:41.554184: Epoch time: 21.01 s +2025-10-31 06:19:42.690969: +2025-10-31 06:19:42.692832: Epoch 511 +2025-10-31 06:19:42.694499: Current learning rate: 0.00525 +2025-10-31 06:20:04.237627: train_loss -0.9844 +2025-10-31 06:20:04.242489: val_loss -0.9008 +2025-10-31 06:20:04.244982: Pseudo dice [np.float32(0.9845), np.float32(0.992), np.float32(0.9945), np.float32(0.7987)] +2025-10-31 06:20:04.246889: Epoch time: 21.55 s +2025-10-31 06:20:05.260264: +2025-10-31 06:20:05.262405: Epoch 512 +2025-10-31 06:20:05.265064: Current learning rate: 0.00524 +2025-10-31 06:20:27.237347: train_loss -0.9821 +2025-10-31 06:20:27.240124: val_loss -0.8999 +2025-10-31 06:20:27.241929: Pseudo dice [np.float32(0.984), np.float32(0.991), np.float32(0.9943), np.float32(0.7941)] +2025-10-31 06:20:27.243723: Epoch time: 21.98 s +2025-10-31 06:20:28.267884: +2025-10-31 06:20:28.269599: Epoch 513 +2025-10-31 06:20:28.271365: Current learning rate: 0.00523 +2025-10-31 06:20:50.061699: train_loss -0.9845 +2025-10-31 06:20:50.066156: val_loss -0.8963 +2025-10-31 06:20:50.068571: Pseudo dice [np.float32(0.9843), np.float32(0.9912), np.float32(0.9941), np.float32(0.7898)] +2025-10-31 06:20:50.071002: Epoch time: 21.79 s +2025-10-31 06:20:51.443358: +2025-10-31 06:20:51.445936: Epoch 514 +2025-10-31 06:20:51.448542: Current learning rate: 0.00522 +2025-10-31 06:21:13.162157: train_loss -0.9835 +2025-10-31 06:21:13.167186: val_loss -0.8944 +2025-10-31 06:21:13.169128: Pseudo dice [np.float32(0.9839), np.float32(0.991), np.float32(0.9941), np.float32(0.787)] +2025-10-31 06:21:13.170691: Epoch time: 21.72 s +2025-10-31 06:21:14.394717: +2025-10-31 06:21:14.396693: Epoch 515 +2025-10-31 06:21:14.398384: Current learning rate: 0.00521 +2025-10-31 06:21:36.955888: train_loss -0.9851 +2025-10-31 06:21:36.960578: val_loss -0.8926 +2025-10-31 06:21:36.962341: Pseudo dice [np.float32(0.9845), np.float32(0.9908), np.float32(0.994), np.float32(0.7867)] +2025-10-31 06:21:36.964060: Epoch time: 22.56 s +2025-10-31 06:21:38.007413: +2025-10-31 06:21:38.009472: Epoch 516 +2025-10-31 06:21:38.011417: Current learning rate: 0.0052 +2025-10-31 06:21:58.575110: train_loss -0.9855 +2025-10-31 06:21:58.578820: val_loss -0.895 +2025-10-31 06:21:58.581156: Pseudo dice [np.float32(0.9855), np.float32(0.9924), np.float32(0.9944), np.float32(0.7826)] +2025-10-31 06:21:58.583263: Epoch time: 20.57 s +2025-10-31 06:21:59.817999: +2025-10-31 06:21:59.819860: Epoch 517 +2025-10-31 06:21:59.821528: Current learning rate: 0.00519 +2025-10-31 06:22:22.068724: train_loss -0.9868 +2025-10-31 06:22:22.073438: val_loss -0.8973 +2025-10-31 06:22:22.075426: Pseudo dice [np.float32(0.9847), np.float32(0.9924), np.float32(0.9949), np.float32(0.8)] +2025-10-31 06:22:22.077330: Epoch time: 22.25 s +2025-10-31 06:22:23.390969: +2025-10-31 06:22:23.397089: Epoch 518 +2025-10-31 06:22:23.399326: Current learning rate: 0.00518 +2025-10-31 06:22:44.249838: train_loss -0.9862 +2025-10-31 06:22:44.256821: val_loss -0.8877 +2025-10-31 06:22:44.259437: Pseudo dice [np.float32(0.9839), np.float32(0.9917), np.float32(0.9933), np.float32(0.7823)] +2025-10-31 06:22:44.261584: Epoch time: 20.86 s +2025-10-31 06:22:45.399773: +2025-10-31 06:22:45.402138: Epoch 519 +2025-10-31 06:22:45.404164: Current learning rate: 0.00518 +2025-10-31 06:23:07.612723: train_loss -0.9873 +2025-10-31 06:23:07.615681: val_loss -0.9028 +2025-10-31 06:23:07.617472: Pseudo dice [np.float32(0.9835), np.float32(0.9919), np.float32(0.9947), np.float32(0.8177)] +2025-10-31 06:23:07.619220: Epoch time: 22.21 s +2025-10-31 06:23:08.717436: +2025-10-31 06:23:08.719542: Epoch 520 +2025-10-31 06:23:08.721640: Current learning rate: 0.00517 +2025-10-31 06:23:30.595698: train_loss -0.9878 +2025-10-31 06:23:30.600147: val_loss -0.8863 +2025-10-31 06:23:30.602203: Pseudo dice [np.float32(0.9842), np.float32(0.9905), np.float32(0.9939), np.float32(0.7775)] +2025-10-31 06:23:30.604131: Epoch time: 21.88 s +2025-10-31 06:23:31.884142: +2025-10-31 06:23:31.886486: Epoch 521 +2025-10-31 06:23:31.888408: Current learning rate: 0.00516 +2025-10-31 06:23:53.967122: train_loss -0.9878 +2025-10-31 06:23:53.970888: val_loss -0.8909 +2025-10-31 06:23:53.973128: Pseudo dice [np.float32(0.9831), np.float32(0.9899), np.float32(0.9942), np.float32(0.7881)] +2025-10-31 06:23:53.975035: Epoch time: 22.09 s +2025-10-31 06:23:55.614398: +2025-10-31 06:23:55.616625: Epoch 522 +2025-10-31 06:23:55.618881: Current learning rate: 0.00515 +2025-10-31 06:24:16.341288: train_loss -0.987 +2025-10-31 06:24:16.344883: val_loss -0.8922 +2025-10-31 06:24:16.346603: Pseudo dice [np.float32(0.9853), np.float32(0.9928), np.float32(0.9941), np.float32(0.7823)] +2025-10-31 06:24:16.348123: Epoch time: 20.73 s +2025-10-31 06:24:17.356468: +2025-10-31 06:24:17.358406: Epoch 523 +2025-10-31 06:24:17.360161: Current learning rate: 0.00514 +2025-10-31 06:24:39.480816: train_loss -0.9874 +2025-10-31 06:24:39.483581: val_loss -0.8908 +2025-10-31 06:24:39.485460: Pseudo dice [np.float32(0.9863), np.float32(0.9923), np.float32(0.9942), np.float32(0.7665)] +2025-10-31 06:24:39.487131: Epoch time: 22.13 s +2025-10-31 06:24:40.718771: +2025-10-31 06:24:40.720619: Epoch 524 +2025-10-31 06:24:40.722163: Current learning rate: 0.00513 +2025-10-31 06:25:01.507786: train_loss -0.9883 +2025-10-31 06:25:01.511178: val_loss -0.8918 +2025-10-31 06:25:01.512759: Pseudo dice [np.float32(0.9847), np.float32(0.9914), np.float32(0.994), np.float32(0.7865)] +2025-10-31 06:25:01.514436: Epoch time: 20.79 s +2025-10-31 06:25:02.621307: +2025-10-31 06:25:02.623330: Epoch 525 +2025-10-31 06:25:02.625175: Current learning rate: 0.00512 +2025-10-31 06:25:25.134024: train_loss -0.9876 +2025-10-31 06:25:25.137583: val_loss -0.8965 +2025-10-31 06:25:25.139379: Pseudo dice [np.float32(0.985), np.float32(0.9918), np.float32(0.9946), np.float32(0.7899)] +2025-10-31 06:25:25.141037: Epoch time: 22.51 s +2025-10-31 06:25:26.231169: +2025-10-31 06:25:26.233276: Epoch 526 +2025-10-31 06:25:26.235198: Current learning rate: 0.00511 +2025-10-31 06:25:48.355171: train_loss -0.9872 +2025-10-31 06:25:48.363633: val_loss -0.897 +2025-10-31 06:25:48.365343: Pseudo dice [np.float32(0.9855), np.float32(0.9916), np.float32(0.9943), np.float32(0.7973)] +2025-10-31 06:25:48.367861: Epoch time: 22.13 s +2025-10-31 06:25:49.671391: +2025-10-31 06:25:49.674800: Epoch 527 +2025-10-31 06:25:49.677564: Current learning rate: 0.0051 +2025-10-31 06:26:11.669466: train_loss -0.9876 +2025-10-31 06:26:11.672499: val_loss -0.8874 +2025-10-31 06:26:11.674581: Pseudo dice [np.float32(0.9863), np.float32(0.992), np.float32(0.9942), np.float32(0.7635)] +2025-10-31 06:26:11.676071: Epoch time: 22.0 s +2025-10-31 06:26:12.799387: +2025-10-31 06:26:12.801206: Epoch 528 +2025-10-31 06:26:12.802669: Current learning rate: 0.00509 +2025-10-31 06:26:33.375175: train_loss -0.9884 +2025-10-31 06:26:33.380222: val_loss -0.8941 +2025-10-31 06:26:33.382027: Pseudo dice [np.float32(0.9842), np.float32(0.9904), np.float32(0.994), np.float32(0.7915)] +2025-10-31 06:26:33.383770: Epoch time: 20.58 s +2025-10-31 06:26:34.417055: +2025-10-31 06:26:34.419099: Epoch 529 +2025-10-31 06:26:34.420839: Current learning rate: 0.00508 +2025-10-31 06:26:56.965799: train_loss -0.989 +2025-10-31 06:26:56.967934: val_loss -0.8966 +2025-10-31 06:26:56.969472: Pseudo dice [np.float32(0.9861), np.float32(0.9916), np.float32(0.9944), np.float32(0.7945)] +2025-10-31 06:26:56.970878: Epoch time: 22.55 s +2025-10-31 06:26:57.968139: +2025-10-31 06:26:57.969746: Epoch 530 +2025-10-31 06:26:57.971230: Current learning rate: 0.00507 +2025-10-31 06:27:20.121438: train_loss -0.9892 +2025-10-31 06:27:20.126748: val_loss -0.8956 +2025-10-31 06:27:20.128851: Pseudo dice [np.float32(0.984), np.float32(0.9909), np.float32(0.9943), np.float32(0.7943)] +2025-10-31 06:27:20.130899: Epoch time: 22.16 s +2025-10-31 06:27:21.297117: +2025-10-31 06:27:21.299067: Epoch 531 +2025-10-31 06:27:21.301218: Current learning rate: 0.00506 +2025-10-31 06:27:42.577426: train_loss -0.9885 +2025-10-31 06:27:42.580916: val_loss -0.8982 +2025-10-31 06:27:42.582641: Pseudo dice [np.float32(0.986), np.float32(0.9915), np.float32(0.9939), np.float32(0.79)] +2025-10-31 06:27:42.584414: Epoch time: 21.28 s +2025-10-31 06:27:43.755829: +2025-10-31 06:27:43.757852: Epoch 532 +2025-10-31 06:27:43.759581: Current learning rate: 0.00505 +2025-10-31 06:28:06.200876: train_loss -0.9875 +2025-10-31 06:28:06.204250: val_loss -0.9018 +2025-10-31 06:28:06.206048: Pseudo dice [np.float32(0.9849), np.float32(0.991), np.float32(0.9946), np.float32(0.8143)] +2025-10-31 06:28:06.207747: Epoch time: 22.45 s +2025-10-31 06:28:07.430225: +2025-10-31 06:28:07.433064: Epoch 533 +2025-10-31 06:28:07.435460: Current learning rate: 0.00504 +2025-10-31 06:28:29.846932: train_loss -0.988 +2025-10-31 06:28:29.849509: val_loss -0.8981 +2025-10-31 06:28:29.851583: Pseudo dice [np.float32(0.9848), np.float32(0.9907), np.float32(0.9941), np.float32(0.8042)] +2025-10-31 06:28:29.853187: Epoch time: 22.42 s +2025-10-31 06:28:31.039426: +2025-10-31 06:28:31.041386: Epoch 534 +2025-10-31 06:28:31.043597: Current learning rate: 0.00503 +2025-10-31 06:28:51.563604: train_loss -0.9889 +2025-10-31 06:28:51.567885: val_loss -0.8946 +2025-10-31 06:28:51.572825: Pseudo dice [np.float32(0.9843), np.float32(0.9908), np.float32(0.9941), np.float32(0.7954)] +2025-10-31 06:28:51.576161: Epoch time: 20.53 s +2025-10-31 06:28:53.111135: +2025-10-31 06:28:53.112928: Epoch 535 +2025-10-31 06:28:53.114648: Current learning rate: 0.00502 +2025-10-31 06:29:15.494479: train_loss -0.9886 +2025-10-31 06:29:15.497258: val_loss -0.8903 +2025-10-31 06:29:15.498851: Pseudo dice [np.float32(0.9861), np.float32(0.9912), np.float32(0.994), np.float32(0.7801)] +2025-10-31 06:29:15.500424: Epoch time: 22.38 s +2025-10-31 06:29:16.700768: +2025-10-31 06:29:16.702654: Epoch 536 +2025-10-31 06:29:16.707255: Current learning rate: 0.00501 +2025-10-31 06:29:39.395853: train_loss -0.9893 +2025-10-31 06:29:39.400380: val_loss -0.8996 +2025-10-31 06:29:39.402279: Pseudo dice [np.float32(0.984), np.float32(0.9903), np.float32(0.9944), np.float32(0.8148)] +2025-10-31 06:29:39.404184: Epoch time: 22.7 s +2025-10-31 06:29:40.450908: +2025-10-31 06:29:40.452937: Epoch 537 +2025-10-31 06:29:40.454693: Current learning rate: 0.005 +2025-10-31 06:30:01.139688: train_loss -0.9891 +2025-10-31 06:30:01.142963: val_loss -0.8917 +2025-10-31 06:30:01.144904: Pseudo dice [np.float32(0.9849), np.float32(0.9918), np.float32(0.9938), np.float32(0.7843)] +2025-10-31 06:30:01.146748: Epoch time: 20.69 s +2025-10-31 06:30:02.449000: +2025-10-31 06:30:02.453868: Epoch 538 +2025-10-31 06:30:02.480394: Current learning rate: 0.00499 +2025-10-31 06:30:24.379789: train_loss -0.9888 +2025-10-31 06:30:24.383517: val_loss -0.8928 +2025-10-31 06:30:24.385232: Pseudo dice [np.float32(0.985), np.float32(0.9918), np.float32(0.994), np.float32(0.789)] +2025-10-31 06:30:24.387099: Epoch time: 21.93 s +2025-10-31 06:30:25.403849: +2025-10-31 06:30:25.405888: Epoch 539 +2025-10-31 06:30:25.407745: Current learning rate: 0.00498 +2025-10-31 06:30:47.772109: train_loss -0.9893 +2025-10-31 06:30:47.775097: val_loss -0.8953 +2025-10-31 06:30:47.777002: Pseudo dice [np.float32(0.9866), np.float32(0.9917), np.float32(0.9937), np.float32(0.7911)] +2025-10-31 06:30:47.778854: Epoch time: 22.37 s +2025-10-31 06:30:48.838505: +2025-10-31 06:30:48.840450: Epoch 540 +2025-10-31 06:30:48.842067: Current learning rate: 0.00497 +2025-10-31 06:31:10.507395: train_loss -0.9896 +2025-10-31 06:31:10.513927: val_loss -0.8849 +2025-10-31 06:31:10.515778: Pseudo dice [np.float32(0.985), np.float32(0.9917), np.float32(0.9939), np.float32(0.7666)] +2025-10-31 06:31:10.517610: Epoch time: 21.67 s +2025-10-31 06:31:11.786050: +2025-10-31 06:31:11.788011: Epoch 541 +2025-10-31 06:31:11.789759: Current learning rate: 0.00496 +2025-10-31 06:31:33.505603: train_loss -0.9887 +2025-10-31 06:31:33.508210: val_loss -0.8982 +2025-10-31 06:31:33.509931: Pseudo dice [np.float32(0.9851), np.float32(0.9914), np.float32(0.9939), np.float32(0.802)] +2025-10-31 06:31:33.511764: Epoch time: 21.72 s +2025-10-31 06:31:34.691555: +2025-10-31 06:31:34.693692: Epoch 542 +2025-10-31 06:31:34.695346: Current learning rate: 0.00495 +2025-10-31 06:31:57.092148: train_loss -0.9893 +2025-10-31 06:31:57.096577: val_loss -0.8903 +2025-10-31 06:31:57.098387: Pseudo dice [np.float32(0.9861), np.float32(0.9915), np.float32(0.9938), np.float32(0.7805)] +2025-10-31 06:31:57.100398: Epoch time: 22.4 s +2025-10-31 06:31:58.181098: +2025-10-31 06:31:58.183046: Epoch 543 +2025-10-31 06:31:58.184788: Current learning rate: 0.00494 +2025-10-31 06:32:20.612025: train_loss -0.9888 +2025-10-31 06:32:20.616056: val_loss -0.8893 +2025-10-31 06:32:20.617626: Pseudo dice [np.float32(0.9845), np.float32(0.9908), np.float32(0.9941), np.float32(0.7884)] +2025-10-31 06:32:20.619325: Epoch time: 22.43 s +2025-10-31 06:32:21.757486: +2025-10-31 06:32:21.759462: Epoch 544 +2025-10-31 06:32:21.761248: Current learning rate: 0.00493 +2025-10-31 06:32:43.010810: train_loss -0.9898 +2025-10-31 06:32:43.015022: val_loss -0.8929 +2025-10-31 06:32:43.016694: Pseudo dice [np.float32(0.9845), np.float32(0.9913), np.float32(0.9942), np.float32(0.7904)] +2025-10-31 06:32:43.018401: Epoch time: 21.26 s +2025-10-31 06:32:44.014248: +2025-10-31 06:32:44.015954: Epoch 545 +2025-10-31 06:32:44.017657: Current learning rate: 0.00492 +2025-10-31 06:33:05.603272: train_loss -0.99 +2025-10-31 06:33:05.605470: val_loss -0.8955 +2025-10-31 06:33:05.607169: Pseudo dice [np.float32(0.986), np.float32(0.9918), np.float32(0.9942), np.float32(0.7931)] +2025-10-31 06:33:05.608835: Epoch time: 21.59 s +2025-10-31 06:33:06.825683: +2025-10-31 06:33:06.827533: Epoch 546 +2025-10-31 06:33:06.829102: Current learning rate: 0.00491 +2025-10-31 06:33:28.791514: train_loss -0.9896 +2025-10-31 06:33:28.794879: val_loss -0.8959 +2025-10-31 06:33:28.796511: Pseudo dice [np.float32(0.9859), np.float32(0.9916), np.float32(0.9943), np.float32(0.802)] +2025-10-31 06:33:28.798116: Epoch time: 21.97 s +2025-10-31 06:33:30.225270: +2025-10-31 06:33:30.227355: Epoch 547 +2025-10-31 06:33:30.228865: Current learning rate: 0.0049 +2025-10-31 06:33:51.861923: train_loss -0.9899 +2025-10-31 06:33:51.864848: val_loss -0.8994 +2025-10-31 06:33:51.866980: Pseudo dice [np.float32(0.9844), np.float32(0.9912), np.float32(0.9947), np.float32(0.8096)] +2025-10-31 06:33:51.868775: Epoch time: 21.64 s +2025-10-31 06:33:52.938193: +2025-10-31 06:33:52.940501: Epoch 548 +2025-10-31 06:33:52.942995: Current learning rate: 0.00489 +2025-10-31 06:34:14.890431: train_loss -0.9893 +2025-10-31 06:34:14.892883: val_loss -0.8902 +2025-10-31 06:34:14.894692: Pseudo dice [np.float32(0.9844), np.float32(0.9916), np.float32(0.9942), np.float32(0.7847)] +2025-10-31 06:34:14.896425: Epoch time: 21.95 s +2025-10-31 06:34:16.118513: +2025-10-31 06:34:16.120516: Epoch 549 +2025-10-31 06:34:16.122319: Current learning rate: 0.00488 +2025-10-31 06:34:38.323713: train_loss -0.989 +2025-10-31 06:34:38.327034: val_loss -0.8925 +2025-10-31 06:34:38.328773: Pseudo dice [np.float32(0.9834), np.float32(0.9906), np.float32(0.9944), np.float32(0.7951)] +2025-10-31 06:34:38.331392: Epoch time: 22.21 s +2025-10-31 06:34:40.670854: +2025-10-31 06:34:40.672906: Epoch 550 +2025-10-31 06:34:40.674687: Current learning rate: 0.00487 +2025-10-31 06:35:02.133006: train_loss -0.9889 +2025-10-31 06:35:02.136570: val_loss -0.9022 +2025-10-31 06:35:02.138515: Pseudo dice [np.float32(0.9858), np.float32(0.9916), np.float32(0.9944), np.float32(0.8147)] +2025-10-31 06:35:02.140071: Epoch time: 21.46 s +2025-10-31 06:35:03.159027: +2025-10-31 06:35:03.160990: Epoch 551 +2025-10-31 06:35:03.162863: Current learning rate: 0.00486 +2025-10-31 06:35:25.169628: train_loss -0.9887 +2025-10-31 06:35:25.173241: val_loss -0.888 +2025-10-31 06:35:25.174911: Pseudo dice [np.float32(0.9838), np.float32(0.9905), np.float32(0.9936), np.float32(0.7767)] +2025-10-31 06:35:25.176651: Epoch time: 22.01 s +2025-10-31 06:35:26.402218: +2025-10-31 06:35:26.404149: Epoch 552 +2025-10-31 06:35:26.405778: Current learning rate: 0.00485 +2025-10-31 06:35:48.179046: train_loss -0.9898 +2025-10-31 06:35:48.183087: val_loss -0.8961 +2025-10-31 06:35:48.186492: Pseudo dice [np.float32(0.9853), np.float32(0.9906), np.float32(0.9943), np.float32(0.7989)] +2025-10-31 06:35:48.188408: Epoch time: 21.78 s +2025-10-31 06:35:49.278475: +2025-10-31 06:35:49.280773: Epoch 553 +2025-10-31 06:35:49.282399: Current learning rate: 0.00484 +2025-10-31 06:36:10.107751: train_loss -0.9902 +2025-10-31 06:36:10.110220: val_loss -0.8949 +2025-10-31 06:36:10.112456: Pseudo dice [np.float32(0.9848), np.float32(0.9914), np.float32(0.9941), np.float32(0.7969)] +2025-10-31 06:36:10.114844: Epoch time: 20.83 s +2025-10-31 06:36:11.276892: +2025-10-31 06:36:11.278654: Epoch 554 +2025-10-31 06:36:11.280393: Current learning rate: 0.00484 +2025-10-31 06:36:33.306780: train_loss -0.9896 +2025-10-31 06:36:33.309778: val_loss -0.8942 +2025-10-31 06:36:33.311467: Pseudo dice [np.float32(0.9847), np.float32(0.9912), np.float32(0.9944), np.float32(0.7904)] +2025-10-31 06:36:33.313022: Epoch time: 22.03 s +2025-10-31 06:36:34.528692: +2025-10-31 06:36:34.530736: Epoch 555 +2025-10-31 06:36:34.532363: Current learning rate: 0.00483 +2025-10-31 06:36:56.587396: train_loss -0.9909 +2025-10-31 06:36:56.591899: val_loss -0.8884 +2025-10-31 06:36:56.593734: Pseudo dice [np.float32(0.9855), np.float32(0.991), np.float32(0.9941), np.float32(0.7898)] +2025-10-31 06:36:56.595491: Epoch time: 22.06 s +2025-10-31 06:36:57.811640: +2025-10-31 06:36:57.813708: Epoch 556 +2025-10-31 06:36:57.815715: Current learning rate: 0.00482 +2025-10-31 06:37:18.141636: train_loss -0.9901 +2025-10-31 06:37:18.143968: val_loss -0.906 +2025-10-31 06:37:18.145684: Pseudo dice [np.float32(0.9868), np.float32(0.9925), np.float32(0.9949), np.float32(0.8073)] +2025-10-31 06:37:18.147282: Epoch time: 20.33 s +2025-10-31 06:37:19.201853: +2025-10-31 06:37:19.203923: Epoch 557 +2025-10-31 06:37:19.205559: Current learning rate: 0.00481 +2025-10-31 06:37:41.722362: train_loss -0.9895 +2025-10-31 06:37:41.725596: val_loss -0.895 +2025-10-31 06:37:41.727879: Pseudo dice [np.float32(0.9871), np.float32(0.9925), np.float32(0.994), np.float32(0.8011)] +2025-10-31 06:37:41.729811: Epoch time: 22.52 s +2025-10-31 06:37:42.913468: +2025-10-31 06:37:42.915590: Epoch 558 +2025-10-31 06:37:42.917436: Current learning rate: 0.0048 +2025-10-31 06:38:05.016294: train_loss -0.9903 +2025-10-31 06:38:05.019974: val_loss -0.8993 +2025-10-31 06:38:05.021683: Pseudo dice [np.float32(0.9859), np.float32(0.991), np.float32(0.9941), np.float32(0.8111)] +2025-10-31 06:38:05.023498: Epoch time: 22.1 s +2025-10-31 06:38:06.664680: +2025-10-31 06:38:06.666614: Epoch 559 +2025-10-31 06:38:06.670046: Current learning rate: 0.00479 +2025-10-31 06:38:27.213110: train_loss -0.9902 +2025-10-31 06:38:27.215918: val_loss -0.8906 +2025-10-31 06:38:27.217695: Pseudo dice [np.float32(0.9834), np.float32(0.9908), np.float32(0.9945), np.float32(0.796)] +2025-10-31 06:38:27.219404: Epoch time: 20.55 s +2025-10-31 06:38:28.251050: +2025-10-31 06:38:28.253179: Epoch 560 +2025-10-31 06:38:28.255193: Current learning rate: 0.00478 +2025-10-31 06:38:50.437600: train_loss -0.99 +2025-10-31 06:38:50.440869: val_loss -0.8964 +2025-10-31 06:38:50.443466: Pseudo dice [np.float32(0.987), np.float32(0.9916), np.float32(0.9943), np.float32(0.7964)] +2025-10-31 06:38:50.445712: Epoch time: 22.19 s +2025-10-31 06:38:51.730928: +2025-10-31 06:38:51.733054: Epoch 561 +2025-10-31 06:38:51.734866: Current learning rate: 0.00477 +2025-10-31 06:39:13.401020: train_loss -0.9896 +2025-10-31 06:39:13.404922: val_loss -0.898 +2025-10-31 06:39:13.407632: Pseudo dice [np.float32(0.9863), np.float32(0.9919), np.float32(0.9944), np.float32(0.8026)] +2025-10-31 06:39:13.409513: Epoch time: 21.67 s +2025-10-31 06:39:14.568457: +2025-10-31 06:39:14.570894: Epoch 562 +2025-10-31 06:39:14.573237: Current learning rate: 0.00476 +2025-10-31 06:39:36.378827: train_loss -0.9891 +2025-10-31 06:39:36.382570: val_loss -0.8975 +2025-10-31 06:39:36.384633: Pseudo dice [np.float32(0.9865), np.float32(0.9922), np.float32(0.9943), np.float32(0.8041)] +2025-10-31 06:39:36.386460: Epoch time: 21.81 s +2025-10-31 06:39:37.391153: +2025-10-31 06:39:37.393072: Epoch 563 +2025-10-31 06:39:37.394890: Current learning rate: 0.00475 +2025-10-31 06:39:58.083385: train_loss -0.9896 +2025-10-31 06:39:58.085781: val_loss -0.888 +2025-10-31 06:39:58.087764: Pseudo dice [np.float32(0.9862), np.float32(0.9916), np.float32(0.994), np.float32(0.7807)] +2025-10-31 06:39:58.089312: Epoch time: 20.69 s +2025-10-31 06:39:59.294206: +2025-10-31 06:39:59.296414: Epoch 564 +2025-10-31 06:39:59.297971: Current learning rate: 0.00474 +2025-10-31 06:40:21.091714: train_loss -0.9897 +2025-10-31 06:40:21.094954: val_loss -0.8882 +2025-10-31 06:40:21.096740: Pseudo dice [np.float32(0.9858), np.float32(0.9912), np.float32(0.994), np.float32(0.7774)] +2025-10-31 06:40:21.098337: Epoch time: 21.8 s +2025-10-31 06:40:22.571539: +2025-10-31 06:40:22.573700: Epoch 565 +2025-10-31 06:40:22.575556: Current learning rate: 0.00473 +2025-10-31 06:40:43.247044: train_loss -0.9899 +2025-10-31 06:40:43.251081: val_loss -0.8807 +2025-10-31 06:40:43.253696: Pseudo dice [np.float32(0.9856), np.float32(0.991), np.float32(0.9939), np.float32(0.7645)] +2025-10-31 06:40:43.256052: Epoch time: 20.68 s +2025-10-31 06:40:44.467145: +2025-10-31 06:40:44.469822: Epoch 566 +2025-10-31 06:40:44.472932: Current learning rate: 0.00472 +2025-10-31 06:41:06.827237: train_loss -0.9905 +2025-10-31 06:41:06.835327: val_loss -0.892 +2025-10-31 06:41:06.836839: Pseudo dice [np.float32(0.9849), np.float32(0.991), np.float32(0.9942), np.float32(0.8015)] +2025-10-31 06:41:06.838479: Epoch time: 22.36 s +2025-10-31 06:41:08.074148: +2025-10-31 06:41:08.076120: Epoch 567 +2025-10-31 06:41:08.077814: Current learning rate: 0.00471 +2025-10-31 06:41:30.479699: train_loss -0.9906 +2025-10-31 06:41:30.483511: val_loss -0.8967 +2025-10-31 06:41:30.484948: Pseudo dice [np.float32(0.9856), np.float32(0.9912), np.float32(0.9945), np.float32(0.7993)] +2025-10-31 06:41:30.486336: Epoch time: 22.41 s +2025-10-31 06:41:31.811379: +2025-10-31 06:41:31.813564: Epoch 568 +2025-10-31 06:41:31.815336: Current learning rate: 0.0047 +2025-10-31 06:41:54.031085: train_loss -0.9905 +2025-10-31 06:41:54.033632: val_loss -0.8942 +2025-10-31 06:41:54.035373: Pseudo dice [np.float32(0.9872), np.float32(0.9923), np.float32(0.9943), np.float32(0.7912)] +2025-10-31 06:41:54.037045: Epoch time: 22.22 s +2025-10-31 06:41:55.147983: +2025-10-31 06:41:55.150043: Epoch 569 +2025-10-31 06:41:55.152549: Current learning rate: 0.00469 +2025-10-31 06:42:16.785780: train_loss -0.9904 +2025-10-31 06:42:16.789875: val_loss -0.8967 +2025-10-31 06:42:16.792379: Pseudo dice [np.float32(0.9854), np.float32(0.9911), np.float32(0.9944), np.float32(0.8012)] +2025-10-31 06:42:16.794157: Epoch time: 21.64 s +2025-10-31 06:42:17.819403: +2025-10-31 06:42:17.821721: Epoch 570 +2025-10-31 06:42:17.823616: Current learning rate: 0.00468 +2025-10-31 06:42:40.377191: train_loss -0.9908 +2025-10-31 06:42:40.382077: val_loss -0.8973 +2025-10-31 06:42:40.384745: Pseudo dice [np.float32(0.987), np.float32(0.9913), np.float32(0.9945), np.float32(0.8042)] +2025-10-31 06:42:40.387579: Epoch time: 22.56 s +2025-10-31 06:42:41.625543: +2025-10-31 06:42:41.627456: Epoch 571 +2025-10-31 06:42:41.629058: Current learning rate: 0.00467 +2025-10-31 06:43:02.745888: train_loss -0.9901 +2025-10-31 06:43:02.750763: val_loss -0.8894 +2025-10-31 06:43:02.752778: Pseudo dice [np.float32(0.9839), np.float32(0.9904), np.float32(0.9942), np.float32(0.7959)] +2025-10-31 06:43:02.754696: Epoch time: 21.12 s +2025-10-31 06:43:04.337349: +2025-10-31 06:43:04.338889: Epoch 572 +2025-10-31 06:43:04.341226: Current learning rate: 0.00466 +2025-10-31 06:43:26.683560: train_loss -0.9901 +2025-10-31 06:43:26.687378: val_loss -0.8978 +2025-10-31 06:43:26.689132: Pseudo dice [np.float32(0.987), np.float32(0.9923), np.float32(0.9947), np.float32(0.8)] +2025-10-31 06:43:26.690791: Epoch time: 22.35 s +2025-10-31 06:43:27.926221: +2025-10-31 06:43:27.928176: Epoch 573 +2025-10-31 06:43:27.929818: Current learning rate: 0.00465 +2025-10-31 06:43:49.938583: train_loss -0.9906 +2025-10-31 06:43:49.941892: val_loss -0.8968 +2025-10-31 06:43:49.943782: Pseudo dice [np.float32(0.9865), np.float32(0.9913), np.float32(0.9944), np.float32(0.807)] +2025-10-31 06:43:49.945794: Epoch time: 22.01 s +2025-10-31 06:43:51.160265: +2025-10-31 06:43:51.162544: Epoch 574 +2025-10-31 06:43:51.164371: Current learning rate: 0.00464 +2025-10-31 06:44:13.031167: train_loss -0.9902 +2025-10-31 06:44:13.035431: val_loss -0.9024 +2025-10-31 06:44:13.036859: Pseudo dice [np.float32(0.9875), np.float32(0.9926), np.float32(0.9952), np.float32(0.8075)] +2025-10-31 06:44:13.038454: Epoch time: 21.87 s +2025-10-31 06:44:14.125265: +2025-10-31 06:44:14.127497: Epoch 575 +2025-10-31 06:44:14.129551: Current learning rate: 0.00463 +2025-10-31 06:44:36.435848: train_loss -0.9906 +2025-10-31 06:44:36.441118: val_loss -0.8938 +2025-10-31 06:44:36.442640: Pseudo dice [np.float32(0.9862), np.float32(0.9906), np.float32(0.9941), np.float32(0.7993)] +2025-10-31 06:44:36.444185: Epoch time: 22.31 s +2025-10-31 06:44:37.464496: +2025-10-31 06:44:37.466420: Epoch 576 +2025-10-31 06:44:37.468408: Current learning rate: 0.00462 +2025-10-31 06:44:59.081569: train_loss -0.9907 +2025-10-31 06:44:59.085446: val_loss -0.8968 +2025-10-31 06:44:59.087501: Pseudo dice [np.float32(0.9864), np.float32(0.9918), np.float32(0.9944), np.float32(0.7982)] +2025-10-31 06:44:59.089738: Epoch time: 21.62 s +2025-10-31 06:45:00.209597: +2025-10-31 06:45:00.211775: Epoch 577 +2025-10-31 06:45:00.213605: Current learning rate: 0.00461 +2025-10-31 06:45:21.004608: train_loss -0.9907 +2025-10-31 06:45:21.007655: val_loss -0.8892 +2025-10-31 06:45:21.013521: Pseudo dice [np.float32(0.9858), np.float32(0.9908), np.float32(0.9941), np.float32(0.7852)] +2025-10-31 06:45:21.015186: Epoch time: 20.8 s +2025-10-31 06:45:22.070655: +2025-10-31 06:45:22.072475: Epoch 578 +2025-10-31 06:45:22.074265: Current learning rate: 0.0046 +2025-10-31 06:45:44.790686: train_loss -0.9911 +2025-10-31 06:45:44.793889: val_loss -0.8962 +2025-10-31 06:45:44.796035: Pseudo dice [np.float32(0.9855), np.float32(0.9914), np.float32(0.9946), np.float32(0.8062)] +2025-10-31 06:45:44.798546: Epoch time: 22.72 s +2025-10-31 06:45:45.874382: +2025-10-31 06:45:45.876490: Epoch 579 +2025-10-31 06:45:45.878125: Current learning rate: 0.00459 +2025-10-31 06:46:08.322005: train_loss -0.9899 +2025-10-31 06:46:08.326682: val_loss -0.8995 +2025-10-31 06:46:08.328838: Pseudo dice [np.float32(0.9851), np.float32(0.9914), np.float32(0.995), np.float32(0.8123)] +2025-10-31 06:46:08.331508: Epoch time: 22.45 s +2025-10-31 06:46:09.504495: +2025-10-31 06:46:09.506451: Epoch 580 +2025-10-31 06:46:09.508071: Current learning rate: 0.00458 +2025-10-31 06:46:31.275282: train_loss -0.9906 +2025-10-31 06:46:31.279018: val_loss -0.8936 +2025-10-31 06:46:31.280994: Pseudo dice [np.float32(0.9868), np.float32(0.9913), np.float32(0.9944), np.float32(0.8078)] +2025-10-31 06:46:31.283000: Epoch time: 21.77 s +2025-10-31 06:46:32.493651: +2025-10-31 06:46:32.496397: Epoch 581 +2025-10-31 06:46:32.498279: Current learning rate: 0.00457 +2025-10-31 06:46:54.758143: train_loss -0.99 +2025-10-31 06:46:54.761032: val_loss -0.8932 +2025-10-31 06:46:54.762710: Pseudo dice [np.float32(0.9864), np.float32(0.9917), np.float32(0.9944), np.float32(0.7913)] +2025-10-31 06:46:54.764307: Epoch time: 22.27 s +2025-10-31 06:46:55.803894: +2025-10-31 06:46:55.806246: Epoch 582 +2025-10-31 06:46:55.808477: Current learning rate: 0.00456 +2025-10-31 06:47:17.122671: train_loss -0.9899 +2025-10-31 06:47:17.125307: val_loss -0.8942 +2025-10-31 06:47:17.127802: Pseudo dice [np.float32(0.9857), np.float32(0.992), np.float32(0.9946), np.float32(0.7891)] +2025-10-31 06:47:17.129536: Epoch time: 21.32 s +2025-10-31 06:47:18.222869: +2025-10-31 06:47:18.225096: Epoch 583 +2025-10-31 06:47:18.226783: Current learning rate: 0.00455 +2025-10-31 06:47:39.371803: train_loss -0.9901 +2025-10-31 06:47:39.375292: val_loss -0.8943 +2025-10-31 06:47:39.377170: Pseudo dice [np.float32(0.9854), np.float32(0.9908), np.float32(0.9942), np.float32(0.8008)] +2025-10-31 06:47:39.378922: Epoch time: 21.15 s +2025-10-31 06:47:41.032046: +2025-10-31 06:47:41.034176: Epoch 584 +2025-10-31 06:47:41.036192: Current learning rate: 0.00454 +2025-10-31 06:48:03.717487: train_loss -0.9894 +2025-10-31 06:48:03.721902: val_loss -0.8905 +2025-10-31 06:48:03.724533: Pseudo dice [np.float32(0.9868), np.float32(0.9915), np.float32(0.994), np.float32(0.7798)] +2025-10-31 06:48:03.726066: Epoch time: 22.69 s +2025-10-31 06:48:04.805439: +2025-10-31 06:48:04.807404: Epoch 585 +2025-10-31 06:48:04.809168: Current learning rate: 0.00453 +2025-10-31 06:48:27.243525: train_loss -0.9895 +2025-10-31 06:48:27.246284: val_loss -0.8892 +2025-10-31 06:48:27.247819: Pseudo dice [np.float32(0.9855), np.float32(0.9915), np.float32(0.9939), np.float32(0.7952)] +2025-10-31 06:48:27.249228: Epoch time: 22.44 s +2025-10-31 06:48:28.290502: +2025-10-31 06:48:28.292395: Epoch 586 +2025-10-31 06:48:28.293946: Current learning rate: 0.00452 +2025-10-31 06:48:50.182537: train_loss -0.9902 +2025-10-31 06:48:50.185097: val_loss -0.8878 +2025-10-31 06:48:50.186616: Pseudo dice [np.float32(0.9845), np.float32(0.9903), np.float32(0.994), np.float32(0.7908)] +2025-10-31 06:48:50.188276: Epoch time: 21.89 s +2025-10-31 06:48:51.510142: +2025-10-31 06:48:51.512108: Epoch 587 +2025-10-31 06:48:51.513634: Current learning rate: 0.00451 +2025-10-31 06:49:13.332916: train_loss -0.9911 +2025-10-31 06:49:13.335588: val_loss -0.8881 +2025-10-31 06:49:13.338047: Pseudo dice [np.float32(0.9839), np.float32(0.9913), np.float32(0.9945), np.float32(0.7824)] +2025-10-31 06:49:13.340835: Epoch time: 21.82 s +2025-10-31 06:49:14.404051: +2025-10-31 06:49:14.406023: Epoch 588 +2025-10-31 06:49:14.407545: Current learning rate: 0.0045 +2025-10-31 06:49:36.382812: train_loss -0.9907 +2025-10-31 06:49:36.385212: val_loss -0.8974 +2025-10-31 06:49:36.386688: Pseudo dice [np.float32(0.9873), np.float32(0.9924), np.float32(0.9946), np.float32(0.7939)] +2025-10-31 06:49:36.388172: Epoch time: 21.98 s +2025-10-31 06:49:37.408803: +2025-10-31 06:49:37.410580: Epoch 589 +2025-10-31 06:49:37.411946: Current learning rate: 0.00449 +2025-10-31 06:49:59.428756: train_loss -0.9908 +2025-10-31 06:49:59.431484: val_loss -0.894 +2025-10-31 06:49:59.433427: Pseudo dice [np.float32(0.9863), np.float32(0.9917), np.float32(0.9943), np.float32(0.788)] +2025-10-31 06:49:59.436260: Epoch time: 22.02 s +2025-10-31 06:50:00.516638: +2025-10-31 06:50:00.519494: Epoch 590 +2025-10-31 06:50:00.521630: Current learning rate: 0.00448 +2025-10-31 06:50:22.390120: train_loss -0.9906 +2025-10-31 06:50:22.393904: val_loss -0.889 +2025-10-31 06:50:22.395736: Pseudo dice [np.float32(0.9858), np.float32(0.9919), np.float32(0.9941), np.float32(0.7785)] +2025-10-31 06:50:22.397532: Epoch time: 21.88 s +2025-10-31 06:50:23.697208: +2025-10-31 06:50:23.699304: Epoch 591 +2025-10-31 06:50:23.701158: Current learning rate: 0.00447 +2025-10-31 06:50:45.977050: train_loss -0.9899 +2025-10-31 06:50:45.980175: val_loss -0.8933 +2025-10-31 06:50:45.982204: Pseudo dice [np.float32(0.9865), np.float32(0.9915), np.float32(0.9942), np.float32(0.7969)] +2025-10-31 06:50:45.983945: Epoch time: 22.28 s +2025-10-31 06:50:47.188487: +2025-10-31 06:50:47.190451: Epoch 592 +2025-10-31 06:50:47.192147: Current learning rate: 0.00446 +2025-10-31 06:51:09.686691: train_loss -0.9907 +2025-10-31 06:51:09.689840: val_loss -0.8909 +2025-10-31 06:51:09.691593: Pseudo dice [np.float32(0.9868), np.float32(0.9925), np.float32(0.9942), np.float32(0.7787)] +2025-10-31 06:51:09.693194: Epoch time: 22.5 s +2025-10-31 06:51:10.915602: +2025-10-31 06:51:10.917547: Epoch 593 +2025-10-31 06:51:10.919236: Current learning rate: 0.00445 +2025-10-31 06:51:32.772699: train_loss -0.9905 +2025-10-31 06:51:32.776267: val_loss -0.888 +2025-10-31 06:51:32.777962: Pseudo dice [np.float32(0.9838), np.float32(0.9904), np.float32(0.9944), np.float32(0.7853)] +2025-10-31 06:51:32.779589: Epoch time: 21.86 s +2025-10-31 06:51:33.984101: +2025-10-31 06:51:33.986541: Epoch 594 +2025-10-31 06:51:33.989017: Current learning rate: 0.00444 +2025-10-31 06:51:56.171644: train_loss -0.9904 +2025-10-31 06:51:56.175715: val_loss -0.893 +2025-10-31 06:51:56.177538: Pseudo dice [np.float32(0.9859), np.float32(0.9917), np.float32(0.9942), np.float32(0.7984)] +2025-10-31 06:51:56.179505: Epoch time: 22.19 s +2025-10-31 06:51:57.226924: +2025-10-31 06:51:57.228840: Epoch 595 +2025-10-31 06:51:57.230999: Current learning rate: 0.00443 +2025-10-31 06:52:16.481751: train_loss -0.9903 +2025-10-31 06:52:16.486044: val_loss -0.8885 +2025-10-31 06:52:16.487678: Pseudo dice [np.float32(0.9848), np.float32(0.9905), np.float32(0.9946), np.float32(0.7888)] +2025-10-31 06:52:16.489192: Epoch time: 19.26 s +2025-10-31 06:52:17.936701: +2025-10-31 06:52:17.938543: Epoch 596 +2025-10-31 06:52:17.940289: Current learning rate: 0.00442 +2025-10-31 06:52:40.324084: train_loss -0.9906 +2025-10-31 06:52:40.326720: val_loss -0.8892 +2025-10-31 06:52:40.328637: Pseudo dice [np.float32(0.9859), np.float32(0.9903), np.float32(0.9938), np.float32(0.7932)] +2025-10-31 06:52:40.330359: Epoch time: 22.39 s +2025-10-31 06:52:41.659354: +2025-10-31 06:52:41.661490: Epoch 597 +2025-10-31 06:52:41.663212: Current learning rate: 0.00441 +2025-10-31 06:53:03.775927: train_loss -0.9902 +2025-10-31 06:53:03.778788: val_loss -0.8878 +2025-10-31 06:53:03.780843: Pseudo dice [np.float32(0.9855), np.float32(0.9913), np.float32(0.9941), np.float32(0.7805)] +2025-10-31 06:53:03.782753: Epoch time: 22.12 s +2025-10-31 06:53:04.844841: +2025-10-31 06:53:04.847694: Epoch 598 +2025-10-31 06:53:04.850587: Current learning rate: 0.0044 +2025-10-31 06:53:26.714946: train_loss -0.9903 +2025-10-31 06:53:26.718762: val_loss -0.8935 +2025-10-31 06:53:26.720792: Pseudo dice [np.float32(0.9867), np.float32(0.9919), np.float32(0.9947), np.float32(0.792)] +2025-10-31 06:53:26.722773: Epoch time: 21.87 s +2025-10-31 06:53:27.811044: +2025-10-31 06:53:27.812886: Epoch 599 +2025-10-31 06:53:27.814344: Current learning rate: 0.00439 +2025-10-31 06:53:50.242097: train_loss -0.99 +2025-10-31 06:53:50.244781: val_loss -0.8878 +2025-10-31 06:53:50.246540: Pseudo dice [np.float32(0.9854), np.float32(0.9908), np.float32(0.9941), np.float32(0.7874)] +2025-10-31 06:53:50.248347: Epoch time: 22.43 s +2025-10-31 06:53:52.949316: +2025-10-31 06:53:52.951486: Epoch 600 +2025-10-31 06:53:52.953315: Current learning rate: 0.00438 +2025-10-31 06:54:14.909698: train_loss -0.9902 +2025-10-31 06:54:14.914923: val_loss -0.8896 +2025-10-31 06:54:14.917500: Pseudo dice [np.float32(0.9858), np.float32(0.9911), np.float32(0.994), np.float32(0.791)] +2025-10-31 06:54:14.919634: Epoch time: 21.96 s +2025-10-31 06:54:16.057516: +2025-10-31 06:54:16.059870: Epoch 601 +2025-10-31 06:54:16.061816: Current learning rate: 0.00437 +2025-10-31 06:54:36.448840: train_loss -0.9892 +2025-10-31 06:54:36.451886: val_loss -0.887 +2025-10-31 06:54:36.453768: Pseudo dice [np.float32(0.9861), np.float32(0.9915), np.float32(0.9938), np.float32(0.7711)] +2025-10-31 06:54:36.455396: Epoch time: 20.39 s +2025-10-31 06:54:37.492676: +2025-10-31 06:54:37.495003: Epoch 602 +2025-10-31 06:54:37.496831: Current learning rate: 0.00436 +2025-10-31 06:54:59.488153: train_loss -0.9895 +2025-10-31 06:54:59.491215: val_loss -0.9031 +2025-10-31 06:54:59.492850: Pseudo dice [np.float32(0.9855), np.float32(0.992), np.float32(0.9946), np.float32(0.8144)] +2025-10-31 06:54:59.494502: Epoch time: 22.0 s +2025-10-31 06:55:00.619745: +2025-10-31 06:55:00.622153: Epoch 603 +2025-10-31 06:55:00.623842: Current learning rate: 0.00435 +2025-10-31 06:55:22.628684: train_loss -0.991 +2025-10-31 06:55:22.632080: val_loss -0.8969 +2025-10-31 06:55:22.633983: Pseudo dice [np.float32(0.9845), np.float32(0.9911), np.float32(0.9944), np.float32(0.8098)] +2025-10-31 06:55:22.635637: Epoch time: 22.01 s +2025-10-31 06:55:23.762492: +2025-10-31 06:55:23.764525: Epoch 604 +2025-10-31 06:55:23.766247: Current learning rate: 0.00434 +2025-10-31 06:55:46.026082: train_loss -0.9908 +2025-10-31 06:55:46.032796: val_loss -0.8892 +2025-10-31 06:55:46.035318: Pseudo dice [np.float32(0.9869), np.float32(0.9916), np.float32(0.994), np.float32(0.7739)] +2025-10-31 06:55:46.037494: Epoch time: 22.27 s +2025-10-31 06:55:47.269213: +2025-10-31 06:55:47.271596: Epoch 605 +2025-10-31 06:55:47.273520: Current learning rate: 0.00433 +2025-10-31 06:56:09.767014: train_loss -0.9898 +2025-10-31 06:56:09.769722: val_loss -0.8909 +2025-10-31 06:56:09.771424: Pseudo dice [np.float32(0.9847), np.float32(0.9912), np.float32(0.9941), np.float32(0.7882)] +2025-10-31 06:56:09.773154: Epoch time: 22.5 s +2025-10-31 06:56:10.823009: +2025-10-31 06:56:10.824990: Epoch 606 +2025-10-31 06:56:10.826683: Current learning rate: 0.00432 +2025-10-31 06:56:32.521394: train_loss -0.99 +2025-10-31 06:56:32.524348: val_loss -0.8928 +2025-10-31 06:56:32.525979: Pseudo dice [np.float32(0.9843), np.float32(0.9915), np.float32(0.9942), np.float32(0.7945)] +2025-10-31 06:56:32.527546: Epoch time: 21.7 s +2025-10-31 06:56:33.641268: +2025-10-31 06:56:33.643085: Epoch 607 +2025-10-31 06:56:33.644634: Current learning rate: 0.00431 +2025-10-31 06:56:54.717281: train_loss -0.9904 +2025-10-31 06:56:54.722539: val_loss -0.8925 +2025-10-31 06:56:54.724239: Pseudo dice [np.float32(0.986), np.float32(0.991), np.float32(0.9942), np.float32(0.7936)] +2025-10-31 06:56:54.725848: Epoch time: 21.08 s +2025-10-31 06:56:56.449869: +2025-10-31 06:56:56.452049: Epoch 608 +2025-10-31 06:56:56.453812: Current learning rate: 0.0043 +2025-10-31 06:57:17.529835: train_loss -0.9903 +2025-10-31 06:57:17.532362: val_loss -0.8864 +2025-10-31 06:57:17.534413: Pseudo dice [np.float32(0.985), np.float32(0.9914), np.float32(0.9941), np.float32(0.7841)] +2025-10-31 06:57:17.536131: Epoch time: 21.08 s +2025-10-31 06:57:18.720086: +2025-10-31 06:57:18.722426: Epoch 609 +2025-10-31 06:57:18.724251: Current learning rate: 0.00429 +2025-10-31 06:57:41.079777: train_loss -0.9908 +2025-10-31 06:57:41.082658: val_loss -0.8929 +2025-10-31 06:57:41.084092: Pseudo dice [np.float32(0.9873), np.float32(0.992), np.float32(0.9944), np.float32(0.7887)] +2025-10-31 06:57:41.085461: Epoch time: 22.36 s +2025-10-31 06:57:42.327127: +2025-10-31 06:57:42.329298: Epoch 610 +2025-10-31 06:57:42.330914: Current learning rate: 0.00429 +2025-10-31 06:58:04.401951: train_loss -0.9911 +2025-10-31 06:58:04.405592: val_loss -0.8889 +2025-10-31 06:58:04.409063: Pseudo dice [np.float32(0.9869), np.float32(0.9913), np.float32(0.994), np.float32(0.7866)] +2025-10-31 06:58:04.412350: Epoch time: 22.08 s +2025-10-31 06:58:05.707647: +2025-10-31 06:58:05.709572: Epoch 611 +2025-10-31 06:58:05.711280: Current learning rate: 0.00428 +2025-10-31 06:58:28.286270: train_loss -0.9897 +2025-10-31 06:58:28.290547: val_loss -0.8868 +2025-10-31 06:58:28.292833: Pseudo dice [np.float32(0.9854), np.float32(0.9902), np.float32(0.9943), np.float32(0.7928)] +2025-10-31 06:58:28.294682: Epoch time: 22.58 s +2025-10-31 06:58:29.346591: +2025-10-31 06:58:29.348858: Epoch 612 +2025-10-31 06:58:29.350873: Current learning rate: 0.00427 +2025-10-31 06:58:51.641105: train_loss -0.9905 +2025-10-31 06:58:51.644248: val_loss -0.8911 +2025-10-31 06:58:51.646112: Pseudo dice [np.float32(0.9842), np.float32(0.991), np.float32(0.9941), np.float32(0.7946)] +2025-10-31 06:58:51.647780: Epoch time: 22.3 s +2025-10-31 06:58:52.704637: +2025-10-31 06:58:52.707413: Epoch 613 +2025-10-31 06:58:52.709741: Current learning rate: 0.00426 +2025-10-31 06:59:14.338423: train_loss -0.991 +2025-10-31 06:59:14.343020: val_loss -0.9001 +2025-10-31 06:59:14.345670: Pseudo dice [np.float32(0.9868), np.float32(0.9922), np.float32(0.995), np.float32(0.8162)] +2025-10-31 06:59:14.348183: Epoch time: 21.64 s +2025-10-31 06:59:15.461712: +2025-10-31 06:59:15.463949: Epoch 614 +2025-10-31 06:59:15.465822: Current learning rate: 0.00425 +2025-10-31 06:59:36.720798: train_loss -0.9906 +2025-10-31 06:59:36.723279: val_loss -0.8881 +2025-10-31 06:59:36.726075: Pseudo dice [np.float32(0.9861), np.float32(0.9916), np.float32(0.9943), np.float32(0.7846)] +2025-10-31 06:59:36.728546: Epoch time: 21.26 s +2025-10-31 06:59:37.792646: +2025-10-31 06:59:37.801356: Epoch 615 +2025-10-31 06:59:37.804213: Current learning rate: 0.00424 +2025-10-31 07:00:00.654924: train_loss -0.9901 +2025-10-31 07:00:00.661145: val_loss -0.8926 +2025-10-31 07:00:00.664506: Pseudo dice [np.float32(0.9843), np.float32(0.9911), np.float32(0.9944), np.float32(0.796)] +2025-10-31 07:00:00.682616: Epoch time: 22.86 s +2025-10-31 07:00:01.738605: +2025-10-31 07:00:01.740175: Epoch 616 +2025-10-31 07:00:01.741569: Current learning rate: 0.00423 +2025-10-31 07:00:23.908247: train_loss -0.9905 +2025-10-31 07:00:23.912897: val_loss -0.8923 +2025-10-31 07:00:23.915116: Pseudo dice [np.float32(0.9866), np.float32(0.9916), np.float32(0.9943), np.float32(0.7993)] +2025-10-31 07:00:23.918242: Epoch time: 22.17 s +2025-10-31 07:00:25.223741: +2025-10-31 07:00:25.228231: Epoch 617 +2025-10-31 07:00:25.231262: Current learning rate: 0.00422 +2025-10-31 07:00:47.373826: train_loss -0.9909 +2025-10-31 07:00:47.377468: val_loss -0.8867 +2025-10-31 07:00:47.379172: Pseudo dice [np.float32(0.9863), np.float32(0.9917), np.float32(0.9941), np.float32(0.7772)] +2025-10-31 07:00:47.381317: Epoch time: 22.15 s +2025-10-31 07:00:48.470659: +2025-10-31 07:00:48.473672: Epoch 618 +2025-10-31 07:00:48.476381: Current learning rate: 0.00421 +2025-10-31 07:01:11.061718: train_loss -0.9911 +2025-10-31 07:01:11.067615: val_loss -0.8916 +2025-10-31 07:01:11.070251: Pseudo dice [np.float32(0.9858), np.float32(0.9911), np.float32(0.9942), np.float32(0.7935)] +2025-10-31 07:01:11.072976: Epoch time: 22.59 s +2025-10-31 07:01:12.285799: +2025-10-31 07:01:12.288186: Epoch 619 +2025-10-31 07:01:12.290166: Current learning rate: 0.0042 +2025-10-31 07:01:33.479350: train_loss -0.9915 +2025-10-31 07:01:33.488581: val_loss -0.8947 +2025-10-31 07:01:33.491224: Pseudo dice [np.float32(0.9865), np.float32(0.992), np.float32(0.9945), np.float32(0.8031)] +2025-10-31 07:01:33.494102: Epoch time: 21.2 s +2025-10-31 07:01:34.706430: +2025-10-31 07:01:34.718784: Epoch 620 +2025-10-31 07:01:34.734568: Current learning rate: 0.00419 +2025-10-31 07:01:57.317138: train_loss -0.991 +2025-10-31 07:01:57.322323: val_loss -0.8936 +2025-10-31 07:01:57.326416: Pseudo dice [np.float32(0.9877), np.float32(0.9921), np.float32(0.9943), np.float32(0.792)] +2025-10-31 07:01:57.330029: Epoch time: 22.61 s +2025-10-31 07:01:59.454533: +2025-10-31 07:01:59.459852: Epoch 621 +2025-10-31 07:01:59.464055: Current learning rate: 0.00418 +2025-10-31 07:02:21.870187: train_loss -0.9911 +2025-10-31 07:02:21.881210: val_loss -0.898 +2025-10-31 07:02:21.892981: Pseudo dice [np.float32(0.9865), np.float32(0.9921), np.float32(0.9944), np.float32(0.8038)] +2025-10-31 07:02:21.896065: Epoch time: 22.42 s +2025-10-31 07:02:23.035191: +2025-10-31 07:02:23.037616: Epoch 622 +2025-10-31 07:02:23.039632: Current learning rate: 0.00417 +2025-10-31 07:02:45.437293: train_loss -0.991 +2025-10-31 07:02:45.441594: val_loss -0.895 +2025-10-31 07:02:45.443397: Pseudo dice [np.float32(0.9847), np.float32(0.991), np.float32(0.994), np.float32(0.8109)] +2025-10-31 07:02:45.444975: Epoch time: 22.4 s +2025-10-31 07:02:46.832530: +2025-10-31 07:02:46.835286: Epoch 623 +2025-10-31 07:02:46.838048: Current learning rate: 0.00416 +2025-10-31 07:03:08.960502: train_loss -0.991 +2025-10-31 07:03:08.963149: val_loss -0.8916 +2025-10-31 07:03:08.964752: Pseudo dice [np.float32(0.9839), np.float32(0.9907), np.float32(0.9942), np.float32(0.8)] +2025-10-31 07:03:08.966471: Epoch time: 22.13 s +2025-10-31 07:03:10.344266: +2025-10-31 07:03:10.347393: Epoch 624 +2025-10-31 07:03:10.349256: Current learning rate: 0.00415 +2025-10-31 07:03:33.062746: train_loss -0.9908 +2025-10-31 07:03:33.070026: val_loss -0.8932 +2025-10-31 07:03:33.078142: Pseudo dice [np.float32(0.9849), np.float32(0.9909), np.float32(0.9942), np.float32(0.8053)] +2025-10-31 07:03:33.080248: Epoch time: 22.72 s +2025-10-31 07:03:34.359515: +2025-10-31 07:03:34.361369: Epoch 625 +2025-10-31 07:03:34.362805: Current learning rate: 0.00414 +2025-10-31 07:03:56.248362: train_loss -0.991 +2025-10-31 07:03:56.252206: val_loss -0.8886 +2025-10-31 07:03:56.253811: Pseudo dice [np.float32(0.9855), np.float32(0.9905), np.float32(0.994), np.float32(0.7861)] +2025-10-31 07:03:56.255539: Epoch time: 21.89 s +2025-10-31 07:03:57.592266: +2025-10-31 07:03:57.594215: Epoch 626 +2025-10-31 07:03:57.595914: Current learning rate: 0.00413 +2025-10-31 07:04:19.541827: train_loss -0.9907 +2025-10-31 07:04:19.544588: val_loss -0.8858 +2025-10-31 07:04:19.546926: Pseudo dice [np.float32(0.985), np.float32(0.9912), np.float32(0.9942), np.float32(0.7813)] +2025-10-31 07:04:19.549172: Epoch time: 21.95 s +2025-10-31 07:04:20.822936: +2025-10-31 07:04:20.824821: Epoch 627 +2025-10-31 07:04:20.826238: Current learning rate: 0.00412 +2025-10-31 07:04:42.666430: train_loss -0.991 +2025-10-31 07:04:42.669956: val_loss -0.8878 +2025-10-31 07:04:42.672666: Pseudo dice [np.float32(0.9854), np.float32(0.9912), np.float32(0.9938), np.float32(0.7907)] +2025-10-31 07:04:42.675207: Epoch time: 21.85 s +2025-10-31 07:04:43.659637: +2025-10-31 07:04:43.662705: Epoch 628 +2025-10-31 07:04:43.667885: Current learning rate: 0.00411 +2025-10-31 07:05:05.950702: train_loss -0.9908 +2025-10-31 07:05:05.953611: val_loss -0.8895 +2025-10-31 07:05:05.955311: Pseudo dice [np.float32(0.9867), np.float32(0.9916), np.float32(0.9942), np.float32(0.7786)] +2025-10-31 07:05:05.957664: Epoch time: 22.29 s +2025-10-31 07:05:07.284187: +2025-10-31 07:05:07.291634: Epoch 629 +2025-10-31 07:05:07.293861: Current learning rate: 0.0041 +2025-10-31 07:05:29.457922: train_loss -0.9912 +2025-10-31 07:05:29.470359: val_loss -0.8947 +2025-10-31 07:05:29.473503: Pseudo dice [np.float32(0.9832), np.float32(0.9903), np.float32(0.9942), np.float32(0.8026)] +2025-10-31 07:05:29.475904: Epoch time: 22.18 s +2025-10-31 07:05:30.809229: +2025-10-31 07:05:30.812317: Epoch 630 +2025-10-31 07:05:30.814768: Current learning rate: 0.00409 +2025-10-31 07:05:53.176111: train_loss -0.9905 +2025-10-31 07:05:53.180062: val_loss -0.9004 +2025-10-31 07:05:53.182448: Pseudo dice [np.float32(0.9856), np.float32(0.9918), np.float32(0.9948), np.float32(0.8086)] +2025-10-31 07:05:53.183958: Epoch time: 22.37 s +2025-10-31 07:05:54.413468: +2025-10-31 07:05:54.419517: Epoch 631 +2025-10-31 07:05:54.423085: Current learning rate: 0.00408 +2025-10-31 07:06:15.796993: train_loss -0.9909 +2025-10-31 07:06:15.799240: val_loss -0.887 +2025-10-31 07:06:15.800743: Pseudo dice [np.float32(0.9862), np.float32(0.9923), np.float32(0.9943), np.float32(0.7799)] +2025-10-31 07:06:15.802287: Epoch time: 21.39 s +2025-10-31 07:06:17.672081: +2025-10-31 07:06:17.674122: Epoch 632 +2025-10-31 07:06:17.675946: Current learning rate: 0.00407 +2025-10-31 07:06:39.442375: train_loss -0.9907 +2025-10-31 07:06:39.446557: val_loss -0.8902 +2025-10-31 07:06:39.449073: Pseudo dice [np.float32(0.9833), np.float32(0.9916), np.float32(0.9946), np.float32(0.795)] +2025-10-31 07:06:39.451820: Epoch time: 21.77 s +2025-10-31 07:06:40.559808: +2025-10-31 07:06:40.561983: Epoch 633 +2025-10-31 07:06:40.563700: Current learning rate: 0.00406 +2025-10-31 07:07:01.966945: train_loss -0.9905 +2025-10-31 07:07:01.970296: val_loss -0.8911 +2025-10-31 07:07:01.972103: Pseudo dice [np.float32(0.9869), np.float32(0.9916), np.float32(0.9938), np.float32(0.7936)] +2025-10-31 07:07:01.973747: Epoch time: 21.41 s +2025-10-31 07:07:03.104001: +2025-10-31 07:07:03.106127: Epoch 634 +2025-10-31 07:07:03.107831: Current learning rate: 0.00405 +2025-10-31 07:07:25.360460: train_loss -0.9902 +2025-10-31 07:07:25.363604: val_loss -0.8896 +2025-10-31 07:07:25.365252: Pseudo dice [np.float32(0.9856), np.float32(0.9905), np.float32(0.9943), np.float32(0.7896)] +2025-10-31 07:07:25.366741: Epoch time: 22.26 s +2025-10-31 07:07:26.342540: +2025-10-31 07:07:26.345204: Epoch 635 +2025-10-31 07:07:26.347263: Current learning rate: 0.00404 +2025-10-31 07:07:47.836298: train_loss -0.9904 +2025-10-31 07:07:47.838829: val_loss -0.8943 +2025-10-31 07:07:47.840677: Pseudo dice [np.float32(0.9861), np.float32(0.9916), np.float32(0.9946), np.float32(0.7942)] +2025-10-31 07:07:47.842302: Epoch time: 21.5 s +2025-10-31 07:07:48.926337: +2025-10-31 07:07:48.928499: Epoch 636 +2025-10-31 07:07:48.930334: Current learning rate: 0.00403 +2025-10-31 07:08:10.984832: train_loss -0.9909 +2025-10-31 07:08:10.988893: val_loss -0.8986 +2025-10-31 07:08:10.990388: Pseudo dice [np.float32(0.9856), np.float32(0.991), np.float32(0.9946), np.float32(0.8055)] +2025-10-31 07:08:10.991926: Epoch time: 22.06 s +2025-10-31 07:08:12.011464: +2025-10-31 07:08:12.013314: Epoch 637 +2025-10-31 07:08:12.015141: Current learning rate: 0.00402 +2025-10-31 07:08:33.441028: train_loss -0.9911 +2025-10-31 07:08:33.445321: val_loss -0.9035 +2025-10-31 07:08:33.447108: Pseudo dice [np.float32(0.986), np.float32(0.9923), np.float32(0.9949), np.float32(0.8196)] +2025-10-31 07:08:33.448882: Epoch time: 21.43 s +2025-10-31 07:08:34.691962: +2025-10-31 07:08:34.694107: Epoch 638 +2025-10-31 07:08:34.695786: Current learning rate: 0.00401 +2025-10-31 07:08:56.724844: train_loss -0.9907 +2025-10-31 07:08:56.727260: val_loss -0.8974 +2025-10-31 07:08:56.728836: Pseudo dice [np.float32(0.9846), np.float32(0.9912), np.float32(0.9951), np.float32(0.8073)] +2025-10-31 07:08:56.730327: Epoch time: 22.03 s +2025-10-31 07:08:57.995462: +2025-10-31 07:08:57.997800: Epoch 639 +2025-10-31 07:08:57.999242: Current learning rate: 0.004 +2025-10-31 07:09:19.591053: train_loss -0.9909 +2025-10-31 07:09:19.597003: val_loss -0.8879 +2025-10-31 07:09:19.599085: Pseudo dice [np.float32(0.9862), np.float32(0.9912), np.float32(0.9939), np.float32(0.7789)] +2025-10-31 07:09:19.600915: Epoch time: 21.6 s +2025-10-31 07:09:20.723862: +2025-10-31 07:09:20.725995: Epoch 640 +2025-10-31 07:09:20.727669: Current learning rate: 0.00399 +2025-10-31 07:09:41.375868: train_loss -0.9912 +2025-10-31 07:09:41.379197: val_loss -0.8915 +2025-10-31 07:09:41.380808: Pseudo dice [np.float32(0.9862), np.float32(0.9917), np.float32(0.9939), np.float32(0.7908)] +2025-10-31 07:09:41.382371: Epoch time: 20.65 s +2025-10-31 07:09:42.555623: +2025-10-31 07:09:42.557740: Epoch 641 +2025-10-31 07:09:42.559569: Current learning rate: 0.00398 +2025-10-31 07:10:05.035366: train_loss -0.9912 +2025-10-31 07:10:05.041900: val_loss -0.8935 +2025-10-31 07:10:05.043451: Pseudo dice [np.float32(0.9828), np.float32(0.9913), np.float32(0.9948), np.float32(0.8061)] +2025-10-31 07:10:05.044882: Epoch time: 22.48 s +2025-10-31 07:10:06.310113: +2025-10-31 07:10:06.312165: Epoch 642 +2025-10-31 07:10:06.314097: Current learning rate: 0.00397 +2025-10-31 07:10:28.807674: train_loss -0.9901 +2025-10-31 07:10:28.811038: val_loss -0.9056 +2025-10-31 07:10:28.812670: Pseudo dice [np.float32(0.9872), np.float32(0.9923), np.float32(0.995), np.float32(0.8119)] +2025-10-31 07:10:28.814301: Epoch time: 22.5 s +2025-10-31 07:10:30.134114: +2025-10-31 07:10:30.136405: Epoch 643 +2025-10-31 07:10:30.138259: Current learning rate: 0.00396 +2025-10-31 07:10:51.540661: train_loss -0.9908 +2025-10-31 07:10:51.544274: val_loss -0.89 +2025-10-31 07:10:51.546444: Pseudo dice [np.float32(0.9851), np.float32(0.9904), np.float32(0.9943), np.float32(0.7919)] +2025-10-31 07:10:51.548142: Epoch time: 21.41 s +2025-10-31 07:10:52.584988: +2025-10-31 07:10:52.587157: Epoch 644 +2025-10-31 07:10:52.589032: Current learning rate: 0.00395 +2025-10-31 07:11:14.944438: train_loss -0.9917 +2025-10-31 07:11:14.947391: val_loss -0.8947 +2025-10-31 07:11:14.949701: Pseudo dice [np.float32(0.9872), np.float32(0.9915), np.float32(0.9942), np.float32(0.7953)] +2025-10-31 07:11:14.951795: Epoch time: 22.36 s +2025-10-31 07:11:16.460067: +2025-10-31 07:11:16.462580: Epoch 645 +2025-10-31 07:11:16.464444: Current learning rate: 0.00394 +2025-10-31 07:11:39.090347: train_loss -0.9919 +2025-10-31 07:11:39.096163: val_loss -0.8932 +2025-10-31 07:11:39.098079: Pseudo dice [np.float32(0.9855), np.float32(0.9912), np.float32(0.9942), np.float32(0.7958)] +2025-10-31 07:11:39.099860: Epoch time: 22.63 s +2025-10-31 07:11:40.314667: +2025-10-31 07:11:40.316590: Epoch 646 +2025-10-31 07:11:40.318379: Current learning rate: 0.00393 +2025-10-31 07:12:01.323977: train_loss -0.9916 +2025-10-31 07:12:01.327689: val_loss -0.8826 +2025-10-31 07:12:01.331662: Pseudo dice [np.float32(0.9852), np.float32(0.9909), np.float32(0.9938), np.float32(0.7795)] +2025-10-31 07:12:01.333934: Epoch time: 21.01 s +2025-10-31 07:12:02.594892: +2025-10-31 07:12:02.596968: Epoch 647 +2025-10-31 07:12:02.598691: Current learning rate: 0.00392 +2025-10-31 07:12:24.763916: train_loss -0.9913 +2025-10-31 07:12:24.766141: val_loss -0.8967 +2025-10-31 07:12:24.767834: Pseudo dice [np.float32(0.9859), np.float32(0.9913), np.float32(0.9943), np.float32(0.8044)] +2025-10-31 07:12:24.770098: Epoch time: 22.17 s +2025-10-31 07:12:25.907564: +2025-10-31 07:12:25.909512: Epoch 648 +2025-10-31 07:12:25.911478: Current learning rate: 0.00391 +2025-10-31 07:12:48.064154: train_loss -0.9911 +2025-10-31 07:12:48.068886: val_loss -0.9015 +2025-10-31 07:12:48.070816: Pseudo dice [np.float32(0.9854), np.float32(0.9911), np.float32(0.9946), np.float32(0.8191)] +2025-10-31 07:12:48.072351: Epoch time: 22.16 s +2025-10-31 07:12:49.317424: +2025-10-31 07:12:49.319650: Epoch 649 +2025-10-31 07:12:49.321578: Current learning rate: 0.0039 +2025-10-31 07:13:10.413815: train_loss -0.9912 +2025-10-31 07:13:10.418579: val_loss -0.8982 +2025-10-31 07:13:10.422147: Pseudo dice [np.float32(0.9872), np.float32(0.9924), np.float32(0.9944), np.float32(0.8058)] +2025-10-31 07:13:10.424549: Epoch time: 21.1 s +2025-10-31 07:13:12.679801: +2025-10-31 07:13:12.681851: Epoch 650 +2025-10-31 07:13:12.683914: Current learning rate: 0.00389 +2025-10-31 07:13:34.256260: train_loss -0.991 +2025-10-31 07:13:34.259915: val_loss -0.8984 +2025-10-31 07:13:34.261687: Pseudo dice [np.float32(0.988), np.float32(0.9921), np.float32(0.9943), np.float32(0.8074)] +2025-10-31 07:13:34.263276: Epoch time: 21.58 s +2025-10-31 07:13:35.487393: +2025-10-31 07:13:35.489737: Epoch 651 +2025-10-31 07:13:35.491381: Current learning rate: 0.00388 +2025-10-31 07:13:57.550442: train_loss -0.9906 +2025-10-31 07:13:57.554681: val_loss -0.8946 +2025-10-31 07:13:57.556248: Pseudo dice [np.float32(0.9866), np.float32(0.9909), np.float32(0.9944), np.float32(0.8012)] +2025-10-31 07:13:57.557738: Epoch time: 22.06 s +2025-10-31 07:13:58.575711: +2025-10-31 07:13:58.585016: Epoch 652 +2025-10-31 07:13:58.586741: Current learning rate: 0.00387 +2025-10-31 07:14:20.080922: train_loss -0.9914 +2025-10-31 07:14:20.084490: val_loss -0.8977 +2025-10-31 07:14:20.086832: Pseudo dice [np.float32(0.9863), np.float32(0.9917), np.float32(0.9944), np.float32(0.8086)] +2025-10-31 07:14:20.088539: Epoch time: 21.51 s +2025-10-31 07:14:21.183771: +2025-10-31 07:14:21.185850: Epoch 653 +2025-10-31 07:14:21.187612: Current learning rate: 0.00386 +2025-10-31 07:14:43.518577: train_loss -0.9911 +2025-10-31 07:14:43.523300: val_loss -0.8971 +2025-10-31 07:14:43.525269: Pseudo dice [np.float32(0.9861), np.float32(0.9914), np.float32(0.9945), np.float32(0.8064)] +2025-10-31 07:14:43.526933: Epoch time: 22.34 s +2025-10-31 07:14:44.572565: +2025-10-31 07:14:44.574549: Epoch 654 +2025-10-31 07:14:44.576279: Current learning rate: 0.00385 +2025-10-31 07:15:06.865411: train_loss -0.9917 +2025-10-31 07:15:06.873908: val_loss -0.8988 +2025-10-31 07:15:06.875468: Pseudo dice [np.float32(0.987), np.float32(0.9914), np.float32(0.9947), np.float32(0.8049)] +2025-10-31 07:15:06.877385: Epoch time: 22.29 s +2025-10-31 07:15:08.187186: +2025-10-31 07:15:08.189175: Epoch 655 +2025-10-31 07:15:08.190922: Current learning rate: 0.00384 +2025-10-31 07:15:29.536231: train_loss -0.9918 +2025-10-31 07:15:29.538570: val_loss -0.8911 +2025-10-31 07:15:29.540067: Pseudo dice [np.float32(0.9876), np.float32(0.9909), np.float32(0.9939), np.float32(0.7882)] +2025-10-31 07:15:29.541839: Epoch time: 21.35 s +2025-10-31 07:15:31.477313: +2025-10-31 07:15:31.479521: Epoch 656 +2025-10-31 07:15:31.481389: Current learning rate: 0.00383 +2025-10-31 07:15:53.305179: train_loss -0.9864 +2025-10-31 07:15:53.308664: val_loss -0.8954 +2025-10-31 07:15:53.310710: Pseudo dice [np.float32(0.9836), np.float32(0.9898), np.float32(0.9943), np.float32(0.8029)] +2025-10-31 07:15:53.312493: Epoch time: 21.83 s +2025-10-31 07:15:54.403770: +2025-10-31 07:15:54.406119: Epoch 657 +2025-10-31 07:15:54.407926: Current learning rate: 0.00382 +2025-10-31 07:16:16.695248: train_loss -0.9884 +2025-10-31 07:16:16.698239: val_loss -0.8839 +2025-10-31 07:16:16.700067: Pseudo dice [np.float32(0.9856), np.float32(0.9904), np.float32(0.9943), np.float32(0.7758)] +2025-10-31 07:16:16.701869: Epoch time: 22.29 s +2025-10-31 07:16:17.725971: +2025-10-31 07:16:17.728005: Epoch 658 +2025-10-31 07:16:17.729605: Current learning rate: 0.00381 +2025-10-31 07:16:39.822207: train_loss -0.9879 +2025-10-31 07:16:39.824450: val_loss -0.8877 +2025-10-31 07:16:39.826049: Pseudo dice [np.float32(0.9848), np.float32(0.992), np.float32(0.9939), np.float32(0.7696)] +2025-10-31 07:16:39.827657: Epoch time: 22.1 s +2025-10-31 07:16:40.920776: +2025-10-31 07:16:40.922862: Epoch 659 +2025-10-31 07:16:40.924683: Current learning rate: 0.0038 +2025-10-31 07:17:01.886046: train_loss -0.9885 +2025-10-31 07:17:01.889133: val_loss -0.9052 +2025-10-31 07:17:01.891163: Pseudo dice [np.float32(0.9852), np.float32(0.9919), np.float32(0.9952), np.float32(0.8175)] +2025-10-31 07:17:01.893202: Epoch time: 20.97 s +2025-10-31 07:17:03.183058: +2025-10-31 07:17:03.185038: Epoch 660 +2025-10-31 07:17:03.187063: Current learning rate: 0.00379 +2025-10-31 07:17:25.027991: train_loss -0.9896 +2025-10-31 07:17:25.032067: val_loss -0.8982 +2025-10-31 07:17:25.034330: Pseudo dice [np.float32(0.9861), np.float32(0.9909), np.float32(0.9943), np.float32(0.8043)] +2025-10-31 07:17:25.036530: Epoch time: 21.85 s +2025-10-31 07:17:26.263389: +2025-10-31 07:17:26.265556: Epoch 661 +2025-10-31 07:17:26.267536: Current learning rate: 0.00378 +2025-10-31 07:17:46.973981: train_loss -0.9908 +2025-10-31 07:17:46.976635: val_loss -0.8953 +2025-10-31 07:17:46.979480: Pseudo dice [np.float32(0.9855), np.float32(0.991), np.float32(0.9945), np.float32(0.8006)] +2025-10-31 07:17:46.981552: Epoch time: 20.71 s +2025-10-31 07:17:48.036782: +2025-10-31 07:17:48.039085: Epoch 662 +2025-10-31 07:17:48.040827: Current learning rate: 0.00377 +2025-10-31 07:18:10.476859: train_loss -0.9896 +2025-10-31 07:18:10.479429: val_loss -0.8914 +2025-10-31 07:18:10.481418: Pseudo dice [np.float32(0.9852), np.float32(0.99), np.float32(0.9944), np.float32(0.8004)] +2025-10-31 07:18:10.484218: Epoch time: 22.44 s +2025-10-31 07:18:11.525130: +2025-10-31 07:18:11.528463: Epoch 663 +2025-10-31 07:18:11.531087: Current learning rate: 0.00376 +2025-10-31 07:18:33.737554: train_loss -0.9903 +2025-10-31 07:18:33.741635: val_loss -0.8916 +2025-10-31 07:18:33.743432: Pseudo dice [np.float32(0.9854), np.float32(0.9913), np.float32(0.9938), np.float32(0.7939)] +2025-10-31 07:18:33.745120: Epoch time: 22.21 s +2025-10-31 07:18:35.000878: +2025-10-31 07:18:35.002879: Epoch 664 +2025-10-31 07:18:35.004682: Current learning rate: 0.00375 +2025-10-31 07:18:57.105821: train_loss -0.9915 +2025-10-31 07:18:57.109216: val_loss -0.8934 +2025-10-31 07:18:57.111064: Pseudo dice [np.float32(0.9859), np.float32(0.9916), np.float32(0.9941), np.float32(0.7962)] +2025-10-31 07:18:57.113176: Epoch time: 22.11 s +2025-10-31 07:18:58.306274: +2025-10-31 07:18:58.308382: Epoch 665 +2025-10-31 07:18:58.310081: Current learning rate: 0.00374 +2025-10-31 07:19:18.984147: train_loss -0.9909 +2025-10-31 07:19:18.991135: val_loss -0.89 +2025-10-31 07:19:18.992788: Pseudo dice [np.float32(0.9845), np.float32(0.9907), np.float32(0.9936), np.float32(0.7966)] +2025-10-31 07:19:18.995011: Epoch time: 20.68 s +2025-10-31 07:19:20.128544: +2025-10-31 07:19:20.131066: Epoch 666 +2025-10-31 07:19:20.132801: Current learning rate: 0.00373 +2025-10-31 07:19:40.237089: train_loss -0.991 +2025-10-31 07:19:40.241059: val_loss -0.9002 +2025-10-31 07:19:40.243374: Pseudo dice [np.float32(0.9851), np.float32(0.9918), np.float32(0.9947), np.float32(0.8134)] +2025-10-31 07:19:40.245467: Epoch time: 20.11 s +2025-10-31 07:19:41.543834: +2025-10-31 07:19:41.546043: Epoch 667 +2025-10-31 07:19:41.548301: Current learning rate: 0.00372 +2025-10-31 07:20:01.668555: train_loss -0.9913 +2025-10-31 07:20:01.670507: val_loss -0.9002 +2025-10-31 07:20:01.672434: Pseudo dice [np.float32(0.9855), np.float32(0.9913), np.float32(0.9944), np.float32(0.8152)] +2025-10-31 07:20:01.674722: Epoch time: 20.13 s +2025-10-31 07:20:03.223898: +2025-10-31 07:20:03.225981: Epoch 668 +2025-10-31 07:20:03.227829: Current learning rate: 0.00371 +2025-10-31 07:20:26.074960: train_loss -0.991 +2025-10-31 07:20:26.078939: val_loss -0.8966 +2025-10-31 07:20:26.080572: Pseudo dice [np.float32(0.985), np.float32(0.9916), np.float32(0.9945), np.float32(0.8003)] +2025-10-31 07:20:26.082098: Epoch time: 22.85 s +2025-10-31 07:20:27.306023: +2025-10-31 07:20:27.307981: Epoch 669 +2025-10-31 07:20:27.309702: Current learning rate: 0.0037 +2025-10-31 07:20:50.160978: train_loss -0.9915 +2025-10-31 07:20:50.164022: val_loss -0.891 +2025-10-31 07:20:50.165586: Pseudo dice [np.float32(0.9845), np.float32(0.9913), np.float32(0.9945), np.float32(0.7994)] +2025-10-31 07:20:50.167109: Epoch time: 22.86 s +2025-10-31 07:20:51.448510: +2025-10-31 07:20:51.450493: Epoch 670 +2025-10-31 07:20:51.452435: Current learning rate: 0.00369 +2025-10-31 07:21:14.347412: train_loss -0.9917 +2025-10-31 07:21:14.349562: val_loss -0.8946 +2025-10-31 07:21:14.351132: Pseudo dice [np.float32(0.9863), np.float32(0.9913), np.float32(0.9944), np.float32(0.8061)] +2025-10-31 07:21:14.353247: Epoch time: 22.9 s +2025-10-31 07:21:15.594752: +2025-10-31 07:21:15.597404: Epoch 671 +2025-10-31 07:21:15.602244: Current learning rate: 0.00368 +2025-10-31 07:21:37.485974: train_loss -0.9915 +2025-10-31 07:21:37.488899: val_loss -0.8952 +2025-10-31 07:21:37.490659: Pseudo dice [np.float32(0.9859), np.float32(0.9914), np.float32(0.9944), np.float32(0.7965)] +2025-10-31 07:21:37.492489: Epoch time: 21.89 s +2025-10-31 07:21:38.792303: +2025-10-31 07:21:38.794160: Epoch 672 +2025-10-31 07:21:38.795818: Current learning rate: 0.00367 +2025-10-31 07:22:00.290455: train_loss -0.9914 +2025-10-31 07:22:00.293800: val_loss -0.8906 +2025-10-31 07:22:00.295472: Pseudo dice [np.float32(0.9851), np.float32(0.9903), np.float32(0.9943), np.float32(0.8037)] +2025-10-31 07:22:00.297125: Epoch time: 21.5 s +2025-10-31 07:22:01.616592: +2025-10-31 07:22:01.618782: Epoch 673 +2025-10-31 07:22:01.620560: Current learning rate: 0.00366 +2025-10-31 07:22:22.761969: train_loss -0.9913 +2025-10-31 07:22:22.764479: val_loss -0.8848 +2025-10-31 07:22:22.766241: Pseudo dice [np.float32(0.9859), np.float32(0.9901), np.float32(0.9933), np.float32(0.7826)] +2025-10-31 07:22:22.767946: Epoch time: 21.15 s +2025-10-31 07:22:23.801322: +2025-10-31 07:22:23.803210: Epoch 674 +2025-10-31 07:22:23.804821: Current learning rate: 0.00365 +2025-10-31 07:22:46.071101: train_loss -0.9906 +2025-10-31 07:22:46.073502: val_loss -0.8815 +2025-10-31 07:22:46.075625: Pseudo dice [np.float32(0.9842), np.float32(0.9904), np.float32(0.993), np.float32(0.7815)] +2025-10-31 07:22:46.077865: Epoch time: 22.27 s +2025-10-31 07:22:47.339679: +2025-10-31 07:22:47.341856: Epoch 675 +2025-10-31 07:22:47.343690: Current learning rate: 0.00364 +2025-10-31 07:23:08.914370: train_loss -0.9912 +2025-10-31 07:23:08.917480: val_loss -0.8891 +2025-10-31 07:23:08.921026: Pseudo dice [np.float32(0.9856), np.float32(0.9902), np.float32(0.9939), np.float32(0.7911)] +2025-10-31 07:23:08.924854: Epoch time: 21.58 s +2025-10-31 07:23:10.099433: +2025-10-31 07:23:10.101288: Epoch 676 +2025-10-31 07:23:10.103175: Current learning rate: 0.00363 +2025-10-31 07:23:32.445664: train_loss -0.9915 +2025-10-31 07:23:32.449241: val_loss -0.8913 +2025-10-31 07:23:32.452171: Pseudo dice [np.float32(0.9859), np.float32(0.9905), np.float32(0.9943), np.float32(0.7885)] +2025-10-31 07:23:32.454064: Epoch time: 22.35 s +2025-10-31 07:23:33.624987: +2025-10-31 07:23:33.629493: Epoch 677 +2025-10-31 07:23:33.633454: Current learning rate: 0.00362 +2025-10-31 07:23:56.173675: train_loss -0.9917 +2025-10-31 07:23:56.176120: val_loss -0.8903 +2025-10-31 07:23:56.177699: Pseudo dice [np.float32(0.9862), np.float32(0.9911), np.float32(0.994), np.float32(0.7861)] +2025-10-31 07:23:56.179297: Epoch time: 22.55 s +2025-10-31 07:23:57.394863: +2025-10-31 07:23:57.397567: Epoch 678 +2025-10-31 07:23:57.399467: Current learning rate: 0.00361 +2025-10-31 07:24:19.206989: train_loss -0.9918 +2025-10-31 07:24:19.209684: val_loss -0.8845 +2025-10-31 07:24:19.212119: Pseudo dice [np.float32(0.9857), np.float32(0.9906), np.float32(0.9939), np.float32(0.7783)] +2025-10-31 07:24:19.214314: Epoch time: 21.81 s +2025-10-31 07:24:20.465094: +2025-10-31 07:24:20.466942: Epoch 679 +2025-10-31 07:24:20.468554: Current learning rate: 0.0036 +2025-10-31 07:24:41.575254: train_loss -0.9915 +2025-10-31 07:24:41.577590: val_loss -0.8926 +2025-10-31 07:24:41.579484: Pseudo dice [np.float32(0.9855), np.float32(0.9914), np.float32(0.9948), np.float32(0.7962)] +2025-10-31 07:24:41.581002: Epoch time: 21.11 s +2025-10-31 07:24:43.254509: +2025-10-31 07:24:43.256574: Epoch 680 +2025-10-31 07:24:43.258416: Current learning rate: 0.00359 +2025-10-31 07:25:05.741486: train_loss -0.9911 +2025-10-31 07:25:05.743714: val_loss -0.8842 +2025-10-31 07:25:05.745266: Pseudo dice [np.float32(0.9863), np.float32(0.9912), np.float32(0.9943), np.float32(0.7696)] +2025-10-31 07:25:05.747000: Epoch time: 22.49 s +2025-10-31 07:25:07.027027: +2025-10-31 07:25:07.029180: Epoch 681 +2025-10-31 07:25:07.031046: Current learning rate: 0.00358 +2025-10-31 07:25:28.595473: train_loss -0.991 +2025-10-31 07:25:28.598919: val_loss -0.8896 +2025-10-31 07:25:28.600388: Pseudo dice [np.float32(0.9842), np.float32(0.9907), np.float32(0.994), np.float32(0.7977)] +2025-10-31 07:25:28.601893: Epoch time: 21.57 s +2025-10-31 07:25:29.754407: +2025-10-31 07:25:29.756355: Epoch 682 +2025-10-31 07:25:29.758038: Current learning rate: 0.00357 +2025-10-31 07:25:51.511050: train_loss -0.9911 +2025-10-31 07:25:51.513548: val_loss -0.8842 +2025-10-31 07:25:51.514834: Pseudo dice [np.float32(0.9853), np.float32(0.9917), np.float32(0.9943), np.float32(0.7664)] +2025-10-31 07:25:51.516160: Epoch time: 21.76 s +2025-10-31 07:25:52.655849: +2025-10-31 07:25:52.657868: Epoch 683 +2025-10-31 07:25:52.659576: Current learning rate: 0.00356 +2025-10-31 07:26:15.180377: train_loss -0.9916 +2025-10-31 07:26:15.184436: val_loss -0.8791 +2025-10-31 07:26:15.186011: Pseudo dice [np.float32(0.9862), np.float32(0.9916), np.float32(0.9936), np.float32(0.7638)] +2025-10-31 07:26:15.187588: Epoch time: 22.53 s +2025-10-31 07:26:16.311883: +2025-10-31 07:26:16.314115: Epoch 684 +2025-10-31 07:26:16.315593: Current learning rate: 0.00355 +2025-10-31 07:26:38.419650: train_loss -0.9913 +2025-10-31 07:26:38.424571: val_loss -0.8867 +2025-10-31 07:26:38.426420: Pseudo dice [np.float32(0.9827), np.float32(0.9898), np.float32(0.9939), np.float32(0.7915)] +2025-10-31 07:26:38.428180: Epoch time: 22.11 s +2025-10-31 07:26:39.639353: +2025-10-31 07:26:39.641210: Epoch 685 +2025-10-31 07:26:39.642992: Current learning rate: 0.00354 +2025-10-31 07:27:00.224776: train_loss -0.991 +2025-10-31 07:27:00.228271: val_loss -0.8876 +2025-10-31 07:27:00.230421: Pseudo dice [np.float32(0.9859), np.float32(0.9916), np.float32(0.994), np.float32(0.7883)] +2025-10-31 07:27:00.232422: Epoch time: 20.59 s +2025-10-31 07:27:01.521760: +2025-10-31 07:27:01.524489: Epoch 686 +2025-10-31 07:27:01.526685: Current learning rate: 0.00353 +2025-10-31 07:27:23.186557: train_loss -0.9915 +2025-10-31 07:27:23.189739: val_loss -0.8921 +2025-10-31 07:27:23.191360: Pseudo dice [np.float32(0.9855), np.float32(0.9916), np.float32(0.9944), np.float32(0.7862)] +2025-10-31 07:27:23.192985: Epoch time: 21.67 s +2025-10-31 07:27:24.305391: +2025-10-31 07:27:24.307585: Epoch 687 +2025-10-31 07:27:24.309435: Current learning rate: 0.00352 +2025-10-31 07:27:46.414939: train_loss -0.9908 +2025-10-31 07:27:46.418059: val_loss -0.8881 +2025-10-31 07:27:46.420064: Pseudo dice [np.float32(0.9837), np.float32(0.9905), np.float32(0.994), np.float32(0.7891)] +2025-10-31 07:27:46.422037: Epoch time: 22.11 s +2025-10-31 07:27:47.547084: +2025-10-31 07:27:47.548933: Epoch 688 +2025-10-31 07:27:47.550496: Current learning rate: 0.00351 +2025-10-31 07:28:09.856681: train_loss -0.9913 +2025-10-31 07:28:09.859953: val_loss -0.8918 +2025-10-31 07:28:09.861401: Pseudo dice [np.float32(0.9859), np.float32(0.9916), np.float32(0.9941), np.float32(0.7931)] +2025-10-31 07:28:09.863039: Epoch time: 22.31 s +2025-10-31 07:28:11.120773: +2025-10-31 07:28:11.122529: Epoch 689 +2025-10-31 07:28:11.123998: Current learning rate: 0.0035 +2025-10-31 07:28:33.158261: train_loss -0.9913 +2025-10-31 07:28:33.162115: val_loss -0.8864 +2025-10-31 07:28:33.163577: Pseudo dice [np.float32(0.9847), np.float32(0.9898), np.float32(0.9937), np.float32(0.7887)] +2025-10-31 07:28:33.164917: Epoch time: 22.04 s +2025-10-31 07:28:34.543943: +2025-10-31 07:28:34.546270: Epoch 690 +2025-10-31 07:28:34.548005: Current learning rate: 0.00349 +2025-10-31 07:28:56.488693: train_loss -0.9918 +2025-10-31 07:28:56.492118: val_loss -0.887 +2025-10-31 07:28:56.493844: Pseudo dice [np.float32(0.9853), np.float32(0.9918), np.float32(0.9942), np.float32(0.7881)] +2025-10-31 07:28:56.495512: Epoch time: 21.95 s +2025-10-31 07:28:57.720335: +2025-10-31 07:28:57.722321: Epoch 691 +2025-10-31 07:28:57.724442: Current learning rate: 0.00348 +2025-10-31 07:29:18.448187: train_loss -0.9916 +2025-10-31 07:29:18.451189: val_loss -0.8869 +2025-10-31 07:29:18.453959: Pseudo dice [np.float32(0.9861), np.float32(0.9911), np.float32(0.994), np.float32(0.7767)] +2025-10-31 07:29:18.456474: Epoch time: 20.73 s +2025-10-31 07:29:19.931775: +2025-10-31 07:29:19.938555: Epoch 692 +2025-10-31 07:29:19.942305: Current learning rate: 0.00346 +2025-10-31 07:29:41.245930: train_loss -0.9906 +2025-10-31 07:29:41.248530: val_loss -0.8931 +2025-10-31 07:29:41.250338: Pseudo dice [np.float32(0.9853), np.float32(0.9918), np.float32(0.9945), np.float32(0.7907)] +2025-10-31 07:29:41.251999: Epoch time: 21.32 s +2025-10-31 07:29:42.328631: +2025-10-31 07:29:42.331687: Epoch 693 +2025-10-31 07:29:42.334311: Current learning rate: 0.00345 +2025-10-31 07:30:05.567158: train_loss -0.9906 +2025-10-31 07:30:05.571942: val_loss -0.8841 +2025-10-31 07:30:05.573958: Pseudo dice [np.float32(0.9857), np.float32(0.9919), np.float32(0.9936), np.float32(0.7712)] +2025-10-31 07:30:05.575819: Epoch time: 23.24 s +2025-10-31 07:30:06.838808: +2025-10-31 07:30:06.841066: Epoch 694 +2025-10-31 07:30:06.842981: Current learning rate: 0.00344 +2025-10-31 07:30:29.065686: train_loss -0.9906 +2025-10-31 07:30:29.069839: val_loss -0.8935 +2025-10-31 07:30:29.071636: Pseudo dice [np.float32(0.987), np.float32(0.9917), np.float32(0.9942), np.float32(0.786)] +2025-10-31 07:30:29.073301: Epoch time: 22.23 s +2025-10-31 07:30:30.394318: +2025-10-31 07:30:30.396114: Epoch 695 +2025-10-31 07:30:30.397624: Current learning rate: 0.00343 +2025-10-31 07:30:52.167411: train_loss -0.9916 +2025-10-31 07:30:52.173029: val_loss -0.8925 +2025-10-31 07:30:52.174834: Pseudo dice [np.float32(0.9858), np.float32(0.9913), np.float32(0.9945), np.float32(0.7959)] +2025-10-31 07:30:52.176713: Epoch time: 21.78 s +2025-10-31 07:30:53.348375: +2025-10-31 07:30:53.351261: Epoch 696 +2025-10-31 07:30:53.354051: Current learning rate: 0.00342 +2025-10-31 07:31:15.345589: train_loss -0.9918 +2025-10-31 07:31:15.351085: val_loss -0.8871 +2025-10-31 07:31:15.353119: Pseudo dice [np.float32(0.9867), np.float32(0.9914), np.float32(0.9939), np.float32(0.7772)] +2025-10-31 07:31:15.354993: Epoch time: 22.0 s +2025-10-31 07:31:16.512171: +2025-10-31 07:31:16.514289: Epoch 697 +2025-10-31 07:31:16.515932: Current learning rate: 0.00341 +2025-10-31 07:31:39.006064: train_loss -0.9906 +2025-10-31 07:31:39.009262: val_loss -0.876 +2025-10-31 07:31:39.011042: Pseudo dice [np.float32(0.9861), np.float32(0.9912), np.float32(0.9934), np.float32(0.7552)] +2025-10-31 07:31:39.012779: Epoch time: 22.5 s +2025-10-31 07:31:40.202906: +2025-10-31 07:31:40.204980: Epoch 698 +2025-10-31 07:31:40.206645: Current learning rate: 0.0034 +2025-10-31 07:32:00.590095: train_loss -0.9914 +2025-10-31 07:32:00.593935: val_loss -0.9011 +2025-10-31 07:32:00.595828: Pseudo dice [np.float32(0.9861), np.float32(0.9915), np.float32(0.9948), np.float32(0.8254)] +2025-10-31 07:32:00.597737: Epoch time: 20.39 s +2025-10-31 07:32:01.890537: +2025-10-31 07:32:01.892478: Epoch 699 +2025-10-31 07:32:01.894017: Current learning rate: 0.00339 +2025-10-31 07:32:24.012592: train_loss -0.9915 +2025-10-31 07:32:24.018066: val_loss -0.8956 +2025-10-31 07:32:24.020134: Pseudo dice [np.float32(0.9876), np.float32(0.9923), np.float32(0.9944), np.float32(0.7926)] +2025-10-31 07:32:24.022089: Epoch time: 22.12 s +2025-10-31 07:32:26.488205: +2025-10-31 07:32:26.490260: Epoch 700 +2025-10-31 07:32:26.491974: Current learning rate: 0.00338 +2025-10-31 07:32:49.138687: train_loss -0.9916 +2025-10-31 07:32:49.140802: val_loss -0.8906 +2025-10-31 07:32:49.142228: Pseudo dice [np.float32(0.9851), np.float32(0.9919), np.float32(0.9942), np.float32(0.7942)] +2025-10-31 07:32:49.143685: Epoch time: 22.65 s +2025-10-31 07:32:50.380065: +2025-10-31 07:32:50.381820: Epoch 701 +2025-10-31 07:32:50.383339: Current learning rate: 0.00337 +2025-10-31 07:33:12.242997: train_loss -0.9917 +2025-10-31 07:33:12.245074: val_loss -0.8924 +2025-10-31 07:33:12.246867: Pseudo dice [np.float32(0.9853), np.float32(0.9911), np.float32(0.994), np.float32(0.7935)] +2025-10-31 07:33:12.248532: Epoch time: 21.86 s +2025-10-31 07:33:13.469086: +2025-10-31 07:33:13.471012: Epoch 702 +2025-10-31 07:33:13.472822: Current learning rate: 0.00336 +2025-10-31 07:33:35.500624: train_loss -0.9917 +2025-10-31 07:33:35.503798: val_loss -0.8931 +2025-10-31 07:33:35.505877: Pseudo dice [np.float32(0.9874), np.float32(0.9918), np.float32(0.9943), np.float32(0.7915)] +2025-10-31 07:33:35.507740: Epoch time: 22.03 s +2025-10-31 07:33:36.573691: +2025-10-31 07:33:36.575693: Epoch 703 +2025-10-31 07:33:36.577340: Current learning rate: 0.00335 +2025-10-31 07:33:58.833485: train_loss -0.9909 +2025-10-31 07:33:58.837314: val_loss -0.8947 +2025-10-31 07:33:58.838906: Pseudo dice [np.float32(0.9865), np.float32(0.9919), np.float32(0.9945), np.float32(0.7995)] +2025-10-31 07:33:58.840498: Epoch time: 22.26 s +2025-10-31 07:34:00.749211: +2025-10-31 07:34:00.751162: Epoch 704 +2025-10-31 07:34:00.752749: Current learning rate: 0.00334 +2025-10-31 07:34:20.670037: train_loss -0.9918 +2025-10-31 07:34:20.673232: val_loss -0.884 +2025-10-31 07:34:20.674919: Pseudo dice [np.float32(0.9849), np.float32(0.9904), np.float32(0.9937), np.float32(0.7849)] +2025-10-31 07:34:20.676544: Epoch time: 19.92 s +2025-10-31 07:34:21.887147: +2025-10-31 07:34:21.888982: Epoch 705 +2025-10-31 07:34:21.890667: Current learning rate: 0.00333 +2025-10-31 07:34:43.696224: train_loss -0.9909 +2025-10-31 07:34:43.702362: val_loss -0.8982 +2025-10-31 07:34:43.703848: Pseudo dice [np.float32(0.9864), np.float32(0.992), np.float32(0.9946), np.float32(0.8013)] +2025-10-31 07:34:43.705357: Epoch time: 21.81 s +2025-10-31 07:34:44.954862: +2025-10-31 07:34:44.956722: Epoch 706 +2025-10-31 07:34:44.958238: Current learning rate: 0.00332 +2025-10-31 07:35:07.431590: train_loss -0.9913 +2025-10-31 07:35:07.434691: val_loss -0.887 +2025-10-31 07:35:07.436664: Pseudo dice [np.float32(0.985), np.float32(0.9905), np.float32(0.9944), np.float32(0.7824)] +2025-10-31 07:35:07.438661: Epoch time: 22.48 s +2025-10-31 07:35:08.533920: +2025-10-31 07:35:08.535639: Epoch 707 +2025-10-31 07:35:08.537199: Current learning rate: 0.00331 +2025-10-31 07:35:31.046915: train_loss -0.9911 +2025-10-31 07:35:31.050565: val_loss -0.8866 +2025-10-31 07:35:31.052258: Pseudo dice [np.float32(0.9865), np.float32(0.9918), np.float32(0.994), np.float32(0.7771)] +2025-10-31 07:35:31.054179: Epoch time: 22.51 s +2025-10-31 07:35:32.135252: +2025-10-31 07:35:32.136988: Epoch 708 +2025-10-31 07:35:32.138875: Current learning rate: 0.0033 +2025-10-31 07:35:54.481078: train_loss -0.9918 +2025-10-31 07:35:54.491378: val_loss -0.8955 +2025-10-31 07:35:54.493013: Pseudo dice [np.float32(0.9867), np.float32(0.9913), np.float32(0.9941), np.float32(0.8016)] +2025-10-31 07:35:54.494794: Epoch time: 22.35 s +2025-10-31 07:35:55.854119: +2025-10-31 07:35:55.856434: Epoch 709 +2025-10-31 07:35:55.858312: Current learning rate: 0.00329 +2025-10-31 07:36:17.984436: train_loss -0.9914 +2025-10-31 07:36:17.990039: val_loss -0.8902 +2025-10-31 07:36:17.991910: Pseudo dice [np.float32(0.9863), np.float32(0.9919), np.float32(0.9948), np.float32(0.7915)] +2025-10-31 07:36:17.993633: Epoch time: 22.13 s +2025-10-31 07:36:19.258203: +2025-10-31 07:36:19.260156: Epoch 710 +2025-10-31 07:36:19.265833: Current learning rate: 0.00328 +2025-10-31 07:36:40.023963: train_loss -0.9914 +2025-10-31 07:36:40.026205: val_loss -0.8905 +2025-10-31 07:36:40.028157: Pseudo dice [np.float32(0.9855), np.float32(0.992), np.float32(0.9944), np.float32(0.7885)] +2025-10-31 07:36:40.030077: Epoch time: 20.77 s +2025-10-31 07:36:41.260968: +2025-10-31 07:36:41.263471: Epoch 711 +2025-10-31 07:36:41.265557: Current learning rate: 0.00327 +2025-10-31 07:37:03.509572: train_loss -0.9911 +2025-10-31 07:37:03.513681: val_loss -0.8919 +2025-10-31 07:37:03.516070: Pseudo dice [np.float32(0.9881), np.float32(0.9927), np.float32(0.9942), np.float32(0.7817)] +2025-10-31 07:37:03.519237: Epoch time: 22.25 s +2025-10-31 07:37:04.843130: +2025-10-31 07:37:04.845191: Epoch 712 +2025-10-31 07:37:04.847077: Current learning rate: 0.00326 +2025-10-31 07:37:26.700803: train_loss -0.9922 +2025-10-31 07:37:26.703201: val_loss -0.8848 +2025-10-31 07:37:26.704868: Pseudo dice [np.float32(0.9873), np.float32(0.9924), np.float32(0.9942), np.float32(0.7638)] +2025-10-31 07:37:26.706497: Epoch time: 21.86 s +2025-10-31 07:37:27.956410: +2025-10-31 07:37:27.958279: Epoch 713 +2025-10-31 07:37:27.960353: Current learning rate: 0.00325 +2025-10-31 07:37:50.596955: train_loss -0.9917 +2025-10-31 07:37:50.599818: val_loss -0.8802 +2025-10-31 07:37:50.601478: Pseudo dice [np.float32(0.9847), np.float32(0.991), np.float32(0.9937), np.float32(0.7725)] +2025-10-31 07:37:50.603463: Epoch time: 22.64 s +2025-10-31 07:37:51.895138: +2025-10-31 07:37:51.896900: Epoch 714 +2025-10-31 07:37:51.898449: Current learning rate: 0.00324 +2025-10-31 07:38:14.648783: train_loss -0.9909 +2025-10-31 07:38:14.653733: val_loss -0.8931 +2025-10-31 07:38:14.655794: Pseudo dice [np.float32(0.9867), np.float32(0.9924), np.float32(0.9947), np.float32(0.7892)] +2025-10-31 07:38:14.657938: Epoch time: 22.76 s +2025-10-31 07:38:16.468759: +2025-10-31 07:38:16.471133: Epoch 715 +2025-10-31 07:38:16.473267: Current learning rate: 0.00323 +2025-10-31 07:38:38.056226: train_loss -0.9916 +2025-10-31 07:38:38.059256: val_loss -0.8915 +2025-10-31 07:38:38.061211: Pseudo dice [np.float32(0.9875), np.float32(0.9927), np.float32(0.9944), np.float32(0.7841)] +2025-10-31 07:38:38.063012: Epoch time: 21.59 s +2025-10-31 07:38:39.319176: +2025-10-31 07:38:39.321133: Epoch 716 +2025-10-31 07:38:39.322896: Current learning rate: 0.00322 +2025-10-31 07:39:00.771988: train_loss -0.9932 +2025-10-31 07:39:00.775826: val_loss -0.8918 +2025-10-31 07:39:00.777510: Pseudo dice [np.float32(0.9861), np.float32(0.9917), np.float32(0.9945), np.float32(0.789)] +2025-10-31 07:39:00.779122: Epoch time: 21.45 s +2025-10-31 07:39:01.936979: +2025-10-31 07:39:01.938552: Epoch 717 +2025-10-31 07:39:01.939867: Current learning rate: 0.00321 +2025-10-31 07:39:23.628433: train_loss -0.9919 +2025-10-31 07:39:23.635663: val_loss -0.8902 +2025-10-31 07:39:23.637228: Pseudo dice [np.float32(0.9864), np.float32(0.9919), np.float32(0.9945), np.float32(0.789)] +2025-10-31 07:39:23.638755: Epoch time: 21.69 s +2025-10-31 07:39:24.916736: +2025-10-31 07:39:24.919009: Epoch 718 +2025-10-31 07:39:24.920695: Current learning rate: 0.0032 +2025-10-31 07:39:47.105748: train_loss -0.9917 +2025-10-31 07:39:47.108903: val_loss -0.895 +2025-10-31 07:39:47.110544: Pseudo dice [np.float32(0.987), np.float32(0.9922), np.float32(0.9947), np.float32(0.8008)] +2025-10-31 07:39:47.112173: Epoch time: 22.19 s +2025-10-31 07:39:48.337998: +2025-10-31 07:39:48.339852: Epoch 719 +2025-10-31 07:39:48.341524: Current learning rate: 0.00319 +2025-10-31 07:40:10.415665: train_loss -0.9928 +2025-10-31 07:40:10.418376: val_loss -0.8989 +2025-10-31 07:40:10.419945: Pseudo dice [np.float32(0.9868), np.float32(0.992), np.float32(0.9946), np.float32(0.8109)] +2025-10-31 07:40:10.421633: Epoch time: 22.08 s +2025-10-31 07:40:11.641160: +2025-10-31 07:40:11.643073: Epoch 720 +2025-10-31 07:40:11.644845: Current learning rate: 0.00318 +2025-10-31 07:40:34.266885: train_loss -0.9921 +2025-10-31 07:40:34.272479: val_loss -0.8842 +2025-10-31 07:40:34.274172: Pseudo dice [np.float32(0.986), np.float32(0.9909), np.float32(0.9938), np.float32(0.7786)] +2025-10-31 07:40:34.275841: Epoch time: 22.63 s +2025-10-31 07:40:35.562567: +2025-10-31 07:40:35.564576: Epoch 721 +2025-10-31 07:40:35.566414: Current learning rate: 0.00317 +2025-10-31 07:40:58.323564: train_loss -0.992 +2025-10-31 07:40:58.327325: val_loss -0.8931 +2025-10-31 07:40:58.328932: Pseudo dice [np.float32(0.9869), np.float32(0.9925), np.float32(0.9944), np.float32(0.7973)] +2025-10-31 07:40:58.330594: Epoch time: 22.76 s +2025-10-31 07:40:59.516192: +2025-10-31 07:40:59.517935: Epoch 722 +2025-10-31 07:40:59.519549: Current learning rate: 0.00316 +2025-10-31 07:41:20.605620: train_loss -0.992 +2025-10-31 07:41:20.608315: val_loss -0.8957 +2025-10-31 07:41:20.609902: Pseudo dice [np.float32(0.9862), np.float32(0.9917), np.float32(0.9943), np.float32(0.8039)] +2025-10-31 07:41:20.611472: Epoch time: 21.09 s +2025-10-31 07:41:21.879507: +2025-10-31 07:41:21.881872: Epoch 723 +2025-10-31 07:41:21.883609: Current learning rate: 0.00315 +2025-10-31 07:41:43.604153: train_loss -0.9913 +2025-10-31 07:41:43.607624: val_loss -0.8945 +2025-10-31 07:41:43.609410: Pseudo dice [np.float32(0.9871), np.float32(0.9921), np.float32(0.9943), np.float32(0.796)] +2025-10-31 07:41:43.611255: Epoch time: 21.73 s +2025-10-31 07:41:44.805179: +2025-10-31 07:41:44.807255: Epoch 724 +2025-10-31 07:41:44.809056: Current learning rate: 0.00314 +2025-10-31 07:42:07.881426: train_loss -0.9913 +2025-10-31 07:42:07.883963: val_loss -0.8933 +2025-10-31 07:42:07.885421: Pseudo dice [np.float32(0.9863), np.float32(0.992), np.float32(0.9946), np.float32(0.7979)] +2025-10-31 07:42:07.886796: Epoch time: 23.08 s +2025-10-31 07:42:09.128433: +2025-10-31 07:42:09.130149: Epoch 725 +2025-10-31 07:42:09.131636: Current learning rate: 0.00313 +2025-10-31 07:42:31.498092: train_loss -0.9914 +2025-10-31 07:42:31.501118: val_loss -0.8896 +2025-10-31 07:42:31.502738: Pseudo dice [np.float32(0.9871), np.float32(0.9915), np.float32(0.9938), np.float32(0.7877)] +2025-10-31 07:42:31.504245: Epoch time: 22.37 s +2025-10-31 07:42:32.771919: +2025-10-31 07:42:32.774325: Epoch 726 +2025-10-31 07:42:32.775911: Current learning rate: 0.00312 +2025-10-31 07:42:54.679004: train_loss -0.9919 +2025-10-31 07:42:54.683919: val_loss -0.8841 +2025-10-31 07:42:54.685245: Pseudo dice [np.float32(0.9851), np.float32(0.9912), np.float32(0.9941), np.float32(0.7884)] +2025-10-31 07:42:54.686641: Epoch time: 21.91 s +2025-10-31 07:42:56.401799: +2025-10-31 07:42:56.403793: Epoch 727 +2025-10-31 07:42:56.405426: Current learning rate: 0.00311 +2025-10-31 07:43:18.833345: train_loss -0.9926 +2025-10-31 07:43:18.837050: val_loss -0.8987 +2025-10-31 07:43:18.838892: Pseudo dice [np.float32(0.9876), np.float32(0.9919), np.float32(0.9943), np.float32(0.8072)] +2025-10-31 07:43:18.844163: Epoch time: 22.43 s +2025-10-31 07:43:20.101200: +2025-10-31 07:43:20.103019: Epoch 728 +2025-10-31 07:43:20.104527: Current learning rate: 0.0031 +2025-10-31 07:43:41.747690: train_loss -0.9923 +2025-10-31 07:43:41.752212: val_loss -0.8934 +2025-10-31 07:43:41.753803: Pseudo dice [np.float32(0.9865), np.float32(0.9925), np.float32(0.9946), np.float32(0.7919)] +2025-10-31 07:43:41.755351: Epoch time: 21.65 s +2025-10-31 07:43:42.806059: +2025-10-31 07:43:42.808031: Epoch 729 +2025-10-31 07:43:42.809698: Current learning rate: 0.00309 +2025-10-31 07:44:03.720439: train_loss -0.9921 +2025-10-31 07:44:03.723912: val_loss -0.8967 +2025-10-31 07:44:03.725701: Pseudo dice [np.float32(0.9867), np.float32(0.9922), np.float32(0.9946), np.float32(0.8066)] +2025-10-31 07:44:03.727467: Epoch time: 20.92 s +2025-10-31 07:44:04.964053: +2025-10-31 07:44:04.966000: Epoch 730 +2025-10-31 07:44:04.967651: Current learning rate: 0.00308 +2025-10-31 07:44:27.101174: train_loss -0.9916 +2025-10-31 07:44:27.103860: val_loss -0.8936 +2025-10-31 07:44:27.107294: Pseudo dice [np.float32(0.9864), np.float32(0.9918), np.float32(0.9944), np.float32(0.7948)] +2025-10-31 07:44:27.109280: Epoch time: 22.14 s +2025-10-31 07:44:28.413311: +2025-10-31 07:44:28.415287: Epoch 731 +2025-10-31 07:44:28.416800: Current learning rate: 0.00307 +2025-10-31 07:44:51.363195: train_loss -0.9918 +2025-10-31 07:44:51.365826: val_loss -0.9005 +2025-10-31 07:44:51.367744: Pseudo dice [np.float32(0.9869), np.float32(0.9926), np.float32(0.9953), np.float32(0.8101)] +2025-10-31 07:44:51.369663: Epoch time: 22.95 s +2025-10-31 07:44:52.677385: +2025-10-31 07:44:52.679206: Epoch 732 +2025-10-31 07:44:52.680904: Current learning rate: 0.00306 +2025-10-31 07:45:15.381658: train_loss -0.992 +2025-10-31 07:45:15.385546: val_loss -0.9007 +2025-10-31 07:45:15.387437: Pseudo dice [np.float32(0.9865), np.float32(0.992), np.float32(0.9948), np.float32(0.8105)] +2025-10-31 07:45:15.389183: Epoch time: 22.71 s +2025-10-31 07:45:16.552715: +2025-10-31 07:45:16.558446: Epoch 733 +2025-10-31 07:45:16.560229: Current learning rate: 0.00305 +2025-10-31 07:45:37.877849: train_loss -0.992 +2025-10-31 07:45:37.879907: val_loss -0.8922 +2025-10-31 07:45:37.881378: Pseudo dice [np.float32(0.9866), np.float32(0.9919), np.float32(0.9943), np.float32(0.8021)] +2025-10-31 07:45:37.882870: Epoch time: 21.33 s +2025-10-31 07:45:39.026118: +2025-10-31 07:45:39.027836: Epoch 734 +2025-10-31 07:45:39.029731: Current learning rate: 0.00304 +2025-10-31 07:46:01.440090: train_loss -0.9913 +2025-10-31 07:46:01.443081: val_loss -0.894 +2025-10-31 07:46:01.444841: Pseudo dice [np.float32(0.986), np.float32(0.9914), np.float32(0.9944), np.float32(0.7939)] +2025-10-31 07:46:01.446456: Epoch time: 22.42 s +2025-10-31 07:46:02.707594: +2025-10-31 07:46:02.709470: Epoch 735 +2025-10-31 07:46:02.712081: Current learning rate: 0.00303 +2025-10-31 07:46:25.716039: train_loss -0.9921 +2025-10-31 07:46:25.719033: val_loss -0.8964 +2025-10-31 07:46:25.720638: Pseudo dice [np.float32(0.9857), np.float32(0.9915), np.float32(0.9945), np.float32(0.8079)] +2025-10-31 07:46:25.722142: Epoch time: 23.01 s +2025-10-31 07:46:27.014463: +2025-10-31 07:46:27.016504: Epoch 736 +2025-10-31 07:46:27.018162: Current learning rate: 0.00302 +2025-10-31 07:46:48.054039: train_loss -0.9918 +2025-10-31 07:46:48.061184: val_loss -0.8935 +2025-10-31 07:46:48.063184: Pseudo dice [np.float32(0.9863), np.float32(0.9916), np.float32(0.9945), np.float32(0.8022)] +2025-10-31 07:46:48.064877: Epoch time: 21.04 s +2025-10-31 07:46:49.354858: +2025-10-31 07:46:49.356787: Epoch 737 +2025-10-31 07:46:49.358936: Current learning rate: 0.00301 +2025-10-31 07:47:11.927443: train_loss -0.9924 +2025-10-31 07:47:11.932705: val_loss -0.8986 +2025-10-31 07:47:11.937284: Pseudo dice [np.float32(0.9848), np.float32(0.9916), np.float32(0.9948), np.float32(0.8153)] +2025-10-31 07:47:11.941174: Epoch time: 22.57 s +2025-10-31 07:47:13.131994: +2025-10-31 07:47:13.134013: Epoch 738 +2025-10-31 07:47:13.135584: Current learning rate: 0.003 +2025-10-31 07:47:35.089106: train_loss -0.9922 +2025-10-31 07:47:35.093602: val_loss -0.895 +2025-10-31 07:47:35.095431: Pseudo dice [np.float32(0.9871), np.float32(0.9921), np.float32(0.9947), np.float32(0.8009)] +2025-10-31 07:47:35.096984: Epoch time: 21.96 s +2025-10-31 07:47:36.803430: +2025-10-31 07:47:36.805647: Epoch 739 +2025-10-31 07:47:36.807464: Current learning rate: 0.00299 +2025-10-31 07:47:58.312494: train_loss -0.9918 +2025-10-31 07:47:58.315161: val_loss -0.9052 +2025-10-31 07:47:58.316713: Pseudo dice [np.float32(0.9876), np.float32(0.9929), np.float32(0.9951), np.float32(0.8176)] +2025-10-31 07:47:58.318337: Epoch time: 21.51 s +2025-10-31 07:47:58.319895: Yayy! New best EMA pseudo Dice: 0.9437999725341797 +2025-10-31 07:48:00.885812: +2025-10-31 07:48:00.888487: Epoch 740 +2025-10-31 07:48:00.890108: Current learning rate: 0.00297 +2025-10-31 07:48:22.874108: train_loss -0.9917 +2025-10-31 07:48:22.880211: val_loss -0.8967 +2025-10-31 07:48:22.881708: Pseudo dice [np.float32(0.9872), np.float32(0.9921), np.float32(0.9945), np.float32(0.8039)] +2025-10-31 07:48:22.883113: Epoch time: 21.99 s +2025-10-31 07:48:22.884492: Yayy! New best EMA pseudo Dice: 0.9438999891281128 +2025-10-31 07:48:25.242344: +2025-10-31 07:48:25.243961: Epoch 741 +2025-10-31 07:48:25.245423: Current learning rate: 0.00296 +2025-10-31 07:48:47.919211: train_loss -0.9921 +2025-10-31 07:48:47.922549: val_loss -0.9004 +2025-10-31 07:48:47.924277: Pseudo dice [np.float32(0.988), np.float32(0.9921), np.float32(0.9948), np.float32(0.8074)] +2025-10-31 07:48:47.925961: Epoch time: 22.68 s +2025-10-31 07:48:47.927612: Yayy! New best EMA pseudo Dice: 0.9440000057220459 +2025-10-31 07:48:50.438186: +2025-10-31 07:48:50.440152: Epoch 742 +2025-10-31 07:48:50.442076: Current learning rate: 0.00295 +2025-10-31 07:49:11.929411: train_loss -0.9915 +2025-10-31 07:49:11.931691: val_loss -0.8978 +2025-10-31 07:49:11.933283: Pseudo dice [np.float32(0.9853), np.float32(0.9921), np.float32(0.9946), np.float32(0.8075)] +2025-10-31 07:49:11.934966: Epoch time: 21.49 s +2025-10-31 07:49:11.936440: Yayy! New best EMA pseudo Dice: 0.944100022315979 +2025-10-31 07:49:14.479989: +2025-10-31 07:49:14.482339: Epoch 743 +2025-10-31 07:49:14.484565: Current learning rate: 0.00294 +2025-10-31 07:49:36.419921: train_loss -0.9917 +2025-10-31 07:49:36.423998: val_loss -0.8901 +2025-10-31 07:49:36.426182: Pseudo dice [np.float32(0.9855), np.float32(0.9914), np.float32(0.9942), np.float32(0.7918)] +2025-10-31 07:49:36.428180: Epoch time: 21.94 s +2025-10-31 07:49:37.675283: +2025-10-31 07:49:37.677076: Epoch 744 +2025-10-31 07:49:37.678776: Current learning rate: 0.00293 +2025-10-31 07:50:00.752653: train_loss -0.9923 +2025-10-31 07:50:00.757580: val_loss -0.8858 +2025-10-31 07:50:00.758921: Pseudo dice [np.float32(0.9866), np.float32(0.9923), np.float32(0.9943), np.float32(0.7826)] +2025-10-31 07:50:00.760460: Epoch time: 23.08 s +2025-10-31 07:50:02.005049: +2025-10-31 07:50:02.006912: Epoch 745 +2025-10-31 07:50:02.010863: Current learning rate: 0.00292 +2025-10-31 07:50:23.681098: train_loss -0.9924 +2025-10-31 07:50:23.684486: val_loss -0.8859 +2025-10-31 07:50:23.686189: Pseudo dice [np.float32(0.9864), np.float32(0.9914), np.float32(0.994), np.float32(0.7792)] +2025-10-31 07:50:23.688568: Epoch time: 21.68 s +2025-10-31 07:50:24.604635: +2025-10-31 07:50:24.606425: Epoch 746 +2025-10-31 07:50:24.607895: Current learning rate: 0.00291 +2025-10-31 07:50:46.053447: train_loss -0.9918 +2025-10-31 07:50:46.058989: val_loss -0.8862 +2025-10-31 07:50:46.060589: Pseudo dice [np.float32(0.9862), np.float32(0.9916), np.float32(0.9944), np.float32(0.7887)] +2025-10-31 07:50:46.062349: Epoch time: 21.45 s +2025-10-31 07:50:47.299556: +2025-10-31 07:50:47.301253: Epoch 747 +2025-10-31 07:50:47.302672: Current learning rate: 0.0029 +2025-10-31 07:51:09.755309: train_loss -0.9925 +2025-10-31 07:51:09.760011: val_loss -0.8906 +2025-10-31 07:51:09.762008: Pseudo dice [np.float32(0.9871), np.float32(0.9905), np.float32(0.9944), np.float32(0.7971)] +2025-10-31 07:51:09.763943: Epoch time: 22.46 s +2025-10-31 07:51:10.941603: +2025-10-31 07:51:10.943233: Epoch 748 +2025-10-31 07:51:10.945065: Current learning rate: 0.00289 +2025-10-31 07:51:32.810819: train_loss -0.9921 +2025-10-31 07:51:32.814648: val_loss -0.8982 +2025-10-31 07:51:32.816196: Pseudo dice [np.float32(0.9873), np.float32(0.9925), np.float32(0.9947), np.float32(0.7996)] +2025-10-31 07:51:32.817716: Epoch time: 21.87 s +2025-10-31 07:51:34.114872: +2025-10-31 07:51:34.116836: Epoch 749 +2025-10-31 07:51:34.118443: Current learning rate: 0.00288 +2025-10-31 07:51:55.898018: train_loss -0.9924 +2025-10-31 07:51:55.901817: val_loss -0.8948 +2025-10-31 07:51:55.903427: Pseudo dice [np.float32(0.9878), np.float32(0.9916), np.float32(0.9945), np.float32(0.7996)] +2025-10-31 07:51:55.905078: Epoch time: 21.79 s +2025-10-31 07:51:59.085127: +2025-10-31 07:51:59.087342: Epoch 750 +2025-10-31 07:51:59.088986: Current learning rate: 0.00287 +2025-10-31 07:52:21.303030: train_loss -0.9927 +2025-10-31 07:52:21.307119: val_loss -0.8865 +2025-10-31 07:52:21.310116: Pseudo dice [np.float32(0.9863), np.float32(0.9916), np.float32(0.9943), np.float32(0.7767)] +2025-10-31 07:52:21.311956: Epoch time: 22.22 s +2025-10-31 07:52:22.594512: +2025-10-31 07:52:22.596498: Epoch 751 +2025-10-31 07:52:22.598120: Current learning rate: 0.00286 +2025-10-31 07:52:43.674471: train_loss -0.9925 +2025-10-31 07:52:43.677032: val_loss -0.8915 +2025-10-31 07:52:43.678710: Pseudo dice [np.float32(0.9855), np.float32(0.991), np.float32(0.9943), np.float32(0.7999)] +2025-10-31 07:52:43.680335: Epoch time: 21.08 s +2025-10-31 07:52:44.958249: +2025-10-31 07:52:44.960151: Epoch 752 +2025-10-31 07:52:44.961801: Current learning rate: 0.00285 +2025-10-31 07:53:06.553014: train_loss -0.9922 +2025-10-31 07:53:06.555556: val_loss -0.896 +2025-10-31 07:53:06.557083: Pseudo dice [np.float32(0.9853), np.float32(0.9914), np.float32(0.9947), np.float32(0.8082)] +2025-10-31 07:53:06.558514: Epoch time: 21.6 s +2025-10-31 07:53:07.793922: +2025-10-31 07:53:07.795652: Epoch 753 +2025-10-31 07:53:07.796984: Current learning rate: 0.00284 +2025-10-31 07:53:29.665527: train_loss -0.9927 +2025-10-31 07:53:29.668565: val_loss -0.8862 +2025-10-31 07:53:29.670340: Pseudo dice [np.float32(0.9856), np.float32(0.992), np.float32(0.9941), np.float32(0.7866)] +2025-10-31 07:53:29.672176: Epoch time: 21.87 s +2025-10-31 07:53:30.846903: +2025-10-31 07:53:30.848910: Epoch 754 +2025-10-31 07:53:30.850744: Current learning rate: 0.00283 +2025-10-31 07:53:52.246484: train_loss -0.9925 +2025-10-31 07:53:52.249169: val_loss -0.8813 +2025-10-31 07:53:52.251078: Pseudo dice [np.float32(0.9853), np.float32(0.9907), np.float32(0.9936), np.float32(0.7814)] +2025-10-31 07:53:52.252851: Epoch time: 21.4 s +2025-10-31 07:53:53.421043: +2025-10-31 07:53:53.422920: Epoch 755 +2025-10-31 07:53:53.424585: Current learning rate: 0.00282 +2025-10-31 07:54:15.960714: train_loss -0.9924 +2025-10-31 07:54:15.963747: val_loss -0.8901 +2025-10-31 07:54:15.965563: Pseudo dice [np.float32(0.985), np.float32(0.9915), np.float32(0.9946), np.float32(0.7983)] +2025-10-31 07:54:15.967265: Epoch time: 22.54 s +2025-10-31 07:54:17.097279: +2025-10-31 07:54:17.099487: Epoch 756 +2025-10-31 07:54:17.101134: Current learning rate: 0.00281 +2025-10-31 07:54:38.518361: train_loss -0.9926 +2025-10-31 07:54:38.520887: val_loss -0.8896 +2025-10-31 07:54:38.522337: Pseudo dice [np.float32(0.9872), np.float32(0.9927), np.float32(0.9944), np.float32(0.7799)] +2025-10-31 07:54:38.523863: Epoch time: 21.42 s +2025-10-31 07:54:39.850746: +2025-10-31 07:54:39.884530: Epoch 757 +2025-10-31 07:54:39.886960: Current learning rate: 0.0028 +2025-10-31 07:54:59.500361: train_loss -0.9916 +2025-10-31 07:54:59.513805: val_loss -0.8902 +2025-10-31 07:54:59.524261: Pseudo dice [np.float32(0.9864), np.float32(0.9926), np.float32(0.9944), np.float32(0.793)] +2025-10-31 07:54:59.538173: Epoch time: 19.65 s +2025-10-31 07:55:00.700265: +2025-10-31 07:55:00.707740: Epoch 758 +2025-10-31 07:55:00.715322: Current learning rate: 0.00279 +2025-10-31 07:55:22.317992: train_loss -0.9925 +2025-10-31 07:55:22.319998: val_loss -0.8864 +2025-10-31 07:55:22.321521: Pseudo dice [np.float32(0.9857), np.float32(0.9916), np.float32(0.9942), np.float32(0.7842)] +2025-10-31 07:55:22.323197: Epoch time: 21.62 s +2025-10-31 07:55:23.522672: +2025-10-31 07:55:23.539154: Epoch 759 +2025-10-31 07:55:23.556610: Current learning rate: 0.00278 +2025-10-31 07:55:45.842081: train_loss -0.9922 +2025-10-31 07:55:45.844812: val_loss -0.889 +2025-10-31 07:55:45.846364: Pseudo dice [np.float32(0.9866), np.float32(0.9915), np.float32(0.9941), np.float32(0.7866)] +2025-10-31 07:55:45.848004: Epoch time: 22.32 s +2025-10-31 07:55:47.073459: +2025-10-31 07:55:47.075259: Epoch 760 +2025-10-31 07:55:47.076790: Current learning rate: 0.00277 +2025-10-31 07:56:08.920389: train_loss -0.9925 +2025-10-31 07:56:08.922983: val_loss -0.8892 +2025-10-31 07:56:08.924791: Pseudo dice [np.float32(0.9863), np.float32(0.9917), np.float32(0.9943), np.float32(0.7879)] +2025-10-31 07:56:08.927012: Epoch time: 21.85 s +2025-10-31 07:56:10.244736: +2025-10-31 07:56:10.246450: Epoch 761 +2025-10-31 07:56:10.248353: Current learning rate: 0.00276 +2025-10-31 07:56:31.187269: train_loss -0.9928 +2025-10-31 07:56:31.190552: val_loss -0.8845 +2025-10-31 07:56:31.192421: Pseudo dice [np.float32(0.985), np.float32(0.9911), np.float32(0.9942), np.float32(0.783)] +2025-10-31 07:56:31.194219: Epoch time: 20.94 s +2025-10-31 07:56:32.797274: +2025-10-31 07:56:32.798819: Epoch 762 +2025-10-31 07:56:32.800236: Current learning rate: 0.00275 +2025-10-31 07:56:55.308271: train_loss -0.9925 +2025-10-31 07:56:55.314158: val_loss -0.8944 +2025-10-31 07:56:55.315989: Pseudo dice [np.float32(0.9858), np.float32(0.991), np.float32(0.9946), np.float32(0.805)] +2025-10-31 07:56:55.317584: Epoch time: 22.51 s +2025-10-31 07:56:56.488602: +2025-10-31 07:56:56.490390: Epoch 763 +2025-10-31 07:56:56.491885: Current learning rate: 0.00274 +2025-10-31 07:57:18.464164: train_loss -0.9913 +2025-10-31 07:57:18.466734: val_loss -0.8905 +2025-10-31 07:57:18.468462: Pseudo dice [np.float32(0.986), np.float32(0.9912), np.float32(0.9943), np.float32(0.7936)] +2025-10-31 07:57:18.470220: Epoch time: 21.98 s +2025-10-31 07:57:19.767146: +2025-10-31 07:57:19.783533: Epoch 764 +2025-10-31 07:57:19.798961: Current learning rate: 0.00273 +2025-10-31 07:57:40.813231: train_loss -0.9915 +2025-10-31 07:57:40.815691: val_loss -0.8992 +2025-10-31 07:57:40.817201: Pseudo dice [np.float32(0.9856), np.float32(0.9918), np.float32(0.9949), np.float32(0.8188)] +2025-10-31 07:57:40.818830: Epoch time: 21.05 s +2025-10-31 07:57:42.066196: +2025-10-31 07:57:42.068092: Epoch 765 +2025-10-31 07:57:42.069689: Current learning rate: 0.00272 +2025-10-31 07:58:04.871440: train_loss -0.9922 +2025-10-31 07:58:04.874305: val_loss -0.8945 +2025-10-31 07:58:04.875877: Pseudo dice [np.float32(0.9862), np.float32(0.992), np.float32(0.9945), np.float32(0.8036)] +2025-10-31 07:58:04.877476: Epoch time: 22.81 s +2025-10-31 07:58:06.132292: +2025-10-31 07:58:06.134217: Epoch 766 +2025-10-31 07:58:06.135745: Current learning rate: 0.00271 +2025-10-31 07:58:27.810486: train_loss -0.9922 +2025-10-31 07:58:27.812446: val_loss -0.892 +2025-10-31 07:58:27.813826: Pseudo dice [np.float32(0.986), np.float32(0.9912), np.float32(0.9943), np.float32(0.8033)] +2025-10-31 07:58:27.815258: Epoch time: 21.68 s +2025-10-31 07:58:29.035487: +2025-10-31 07:58:29.037266: Epoch 767 +2025-10-31 07:58:29.038882: Current learning rate: 0.0027 +2025-10-31 07:58:50.212227: train_loss -0.9924 +2025-10-31 07:58:50.215159: val_loss -0.8971 +2025-10-31 07:58:50.216976: Pseudo dice [np.float32(0.9855), np.float32(0.9918), np.float32(0.9949), np.float32(0.8068)] +2025-10-31 07:58:50.218724: Epoch time: 21.18 s +2025-10-31 07:58:51.500723: +2025-10-31 07:58:51.502977: Epoch 768 +2025-10-31 07:58:51.504587: Current learning rate: 0.00268 +2025-10-31 07:59:14.085364: train_loss -0.9925 +2025-10-31 07:59:14.088469: val_loss -0.8894 +2025-10-31 07:59:14.090005: Pseudo dice [np.float32(0.9869), np.float32(0.9915), np.float32(0.994), np.float32(0.788)] +2025-10-31 07:59:14.091472: Epoch time: 22.59 s +2025-10-31 07:59:15.358832: +2025-10-31 07:59:15.361016: Epoch 769 +2025-10-31 07:59:15.362888: Current learning rate: 0.00267 +2025-10-31 07:59:37.395899: train_loss -0.9926 +2025-10-31 07:59:37.398474: val_loss -0.89 +2025-10-31 07:59:37.400316: Pseudo dice [np.float32(0.9858), np.float32(0.9914), np.float32(0.9945), np.float32(0.7944)] +2025-10-31 07:59:37.402112: Epoch time: 22.04 s +2025-10-31 07:59:38.518880: +2025-10-31 07:59:38.520590: Epoch 770 +2025-10-31 07:59:38.522042: Current learning rate: 0.00266 +2025-10-31 07:59:59.732254: train_loss -0.992 +2025-10-31 07:59:59.736670: val_loss -0.8936 +2025-10-31 07:59:59.738239: Pseudo dice [np.float32(0.9851), np.float32(0.9912), np.float32(0.9944), np.float32(0.8028)] +2025-10-31 07:59:59.739886: Epoch time: 21.21 s +2025-10-31 08:00:00.909540: +2025-10-31 08:00:00.911673: Epoch 771 +2025-10-31 08:00:00.913541: Current learning rate: 0.00265 +2025-10-31 08:00:22.741974: train_loss -0.992 +2025-10-31 08:00:22.745754: val_loss -0.8952 +2025-10-31 08:00:22.747906: Pseudo dice [np.float32(0.9851), np.float32(0.9917), np.float32(0.9947), np.float32(0.8012)] +2025-10-31 08:00:22.749895: Epoch time: 21.83 s +2025-10-31 08:00:24.059478: +2025-10-31 08:00:24.061301: Epoch 772 +2025-10-31 08:00:24.062839: Current learning rate: 0.00264 +2025-10-31 08:00:45.907136: train_loss -0.9925 +2025-10-31 08:00:45.909294: val_loss -0.8868 +2025-10-31 08:00:45.910807: Pseudo dice [np.float32(0.985), np.float32(0.9911), np.float32(0.9942), np.float32(0.7896)] +2025-10-31 08:00:45.912210: Epoch time: 21.85 s +2025-10-31 08:00:47.593757: +2025-10-31 08:00:47.595422: Epoch 773 +2025-10-31 08:00:47.596756: Current learning rate: 0.00263 +2025-10-31 08:01:10.309845: train_loss -0.992 +2025-10-31 08:01:10.312555: val_loss -0.8935 +2025-10-31 08:01:10.314237: Pseudo dice [np.float32(0.9863), np.float32(0.9915), np.float32(0.9945), np.float32(0.8026)] +2025-10-31 08:01:10.315990: Epoch time: 22.72 s +2025-10-31 08:01:11.596628: +2025-10-31 08:01:11.598496: Epoch 774 +2025-10-31 08:01:11.600132: Current learning rate: 0.00262 +2025-10-31 08:01:34.094692: train_loss -0.9925 +2025-10-31 08:01:34.098065: val_loss -0.8926 +2025-10-31 08:01:34.099637: Pseudo dice [np.float32(0.9855), np.float32(0.9909), np.float32(0.9943), np.float32(0.8016)] +2025-10-31 08:01:34.101152: Epoch time: 22.5 s +2025-10-31 08:01:35.201593: +2025-10-31 08:01:35.203572: Epoch 775 +2025-10-31 08:01:35.205020: Current learning rate: 0.00261 +2025-10-31 08:01:56.805743: train_loss -0.9919 +2025-10-31 08:01:56.809784: val_loss -0.894 +2025-10-31 08:01:56.811546: Pseudo dice [np.float32(0.9862), np.float32(0.9917), np.float32(0.9942), np.float32(0.8017)] +2025-10-31 08:01:56.813213: Epoch time: 21.61 s +2025-10-31 08:01:58.019790: +2025-10-31 08:01:58.021676: Epoch 776 +2025-10-31 08:01:58.023135: Current learning rate: 0.0026 +2025-10-31 08:02:18.995974: train_loss -0.9922 +2025-10-31 08:02:19.000219: val_loss -0.8911 +2025-10-31 08:02:19.002400: Pseudo dice [np.float32(0.9863), np.float32(0.9916), np.float32(0.9943), np.float32(0.7921)] +2025-10-31 08:02:19.004382: Epoch time: 20.98 s +2025-10-31 08:02:20.303408: +2025-10-31 08:02:20.305597: Epoch 777 +2025-10-31 08:02:20.307427: Current learning rate: 0.00259 +2025-10-31 08:02:43.001772: train_loss -0.9923 +2025-10-31 08:02:43.008616: val_loss -0.8879 +2025-10-31 08:02:43.010368: Pseudo dice [np.float32(0.9862), np.float32(0.9908), np.float32(0.9944), np.float32(0.784)] +2025-10-31 08:02:43.012081: Epoch time: 22.7 s +2025-10-31 08:02:44.004035: +2025-10-31 08:02:44.006292: Epoch 778 +2025-10-31 08:02:44.007942: Current learning rate: 0.00258 +2025-10-31 08:03:05.640783: train_loss -0.9921 +2025-10-31 08:03:05.644496: val_loss -0.8956 +2025-10-31 08:03:05.646261: Pseudo dice [np.float32(0.9865), np.float32(0.992), np.float32(0.9946), np.float32(0.8137)] +2025-10-31 08:03:05.647857: Epoch time: 21.64 s +2025-10-31 08:03:06.811813: +2025-10-31 08:03:06.813859: Epoch 779 +2025-10-31 08:03:06.815444: Current learning rate: 0.00257 +2025-10-31 08:03:29.249267: train_loss -0.9922 +2025-10-31 08:03:29.252769: val_loss -0.891 +2025-10-31 08:03:29.254311: Pseudo dice [np.float32(0.9843), np.float32(0.9902), np.float32(0.9944), np.float32(0.8061)] +2025-10-31 08:03:29.255750: Epoch time: 22.44 s +2025-10-31 08:03:30.308211: +2025-10-31 08:03:30.310281: Epoch 780 +2025-10-31 08:03:30.311897: Current learning rate: 0.00256 +2025-10-31 08:03:51.942103: train_loss -0.9927 +2025-10-31 08:03:51.945722: val_loss -0.8948 +2025-10-31 08:03:51.947232: Pseudo dice [np.float32(0.9865), np.float32(0.9914), np.float32(0.9942), np.float32(0.8033)] +2025-10-31 08:03:51.948858: Epoch time: 21.64 s +2025-10-31 08:03:53.191120: +2025-10-31 08:03:53.193336: Epoch 781 +2025-10-31 08:03:53.194808: Current learning rate: 0.00255 +2025-10-31 08:04:15.346383: train_loss -0.9925 +2025-10-31 08:04:15.350362: val_loss -0.8859 +2025-10-31 08:04:15.352122: Pseudo dice [np.float32(0.9882), np.float32(0.9916), np.float32(0.9938), np.float32(0.778)] +2025-10-31 08:04:15.353746: Epoch time: 22.16 s +2025-10-31 08:04:16.689347: +2025-10-31 08:04:16.693846: Epoch 782 +2025-10-31 08:04:16.695460: Current learning rate: 0.00254 +2025-10-31 08:04:36.508319: train_loss -0.9928 +2025-10-31 08:04:36.511041: val_loss -0.891 +2025-10-31 08:04:36.512469: Pseudo dice [np.float32(0.986), np.float32(0.9918), np.float32(0.9944), np.float32(0.7986)] +2025-10-31 08:04:36.513813: Epoch time: 19.82 s +2025-10-31 08:04:37.653700: +2025-10-31 08:04:37.659539: Epoch 783 +2025-10-31 08:04:37.661300: Current learning rate: 0.00253 +2025-10-31 08:04:59.923770: train_loss -0.9923 +2025-10-31 08:04:59.926419: val_loss -0.8963 +2025-10-31 08:04:59.927816: Pseudo dice [np.float32(0.9858), np.float32(0.9917), np.float32(0.9946), np.float32(0.8093)] +2025-10-31 08:04:59.929311: Epoch time: 22.27 s +2025-10-31 08:05:01.110333: +2025-10-31 08:05:01.112237: Epoch 784 +2025-10-31 08:05:01.113882: Current learning rate: 0.00252 +2025-10-31 08:05:23.728778: train_loss -0.9924 +2025-10-31 08:05:23.733589: val_loss -0.8895 +2025-10-31 08:05:23.735208: Pseudo dice [np.float32(0.9875), np.float32(0.9919), np.float32(0.9941), np.float32(0.7857)] +2025-10-31 08:05:23.736757: Epoch time: 22.62 s +2025-10-31 08:05:25.380205: +2025-10-31 08:05:25.382217: Epoch 785 +2025-10-31 08:05:25.383859: Current learning rate: 0.00251 +2025-10-31 08:05:48.465808: train_loss -0.9922 +2025-10-31 08:05:48.468578: val_loss -0.8854 +2025-10-31 08:05:48.470191: Pseudo dice [np.float32(0.986), np.float32(0.9913), np.float32(0.9941), np.float32(0.7837)] +2025-10-31 08:05:48.471528: Epoch time: 23.09 s +2025-10-31 08:05:49.436672: +2025-10-31 08:05:49.438396: Epoch 786 +2025-10-31 08:05:49.439827: Current learning rate: 0.0025 +2025-10-31 08:06:10.518981: train_loss -0.9925 +2025-10-31 08:06:10.522180: val_loss -0.8968 +2025-10-31 08:06:10.523847: Pseudo dice [np.float32(0.9854), np.float32(0.9916), np.float32(0.9948), np.float32(0.812)] +2025-10-31 08:06:10.525509: Epoch time: 21.08 s +2025-10-31 08:06:11.746610: +2025-10-31 08:06:11.748505: Epoch 787 +2025-10-31 08:06:11.749951: Current learning rate: 0.00249 +2025-10-31 08:06:34.175667: train_loss -0.9927 +2025-10-31 08:06:34.178678: val_loss -0.8873 +2025-10-31 08:06:34.180253: Pseudo dice [np.float32(0.9845), np.float32(0.9909), np.float32(0.9942), np.float32(0.7931)] +2025-10-31 08:06:34.181745: Epoch time: 22.43 s +2025-10-31 08:06:35.491127: +2025-10-31 08:06:35.492997: Epoch 788 +2025-10-31 08:06:35.494518: Current learning rate: 0.00248 +2025-10-31 08:06:57.043923: train_loss -0.9924 +2025-10-31 08:06:57.049369: val_loss -0.8956 +2025-10-31 08:06:57.050933: Pseudo dice [np.float32(0.9851), np.float32(0.9913), np.float32(0.9945), np.float32(0.809)] +2025-10-31 08:06:57.052587: Epoch time: 21.55 s +2025-10-31 08:06:58.297480: +2025-10-31 08:06:58.299187: Epoch 789 +2025-10-31 08:06:58.300684: Current learning rate: 0.00247 +2025-10-31 08:07:20.762014: train_loss -0.9924 +2025-10-31 08:07:20.765210: val_loss -0.8969 +2025-10-31 08:07:20.766902: Pseudo dice [np.float32(0.9871), np.float32(0.9924), np.float32(0.9946), np.float32(0.8098)] +2025-10-31 08:07:20.768600: Epoch time: 22.47 s +2025-10-31 08:07:22.159106: +2025-10-31 08:07:22.161761: Epoch 790 +2025-10-31 08:07:22.163914: Current learning rate: 0.00245 +2025-10-31 08:07:44.446189: train_loss -0.992 +2025-10-31 08:07:44.449078: val_loss -0.8916 +2025-10-31 08:07:44.450812: Pseudo dice [np.float32(0.9848), np.float32(0.9917), np.float32(0.9946), np.float32(0.7882)] +2025-10-31 08:07:44.452478: Epoch time: 22.29 s +2025-10-31 08:07:45.717350: +2025-10-31 08:07:45.719203: Epoch 791 +2025-10-31 08:07:45.720834: Current learning rate: 0.00244 +2025-10-31 08:08:08.298218: train_loss -0.9926 +2025-10-31 08:08:08.302904: val_loss -0.9007 +2025-10-31 08:08:08.304921: Pseudo dice [np.float32(0.9859), np.float32(0.9914), np.float32(0.9953), np.float32(0.8115)] +2025-10-31 08:08:08.307067: Epoch time: 22.58 s +2025-10-31 08:08:09.579375: +2025-10-31 08:08:09.581270: Epoch 792 +2025-10-31 08:08:09.582925: Current learning rate: 0.00243 +2025-10-31 08:08:32.098532: train_loss -0.993 +2025-10-31 08:08:32.103846: val_loss -0.893 +2025-10-31 08:08:32.105744: Pseudo dice [np.float32(0.9864), np.float32(0.9917), np.float32(0.9943), np.float32(0.7986)] +2025-10-31 08:08:32.107758: Epoch time: 22.52 s +2025-10-31 08:08:33.458602: +2025-10-31 08:08:33.460476: Epoch 793 +2025-10-31 08:08:33.462007: Current learning rate: 0.00242 +2025-10-31 08:08:53.302351: train_loss -0.9924 +2025-10-31 08:08:53.306009: val_loss -0.9068 +2025-10-31 08:08:53.309074: Pseudo dice [np.float32(0.9857), np.float32(0.9912), np.float32(0.9953), np.float32(0.832)] +2025-10-31 08:08:53.310924: Epoch time: 19.85 s +2025-10-31 08:08:54.558988: +2025-10-31 08:08:54.560887: Epoch 794 +2025-10-31 08:08:54.562558: Current learning rate: 0.00241 +2025-10-31 08:09:16.722717: train_loss -0.9925 +2025-10-31 08:09:16.725697: val_loss -0.8981 +2025-10-31 08:09:16.728054: Pseudo dice [np.float32(0.9854), np.float32(0.9908), np.float32(0.9949), np.float32(0.8125)] +2025-10-31 08:09:16.730378: Epoch time: 22.17 s +2025-10-31 08:09:17.975154: +2025-10-31 08:09:17.976898: Epoch 795 +2025-10-31 08:09:17.978488: Current learning rate: 0.0024 +2025-10-31 08:09:40.794704: train_loss -0.9926 +2025-10-31 08:09:40.801650: val_loss -0.8847 +2025-10-31 08:09:40.803533: Pseudo dice [np.float32(0.9862), np.float32(0.9914), np.float32(0.9944), np.float32(0.7823)] +2025-10-31 08:09:40.805412: Epoch time: 22.82 s +2025-10-31 08:09:42.121412: +2025-10-31 08:09:42.123685: Epoch 796 +2025-10-31 08:09:42.125375: Current learning rate: 0.00239 +2025-10-31 08:10:04.575856: train_loss -0.9924 +2025-10-31 08:10:04.581864: val_loss -0.8923 +2025-10-31 08:10:04.583418: Pseudo dice [np.float32(0.9854), np.float32(0.9915), np.float32(0.9945), np.float32(0.7902)] +2025-10-31 08:10:04.585107: Epoch time: 22.46 s +2025-10-31 08:10:05.863148: +2025-10-31 08:10:05.865066: Epoch 797 +2025-10-31 08:10:05.866596: Current learning rate: 0.00238 +2025-10-31 08:10:27.622850: train_loss -0.9927 +2025-10-31 08:10:27.624841: val_loss -0.8909 +2025-10-31 08:10:27.626931: Pseudo dice [np.float32(0.987), np.float32(0.9914), np.float32(0.9943), np.float32(0.7894)] +2025-10-31 08:10:27.628755: Epoch time: 21.76 s +2025-10-31 08:10:28.719064: +2025-10-31 08:10:28.720953: Epoch 798 +2025-10-31 08:10:28.722610: Current learning rate: 0.00237 +2025-10-31 08:10:50.967498: train_loss -0.9928 +2025-10-31 08:10:50.970215: val_loss -0.8902 +2025-10-31 08:10:50.971788: Pseudo dice [np.float32(0.9869), np.float32(0.9917), np.float32(0.9947), np.float32(0.7858)] +2025-10-31 08:10:50.973418: Epoch time: 22.25 s +2025-10-31 08:10:52.074168: +2025-10-31 08:10:52.076332: Epoch 799 +2025-10-31 08:10:52.077905: Current learning rate: 0.00236 +2025-10-31 08:11:12.545325: train_loss -0.9921 +2025-10-31 08:11:12.547798: val_loss -0.8879 +2025-10-31 08:11:12.552800: Pseudo dice [np.float32(0.9864), np.float32(0.9917), np.float32(0.9946), np.float32(0.7848)] +2025-10-31 08:11:12.554738: Epoch time: 20.47 s +2025-10-31 08:11:15.108258: +2025-10-31 08:11:15.110677: Epoch 800 +2025-10-31 08:11:15.112653: Current learning rate: 0.00235 +2025-10-31 08:11:36.707486: train_loss -0.9922 +2025-10-31 08:11:36.710223: val_loss -0.9002 +2025-10-31 08:11:36.712445: Pseudo dice [np.float32(0.9877), np.float32(0.9925), np.float32(0.9949), np.float32(0.8091)] +2025-10-31 08:11:36.714461: Epoch time: 21.6 s +2025-10-31 08:11:37.941834: +2025-10-31 08:11:37.944798: Epoch 801 +2025-10-31 08:11:37.946718: Current learning rate: 0.00234 +2025-10-31 08:12:00.394238: train_loss -0.9932 +2025-10-31 08:12:00.398062: val_loss -0.8834 +2025-10-31 08:12:00.399806: Pseudo dice [np.float32(0.9857), np.float32(0.9914), np.float32(0.994), np.float32(0.7807)] +2025-10-31 08:12:00.401313: Epoch time: 22.45 s +2025-10-31 08:12:01.520075: +2025-10-31 08:12:01.522325: Epoch 802 +2025-10-31 08:12:01.524401: Current learning rate: 0.00233 +2025-10-31 08:12:24.226221: train_loss -0.9921 +2025-10-31 08:12:24.228597: val_loss -0.8959 +2025-10-31 08:12:24.230215: Pseudo dice [np.float32(0.9864), np.float32(0.9918), np.float32(0.9948), np.float32(0.8017)] +2025-10-31 08:12:24.231761: Epoch time: 22.71 s +2025-10-31 08:12:25.514899: +2025-10-31 08:12:25.516751: Epoch 803 +2025-10-31 08:12:25.518299: Current learning rate: 0.00232 +2025-10-31 08:12:47.644538: train_loss -0.9927 +2025-10-31 08:12:47.646764: val_loss -0.8991 +2025-10-31 08:12:47.648367: Pseudo dice [np.float32(0.9861), np.float32(0.9922), np.float32(0.9951), np.float32(0.8098)] +2025-10-31 08:12:47.649886: Epoch time: 22.13 s +2025-10-31 08:12:48.963407: +2025-10-31 08:12:48.965259: Epoch 804 +2025-10-31 08:12:48.966811: Current learning rate: 0.00231 +2025-10-31 08:13:10.493002: train_loss -0.9929 +2025-10-31 08:13:10.495441: val_loss -0.898 +2025-10-31 08:13:10.496907: Pseudo dice [np.float32(0.9868), np.float32(0.9924), np.float32(0.9944), np.float32(0.8032)] +2025-10-31 08:13:10.498377: Epoch time: 21.53 s +2025-10-31 08:13:11.695484: +2025-10-31 08:13:11.697414: Epoch 805 +2025-10-31 08:13:11.699207: Current learning rate: 0.0023 +2025-10-31 08:13:33.561064: train_loss -0.9936 +2025-10-31 08:13:33.563309: val_loss -0.8978 +2025-10-31 08:13:33.565301: Pseudo dice [np.float32(0.9862), np.float32(0.9918), np.float32(0.9948), np.float32(0.8081)] +2025-10-31 08:13:33.566898: Epoch time: 21.87 s +2025-10-31 08:13:34.700026: +2025-10-31 08:13:34.701607: Epoch 806 +2025-10-31 08:13:34.702941: Current learning rate: 0.00229 +2025-10-31 08:13:55.610262: train_loss -0.9924 +2025-10-31 08:13:55.613180: val_loss -0.8948 +2025-10-31 08:13:55.614940: Pseudo dice [np.float32(0.9863), np.float32(0.9919), np.float32(0.9946), np.float32(0.7995)] +2025-10-31 08:13:55.616674: Epoch time: 20.91 s +2025-10-31 08:13:56.804970: +2025-10-31 08:13:56.807209: Epoch 807 +2025-10-31 08:13:56.809041: Current learning rate: 0.00228 +2025-10-31 08:14:18.956324: train_loss -0.9924 +2025-10-31 08:14:18.958892: val_loss -0.8882 +2025-10-31 08:14:18.960232: Pseudo dice [np.float32(0.9864), np.float32(0.9915), np.float32(0.9945), np.float32(0.785)] +2025-10-31 08:14:18.961770: Epoch time: 22.15 s +2025-10-31 08:14:20.726348: +2025-10-31 08:14:20.728433: Epoch 808 +2025-10-31 08:14:20.730296: Current learning rate: 0.00226 +2025-10-31 08:14:43.148386: train_loss -0.9928 +2025-10-31 08:14:43.150615: val_loss -0.8957 +2025-10-31 08:14:43.152231: Pseudo dice [np.float32(0.9862), np.float32(0.9918), np.float32(0.9944), np.float32(0.8067)] +2025-10-31 08:14:43.153706: Epoch time: 22.42 s +2025-10-31 08:14:44.412536: +2025-10-31 08:14:44.414745: Epoch 809 +2025-10-31 08:14:44.416422: Current learning rate: 0.00225 +2025-10-31 08:15:07.060365: train_loss -0.9926 +2025-10-31 08:15:07.062958: val_loss -0.8981 +2025-10-31 08:15:07.064665: Pseudo dice [np.float32(0.9868), np.float32(0.9921), np.float32(0.9948), np.float32(0.8114)] +2025-10-31 08:15:07.066230: Epoch time: 22.65 s +2025-10-31 08:15:08.362424: +2025-10-31 08:15:08.364393: Epoch 810 +2025-10-31 08:15:08.366225: Current learning rate: 0.00224 +2025-10-31 08:15:30.301875: train_loss -0.9924 +2025-10-31 08:15:30.305670: val_loss -0.897 +2025-10-31 08:15:30.307506: Pseudo dice [np.float32(0.9871), np.float32(0.9917), np.float32(0.9947), np.float32(0.8019)] +2025-10-31 08:15:30.309177: Epoch time: 21.94 s +2025-10-31 08:15:31.570559: +2025-10-31 08:15:31.572538: Epoch 811 +2025-10-31 08:15:31.574207: Current learning rate: 0.00223 +2025-10-31 08:15:53.414758: train_loss -0.9924 +2025-10-31 08:15:53.423269: val_loss -0.8863 +2025-10-31 08:15:53.425094: Pseudo dice [np.float32(0.9844), np.float32(0.9902), np.float32(0.9941), np.float32(0.7899)] +2025-10-31 08:15:53.426645: Epoch time: 21.85 s +2025-10-31 08:15:54.636024: +2025-10-31 08:15:54.637792: Epoch 812 +2025-10-31 08:15:54.639273: Current learning rate: 0.00222 +2025-10-31 08:16:15.014803: train_loss -0.9928 +2025-10-31 08:16:15.017703: val_loss -0.8939 +2025-10-31 08:16:15.020151: Pseudo dice [np.float32(0.9869), np.float32(0.992), np.float32(0.9948), np.float32(0.8039)] +2025-10-31 08:16:15.022555: Epoch time: 20.38 s +2025-10-31 08:16:16.220857: +2025-10-31 08:16:16.222770: Epoch 813 +2025-10-31 08:16:16.224380: Current learning rate: 0.00221 +2025-10-31 08:16:38.497607: train_loss -0.9925 +2025-10-31 08:16:38.500572: val_loss -0.9021 +2025-10-31 08:16:38.502365: Pseudo dice [np.float32(0.9863), np.float32(0.9916), np.float32(0.995), np.float32(0.8171)] +2025-10-31 08:16:38.503912: Epoch time: 22.28 s +2025-10-31 08:16:39.800950: +2025-10-31 08:16:39.803080: Epoch 814 +2025-10-31 08:16:39.804662: Current learning rate: 0.0022 +2025-10-31 08:17:01.686757: train_loss -0.9929 +2025-10-31 08:17:01.689077: val_loss -0.8926 +2025-10-31 08:17:01.691166: Pseudo dice [np.float32(0.9866), np.float32(0.9913), np.float32(0.9944), np.float32(0.7925)] +2025-10-31 08:17:01.692815: Epoch time: 21.89 s +2025-10-31 08:17:02.848758: +2025-10-31 08:17:02.850722: Epoch 815 +2025-10-31 08:17:02.852453: Current learning rate: 0.00219 +2025-10-31 08:17:25.378171: train_loss -0.9929 +2025-10-31 08:17:25.391708: val_loss -0.894 +2025-10-31 08:17:25.393307: Pseudo dice [np.float32(0.9866), np.float32(0.9912), np.float32(0.9944), np.float32(0.797)] +2025-10-31 08:17:25.394772: Epoch time: 22.53 s +2025-10-31 08:17:26.668503: +2025-10-31 08:17:26.670569: Epoch 816 +2025-10-31 08:17:26.672265: Current learning rate: 0.00218 +2025-10-31 08:17:49.546511: train_loss -0.9929 +2025-10-31 08:17:49.553077: val_loss -0.9047 +2025-10-31 08:17:49.555083: Pseudo dice [np.float32(0.9862), np.float32(0.9911), np.float32(0.9948), np.float32(0.8281)] +2025-10-31 08:17:49.557274: Epoch time: 22.88 s +2025-10-31 08:17:50.810917: +2025-10-31 08:17:50.813262: Epoch 817 +2025-10-31 08:17:50.815428: Current learning rate: 0.00217 +2025-10-31 08:18:12.462584: train_loss -0.9921 +2025-10-31 08:18:12.465079: val_loss -0.8925 +2025-10-31 08:18:12.466933: Pseudo dice [np.float32(0.9859), np.float32(0.9911), np.float32(0.9943), np.float32(0.7973)] +2025-10-31 08:18:12.468790: Epoch time: 21.65 s +2025-10-31 08:18:13.695434: +2025-10-31 08:18:13.697544: Epoch 818 +2025-10-31 08:18:13.699075: Current learning rate: 0.00216 +2025-10-31 08:18:33.413964: train_loss -0.9931 +2025-10-31 08:18:33.416494: val_loss -0.8903 +2025-10-31 08:18:33.422010: Pseudo dice [np.float32(0.9859), np.float32(0.9918), np.float32(0.9944), np.float32(0.7979)] +2025-10-31 08:18:33.423858: Epoch time: 19.72 s +2025-10-31 08:18:35.127202: +2025-10-31 08:18:35.129263: Epoch 819 +2025-10-31 08:18:35.130991: Current learning rate: 0.00215 +2025-10-31 08:18:57.576877: train_loss -0.9928 +2025-10-31 08:18:57.580128: val_loss -0.8928 +2025-10-31 08:18:57.581816: Pseudo dice [np.float32(0.9866), np.float32(0.9913), np.float32(0.9942), np.float32(0.8041)] +2025-10-31 08:18:57.583835: Epoch time: 22.45 s +2025-10-31 08:18:58.720917: +2025-10-31 08:18:58.722902: Epoch 820 +2025-10-31 08:18:58.724796: Current learning rate: 0.00214 +2025-10-31 08:19:20.439328: train_loss -0.993 +2025-10-31 08:19:20.444173: val_loss -0.8937 +2025-10-31 08:19:20.445766: Pseudo dice [np.float32(0.9866), np.float32(0.9916), np.float32(0.9947), np.float32(0.7989)] +2025-10-31 08:19:20.447427: Epoch time: 21.72 s +2025-10-31 08:19:21.645749: +2025-10-31 08:19:21.647507: Epoch 821 +2025-10-31 08:19:21.649018: Current learning rate: 0.00213 +2025-10-31 08:19:44.074777: train_loss -0.9935 +2025-10-31 08:19:44.077269: val_loss -0.8989 +2025-10-31 08:19:44.079310: Pseudo dice [np.float32(0.9866), np.float32(0.9927), np.float32(0.9947), np.float32(0.8137)] +2025-10-31 08:19:44.081631: Epoch time: 22.43 s +2025-10-31 08:19:45.186236: +2025-10-31 08:19:45.188233: Epoch 822 +2025-10-31 08:19:45.189870: Current learning rate: 0.00212 +2025-10-31 08:20:07.979949: train_loss -0.9929 +2025-10-31 08:20:07.983371: val_loss -0.8925 +2025-10-31 08:20:07.985121: Pseudo dice [np.float32(0.9856), np.float32(0.9911), np.float32(0.9944), np.float32(0.7985)] +2025-10-31 08:20:07.986814: Epoch time: 22.8 s +2025-10-31 08:20:09.275925: +2025-10-31 08:20:09.278899: Epoch 823 +2025-10-31 08:20:09.281094: Current learning rate: 0.0021 +2025-10-31 08:20:30.992295: train_loss -0.9929 +2025-10-31 08:20:30.995469: val_loss -0.8914 +2025-10-31 08:20:30.997085: Pseudo dice [np.float32(0.987), np.float32(0.9915), np.float32(0.9941), np.float32(0.8006)] +2025-10-31 08:20:30.998593: Epoch time: 21.72 s +2025-10-31 08:20:32.170006: +2025-10-31 08:20:32.171755: Epoch 824 +2025-10-31 08:20:32.173631: Current learning rate: 0.00209 +2025-10-31 08:20:53.598600: train_loss -0.9932 +2025-10-31 08:20:53.601081: val_loss -0.8971 +2025-10-31 08:20:53.602607: Pseudo dice [np.float32(0.9874), np.float32(0.9916), np.float32(0.9943), np.float32(0.8052)] +2025-10-31 08:20:53.604305: Epoch time: 21.43 s +2025-10-31 08:20:54.696455: +2025-10-31 08:20:54.698494: Epoch 825 +2025-10-31 08:20:54.700017: Current learning rate: 0.00208 +2025-10-31 08:21:15.843830: train_loss -0.9927 +2025-10-31 08:21:15.847019: val_loss -0.8982 +2025-10-31 08:21:15.848545: Pseudo dice [np.float32(0.9859), np.float32(0.9918), np.float32(0.9947), np.float32(0.8162)] +2025-10-31 08:21:15.849837: Epoch time: 21.15 s +2025-10-31 08:21:15.851134: Yayy! New best EMA pseudo Dice: 0.944100022315979 +2025-10-31 08:21:18.213052: +2025-10-31 08:21:18.214980: Epoch 826 +2025-10-31 08:21:18.216435: Current learning rate: 0.00207 +2025-10-31 08:21:40.073405: train_loss -0.9931 +2025-10-31 08:21:40.077085: val_loss -0.8934 +2025-10-31 08:21:40.078819: Pseudo dice [np.float32(0.9867), np.float32(0.9919), np.float32(0.9945), np.float32(0.8024)] +2025-10-31 08:21:40.080438: Epoch time: 21.86 s +2025-10-31 08:21:41.373858: +2025-10-31 08:21:41.375821: Epoch 827 +2025-10-31 08:21:41.377668: Current learning rate: 0.00206 +2025-10-31 08:22:03.573586: train_loss -0.9928 +2025-10-31 08:22:03.577531: val_loss -0.8922 +2025-10-31 08:22:03.579746: Pseudo dice [np.float32(0.9857), np.float32(0.9913), np.float32(0.9942), np.float32(0.8074)] +2025-10-31 08:22:03.581321: Epoch time: 22.2 s +2025-10-31 08:22:03.582812: Yayy! New best EMA pseudo Dice: 0.9441999793052673 +2025-10-31 08:22:06.156545: +2025-10-31 08:22:06.158516: Epoch 828 +2025-10-31 08:22:06.160431: Current learning rate: 0.00205 +2025-10-31 08:22:29.134900: train_loss -0.9933 +2025-10-31 08:22:29.137298: val_loss -0.8955 +2025-10-31 08:22:29.138495: Pseudo dice [np.float32(0.9863), np.float32(0.9919), np.float32(0.9948), np.float32(0.806)] +2025-10-31 08:22:29.139685: Epoch time: 22.98 s +2025-10-31 08:22:29.140959: Yayy! New best EMA pseudo Dice: 0.9441999793052673 +2025-10-31 08:22:31.717638: +2025-10-31 08:22:31.719702: Epoch 829 +2025-10-31 08:22:31.721493: Current learning rate: 0.00204 +2025-10-31 08:22:52.324988: train_loss -0.9925 +2025-10-31 08:22:52.327632: val_loss -0.8991 +2025-10-31 08:22:52.329248: Pseudo dice [np.float32(0.9866), np.float32(0.9911), np.float32(0.9942), np.float32(0.8217)] +2025-10-31 08:22:52.330920: Epoch time: 20.61 s +2025-10-31 08:22:52.332685: Yayy! New best EMA pseudo Dice: 0.944599986076355 +2025-10-31 08:22:54.717519: +2025-10-31 08:22:54.741374: Epoch 830 +2025-10-31 08:22:54.744082: Current learning rate: 0.00203 +2025-10-31 08:23:17.720447: train_loss -0.9921 +2025-10-31 08:23:17.724436: val_loss -0.8919 +2025-10-31 08:23:17.725971: Pseudo dice [np.float32(0.9868), np.float32(0.992), np.float32(0.9942), np.float32(0.7919)] +2025-10-31 08:23:17.727690: Epoch time: 23.0 s +2025-10-31 08:23:19.427948: +2025-10-31 08:23:19.430263: Epoch 831 +2025-10-31 08:23:19.432061: Current learning rate: 0.00202 +2025-10-31 08:23:40.149454: train_loss -0.9924 +2025-10-31 08:23:40.157044: val_loss -0.8916 +2025-10-31 08:23:40.158905: Pseudo dice [np.float32(0.9866), np.float32(0.992), np.float32(0.9943), np.float32(0.7965)] +2025-10-31 08:23:40.160612: Epoch time: 20.72 s +2025-10-31 08:23:41.387655: +2025-10-31 08:23:41.389797: Epoch 832 +2025-10-31 08:23:41.391544: Current learning rate: 0.00201 +2025-10-31 08:24:03.182760: train_loss -0.9928 +2025-10-31 08:24:03.185064: val_loss -0.8926 +2025-10-31 08:24:03.186933: Pseudo dice [np.float32(0.9865), np.float32(0.9917), np.float32(0.9946), np.float32(0.7956)] +2025-10-31 08:24:03.188479: Epoch time: 21.8 s +2025-10-31 08:24:04.459739: +2025-10-31 08:24:04.461822: Epoch 833 +2025-10-31 08:24:04.463492: Current learning rate: 0.002 +2025-10-31 08:24:27.057761: train_loss -0.9928 +2025-10-31 08:24:27.060264: val_loss -0.8994 +2025-10-31 08:24:27.062503: Pseudo dice [np.float32(0.9859), np.float32(0.9913), np.float32(0.9949), np.float32(0.8167)] +2025-10-31 08:24:27.064415: Epoch time: 22.6 s +2025-10-31 08:24:28.297323: +2025-10-31 08:24:28.299184: Epoch 834 +2025-10-31 08:24:28.300896: Current learning rate: 0.00199 +2025-10-31 08:24:50.965207: train_loss -0.993 +2025-10-31 08:24:50.970455: val_loss -0.8862 +2025-10-31 08:24:50.972400: Pseudo dice [np.float32(0.9863), np.float32(0.9905), np.float32(0.9944), np.float32(0.7903)] +2025-10-31 08:24:50.974022: Epoch time: 22.67 s +2025-10-31 08:24:52.254363: +2025-10-31 08:24:52.257149: Epoch 835 +2025-10-31 08:24:52.258795: Current learning rate: 0.00198 +2025-10-31 08:25:12.621277: train_loss -0.9927 +2025-10-31 08:25:12.624021: val_loss -0.8948 +2025-10-31 08:25:12.625871: Pseudo dice [np.float32(0.9858), np.float32(0.9913), np.float32(0.9946), np.float32(0.8107)] +2025-10-31 08:25:12.627551: Epoch time: 20.37 s +2025-10-31 08:25:13.869284: +2025-10-31 08:25:13.871149: Epoch 836 +2025-10-31 08:25:13.872843: Current learning rate: 0.00196 +2025-10-31 08:25:36.421548: train_loss -0.9937 +2025-10-31 08:25:36.424444: val_loss -0.8922 +2025-10-31 08:25:36.426525: Pseudo dice [np.float32(0.986), np.float32(0.9914), np.float32(0.9944), np.float32(0.8028)] +2025-10-31 08:25:36.428326: Epoch time: 22.55 s +2025-10-31 08:25:37.515985: +2025-10-31 08:25:37.518060: Epoch 837 +2025-10-31 08:25:37.519753: Current learning rate: 0.00195 +2025-10-31 08:25:58.927275: train_loss -0.9932 +2025-10-31 08:25:58.937937: val_loss -0.8949 +2025-10-31 08:25:58.940258: Pseudo dice [np.float32(0.9864), np.float32(0.9912), np.float32(0.9947), np.float32(0.7991)] +2025-10-31 08:25:58.943253: Epoch time: 21.41 s +2025-10-31 08:26:00.187952: +2025-10-31 08:26:00.190203: Epoch 838 +2025-10-31 08:26:00.192036: Current learning rate: 0.00194 +2025-10-31 08:26:21.338648: train_loss -0.9931 +2025-10-31 08:26:21.340964: val_loss -0.8992 +2025-10-31 08:26:21.343023: Pseudo dice [np.float32(0.9866), np.float32(0.9919), np.float32(0.9949), np.float32(0.8124)] +2025-10-31 08:26:21.345107: Epoch time: 21.15 s +2025-10-31 08:26:22.527838: +2025-10-31 08:26:22.530946: Epoch 839 +2025-10-31 08:26:22.534300: Current learning rate: 0.00193 +2025-10-31 08:26:44.995066: train_loss -0.993 +2025-10-31 08:26:44.998301: val_loss -0.8915 +2025-10-31 08:26:45.004436: Pseudo dice [np.float32(0.9872), np.float32(0.9916), np.float32(0.9942), np.float32(0.7969)] +2025-10-31 08:26:45.007293: Epoch time: 22.47 s +2025-10-31 08:26:46.255640: +2025-10-31 08:26:46.258080: Epoch 840 +2025-10-31 08:26:46.260008: Current learning rate: 0.00192 +2025-10-31 08:27:09.163218: train_loss -0.9929 +2025-10-31 08:27:09.166586: val_loss -0.898 +2025-10-31 08:27:09.168554: Pseudo dice [np.float32(0.9874), np.float32(0.9921), np.float32(0.9948), np.float32(0.8082)] +2025-10-31 08:27:09.170228: Epoch time: 22.91 s +2025-10-31 08:27:10.135494: +2025-10-31 08:27:10.138113: Epoch 841 +2025-10-31 08:27:10.140270: Current learning rate: 0.00191 +2025-10-31 08:27:31.297409: train_loss -0.9928 +2025-10-31 08:27:31.300038: val_loss -0.9008 +2025-10-31 08:27:31.302040: Pseudo dice [np.float32(0.9869), np.float32(0.9919), np.float32(0.9946), np.float32(0.8136)] +2025-10-31 08:27:31.303921: Epoch time: 21.16 s +2025-10-31 08:27:32.521170: +2025-10-31 08:27:32.523704: Epoch 842 +2025-10-31 08:27:32.525680: Current learning rate: 0.0019 +2025-10-31 08:27:55.197148: train_loss -0.9932 +2025-10-31 08:27:55.200289: val_loss -0.8994 +2025-10-31 08:27:55.202155: Pseudo dice [np.float32(0.9868), np.float32(0.9918), np.float32(0.9949), np.float32(0.8136)] +2025-10-31 08:27:55.204012: Epoch time: 22.68 s +2025-10-31 08:27:56.355947: +2025-10-31 08:27:56.358120: Epoch 843 +2025-10-31 08:27:56.359974: Current learning rate: 0.00189 +2025-10-31 08:28:19.494052: train_loss -0.9926 +2025-10-31 08:28:19.498949: val_loss -0.8895 +2025-10-31 08:28:19.501294: Pseudo dice [np.float32(0.9858), np.float32(0.9917), np.float32(0.9941), np.float32(0.7929)] +2025-10-31 08:28:19.503191: Epoch time: 23.14 s +2025-10-31 08:28:21.253924: +2025-10-31 08:28:21.256653: Epoch 844 +2025-10-31 08:28:21.258723: Current learning rate: 0.00188 +2025-10-31 08:28:42.401079: train_loss -0.9927 +2025-10-31 08:28:42.403845: val_loss -0.892 +2025-10-31 08:28:42.405647: Pseudo dice [np.float32(0.9861), np.float32(0.9905), np.float32(0.9944), np.float32(0.8055)] +2025-10-31 08:28:42.407522: Epoch time: 21.15 s +2025-10-31 08:28:43.627712: +2025-10-31 08:28:43.629557: Epoch 845 +2025-10-31 08:28:43.631046: Current learning rate: 0.00187 +2025-10-31 08:29:06.037973: train_loss -0.9928 +2025-10-31 08:29:06.041581: val_loss -0.8897 +2025-10-31 08:29:06.044307: Pseudo dice [np.float32(0.986), np.float32(0.9912), np.float32(0.9941), np.float32(0.7931)] +2025-10-31 08:29:06.046781: Epoch time: 22.41 s +2025-10-31 08:29:07.251183: +2025-10-31 08:29:07.253949: Epoch 846 +2025-10-31 08:29:07.257323: Current learning rate: 0.00186 +2025-10-31 08:29:29.888012: train_loss -0.9933 +2025-10-31 08:29:29.892244: val_loss -0.8909 +2025-10-31 08:29:29.894086: Pseudo dice [np.float32(0.9858), np.float32(0.991), np.float32(0.9944), np.float32(0.7997)] +2025-10-31 08:29:29.896065: Epoch time: 22.64 s +2025-10-31 08:29:31.059004: +2025-10-31 08:29:31.061451: Epoch 847 +2025-10-31 08:29:31.063645: Current learning rate: 0.00185 +2025-10-31 08:29:51.310447: train_loss -0.9928 +2025-10-31 08:29:51.313377: val_loss -0.8981 +2025-10-31 08:29:51.315334: Pseudo dice [np.float32(0.9861), np.float32(0.9919), np.float32(0.9951), np.float32(0.8113)] +2025-10-31 08:29:51.317464: Epoch time: 20.25 s +2025-10-31 08:29:52.575004: +2025-10-31 08:29:52.577339: Epoch 848 +2025-10-31 08:29:52.579675: Current learning rate: 0.00184 +2025-10-31 08:30:14.342841: train_loss -0.9931 +2025-10-31 08:30:14.345705: val_loss -0.8945 +2025-10-31 08:30:14.347965: Pseudo dice [np.float32(0.9876), np.float32(0.9919), np.float32(0.9944), np.float32(0.7968)] +2025-10-31 08:30:14.350942: Epoch time: 21.77 s +2025-10-31 08:30:15.586470: +2025-10-31 08:30:15.588382: Epoch 849 +2025-10-31 08:30:15.590044: Current learning rate: 0.00182 +2025-10-31 08:30:37.342540: train_loss -0.9926 +2025-10-31 08:30:37.346279: val_loss -0.8935 +2025-10-31 08:30:37.348307: Pseudo dice [np.float32(0.9862), np.float32(0.9918), np.float32(0.9948), np.float32(0.7978)] +2025-10-31 08:30:37.350123: Epoch time: 21.76 s +2025-10-31 08:30:39.736314: +2025-10-31 08:30:39.738827: Epoch 850 +2025-10-31 08:30:39.740652: Current learning rate: 0.00181 +2025-10-31 08:31:01.306925: train_loss -0.993 +2025-10-31 08:31:01.309255: val_loss -0.8846 +2025-10-31 08:31:01.311002: Pseudo dice [np.float32(0.9856), np.float32(0.9908), np.float32(0.9938), np.float32(0.792)] +2025-10-31 08:31:01.312906: Epoch time: 21.57 s +2025-10-31 08:31:02.568283: +2025-10-31 08:31:02.570451: Epoch 851 +2025-10-31 08:31:02.576019: Current learning rate: 0.0018 +2025-10-31 08:31:25.132946: train_loss -0.9938 +2025-10-31 08:31:25.135902: val_loss -0.8904 +2025-10-31 08:31:25.138155: Pseudo dice [np.float32(0.9862), np.float32(0.9916), np.float32(0.9945), np.float32(0.7932)] +2025-10-31 08:31:25.140336: Epoch time: 22.57 s +2025-10-31 08:31:26.290154: +2025-10-31 08:31:26.292278: Epoch 852 +2025-10-31 08:31:26.294101: Current learning rate: 0.00179 +2025-10-31 08:31:48.158931: train_loss -0.9935 +2025-10-31 08:31:48.163522: val_loss -0.902 +2025-10-31 08:31:48.165440: Pseudo dice [np.float32(0.9871), np.float32(0.9916), np.float32(0.9949), np.float32(0.8173)] +2025-10-31 08:31:48.167290: Epoch time: 21.87 s +2025-10-31 08:31:49.409020: +2025-10-31 08:31:49.411205: Epoch 853 +2025-10-31 08:31:49.413359: Current learning rate: 0.00178 +2025-10-31 08:32:10.770168: train_loss -0.9934 +2025-10-31 08:32:10.773717: val_loss -0.8975 +2025-10-31 08:32:10.776302: Pseudo dice [np.float32(0.9868), np.float32(0.9914), np.float32(0.9946), np.float32(0.8081)] +2025-10-31 08:32:10.778789: Epoch time: 21.36 s +2025-10-31 08:32:11.894451: +2025-10-31 08:32:11.896597: Epoch 854 +2025-10-31 08:32:11.898898: Current learning rate: 0.00177 +2025-10-31 08:32:34.716214: train_loss -0.9938 +2025-10-31 08:32:34.718429: val_loss -0.8929 +2025-10-31 08:32:34.720083: Pseudo dice [np.float32(0.9869), np.float32(0.9916), np.float32(0.9944), np.float32(0.7989)] +2025-10-31 08:32:34.721765: Epoch time: 22.82 s +2025-10-31 08:32:35.907555: +2025-10-31 08:32:35.910218: Epoch 855 +2025-10-31 08:32:35.911823: Current learning rate: 0.00176 +2025-10-31 08:32:57.755242: train_loss -0.9933 +2025-10-31 08:32:57.758618: val_loss -0.9016 +2025-10-31 08:32:57.760495: Pseudo dice [np.float32(0.9869), np.float32(0.9917), np.float32(0.9949), np.float32(0.8144)] +2025-10-31 08:32:57.762452: Epoch time: 21.85 s +2025-10-31 08:32:59.692128: +2025-10-31 08:32:59.694231: Epoch 856 +2025-10-31 08:32:59.695741: Current learning rate: 0.00175 +2025-10-31 08:33:22.166564: train_loss -0.9932 +2025-10-31 08:33:22.170491: val_loss -0.8925 +2025-10-31 08:33:22.172345: Pseudo dice [np.float32(0.9852), np.float32(0.9909), np.float32(0.9946), np.float32(0.8007)] +2025-10-31 08:33:22.174290: Epoch time: 22.48 s +2025-10-31 08:33:23.394133: +2025-10-31 08:33:23.396235: Epoch 857 +2025-10-31 08:33:23.398259: Current learning rate: 0.00174 +2025-10-31 08:33:44.142819: train_loss -0.9942 +2025-10-31 08:33:44.145246: val_loss -0.897 +2025-10-31 08:33:44.147330: Pseudo dice [np.float32(0.9868), np.float32(0.9911), np.float32(0.9947), np.float32(0.8149)] +2025-10-31 08:33:44.149365: Epoch time: 20.75 s +2025-10-31 08:33:45.349395: +2025-10-31 08:33:45.351756: Epoch 858 +2025-10-31 08:33:45.353877: Current learning rate: 0.00173 +2025-10-31 08:34:07.480694: train_loss -0.9936 +2025-10-31 08:34:07.487097: val_loss -0.8923 +2025-10-31 08:34:07.488971: Pseudo dice [np.float32(0.9868), np.float32(0.9918), np.float32(0.9945), np.float32(0.8003)] +2025-10-31 08:34:07.490890: Epoch time: 22.13 s +2025-10-31 08:34:08.706170: +2025-10-31 08:34:08.708643: Epoch 859 +2025-10-31 08:34:08.711052: Current learning rate: 0.00172 +2025-10-31 08:34:29.896479: train_loss -0.9938 +2025-10-31 08:34:29.899049: val_loss -0.8961 +2025-10-31 08:34:29.901196: Pseudo dice [np.float32(0.9863), np.float32(0.991), np.float32(0.9949), np.float32(0.8081)] +2025-10-31 08:34:29.903157: Epoch time: 21.19 s +2025-10-31 08:34:31.127881: +2025-10-31 08:34:31.130180: Epoch 860 +2025-10-31 08:34:31.132350: Current learning rate: 0.0017 +2025-10-31 08:34:53.527573: train_loss -0.9935 +2025-10-31 08:34:53.534592: val_loss -0.8922 +2025-10-31 08:34:53.536315: Pseudo dice [np.float32(0.9862), np.float32(0.9911), np.float32(0.995), np.float32(0.8062)] +2025-10-31 08:34:53.537868: Epoch time: 22.4 s +2025-10-31 08:34:54.839020: +2025-10-31 08:34:54.841396: Epoch 861 +2025-10-31 08:34:54.843744: Current learning rate: 0.00169 +2025-10-31 08:35:17.393791: train_loss -0.9936 +2025-10-31 08:35:17.397046: val_loss -0.8967 +2025-10-31 08:35:17.399144: Pseudo dice [np.float32(0.9864), np.float32(0.9916), np.float32(0.9948), np.float32(0.8102)] +2025-10-31 08:35:17.401140: Epoch time: 22.56 s +2025-10-31 08:35:18.312646: +2025-10-31 08:35:18.314399: Epoch 862 +2025-10-31 08:35:18.316093: Current learning rate: 0.00168 +2025-10-31 08:35:39.846760: train_loss -0.9938 +2025-10-31 08:35:39.849472: val_loss -0.8925 +2025-10-31 08:35:39.851764: Pseudo dice [np.float32(0.9875), np.float32(0.9918), np.float32(0.9944), np.float32(0.7935)] +2025-10-31 08:35:39.853997: Epoch time: 21.54 s +2025-10-31 08:35:41.115627: +2025-10-31 08:35:41.117789: Epoch 863 +2025-10-31 08:35:41.119796: Current learning rate: 0.00167 +2025-10-31 08:36:02.228348: train_loss -0.9926 +2025-10-31 08:36:02.230935: val_loss -0.8903 +2025-10-31 08:36:02.232890: Pseudo dice [np.float32(0.9869), np.float32(0.992), np.float32(0.9946), np.float32(0.7938)] +2025-10-31 08:36:02.235175: Epoch time: 21.11 s +2025-10-31 08:36:03.491095: +2025-10-31 08:36:03.494707: Epoch 864 +2025-10-31 08:36:03.497204: Current learning rate: 0.00166 +2025-10-31 08:36:25.829093: train_loss -0.9932 +2025-10-31 08:36:25.832665: val_loss -0.8987 +2025-10-31 08:36:25.834581: Pseudo dice [np.float32(0.9868), np.float32(0.992), np.float32(0.9948), np.float32(0.8103)] +2025-10-31 08:36:25.836345: Epoch time: 22.34 s +2025-10-31 08:36:27.056346: +2025-10-31 08:36:27.059087: Epoch 865 +2025-10-31 08:36:27.060916: Current learning rate: 0.00165 +2025-10-31 08:36:47.971556: train_loss -0.9937 +2025-10-31 08:36:47.974535: val_loss -0.898 +2025-10-31 08:36:47.976871: Pseudo dice [np.float32(0.9851), np.float32(0.991), np.float32(0.9949), np.float32(0.8068)] +2025-10-31 08:36:47.979206: Epoch time: 20.92 s +2025-10-31 08:36:49.246003: +2025-10-31 08:36:49.247869: Epoch 866 +2025-10-31 08:36:49.249375: Current learning rate: 0.00164 +2025-10-31 08:37:11.347097: train_loss -0.9933 +2025-10-31 08:37:11.350010: val_loss -0.8922 +2025-10-31 08:37:11.351638: Pseudo dice [np.float32(0.9865), np.float32(0.9922), np.float32(0.9944), np.float32(0.791)] +2025-10-31 08:37:11.353194: Epoch time: 22.1 s +2025-10-31 08:37:12.456322: +2025-10-31 08:37:12.458373: Epoch 867 +2025-10-31 08:37:12.460003: Current learning rate: 0.00163 +2025-10-31 08:37:35.083494: train_loss -0.9933 +2025-10-31 08:37:35.087349: val_loss -0.8957 +2025-10-31 08:37:35.089213: Pseudo dice [np.float32(0.9849), np.float32(0.9909), np.float32(0.9943), np.float32(0.8058)] +2025-10-31 08:37:35.091188: Epoch time: 22.63 s +2025-10-31 08:37:36.352676: +2025-10-31 08:37:36.354848: Epoch 868 +2025-10-31 08:37:36.356656: Current learning rate: 0.00162 +2025-10-31 08:37:58.204107: train_loss -0.9936 +2025-10-31 08:37:58.206785: val_loss -0.8937 +2025-10-31 08:37:58.208493: Pseudo dice [np.float32(0.9867), np.float32(0.9911), np.float32(0.9946), np.float32(0.8025)] +2025-10-31 08:37:58.210257: Epoch time: 21.85 s +2025-10-31 08:38:00.063832: +2025-10-31 08:38:00.065902: Epoch 869 +2025-10-31 08:38:00.067639: Current learning rate: 0.00161 +2025-10-31 08:38:21.810190: train_loss -0.9932 +2025-10-31 08:38:21.812396: val_loss -0.8953 +2025-10-31 08:38:21.813899: Pseudo dice [np.float32(0.9864), np.float32(0.9917), np.float32(0.9947), np.float32(0.8091)] +2025-10-31 08:38:21.815379: Epoch time: 21.75 s +2025-10-31 08:38:22.886682: +2025-10-31 08:38:22.888818: Epoch 870 +2025-10-31 08:38:22.890629: Current learning rate: 0.00159 +2025-10-31 08:38:44.679172: train_loss -0.9932 +2025-10-31 08:38:44.683125: val_loss -0.8973 +2025-10-31 08:38:44.685043: Pseudo dice [np.float32(0.9862), np.float32(0.9914), np.float32(0.9947), np.float32(0.8074)] +2025-10-31 08:38:44.687295: Epoch time: 21.79 s +2025-10-31 08:38:45.912488: +2025-10-31 08:38:45.914817: Epoch 871 +2025-10-31 08:38:45.917424: Current learning rate: 0.00158 +2025-10-31 08:39:07.382588: train_loss -0.9935 +2025-10-31 08:39:07.385090: val_loss -0.901 +2025-10-31 08:39:07.387083: Pseudo dice [np.float32(0.9875), np.float32(0.9917), np.float32(0.995), np.float32(0.816)] +2025-10-31 08:39:07.388975: Epoch time: 21.47 s +2025-10-31 08:39:08.366238: +2025-10-31 08:39:08.368235: Epoch 872 +2025-10-31 08:39:08.370053: Current learning rate: 0.00157 +2025-10-31 08:39:29.965276: train_loss -0.9936 +2025-10-31 08:39:29.967979: val_loss -0.8968 +2025-10-31 08:39:29.969992: Pseudo dice [np.float32(0.9857), np.float32(0.991), np.float32(0.9948), np.float32(0.8106)] +2025-10-31 08:39:29.971930: Epoch time: 21.6 s +2025-10-31 08:39:31.278285: +2025-10-31 08:39:31.280413: Epoch 873 +2025-10-31 08:39:31.282231: Current learning rate: 0.00156 +2025-10-31 08:39:53.483819: train_loss -0.9931 +2025-10-31 08:39:53.487674: val_loss -0.8964 +2025-10-31 08:39:53.489579: Pseudo dice [np.float32(0.9855), np.float32(0.9915), np.float32(0.9949), np.float32(0.8069)] +2025-10-31 08:39:53.491388: Epoch time: 22.21 s +2025-10-31 08:39:54.724097: +2025-10-31 08:39:54.725941: Epoch 874 +2025-10-31 08:39:54.727608: Current learning rate: 0.00155 +2025-10-31 08:40:17.382478: train_loss -0.9934 +2025-10-31 08:40:17.385747: val_loss -0.8984 +2025-10-31 08:40:17.388022: Pseudo dice [np.float32(0.9856), np.float32(0.9911), np.float32(0.9949), np.float32(0.8102)] +2025-10-31 08:40:17.390233: Epoch time: 22.66 s +2025-10-31 08:40:17.392527: Yayy! New best EMA pseudo Dice: 0.9447000026702881 +2025-10-31 08:40:19.845585: +2025-10-31 08:40:19.847788: Epoch 875 +2025-10-31 08:40:19.849472: Current learning rate: 0.00154 +2025-10-31 08:40:41.487634: train_loss -0.9939 +2025-10-31 08:40:41.490464: val_loss -0.8932 +2025-10-31 08:40:41.492417: Pseudo dice [np.float32(0.9871), np.float32(0.9919), np.float32(0.9947), np.float32(0.7999)] +2025-10-31 08:40:41.494597: Epoch time: 21.64 s +2025-10-31 08:40:42.718193: +2025-10-31 08:40:42.720949: Epoch 876 +2025-10-31 08:40:42.722754: Current learning rate: 0.00153 +2025-10-31 08:41:04.310967: train_loss -0.9933 +2025-10-31 08:41:04.314661: val_loss -0.8899 +2025-10-31 08:41:04.316471: Pseudo dice [np.float32(0.9854), np.float32(0.9917), np.float32(0.9941), np.float32(0.7961)] +2025-10-31 08:41:04.318332: Epoch time: 21.59 s +2025-10-31 08:41:05.517969: +2025-10-31 08:41:05.520315: Epoch 877 +2025-10-31 08:41:05.522415: Current learning rate: 0.00152 +2025-10-31 08:41:26.368593: train_loss -0.9931 +2025-10-31 08:41:26.370929: val_loss -0.8906 +2025-10-31 08:41:26.372366: Pseudo dice [np.float32(0.9861), np.float32(0.9907), np.float32(0.9944), np.float32(0.7993)] +2025-10-31 08:41:26.373669: Epoch time: 20.85 s +2025-10-31 08:41:27.595211: +2025-10-31 08:41:27.596950: Epoch 878 +2025-10-31 08:41:27.598429: Current learning rate: 0.00151 +2025-10-31 08:41:49.157808: train_loss -0.9938 +2025-10-31 08:41:49.160799: val_loss -0.8909 +2025-10-31 08:41:49.162918: Pseudo dice [np.float32(0.9858), np.float32(0.9918), np.float32(0.9946), np.float32(0.7964)] +2025-10-31 08:41:49.164864: Epoch time: 21.56 s +2025-10-31 08:41:50.316365: +2025-10-31 08:41:50.318898: Epoch 879 +2025-10-31 08:41:50.320975: Current learning rate: 0.00149 +2025-10-31 08:42:12.671510: train_loss -0.9936 +2025-10-31 08:42:12.676160: val_loss -0.8979 +2025-10-31 08:42:12.678479: Pseudo dice [np.float32(0.986), np.float32(0.9917), np.float32(0.9951), np.float32(0.8126)] +2025-10-31 08:42:12.680208: Epoch time: 22.36 s +2025-10-31 08:42:13.891664: +2025-10-31 08:42:13.901635: Epoch 880 +2025-10-31 08:42:13.903220: Current learning rate: 0.00148 +2025-10-31 08:42:36.386976: train_loss -0.9943 +2025-10-31 08:42:36.389859: val_loss -0.8945 +2025-10-31 08:42:36.391531: Pseudo dice [np.float32(0.9864), np.float32(0.9917), np.float32(0.9949), np.float32(0.8017)] +2025-10-31 08:42:36.392978: Epoch time: 22.5 s +2025-10-31 08:42:37.510026: +2025-10-31 08:42:37.511997: Epoch 881 +2025-10-31 08:42:37.513761: Current learning rate: 0.00147 +2025-10-31 08:42:59.430230: train_loss -0.9938 +2025-10-31 08:42:59.435939: val_loss -0.8909 +2025-10-31 08:42:59.437994: Pseudo dice [np.float32(0.9865), np.float32(0.9919), np.float32(0.9946), np.float32(0.7951)] +2025-10-31 08:42:59.440011: Epoch time: 21.92 s +2025-10-31 08:43:00.712997: +2025-10-31 08:43:00.715796: Epoch 882 +2025-10-31 08:43:00.717918: Current learning rate: 0.00146 +2025-10-31 08:43:22.465343: train_loss -0.9934 +2025-10-31 08:43:22.470133: val_loss -0.8858 +2025-10-31 08:43:22.472137: Pseudo dice [np.float32(0.9865), np.float32(0.9918), np.float32(0.9945), np.float32(0.7812)] +2025-10-31 08:43:22.473994: Epoch time: 21.75 s +2025-10-31 08:43:23.664646: +2025-10-31 08:43:23.666800: Epoch 883 +2025-10-31 08:43:23.668743: Current learning rate: 0.00145 +2025-10-31 08:43:45.322561: train_loss -0.9935 +2025-10-31 08:43:45.324963: val_loss -0.8932 +2025-10-31 08:43:45.326746: Pseudo dice [np.float32(0.9863), np.float32(0.9922), np.float32(0.9946), np.float32(0.7988)] +2025-10-31 08:43:45.328585: Epoch time: 21.66 s +2025-10-31 08:43:46.440398: +2025-10-31 08:43:46.442308: Epoch 884 +2025-10-31 08:43:46.447139: Current learning rate: 0.00144 +2025-10-31 08:44:07.894815: train_loss -0.9937 +2025-10-31 08:44:07.897244: val_loss -0.9043 +2025-10-31 08:44:07.899093: Pseudo dice [np.float32(0.9866), np.float32(0.9921), np.float32(0.9953), np.float32(0.8257)] +2025-10-31 08:44:07.900962: Epoch time: 21.46 s +2025-10-31 08:44:09.068558: +2025-10-31 08:44:09.070897: Epoch 885 +2025-10-31 08:44:09.073206: Current learning rate: 0.00143 +2025-10-31 08:44:31.258591: train_loss -0.9932 +2025-10-31 08:44:31.263825: val_loss -0.8945 +2025-10-31 08:44:31.265582: Pseudo dice [np.float32(0.9866), np.float32(0.9917), np.float32(0.9945), np.float32(0.804)] +2025-10-31 08:44:31.267281: Epoch time: 22.19 s +2025-10-31 08:44:32.463629: +2025-10-31 08:44:32.465493: Epoch 886 +2025-10-31 08:44:32.469472: Current learning rate: 0.00142 +2025-10-31 08:44:55.226869: train_loss -0.9939 +2025-10-31 08:44:55.229713: val_loss -0.8964 +2025-10-31 08:44:55.231719: Pseudo dice [np.float32(0.9871), np.float32(0.9921), np.float32(0.9944), np.float32(0.8024)] +2025-10-31 08:44:55.234133: Epoch time: 22.76 s +2025-10-31 08:44:56.377269: +2025-10-31 08:44:56.379425: Epoch 887 +2025-10-31 08:44:56.381125: Current learning rate: 0.00141 +2025-10-31 08:45:17.870272: train_loss -0.9938 +2025-10-31 08:45:17.872936: val_loss -0.8873 +2025-10-31 08:45:17.875004: Pseudo dice [np.float32(0.986), np.float32(0.9912), np.float32(0.9945), np.float32(0.7909)] +2025-10-31 08:45:17.876918: Epoch time: 21.49 s +2025-10-31 08:45:19.153017: +2025-10-31 08:45:19.156244: Epoch 888 +2025-10-31 08:45:19.158050: Current learning rate: 0.00139 +2025-10-31 08:45:41.936343: train_loss -0.9935 +2025-10-31 08:45:41.947134: val_loss -0.9007 +2025-10-31 08:45:41.949845: Pseudo dice [np.float32(0.9856), np.float32(0.9923), np.float32(0.9951), np.float32(0.8205)] +2025-10-31 08:45:41.951473: Epoch time: 22.78 s +2025-10-31 08:45:43.076403: +2025-10-31 08:45:43.078659: Epoch 889 +2025-10-31 08:45:43.080428: Current learning rate: 0.00138 +2025-10-31 08:46:03.226846: train_loss -0.9937 +2025-10-31 08:46:03.232034: val_loss -0.8984 +2025-10-31 08:46:03.234319: Pseudo dice [np.float32(0.9862), np.float32(0.9919), np.float32(0.9946), np.float32(0.8154)] +2025-10-31 08:46:03.236096: Epoch time: 20.15 s +2025-10-31 08:46:04.496021: +2025-10-31 08:46:04.498187: Epoch 890 +2025-10-31 08:46:04.500126: Current learning rate: 0.00137 +2025-10-31 08:46:26.526145: train_loss -0.9941 +2025-10-31 08:46:26.531632: val_loss -0.8884 +2025-10-31 08:46:26.533432: Pseudo dice [np.float32(0.9867), np.float32(0.9923), np.float32(0.9944), np.float32(0.786)] +2025-10-31 08:46:26.535895: Epoch time: 22.03 s +2025-10-31 08:46:27.728922: +2025-10-31 08:46:27.731027: Epoch 891 +2025-10-31 08:46:27.732923: Current learning rate: 0.00136 +2025-10-31 08:46:49.607332: train_loss -0.9942 +2025-10-31 08:46:49.612322: val_loss -0.888 +2025-10-31 08:46:49.614202: Pseudo dice [np.float32(0.9859), np.float32(0.9909), np.float32(0.9941), np.float32(0.7959)] +2025-10-31 08:46:49.615972: Epoch time: 21.88 s +2025-10-31 08:46:50.857945: +2025-10-31 08:46:50.860240: Epoch 892 +2025-10-31 08:46:50.862056: Current learning rate: 0.00135 +2025-10-31 08:47:13.186898: train_loss -0.9934 +2025-10-31 08:47:13.189457: val_loss -0.8948 +2025-10-31 08:47:13.191235: Pseudo dice [np.float32(0.9868), np.float32(0.9924), np.float32(0.995), np.float32(0.8007)] +2025-10-31 08:47:13.192770: Epoch time: 22.33 s +2025-10-31 08:47:14.385202: +2025-10-31 08:47:14.387458: Epoch 893 +2025-10-31 08:47:14.389404: Current learning rate: 0.00134 +2025-10-31 08:47:37.108225: train_loss -0.9942 +2025-10-31 08:47:37.111722: val_loss -0.8957 +2025-10-31 08:47:37.113436: Pseudo dice [np.float32(0.9854), np.float32(0.9914), np.float32(0.9948), np.float32(0.8058)] +2025-10-31 08:47:37.115213: Epoch time: 22.72 s +2025-10-31 08:47:38.261843: +2025-10-31 08:47:38.264187: Epoch 894 +2025-10-31 08:47:38.265974: Current learning rate: 0.00133 +2025-10-31 08:47:59.965782: train_loss -0.9939 +2025-10-31 08:47:59.970592: val_loss -0.8941 +2025-10-31 08:47:59.972371: Pseudo dice [np.float32(0.9854), np.float32(0.9912), np.float32(0.9947), np.float32(0.8053)] +2025-10-31 08:47:59.974396: Epoch time: 21.71 s +2025-10-31 08:48:01.762510: +2025-10-31 08:48:01.764586: Epoch 895 +2025-10-31 08:48:01.766723: Current learning rate: 0.00132 +2025-10-31 08:48:22.248314: train_loss -0.9933 +2025-10-31 08:48:22.250809: val_loss -0.8906 +2025-10-31 08:48:22.252374: Pseudo dice [np.float32(0.9861), np.float32(0.9912), np.float32(0.9946), np.float32(0.7955)] +2025-10-31 08:48:22.254140: Epoch time: 20.49 s +2025-10-31 08:48:23.499722: +2025-10-31 08:48:23.501877: Epoch 896 +2025-10-31 08:48:23.504111: Current learning rate: 0.0013 +2025-10-31 08:48:45.838896: train_loss -0.994 +2025-10-31 08:48:45.842347: val_loss -0.8879 +2025-10-31 08:48:45.844440: Pseudo dice [np.float32(0.9866), np.float32(0.992), np.float32(0.9938), np.float32(0.7889)] +2025-10-31 08:48:45.846318: Epoch time: 22.34 s +2025-10-31 08:48:47.068044: +2025-10-31 08:48:47.071345: Epoch 897 +2025-10-31 08:48:47.072909: Current learning rate: 0.00129 +2025-10-31 08:49:08.954067: train_loss -0.9934 +2025-10-31 08:49:08.959816: val_loss -0.8947 +2025-10-31 08:49:08.961883: Pseudo dice [np.float32(0.9871), np.float32(0.9915), np.float32(0.9945), np.float32(0.8092)] +2025-10-31 08:49:08.963761: Epoch time: 21.89 s +2025-10-31 08:49:10.189229: +2025-10-31 08:49:10.191367: Epoch 898 +2025-10-31 08:49:10.193104: Current learning rate: 0.00128 +2025-10-31 08:49:32.493290: train_loss -0.994 +2025-10-31 08:49:32.495780: val_loss -0.9023 +2025-10-31 08:49:32.497763: Pseudo dice [np.float32(0.987), np.float32(0.9925), np.float32(0.9952), np.float32(0.8164)] +2025-10-31 08:49:32.499333: Epoch time: 22.31 s +2025-10-31 08:49:33.737594: +2025-10-31 08:49:33.739810: Epoch 899 +2025-10-31 08:49:33.741561: Current learning rate: 0.00127 +2025-10-31 08:49:56.408402: train_loss -0.994 +2025-10-31 08:49:56.414963: val_loss -0.9039 +2025-10-31 08:49:56.417187: Pseudo dice [np.float32(0.9863), np.float32(0.9921), np.float32(0.995), np.float32(0.8244)] +2025-10-31 08:49:56.419575: Epoch time: 22.67 s +2025-10-31 08:49:58.965452: +2025-10-31 08:49:58.967421: Epoch 900 +2025-10-31 08:49:58.969185: Current learning rate: 0.00126 +2025-10-31 08:50:21.315291: train_loss -0.9936 +2025-10-31 08:50:21.320229: val_loss -0.8908 +2025-10-31 08:50:21.321958: Pseudo dice [np.float32(0.986), np.float32(0.9913), np.float32(0.9943), np.float32(0.7979)] +2025-10-31 08:50:21.323535: Epoch time: 22.35 s +2025-10-31 08:50:22.602250: +2025-10-31 08:50:22.603756: Epoch 901 +2025-10-31 08:50:22.605279: Current learning rate: 0.00125 +2025-10-31 08:50:43.786164: train_loss -0.9939 +2025-10-31 08:50:43.788581: val_loss -0.8953 +2025-10-31 08:50:43.790178: Pseudo dice [np.float32(0.9868), np.float32(0.9917), np.float32(0.9945), np.float32(0.806)] +2025-10-31 08:50:43.791755: Epoch time: 21.19 s +2025-10-31 08:50:45.018312: +2025-10-31 08:50:45.020233: Epoch 902 +2025-10-31 08:50:45.021683: Current learning rate: 0.00124 +2025-10-31 08:51:07.581435: train_loss -0.994 +2025-10-31 08:51:07.584021: val_loss -0.8953 +2025-10-31 08:51:07.585912: Pseudo dice [np.float32(0.9858), np.float32(0.992), np.float32(0.995), np.float32(0.805)] +2025-10-31 08:51:07.587998: Epoch time: 22.57 s +2025-10-31 08:51:08.477323: +2025-10-31 08:51:08.479307: Epoch 903 +2025-10-31 08:51:08.481046: Current learning rate: 0.00122 +2025-10-31 08:51:29.846012: train_loss -0.9936 +2025-10-31 08:51:29.848747: val_loss -0.899 +2025-10-31 08:51:29.850631: Pseudo dice [np.float32(0.9866), np.float32(0.9916), np.float32(0.995), np.float32(0.8186)] +2025-10-31 08:51:29.852117: Epoch time: 21.37 s +2025-10-31 08:51:29.853431: Yayy! New best EMA pseudo Dice: 0.9447000026702881 +2025-10-31 08:51:32.239215: +2025-10-31 08:51:32.241063: Epoch 904 +2025-10-31 08:51:32.242954: Current learning rate: 0.00121 +2025-10-31 08:51:54.575620: train_loss -0.9937 +2025-10-31 08:51:54.581666: val_loss -0.8948 +2025-10-31 08:51:54.583378: Pseudo dice [np.float32(0.9863), np.float32(0.9918), np.float32(0.9944), np.float32(0.8057)] +2025-10-31 08:51:54.585216: Epoch time: 22.34 s +2025-10-31 08:51:55.825166: +2025-10-31 08:51:55.827266: Epoch 905 +2025-10-31 08:51:55.828995: Current learning rate: 0.0012 +2025-10-31 08:52:18.344943: train_loss -0.9938 +2025-10-31 08:52:18.349154: val_loss -0.885 +2025-10-31 08:52:18.350926: Pseudo dice [np.float32(0.9859), np.float32(0.9907), np.float32(0.994), np.float32(0.7941)] +2025-10-31 08:52:18.353390: Epoch time: 22.52 s +2025-10-31 08:52:19.613910: +2025-10-31 08:52:19.616241: Epoch 906 +2025-10-31 08:52:19.618384: Current learning rate: 0.00119 +2025-10-31 08:52:41.506093: train_loss -0.9937 +2025-10-31 08:52:41.510648: val_loss -0.8935 +2025-10-31 08:52:41.512434: Pseudo dice [np.float32(0.9866), np.float32(0.9915), np.float32(0.9945), np.float32(0.8067)] +2025-10-31 08:52:41.514252: Epoch time: 21.89 s +2025-10-31 08:52:42.654371: +2025-10-31 08:52:42.656493: Epoch 907 +2025-10-31 08:52:42.658096: Current learning rate: 0.00118 +2025-10-31 08:53:03.893006: train_loss -0.9937 +2025-10-31 08:53:03.896248: val_loss -0.8891 +2025-10-31 08:53:03.898516: Pseudo dice [np.float32(0.9865), np.float32(0.9918), np.float32(0.9942), np.float32(0.7945)] +2025-10-31 08:53:03.901045: Epoch time: 21.24 s +2025-10-31 08:53:05.864971: +2025-10-31 08:53:05.867035: Epoch 908 +2025-10-31 08:53:05.868829: Current learning rate: 0.00117 +2025-10-31 08:53:27.662012: train_loss -0.9938 +2025-10-31 08:53:27.665390: val_loss -0.8988 +2025-10-31 08:53:27.667658: Pseudo dice [np.float32(0.9869), np.float32(0.9918), np.float32(0.9947), np.float32(0.8127)] +2025-10-31 08:53:27.669944: Epoch time: 21.8 s +2025-10-31 08:53:28.793619: +2025-10-31 08:53:28.796004: Epoch 909 +2025-10-31 08:53:28.798075: Current learning rate: 0.00116 +2025-10-31 08:53:50.778262: train_loss -0.9942 +2025-10-31 08:53:50.784355: val_loss -0.8993 +2025-10-31 08:53:50.786098: Pseudo dice [np.float32(0.9869), np.float32(0.9923), np.float32(0.9947), np.float32(0.8153)] +2025-10-31 08:53:50.787896: Epoch time: 21.99 s +2025-10-31 08:53:52.060448: +2025-10-31 08:53:52.062748: Epoch 910 +2025-10-31 08:53:52.064661: Current learning rate: 0.00115 +2025-10-31 08:54:14.131264: train_loss -0.9941 +2025-10-31 08:54:14.133553: val_loss -0.8913 +2025-10-31 08:54:14.135307: Pseudo dice [np.float32(0.9862), np.float32(0.9915), np.float32(0.9944), np.float32(0.7951)] +2025-10-31 08:54:14.137220: Epoch time: 22.07 s +2025-10-31 08:54:15.371503: +2025-10-31 08:54:15.373873: Epoch 911 +2025-10-31 08:54:15.376033: Current learning rate: 0.00113 +2025-10-31 08:54:38.141922: train_loss -0.9943 +2025-10-31 08:54:38.145515: val_loss -0.8859 +2025-10-31 08:54:38.147887: Pseudo dice [np.float32(0.987), np.float32(0.9912), np.float32(0.9941), np.float32(0.7812)] +2025-10-31 08:54:38.150128: Epoch time: 22.77 s +2025-10-31 08:54:39.319085: +2025-10-31 08:54:39.320766: Epoch 912 +2025-10-31 08:54:39.322184: Current learning rate: 0.00112 +2025-10-31 08:55:01.171606: train_loss -0.9938 +2025-10-31 08:55:01.178217: val_loss -0.9025 +2025-10-31 08:55:01.179969: Pseudo dice [np.float32(0.9866), np.float32(0.9926), np.float32(0.995), np.float32(0.8261)] +2025-10-31 08:55:01.181758: Epoch time: 21.85 s +2025-10-31 08:55:02.287714: +2025-10-31 08:55:02.289896: Epoch 913 +2025-10-31 08:55:02.291847: Current learning rate: 0.00111 +2025-10-31 08:55:22.661871: train_loss -0.9941 +2025-10-31 08:55:22.664097: val_loss -0.8891 +2025-10-31 08:55:22.665968: Pseudo dice [np.float32(0.9855), np.float32(0.9906), np.float32(0.9943), np.float32(0.8028)] +2025-10-31 08:55:22.667740: Epoch time: 20.38 s +2025-10-31 08:55:23.876172: +2025-10-31 08:55:23.878135: Epoch 914 +2025-10-31 08:55:23.879803: Current learning rate: 0.0011 +2025-10-31 08:55:43.853409: train_loss -0.9943 +2025-10-31 08:55:43.855491: val_loss -0.8945 +2025-10-31 08:55:43.857085: Pseudo dice [np.float32(0.9869), np.float32(0.9918), np.float32(0.9947), np.float32(0.8087)] +2025-10-31 08:55:43.858574: Epoch time: 19.98 s +2025-10-31 08:55:45.136554: +2025-10-31 08:55:45.138561: Epoch 915 +2025-10-31 08:55:45.140351: Current learning rate: 0.00109 +2025-10-31 08:56:07.565808: train_loss -0.994 +2025-10-31 08:56:07.569122: val_loss -0.8935 +2025-10-31 08:56:07.570760: Pseudo dice [np.float32(0.9867), np.float32(0.9916), np.float32(0.9947), np.float32(0.8045)] +2025-10-31 08:56:07.572253: Epoch time: 22.43 s +2025-10-31 08:56:08.765213: +2025-10-31 08:56:08.767497: Epoch 916 +2025-10-31 08:56:08.769475: Current learning rate: 0.00108 +2025-10-31 08:56:31.658862: train_loss -0.9941 +2025-10-31 08:56:31.660830: val_loss -0.897 +2025-10-31 08:56:31.662630: Pseudo dice [np.float32(0.988), np.float32(0.9928), np.float32(0.9947), np.float32(0.8049)] +2025-10-31 08:56:31.664068: Epoch time: 22.9 s +2025-10-31 08:56:32.907190: +2025-10-31 08:56:32.909594: Epoch 917 +2025-10-31 08:56:32.911329: Current learning rate: 0.00106 +2025-10-31 08:56:54.926249: train_loss -0.9943 +2025-10-31 08:56:54.930605: val_loss -0.8939 +2025-10-31 08:56:54.932884: Pseudo dice [np.float32(0.9858), np.float32(0.9913), np.float32(0.9945), np.float32(0.809)] +2025-10-31 08:56:54.934704: Epoch time: 22.02 s +2025-10-31 08:56:56.191142: +2025-10-31 08:56:56.196130: Epoch 918 +2025-10-31 08:56:56.200857: Current learning rate: 0.00105 +2025-10-31 08:57:18.017679: train_loss -0.9944 +2025-10-31 08:57:18.020681: val_loss -0.8892 +2025-10-31 08:57:18.022428: Pseudo dice [np.float32(0.9851), np.float32(0.9919), np.float32(0.9949), np.float32(0.7995)] +2025-10-31 08:57:18.024148: Epoch time: 21.83 s +2025-10-31 08:57:19.237212: +2025-10-31 08:57:19.239214: Epoch 919 +2025-10-31 08:57:19.240715: Current learning rate: 0.00104 +2025-10-31 08:57:40.804015: train_loss -0.9941 +2025-10-31 08:57:40.809722: val_loss -0.8884 +2025-10-31 08:57:40.811821: Pseudo dice [np.float32(0.9853), np.float32(0.9911), np.float32(0.9942), np.float32(0.7951)] +2025-10-31 08:57:40.814202: Epoch time: 21.57 s +2025-10-31 08:57:42.039279: +2025-10-31 08:57:42.041240: Epoch 920 +2025-10-31 08:57:42.042870: Current learning rate: 0.00103 +2025-10-31 08:58:04.471713: train_loss -0.9941 +2025-10-31 08:58:04.474261: val_loss -0.8915 +2025-10-31 08:58:04.477036: Pseudo dice [np.float32(0.986), np.float32(0.9917), np.float32(0.9946), np.float32(0.8005)] +2025-10-31 08:58:04.478849: Epoch time: 22.43 s +2025-10-31 08:58:06.310984: +2025-10-31 08:58:06.313306: Epoch 921 +2025-10-31 08:58:06.315449: Current learning rate: 0.00102 +2025-10-31 08:58:27.023705: train_loss -0.9939 +2025-10-31 08:58:27.027409: val_loss -0.9039 +2025-10-31 08:58:27.029334: Pseudo dice [np.float32(0.9877), np.float32(0.9927), np.float32(0.9951), np.float32(0.8192)] +2025-10-31 08:58:27.031100: Epoch time: 20.71 s +2025-10-31 08:58:28.286869: +2025-10-31 08:58:28.288654: Epoch 922 +2025-10-31 08:58:28.290283: Current learning rate: 0.00101 +2025-10-31 08:58:50.912581: train_loss -0.9941 +2025-10-31 08:58:50.915112: val_loss -0.894 +2025-10-31 08:58:50.917125: Pseudo dice [np.float32(0.9855), np.float32(0.9914), np.float32(0.9947), np.float32(0.8075)] +2025-10-31 08:58:50.919841: Epoch time: 22.63 s +2025-10-31 08:58:52.145564: +2025-10-31 08:58:52.147488: Epoch 923 +2025-10-31 08:58:52.149357: Current learning rate: 0.001 +2025-10-31 08:59:15.162493: train_loss -0.9942 +2025-10-31 08:59:15.165865: val_loss -0.9 +2025-10-31 08:59:15.167902: Pseudo dice [np.float32(0.9865), np.float32(0.9919), np.float32(0.9949), np.float32(0.8164)] +2025-10-31 08:59:15.169892: Epoch time: 23.02 s +2025-10-31 08:59:15.171708: Yayy! New best EMA pseudo Dice: 0.9448000192642212 +2025-10-31 08:59:17.356607: +2025-10-31 08:59:17.359085: Epoch 924 +2025-10-31 08:59:17.361102: Current learning rate: 0.00098 +2025-10-31 08:59:39.138160: train_loss -0.9941 +2025-10-31 08:59:39.141899: val_loss -0.8973 +2025-10-31 08:59:39.143874: Pseudo dice [np.float32(0.9872), np.float32(0.9918), np.float32(0.9949), np.float32(0.8079)] +2025-10-31 08:59:39.145788: Epoch time: 21.78 s +2025-10-31 08:59:39.147446: Yayy! New best EMA pseudo Dice: 0.9448999762535095 +2025-10-31 08:59:41.420712: +2025-10-31 08:59:41.422819: Epoch 925 +2025-10-31 08:59:41.424555: Current learning rate: 0.00097 +2025-10-31 09:00:03.152877: train_loss -0.994 +2025-10-31 09:00:03.155664: val_loss -0.895 +2025-10-31 09:00:03.158035: Pseudo dice [np.float32(0.9859), np.float32(0.9912), np.float32(0.9946), np.float32(0.8124)] +2025-10-31 09:00:03.160207: Epoch time: 21.73 s +2025-10-31 09:00:03.162105: Yayy! New best EMA pseudo Dice: 0.9449999928474426 +2025-10-31 09:00:05.718737: +2025-10-31 09:00:05.721101: Epoch 926 +2025-10-31 09:00:05.723027: Current learning rate: 0.00096 +2025-10-31 09:00:28.503714: train_loss -0.9944 +2025-10-31 09:00:28.508091: val_loss -0.9026 +2025-10-31 09:00:28.512723: Pseudo dice [np.float32(0.9865), np.float32(0.9924), np.float32(0.9952), np.float32(0.8173)] +2025-10-31 09:00:28.517566: Epoch time: 22.79 s +2025-10-31 09:00:28.522057: Yayy! New best EMA pseudo Dice: 0.9452999830245972 +2025-10-31 09:00:30.968802: +2025-10-31 09:00:30.971363: Epoch 927 +2025-10-31 09:00:30.974817: Current learning rate: 0.00095 +2025-10-31 09:00:52.649247: train_loss -0.9946 +2025-10-31 09:00:52.656690: val_loss -0.9031 +2025-10-31 09:00:52.658421: Pseudo dice [np.float32(0.9841), np.float32(0.9914), np.float32(0.9952), np.float32(0.8362)] +2025-10-31 09:00:52.660296: Epoch time: 21.68 s +2025-10-31 09:00:52.661852: Yayy! New best EMA pseudo Dice: 0.945900022983551 +2025-10-31 09:00:55.212362: +2025-10-31 09:00:55.214720: Epoch 928 +2025-10-31 09:00:55.216434: Current learning rate: 0.00094 +2025-10-31 09:01:17.371818: train_loss -0.9941 +2025-10-31 09:01:17.374173: val_loss -0.8901 +2025-10-31 09:01:17.376229: Pseudo dice [np.float32(0.9849), np.float32(0.9918), np.float32(0.9944), np.float32(0.7977)] +2025-10-31 09:01:17.378846: Epoch time: 22.16 s +2025-10-31 09:01:18.602205: +2025-10-31 09:01:18.604590: Epoch 929 +2025-10-31 09:01:18.606178: Current learning rate: 0.00092 +2025-10-31 09:01:40.882357: train_loss -0.9944 +2025-10-31 09:01:40.886690: val_loss -0.8964 +2025-10-31 09:01:40.888681: Pseudo dice [np.float32(0.9856), np.float32(0.9924), np.float32(0.9948), np.float32(0.8055)] +2025-10-31 09:01:40.890595: Epoch time: 22.28 s +2025-10-31 09:01:42.044461: +2025-10-31 09:01:42.049792: Epoch 930 +2025-10-31 09:01:42.051610: Current learning rate: 0.00091 +2025-10-31 09:02:04.185603: train_loss -0.9949 +2025-10-31 09:02:04.188020: val_loss -0.8944 +2025-10-31 09:02:04.190570: Pseudo dice [np.float32(0.9861), np.float32(0.9919), np.float32(0.9946), np.float32(0.7996)] +2025-10-31 09:02:04.193410: Epoch time: 22.14 s +2025-10-31 09:02:05.409487: +2025-10-31 09:02:05.415315: Epoch 931 +2025-10-31 09:02:05.420811: Current learning rate: 0.0009 +2025-10-31 09:02:27.269896: train_loss -0.9942 +2025-10-31 09:02:27.272234: val_loss -0.8868 +2025-10-31 09:02:27.273793: Pseudo dice [np.float32(0.9863), np.float32(0.9914), np.float32(0.9942), np.float32(0.7915)] +2025-10-31 09:02:27.275511: Epoch time: 21.86 s +2025-10-31 09:02:28.479070: +2025-10-31 09:02:28.480788: Epoch 932 +2025-10-31 09:02:28.482358: Current learning rate: 0.00089 +2025-10-31 09:02:50.664993: train_loss -0.9941 +2025-10-31 09:02:50.668301: val_loss -0.8931 +2025-10-31 09:02:50.670378: Pseudo dice [np.float32(0.9869), np.float32(0.9923), np.float32(0.9946), np.float32(0.7982)] +2025-10-31 09:02:50.672454: Epoch time: 22.19 s +2025-10-31 09:02:52.143440: +2025-10-31 09:02:52.145126: Epoch 933 +2025-10-31 09:02:52.146516: Current learning rate: 0.00088 +2025-10-31 09:03:13.837310: train_loss -0.9946 +2025-10-31 09:03:13.841444: val_loss -0.8966 +2025-10-31 09:03:13.842999: Pseudo dice [np.float32(0.9859), np.float32(0.9918), np.float32(0.995), np.float32(0.8128)] +2025-10-31 09:03:13.845455: Epoch time: 21.7 s +2025-10-31 09:03:15.046494: +2025-10-31 09:03:15.052560: Epoch 934 +2025-10-31 09:03:15.054529: Current learning rate: 0.00087 +2025-10-31 09:03:37.693552: train_loss -0.9948 +2025-10-31 09:03:37.695739: val_loss -0.895 +2025-10-31 09:03:37.697266: Pseudo dice [np.float32(0.9856), np.float32(0.9919), np.float32(0.9948), np.float32(0.8086)] +2025-10-31 09:03:37.698751: Epoch time: 22.65 s +2025-10-31 09:03:38.898272: +2025-10-31 09:03:38.900237: Epoch 935 +2025-10-31 09:03:38.902774: Current learning rate: 0.00085 +2025-10-31 09:04:00.998709: train_loss -0.9949 +2025-10-31 09:04:01.001704: val_loss -0.897 +2025-10-31 09:04:01.003177: Pseudo dice [np.float32(0.986), np.float32(0.9918), np.float32(0.9951), np.float32(0.8113)] +2025-10-31 09:04:01.005523: Epoch time: 22.1 s +2025-10-31 09:04:02.209016: +2025-10-31 09:04:02.211179: Epoch 936 +2025-10-31 09:04:02.212630: Current learning rate: 0.00084 +2025-10-31 09:04:22.369721: train_loss -0.9943 +2025-10-31 09:04:22.375799: val_loss -0.8942 +2025-10-31 09:04:22.377612: Pseudo dice [np.float32(0.987), np.float32(0.9919), np.float32(0.9948), np.float32(0.8029)] +2025-10-31 09:04:22.379446: Epoch time: 20.16 s +2025-10-31 09:04:23.579051: +2025-10-31 09:04:23.581025: Epoch 937 +2025-10-31 09:04:23.582744: Current learning rate: 0.00083 +2025-10-31 09:04:45.858835: train_loss -0.9944 +2025-10-31 09:04:45.860924: val_loss -0.8961 +2025-10-31 09:04:45.862280: Pseudo dice [np.float32(0.9865), np.float32(0.9918), np.float32(0.995), np.float32(0.8083)] +2025-10-31 09:04:45.863677: Epoch time: 22.28 s +2025-10-31 09:04:47.063097: +2025-10-31 09:04:47.065988: Epoch 938 +2025-10-31 09:04:47.070002: Current learning rate: 0.00082 +2025-10-31 09:05:09.557197: train_loss -0.9945 +2025-10-31 09:05:09.560352: val_loss -0.8876 +2025-10-31 09:05:09.562167: Pseudo dice [np.float32(0.9858), np.float32(0.9908), np.float32(0.9945), np.float32(0.7951)] +2025-10-31 09:05:09.563815: Epoch time: 22.5 s +2025-10-31 09:05:10.774760: +2025-10-31 09:05:10.776825: Epoch 939 +2025-10-31 09:05:10.778486: Current learning rate: 0.00081 +2025-10-31 09:05:32.231938: train_loss -0.9944 +2025-10-31 09:05:32.234397: val_loss -0.8864 +2025-10-31 09:05:32.236086: Pseudo dice [np.float32(0.9855), np.float32(0.9919), np.float32(0.9944), np.float32(0.7864)] +2025-10-31 09:05:32.237715: Epoch time: 21.46 s +2025-10-31 09:05:33.356690: +2025-10-31 09:05:33.358596: Epoch 940 +2025-10-31 09:05:33.360217: Current learning rate: 0.00079 +2025-10-31 09:05:55.553487: train_loss -0.9946 +2025-10-31 09:05:55.555763: val_loss -0.8864 +2025-10-31 09:05:55.557984: Pseudo dice [np.float32(0.9856), np.float32(0.9914), np.float32(0.9943), np.float32(0.7857)] +2025-10-31 09:05:55.560103: Epoch time: 22.2 s +2025-10-31 09:05:56.770413: +2025-10-31 09:05:56.772545: Epoch 941 +2025-10-31 09:05:56.774528: Current learning rate: 0.00078 +2025-10-31 09:06:18.531283: train_loss -0.9942 +2025-10-31 09:06:18.534133: val_loss -0.8901 +2025-10-31 09:06:18.535867: Pseudo dice [np.float32(0.9853), np.float32(0.9912), np.float32(0.9943), np.float32(0.8025)] +2025-10-31 09:06:18.537662: Epoch time: 21.76 s +2025-10-31 09:06:19.802502: +2025-10-31 09:06:19.804584: Epoch 942 +2025-10-31 09:06:19.806300: Current learning rate: 0.00077 +2025-10-31 09:06:39.752294: train_loss -0.9946 +2025-10-31 09:06:39.764941: val_loss -0.8906 +2025-10-31 09:06:39.772192: Pseudo dice [np.float32(0.9852), np.float32(0.9911), np.float32(0.9944), np.float32(0.7969)] +2025-10-31 09:06:39.779403: Epoch time: 19.95 s +2025-10-31 09:06:41.021381: +2025-10-31 09:06:41.023424: Epoch 943 +2025-10-31 09:06:41.025661: Current learning rate: 0.00076 +2025-10-31 09:07:03.142861: train_loss -0.9947 +2025-10-31 09:07:03.145194: val_loss -0.8923 +2025-10-31 09:07:03.146753: Pseudo dice [np.float32(0.9865), np.float32(0.992), np.float32(0.9947), np.float32(0.7974)] +2025-10-31 09:07:03.148200: Epoch time: 22.12 s +2025-10-31 09:07:04.371361: +2025-10-31 09:07:04.374328: Epoch 944 +2025-10-31 09:07:04.376161: Current learning rate: 0.00075 +2025-10-31 09:07:26.658086: train_loss -0.9948 +2025-10-31 09:07:26.662430: val_loss -0.8858 +2025-10-31 09:07:26.664563: Pseudo dice [np.float32(0.9866), np.float32(0.9916), np.float32(0.9943), np.float32(0.7888)] +2025-10-31 09:07:26.666288: Epoch time: 22.29 s +2025-10-31 09:07:27.697682: +2025-10-31 09:07:27.699367: Epoch 945 +2025-10-31 09:07:27.701060: Current learning rate: 0.00074 +2025-10-31 09:07:49.942725: train_loss -0.9943 +2025-10-31 09:07:49.945929: val_loss -0.8866 +2025-10-31 09:07:49.950453: Pseudo dice [np.float32(0.9861), np.float32(0.9914), np.float32(0.9944), np.float32(0.7888)] +2025-10-31 09:07:49.953537: Epoch time: 22.25 s +2025-10-31 09:07:51.625615: +2025-10-31 09:07:51.627696: Epoch 946 +2025-10-31 09:07:51.629372: Current learning rate: 0.00072 +2025-10-31 09:08:13.009389: train_loss -0.9945 +2025-10-31 09:08:13.011965: val_loss -0.8943 +2025-10-31 09:08:13.013820: Pseudo dice [np.float32(0.9863), np.float32(0.9916), np.float32(0.9947), np.float32(0.7999)] +2025-10-31 09:08:13.015831: Epoch time: 21.39 s +2025-10-31 09:08:14.217049: +2025-10-31 09:08:14.219071: Epoch 947 +2025-10-31 09:08:14.220777: Current learning rate: 0.00071 +2025-10-31 09:08:36.188279: train_loss -0.9945 +2025-10-31 09:08:36.194940: val_loss -0.8949 +2025-10-31 09:08:36.196786: Pseudo dice [np.float32(0.9868), np.float32(0.9915), np.float32(0.9945), np.float32(0.8075)] +2025-10-31 09:08:36.198436: Epoch time: 21.97 s +2025-10-31 09:08:37.499947: +2025-10-31 09:08:37.501783: Epoch 948 +2025-10-31 09:08:37.503328: Current learning rate: 0.0007 +2025-10-31 09:08:58.325373: train_loss -0.9945 +2025-10-31 09:08:58.327586: val_loss -0.8965 +2025-10-31 09:08:58.329182: Pseudo dice [np.float32(0.9866), np.float32(0.9918), np.float32(0.9946), np.float32(0.8089)] +2025-10-31 09:08:58.330796: Epoch time: 20.83 s +2025-10-31 09:08:59.695427: +2025-10-31 09:08:59.697506: Epoch 949 +2025-10-31 09:08:59.699045: Current learning rate: 0.00069 +2025-10-31 09:09:22.214230: train_loss -0.9946 +2025-10-31 09:09:22.217171: val_loss -0.8892 +2025-10-31 09:09:22.218882: Pseudo dice [np.float32(0.9852), np.float32(0.9911), np.float32(0.9945), np.float32(0.7993)] +2025-10-31 09:09:22.220445: Epoch time: 22.52 s +2025-10-31 09:09:24.831954: +2025-10-31 09:09:24.833633: Epoch 950 +2025-10-31 09:09:24.835157: Current learning rate: 0.00067 +2025-10-31 09:09:47.379342: train_loss -0.9948 +2025-10-31 09:09:47.384063: val_loss -0.8926 +2025-10-31 09:09:47.386045: Pseudo dice [np.float32(0.9868), np.float32(0.9914), np.float32(0.9944), np.float32(0.8065)] +2025-10-31 09:09:47.388017: Epoch time: 22.55 s +2025-10-31 09:09:48.577566: +2025-10-31 09:09:48.580086: Epoch 951 +2025-10-31 09:09:48.582459: Current learning rate: 0.00066 +2025-10-31 09:10:11.026655: train_loss -0.9942 +2025-10-31 09:10:11.029468: val_loss -0.8936 +2025-10-31 09:10:11.031373: Pseudo dice [np.float32(0.9863), np.float32(0.9922), np.float32(0.9944), np.float32(0.8022)] +2025-10-31 09:10:11.032968: Epoch time: 22.45 s +2025-10-31 09:10:12.236886: +2025-10-31 09:10:12.238787: Epoch 952 +2025-10-31 09:10:12.240338: Current learning rate: 0.00065 +2025-10-31 09:10:33.262424: train_loss -0.9941 +2025-10-31 09:10:33.265008: val_loss -0.8865 +2025-10-31 09:10:33.266491: Pseudo dice [np.float32(0.9856), np.float32(0.991), np.float32(0.994), np.float32(0.796)] +2025-10-31 09:10:33.268085: Epoch time: 21.03 s +2025-10-31 09:10:34.408623: +2025-10-31 09:10:34.414348: Epoch 953 +2025-10-31 09:10:34.415971: Current learning rate: 0.00064 +2025-10-31 09:10:56.486403: train_loss -0.9946 +2025-10-31 09:10:56.491948: val_loss -0.8894 +2025-10-31 09:10:56.493526: Pseudo dice [np.float32(0.9862), np.float32(0.9915), np.float32(0.9943), np.float32(0.7963)] +2025-10-31 09:10:56.495037: Epoch time: 22.08 s +2025-10-31 09:10:57.604052: +2025-10-31 09:10:57.606007: Epoch 954 +2025-10-31 09:10:57.607965: Current learning rate: 0.00063 +2025-10-31 09:11:18.646233: train_loss -0.9946 +2025-10-31 09:11:18.649482: val_loss -0.8943 +2025-10-31 09:11:18.651271: Pseudo dice [np.float32(0.9877), np.float32(0.9924), np.float32(0.9944), np.float32(0.8019)] +2025-10-31 09:11:18.653134: Epoch time: 21.04 s +2025-10-31 09:11:19.790267: +2025-10-31 09:11:19.792594: Epoch 955 +2025-10-31 09:11:19.794445: Current learning rate: 0.00061 +2025-10-31 09:11:42.216612: train_loss -0.9948 +2025-10-31 09:11:42.219746: val_loss -0.8868 +2025-10-31 09:11:42.221605: Pseudo dice [np.float32(0.9865), np.float32(0.9919), np.float32(0.9941), np.float32(0.7881)] +2025-10-31 09:11:42.223635: Epoch time: 22.43 s +2025-10-31 09:11:43.366355: +2025-10-31 09:11:43.368809: Epoch 956 +2025-10-31 09:11:43.370854: Current learning rate: 0.0006 +2025-10-31 09:12:05.512993: train_loss -0.995 +2025-10-31 09:12:05.518038: val_loss -0.8947 +2025-10-31 09:12:05.521800: Pseudo dice [np.float32(0.9863), np.float32(0.9916), np.float32(0.9947), np.float32(0.8102)] +2025-10-31 09:12:05.524980: Epoch time: 22.15 s +2025-10-31 09:12:06.711718: +2025-10-31 09:12:06.713620: Epoch 957 +2025-10-31 09:12:06.715405: Current learning rate: 0.00059 +2025-10-31 09:12:28.897602: train_loss -0.9947 +2025-10-31 09:12:28.900010: val_loss -0.8873 +2025-10-31 09:12:28.901655: Pseudo dice [np.float32(0.9852), np.float32(0.9914), np.float32(0.9945), np.float32(0.7964)] +2025-10-31 09:12:28.903476: Epoch time: 22.19 s +2025-10-31 09:12:30.022648: +2025-10-31 09:12:30.024536: Epoch 958 +2025-10-31 09:12:30.026231: Current learning rate: 0.00058 +2025-10-31 09:12:52.270849: train_loss -0.9943 +2025-10-31 09:12:52.273145: val_loss -0.8902 +2025-10-31 09:12:52.274917: Pseudo dice [np.float32(0.9864), np.float32(0.9915), np.float32(0.9947), np.float32(0.7941)] +2025-10-31 09:12:52.276565: Epoch time: 22.25 s +2025-10-31 09:12:53.982231: +2025-10-31 09:12:53.984689: Epoch 959 +2025-10-31 09:12:53.986684: Current learning rate: 0.00056 +2025-10-31 09:13:14.203415: train_loss -0.9951 +2025-10-31 09:13:14.206722: val_loss -0.887 +2025-10-31 09:13:14.208740: Pseudo dice [np.float32(0.9851), np.float32(0.992), np.float32(0.9942), np.float32(0.7942)] +2025-10-31 09:13:14.210690: Epoch time: 20.22 s +2025-10-31 09:13:15.458720: +2025-10-31 09:13:15.461006: Epoch 960 +2025-10-31 09:13:15.462931: Current learning rate: 0.00055 +2025-10-31 09:13:36.740604: train_loss -0.9948 +2025-10-31 09:13:36.743757: val_loss -0.8818 +2025-10-31 09:13:36.745802: Pseudo dice [np.float32(0.985), np.float32(0.991), np.float32(0.9943), np.float32(0.779)] +2025-10-31 09:13:36.747787: Epoch time: 21.28 s +2025-10-31 09:13:37.910028: +2025-10-31 09:13:37.912533: Epoch 961 +2025-10-31 09:13:37.914787: Current learning rate: 0.00054 +2025-10-31 09:14:00.474738: train_loss -0.9945 +2025-10-31 09:14:00.477421: val_loss -0.8894 +2025-10-31 09:14:00.479187: Pseudo dice [np.float32(0.986), np.float32(0.9913), np.float32(0.9943), np.float32(0.7993)] +2025-10-31 09:14:00.480922: Epoch time: 22.57 s +2025-10-31 09:14:01.738393: +2025-10-31 09:14:01.740464: Epoch 962 +2025-10-31 09:14:01.746026: Current learning rate: 0.00053 +2025-10-31 09:14:24.367427: train_loss -0.9947 +2025-10-31 09:14:24.370535: val_loss -0.8873 +2025-10-31 09:14:24.372605: Pseudo dice [np.float32(0.9846), np.float32(0.9911), np.float32(0.9944), np.float32(0.793)] +2025-10-31 09:14:24.374721: Epoch time: 22.63 s +2025-10-31 09:14:25.498365: +2025-10-31 09:14:25.500378: Epoch 963 +2025-10-31 09:14:25.502135: Current learning rate: 0.00051 +2025-10-31 09:14:46.969109: train_loss -0.9948 +2025-10-31 09:14:46.972168: val_loss -0.882 +2025-10-31 09:14:46.973994: Pseudo dice [np.float32(0.9849), np.float32(0.9911), np.float32(0.9941), np.float32(0.7825)] +2025-10-31 09:14:46.975806: Epoch time: 21.47 s +2025-10-31 09:14:48.115732: +2025-10-31 09:14:48.118356: Epoch 964 +2025-10-31 09:14:48.120296: Current learning rate: 0.0005 +2025-10-31 09:15:10.181515: train_loss -0.9948 +2025-10-31 09:15:10.183784: val_loss -0.8911 +2025-10-31 09:15:10.185812: Pseudo dice [np.float32(0.9843), np.float32(0.9912), np.float32(0.9945), np.float32(0.807)] +2025-10-31 09:15:10.187645: Epoch time: 22.07 s +2025-10-31 09:15:11.391998: +2025-10-31 09:15:11.394388: Epoch 965 +2025-10-31 09:15:11.396271: Current learning rate: 0.00049 +2025-10-31 09:15:33.238724: train_loss -0.9947 +2025-10-31 09:15:33.245148: val_loss -0.8849 +2025-10-31 09:15:33.247040: Pseudo dice [np.float32(0.9857), np.float32(0.9915), np.float32(0.9943), np.float32(0.7839)] +2025-10-31 09:15:33.248750: Epoch time: 21.85 s +2025-10-31 09:15:34.503206: +2025-10-31 09:15:34.504890: Epoch 966 +2025-10-31 09:15:34.506390: Current learning rate: 0.00048 +2025-10-31 09:15:56.095056: train_loss -0.9952 +2025-10-31 09:15:56.098331: val_loss -0.8886 +2025-10-31 09:15:56.100507: Pseudo dice [np.float32(0.986), np.float32(0.9912), np.float32(0.9945), np.float32(0.7958)] +2025-10-31 09:15:56.102536: Epoch time: 21.59 s +2025-10-31 09:15:57.375540: +2025-10-31 09:15:57.377539: Epoch 967 +2025-10-31 09:15:57.379184: Current learning rate: 0.00046 +2025-10-31 09:16:19.759444: train_loss -0.995 +2025-10-31 09:16:19.763157: val_loss -0.8905 +2025-10-31 09:16:19.766876: Pseudo dice [np.float32(0.9859), np.float32(0.992), np.float32(0.9947), np.float32(0.7969)] +2025-10-31 09:16:19.769863: Epoch time: 22.39 s +2025-10-31 09:16:20.965658: +2025-10-31 09:16:20.967999: Epoch 968 +2025-10-31 09:16:20.969982: Current learning rate: 0.00045 +2025-10-31 09:16:42.972530: train_loss -0.9949 +2025-10-31 09:16:42.976172: val_loss -0.8871 +2025-10-31 09:16:42.978292: Pseudo dice [np.float32(0.9862), np.float32(0.9917), np.float32(0.9944), np.float32(0.794)] +2025-10-31 09:16:42.980424: Epoch time: 22.01 s +2025-10-31 09:16:44.290054: +2025-10-31 09:16:44.292374: Epoch 969 +2025-10-31 09:16:44.294633: Current learning rate: 0.00044 +2025-10-31 09:17:06.296420: train_loss -0.9955 +2025-10-31 09:17:06.321482: val_loss -0.8925 +2025-10-31 09:17:06.339627: Pseudo dice [np.float32(0.9852), np.float32(0.9914), np.float32(0.9946), np.float32(0.8046)] +2025-10-31 09:17:06.358687: Epoch time: 22.01 s +2025-10-31 09:17:07.461818: +2025-10-31 09:17:07.465964: Epoch 970 +2025-10-31 09:17:07.469034: Current learning rate: 0.00043 +2025-10-31 09:17:29.234588: train_loss -0.9953 +2025-10-31 09:17:29.237677: val_loss -0.8941 +2025-10-31 09:17:29.239772: Pseudo dice [np.float32(0.9858), np.float32(0.9918), np.float32(0.9949), np.float32(0.8081)] +2025-10-31 09:17:29.241682: Epoch time: 21.77 s +2025-10-31 09:17:31.018836: +2025-10-31 09:17:31.021633: Epoch 971 +2025-10-31 09:17:31.023968: Current learning rate: 0.00041 +2025-10-31 09:17:52.597398: train_loss -0.9952 +2025-10-31 09:17:52.600315: val_loss -0.8914 +2025-10-31 09:17:52.602040: Pseudo dice [np.float32(0.9857), np.float32(0.9917), np.float32(0.9946), np.float32(0.8011)] +2025-10-31 09:17:52.603718: Epoch time: 21.58 s +2025-10-31 09:17:53.837291: +2025-10-31 09:17:53.842455: Epoch 972 +2025-10-31 09:17:53.844375: Current learning rate: 0.0004 +2025-10-31 09:18:14.483636: train_loss -0.9954 +2025-10-31 09:18:14.486195: val_loss -0.8888 +2025-10-31 09:18:14.487876: Pseudo dice [np.float32(0.9857), np.float32(0.9914), np.float32(0.9943), np.float32(0.7985)] +2025-10-31 09:18:14.490158: Epoch time: 20.65 s +2025-10-31 09:18:15.695487: +2025-10-31 09:18:15.697978: Epoch 973 +2025-10-31 09:18:15.699845: Current learning rate: 0.00039 +2025-10-31 09:18:37.368459: train_loss -0.9948 +2025-10-31 09:18:37.371560: val_loss -0.8882 +2025-10-31 09:18:37.373948: Pseudo dice [np.float32(0.9854), np.float32(0.991), np.float32(0.9945), np.float32(0.796)] +2025-10-31 09:18:37.376287: Epoch time: 21.67 s +2025-10-31 09:18:38.501674: +2025-10-31 09:18:38.503589: Epoch 974 +2025-10-31 09:18:38.505795: Current learning rate: 0.00037 +2025-10-31 09:19:00.285713: train_loss -0.9951 +2025-10-31 09:19:00.290148: val_loss -0.8904 +2025-10-31 09:19:00.292184: Pseudo dice [np.float32(0.9862), np.float32(0.992), np.float32(0.9945), np.float32(0.7981)] +2025-10-31 09:19:00.294205: Epoch time: 21.79 s +2025-10-31 09:19:01.360651: +2025-10-31 09:19:01.363158: Epoch 975 +2025-10-31 09:19:01.364995: Current learning rate: 0.00036 +2025-10-31 09:19:23.506741: train_loss -0.9948 +2025-10-31 09:19:23.509976: val_loss -0.893 +2025-10-31 09:19:23.512379: Pseudo dice [np.float32(0.9853), np.float32(0.9918), np.float32(0.9949), np.float32(0.8056)] +2025-10-31 09:19:23.514606: Epoch time: 22.15 s +2025-10-31 09:19:24.551092: +2025-10-31 09:19:24.553626: Epoch 976 +2025-10-31 09:19:24.555869: Current learning rate: 0.00035 +2025-10-31 09:19:46.773785: train_loss -0.9951 +2025-10-31 09:19:46.777768: val_loss -0.8892 +2025-10-31 09:19:46.779850: Pseudo dice [np.float32(0.9855), np.float32(0.9914), np.float32(0.9947), np.float32(0.7946)] +2025-10-31 09:19:46.781962: Epoch time: 22.22 s +2025-10-31 09:19:48.050031: +2025-10-31 09:19:48.053335: Epoch 977 +2025-10-31 09:19:48.055609: Current learning rate: 0.00034 +2025-10-31 09:20:10.178333: train_loss -0.9955 +2025-10-31 09:20:10.181941: val_loss -0.8919 +2025-10-31 09:20:10.184006: Pseudo dice [np.float32(0.9859), np.float32(0.9918), np.float32(0.9946), np.float32(0.803)] +2025-10-31 09:20:10.185930: Epoch time: 22.13 s +2025-10-31 09:20:11.465883: +2025-10-31 09:20:11.468276: Epoch 978 +2025-10-31 09:20:11.470304: Current learning rate: 0.00032 +2025-10-31 09:20:31.038803: train_loss -0.9951 +2025-10-31 09:20:31.042504: val_loss -0.8944 +2025-10-31 09:20:31.044459: Pseudo dice [np.float32(0.9861), np.float32(0.9919), np.float32(0.9948), np.float32(0.8073)] +2025-10-31 09:20:31.046477: Epoch time: 19.57 s +2025-10-31 09:20:32.301285: +2025-10-31 09:20:32.303583: Epoch 979 +2025-10-31 09:20:32.305570: Current learning rate: 0.00031 +2025-10-31 09:20:53.469173: train_loss -0.9951 +2025-10-31 09:20:53.473321: val_loss -0.8936 +2025-10-31 09:20:53.475476: Pseudo dice [np.float32(0.9862), np.float32(0.9921), np.float32(0.9949), np.float32(0.8023)] +2025-10-31 09:20:53.477414: Epoch time: 21.17 s +2025-10-31 09:20:54.751479: +2025-10-31 09:20:54.753467: Epoch 980 +2025-10-31 09:20:54.755237: Current learning rate: 0.0003 +2025-10-31 09:21:17.538852: train_loss -0.995 +2025-10-31 09:21:17.543301: val_loss -0.8925 +2025-10-31 09:21:17.545080: Pseudo dice [np.float32(0.9856), np.float32(0.9921), np.float32(0.9948), np.float32(0.8062)] +2025-10-31 09:21:17.546761: Epoch time: 22.79 s +2025-10-31 09:21:18.763502: +2025-10-31 09:21:18.766881: Epoch 981 +2025-10-31 09:21:18.769120: Current learning rate: 0.00028 +2025-10-31 09:21:41.074859: train_loss -0.9949 +2025-10-31 09:21:41.079748: val_loss -0.8976 +2025-10-31 09:21:41.082318: Pseudo dice [np.float32(0.9863), np.float32(0.9918), np.float32(0.9949), np.float32(0.8128)] +2025-10-31 09:21:41.085069: Epoch time: 22.31 s +2025-10-31 09:21:42.286623: +2025-10-31 09:21:42.288635: Epoch 982 +2025-10-31 09:21:42.290363: Current learning rate: 0.00027 +2025-10-31 09:22:04.672523: train_loss -0.9952 +2025-10-31 09:22:04.675589: val_loss -0.8929 +2025-10-31 09:22:04.677511: Pseudo dice [np.float32(0.9865), np.float32(0.9921), np.float32(0.9946), np.float32(0.8011)] +2025-10-31 09:22:04.679778: Epoch time: 22.39 s +2025-10-31 09:22:05.684274: +2025-10-31 09:22:05.687575: Epoch 983 +2025-10-31 09:22:05.691141: Current learning rate: 0.00026 +2025-10-31 09:22:27.497267: train_loss -0.9953 +2025-10-31 09:22:27.502448: val_loss -0.8949 +2025-10-31 09:22:27.504974: Pseudo dice [np.float32(0.9854), np.float32(0.9916), np.float32(0.9948), np.float32(0.813)] +2025-10-31 09:22:27.507327: Epoch time: 21.81 s +2025-10-31 09:22:28.775212: +2025-10-31 09:22:28.778004: Epoch 984 +2025-10-31 09:22:28.780942: Current learning rate: 0.00024 +2025-10-31 09:22:49.703773: train_loss -0.9951 +2025-10-31 09:22:49.710815: val_loss -0.8896 +2025-10-31 09:22:49.713037: Pseudo dice [np.float32(0.9851), np.float32(0.9916), np.float32(0.9947), np.float32(0.8002)] +2025-10-31 09:22:49.715220: Epoch time: 20.93 s +2025-10-31 09:22:50.937174: +2025-10-31 09:22:50.939426: Epoch 985 +2025-10-31 09:22:50.941550: Current learning rate: 0.00023 +2025-10-31 09:23:13.194346: train_loss -0.995 +2025-10-31 09:23:13.199546: val_loss -0.8846 +2025-10-31 09:23:13.203475: Pseudo dice [np.float32(0.9859), np.float32(0.9913), np.float32(0.9942), np.float32(0.7899)] +2025-10-31 09:23:13.207391: Epoch time: 22.26 s +2025-10-31 09:23:14.485440: +2025-10-31 09:23:14.490561: Epoch 986 +2025-10-31 09:23:14.495889: Current learning rate: 0.00021 +2025-10-31 09:23:37.401665: train_loss -0.9952 +2025-10-31 09:23:37.405416: val_loss -0.9006 +2025-10-31 09:23:37.407579: Pseudo dice [np.float32(0.9869), np.float32(0.9927), np.float32(0.9952), np.float32(0.8209)] +2025-10-31 09:23:37.409565: Epoch time: 22.92 s +2025-10-31 09:23:38.675059: +2025-10-31 09:23:38.677554: Epoch 987 +2025-10-31 09:23:38.679660: Current learning rate: 0.0002 +2025-10-31 09:24:00.556830: train_loss -0.9952 +2025-10-31 09:24:00.559529: val_loss -0.8985 +2025-10-31 09:24:00.561055: Pseudo dice [np.float32(0.9857), np.float32(0.9916), np.float32(0.995), np.float32(0.8187)] +2025-10-31 09:24:00.563509: Epoch time: 21.88 s +2025-10-31 09:24:01.813781: +2025-10-31 09:24:01.815934: Epoch 988 +2025-10-31 09:24:01.817796: Current learning rate: 0.00019 +2025-10-31 09:24:24.046235: train_loss -0.9953 +2025-10-31 09:24:24.049285: val_loss -0.8921 +2025-10-31 09:24:24.051532: Pseudo dice [np.float32(0.9853), np.float32(0.9912), np.float32(0.9946), np.float32(0.8083)] +2025-10-31 09:24:24.053954: Epoch time: 22.23 s +2025-10-31 09:24:25.304284: +2025-10-31 09:24:25.306656: Epoch 989 +2025-10-31 09:24:25.308793: Current learning rate: 0.00017 +2025-10-31 09:24:47.932106: train_loss -0.9956 +2025-10-31 09:24:47.942248: val_loss -0.8861 +2025-10-31 09:24:47.945163: Pseudo dice [np.float32(0.9855), np.float32(0.9913), np.float32(0.9943), np.float32(0.7951)] +2025-10-31 09:24:47.947434: Epoch time: 22.63 s +2025-10-31 09:24:49.083984: +2025-10-31 09:24:49.086269: Epoch 990 +2025-10-31 09:24:49.087945: Current learning rate: 0.00016 +2025-10-31 09:25:11.247531: train_loss -0.9954 +2025-10-31 09:25:11.251019: val_loss -0.8913 +2025-10-31 09:25:11.253114: Pseudo dice [np.float32(0.9861), np.float32(0.9919), np.float32(0.9944), np.float32(0.8008)] +2025-10-31 09:25:11.255110: Epoch time: 22.17 s +2025-10-31 09:25:12.344311: +2025-10-31 09:25:12.346539: Epoch 991 +2025-10-31 09:25:12.348523: Current learning rate: 0.00014 +2025-10-31 09:25:31.517396: train_loss -0.9954 +2025-10-31 09:25:31.553168: val_loss -0.894 +2025-10-31 09:25:31.555774: Pseudo dice [np.float32(0.9849), np.float32(0.9912), np.float32(0.9949), np.float32(0.8145)] +2025-10-31 09:25:31.557889: Epoch time: 19.17 s +2025-10-31 09:25:32.701535: +2025-10-31 09:25:32.703781: Epoch 992 +2025-10-31 09:25:32.706350: Current learning rate: 0.00013 +2025-10-31 09:25:54.217856: train_loss -0.9954 +2025-10-31 09:25:54.222375: val_loss -0.8945 +2025-10-31 09:25:54.224182: Pseudo dice [np.float32(0.9857), np.float32(0.9919), np.float32(0.9947), np.float32(0.8122)] +2025-10-31 09:25:54.226937: Epoch time: 21.52 s +2025-10-31 09:25:55.388881: +2025-10-31 09:25:55.391181: Epoch 993 +2025-10-31 09:25:55.393312: Current learning rate: 0.00011 +2025-10-31 09:26:17.551980: train_loss -0.9949 +2025-10-31 09:26:17.555271: val_loss -0.8929 +2025-10-31 09:26:17.558047: Pseudo dice [np.float32(0.9857), np.float32(0.9912), np.float32(0.9948), np.float32(0.8088)] +2025-10-31 09:26:17.560105: Epoch time: 22.16 s +2025-10-31 09:26:18.838565: +2025-10-31 09:26:18.840923: Epoch 994 +2025-10-31 09:26:18.842984: Current learning rate: 0.0001 +2025-10-31 09:26:41.322177: train_loss -0.9954 +2025-10-31 09:26:41.326088: val_loss -0.8957 +2025-10-31 09:26:41.328183: Pseudo dice [np.float32(0.987), np.float32(0.9921), np.float32(0.9947), np.float32(0.8058)] +2025-10-31 09:26:41.330409: Epoch time: 22.49 s +2025-10-31 09:26:42.530237: +2025-10-31 09:26:42.533170: Epoch 995 +2025-10-31 09:26:42.535102: Current learning rate: 8e-05 +2025-10-31 09:27:05.228926: train_loss -0.9955 +2025-10-31 09:27:05.233206: val_loss -0.8916 +2025-10-31 09:27:05.234707: Pseudo dice [np.float32(0.9859), np.float32(0.9917), np.float32(0.9947), np.float32(0.8008)] +2025-10-31 09:27:05.236480: Epoch time: 22.7 s +2025-10-31 09:27:07.207469: +2025-10-31 09:27:07.210035: Epoch 996 +2025-10-31 09:27:07.212512: Current learning rate: 7e-05 +2025-10-31 09:27:28.721182: train_loss -0.9956 +2025-10-31 09:27:28.728368: val_loss -0.8986 +2025-10-31 09:27:28.730617: Pseudo dice [np.float32(0.9861), np.float32(0.9921), np.float32(0.9947), np.float32(0.8163)] +2025-10-31 09:27:28.733051: Epoch time: 21.52 s +2025-10-31 09:27:29.992411: +2025-10-31 09:27:29.995212: Epoch 997 +2025-10-31 09:27:29.997127: Current learning rate: 5e-05 +2025-10-31 09:27:50.135079: train_loss -0.9955 +2025-10-31 09:27:50.138822: val_loss -0.8895 +2025-10-31 09:27:50.141136: Pseudo dice [np.float32(0.985), np.float32(0.9909), np.float32(0.9943), np.float32(0.8047)] +2025-10-31 09:27:50.143713: Epoch time: 20.14 s +2025-10-31 09:27:51.267094: +2025-10-31 09:27:51.269514: Epoch 998 +2025-10-31 09:27:51.271809: Current learning rate: 4e-05 +2025-10-31 09:28:14.026097: train_loss -0.9953 +2025-10-31 09:28:14.029532: val_loss -0.8997 +2025-10-31 09:28:14.031817: Pseudo dice [np.float32(0.9858), np.float32(0.9919), np.float32(0.9951), np.float32(0.8208)] +2025-10-31 09:28:14.034135: Epoch time: 22.76 s +2025-10-31 09:28:15.081405: +2025-10-31 09:28:15.083718: Epoch 999 +2025-10-31 09:28:15.085871: Current learning rate: 2e-05 +2025-10-31 09:28:37.004279: train_loss -0.9955 +2025-10-31 09:28:37.013558: val_loss -0.892 +2025-10-31 09:28:37.016657: Pseudo dice [np.float32(0.9858), np.float32(0.9915), np.float32(0.9946), np.float32(0.808)] +2025-10-31 09:28:37.018920: Epoch time: 21.92 s +2025-10-31 09:28:39.861387: Training done. +2025-10-31 09:28:39.952822: Using splits from existing split file: /hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/splits_final.json +2025-10-31 09:28:39.956484: The split file contains 5 splits. +2025-10-31 09:28:39.958880: Desired fold for training: 3 +2025-10-31 09:28:39.963319: This split has 87 training and 21 validation cases. +2025-10-31 09:28:39.965336: predicting fish0003 +2025-10-31 09:28:39.970532: fish0003, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 09:28:51.436336: predicting fish0005 +2025-10-31 09:28:51.441300: fish0005, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 09:28:51.493970: predicting fish0007 +2025-10-31 09:28:51.498098: fish0007, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 09:28:51.544232: predicting fish0012 +2025-10-31 09:28:51.558763: fish0012, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 09:28:51.617116: predicting fish0015 +2025-10-31 09:28:51.620989: fish0015, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 09:28:51.701331: predicting fish0023 +2025-10-31 09:28:51.706437: fish0023, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 09:28:51.771862: predicting fish0031 +2025-10-31 09:28:51.775850: fish0031, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 09:28:51.845760: predicting fish0043 +2025-10-31 09:28:51.853792: fish0043, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 09:28:51.901869: predicting fish0053 +2025-10-31 09:28:51.907343: fish0053, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 09:28:51.971255: predicting fish0055 +2025-10-31 09:28:51.975460: fish0055, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 09:28:52.030215: predicting fish0056 +2025-10-31 09:28:52.035998: fish0056, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 09:28:52.086997: predicting fish0061 +2025-10-31 09:28:52.097027: fish0061, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 09:28:52.141652: predicting fish0064 +2025-10-31 09:28:52.148186: fish0064, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 09:28:52.218014: predicting fish0069 +2025-10-31 09:28:52.225595: fish0069, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 09:28:52.280499: predicting fish0072 +2025-10-31 09:28:52.285561: fish0072, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 09:28:52.333349: predicting fish0075 +2025-10-31 09:28:52.340053: fish0075, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 09:28:52.384109: predicting fish0096 +2025-10-31 09:28:52.388588: fish0096, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 09:28:52.439803: predicting fish0097 +2025-10-31 09:28:52.443991: fish0097, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 09:28:52.492475: predicting fish0099 +2025-10-31 09:28:52.526031: fish0099, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 09:28:52.576361: predicting fish0100 +2025-10-31 09:28:52.580470: fish0100, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 09:28:52.652957: predicting fish0103 +2025-10-31 09:28:52.657496: fish0103, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 09:29:00.500859: Validation complete +2025-10-31 09:29:00.502879: Mean Validation Dice: 0.9429614312790959 diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0003.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0003.png new file mode 100644 index 0000000000000000000000000000000000000000..fb988f5031fa37504d92881ba6ee267bdbcf1147 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0003.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0005.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0005.png new file mode 100644 index 0000000000000000000000000000000000000000..918b7ac57dd9a09caea372dd4b8a892b50191695 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0005.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0007.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0007.png new file mode 100644 index 0000000000000000000000000000000000000000..87a1887ddd19d37987565e3defd69398f2f57732 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0007.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0012.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0012.png new file mode 100644 index 0000000000000000000000000000000000000000..f3880d82b2dbbfa2e65cc32085ede90788f7f39c Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0012.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0015.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0015.png new file mode 100644 index 0000000000000000000000000000000000000000..009aad918054549d7ae91949aee709bb86e08307 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0015.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0023.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0023.png new file mode 100644 index 0000000000000000000000000000000000000000..c1c16989d9c53b265943e6ae323709a516477756 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0023.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0031.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0031.png new file mode 100644 index 0000000000000000000000000000000000000000..f4760e94e63cc48e7f97eb90a632d46bdaa04e57 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0031.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0043.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0043.png new file mode 100644 index 0000000000000000000000000000000000000000..da3cdc6ee55d53f92ed4af948be1ae6970f13e25 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0043.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0053.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0053.png new file mode 100644 index 0000000000000000000000000000000000000000..2a917400fe9a7867080e3169f97fdd2d4b908643 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0053.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0055.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0055.png new file mode 100644 index 0000000000000000000000000000000000000000..bedb4a28e299205ff4646845cc9316f1979f2eec Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0055.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0056.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0056.png new file mode 100644 index 0000000000000000000000000000000000000000..b639798aa2c06f6a5bf966118aaa359535e94ab8 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0056.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0061.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0061.png new file mode 100644 index 0000000000000000000000000000000000000000..3ca93eda487f90b2698b899bf608931fc1c697f5 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0061.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0064.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0064.png new file mode 100644 index 0000000000000000000000000000000000000000..f1c159a2e07d849977d1a1cb994513a90de165a0 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0064.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0069.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0069.png new file mode 100644 index 0000000000000000000000000000000000000000..279822da2f49b80b62652df8b609777165693567 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0069.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0072.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0072.png new file mode 100644 index 0000000000000000000000000000000000000000..7f2b71edf7b07a20e68a6640e653348670e352f4 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0072.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0075.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0075.png new file mode 100644 index 0000000000000000000000000000000000000000..af9f0ddb74a9a0f8553c0b0c04448b9168751dec Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0075.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0096.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0096.png new file mode 100644 index 0000000000000000000000000000000000000000..2cd0ab2b9159695ed80a01bf24636f140becbafe Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0096.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0097.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0097.png new file mode 100644 index 0000000000000000000000000000000000000000..56aa562fe12526a9b08f7945cf7c63cbcfceab14 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0097.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0099.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0099.png new file mode 100644 index 0000000000000000000000000000000000000000..bec3f9b411792621d1ab9c79709cb4c4efa4a414 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0099.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0100.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0100.png new file mode 100644 index 0000000000000000000000000000000000000000..f6fe003b8945517a2e94650bbf6d2a74896947e0 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0100.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0103.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0103.png new file mode 100644 index 0000000000000000000000000000000000000000..5ec5e124a72b36b2f1873b2ef8009005c7f95bdc Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0103.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/summary.json b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/summary.json new file mode 100644 index 0000000000000000000000000000000000000000..72554d93c5cc16473c69073a31cc4e8626d560d9 --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/summary.json @@ -0,0 +1,1022 @@ +{ + "foreground_mean": { + "Dice": 0.9429614312790959, + "FN": 123.67857142857143, + "FP": 135.17857142857144, + "IoU": 0.9073426975915769, + "TN": 91925.89285714286, + "TP": 12263.25, + "n_pred": 12398.428571428572, + "n_ref": 12386.92857142857 + }, + "mean": { + "1": { + "Dice": 0.9856181627480768, + "FN": 80.0952380952381, + "FP": 99.66666666666667, + "IoU": 0.9717863352733715, + "TN": 98116.61904761905, + "TP": 6151.619047619048, + "n_pred": 6251.285714285715, + "n_ref": 6231.714285714285 + }, + "2": { + "Dice": 0.9915738144073025, + "FN": 103.23809523809524, + "FP": 96.28571428571429, + "IoU": 0.9833671069783715, + "TN": 92427.42857142857, + "TP": 11821.047619047618, + "n_pred": 11917.333333333334, + "n_ref": 11924.285714285714 + }, + "3": { + "Dice": 0.9944510609492512, + "FN": 140.66666666666666, + "FP": 194.52380952380952, + "IoU": 0.9889973390546898, + "TN": 73692.33333333333, + "TP": 30420.47619047619, + "n_pred": 30615.0, + "n_ref": 30561.14285714286 + }, + "4": { + "Dice": 0.8002026870117531, + "FN": 170.71428571428572, + "FP": 150.23809523809524, + "IoU": 0.6852200090598753, + "TN": 103467.19047619047, + "TP": 659.8571428571429, + "n_pred": 810.0952380952381, + "n_ref": 830.5714285714286 + } + }, + "metric_per_case": [ + { + "metrics": { + "1": { + "Dice": 0.9935404490925869, + "FN": 68, + "FP": 16, + "IoU": 0.9871638141809291, + "TN": 97904, + "TP": 6460, + "n_pred": 6476, + "n_ref": 6528 + }, + "2": { + "Dice": 0.9964319118716874, + "FN": 0, + "FP": 103, + "IoU": 0.99288919571971, + "TN": 89963, + "TP": 14382, + "n_pred": 14485, + "n_ref": 14382 + }, + "3": { + "Dice": 0.9971123100111282, + "FN": 103, + "FP": 102, + "IoU": 0.9942412495083993, + "TN": 68850, + "TP": 35393, + "n_pred": 35495, + "n_ref": 35496 + }, + "4": { + "Dice": 0.9411764705882353, + "FN": 102, + "FP": 0, + "IoU": 0.8888888888888888, + "TN": 103530, + "TP": 816, + "n_pred": 816, + "n_ref": 918 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0003.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0003.png" + }, + { + "metrics": { + "1": { + "Dice": 0.991869918699187, + "FN": 0, + "FP": 102, + "IoU": 0.9838709677419355, + "TN": 98124, + "TP": 6222, + "n_pred": 6324, + "n_ref": 6222 + }, + "2": { + "Dice": 0.9963636363636363, + "FN": 0, + "FP": 102, + "IoU": 0.9927536231884058, + "TN": 90372, + "TP": 13974, + "n_pred": 14076, + "n_ref": 13974 + }, + "3": { + "Dice": 0.9953456595072377, + "FN": 327, + "FP": 0, + "IoU": 0.990734444066644, + "TN": 69156, + "TP": 34965, + "n_pred": 34965, + "n_ref": 35292 + }, + "4": { + "Dice": 0.9006622516556292, + "FN": 0, + "FP": 225, + "IoU": 0.8192771084337349, + "TN": 103203, + "TP": 1020, + "n_pred": 1245, + "n_ref": 1020 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0005.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0005.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9751276026897837, + "FN": 0, + "FP": 307, + "IoU": 0.9514624505928854, + "TN": 98123, + "TP": 6018, + "n_pred": 6325, + "n_ref": 6018 + }, + "2": { + "Dice": 0.9954206135123267, + "FN": 146, + "FP": 0, + "IoU": 0.9908829773947796, + "TN": 88434, + "TP": 15868, + "n_pred": 15868, + "n_ref": 16014 + }, + "3": { + "Dice": 0.9916801699369545, + "FN": 0, + "FP": 611, + "IoU": 0.9834976367319379, + "TN": 67423, + "TP": 36414, + "n_pred": 37025, + "n_ref": 36414 + }, + "4": { + "Dice": 0.6995325116872079, + "FN": 707, + "FP": 0, + "IoU": 0.5379084967320261, + "TN": 102918, + "TP": 823, + "n_pred": 823, + "n_ref": 1530 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0007.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0007.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9891145410235581, + "FN": 134, + "FP": 0, + "IoU": 0.9784635165541626, + "TN": 98226, + "TP": 6088, + "n_pred": 6088, + "n_ref": 6222 + }, + "2": { + "Dice": 0.9907547046095339, + "FN": 95, + "FP": 46, + "IoU": 0.9816787941787942, + "TN": 96752, + "TP": 7555, + "n_pred": 7601, + "n_ref": 7650 + }, + "3": { + "Dice": 0.9938016957233774, + "FN": 204, + "FP": 95, + "IoU": 0.9876797560674111, + "TN": 80179, + "TP": 23970, + "n_pred": 24065, + "n_ref": 24174 + }, + "4": { + "Dice": 0.8333333333333334, + "FN": 0, + "FP": 204, + "IoU": 0.7142857142857143, + "TN": 103734, + "TP": 510, + "n_pred": 714, + "n_ref": 510 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0012.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0012.png" + }, + { + "metrics": { + "1": { + "Dice": 0.997924696116217, + "FN": 0, + "FP": 28, + "IoU": 0.9958579881656805, + "TN": 97688, + "TP": 6732, + "n_pred": 6760, + "n_ref": 6732 + }, + "2": { + "Dice": 0.9964073790013321, + "FN": 0, + "FP": 89, + "IoU": 0.992840479446545, + "TN": 92017, + "TP": 12342, + "n_pred": 12431, + "n_ref": 12342 + }, + "3": { + "Dice": 0.9979402839577994, + "FN": 89, + "FP": 42, + "IoU": 0.9958890353354672, + "TN": 72582, + "TP": 31735, + "n_pred": 31777, + "n_ref": 31824 + }, + "4": { + "Dice": 0.9664344521849272, + "FN": 53, + "FP": 0, + "IoU": 0.9350490196078431, + "TN": 103632, + "TP": 763, + "n_pred": 763, + "n_ref": 816 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0015.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0015.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9911733743622966, + "FN": 102, + "FP": 7, + "IoU": 0.9825012040455932, + "TN": 98219, + "TP": 6120, + "n_pred": 6127, + "n_ref": 6222 + }, + "2": { + "Dice": 0.9874476987447699, + "FN": 204, + "FP": 102, + "IoU": 0.9752066115702479, + "TN": 92106, + "TP": 12036, + "n_pred": 12138, + "n_ref": 12240 + }, + "3": { + "Dice": 0.9965277777777778, + "FN": 0, + "FP": 204, + "IoU": 0.9930795847750865, + "TN": 74970, + "TP": 29274, + "n_pred": 29478, + "n_ref": 29274 + }, + "4": { + "Dice": 1.0, + "FN": 0, + "FP": 0, + "IoU": 1.0, + "TN": 103836, + "TP": 612, + "n_pred": 612, + "n_ref": 612 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0023.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0023.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9840965395988173, + "FN": 65, + "FP": 134, + "IoU": 0.9686910006293267, + "TN": 98092, + "TP": 6157, + "n_pred": 6291, + "n_ref": 6222 + }, + "2": { + "Dice": 0.9874720792463825, + "FN": 134, + "FP": 124, + "IoU": 0.9752541722616536, + "TN": 94022, + "TP": 10168, + "n_pred": 10292, + "n_ref": 10302 + }, + "3": { + "Dice": 0.9906501255138793, + "FN": 514, + "FP": 0, + "IoU": 0.9814734717416378, + "TN": 76704, + "TP": 27230, + "n_pred": 27230, + "n_ref": 27744 + }, + "4": { + "Dice": 0.6336633663366337, + "FN": 202, + "FP": 390, + "IoU": 0.463768115942029, + "TN": 103344, + "TP": 512, + "n_pred": 902, + "n_ref": 714 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0031.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0031.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9905316824471959, + "FN": 0, + "FP": 117, + "IoU": 0.9812409812409812, + "TN": 98211, + "TP": 6120, + "n_pred": 6237, + "n_ref": 6120 + }, + "2": { + "Dice": 0.992847135167023, + "FN": 102, + "FP": 92, + "IoU": 0.9857958705520574, + "TN": 90790, + "TP": 13464, + "n_pred": 13556, + "n_ref": 13566 + }, + "3": { + "Dice": 0.9986752750547321, + "FN": 95, + "FP": 0, + "IoU": 0.997354055258467, + "TN": 68544, + "TP": 35809, + "n_pred": 35809, + "n_ref": 35904 + }, + "4": { + "Dice": 0.9395509499136442, + "FN": 0, + "FP": 105, + "IoU": 0.8859934853420195, + "TN": 103527, + "TP": 816, + "n_pred": 921, + "n_ref": 816 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0043.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0043.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9901867129830656, + "FN": 11, + "FP": 102, + "IoU": 0.9805641554867561, + "TN": 98634, + "TP": 5701, + "n_pred": 5803, + "n_ref": 5712 + }, + "2": { + "Dice": 0.9989621771217713, + "FN": 7, + "FP": 11, + "IoU": 0.9979265061628845, + "TN": 95767, + "TP": 8663, + "n_pred": 8674, + "n_ref": 8670 + }, + "3": { + "Dice": 0.9936476366366975, + "FN": 0, + "FP": 313, + "IoU": 0.9873754688823458, + "TN": 79655, + "TP": 24480, + "n_pred": 24793, + "n_ref": 24480 + }, + "4": { + "Dice": 0.7142857142857143, + "FN": 306, + "FP": 102, + "IoU": 0.5555555555555556, + "TN": 103530, + "TP": 510, + "n_pred": 612, + "n_ref": 816 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0053.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0053.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9815557337610264, + "FN": 0, + "FP": 230, + "IoU": 0.9637795275590552, + "TN": 98098, + "TP": 6120, + "n_pred": 6350, + "n_ref": 6120 + }, + "2": { + "Dice": 0.9934683520511254, + "FN": 139, + "FP": 0, + "IoU": 0.9870214752567694, + "TN": 93738, + "TP": 10571, + "n_pred": 10571, + "n_ref": 10710 + }, + "3": { + "Dice": 0.9952063063702862, + "FN": 227, + "FP": 43, + "IoU": 0.9904583524755275, + "TN": 76151, + "TP": 28027, + "n_pred": 28070, + "n_ref": 28254 + }, + "4": { + "Dice": 0.8166533226581265, + "FN": 0, + "FP": 229, + "IoU": 0.6901217861975643, + "TN": 103709, + "TP": 510, + "n_pred": 739, + "n_ref": 510 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0055.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0055.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9967213114754099, + "FN": 42, + "FP": 0, + "IoU": 0.9934640522875817, + "TN": 98022, + "TP": 6384, + "n_pred": 6384, + "n_ref": 6426 + }, + "2": { + "Dice": 0.9973879847297569, + "FN": 0, + "FP": 78, + "IoU": 0.9947895791583167, + "TN": 89478, + "TP": 14892, + "n_pred": 14970, + "n_ref": 14892 + }, + "3": { + "Dice": 0.9974653599188915, + "FN": 78, + "FP": 102, + "IoU": 0.9949435361537164, + "TN": 68850, + "TP": 35418, + "n_pred": 35520, + "n_ref": 35496 + }, + "4": { + "Dice": 0.875, + "FN": 204, + "FP": 0, + "IoU": 0.7777777777777778, + "TN": 103530, + "TP": 714, + "n_pred": 714, + "n_ref": 918 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0056.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0056.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9715056750535757, + "FN": 102, + "FP": 257, + "IoU": 0.9445902145392807, + "TN": 97969, + "TP": 6120, + "n_pred": 6377, + "n_ref": 6222 + }, + "2": { + "Dice": 0.9928730512249443, + "FN": 90, + "FP": 102, + "IoU": 0.9858469703670942, + "TN": 90882, + "TP": 13374, + "n_pred": 13476, + "n_ref": 13464 + }, + "3": { + "Dice": 0.9970856102003643, + "FN": 0, + "FP": 192, + "IoU": 0.9941881583726844, + "TN": 71412, + "TP": 32844, + "n_pred": 33036, + "n_ref": 32844 + }, + "4": { + "Dice": 0.9286652078774617, + "FN": 163, + "FP": 0, + "IoU": 0.8668300653594772, + "TN": 103224, + "TP": 1061, + "n_pred": 1061, + "n_ref": 1224 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0061.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0061.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9831756046267087, + "FN": 0, + "FP": 192, + "IoU": 0.9669079627714581, + "TN": 98646, + "TP": 5610, + "n_pred": 5802, + "n_ref": 5610 + }, + "2": { + "Dice": 0.990963698093497, + "FN": 102, + "FP": 71, + "IoU": 0.9820892431928772, + "TN": 94789, + "TP": 9486, + "n_pred": 9557, + "n_ref": 9588 + }, + "3": { + "Dice": 0.9967402159371408, + "FN": 173, + "FP": 0, + "IoU": 0.9935016152054692, + "TN": 77826, + "TP": 26449, + "n_pred": 26449, + "n_ref": 26622 + }, + "4": { + "Dice": 0.8369230769230769, + "FN": 0, + "FP": 159, + "IoU": 0.7195767195767195, + "TN": 103881, + "TP": 408, + "n_pred": 567, + "n_ref": 408 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0064.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0064.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9858889934148636, + "FN": 138, + "FP": 42, + "IoU": 0.9721706864564007, + "TN": 97980, + "TP": 6288, + "n_pred": 6330, + "n_ref": 6426 + }, + "2": { + "Dice": 0.9929169349645847, + "FN": 165, + "FP": 0, + "IoU": 0.9859335038363172, + "TN": 92718, + "TP": 11565, + "n_pred": 11565, + "n_ref": 11730 + }, + "3": { + "Dice": 0.9896141950187205, + "FN": 0, + "FP": 638, + "IoU": 0.9794419024295934, + "TN": 73414, + "TP": 30396, + "n_pred": 31034, + "n_ref": 30396 + }, + "4": { + "Dice": 0.7794176306342242, + "FN": 553, + "FP": 0, + "IoU": 0.6385620915032679, + "TN": 102918, + "TP": 977, + "n_pred": 977, + "n_ref": 1530 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0069.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0069.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9879759519038076, + "FN": 0, + "FP": 144, + "IoU": 0.9762376237623762, + "TN": 98388, + "TP": 5916, + "n_pred": 6060, + "n_ref": 5916 + }, + "2": { + "Dice": 0.9893183342793745, + "FN": 104, + "FP": 103, + "IoU": 0.9788624527723885, + "TN": 94655, + "TP": 9586, + "n_pred": 9689, + "n_ref": 9690 + }, + "3": { + "Dice": 0.9970131962420579, + "FN": 103, + "FP": 62, + "IoU": 0.9940441813456541, + "TN": 76744, + "TP": 27539, + "n_pred": 27601, + "n_ref": 27642 + }, + "4": { + "Dice": 0.5955249569707401, + "FN": 62, + "FP": 408, + "IoU": 0.42401960784313725, + "TN": 103632, + "TP": 346, + "n_pred": 754, + "n_ref": 408 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0072.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0072.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9866193777204578, + "FN": 0, + "FP": 166, + "IoU": 0.9735921094495704, + "TN": 98162, + "TP": 6120, + "n_pred": 6286, + "n_ref": 6120 + }, + "2": { + "Dice": 0.9916920811862446, + "FN": 158, + "FP": 0, + "IoU": 0.9835210680016687, + "TN": 94860, + "TP": 9430, + "n_pred": 9430, + "n_ref": 9588 + }, + "3": { + "Dice": 0.995545529279064, + "FN": 177, + "FP": 56, + "IoU": 0.9911305671869052, + "TN": 78178, + "TP": 26037, + "n_pred": 26093, + "n_ref": 26214 + }, + "4": { + "Dice": 0.6725274725274726, + "FN": 0, + "FP": 298, + "IoU": 0.5066225165562914, + "TN": 103844, + "TP": 306, + "n_pred": 604, + "n_ref": 306 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0075.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0075.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9937550040032026, + "FN": 16, + "FP": 62, + "IoU": 0.9875875238701464, + "TN": 98164, + "TP": 6206, + "n_pred": 6268, + "n_ref": 6222 + }, + "2": { + "Dice": 0.9994236311239193, + "FN": 0, + "FP": 16, + "IoU": 0.9988479262672811, + "TN": 90560, + "TP": 13872, + "n_pred": 13888, + "n_ref": 13872 + }, + "3": { + "Dice": 0.9954661462242906, + "FN": 302, + "FP": 0, + "IoU": 0.990973218555715, + "TN": 70992, + "TP": 33154, + "n_pred": 33154, + "n_ref": 33456 + }, + "4": { + "Dice": 0.814139110604333, + "FN": 0, + "FP": 326, + "IoU": 0.6865384615384615, + "TN": 103408, + "TP": 714, + "n_pred": 1040, + "n_ref": 714 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0096.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0096.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9694262610704659, + "FN": 336, + "FP": 61, + "IoU": 0.9406665670303392, + "TN": 97757, + "TP": 6294, + "n_pred": 6355, + "n_ref": 6630 + }, + "2": { + "Dice": 0.9810241746815701, + "FN": 102, + "FP": 336, + "IoU": 0.9627551020408164, + "TN": 92688, + "TP": 11322, + "n_pred": 11658, + "n_ref": 11424 + }, + "3": { + "Dice": 0.9963498020667317, + "FN": 0, + "FP": 213, + "IoU": 0.9927261551070587, + "TN": 75165, + "TP": 29070, + "n_pred": 29283, + "n_ref": 29070 + }, + "4": { + "Dice": 0.8951255539143279, + "FN": 213, + "FP": 0, + "IoU": 0.8101604278074866, + "TN": 103326, + "TP": 909, + "n_pred": 909, + "n_ref": 1122 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0097.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0097.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9902912621359223, + "FN": 0, + "FP": 126, + "IoU": 0.9807692307692307, + "TN": 97896, + "TP": 6426, + "n_pred": 6552, + "n_ref": 6426 + }, + "2": { + "Dice": 0.9856598805773661, + "FN": 126, + "FP": 179, + "IoU": 0.9717252248076388, + "TN": 93661, + "TP": 10482, + "n_pred": 10661, + "n_ref": 10608 + }, + "3": { + "Dice": 0.9809730292255658, + "FN": 179, + "FP": 918, + "IoU": 0.9626565904139434, + "TN": 75072, + "TP": 28279, + "n_pred": 29197, + "n_ref": 28458 + }, + "4": { + "Dice": 0.5643153526970954, + "FN": 918, + "FP": 27, + "IoU": 0.3930635838150289, + "TN": 102891, + "TP": 612, + "n_pred": 639, + "n_ref": 1530 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0099.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0099.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9818754925137904, + "FN": 207, + "FP": 0, + "IoU": 0.9643962848297214, + "TN": 98634, + "TP": 5607, + "n_pred": 5607, + "n_ref": 5814 + }, + "2": { + "Dice": 0.9949845856531542, + "FN": 0, + "FP": 109, + "IoU": 0.9900192290083326, + "TN": 93527, + "TP": 10812, + "n_pred": 10921, + "n_ref": 10812 + }, + "3": { + "Dice": 0.9987012329853088, + "FN": 77, + "FP": 0, + "IoU": 0.9974058351863082, + "TN": 74766, + "TP": 29605, + "n_pred": 29605, + "n_ref": 29682 + }, + "4": { + "Dice": 0.7306590257879656, + "FN": 0, + "FP": 376, + "IoU": 0.5756207674943566, + "TN": 103562, + "TP": 510, + "n_pred": 886, + "n_ref": 510 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0100.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0100.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9656252330176721, + "FN": 461, + "FP": 0, + "IoU": 0.9335351787773933, + "TN": 97512, + "TP": 6475, + "n_pred": 6475, + "n_ref": 6936 + }, + "2": { + "Dice": 0.9712300583493542, + "FN": 494, + "FP": 359, + "IoU": 0.9440692413612222, + "TN": 89197, + "TP": 14398, + "n_pred": 14757, + "n_ref": 14892 + }, + "3": { + "Dice": 0.9879307223462676, + "FN": 306, + "FP": 494, + "IoU": 0.9761493053485183, + "TN": 70906, + "TP": 32742, + "n_pred": 33236, + "n_ref": 33048 + }, + "4": { + "Dice": 0.6666666666666666, + "FN": 102, + "FP": 306, + "IoU": 0.5, + "TN": 103632, + "TP": 408, + "n_pred": 714, + "n_ref": 510 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_3/validation/fish0103.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0103.png" + } + ] +} \ No newline at end of file diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/.DS_Store b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/.DS_Store new file mode 100644 index 0000000000000000000000000000000000000000..221d5b6a94fc3c3050b732fbbfea7e6e3e19c6cd Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/.DS_Store differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/checkpoint_best.pth b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/checkpoint_best.pth new file mode 100644 index 0000000000000000000000000000000000000000..6b7d0bf8cc89983bfb76f5f814860c92508c05e6 --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/checkpoint_best.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3129b6ea2548af66fe8dd9ddbeaf1bfd041ca0805154e4c51897cb16c6f80db +size 358292354 diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/checkpoint_final.pth b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/checkpoint_final.pth new file mode 100644 index 0000000000000000000000000000000000000000..4a75ada33787b9a10c7ae7deab08845cf4462b71 --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/checkpoint_final.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d4fc570e8f27edec502dbc77f5ffab204f7f81e3536e6fc5570bdc02e71eade +size 358731758 diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/debug.json b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/debug.json new file mode 100644 index 0000000000000000000000000000000000000000..483071139cc75bc67a4f5c17b5a670f93030620e --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/debug.json @@ -0,0 +1,53 @@ +{ + "_best_ema": "None", + "batch_size": "5", + "configuration_manager": "{'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 5, 'patch_size': [1024, 112], 'median_image_size_in_voxels': [1024.0, 102.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['ZScoreNormalization'], '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': 8, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 1], [2, 1], [2, 1]], 'n_conv_per_stage': [2, 2, 2, 2, 2, 2, 2, 2], 'n_conv_per_stage_decoder': [2, 2, 2, 2, 2, 2, 2], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}", + "configuration_name": "2d", + "cudnn_version": 90100, + "current_epoch": "0", + "dataloader_train": "", + "dataloader_train.generator": "", + "dataloader_train.num_processes": "12", + "dataloader_train.transform": "None", + "dataloader_val": "", + "dataloader_val.generator": "", + "dataloader_val.num_processes": "6", + "dataloader_val.transform": "None", + "dataset_json": "{'channel_names': {'0': '\u00b5OCT'}, 'labels': {'background': 0, 'Retina': 1, 'VCD': 2, 'lens': 3, 'cornea': 4}, 'numTraining': 108, 'file_ending': '.png'}", + "device": "cuda:0", + "disable_checkpointing": "False", + "enable_deep_supervision": "True", + "fold": "4", + "folder_with_segs_from_previous_stage": "None", + "gpu_name": "NVIDIA A100 80GB PCIe", + "grad_scaler": "", + "hostname": "hpc5", + "inference_allowed_mirroring_axes": "(0, 1)", + "initial_lr": "0.01", + "is_cascaded": "False", + "is_ddp": "False", + "label_manager": "", + "local_rank": "0", + "log_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/training_log_2025_10_31_09_29_10.txt", + "logger": "", + "loss": "DeepSupervisionWrapper(\n (loss): DC_and_CE_loss(\n (ce): RobustCrossEntropyLoss()\n (dc): OptimizedModule(\n (_orig_mod): MemoryEfficientSoftDiceLoss()\n )\n )\n)", + "lr_scheduler": "", + "my_init_kwargs": "{'plans': {'dataset_name': 'Dataset001_zebrafish', 'plans_name': 'nnUNetPlans', 'original_median_spacing_after_transp': [999.0, 1.0, 1.0], 'original_median_shape_after_transp': [1, 1024, 102], 'image_reader_writer': 'NaturalImage2DIO', 'transpose_forward': [0, 1, 2], 'transpose_backward': [0, 1, 2], 'configurations': {'2d': {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 5, 'patch_size': [1024, 112], 'median_image_size_in_voxels': [1024.0, 102.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['ZScoreNormalization'], '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': 8, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 1], [2, 1], [2, 1]], 'n_conv_per_stage': [2, 2, 2, 2, 2, 2, 2, 2], 'n_conv_per_stage_decoder': [2, 2, 2, 2, 2, 2, 2], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}}, 'experiment_planner_used': 'ExperimentPlanner', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 255.0, 'mean': 49.659568786621094, 'median': 45.0, 'min': 0.0, 'percentile_00_5': 10.0, 'percentile_99_5': 163.0, 'std': 24.689043045043945}}}, 'configuration': '2d', 'fold': 4, 'dataset_json': {'channel_names': {'0': '\u00b5OCT'}, 'labels': {'background': 0, 'Retina': 1, 'VCD': 2, 'lens': 3, 'cornea': 4}, 'numTraining': 108, 'file_ending': '.png'}, 'device': device(type='cuda')}", + "network": "OptimizedModule", + "num_epochs": "1000", + "num_input_channels": "1", + "num_iterations_per_epoch": "250", + "num_val_iterations_per_epoch": "50", + "optimizer": "SGD (\nParameter Group 0\n dampening: 0\n differentiable: False\n foreach: None\n fused: None\n initial_lr: 0.01\n lr: 0.01\n maximize: False\n momentum: 0.99\n nesterov: True\n weight_decay: 3e-05\n)", + "output_folder": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4", + "output_folder_base": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d", + "oversample_foreground_percent": "0.33", + "plans_manager": "{'dataset_name': 'Dataset001_zebrafish', 'plans_name': 'nnUNetPlans', 'original_median_spacing_after_transp': [999.0, 1.0, 1.0], 'original_median_shape_after_transp': [1, 1024, 102], 'image_reader_writer': 'NaturalImage2DIO', 'transpose_forward': [0, 1, 2], 'transpose_backward': [0, 1, 2], 'configurations': {'2d': {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 5, 'patch_size': [1024, 112], 'median_image_size_in_voxels': [1024.0, 102.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['ZScoreNormalization'], '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': 8, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 1], [2, 1], [2, 1]], 'n_conv_per_stage': [2, 2, 2, 2, 2, 2, 2, 2], 'n_conv_per_stage_decoder': [2, 2, 2, 2, 2, 2, 2], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}}, 'experiment_planner_used': 'ExperimentPlanner', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 255.0, 'mean': 49.659568786621094, 'median': 45.0, 'min': 0.0, 'percentile_00_5': 10.0, 'percentile_99_5': 163.0, 'std': 24.689043045043945}}}", + "preprocessed_dataset_folder": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/nnUNetPlans_2d", + "preprocessed_dataset_folder_base": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish", + "probabilistic_oversampling": "False", + "save_every": "50", + "torch_version": "2.5.1+cu121", + "was_initialized": "True", + "weight_decay": "3e-05" +} \ No newline at end of file diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/progress.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/progress.png new file mode 100644 index 0000000000000000000000000000000000000000..ef642cd355c2821dbc0c0da60ce9e94140e66d47 --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/progress.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9459fc714f052b191864fe13533da3e17ba775bb7adf59b967b0de1b57fd1e7 +size 975486 diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/training_log_2025_10_30_12_32_44.txt b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/training_log_2025_10_30_12_32_44.txt new file mode 100644 index 0000000000000000000000000000000000000000..89e9f9560fca955a960f0159950385239c11ebd7 --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/training_log_2025_10_30_12_32_44.txt @@ -0,0 +1,24 @@ + +####################################################################### +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. +####################################################################### + +2025-10-30 12:32:47.041057: Using torch.compile... +2025-10-30 12:32:48.253016: do_dummy_2d_data_aug: False +2025-10-30 12:32:48.255485: Using splits from existing split file: /hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/splits_final.json +2025-10-30 12:32:48.257316: The split file contains 5 splits. +2025-10-30 12:32:48.259122: Desired fold for training: 4 +2025-10-30 12:32:48.260680: This split has 87 training and 21 validation cases. + +This is the configuration used by this training: +Configuration name: 2d + {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 5, 'patch_size': [1024, 112], 'median_image_size_in_voxels': [1024.0, 102.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['ZScoreNormalization'], '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': 8, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 1], [2, 1], [2, 1]], 'n_conv_per_stage': [2, 2, 2, 2, 2, 2, 2, 2], 'n_conv_per_stage_decoder': [2, 2, 2, 2, 2, 2, 2], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True} + +These are the global plan.json settings: + {'dataset_name': 'Dataset001_zebrafish', 'plans_name': 'nnUNetPlans', 'original_median_spacing_after_transp': [999.0, 1.0, 1.0], 'original_median_shape_after_transp': [1, 1024, 102], 'image_reader_writer': 'NaturalImage2DIO', 'transpose_forward': [0, 1, 2], 'transpose_backward': [0, 1, 2], 'experiment_planner_used': 'ExperimentPlanner', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 255.0, 'mean': 49.659568786621094, 'median': 45.0, 'min': 0.0, 'percentile_00_5': 10.0, 'percentile_99_5': 163.0, 'std': 24.689043045043945}}} + +2025-10-30 12:32:49.614168: Unable to plot network architecture: nnUNet_compile is enabled! +2025-10-30 12:32:49.631878: +2025-10-30 12:32:49.633821: Epoch 0 +2025-10-30 12:32:49.635923: Current learning rate: 0.01 diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/training_log_2025_10_31_09_29_10.txt b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/training_log_2025_10_31_09_29_10.txt new file mode 100644 index 0000000000000000000000000000000000000000..733d57c628eb12b5acd36ffc6096e59cfd8ddd2a --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/training_log_2025_10_31_09_29_10.txt @@ -0,0 +1,7115 @@ + +####################################################################### +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. +####################################################################### + +2025-10-31 09:29:12.011289: Using torch.compile... +2025-10-31 09:29:13.234161: do_dummy_2d_data_aug: False +2025-10-31 09:29:13.236522: Using splits from existing split file: /hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/splits_final.json +2025-10-31 09:29:13.238392: The split file contains 5 splits. +2025-10-31 09:29:13.240829: Desired fold for training: 4 +2025-10-31 09:29:13.243241: This split has 87 training and 21 validation cases. + +This is the configuration used by this training: +Configuration name: 2d + {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 5, 'patch_size': [1024, 112], 'median_image_size_in_voxels': [1024.0, 102.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['ZScoreNormalization'], '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': 8, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 1], [2, 1], [2, 1]], 'n_conv_per_stage': [2, 2, 2, 2, 2, 2, 2, 2], 'n_conv_per_stage_decoder': [2, 2, 2, 2, 2, 2, 2], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True} + +These are the global plan.json settings: + {'dataset_name': 'Dataset001_zebrafish', 'plans_name': 'nnUNetPlans', 'original_median_spacing_after_transp': [999.0, 1.0, 1.0], 'original_median_shape_after_transp': [1, 1024, 102], 'image_reader_writer': 'NaturalImage2DIO', 'transpose_forward': [0, 1, 2], 'transpose_backward': [0, 1, 2], 'experiment_planner_used': 'ExperimentPlanner', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 255.0, 'mean': 49.659568786621094, 'median': 45.0, 'min': 0.0, 'percentile_00_5': 10.0, 'percentile_99_5': 163.0, 'std': 24.689043045043945}}} + +2025-10-31 09:29:14.912736: Unable to plot network architecture: nnUNet_compile is enabled! +2025-10-31 09:29:14.933710: +2025-10-31 09:29:14.935537: Epoch 0 +2025-10-31 09:29:14.937768: Current learning rate: 0.01 +2025-10-31 09:30:14.764522: train_loss -0.1438 +2025-10-31 09:30:14.767272: val_loss -0.8219 +2025-10-31 09:30:14.769792: Pseudo dice [np.float32(0.9587), np.float32(0.9686), np.float32(0.9785), np.float32(0.6913)] +2025-10-31 09:30:14.771369: Epoch time: 59.83 s +2025-10-31 09:30:14.772780: Yayy! New best EMA pseudo Dice: 0.8992999792098999 +2025-10-31 09:30:17.103392: +2025-10-31 09:30:17.105758: Epoch 1 +2025-10-31 09:30:17.107645: Current learning rate: 0.00999 +2025-10-31 09:30:38.914338: train_loss -0.8372 +2025-10-31 09:30:38.917669: val_loss -0.883 +2025-10-31 09:30:38.919743: Pseudo dice [np.float32(0.9694), np.float32(0.9793), np.float32(0.9895), np.float32(0.7974)] +2025-10-31 09:30:38.921754: Epoch time: 21.81 s +2025-10-31 09:30:38.924060: Yayy! New best EMA pseudo Dice: 0.9027000069618225 +2025-10-31 09:30:41.520846: +2025-10-31 09:30:41.524437: Epoch 2 +2025-10-31 09:30:41.526811: Current learning rate: 0.00998 +2025-10-31 09:31:03.196059: train_loss -0.864 +2025-10-31 09:31:03.198716: val_loss -0.896 +2025-10-31 09:31:03.200814: Pseudo dice [np.float32(0.9772), np.float32(0.9763), np.float32(0.9905), np.float32(0.8269)] +2025-10-31 09:31:03.202828: Epoch time: 21.68 s +2025-10-31 09:31:03.204775: Yayy! New best EMA pseudo Dice: 0.9067000150680542 +2025-10-31 09:31:05.660794: +2025-10-31 09:31:05.663037: Epoch 3 +2025-10-31 09:31:05.665260: Current learning rate: 0.00997 +2025-10-31 09:31:28.312064: train_loss -0.8892 +2025-10-31 09:31:28.315070: val_loss -0.9136 +2025-10-31 09:31:28.316625: Pseudo dice [np.float32(0.9776), np.float32(0.9864), np.float32(0.9938), np.float32(0.8273)] +2025-10-31 09:31:28.341566: Epoch time: 22.65 s +2025-10-31 09:31:28.343648: Yayy! New best EMA pseudo Dice: 0.9107000231742859 +2025-10-31 09:31:30.776286: +2025-10-31 09:31:30.778313: Epoch 4 +2025-10-31 09:31:30.780224: Current learning rate: 0.00996 +2025-10-31 09:31:51.896051: train_loss -0.9075 +2025-10-31 09:31:51.898664: val_loss -0.9106 +2025-10-31 09:31:51.900596: Pseudo dice [np.float32(0.9809), np.float32(0.9881), np.float32(0.9921), np.float32(0.8333)] +2025-10-31 09:31:51.903703: Epoch time: 21.12 s +2025-10-31 09:31:51.905367: Yayy! New best EMA pseudo Dice: 0.9144999980926514 +2025-10-31 09:31:54.604174: +2025-10-31 09:31:54.607269: Epoch 5 +2025-10-31 09:31:54.610180: Current learning rate: 0.00995 +2025-10-31 09:32:15.493814: train_loss -0.9133 +2025-10-31 09:32:15.498117: val_loss -0.9143 +2025-10-31 09:32:15.500052: Pseudo dice [np.float32(0.9814), np.float32(0.9862), np.float32(0.9939), np.float32(0.8272)] +2025-10-31 09:32:15.501857: Epoch time: 20.89 s +2025-10-31 09:32:15.503669: Yayy! New best EMA pseudo Dice: 0.9176999926567078 +2025-10-31 09:32:17.957995: +2025-10-31 09:32:17.959816: Epoch 6 +2025-10-31 09:32:17.961708: Current learning rate: 0.00995 +2025-10-31 09:32:40.218620: train_loss -0.9162 +2025-10-31 09:32:40.226599: val_loss -0.9145 +2025-10-31 09:32:40.230631: Pseudo dice [np.float32(0.98), np.float32(0.9883), np.float32(0.9941), np.float32(0.8194)] +2025-10-31 09:32:40.234517: Epoch time: 22.26 s +2025-10-31 09:32:40.237290: Yayy! New best EMA pseudo Dice: 0.9204999804496765 +2025-10-31 09:32:43.016066: +2025-10-31 09:32:43.018425: Epoch 7 +2025-10-31 09:32:43.021382: Current learning rate: 0.00994 +2025-10-31 09:33:05.552718: train_loss -0.9257 +2025-10-31 09:33:05.555692: val_loss -0.9264 +2025-10-31 09:33:05.557674: Pseudo dice [np.float32(0.9835), np.float32(0.9903), np.float32(0.995), np.float32(0.8389)] +2025-10-31 09:33:05.559847: Epoch time: 22.54 s +2025-10-31 09:33:05.562019: Yayy! New best EMA pseudo Dice: 0.9236999750137329 +2025-10-31 09:33:07.868536: +2025-10-31 09:33:07.871894: Epoch 8 +2025-10-31 09:33:07.874276: Current learning rate: 0.00993 +2025-10-31 09:33:29.490940: train_loss -0.9266 +2025-10-31 09:33:29.494577: val_loss -0.922 +2025-10-31 09:33:29.496856: Pseudo dice [np.float32(0.9839), np.float32(0.99), np.float32(0.9946), np.float32(0.8287)] +2025-10-31 09:33:29.499234: Epoch time: 21.62 s +2025-10-31 09:33:29.501711: Yayy! New best EMA pseudo Dice: 0.9261999726295471 +2025-10-31 09:33:32.162833: +2025-10-31 09:33:32.165179: Epoch 9 +2025-10-31 09:33:32.168124: Current learning rate: 0.00992 +2025-10-31 09:33:54.415374: train_loss -0.9261 +2025-10-31 09:33:54.419373: val_loss -0.9219 +2025-10-31 09:33:54.421488: Pseudo dice [np.float32(0.9824), np.float32(0.9892), np.float32(0.995), np.float32(0.839)] +2025-10-31 09:33:54.423440: Epoch time: 22.25 s +2025-10-31 09:33:54.425521: Yayy! New best EMA pseudo Dice: 0.9286999702453613 +2025-10-31 09:33:57.135859: +2025-10-31 09:33:57.140908: Epoch 10 +2025-10-31 09:33:57.143178: Current learning rate: 0.00991 +2025-10-31 09:34:19.202076: train_loss -0.9318 +2025-10-31 09:34:19.208927: val_loss -0.9214 +2025-10-31 09:34:19.211015: Pseudo dice [np.float32(0.9826), np.float32(0.9897), np.float32(0.9948), np.float32(0.818)] +2025-10-31 09:34:19.213458: Epoch time: 22.07 s +2025-10-31 09:34:19.215436: Yayy! New best EMA pseudo Dice: 0.9304999709129333 +2025-10-31 09:34:21.552371: +2025-10-31 09:34:21.554213: Epoch 11 +2025-10-31 09:34:21.556074: Current learning rate: 0.0099 +2025-10-31 09:34:43.066736: train_loss -0.9345 +2025-10-31 09:34:43.069763: val_loss -0.9174 +2025-10-31 09:34:43.072209: Pseudo dice [np.float32(0.9834), np.float32(0.9895), np.float32(0.9947), np.float32(0.8076)] +2025-10-31 09:34:43.074347: Epoch time: 21.52 s +2025-10-31 09:34:43.076385: Yayy! New best EMA pseudo Dice: 0.9318000078201294 +2025-10-31 09:34:45.405406: +2025-10-31 09:34:45.408284: Epoch 12 +2025-10-31 09:34:45.411259: Current learning rate: 0.00989 +2025-10-31 09:35:07.196148: train_loss -0.94 +2025-10-31 09:35:07.199404: val_loss -0.9169 +2025-10-31 09:35:07.201215: Pseudo dice [np.float32(0.9826), np.float32(0.989), np.float32(0.9944), np.float32(0.8118)] +2025-10-31 09:35:07.203022: Epoch time: 21.79 s +2025-10-31 09:35:07.204709: Yayy! New best EMA pseudo Dice: 0.9330999851226807 +2025-10-31 09:35:09.617604: +2025-10-31 09:35:09.620572: Epoch 13 +2025-10-31 09:35:09.623153: Current learning rate: 0.00988 +2025-10-31 09:35:32.192491: train_loss -0.9369 +2025-10-31 09:35:32.196069: val_loss -0.9137 +2025-10-31 09:35:32.198599: Pseudo dice [np.float32(0.9815), np.float32(0.989), np.float32(0.9907), np.float32(0.8277)] +2025-10-31 09:35:32.200557: Epoch time: 22.58 s +2025-10-31 09:35:32.202411: Yayy! New best EMA pseudo Dice: 0.934499979019165 +2025-10-31 09:35:34.801364: +2025-10-31 09:35:34.804164: Epoch 14 +2025-10-31 09:35:34.806549: Current learning rate: 0.00987 +2025-10-31 09:35:57.269556: train_loss -0.9357 +2025-10-31 09:35:57.276432: val_loss -0.9038 +2025-10-31 09:35:57.278911: Pseudo dice [np.float32(0.9822), np.float32(0.9895), np.float32(0.9906), np.float32(0.7974)] +2025-10-31 09:35:57.280641: Epoch time: 22.47 s +2025-10-31 09:35:57.282417: Yayy! New best EMA pseudo Dice: 0.9350000023841858 +2025-10-31 09:36:00.003986: +2025-10-31 09:36:00.006610: Epoch 15 +2025-10-31 09:36:00.009117: Current learning rate: 0.00986 +2025-10-31 09:36:20.690017: train_loss -0.943 +2025-10-31 09:36:20.695564: val_loss -0.9146 +2025-10-31 09:36:20.697634: Pseudo dice [np.float32(0.9831), np.float32(0.9896), np.float32(0.9918), np.float32(0.8259)] +2025-10-31 09:36:20.699693: Epoch time: 20.69 s +2025-10-31 09:36:20.701997: Yayy! New best EMA pseudo Dice: 0.9362999796867371 +2025-10-31 09:36:23.109396: +2025-10-31 09:36:23.112006: Epoch 16 +2025-10-31 09:36:23.114275: Current learning rate: 0.00986 +2025-10-31 09:36:45.619240: train_loss -0.9352 +2025-10-31 09:36:45.623765: val_loss -0.9006 +2025-10-31 09:36:45.625879: Pseudo dice [np.float32(0.9822), np.float32(0.9867), np.float32(0.9894), np.float32(0.7892)] +2025-10-31 09:36:45.627860: Epoch time: 22.51 s +2025-10-31 09:36:45.636972: Yayy! New best EMA pseudo Dice: 0.9363999962806702 +2025-10-31 09:36:48.300070: +2025-10-31 09:36:48.303632: Epoch 17 +2025-10-31 09:36:48.306117: Current learning rate: 0.00985 +2025-10-31 09:37:08.752040: train_loss -0.9346 +2025-10-31 09:37:08.755304: val_loss -0.9181 +2025-10-31 09:37:08.757632: Pseudo dice [np.float32(0.9837), np.float32(0.9902), np.float32(0.9945), np.float32(0.8101)] +2025-10-31 09:37:08.760764: Epoch time: 20.45 s +2025-10-31 09:37:08.763802: Yayy! New best EMA pseudo Dice: 0.9372000098228455 +2025-10-31 09:37:11.414670: +2025-10-31 09:37:11.420966: Epoch 18 +2025-10-31 09:37:11.426723: Current learning rate: 0.00984 +2025-10-31 09:37:34.084916: train_loss -0.9406 +2025-10-31 09:37:34.089829: val_loss -0.9209 +2025-10-31 09:37:34.091916: Pseudo dice [np.float32(0.9816), np.float32(0.9898), np.float32(0.995), np.float32(0.8265)] +2025-10-31 09:37:34.093766: Epoch time: 22.67 s +2025-10-31 09:37:34.097040: Yayy! New best EMA pseudo Dice: 0.9383000135421753 +2025-10-31 09:37:37.232401: +2025-10-31 09:37:37.234592: Epoch 19 +2025-10-31 09:37:37.236675: Current learning rate: 0.00983 +2025-10-31 09:37:58.579421: train_loss -0.9481 +2025-10-31 09:37:58.585294: val_loss -0.9211 +2025-10-31 09:37:58.587605: Pseudo dice [np.float32(0.9843), np.float32(0.9904), np.float32(0.9942), np.float32(0.823)] +2025-10-31 09:37:58.590974: Epoch time: 21.35 s +2025-10-31 09:37:58.593115: Yayy! New best EMA pseudo Dice: 0.939300000667572 +2025-10-31 09:38:01.307865: +2025-10-31 09:38:01.315848: Epoch 20 +2025-10-31 09:38:01.327048: Current learning rate: 0.00982 +2025-10-31 09:38:23.724747: train_loss -0.9502 +2025-10-31 09:38:23.727759: val_loss -0.9196 +2025-10-31 09:38:23.729540: Pseudo dice [np.float32(0.9841), np.float32(0.9901), np.float32(0.9947), np.float32(0.8214)] +2025-10-31 09:38:23.734923: Epoch time: 22.42 s +2025-10-31 09:38:23.738128: Yayy! New best EMA pseudo Dice: 0.9401000142097473 +2025-10-31 09:38:25.943193: +2025-10-31 09:38:25.946725: Epoch 21 +2025-10-31 09:38:25.952217: Current learning rate: 0.00981 +2025-10-31 09:38:47.511462: train_loss -0.9519 +2025-10-31 09:38:47.514780: val_loss -0.9189 +2025-10-31 09:38:47.516597: Pseudo dice [np.float32(0.9829), np.float32(0.9898), np.float32(0.9947), np.float32(0.8279)] +2025-10-31 09:38:47.518269: Epoch time: 21.57 s +2025-10-31 09:38:47.519739: Yayy! New best EMA pseudo Dice: 0.9409999847412109 +2025-10-31 09:38:50.126362: +2025-10-31 09:38:50.128781: Epoch 22 +2025-10-31 09:38:50.131264: Current learning rate: 0.0098 +2025-10-31 09:39:12.062335: train_loss -0.9521 +2025-10-31 09:39:12.072022: val_loss -0.9195 +2025-10-31 09:39:12.075836: Pseudo dice [np.float32(0.983), np.float32(0.9896), np.float32(0.9947), np.float32(0.8204)] +2025-10-31 09:39:12.079515: Epoch time: 21.94 s +2025-10-31 09:39:12.081980: Yayy! New best EMA pseudo Dice: 0.9416000247001648 +2025-10-31 09:39:15.044399: +2025-10-31 09:39:15.050681: Epoch 23 +2025-10-31 09:39:15.053075: Current learning rate: 0.00979 +2025-10-31 09:39:35.751304: train_loss -0.9565 +2025-10-31 09:39:35.753803: val_loss -0.9025 +2025-10-31 09:39:35.756094: Pseudo dice [np.float32(0.9834), np.float32(0.9903), np.float32(0.9918), np.float32(0.8068)] +2025-10-31 09:39:35.758095: Epoch time: 20.71 s +2025-10-31 09:39:35.760023: Yayy! New best EMA pseudo Dice: 0.9416999816894531 +2025-10-31 09:39:38.457903: +2025-10-31 09:39:38.462395: Epoch 24 +2025-10-31 09:39:38.466485: Current learning rate: 0.00978 +2025-10-31 09:40:00.919477: train_loss -0.9588 +2025-10-31 09:40:00.925065: val_loss -0.9172 +2025-10-31 09:40:00.928614: Pseudo dice [np.float32(0.9822), np.float32(0.9897), np.float32(0.9949), np.float32(0.8182)] +2025-10-31 09:40:00.933765: Epoch time: 22.46 s +2025-10-31 09:40:00.938182: Yayy! New best EMA pseudo Dice: 0.9422000050544739 +2025-10-31 09:40:03.471387: +2025-10-31 09:40:03.473677: Epoch 25 +2025-10-31 09:40:03.476123: Current learning rate: 0.00977 +2025-10-31 09:40:25.799766: train_loss -0.96 +2025-10-31 09:40:25.802958: val_loss -0.9171 +2025-10-31 09:40:25.805474: Pseudo dice [np.float32(0.9825), np.float32(0.9892), np.float32(0.9948), np.float32(0.8171)] +2025-10-31 09:40:25.807853: Epoch time: 22.33 s +2025-10-31 09:40:25.809786: Yayy! New best EMA pseudo Dice: 0.9424999952316284 +2025-10-31 09:40:28.294215: +2025-10-31 09:40:28.297112: Epoch 26 +2025-10-31 09:40:28.299786: Current learning rate: 0.00977 +2025-10-31 09:40:49.194860: train_loss -0.9589 +2025-10-31 09:40:49.200764: val_loss -0.9137 +2025-10-31 09:40:49.202587: Pseudo dice [np.float32(0.9838), np.float32(0.9893), np.float32(0.9946), np.float32(0.8048)] +2025-10-31 09:40:49.204591: Epoch time: 20.9 s +2025-10-31 09:40:49.206609: Yayy! New best EMA pseudo Dice: 0.9426000118255615 +2025-10-31 09:40:51.751969: +2025-10-31 09:40:51.754265: Epoch 27 +2025-10-31 09:40:51.756371: Current learning rate: 0.00976 +2025-10-31 09:41:14.131395: train_loss -0.9578 +2025-10-31 09:41:14.135135: val_loss -0.9188 +2025-10-31 09:41:14.137685: Pseudo dice [np.float32(0.9823), np.float32(0.9899), np.float32(0.994), np.float32(0.8261)] +2025-10-31 09:41:14.139806: Epoch time: 22.38 s +2025-10-31 09:41:14.141648: Yayy! New best EMA pseudo Dice: 0.9430999755859375 +2025-10-31 09:41:16.559678: +2025-10-31 09:41:16.561974: Epoch 28 +2025-10-31 09:41:16.563910: Current learning rate: 0.00975 +2025-10-31 09:41:39.354321: train_loss -0.9604 +2025-10-31 09:41:39.357780: val_loss -0.8947 +2025-10-31 09:41:39.360083: Pseudo dice [np.float32(0.9836), np.float32(0.991), np.float32(0.9904), np.float32(0.7804)] +2025-10-31 09:41:39.362340: Epoch time: 22.8 s +2025-10-31 09:41:40.486783: +2025-10-31 09:41:40.489356: Epoch 29 +2025-10-31 09:41:40.491804: Current learning rate: 0.00974 +2025-10-31 09:42:01.193518: train_loss -0.9606 +2025-10-31 09:42:01.195975: val_loss -0.9146 +2025-10-31 09:42:01.197922: Pseudo dice [np.float32(0.9824), np.float32(0.9894), np.float32(0.9949), np.float32(0.8169)] +2025-10-31 09:42:01.200587: Epoch time: 20.71 s +2025-10-31 09:42:02.418105: +2025-10-31 09:42:02.421178: Epoch 30 +2025-10-31 09:42:02.423573: Current learning rate: 0.00973 +2025-10-31 09:42:24.080534: train_loss -0.9631 +2025-10-31 09:42:24.083572: val_loss -0.9076 +2025-10-31 09:42:24.086290: Pseudo dice [np.float32(0.9823), np.float32(0.9892), np.float32(0.9942), np.float32(0.8015)] +2025-10-31 09:42:24.088733: Epoch time: 21.66 s +2025-10-31 09:42:26.179519: +2025-10-31 09:42:26.182130: Epoch 31 +2025-10-31 09:42:26.184624: Current learning rate: 0.00972 +2025-10-31 09:42:48.298970: train_loss -0.9619 +2025-10-31 09:42:48.302054: val_loss -0.9156 +2025-10-31 09:42:48.305182: Pseudo dice [np.float32(0.9829), np.float32(0.9901), np.float32(0.9948), np.float32(0.8146)] +2025-10-31 09:42:48.307322: Epoch time: 22.12 s +2025-10-31 09:42:49.293360: +2025-10-31 09:42:49.295640: Epoch 32 +2025-10-31 09:42:49.297750: Current learning rate: 0.00971 +2025-10-31 09:43:10.613832: train_loss -0.9632 +2025-10-31 09:43:10.616571: val_loss -0.9196 +2025-10-31 09:43:10.619217: Pseudo dice [np.float32(0.9825), np.float32(0.9906), np.float32(0.9955), np.float32(0.8302)] +2025-10-31 09:43:10.621540: Epoch time: 21.32 s +2025-10-31 09:43:10.623554: Yayy! New best EMA pseudo Dice: 0.9437000155448914 +2025-10-31 09:43:13.018224: +2025-10-31 09:43:13.020558: Epoch 33 +2025-10-31 09:43:13.022621: Current learning rate: 0.0097 +2025-10-31 09:43:35.632991: train_loss -0.9647 +2025-10-31 09:43:35.636095: val_loss -0.9131 +2025-10-31 09:43:35.637778: Pseudo dice [np.float32(0.983), np.float32(0.988), np.float32(0.9944), np.float32(0.8136)] +2025-10-31 09:43:35.639632: Epoch time: 22.62 s +2025-10-31 09:43:35.641216: Yayy! New best EMA pseudo Dice: 0.9437999725341797 +2025-10-31 09:43:38.256578: +2025-10-31 09:43:38.261343: Epoch 34 +2025-10-31 09:43:38.263429: Current learning rate: 0.00969 +2025-10-31 09:43:59.896891: train_loss -0.9644 +2025-10-31 09:43:59.899873: val_loss -0.9164 +2025-10-31 09:43:59.902562: Pseudo dice [np.float32(0.9817), np.float32(0.9898), np.float32(0.9954), np.float32(0.832)] +2025-10-31 09:43:59.906941: Epoch time: 21.64 s +2025-10-31 09:43:59.909576: Yayy! New best EMA pseudo Dice: 0.9444000124931335 +2025-10-31 09:44:02.399971: +2025-10-31 09:44:02.403748: Epoch 35 +2025-10-31 09:44:02.410443: Current learning rate: 0.00968 +2025-10-31 09:44:21.320670: train_loss -0.967 +2025-10-31 09:44:21.323317: val_loss -0.9213 +2025-10-31 09:44:21.325565: Pseudo dice [np.float32(0.9821), np.float32(0.9893), np.float32(0.9957), np.float32(0.847)] +2025-10-31 09:44:21.327663: Epoch time: 18.92 s +2025-10-31 09:44:21.330495: Yayy! New best EMA pseudo Dice: 0.9452999830245972 +2025-10-31 09:44:23.823750: +2025-10-31 09:44:23.826018: Epoch 36 +2025-10-31 09:44:23.828145: Current learning rate: 0.00968 +2025-10-31 09:44:44.593295: train_loss -0.967 +2025-10-31 09:44:44.596228: val_loss -0.9109 +2025-10-31 09:44:44.597979: Pseudo dice [np.float32(0.9829), np.float32(0.9892), np.float32(0.9951), np.float32(0.8169)] +2025-10-31 09:44:44.600030: Epoch time: 20.77 s +2025-10-31 09:44:44.601648: Yayy! New best EMA pseudo Dice: 0.9453999996185303 +2025-10-31 09:44:46.967443: +2025-10-31 09:44:46.969897: Epoch 37 +2025-10-31 09:44:46.972462: Current learning rate: 0.00967 +2025-10-31 09:45:08.773266: train_loss -0.9662 +2025-10-31 09:45:08.777848: val_loss -0.919 +2025-10-31 09:45:08.779964: Pseudo dice [np.float32(0.9836), np.float32(0.9914), np.float32(0.9954), np.float32(0.8267)] +2025-10-31 09:45:08.784631: Epoch time: 21.81 s +2025-10-31 09:45:08.789858: Yayy! New best EMA pseudo Dice: 0.9458000063896179 +2025-10-31 09:45:11.408891: +2025-10-31 09:45:11.411278: Epoch 38 +2025-10-31 09:45:11.414226: Current learning rate: 0.00966 +2025-10-31 09:45:32.663569: train_loss -0.9683 +2025-10-31 09:45:32.666781: val_loss -0.9112 +2025-10-31 09:45:32.668524: Pseudo dice [np.float32(0.9843), np.float32(0.9909), np.float32(0.9951), np.float32(0.8069)] +2025-10-31 09:45:32.670213: Epoch time: 21.26 s +2025-10-31 09:45:33.713301: +2025-10-31 09:45:33.715298: Epoch 39 +2025-10-31 09:45:33.716885: Current learning rate: 0.00965 +2025-10-31 09:45:56.114704: train_loss -0.9691 +2025-10-31 09:45:56.117957: val_loss -0.9171 +2025-10-31 09:45:56.120617: Pseudo dice [np.float32(0.9827), np.float32(0.9897), np.float32(0.995), np.float32(0.8241)] +2025-10-31 09:45:56.124422: Epoch time: 22.4 s +2025-10-31 09:45:56.126313: Yayy! New best EMA pseudo Dice: 0.9458000063896179 +2025-10-31 09:45:58.634576: +2025-10-31 09:45:58.637242: Epoch 40 +2025-10-31 09:45:58.639627: Current learning rate: 0.00964 +2025-10-31 09:46:21.209175: train_loss -0.9704 +2025-10-31 09:46:21.215188: val_loss -0.9207 +2025-10-31 09:46:21.217422: Pseudo dice [np.float32(0.984), np.float32(0.9907), np.float32(0.9955), np.float32(0.8354)] +2025-10-31 09:46:21.219838: Epoch time: 22.58 s +2025-10-31 09:46:21.221902: Yayy! New best EMA pseudo Dice: 0.946399986743927 +2025-10-31 09:46:23.293987: +2025-10-31 09:46:23.296308: Epoch 41 +2025-10-31 09:46:23.298092: Current learning rate: 0.00963 +2025-10-31 09:46:43.919932: train_loss -0.9677 +2025-10-31 09:46:43.926103: val_loss -0.9124 +2025-10-31 09:46:43.927847: Pseudo dice [np.float32(0.9822), np.float32(0.9897), np.float32(0.9951), np.float32(0.8129)] +2025-10-31 09:46:43.931457: Epoch time: 20.63 s +2025-10-31 09:46:45.086459: +2025-10-31 09:46:45.088573: Epoch 42 +2025-10-31 09:46:45.090583: Current learning rate: 0.00962 +2025-10-31 09:47:07.620981: train_loss -0.969 +2025-10-31 09:47:07.627033: val_loss -0.9229 +2025-10-31 09:47:07.629006: Pseudo dice [np.float32(0.9827), np.float32(0.9904), np.float32(0.9953), np.float32(0.8447)] +2025-10-31 09:47:07.630923: Epoch time: 22.54 s +2025-10-31 09:47:07.633119: Yayy! New best EMA pseudo Dice: 0.9469000101089478 +2025-10-31 09:47:10.455870: +2025-10-31 09:47:10.458160: Epoch 43 +2025-10-31 09:47:10.460306: Current learning rate: 0.00961 +2025-10-31 09:47:32.031983: train_loss -0.9695 +2025-10-31 09:47:32.034806: val_loss -0.9121 +2025-10-31 09:47:32.036676: Pseudo dice [np.float32(0.9829), np.float32(0.9906), np.float32(0.9952), np.float32(0.8107)] +2025-10-31 09:47:32.038687: Epoch time: 21.58 s +2025-10-31 09:47:33.121187: +2025-10-31 09:47:33.123521: Epoch 44 +2025-10-31 09:47:33.125569: Current learning rate: 0.0096 +2025-10-31 09:47:54.227540: train_loss -0.9715 +2025-10-31 09:47:54.230393: val_loss -0.9123 +2025-10-31 09:47:54.232763: Pseudo dice [np.float32(0.984), np.float32(0.9916), np.float32(0.9952), np.float32(0.8135)] +2025-10-31 09:47:54.235116: Epoch time: 21.11 s +2025-10-31 09:47:55.340764: +2025-10-31 09:47:55.343501: Epoch 45 +2025-10-31 09:47:55.345630: Current learning rate: 0.00959 +2025-10-31 09:48:17.952394: train_loss -0.9709 +2025-10-31 09:48:17.957185: val_loss -0.9106 +2025-10-31 09:48:17.959978: Pseudo dice [np.float32(0.9836), np.float32(0.9904), np.float32(0.995), np.float32(0.821)] +2025-10-31 09:48:17.962496: Epoch time: 22.61 s +2025-10-31 09:48:18.878426: +2025-10-31 09:48:18.880697: Epoch 46 +2025-10-31 09:48:18.882815: Current learning rate: 0.00959 +2025-10-31 09:48:40.206382: train_loss -0.9705 +2025-10-31 09:48:40.209680: val_loss -0.9159 +2025-10-31 09:48:40.211652: Pseudo dice [np.float32(0.9835), np.float32(0.9909), np.float32(0.9952), np.float32(0.823)] +2025-10-31 09:48:40.213552: Epoch time: 21.33 s +2025-10-31 09:48:41.360655: +2025-10-31 09:48:41.363093: Epoch 47 +2025-10-31 09:48:41.364959: Current learning rate: 0.00958 +2025-10-31 09:49:03.728841: train_loss -0.9742 +2025-10-31 09:49:03.731689: val_loss -0.9159 +2025-10-31 09:49:03.733696: Pseudo dice [np.float32(0.9829), np.float32(0.9906), np.float32(0.9952), np.float32(0.8234)] +2025-10-31 09:49:03.736793: Epoch time: 22.37 s +2025-10-31 09:49:03.739535: Yayy! New best EMA pseudo Dice: 0.9470000267028809 +2025-10-31 09:49:06.183942: +2025-10-31 09:49:06.186440: Epoch 48 +2025-10-31 09:49:06.189577: Current learning rate: 0.00957 +2025-10-31 09:49:28.244354: train_loss -0.9725 +2025-10-31 09:49:28.249372: val_loss -0.9207 +2025-10-31 09:49:28.251543: Pseudo dice [np.float32(0.9827), np.float32(0.9903), np.float32(0.9955), np.float32(0.8405)] +2025-10-31 09:49:28.253755: Epoch time: 22.06 s +2025-10-31 09:49:28.256166: Yayy! New best EMA pseudo Dice: 0.9474999904632568 +2025-10-31 09:49:31.181789: +2025-10-31 09:49:31.184589: Epoch 49 +2025-10-31 09:49:31.186875: Current learning rate: 0.00956 +2025-10-31 09:49:53.315715: train_loss -0.9665 +2025-10-31 09:49:53.318806: val_loss -0.9247 +2025-10-31 09:49:53.320957: Pseudo dice [np.float32(0.9842), np.float32(0.991), np.float32(0.9955), np.float32(0.838)] +2025-10-31 09:49:53.322883: Epoch time: 22.14 s +2025-10-31 09:49:54.608539: Yayy! New best EMA pseudo Dice: 0.9480000138282776 +2025-10-31 09:49:57.027910: +2025-10-31 09:49:57.029974: Epoch 50 +2025-10-31 09:49:57.031706: Current learning rate: 0.00955 +2025-10-31 09:50:19.916779: train_loss -0.9615 +2025-10-31 09:50:19.919208: val_loss -0.9084 +2025-10-31 09:50:19.922124: Pseudo dice [np.float32(0.9835), np.float32(0.9897), np.float32(0.9924), np.float32(0.8074)] +2025-10-31 09:50:19.924086: Epoch time: 22.89 s +2025-10-31 09:50:21.038378: +2025-10-31 09:50:21.040767: Epoch 51 +2025-10-31 09:50:21.043048: Current learning rate: 0.00954 +2025-10-31 09:50:43.658009: train_loss -0.9539 +2025-10-31 09:50:43.661601: val_loss -0.9165 +2025-10-31 09:50:43.668139: Pseudo dice [np.float32(0.9812), np.float32(0.9873), np.float32(0.9946), np.float32(0.8304)] +2025-10-31 09:50:43.669686: Epoch time: 22.62 s +2025-10-31 09:50:44.821348: +2025-10-31 09:50:44.823894: Epoch 52 +2025-10-31 09:50:44.826672: Current learning rate: 0.00953 +2025-10-31 09:51:07.056355: train_loss -0.9601 +2025-10-31 09:51:07.063292: val_loss -0.913 +2025-10-31 09:51:07.066525: Pseudo dice [np.float32(0.9832), np.float32(0.9903), np.float32(0.9948), np.float32(0.8064)] +2025-10-31 09:51:07.068986: Epoch time: 22.24 s +2025-10-31 09:51:08.230024: +2025-10-31 09:51:08.233053: Epoch 53 +2025-10-31 09:51:08.235845: Current learning rate: 0.00952 +2025-10-31 09:51:30.961322: train_loss -0.967 +2025-10-31 09:51:30.964181: val_loss -0.9182 +2025-10-31 09:51:30.969793: Pseudo dice [np.float32(0.9843), np.float32(0.9912), np.float32(0.9954), np.float32(0.8255)] +2025-10-31 09:51:30.971514: Epoch time: 22.73 s +2025-10-31 09:51:31.995893: +2025-10-31 09:51:31.998168: Epoch 54 +2025-10-31 09:51:32.000779: Current learning rate: 0.00951 +2025-10-31 09:51:53.896199: train_loss -0.9665 +2025-10-31 09:51:53.903312: val_loss -0.9141 +2025-10-31 09:51:53.906018: Pseudo dice [np.float32(0.9827), np.float32(0.989), np.float32(0.995), np.float32(0.8167)] +2025-10-31 09:51:53.908631: Epoch time: 21.9 s +2025-10-31 09:51:55.035673: +2025-10-31 09:51:55.037830: Epoch 55 +2025-10-31 09:51:55.040209: Current learning rate: 0.0095 +2025-10-31 09:52:16.398668: train_loss -0.9685 +2025-10-31 09:52:16.416497: val_loss -0.9179 +2025-10-31 09:52:16.433371: Pseudo dice [np.float32(0.986), np.float32(0.9911), np.float32(0.9954), np.float32(0.8232)] +2025-10-31 09:52:16.454869: Epoch time: 21.37 s +2025-10-31 09:52:17.998834: +2025-10-31 09:52:18.000867: Epoch 56 +2025-10-31 09:52:18.002545: Current learning rate: 0.00949 +2025-10-31 09:52:40.196950: train_loss -0.97 +2025-10-31 09:52:40.201570: val_loss -0.9105 +2025-10-31 09:52:40.206507: Pseudo dice [np.float32(0.9817), np.float32(0.9894), np.float32(0.9948), np.float32(0.8069)] +2025-10-31 09:52:40.209488: Epoch time: 22.2 s +2025-10-31 09:52:41.280552: +2025-10-31 09:52:41.282672: Epoch 57 +2025-10-31 09:52:41.284661: Current learning rate: 0.00949 +2025-10-31 09:53:03.904543: train_loss -0.971 +2025-10-31 09:53:03.907774: val_loss -0.912 +2025-10-31 09:53:03.909714: Pseudo dice [np.float32(0.9829), np.float32(0.9899), np.float32(0.9951), np.float32(0.8081)] +2025-10-31 09:53:03.911405: Epoch time: 22.63 s +2025-10-31 09:53:04.899956: +2025-10-31 09:53:04.902629: Epoch 58 +2025-10-31 09:53:04.906055: Current learning rate: 0.00948 +2025-10-31 09:53:26.587292: train_loss -0.9727 +2025-10-31 09:53:26.591111: val_loss -0.9213 +2025-10-31 09:53:26.594416: Pseudo dice [np.float32(0.9843), np.float32(0.991), np.float32(0.9955), np.float32(0.8405)] +2025-10-31 09:53:26.598104: Epoch time: 21.69 s +2025-10-31 09:53:27.781885: +2025-10-31 09:53:27.784234: Epoch 59 +2025-10-31 09:53:27.787436: Current learning rate: 0.00947 +2025-10-31 09:53:50.241990: train_loss -0.9696 +2025-10-31 09:53:50.244535: val_loss -0.9174 +2025-10-31 09:53:50.247209: Pseudo dice [np.float32(0.9847), np.float32(0.9903), np.float32(0.9949), np.float32(0.8238)] +2025-10-31 09:53:50.249738: Epoch time: 22.46 s +2025-10-31 09:53:51.265843: +2025-10-31 09:53:51.268438: Epoch 60 +2025-10-31 09:53:51.271103: Current learning rate: 0.00946 +2025-10-31 09:54:12.301211: train_loss -0.9688 +2025-10-31 09:54:12.306088: val_loss -0.9183 +2025-10-31 09:54:12.308157: Pseudo dice [np.float32(0.9829), np.float32(0.9898), np.float32(0.9953), np.float32(0.8277)] +2025-10-31 09:54:12.311334: Epoch time: 21.04 s +2025-10-31 09:54:13.554718: +2025-10-31 09:54:13.557247: Epoch 61 +2025-10-31 09:54:13.559187: Current learning rate: 0.00945 +2025-10-31 09:54:35.990511: train_loss -0.9562 +2025-10-31 09:54:35.995344: val_loss -0.9171 +2025-10-31 09:54:36.000046: Pseudo dice [np.float32(0.9795), np.float32(0.9878), np.float32(0.9944), np.float32(0.834)] +2025-10-31 09:54:36.005953: Epoch time: 22.44 s +2025-10-31 09:54:37.055077: +2025-10-31 09:54:37.060515: Epoch 62 +2025-10-31 09:54:37.062472: Current learning rate: 0.00944 +2025-10-31 09:54:58.724927: train_loss -0.9631 +2025-10-31 09:54:58.728072: val_loss -0.914 +2025-10-31 09:54:58.729978: Pseudo dice [np.float32(0.9823), np.float32(0.9902), np.float32(0.995), np.float32(0.8195)] +2025-10-31 09:54:58.731970: Epoch time: 21.67 s +2025-10-31 09:54:59.977858: +2025-10-31 09:54:59.995533: Epoch 63 +2025-10-31 09:54:59.998413: Current learning rate: 0.00943 +2025-10-31 09:55:21.626303: train_loss -0.9705 +2025-10-31 09:55:21.634285: val_loss -0.9125 +2025-10-31 09:55:21.638486: Pseudo dice [np.float32(0.9843), np.float32(0.989), np.float32(0.9944), np.float32(0.8105)] +2025-10-31 09:55:21.642665: Epoch time: 21.65 s +2025-10-31 09:55:22.793085: +2025-10-31 09:55:22.795770: Epoch 64 +2025-10-31 09:55:22.798271: Current learning rate: 0.00942 +2025-10-31 09:55:44.699678: train_loss -0.9696 +2025-10-31 09:55:44.702320: val_loss -0.916 +2025-10-31 09:55:44.704529: Pseudo dice [np.float32(0.9851), np.float32(0.9914), np.float32(0.995), np.float32(0.8175)] +2025-10-31 09:55:44.707016: Epoch time: 21.91 s +2025-10-31 09:55:45.708396: +2025-10-31 09:55:45.711191: Epoch 65 +2025-10-31 09:55:45.713377: Current learning rate: 0.00941 +2025-10-31 09:56:07.954267: train_loss -0.9723 +2025-10-31 09:56:07.957325: val_loss -0.9154 +2025-10-31 09:56:07.959731: Pseudo dice [np.float32(0.9845), np.float32(0.9913), np.float32(0.9949), np.float32(0.8251)] +2025-10-31 09:56:07.964450: Epoch time: 22.25 s +2025-10-31 09:56:08.954372: +2025-10-31 09:56:08.957221: Epoch 66 +2025-10-31 09:56:08.962578: Current learning rate: 0.0094 +2025-10-31 09:56:29.198559: train_loss -0.9735 +2025-10-31 09:56:29.202680: val_loss -0.9095 +2025-10-31 09:56:29.204841: Pseudo dice [np.float32(0.9839), np.float32(0.9908), np.float32(0.9947), np.float32(0.8061)] +2025-10-31 09:56:29.206990: Epoch time: 20.25 s +2025-10-31 09:56:30.399027: +2025-10-31 09:56:30.401443: Epoch 67 +2025-10-31 09:56:30.403826: Current learning rate: 0.00939 +2025-10-31 09:56:52.403020: train_loss -0.9731 +2025-10-31 09:56:52.406780: val_loss -0.924 +2025-10-31 09:56:52.409326: Pseudo dice [np.float32(0.9851), np.float32(0.9918), np.float32(0.9955), np.float32(0.841)] +2025-10-31 09:56:52.411620: Epoch time: 22.01 s +2025-10-31 09:56:54.311511: +2025-10-31 09:56:54.314929: Epoch 68 +2025-10-31 09:56:54.317113: Current learning rate: 0.00939 +2025-10-31 09:57:16.559186: train_loss -0.9762 +2025-10-31 09:57:16.562803: val_loss -0.9156 +2025-10-31 09:57:16.565323: Pseudo dice [np.float32(0.9844), np.float32(0.9913), np.float32(0.9953), np.float32(0.827)] +2025-10-31 09:57:16.567443: Epoch time: 22.25 s +2025-10-31 09:57:17.774515: +2025-10-31 09:57:17.776302: Epoch 69 +2025-10-31 09:57:17.777966: Current learning rate: 0.00938 +2025-10-31 09:57:39.900757: train_loss -0.9768 +2025-10-31 09:57:39.905274: val_loss -0.908 +2025-10-31 09:57:39.907468: Pseudo dice [np.float32(0.9825), np.float32(0.9907), np.float32(0.9952), np.float32(0.8118)] +2025-10-31 09:57:39.909567: Epoch time: 22.13 s +2025-10-31 09:57:41.126057: +2025-10-31 09:57:41.128240: Epoch 70 +2025-10-31 09:57:41.130148: Current learning rate: 0.00937 +2025-10-31 09:58:02.872938: train_loss -0.9749 +2025-10-31 09:58:02.876681: val_loss -0.9181 +2025-10-31 09:58:02.880139: Pseudo dice [np.float32(0.9845), np.float32(0.9917), np.float32(0.9954), np.float32(0.8318)] +2025-10-31 09:58:02.883972: Epoch time: 21.75 s +2025-10-31 09:58:04.030472: +2025-10-31 09:58:04.033248: Epoch 71 +2025-10-31 09:58:04.037177: Current learning rate: 0.00936 +2025-10-31 09:58:26.208637: train_loss -0.9735 +2025-10-31 09:58:26.210877: val_loss -0.9183 +2025-10-31 09:58:26.213095: Pseudo dice [np.float32(0.9845), np.float32(0.9905), np.float32(0.9951), np.float32(0.8305)] +2025-10-31 09:58:26.215462: Epoch time: 22.18 s +2025-10-31 09:58:26.217680: Yayy! New best EMA pseudo Dice: 0.948199987411499 +2025-10-31 09:58:28.662300: +2025-10-31 09:58:28.665582: Epoch 72 +2025-10-31 09:58:28.667988: Current learning rate: 0.00935 +2025-10-31 09:58:50.886524: train_loss -0.973 +2025-10-31 09:58:50.890820: val_loss -0.9114 +2025-10-31 09:58:50.894434: Pseudo dice [np.float32(0.9847), np.float32(0.9909), np.float32(0.995), np.float32(0.8131)] +2025-10-31 09:58:50.896645: Epoch time: 22.23 s +2025-10-31 09:58:52.116848: +2025-10-31 09:58:52.121645: Epoch 73 +2025-10-31 09:58:52.124344: Current learning rate: 0.00934 +2025-10-31 09:59:12.660431: train_loss -0.9748 +2025-10-31 09:59:12.663370: val_loss -0.92 +2025-10-31 09:59:12.666223: Pseudo dice [np.float32(0.9834), np.float32(0.99), np.float32(0.9953), np.float32(0.8422)] +2025-10-31 09:59:12.668297: Epoch time: 20.55 s +2025-10-31 09:59:12.670144: Yayy! New best EMA pseudo Dice: 0.9484000205993652 +2025-10-31 09:59:15.159602: +2025-10-31 09:59:15.161560: Epoch 74 +2025-10-31 09:59:15.163182: Current learning rate: 0.00933 +2025-10-31 09:59:38.124178: train_loss -0.9721 +2025-10-31 09:59:38.129228: val_loss -0.9121 +2025-10-31 09:59:38.131353: Pseudo dice [np.float32(0.9844), np.float32(0.9903), np.float32(0.9949), np.float32(0.8177)] +2025-10-31 09:59:38.133889: Epoch time: 22.97 s +2025-10-31 09:59:39.343059: +2025-10-31 09:59:39.345877: Epoch 75 +2025-10-31 09:59:39.348027: Current learning rate: 0.00932 +2025-10-31 10:00:01.669970: train_loss -0.9744 +2025-10-31 10:00:01.673486: val_loss -0.915 +2025-10-31 10:00:01.680444: Pseudo dice [np.float32(0.9845), np.float32(0.9907), np.float32(0.9953), np.float32(0.817)] +2025-10-31 10:00:01.682148: Epoch time: 22.33 s +2025-10-31 10:00:02.735248: +2025-10-31 10:00:02.738435: Epoch 76 +2025-10-31 10:00:02.740358: Current learning rate: 0.00931 +2025-10-31 10:00:24.919505: train_loss -0.9746 +2025-10-31 10:00:24.923496: val_loss -0.9106 +2025-10-31 10:00:24.928312: Pseudo dice [np.float32(0.9848), np.float32(0.9913), np.float32(0.9949), np.float32(0.8153)] +2025-10-31 10:00:24.931426: Epoch time: 22.19 s +2025-10-31 10:00:26.028586: +2025-10-31 10:00:26.030895: Epoch 77 +2025-10-31 10:00:26.032985: Current learning rate: 0.0093 +2025-10-31 10:00:48.511118: train_loss -0.9761 +2025-10-31 10:00:48.513340: val_loss -0.9056 +2025-10-31 10:00:48.514932: Pseudo dice [np.float32(0.9842), np.float32(0.9917), np.float32(0.9948), np.float32(0.8063)] +2025-10-31 10:00:48.516593: Epoch time: 22.48 s +2025-10-31 10:00:49.734457: +2025-10-31 10:00:49.736560: Epoch 78 +2025-10-31 10:00:49.738570: Current learning rate: 0.0093 +2025-10-31 10:01:12.177710: train_loss -0.9779 +2025-10-31 10:01:12.181167: val_loss -0.9124 +2025-10-31 10:01:12.183028: Pseudo dice [np.float32(0.9841), np.float32(0.9907), np.float32(0.9952), np.float32(0.821)] +2025-10-31 10:01:12.185206: Epoch time: 22.45 s +2025-10-31 10:01:13.461611: +2025-10-31 10:01:13.464822: Epoch 79 +2025-10-31 10:01:13.466661: Current learning rate: 0.00929 +2025-10-31 10:01:34.015587: train_loss -0.9766 +2025-10-31 10:01:34.018206: val_loss -0.9058 +2025-10-31 10:01:34.020766: Pseudo dice [np.float32(0.9843), np.float32(0.9905), np.float32(0.9949), np.float32(0.8045)] +2025-10-31 10:01:34.023471: Epoch time: 20.56 s +2025-10-31 10:01:35.925262: +2025-10-31 10:01:35.935644: Epoch 80 +2025-10-31 10:01:35.937654: Current learning rate: 0.00928 +2025-10-31 10:01:58.365043: train_loss -0.9782 +2025-10-31 10:01:58.367534: val_loss -0.9136 +2025-10-31 10:01:58.371193: Pseudo dice [np.float32(0.9836), np.float32(0.9911), np.float32(0.9952), np.float32(0.8251)] +2025-10-31 10:01:58.372802: Epoch time: 22.44 s +2025-10-31 10:01:59.395363: +2025-10-31 10:01:59.397421: Epoch 81 +2025-10-31 10:01:59.399039: Current learning rate: 0.00927 +2025-10-31 10:02:21.600845: train_loss -0.9784 +2025-10-31 10:02:21.619156: val_loss -0.915 +2025-10-31 10:02:21.621343: Pseudo dice [np.float32(0.984), np.float32(0.9908), np.float32(0.9953), np.float32(0.8307)] +2025-10-31 10:02:21.623155: Epoch time: 22.21 s +2025-10-31 10:02:22.824775: +2025-10-31 10:02:22.827078: Epoch 82 +2025-10-31 10:02:22.829144: Current learning rate: 0.00926 +2025-10-31 10:02:44.042925: train_loss -0.9772 +2025-10-31 10:02:44.045908: val_loss -0.9167 +2025-10-31 10:02:44.047863: Pseudo dice [np.float32(0.9831), np.float32(0.9909), np.float32(0.9953), np.float32(0.8374)] +2025-10-31 10:02:44.050086: Epoch time: 21.22 s +2025-10-31 10:02:45.309551: +2025-10-31 10:02:45.314144: Epoch 83 +2025-10-31 10:02:45.316605: Current learning rate: 0.00925 +2025-10-31 10:03:07.515675: train_loss -0.9759 +2025-10-31 10:03:07.518710: val_loss -0.9135 +2025-10-31 10:03:07.520787: Pseudo dice [np.float32(0.9849), np.float32(0.9919), np.float32(0.9952), np.float32(0.8257)] +2025-10-31 10:03:07.522571: Epoch time: 22.21 s +2025-10-31 10:03:08.753038: +2025-10-31 10:03:08.755660: Epoch 84 +2025-10-31 10:03:08.757834: Current learning rate: 0.00924 +2025-10-31 10:03:31.220241: train_loss -0.9701 +2025-10-31 10:03:31.227632: val_loss -0.9169 +2025-10-31 10:03:31.229980: Pseudo dice [np.float32(0.9838), np.float32(0.9906), np.float32(0.9954), np.float32(0.8273)] +2025-10-31 10:03:31.231897: Epoch time: 22.47 s +2025-10-31 10:03:32.277296: +2025-10-31 10:03:32.279706: Epoch 85 +2025-10-31 10:03:32.281854: Current learning rate: 0.00923 +2025-10-31 10:03:52.151453: train_loss -0.9722 +2025-10-31 10:03:52.153584: val_loss -0.9164 +2025-10-31 10:03:52.155203: Pseudo dice [np.float32(0.9839), np.float32(0.9902), np.float32(0.9942), np.float32(0.8259)] +2025-10-31 10:03:52.156567: Epoch time: 19.88 s +2025-10-31 10:03:53.165055: +2025-10-31 10:03:53.169238: Epoch 86 +2025-10-31 10:03:53.171004: Current learning rate: 0.00922 +2025-10-31 10:04:14.956498: train_loss -0.9736 +2025-10-31 10:04:14.961584: val_loss -0.9103 +2025-10-31 10:04:14.963361: Pseudo dice [np.float32(0.9849), np.float32(0.9914), np.float32(0.9949), np.float32(0.8048)] +2025-10-31 10:04:14.965304: Epoch time: 21.79 s +2025-10-31 10:04:16.182490: +2025-10-31 10:04:16.185349: Epoch 87 +2025-10-31 10:04:16.187400: Current learning rate: 0.00921 +2025-10-31 10:04:38.549016: train_loss -0.9779 +2025-10-31 10:04:38.553794: val_loss -0.9089 +2025-10-31 10:04:38.555939: Pseudo dice [np.float32(0.9859), np.float32(0.9906), np.float32(0.9943), np.float32(0.8171)] +2025-10-31 10:04:38.559158: Epoch time: 22.37 s +2025-10-31 10:04:39.755225: +2025-10-31 10:04:39.757505: Epoch 88 +2025-10-31 10:04:39.759329: Current learning rate: 0.0092 +2025-10-31 10:05:02.518107: train_loss -0.9763 +2025-10-31 10:05:02.523297: val_loss -0.9078 +2025-10-31 10:05:02.525923: Pseudo dice [np.float32(0.9848), np.float32(0.9901), np.float32(0.9946), np.float32(0.8081)] +2025-10-31 10:05:02.528696: Epoch time: 22.76 s +2025-10-31 10:05:03.603091: +2025-10-31 10:05:03.605317: Epoch 89 +2025-10-31 10:05:03.607337: Current learning rate: 0.0092 +2025-10-31 10:05:25.833216: train_loss -0.978 +2025-10-31 10:05:25.835804: val_loss -0.9085 +2025-10-31 10:05:25.837545: Pseudo dice [np.float32(0.9833), np.float32(0.9914), np.float32(0.9947), np.float32(0.8205)] +2025-10-31 10:05:25.839690: Epoch time: 22.23 s +2025-10-31 10:05:27.041014: +2025-10-31 10:05:27.043107: Epoch 90 +2025-10-31 10:05:27.045427: Current learning rate: 0.00919 +2025-10-31 10:05:48.902098: train_loss -0.9779 +2025-10-31 10:05:48.904906: val_loss -0.9135 +2025-10-31 10:05:48.906720: Pseudo dice [np.float32(0.9855), np.float32(0.9912), np.float32(0.9952), np.float32(0.8236)] +2025-10-31 10:05:48.908415: Epoch time: 21.86 s +2025-10-31 10:05:50.082774: +2025-10-31 10:05:50.085124: Epoch 91 +2025-10-31 10:05:50.087463: Current learning rate: 0.00918 +2025-10-31 10:06:11.660298: train_loss -0.9773 +2025-10-31 10:06:11.663321: val_loss -0.905 +2025-10-31 10:06:11.665534: Pseudo dice [np.float32(0.9859), np.float32(0.992), np.float32(0.9948), np.float32(0.8018)] +2025-10-31 10:06:11.667598: Epoch time: 21.58 s +2025-10-31 10:06:12.752407: +2025-10-31 10:06:12.755262: Epoch 92 +2025-10-31 10:06:12.757841: Current learning rate: 0.00917 +2025-10-31 10:06:34.919518: train_loss -0.979 +2025-10-31 10:06:34.922247: val_loss -0.9057 +2025-10-31 10:06:34.924070: Pseudo dice [np.float32(0.985), np.float32(0.9918), np.float32(0.9951), np.float32(0.806)] +2025-10-31 10:06:34.926004: Epoch time: 22.17 s +2025-10-31 10:06:36.698541: +2025-10-31 10:06:36.701221: Epoch 93 +2025-10-31 10:06:36.703736: Current learning rate: 0.00916 +2025-10-31 10:06:58.899931: train_loss -0.9777 +2025-10-31 10:06:58.903108: val_loss -0.9187 +2025-10-31 10:06:58.907063: Pseudo dice [np.float32(0.9825), np.float32(0.9902), np.float32(0.9957), np.float32(0.834)] +2025-10-31 10:06:58.908565: Epoch time: 22.2 s +2025-10-31 10:06:59.864357: +2025-10-31 10:06:59.867047: Epoch 94 +2025-10-31 10:06:59.869156: Current learning rate: 0.00915 +2025-10-31 10:07:22.325310: train_loss -0.9802 +2025-10-31 10:07:22.328015: val_loss -0.9143 +2025-10-31 10:07:22.330324: Pseudo dice [np.float32(0.9855), np.float32(0.9924), np.float32(0.9954), np.float32(0.823)] +2025-10-31 10:07:22.332852: Epoch time: 22.46 s +2025-10-31 10:07:23.406564: +2025-10-31 10:07:23.409230: Epoch 95 +2025-10-31 10:07:23.411680: Current learning rate: 0.00914 +2025-10-31 10:07:45.150023: train_loss -0.9782 +2025-10-31 10:07:45.155342: val_loss -0.9139 +2025-10-31 10:07:45.157396: Pseudo dice [np.float32(0.9858), np.float32(0.993), np.float32(0.9956), np.float32(0.8223)] +2025-10-31 10:07:45.159331: Epoch time: 21.75 s +2025-10-31 10:07:46.341078: +2025-10-31 10:07:46.344369: Epoch 96 +2025-10-31 10:07:46.347324: Current learning rate: 0.00913 +2025-10-31 10:08:08.618911: train_loss -0.9797 +2025-10-31 10:08:08.622164: val_loss -0.9127 +2025-10-31 10:08:08.624224: Pseudo dice [np.float32(0.9825), np.float32(0.9912), np.float32(0.9957), np.float32(0.8296)] +2025-10-31 10:08:08.626172: Epoch time: 22.28 s +2025-10-31 10:08:09.778333: +2025-10-31 10:08:09.780361: Epoch 97 +2025-10-31 10:08:09.782222: Current learning rate: 0.00912 +2025-10-31 10:08:31.768993: train_loss -0.9793 +2025-10-31 10:08:31.771898: val_loss -0.9158 +2025-10-31 10:08:31.775484: Pseudo dice [np.float32(0.9829), np.float32(0.9914), np.float32(0.9953), np.float32(0.8305)] +2025-10-31 10:08:31.777636: Epoch time: 21.99 s +2025-10-31 10:08:32.934581: +2025-10-31 10:08:32.939019: Epoch 98 +2025-10-31 10:08:32.941742: Current learning rate: 0.00911 +2025-10-31 10:08:53.872341: train_loss -0.9761 +2025-10-31 10:08:53.875392: val_loss -0.915 +2025-10-31 10:08:53.877670: Pseudo dice [np.float32(0.983), np.float32(0.9913), np.float32(0.9955), np.float32(0.8336)] +2025-10-31 10:08:53.880211: Epoch time: 20.94 s +2025-10-31 10:08:55.041327: +2025-10-31 10:08:55.047863: Epoch 99 +2025-10-31 10:08:55.049907: Current learning rate: 0.0091 +2025-10-31 10:09:17.357572: train_loss -0.9746 +2025-10-31 10:09:17.369521: val_loss -0.9106 +2025-10-31 10:09:17.372105: Pseudo dice [np.float32(0.9846), np.float32(0.9909), np.float32(0.9949), np.float32(0.8183)] +2025-10-31 10:09:17.374355: Epoch time: 22.32 s +2025-10-31 10:09:20.020401: +2025-10-31 10:09:20.024110: Epoch 100 +2025-10-31 10:09:20.025887: Current learning rate: 0.0091 +2025-10-31 10:09:42.655380: train_loss -0.9775 +2025-10-31 10:09:42.658975: val_loss -0.9062 +2025-10-31 10:09:42.663800: Pseudo dice [np.float32(0.9848), np.float32(0.9907), np.float32(0.9953), np.float32(0.8095)] +2025-10-31 10:09:42.666950: Epoch time: 22.64 s +2025-10-31 10:09:43.708059: +2025-10-31 10:09:43.710418: Epoch 101 +2025-10-31 10:09:43.712425: Current learning rate: 0.00909 +2025-10-31 10:10:06.539800: train_loss -0.98 +2025-10-31 10:10:06.546740: val_loss -0.9124 +2025-10-31 10:10:06.549228: Pseudo dice [np.float32(0.986), np.float32(0.9924), np.float32(0.9956), np.float32(0.8231)] +2025-10-31 10:10:06.552283: Epoch time: 22.83 s +2025-10-31 10:10:07.714089: +2025-10-31 10:10:07.716710: Epoch 102 +2025-10-31 10:10:07.719962: Current learning rate: 0.00908 +2025-10-31 10:10:29.448350: train_loss -0.9782 +2025-10-31 10:10:29.454470: val_loss -0.9066 +2025-10-31 10:10:29.457390: Pseudo dice [np.float32(0.985), np.float32(0.9919), np.float32(0.995), np.float32(0.8136)] +2025-10-31 10:10:29.459445: Epoch time: 21.74 s +2025-10-31 10:10:30.622177: +2025-10-31 10:10:30.624703: Epoch 103 +2025-10-31 10:10:30.627190: Current learning rate: 0.00907 +2025-10-31 10:10:52.132411: train_loss -0.9787 +2025-10-31 10:10:52.134691: val_loss -0.921 +2025-10-31 10:10:52.136280: Pseudo dice [np.float32(0.9845), np.float32(0.9917), np.float32(0.9958), np.float32(0.8417)] +2025-10-31 10:10:52.138254: Epoch time: 21.51 s +2025-10-31 10:10:52.140631: Yayy! New best EMA pseudo Dice: 0.9484000205993652 +2025-10-31 10:10:54.670696: +2025-10-31 10:10:54.673657: Epoch 104 +2025-10-31 10:10:54.676661: Current learning rate: 0.00906 +2025-10-31 10:11:16.083828: train_loss -0.9773 +2025-10-31 10:11:16.090625: val_loss -0.9168 +2025-10-31 10:11:16.092611: Pseudo dice [np.float32(0.9865), np.float32(0.9919), np.float32(0.9955), np.float32(0.8253)] +2025-10-31 10:11:16.094585: Epoch time: 21.41 s +2025-10-31 10:11:16.096343: Yayy! New best EMA pseudo Dice: 0.9485999941825867 +2025-10-31 10:11:18.681316: +2025-10-31 10:11:18.684102: Epoch 105 +2025-10-31 10:11:18.686725: Current learning rate: 0.00905 +2025-10-31 10:11:40.576024: train_loss -0.9801 +2025-10-31 10:11:40.582885: val_loss -0.8971 +2025-10-31 10:11:40.585001: Pseudo dice [np.float32(0.9838), np.float32(0.9914), np.float32(0.9951), np.float32(0.7873)] +2025-10-31 10:11:40.587354: Epoch time: 21.9 s +2025-10-31 10:11:42.290884: +2025-10-31 10:11:42.294553: Epoch 106 +2025-10-31 10:11:42.297566: Current learning rate: 0.00904 +2025-10-31 10:12:03.993983: train_loss -0.9805 +2025-10-31 10:12:03.997430: val_loss -0.9141 +2025-10-31 10:12:04.001039: Pseudo dice [np.float32(0.9842), np.float32(0.9921), np.float32(0.9957), np.float32(0.8328)] +2025-10-31 10:12:04.005282: Epoch time: 21.7 s +2025-10-31 10:12:05.188485: +2025-10-31 10:12:05.191061: Epoch 107 +2025-10-31 10:12:05.193062: Current learning rate: 0.00903 +2025-10-31 10:12:27.851393: train_loss -0.9824 +2025-10-31 10:12:27.856978: val_loss -0.9128 +2025-10-31 10:12:27.861261: Pseudo dice [np.float32(0.9832), np.float32(0.9909), np.float32(0.9956), np.float32(0.8287)] +2025-10-31 10:12:27.863328: Epoch time: 22.66 s +2025-10-31 10:12:29.029877: +2025-10-31 10:12:29.032010: Epoch 108 +2025-10-31 10:12:29.034154: Current learning rate: 0.00902 +2025-10-31 10:12:51.605622: train_loss -0.9799 +2025-10-31 10:12:51.610601: val_loss -0.912 +2025-10-31 10:12:51.612715: Pseudo dice [np.float32(0.9845), np.float32(0.9918), np.float32(0.9954), np.float32(0.8213)] +2025-10-31 10:12:51.615587: Epoch time: 22.58 s +2025-10-31 10:12:52.742194: +2025-10-31 10:12:52.745452: Epoch 109 +2025-10-31 10:12:52.748075: Current learning rate: 0.00901 +2025-10-31 10:13:13.334452: train_loss -0.9807 +2025-10-31 10:13:13.339307: val_loss -0.9041 +2025-10-31 10:13:13.341179: Pseudo dice [np.float32(0.9836), np.float32(0.9913), np.float32(0.9949), np.float32(0.8186)] +2025-10-31 10:13:13.343040: Epoch time: 20.59 s +2025-10-31 10:13:14.635910: +2025-10-31 10:13:14.638012: Epoch 110 +2025-10-31 10:13:14.639979: Current learning rate: 0.009 +2025-10-31 10:13:36.215550: train_loss -0.9832 +2025-10-31 10:13:36.219362: val_loss -0.9082 +2025-10-31 10:13:36.222980: Pseudo dice [np.float32(0.9848), np.float32(0.9915), np.float32(0.9954), np.float32(0.8181)] +2025-10-31 10:13:36.225206: Epoch time: 21.58 s +2025-10-31 10:13:37.363184: +2025-10-31 10:13:37.365134: Epoch 111 +2025-10-31 10:13:37.367005: Current learning rate: 0.009 +2025-10-31 10:14:00.109529: train_loss -0.983 +2025-10-31 10:14:00.117098: val_loss -0.909 +2025-10-31 10:14:00.119768: Pseudo dice [np.float32(0.9845), np.float32(0.9917), np.float32(0.9953), np.float32(0.8175)] +2025-10-31 10:14:00.121649: Epoch time: 22.75 s +2025-10-31 10:14:01.292530: +2025-10-31 10:14:01.295645: Epoch 112 +2025-10-31 10:14:01.298086: Current learning rate: 0.00899 +2025-10-31 10:14:22.965257: train_loss -0.9806 +2025-10-31 10:14:22.968934: val_loss -0.9048 +2025-10-31 10:14:22.970995: Pseudo dice [np.float32(0.9847), np.float32(0.9912), np.float32(0.9948), np.float32(0.8087)] +2025-10-31 10:14:22.972692: Epoch time: 21.67 s +2025-10-31 10:14:24.135817: +2025-10-31 10:14:24.138197: Epoch 113 +2025-10-31 10:14:24.140505: Current learning rate: 0.00898 +2025-10-31 10:14:46.599764: train_loss -0.9794 +2025-10-31 10:14:46.603333: val_loss -0.9057 +2025-10-31 10:14:46.605762: Pseudo dice [np.float32(0.9824), np.float32(0.9913), np.float32(0.9945), np.float32(0.8236)] +2025-10-31 10:14:46.608413: Epoch time: 22.47 s +2025-10-31 10:14:47.813645: +2025-10-31 10:14:47.816123: Epoch 114 +2025-10-31 10:14:47.818244: Current learning rate: 0.00897 +2025-10-31 10:15:10.104834: train_loss -0.9801 +2025-10-31 10:15:10.107839: val_loss -0.9051 +2025-10-31 10:15:10.109630: Pseudo dice [np.float32(0.9846), np.float32(0.9915), np.float32(0.9951), np.float32(0.8103)] +2025-10-31 10:15:10.111672: Epoch time: 22.29 s +2025-10-31 10:15:11.311929: +2025-10-31 10:15:11.314000: Epoch 115 +2025-10-31 10:15:11.315898: Current learning rate: 0.00896 +2025-10-31 10:15:31.957763: train_loss -0.9783 +2025-10-31 10:15:31.961406: val_loss -0.9073 +2025-10-31 10:15:31.963621: Pseudo dice [np.float32(0.9849), np.float32(0.9923), np.float32(0.9956), np.float32(0.8148)] +2025-10-31 10:15:31.965690: Epoch time: 20.65 s +2025-10-31 10:15:33.143748: +2025-10-31 10:15:33.145691: Epoch 116 +2025-10-31 10:15:33.147567: Current learning rate: 0.00895 +2025-10-31 10:15:55.715510: train_loss -0.9713 +2025-10-31 10:15:55.718937: val_loss -0.8996 +2025-10-31 10:15:55.720888: Pseudo dice [np.float32(0.9844), np.float32(0.9915), np.float32(0.9945), np.float32(0.7776)] +2025-10-31 10:15:55.722899: Epoch time: 22.57 s +2025-10-31 10:15:56.906761: +2025-10-31 10:15:56.911223: Epoch 117 +2025-10-31 10:15:56.915848: Current learning rate: 0.00894 +2025-10-31 10:16:18.490258: train_loss -0.974 +2025-10-31 10:16:18.493551: val_loss -0.9108 +2025-10-31 10:16:18.495345: Pseudo dice [np.float32(0.9838), np.float32(0.9913), np.float32(0.9956), np.float32(0.8184)] +2025-10-31 10:16:18.496994: Epoch time: 21.59 s +2025-10-31 10:16:19.667449: +2025-10-31 10:16:19.670142: Epoch 118 +2025-10-31 10:16:19.673666: Current learning rate: 0.00893 +2025-10-31 10:16:41.466949: train_loss -0.9754 +2025-10-31 10:16:41.470545: val_loss -0.9109 +2025-10-31 10:16:41.472745: Pseudo dice [np.float32(0.9856), np.float32(0.9917), np.float32(0.9954), np.float32(0.8165)] +2025-10-31 10:16:41.475216: Epoch time: 21.8 s +2025-10-31 10:16:42.999514: +2025-10-31 10:16:43.003418: Epoch 119 +2025-10-31 10:16:43.005471: Current learning rate: 0.00892 +2025-10-31 10:17:06.071278: train_loss -0.9781 +2025-10-31 10:17:06.074624: val_loss -0.9253 +2025-10-31 10:17:06.077196: Pseudo dice [np.float32(0.9845), np.float32(0.9919), np.float32(0.9965), np.float32(0.8531)] +2025-10-31 10:17:06.079479: Epoch time: 23.07 s +2025-10-31 10:17:07.210975: +2025-10-31 10:17:07.213082: Epoch 120 +2025-10-31 10:17:07.215202: Current learning rate: 0.00891 +2025-10-31 10:17:30.088336: train_loss -0.9788 +2025-10-31 10:17:30.091899: val_loss -0.9167 +2025-10-31 10:17:30.093846: Pseudo dice [np.float32(0.9853), np.float32(0.9926), np.float32(0.9957), np.float32(0.8229)] +2025-10-31 10:17:30.097319: Epoch time: 22.88 s +2025-10-31 10:17:31.247814: +2025-10-31 10:17:31.250790: Epoch 121 +2025-10-31 10:17:31.252950: Current learning rate: 0.0089 +2025-10-31 10:17:51.606210: train_loss -0.9779 +2025-10-31 10:17:51.608171: val_loss -0.9069 +2025-10-31 10:17:51.609515: Pseudo dice [np.float32(0.9853), np.float32(0.9908), np.float32(0.995), np.float32(0.802)] +2025-10-31 10:17:51.611253: Epoch time: 20.36 s +2025-10-31 10:17:52.676863: +2025-10-31 10:17:52.679664: Epoch 122 +2025-10-31 10:17:52.681619: Current learning rate: 0.00889 +2025-10-31 10:18:14.927395: train_loss -0.9796 +2025-10-31 10:18:14.932188: val_loss -0.9026 +2025-10-31 10:18:14.934073: Pseudo dice [np.float32(0.9853), np.float32(0.9917), np.float32(0.9949), np.float32(0.7986)] +2025-10-31 10:18:14.936023: Epoch time: 22.25 s +2025-10-31 10:18:16.113734: +2025-10-31 10:18:16.115510: Epoch 123 +2025-10-31 10:18:16.117152: Current learning rate: 0.00889 +2025-10-31 10:18:37.640941: train_loss -0.9795 +2025-10-31 10:18:37.648153: val_loss -0.9131 +2025-10-31 10:18:37.650870: Pseudo dice [np.float32(0.9847), np.float32(0.9905), np.float32(0.9954), np.float32(0.8292)] +2025-10-31 10:18:37.652845: Epoch time: 21.53 s +2025-10-31 10:18:38.729055: +2025-10-31 10:18:38.731465: Epoch 124 +2025-10-31 10:18:38.733491: Current learning rate: 0.00888 +2025-10-31 10:19:00.511410: train_loss -0.9801 +2025-10-31 10:19:00.514122: val_loss -0.915 +2025-10-31 10:19:00.516529: Pseudo dice [np.float32(0.9847), np.float32(0.9919), np.float32(0.9957), np.float32(0.8266)] +2025-10-31 10:19:00.518592: Epoch time: 21.78 s +2025-10-31 10:19:01.746121: +2025-10-31 10:19:01.750642: Epoch 125 +2025-10-31 10:19:01.752669: Current learning rate: 0.00887 +2025-10-31 10:19:23.299263: train_loss -0.9683 +2025-10-31 10:19:23.305989: val_loss -0.9152 +2025-10-31 10:19:23.308172: Pseudo dice [np.float32(0.9848), np.float32(0.9914), np.float32(0.9957), np.float32(0.8239)] +2025-10-31 10:19:23.310321: Epoch time: 21.55 s +2025-10-31 10:19:24.385050: +2025-10-31 10:19:24.392278: Epoch 126 +2025-10-31 10:19:24.394658: Current learning rate: 0.00886 +2025-10-31 10:19:46.843455: train_loss -0.9578 +2025-10-31 10:19:46.848378: val_loss -0.916 +2025-10-31 10:19:46.850459: Pseudo dice [np.float32(0.9824), np.float32(0.9908), np.float32(0.995), np.float32(0.8276)] +2025-10-31 10:19:46.852565: Epoch time: 22.46 s +2025-10-31 10:19:47.932528: +2025-10-31 10:19:47.934800: Epoch 127 +2025-10-31 10:19:47.937046: Current learning rate: 0.00885 +2025-10-31 10:20:10.193836: train_loss -0.9595 +2025-10-31 10:20:10.196947: val_loss -0.9155 +2025-10-31 10:20:10.199667: Pseudo dice [np.float32(0.9849), np.float32(0.9921), np.float32(0.9952), np.float32(0.8173)] +2025-10-31 10:20:10.201587: Epoch time: 22.26 s +2025-10-31 10:20:11.268997: +2025-10-31 10:20:11.271086: Epoch 128 +2025-10-31 10:20:11.273237: Current learning rate: 0.00884 +2025-10-31 10:20:32.652542: train_loss -0.9679 +2025-10-31 10:20:32.658284: val_loss -0.9127 +2025-10-31 10:20:32.660794: Pseudo dice [np.float32(0.9854), np.float32(0.9911), np.float32(0.9951), np.float32(0.8166)] +2025-10-31 10:20:32.663107: Epoch time: 21.38 s +2025-10-31 10:20:33.747831: +2025-10-31 10:20:33.749888: Epoch 129 +2025-10-31 10:20:33.751641: Current learning rate: 0.00883 +2025-10-31 10:20:55.844220: train_loss -0.9744 +2025-10-31 10:20:55.847900: val_loss -0.9139 +2025-10-31 10:20:55.850173: Pseudo dice [np.float32(0.9842), np.float32(0.9911), np.float32(0.9953), np.float32(0.8274)] +2025-10-31 10:20:55.852070: Epoch time: 22.1 s +2025-10-31 10:20:56.899482: +2025-10-31 10:20:56.901389: Epoch 130 +2025-10-31 10:20:56.903122: Current learning rate: 0.00882 +2025-10-31 10:21:18.680433: train_loss -0.9779 +2025-10-31 10:21:18.683326: val_loss -0.9068 +2025-10-31 10:21:18.685195: Pseudo dice [np.float32(0.9844), np.float32(0.9913), np.float32(0.9953), np.float32(0.8004)] +2025-10-31 10:21:18.686912: Epoch time: 21.78 s +2025-10-31 10:21:19.760535: +2025-10-31 10:21:19.763462: Epoch 131 +2025-10-31 10:21:19.766214: Current learning rate: 0.00881 +2025-10-31 10:21:41.475149: train_loss -0.9783 +2025-10-31 10:21:41.478824: val_loss -0.9014 +2025-10-31 10:21:41.481086: Pseudo dice [np.float32(0.9856), np.float32(0.9917), np.float32(0.9946), np.float32(0.7868)] +2025-10-31 10:21:41.483439: Epoch time: 21.72 s +2025-10-31 10:21:43.069213: +2025-10-31 10:21:43.073649: Epoch 132 +2025-10-31 10:21:43.075428: Current learning rate: 0.0088 +2025-10-31 10:22:05.602122: train_loss -0.98 +2025-10-31 10:22:05.611397: val_loss -0.917 +2025-10-31 10:22:05.613746: Pseudo dice [np.float32(0.9853), np.float32(0.9923), np.float32(0.9957), np.float32(0.8407)] +2025-10-31 10:22:05.616040: Epoch time: 22.53 s +2025-10-31 10:22:06.811282: +2025-10-31 10:22:06.815802: Epoch 133 +2025-10-31 10:22:06.820358: Current learning rate: 0.00879 +2025-10-31 10:22:29.132001: train_loss -0.9806 +2025-10-31 10:22:29.134966: val_loss -0.9086 +2025-10-31 10:22:29.137924: Pseudo dice [np.float32(0.9856), np.float32(0.9923), np.float32(0.9955), np.float32(0.8126)] +2025-10-31 10:22:29.141611: Epoch time: 22.32 s +2025-10-31 10:22:30.334020: +2025-10-31 10:22:30.336863: Epoch 134 +2025-10-31 10:22:30.338988: Current learning rate: 0.00879 +2025-10-31 10:22:50.593421: train_loss -0.9789 +2025-10-31 10:22:50.598911: val_loss -0.9085 +2025-10-31 10:22:50.602868: Pseudo dice [np.float32(0.985), np.float32(0.992), np.float32(0.9957), np.float32(0.8194)] +2025-10-31 10:22:50.605661: Epoch time: 20.26 s +2025-10-31 10:22:51.721097: +2025-10-31 10:22:51.723757: Epoch 135 +2025-10-31 10:22:51.727438: Current learning rate: 0.00878 +2025-10-31 10:23:13.826786: train_loss -0.9797 +2025-10-31 10:23:13.829624: val_loss -0.9173 +2025-10-31 10:23:13.831363: Pseudo dice [np.float32(0.9856), np.float32(0.9921), np.float32(0.9959), np.float32(0.8358)] +2025-10-31 10:23:13.832985: Epoch time: 22.11 s +2025-10-31 10:23:14.951720: +2025-10-31 10:23:14.954248: Epoch 136 +2025-10-31 10:23:14.956661: Current learning rate: 0.00877 +2025-10-31 10:23:36.893959: train_loss -0.9794 +2025-10-31 10:23:36.897217: val_loss -0.9223 +2025-10-31 10:23:36.899633: Pseudo dice [np.float32(0.9863), np.float32(0.9928), np.float32(0.9958), np.float32(0.8413)] +2025-10-31 10:23:36.901707: Epoch time: 21.94 s +2025-10-31 10:23:37.938113: +2025-10-31 10:23:37.941025: Epoch 137 +2025-10-31 10:23:37.944786: Current learning rate: 0.00876 +2025-10-31 10:24:01.012878: train_loss -0.9767 +2025-10-31 10:24:01.016927: val_loss -0.9161 +2025-10-31 10:24:01.019304: Pseudo dice [np.float32(0.9843), np.float32(0.9912), np.float32(0.996), np.float32(0.8345)] +2025-10-31 10:24:01.021045: Epoch time: 23.08 s +2025-10-31 10:24:01.022888: Yayy! New best EMA pseudo Dice: 0.9487000107765198 +2025-10-31 10:24:03.419483: +2025-10-31 10:24:03.423497: Epoch 138 +2025-10-31 10:24:03.425492: Current learning rate: 0.00875 +2025-10-31 10:24:25.163769: train_loss -0.9794 +2025-10-31 10:24:25.171491: val_loss -0.9085 +2025-10-31 10:24:25.174065: Pseudo dice [np.float32(0.9842), np.float32(0.9915), np.float32(0.9957), np.float32(0.8114)] +2025-10-31 10:24:25.176094: Epoch time: 21.75 s +2025-10-31 10:24:26.307645: +2025-10-31 10:24:26.310023: Epoch 139 +2025-10-31 10:24:26.312182: Current learning rate: 0.00874 +2025-10-31 10:24:48.661924: train_loss -0.9826 +2025-10-31 10:24:48.664883: val_loss -0.8975 +2025-10-31 10:24:48.667281: Pseudo dice [np.float32(0.9869), np.float32(0.993), np.float32(0.9949), np.float32(0.7781)] +2025-10-31 10:24:48.669482: Epoch time: 22.36 s +2025-10-31 10:24:49.820417: +2025-10-31 10:24:49.823416: Epoch 140 +2025-10-31 10:24:49.825366: Current learning rate: 0.00873 +2025-10-31 10:25:10.763665: train_loss -0.9826 +2025-10-31 10:25:10.766890: val_loss -0.9079 +2025-10-31 10:25:10.769096: Pseudo dice [np.float32(0.9872), np.float32(0.9923), np.float32(0.9951), np.float32(0.8085)] +2025-10-31 10:25:10.771800: Epoch time: 20.94 s +2025-10-31 10:25:11.733465: +2025-10-31 10:25:11.736356: Epoch 141 +2025-10-31 10:25:11.738681: Current learning rate: 0.00872 +2025-10-31 10:25:33.314860: train_loss -0.9824 +2025-10-31 10:25:33.317834: val_loss -0.9049 +2025-10-31 10:25:33.319329: Pseudo dice [np.float32(0.9862), np.float32(0.9928), np.float32(0.9954), np.float32(0.7973)] +2025-10-31 10:25:33.321154: Epoch time: 21.58 s +2025-10-31 10:25:34.500058: +2025-10-31 10:25:34.502139: Epoch 142 +2025-10-31 10:25:34.503765: Current learning rate: 0.00871 +2025-10-31 10:25:56.234457: train_loss -0.9825 +2025-10-31 10:25:56.237006: val_loss -0.9086 +2025-10-31 10:25:56.238919: Pseudo dice [np.float32(0.9853), np.float32(0.9916), np.float32(0.9952), np.float32(0.8171)] +2025-10-31 10:25:56.240901: Epoch time: 21.74 s +2025-10-31 10:25:57.857207: +2025-10-31 10:25:57.859488: Epoch 143 +2025-10-31 10:25:57.863389: Current learning rate: 0.0087 +2025-10-31 10:26:20.339255: train_loss -0.9827 +2025-10-31 10:26:20.342998: val_loss -0.91 +2025-10-31 10:26:20.345418: Pseudo dice [np.float32(0.9856), np.float32(0.9919), np.float32(0.9955), np.float32(0.8232)] +2025-10-31 10:26:20.348412: Epoch time: 22.48 s +2025-10-31 10:26:21.433245: +2025-10-31 10:26:21.435664: Epoch 144 +2025-10-31 10:26:21.437841: Current learning rate: 0.00869 +2025-10-31 10:26:43.973949: train_loss -0.9825 +2025-10-31 10:26:43.981179: val_loss -0.9062 +2025-10-31 10:26:43.983212: Pseudo dice [np.float32(0.9847), np.float32(0.9921), np.float32(0.9953), np.float32(0.8098)] +2025-10-31 10:26:43.985329: Epoch time: 22.54 s +2025-10-31 10:26:45.243690: +2025-10-31 10:26:45.248189: Epoch 145 +2025-10-31 10:26:45.252847: Current learning rate: 0.00868 +2025-10-31 10:27:06.608681: train_loss -0.982 +2025-10-31 10:27:06.612136: val_loss -0.9165 +2025-10-31 10:27:06.614345: Pseudo dice [np.float32(0.9854), np.float32(0.9921), np.float32(0.9958), np.float32(0.8382)] +2025-10-31 10:27:06.616623: Epoch time: 21.37 s +2025-10-31 10:27:07.808071: +2025-10-31 10:27:07.810686: Epoch 146 +2025-10-31 10:27:07.813341: Current learning rate: 0.00868 +2025-10-31 10:27:28.691638: train_loss -0.9831 +2025-10-31 10:27:28.695012: val_loss -0.902 +2025-10-31 10:27:28.696765: Pseudo dice [np.float32(0.9852), np.float32(0.9919), np.float32(0.9954), np.float32(0.8065)] +2025-10-31 10:27:28.698625: Epoch time: 20.88 s +2025-10-31 10:27:29.826088: +2025-10-31 10:27:29.828445: Epoch 147 +2025-10-31 10:27:29.830632: Current learning rate: 0.00867 +2025-10-31 10:27:51.383667: train_loss -0.9834 +2025-10-31 10:27:51.387114: val_loss -0.9063 +2025-10-31 10:27:51.389040: Pseudo dice [np.float32(0.9863), np.float32(0.9924), np.float32(0.9953), np.float32(0.8194)] +2025-10-31 10:27:51.391191: Epoch time: 21.56 s +2025-10-31 10:27:52.585438: +2025-10-31 10:27:52.587637: Epoch 148 +2025-10-31 10:27:52.589548: Current learning rate: 0.00866 +2025-10-31 10:28:14.653116: train_loss -0.984 +2025-10-31 10:28:14.657617: val_loss -0.9114 +2025-10-31 10:28:14.659390: Pseudo dice [np.float32(0.9851), np.float32(0.9925), np.float32(0.9955), np.float32(0.8296)] +2025-10-31 10:28:14.661359: Epoch time: 22.07 s +2025-10-31 10:28:15.891908: +2025-10-31 10:28:15.894128: Epoch 149 +2025-10-31 10:28:15.896194: Current learning rate: 0.00865 +2025-10-31 10:28:36.900020: train_loss -0.9836 +2025-10-31 10:28:36.902602: val_loss -0.9047 +2025-10-31 10:28:36.904522: Pseudo dice [np.float32(0.9851), np.float32(0.9926), np.float32(0.995), np.float32(0.8065)] +2025-10-31 10:28:36.907037: Epoch time: 21.01 s +2025-10-31 10:28:39.399779: +2025-10-31 10:28:39.402219: Epoch 150 +2025-10-31 10:28:39.403982: Current learning rate: 0.00864 +2025-10-31 10:29:02.009546: train_loss -0.9849 +2025-10-31 10:29:02.013894: val_loss -0.8984 +2025-10-31 10:29:02.016170: Pseudo dice [np.float32(0.9858), np.float32(0.9928), np.float32(0.9955), np.float32(0.7934)] +2025-10-31 10:29:02.018323: Epoch time: 22.61 s +2025-10-31 10:29:03.220783: +2025-10-31 10:29:03.223124: Epoch 151 +2025-10-31 10:29:03.225158: Current learning rate: 0.00863 +2025-10-31 10:29:24.598679: train_loss -0.9846 +2025-10-31 10:29:24.601630: val_loss -0.9035 +2025-10-31 10:29:24.603705: Pseudo dice [np.float32(0.9844), np.float32(0.9924), np.float32(0.9957), np.float32(0.8155)] +2025-10-31 10:29:24.605679: Epoch time: 21.38 s +2025-10-31 10:29:25.752781: +2025-10-31 10:29:25.757181: Epoch 152 +2025-10-31 10:29:25.759067: Current learning rate: 0.00862 +2025-10-31 10:29:47.339077: train_loss -0.9837 +2025-10-31 10:29:47.349207: val_loss -0.9094 +2025-10-31 10:29:47.351837: Pseudo dice [np.float32(0.9857), np.float32(0.992), np.float32(0.9955), np.float32(0.8226)] +2025-10-31 10:29:47.354218: Epoch time: 21.59 s +2025-10-31 10:29:48.566383: +2025-10-31 10:29:48.569405: Epoch 153 +2025-10-31 10:29:48.572117: Current learning rate: 0.00861 +2025-10-31 10:30:11.757652: train_loss -0.9843 +2025-10-31 10:30:11.761054: val_loss -0.8954 +2025-10-31 10:30:11.763049: Pseudo dice [np.float32(0.9867), np.float32(0.993), np.float32(0.9948), np.float32(0.791)] +2025-10-31 10:30:11.765210: Epoch time: 23.19 s +2025-10-31 10:30:13.026706: +2025-10-31 10:30:13.028948: Epoch 154 +2025-10-31 10:30:13.030528: Current learning rate: 0.0086 +2025-10-31 10:30:34.767141: train_loss -0.984 +2025-10-31 10:30:34.771024: val_loss -0.898 +2025-10-31 10:30:34.773856: Pseudo dice [np.float32(0.9853), np.float32(0.9927), np.float32(0.9952), np.float32(0.7965)] +2025-10-31 10:30:34.775663: Epoch time: 21.74 s +2025-10-31 10:30:35.977180: +2025-10-31 10:30:35.979576: Epoch 155 +2025-10-31 10:30:35.981401: Current learning rate: 0.00859 +2025-10-31 10:30:57.420262: train_loss -0.9842 +2025-10-31 10:30:57.423297: val_loss -0.901 +2025-10-31 10:30:57.425257: Pseudo dice [np.float32(0.9861), np.float32(0.9899), np.float32(0.9944), np.float32(0.8065)] +2025-10-31 10:30:57.428046: Epoch time: 21.44 s +2025-10-31 10:30:59.025023: +2025-10-31 10:30:59.028207: Epoch 156 +2025-10-31 10:30:59.030566: Current learning rate: 0.00858 +2025-10-31 10:31:21.622572: train_loss -0.9855 +2025-10-31 10:31:21.626487: val_loss -0.8934 +2025-10-31 10:31:21.628374: Pseudo dice [np.float32(0.9867), np.float32(0.9925), np.float32(0.995), np.float32(0.787)] +2025-10-31 10:31:21.630613: Epoch time: 22.6 s +2025-10-31 10:31:22.727971: +2025-10-31 10:31:22.729828: Epoch 157 +2025-10-31 10:31:22.731959: Current learning rate: 0.00858 +2025-10-31 10:31:44.685422: train_loss -0.9839 +2025-10-31 10:31:44.688815: val_loss -0.9007 +2025-10-31 10:31:44.690862: Pseudo dice [np.float32(0.9866), np.float32(0.9924), np.float32(0.9952), np.float32(0.8032)] +2025-10-31 10:31:44.692926: Epoch time: 21.96 s +2025-10-31 10:31:45.972220: +2025-10-31 10:31:45.974339: Epoch 158 +2025-10-31 10:31:45.976135: Current learning rate: 0.00857 +2025-10-31 10:32:06.232688: train_loss -0.982 +2025-10-31 10:32:06.237618: val_loss -0.9023 +2025-10-31 10:32:06.240887: Pseudo dice [np.float32(0.9854), np.float32(0.9923), np.float32(0.9951), np.float32(0.8066)] +2025-10-31 10:32:06.243851: Epoch time: 20.26 s +2025-10-31 10:32:07.514186: +2025-10-31 10:32:07.518063: Epoch 159 +2025-10-31 10:32:07.521655: Current learning rate: 0.00856 +2025-10-31 10:32:29.324102: train_loss -0.9828 +2025-10-31 10:32:29.330962: val_loss -0.895 +2025-10-31 10:32:29.332783: Pseudo dice [np.float32(0.9859), np.float32(0.9932), np.float32(0.9952), np.float32(0.7855)] +2025-10-31 10:32:29.334603: Epoch time: 21.81 s +2025-10-31 10:32:30.565345: +2025-10-31 10:32:30.569093: Epoch 160 +2025-10-31 10:32:30.571827: Current learning rate: 0.00855 +2025-10-31 10:32:51.574498: train_loss -0.9834 +2025-10-31 10:32:51.577826: val_loss -0.9102 +2025-10-31 10:32:51.580240: Pseudo dice [np.float32(0.9856), np.float32(0.993), np.float32(0.9957), np.float32(0.8154)] +2025-10-31 10:32:51.581934: Epoch time: 21.01 s +2025-10-31 10:32:52.883428: +2025-10-31 10:32:52.885741: Epoch 161 +2025-10-31 10:32:52.888105: Current learning rate: 0.00854 +2025-10-31 10:33:15.362199: train_loss -0.9814 +2025-10-31 10:33:15.366470: val_loss -0.9009 +2025-10-31 10:33:15.368501: Pseudo dice [np.float32(0.9834), np.float32(0.9921), np.float32(0.9955), np.float32(0.8079)] +2025-10-31 10:33:15.370629: Epoch time: 22.48 s +2025-10-31 10:33:16.609333: +2025-10-31 10:33:16.612382: Epoch 162 +2025-10-31 10:33:16.615043: Current learning rate: 0.00853 +2025-10-31 10:33:38.911018: train_loss -0.9834 +2025-10-31 10:33:38.914613: val_loss -0.8975 +2025-10-31 10:33:38.916926: Pseudo dice [np.float32(0.986), np.float32(0.9925), np.float32(0.9949), np.float32(0.793)] +2025-10-31 10:33:38.918795: Epoch time: 22.3 s +2025-10-31 10:33:39.962609: +2025-10-31 10:33:39.964864: Epoch 163 +2025-10-31 10:33:39.966630: Current learning rate: 0.00852 +2025-10-31 10:34:02.155571: train_loss -0.9851 +2025-10-31 10:34:02.158030: val_loss -0.8993 +2025-10-31 10:34:02.159891: Pseudo dice [np.float32(0.985), np.float32(0.9921), np.float32(0.9951), np.float32(0.8029)] +2025-10-31 10:34:02.161711: Epoch time: 22.19 s +2025-10-31 10:34:03.187345: +2025-10-31 10:34:03.189443: Epoch 164 +2025-10-31 10:34:03.191238: Current learning rate: 0.00851 +2025-10-31 10:34:23.957008: train_loss -0.9833 +2025-10-31 10:34:23.960365: val_loss -0.9096 +2025-10-31 10:34:23.962455: Pseudo dice [np.float32(0.9873), np.float32(0.9928), np.float32(0.9957), np.float32(0.8189)] +2025-10-31 10:34:23.964462: Epoch time: 20.77 s +2025-10-31 10:34:25.139891: +2025-10-31 10:34:25.142951: Epoch 165 +2025-10-31 10:34:25.145032: Current learning rate: 0.0085 +2025-10-31 10:34:47.226613: train_loss -0.9845 +2025-10-31 10:34:47.230078: val_loss -0.9031 +2025-10-31 10:34:47.231771: Pseudo dice [np.float32(0.986), np.float32(0.992), np.float32(0.9952), np.float32(0.8086)] +2025-10-31 10:34:47.233563: Epoch time: 22.09 s +2025-10-31 10:34:48.427406: +2025-10-31 10:34:48.429555: Epoch 166 +2025-10-31 10:34:48.431538: Current learning rate: 0.00849 +2025-10-31 10:35:11.154269: train_loss -0.9854 +2025-10-31 10:35:11.156338: val_loss -0.8986 +2025-10-31 10:35:11.158193: Pseudo dice [np.float32(0.9867), np.float32(0.9922), np.float32(0.9952), np.float32(0.7948)] +2025-10-31 10:35:11.160512: Epoch time: 22.73 s +2025-10-31 10:35:12.354871: +2025-10-31 10:35:12.357450: Epoch 167 +2025-10-31 10:35:12.359753: Current learning rate: 0.00848 +2025-10-31 10:35:33.897636: train_loss -0.9846 +2025-10-31 10:35:33.900536: val_loss -0.9011 +2025-10-31 10:35:33.902438: Pseudo dice [np.float32(0.9847), np.float32(0.9919), np.float32(0.9952), np.float32(0.8058)] +2025-10-31 10:35:33.904548: Epoch time: 21.54 s +2025-10-31 10:35:35.866255: +2025-10-31 10:35:35.868919: Epoch 168 +2025-10-31 10:35:35.870687: Current learning rate: 0.00847 +2025-10-31 10:35:56.786756: train_loss -0.9851 +2025-10-31 10:35:56.790488: val_loss -0.9099 +2025-10-31 10:35:56.792687: Pseudo dice [np.float32(0.9853), np.float32(0.9925), np.float32(0.9954), np.float32(0.8268)] +2025-10-31 10:35:56.794822: Epoch time: 20.92 s +2025-10-31 10:35:57.988641: +2025-10-31 10:35:57.990987: Epoch 169 +2025-10-31 10:35:57.992837: Current learning rate: 0.00847 +2025-10-31 10:36:20.423177: train_loss -0.9835 +2025-10-31 10:36:20.426308: val_loss -0.9113 +2025-10-31 10:36:20.428240: Pseudo dice [np.float32(0.9842), np.float32(0.9924), np.float32(0.9956), np.float32(0.8225)] +2025-10-31 10:36:20.430166: Epoch time: 22.44 s +2025-10-31 10:36:21.739781: +2025-10-31 10:36:21.743871: Epoch 170 +2025-10-31 10:36:21.746690: Current learning rate: 0.00846 +2025-10-31 10:36:42.724386: train_loss -0.984 +2025-10-31 10:36:42.728047: val_loss -0.9039 +2025-10-31 10:36:42.730641: Pseudo dice [np.float32(0.9849), np.float32(0.9917), np.float32(0.9952), np.float32(0.8103)] +2025-10-31 10:36:42.733374: Epoch time: 20.99 s +2025-10-31 10:36:44.121986: +2025-10-31 10:36:44.124007: Epoch 171 +2025-10-31 10:36:44.125856: Current learning rate: 0.00845 +2025-10-31 10:37:05.991131: train_loss -0.9842 +2025-10-31 10:37:05.995161: val_loss -0.9068 +2025-10-31 10:37:05.998722: Pseudo dice [np.float32(0.9855), np.float32(0.9929), np.float32(0.9958), np.float32(0.8168)] +2025-10-31 10:37:06.001424: Epoch time: 21.87 s +2025-10-31 10:37:07.241575: +2025-10-31 10:37:07.246106: Epoch 172 +2025-10-31 10:37:07.250000: Current learning rate: 0.00844 +2025-10-31 10:37:30.314639: train_loss -0.9849 +2025-10-31 10:37:30.317020: val_loss -0.9099 +2025-10-31 10:37:30.318663: Pseudo dice [np.float32(0.9857), np.float32(0.9933), np.float32(0.9958), np.float32(0.8187)] +2025-10-31 10:37:30.321941: Epoch time: 23.08 s +2025-10-31 10:37:31.493546: +2025-10-31 10:37:31.496037: Epoch 173 +2025-10-31 10:37:31.498218: Current learning rate: 0.00843 +2025-10-31 10:37:53.626025: train_loss -0.9865 +2025-10-31 10:37:53.629833: val_loss -0.8964 +2025-10-31 10:37:53.631827: Pseudo dice [np.float32(0.9858), np.float32(0.9926), np.float32(0.9946), np.float32(0.7936)] +2025-10-31 10:37:53.633722: Epoch time: 22.13 s +2025-10-31 10:37:55.183297: +2025-10-31 10:37:55.185892: Epoch 174 +2025-10-31 10:37:55.188234: Current learning rate: 0.00842 +2025-10-31 10:38:17.043693: train_loss -0.9864 +2025-10-31 10:38:17.049027: val_loss -0.9036 +2025-10-31 10:38:17.051781: Pseudo dice [np.float32(0.986), np.float32(0.9934), np.float32(0.9957), np.float32(0.8109)] +2025-10-31 10:38:17.055306: Epoch time: 21.86 s +2025-10-31 10:38:18.263478: +2025-10-31 10:38:18.266365: Epoch 175 +2025-10-31 10:38:18.270857: Current learning rate: 0.00841 +2025-10-31 10:38:41.574654: train_loss -0.9854 +2025-10-31 10:38:41.576867: val_loss -0.9039 +2025-10-31 10:38:41.578575: Pseudo dice [np.float32(0.9861), np.float32(0.9928), np.float32(0.9953), np.float32(0.8097)] +2025-10-31 10:38:41.580199: Epoch time: 23.31 s +2025-10-31 10:38:42.610066: +2025-10-31 10:38:42.612043: Epoch 176 +2025-10-31 10:38:42.613781: Current learning rate: 0.0084 +2025-10-31 10:39:03.616791: train_loss -0.9861 +2025-10-31 10:39:03.621541: val_loss -0.9002 +2025-10-31 10:39:03.623844: Pseudo dice [np.float32(0.9868), np.float32(0.993), np.float32(0.995), np.float32(0.8046)] +2025-10-31 10:39:03.625967: Epoch time: 21.01 s +2025-10-31 10:39:05.056527: +2025-10-31 10:39:05.059530: Epoch 177 +2025-10-31 10:39:05.061979: Current learning rate: 0.00839 +2025-10-31 10:39:27.828071: train_loss -0.9852 +2025-10-31 10:39:27.832185: val_loss -0.9032 +2025-10-31 10:39:27.834350: Pseudo dice [np.float32(0.9863), np.float32(0.9929), np.float32(0.9952), np.float32(0.8032)] +2025-10-31 10:39:27.836565: Epoch time: 22.77 s +2025-10-31 10:39:29.042073: +2025-10-31 10:39:29.044981: Epoch 178 +2025-10-31 10:39:29.047523: Current learning rate: 0.00838 +2025-10-31 10:39:52.001135: train_loss -0.9849 +2025-10-31 10:39:52.004939: val_loss -0.9003 +2025-10-31 10:39:52.007437: Pseudo dice [np.float32(0.9855), np.float32(0.9929), np.float32(0.9957), np.float32(0.8029)] +2025-10-31 10:39:52.009780: Epoch time: 22.96 s +2025-10-31 10:39:53.097677: +2025-10-31 10:39:53.101043: Epoch 179 +2025-10-31 10:39:53.103396: Current learning rate: 0.00837 +2025-10-31 10:40:14.998234: train_loss -0.9854 +2025-10-31 10:40:15.002289: val_loss -0.8867 +2025-10-31 10:40:15.004815: Pseudo dice [np.float32(0.9858), np.float32(0.9925), np.float32(0.9948), np.float32(0.7748)] +2025-10-31 10:40:15.007020: Epoch time: 21.9 s +2025-10-31 10:40:16.976218: +2025-10-31 10:40:16.979070: Epoch 180 +2025-10-31 10:40:16.981602: Current learning rate: 0.00836 +2025-10-31 10:40:39.107469: train_loss -0.9845 +2025-10-31 10:40:39.118562: val_loss -0.8919 +2025-10-31 10:40:39.123456: Pseudo dice [np.float32(0.9844), np.float32(0.9922), np.float32(0.9951), np.float32(0.791)] +2025-10-31 10:40:39.129751: Epoch time: 22.13 s +2025-10-31 10:40:40.374322: +2025-10-31 10:40:40.376859: Epoch 181 +2025-10-31 10:40:40.378815: Current learning rate: 0.00836 +2025-10-31 10:41:01.389335: train_loss -0.986 +2025-10-31 10:41:01.392352: val_loss -0.8995 +2025-10-31 10:41:01.396430: Pseudo dice [np.float32(0.9855), np.float32(0.9925), np.float32(0.9953), np.float32(0.8058)] +2025-10-31 10:41:01.400063: Epoch time: 21.02 s +2025-10-31 10:41:02.516769: +2025-10-31 10:41:02.519470: Epoch 182 +2025-10-31 10:41:02.521932: Current learning rate: 0.00835 +2025-10-31 10:41:23.518724: train_loss -0.9857 +2025-10-31 10:41:23.521739: val_loss -0.8923 +2025-10-31 10:41:23.523919: Pseudo dice [np.float32(0.9864), np.float32(0.9925), np.float32(0.9947), np.float32(0.7878)] +2025-10-31 10:41:23.527239: Epoch time: 21.0 s +2025-10-31 10:41:24.523449: +2025-10-31 10:41:24.525796: Epoch 183 +2025-10-31 10:41:24.527993: Current learning rate: 0.00834 +2025-10-31 10:41:46.112937: train_loss -0.9807 +2025-10-31 10:41:46.126038: val_loss -0.905 +2025-10-31 10:41:46.131964: Pseudo dice [np.float32(0.985), np.float32(0.9924), np.float32(0.9955), np.float32(0.8098)] +2025-10-31 10:41:46.134940: Epoch time: 21.59 s +2025-10-31 10:41:47.278179: +2025-10-31 10:41:47.285814: Epoch 184 +2025-10-31 10:41:47.296638: Current learning rate: 0.00833 +2025-10-31 10:42:09.356656: train_loss -0.9824 +2025-10-31 10:42:09.367488: val_loss -0.9185 +2025-10-31 10:42:09.375057: Pseudo dice [np.float32(0.9851), np.float32(0.9925), np.float32(0.9958), np.float32(0.8461)] +2025-10-31 10:42:09.385575: Epoch time: 22.08 s +2025-10-31 10:42:10.400459: +2025-10-31 10:42:10.403480: Epoch 185 +2025-10-31 10:42:10.406196: Current learning rate: 0.00832 +2025-10-31 10:42:32.900235: train_loss -0.981 +2025-10-31 10:42:32.913078: val_loss -0.8984 +2025-10-31 10:42:32.925616: Pseudo dice [np.float32(0.9852), np.float32(0.992), np.float32(0.995), np.float32(0.8027)] +2025-10-31 10:42:32.937155: Epoch time: 22.5 s +2025-10-31 10:42:34.151597: +2025-10-31 10:42:34.154272: Epoch 186 +2025-10-31 10:42:34.157444: Current learning rate: 0.00831 +2025-10-31 10:42:56.369756: train_loss -0.9824 +2025-10-31 10:42:56.383518: val_loss -0.8927 +2025-10-31 10:42:56.391523: Pseudo dice [np.float32(0.9858), np.float32(0.9921), np.float32(0.9946), np.float32(0.7831)] +2025-10-31 10:42:56.400081: Epoch time: 22.22 s +2025-10-31 10:42:57.535289: +2025-10-31 10:42:57.543710: Epoch 187 +2025-10-31 10:42:57.555723: Current learning rate: 0.0083 +2025-10-31 10:43:18.405706: train_loss -0.9773 +2025-10-31 10:43:18.414890: val_loss -0.9023 +2025-10-31 10:43:18.425371: Pseudo dice [np.float32(0.9832), np.float32(0.9912), np.float32(0.9947), np.float32(0.8074)] +2025-10-31 10:43:18.435867: Epoch time: 20.87 s +2025-10-31 10:43:19.487828: +2025-10-31 10:43:19.498452: Epoch 188 +2025-10-31 10:43:19.508758: Current learning rate: 0.00829 +2025-10-31 10:43:40.261046: train_loss -0.9763 +2025-10-31 10:43:40.281034: val_loss -0.8984 +2025-10-31 10:43:40.291186: Pseudo dice [np.float32(0.984), np.float32(0.9844), np.float32(0.9923), np.float32(0.8172)] +2025-10-31 10:43:40.301172: Epoch time: 20.77 s +2025-10-31 10:43:41.540415: +2025-10-31 10:43:41.547287: Epoch 189 +2025-10-31 10:43:41.554223: Current learning rate: 0.00828 +2025-10-31 10:44:03.752635: train_loss -0.9672 +2025-10-31 10:44:03.777447: val_loss -0.8879 +2025-10-31 10:44:03.790703: Pseudo dice [np.float32(0.9846), np.float32(0.9893), np.float32(0.9924), np.float32(0.7687)] +2025-10-31 10:44:03.802829: Epoch time: 22.21 s +2025-10-31 10:44:05.119438: +2025-10-31 10:44:05.130321: Epoch 190 +2025-10-31 10:44:05.141268: Current learning rate: 0.00827 +2025-10-31 10:44:27.280543: train_loss -0.9726 +2025-10-31 10:44:27.291862: val_loss -0.9145 +2025-10-31 10:44:27.303175: Pseudo dice [np.float32(0.9845), np.float32(0.991), np.float32(0.9954), np.float32(0.8278)] +2025-10-31 10:44:27.312970: Epoch time: 22.16 s +2025-10-31 10:44:28.367621: +2025-10-31 10:44:28.371789: Epoch 191 +2025-10-31 10:44:28.374194: Current learning rate: 0.00826 +2025-10-31 10:44:51.236518: train_loss -0.9746 +2025-10-31 10:44:51.252024: val_loss -0.9013 +2025-10-31 10:44:51.263626: Pseudo dice [np.float32(0.984), np.float32(0.9912), np.float32(0.9952), np.float32(0.787)] +2025-10-31 10:44:51.275620: Epoch time: 22.87 s +2025-10-31 10:44:52.487754: +2025-10-31 10:44:52.494879: Epoch 192 +2025-10-31 10:44:52.504195: Current learning rate: 0.00825 +2025-10-31 10:45:14.524059: train_loss -0.9719 +2025-10-31 10:45:14.541349: val_loss -0.9052 +2025-10-31 10:45:14.549466: Pseudo dice [np.float32(0.9859), np.float32(0.9919), np.float32(0.9939), np.float32(0.7954)] +2025-10-31 10:45:14.556497: Epoch time: 22.04 s +2025-10-31 10:45:15.959475: +2025-10-31 10:45:15.972641: Epoch 193 +2025-10-31 10:45:15.984924: Current learning rate: 0.00824 +2025-10-31 10:45:37.792173: train_loss -0.975 +2025-10-31 10:45:37.801569: val_loss -0.9002 +2025-10-31 10:45:37.810833: Pseudo dice [np.float32(0.984), np.float32(0.991), np.float32(0.9949), np.float32(0.8013)] +2025-10-31 10:45:37.820071: Epoch time: 21.84 s +2025-10-31 10:45:39.013423: +2025-10-31 10:45:39.017164: Epoch 194 +2025-10-31 10:45:39.019969: Current learning rate: 0.00824 +2025-10-31 10:45:59.690454: train_loss -0.9789 +2025-10-31 10:45:59.694327: val_loss -0.9079 +2025-10-31 10:45:59.696126: Pseudo dice [np.float32(0.9855), np.float32(0.9922), np.float32(0.9956), np.float32(0.8113)] +2025-10-31 10:45:59.697953: Epoch time: 20.68 s +2025-10-31 10:46:00.732981: +2025-10-31 10:46:00.735159: Epoch 195 +2025-10-31 10:46:00.738438: Current learning rate: 0.00823 +2025-10-31 10:46:22.650261: train_loss -0.9822 +2025-10-31 10:46:22.654704: val_loss -0.9034 +2025-10-31 10:46:22.657275: Pseudo dice [np.float32(0.9858), np.float32(0.9926), np.float32(0.9955), np.float32(0.8076)] +2025-10-31 10:46:22.659168: Epoch time: 21.92 s +2025-10-31 10:46:23.972200: +2025-10-31 10:46:23.974530: Epoch 196 +2025-10-31 10:46:23.976987: Current learning rate: 0.00822 +2025-10-31 10:46:46.208648: train_loss -0.9834 +2025-10-31 10:46:46.211969: val_loss -0.9033 +2025-10-31 10:46:46.214129: Pseudo dice [np.float32(0.986), np.float32(0.9919), np.float32(0.9949), np.float32(0.8035)] +2025-10-31 10:46:46.216271: Epoch time: 22.24 s +2025-10-31 10:46:47.467951: +2025-10-31 10:46:47.472688: Epoch 197 +2025-10-31 10:46:47.476438: Current learning rate: 0.00821 +2025-10-31 10:47:10.294860: train_loss -0.9825 +2025-10-31 10:47:10.301836: val_loss -0.8994 +2025-10-31 10:47:10.304123: Pseudo dice [np.float32(0.9854), np.float32(0.9921), np.float32(0.9951), np.float32(0.7903)] +2025-10-31 10:47:10.306661: Epoch time: 22.83 s +2025-10-31 10:47:11.523149: +2025-10-31 10:47:11.525179: Epoch 198 +2025-10-31 10:47:11.527465: Current learning rate: 0.0082 +2025-10-31 10:47:33.828890: train_loss -0.9849 +2025-10-31 10:47:33.831677: val_loss -0.8992 +2025-10-31 10:47:33.834204: Pseudo dice [np.float32(0.9835), np.float32(0.9917), np.float32(0.9952), np.float32(0.804)] +2025-10-31 10:47:33.837068: Epoch time: 22.31 s +2025-10-31 10:47:35.131594: +2025-10-31 10:47:35.133891: Epoch 199 +2025-10-31 10:47:35.136308: Current learning rate: 0.00819 +2025-10-31 10:47:57.169908: train_loss -0.9858 +2025-10-31 10:47:57.173119: val_loss -0.9057 +2025-10-31 10:47:57.174926: Pseudo dice [np.float32(0.9854), np.float32(0.9923), np.float32(0.9952), np.float32(0.811)] +2025-10-31 10:47:57.177328: Epoch time: 22.04 s +2025-10-31 10:47:59.931841: +2025-10-31 10:47:59.934306: Epoch 200 +2025-10-31 10:47:59.936460: Current learning rate: 0.00818 +2025-10-31 10:48:20.755992: train_loss -0.9821 +2025-10-31 10:48:20.758966: val_loss -0.9058 +2025-10-31 10:48:20.760957: Pseudo dice [np.float32(0.9837), np.float32(0.9903), np.float32(0.9949), np.float32(0.8187)] +2025-10-31 10:48:20.762642: Epoch time: 20.83 s +2025-10-31 10:48:21.840082: +2025-10-31 10:48:21.842278: Epoch 201 +2025-10-31 10:48:21.844417: Current learning rate: 0.00817 +2025-10-31 10:48:44.391768: train_loss -0.9818 +2025-10-31 10:48:44.395439: val_loss -0.9054 +2025-10-31 10:48:44.397567: Pseudo dice [np.float32(0.9856), np.float32(0.9921), np.float32(0.9955), np.float32(0.8167)] +2025-10-31 10:48:44.399696: Epoch time: 22.55 s +2025-10-31 10:48:45.686062: +2025-10-31 10:48:45.688913: Epoch 202 +2025-10-31 10:48:45.692020: Current learning rate: 0.00816 +2025-10-31 10:49:08.028596: train_loss -0.983 +2025-10-31 10:49:08.031339: val_loss -0.8985 +2025-10-31 10:49:08.033925: Pseudo dice [np.float32(0.9845), np.float32(0.9923), np.float32(0.9952), np.float32(0.7953)] +2025-10-31 10:49:08.036521: Epoch time: 22.34 s +2025-10-31 10:49:09.648795: +2025-10-31 10:49:09.651852: Epoch 203 +2025-10-31 10:49:09.654163: Current learning rate: 0.00815 +2025-10-31 10:49:31.959449: train_loss -0.9849 +2025-10-31 10:49:31.962919: val_loss -0.9048 +2025-10-31 10:49:31.965325: Pseudo dice [np.float32(0.9854), np.float32(0.9921), np.float32(0.9953), np.float32(0.8037)] +2025-10-31 10:49:31.967588: Epoch time: 22.31 s +2025-10-31 10:49:33.232527: +2025-10-31 10:49:33.235494: Epoch 204 +2025-10-31 10:49:33.238025: Current learning rate: 0.00814 +2025-10-31 10:49:55.055948: train_loss -0.9852 +2025-10-31 10:49:55.059954: val_loss -0.9053 +2025-10-31 10:49:55.062555: Pseudo dice [np.float32(0.9871), np.float32(0.9929), np.float32(0.9954), np.float32(0.8118)] +2025-10-31 10:49:55.066023: Epoch time: 21.83 s +2025-10-31 10:49:56.151509: +2025-10-31 10:49:56.157049: Epoch 205 +2025-10-31 10:49:56.161078: Current learning rate: 0.00813 +2025-10-31 10:50:18.136423: train_loss -0.9855 +2025-10-31 10:50:18.141709: val_loss -0.9039 +2025-10-31 10:50:18.143808: Pseudo dice [np.float32(0.9868), np.float32(0.9933), np.float32(0.9955), np.float32(0.8046)] +2025-10-31 10:50:18.145713: Epoch time: 21.99 s +2025-10-31 10:50:19.165970: +2025-10-31 10:50:19.168660: Epoch 206 +2025-10-31 10:50:19.170756: Current learning rate: 0.00813 +2025-10-31 10:50:39.177220: train_loss -0.9852 +2025-10-31 10:50:39.183621: val_loss -0.9011 +2025-10-31 10:50:39.186032: Pseudo dice [np.float32(0.9853), np.float32(0.9921), np.float32(0.9954), np.float32(0.804)] +2025-10-31 10:50:39.188313: Epoch time: 20.01 s +2025-10-31 10:50:40.409750: +2025-10-31 10:50:40.412499: Epoch 207 +2025-10-31 10:50:40.415183: Current learning rate: 0.00812 +2025-10-31 10:51:02.088917: train_loss -0.9844 +2025-10-31 10:51:02.094190: val_loss -0.9061 +2025-10-31 10:51:02.096874: Pseudo dice [np.float32(0.9856), np.float32(0.9923), np.float32(0.9951), np.float32(0.8117)] +2025-10-31 10:51:02.099943: Epoch time: 21.68 s +2025-10-31 10:51:03.139168: +2025-10-31 10:51:03.141873: Epoch 208 +2025-10-31 10:51:03.144046: Current learning rate: 0.00811 +2025-10-31 10:51:25.847788: train_loss -0.9841 +2025-10-31 10:51:25.851888: val_loss -0.8933 +2025-10-31 10:51:25.855026: Pseudo dice [np.float32(0.9856), np.float32(0.9927), np.float32(0.995), np.float32(0.7959)] +2025-10-31 10:51:25.857599: Epoch time: 22.71 s +2025-10-31 10:51:27.046359: +2025-10-31 10:51:27.049289: Epoch 209 +2025-10-31 10:51:27.052016: Current learning rate: 0.0081 +2025-10-31 10:51:49.653447: train_loss -0.986 +2025-10-31 10:51:49.656023: val_loss -0.9104 +2025-10-31 10:51:49.658716: Pseudo dice [np.float32(0.9874), np.float32(0.9929), np.float32(0.9957), np.float32(0.8213)] +2025-10-31 10:51:49.662207: Epoch time: 22.61 s +2025-10-31 10:51:50.846282: +2025-10-31 10:51:50.848961: Epoch 210 +2025-10-31 10:51:50.851351: Current learning rate: 0.00809 +2025-10-31 10:52:12.872934: train_loss -0.9856 +2025-10-31 10:52:12.883835: val_loss -0.8963 +2025-10-31 10:52:12.885981: Pseudo dice [np.float32(0.9838), np.float32(0.9929), np.float32(0.9952), np.float32(0.7991)] +2025-10-31 10:52:12.888474: Epoch time: 22.03 s +2025-10-31 10:52:14.013967: +2025-10-31 10:52:14.016704: Epoch 211 +2025-10-31 10:52:14.019051: Current learning rate: 0.00808 +2025-10-31 10:52:35.754983: train_loss -0.9861 +2025-10-31 10:52:35.761203: val_loss -0.9013 +2025-10-31 10:52:35.764493: Pseudo dice [np.float32(0.9861), np.float32(0.9926), np.float32(0.9957), np.float32(0.8034)] +2025-10-31 10:52:35.766518: Epoch time: 21.74 s +2025-10-31 10:52:36.812196: +2025-10-31 10:52:36.814551: Epoch 212 +2025-10-31 10:52:36.817109: Current learning rate: 0.00807 +2025-10-31 10:52:58.536496: train_loss -0.9847 +2025-10-31 10:52:58.539899: val_loss -0.9005 +2025-10-31 10:52:58.541687: Pseudo dice [np.float32(0.985), np.float32(0.9921), np.float32(0.9953), np.float32(0.8106)] +2025-10-31 10:52:58.543492: Epoch time: 21.73 s +2025-10-31 10:52:59.792182: +2025-10-31 10:52:59.794675: Epoch 213 +2025-10-31 10:52:59.796565: Current learning rate: 0.00806 +2025-10-31 10:53:20.486273: train_loss -0.9863 +2025-10-31 10:53:20.492072: val_loss -0.8912 +2025-10-31 10:53:20.494375: Pseudo dice [np.float32(0.9854), np.float32(0.9924), np.float32(0.9949), np.float32(0.7799)] +2025-10-31 10:53:20.497897: Epoch time: 20.7 s +2025-10-31 10:53:21.627804: +2025-10-31 10:53:21.630574: Epoch 214 +2025-10-31 10:53:21.632967: Current learning rate: 0.00805 +2025-10-31 10:53:43.568765: train_loss -0.9863 +2025-10-31 10:53:43.571812: val_loss -0.9004 +2025-10-31 10:53:43.575514: Pseudo dice [np.float32(0.9861), np.float32(0.9929), np.float32(0.9956), np.float32(0.8006)] +2025-10-31 10:53:43.578091: Epoch time: 21.94 s +2025-10-31 10:53:45.416626: +2025-10-31 10:53:45.422192: Epoch 215 +2025-10-31 10:53:45.425227: Current learning rate: 0.00804 +2025-10-31 10:54:07.824203: train_loss -0.9876 +2025-10-31 10:54:07.827431: val_loss -0.8938 +2025-10-31 10:54:07.830233: Pseudo dice [np.float32(0.986), np.float32(0.9926), np.float32(0.995), np.float32(0.7921)] +2025-10-31 10:54:07.832464: Epoch time: 22.41 s +2025-10-31 10:54:08.966305: +2025-10-31 10:54:08.968909: Epoch 216 +2025-10-31 10:54:08.971007: Current learning rate: 0.00803 +2025-10-31 10:54:31.554420: train_loss -0.9809 +2025-10-31 10:54:31.557606: val_loss -0.9037 +2025-10-31 10:54:31.559319: Pseudo dice [np.float32(0.9856), np.float32(0.9911), np.float32(0.9949), np.float32(0.8003)] +2025-10-31 10:54:31.560974: Epoch time: 22.59 s +2025-10-31 10:54:32.762183: +2025-10-31 10:54:32.764920: Epoch 217 +2025-10-31 10:54:32.766957: Current learning rate: 0.00802 +2025-10-31 10:54:54.966401: train_loss -0.9656 +2025-10-31 10:54:54.971341: val_loss -0.9153 +2025-10-31 10:54:54.976374: Pseudo dice [np.float32(0.986), np.float32(0.9914), np.float32(0.995), np.float32(0.8187)] +2025-10-31 10:54:54.981005: Epoch time: 22.21 s +2025-10-31 10:54:56.211248: +2025-10-31 10:54:56.213705: Epoch 218 +2025-10-31 10:54:56.215719: Current learning rate: 0.00801 +2025-10-31 10:55:17.735368: train_loss -0.9656 +2025-10-31 10:55:17.738836: val_loss -0.9014 +2025-10-31 10:55:17.740962: Pseudo dice [np.float32(0.9843), np.float32(0.9912), np.float32(0.9951), np.float32(0.7868)] +2025-10-31 10:55:17.742828: Epoch time: 21.53 s +2025-10-31 10:55:18.838813: +2025-10-31 10:55:18.841077: Epoch 219 +2025-10-31 10:55:18.842998: Current learning rate: 0.00801 +2025-10-31 10:55:40.218042: train_loss -0.977 +2025-10-31 10:55:40.221220: val_loss -0.9042 +2025-10-31 10:55:40.223691: Pseudo dice [np.float32(0.9844), np.float32(0.992), np.float32(0.995), np.float32(0.8012)] +2025-10-31 10:55:40.226135: Epoch time: 21.38 s +2025-10-31 10:55:41.422036: +2025-10-31 10:55:41.424896: Epoch 220 +2025-10-31 10:55:41.427263: Current learning rate: 0.008 +2025-10-31 10:56:03.897792: train_loss -0.9796 +2025-10-31 10:56:03.903386: val_loss -0.9074 +2025-10-31 10:56:03.906513: Pseudo dice [np.float32(0.985), np.float32(0.9912), np.float32(0.995), np.float32(0.8128)] +2025-10-31 10:56:03.911981: Epoch time: 22.48 s +2025-10-31 10:56:04.971982: +2025-10-31 10:56:04.974355: Epoch 221 +2025-10-31 10:56:04.976395: Current learning rate: 0.00799 +2025-10-31 10:56:28.070395: train_loss -0.9806 +2025-10-31 10:56:28.074703: val_loss -0.9036 +2025-10-31 10:56:28.077421: Pseudo dice [np.float32(0.9854), np.float32(0.9924), np.float32(0.9951), np.float32(0.7997)] +2025-10-31 10:56:28.080140: Epoch time: 23.1 s +2025-10-31 10:56:29.176707: +2025-10-31 10:56:29.180263: Epoch 222 +2025-10-31 10:56:29.183211: Current learning rate: 0.00798 +2025-10-31 10:56:51.212217: train_loss -0.9835 +2025-10-31 10:56:51.219851: val_loss -0.899 +2025-10-31 10:56:51.222144: Pseudo dice [np.float32(0.9857), np.float32(0.9923), np.float32(0.9952), np.float32(0.7931)] +2025-10-31 10:56:51.225912: Epoch time: 22.04 s +2025-10-31 10:56:52.421430: +2025-10-31 10:56:52.423898: Epoch 223 +2025-10-31 10:56:52.425822: Current learning rate: 0.00797 +2025-10-31 10:57:14.699300: train_loss -0.9841 +2025-10-31 10:57:14.702468: val_loss -0.8928 +2025-10-31 10:57:14.704709: Pseudo dice [np.float32(0.9861), np.float32(0.9927), np.float32(0.9945), np.float32(0.7812)] +2025-10-31 10:57:14.707092: Epoch time: 22.28 s +2025-10-31 10:57:15.760034: +2025-10-31 10:57:15.762397: Epoch 224 +2025-10-31 10:57:15.764629: Current learning rate: 0.00796 +2025-10-31 10:57:36.591711: train_loss -0.9846 +2025-10-31 10:57:36.595713: val_loss -0.8949 +2025-10-31 10:57:36.597616: Pseudo dice [np.float32(0.9862), np.float32(0.9929), np.float32(0.9948), np.float32(0.7798)] +2025-10-31 10:57:36.600581: Epoch time: 20.83 s +2025-10-31 10:57:37.593992: +2025-10-31 10:57:37.596532: Epoch 225 +2025-10-31 10:57:37.598380: Current learning rate: 0.00795 +2025-10-31 10:57:59.095215: train_loss -0.9841 +2025-10-31 10:57:59.098734: val_loss -0.8985 +2025-10-31 10:57:59.100677: Pseudo dice [np.float32(0.9849), np.float32(0.9931), np.float32(0.9952), np.float32(0.7971)] +2025-10-31 10:57:59.102558: Epoch time: 21.5 s +2025-10-31 10:58:00.104235: +2025-10-31 10:58:00.106444: Epoch 226 +2025-10-31 10:58:00.108233: Current learning rate: 0.00794 +2025-10-31 10:58:21.119251: train_loss -0.9853 +2025-10-31 10:58:21.121921: val_loss -0.8932 +2025-10-31 10:58:21.123930: Pseudo dice [np.float32(0.9847), np.float32(0.9926), np.float32(0.9951), np.float32(0.7906)] +2025-10-31 10:58:21.125846: Epoch time: 21.02 s +2025-10-31 10:58:22.209693: +2025-10-31 10:58:22.211484: Epoch 227 +2025-10-31 10:58:22.213169: Current learning rate: 0.00793 +2025-10-31 10:58:43.782433: train_loss -0.9861 +2025-10-31 10:58:43.785625: val_loss -0.8931 +2025-10-31 10:58:43.787602: Pseudo dice [np.float32(0.9858), np.float32(0.9928), np.float32(0.995), np.float32(0.7828)] +2025-10-31 10:58:43.790107: Epoch time: 21.57 s +2025-10-31 10:58:45.417975: +2025-10-31 10:58:45.420117: Epoch 228 +2025-10-31 10:58:45.421995: Current learning rate: 0.00792 +2025-10-31 10:59:07.255623: train_loss -0.9857 +2025-10-31 10:59:07.261466: val_loss -0.8996 +2025-10-31 10:59:07.264060: Pseudo dice [np.float32(0.9848), np.float32(0.9923), np.float32(0.9955), np.float32(0.8004)] +2025-10-31 10:59:07.266225: Epoch time: 21.84 s +2025-10-31 10:59:08.460181: +2025-10-31 10:59:08.462619: Epoch 229 +2025-10-31 10:59:08.464663: Current learning rate: 0.00791 +2025-10-31 10:59:29.461876: train_loss -0.9864 +2025-10-31 10:59:29.464743: val_loss -0.8886 +2025-10-31 10:59:29.466660: Pseudo dice [np.float32(0.9865), np.float32(0.9929), np.float32(0.994), np.float32(0.7684)] +2025-10-31 10:59:29.468761: Epoch time: 21.0 s +2025-10-31 10:59:30.613076: +2025-10-31 10:59:30.615122: Epoch 230 +2025-10-31 10:59:30.617195: Current learning rate: 0.0079 +2025-10-31 10:59:51.547270: train_loss -0.9859 +2025-10-31 10:59:51.549986: val_loss -0.8917 +2025-10-31 10:59:51.551491: Pseudo dice [np.float32(0.9842), np.float32(0.9921), np.float32(0.9949), np.float32(0.7863)] +2025-10-31 10:59:51.553257: Epoch time: 20.94 s +2025-10-31 10:59:52.757645: +2025-10-31 10:59:52.760173: Epoch 231 +2025-10-31 10:59:52.762042: Current learning rate: 0.00789 +2025-10-31 11:00:14.758216: train_loss -0.9855 +2025-10-31 11:00:14.763857: val_loss -0.8984 +2025-10-31 11:00:14.765661: Pseudo dice [np.float32(0.9837), np.float32(0.9919), np.float32(0.9952), np.float32(0.8063)] +2025-10-31 11:00:14.767450: Epoch time: 22.0 s +2025-10-31 11:00:15.899504: +2025-10-31 11:00:15.901274: Epoch 232 +2025-10-31 11:00:15.902807: Current learning rate: 0.00789 +2025-10-31 11:00:36.887990: train_loss -0.9867 +2025-10-31 11:00:36.891361: val_loss -0.8892 +2025-10-31 11:00:36.893801: Pseudo dice [np.float32(0.986), np.float32(0.9932), np.float32(0.9949), np.float32(0.7793)] +2025-10-31 11:00:36.895998: Epoch time: 20.99 s +2025-10-31 11:00:38.052140: +2025-10-31 11:00:38.064923: Epoch 233 +2025-10-31 11:00:38.067111: Current learning rate: 0.00788 +2025-10-31 11:00:59.628664: train_loss -0.9859 +2025-10-31 11:00:59.631078: val_loss -0.8933 +2025-10-31 11:00:59.634159: Pseudo dice [np.float32(0.9852), np.float32(0.9922), np.float32(0.9951), np.float32(0.7939)] +2025-10-31 11:00:59.636240: Epoch time: 21.58 s +2025-10-31 11:01:00.673154: +2025-10-31 11:01:00.675653: Epoch 234 +2025-10-31 11:01:00.677573: Current learning rate: 0.00787 +2025-10-31 11:01:23.259284: train_loss -0.9865 +2025-10-31 11:01:23.263074: val_loss -0.893 +2025-10-31 11:01:23.265250: Pseudo dice [np.float32(0.9857), np.float32(0.9922), np.float32(0.9951), np.float32(0.7913)] +2025-10-31 11:01:23.266953: Epoch time: 22.59 s +2025-10-31 11:01:24.338547: +2025-10-31 11:01:24.340631: Epoch 235 +2025-10-31 11:01:24.342607: Current learning rate: 0.00786 +2025-10-31 11:01:46.610548: train_loss -0.9862 +2025-10-31 11:01:46.613289: val_loss -0.8915 +2025-10-31 11:01:46.615003: Pseudo dice [np.float32(0.9838), np.float32(0.9922), np.float32(0.9953), np.float32(0.7892)] +2025-10-31 11:01:46.616791: Epoch time: 22.28 s +2025-10-31 11:01:47.647233: +2025-10-31 11:01:47.652507: Epoch 236 +2025-10-31 11:01:47.657018: Current learning rate: 0.00785 +2025-10-31 11:02:08.747339: train_loss -0.9861 +2025-10-31 11:02:08.755268: val_loss -0.9003 +2025-10-31 11:02:08.757271: Pseudo dice [np.float32(0.984), np.float32(0.992), np.float32(0.9953), np.float32(0.8154)] +2025-10-31 11:02:08.758996: Epoch time: 21.1 s +2025-10-31 11:02:09.957160: +2025-10-31 11:02:09.959310: Epoch 237 +2025-10-31 11:02:09.962090: Current learning rate: 0.00784 +2025-10-31 11:02:32.629234: train_loss -0.9866 +2025-10-31 11:02:32.632380: val_loss -0.9028 +2025-10-31 11:02:32.634148: Pseudo dice [np.float32(0.9834), np.float32(0.9925), np.float32(0.9956), np.float32(0.8123)] +2025-10-31 11:02:32.635795: Epoch time: 22.67 s +2025-10-31 11:02:33.766843: +2025-10-31 11:02:33.768528: Epoch 238 +2025-10-31 11:02:33.770066: Current learning rate: 0.00783 +2025-10-31 11:02:55.119948: train_loss -0.9867 +2025-10-31 11:02:55.122002: val_loss -0.903 +2025-10-31 11:02:55.123801: Pseudo dice [np.float32(0.9852), np.float32(0.9921), np.float32(0.9954), np.float32(0.8109)] +2025-10-31 11:02:55.125499: Epoch time: 21.35 s +2025-10-31 11:02:56.249690: +2025-10-31 11:02:56.251646: Epoch 239 +2025-10-31 11:02:56.254158: Current learning rate: 0.00782 +2025-10-31 11:03:17.930751: train_loss -0.9655 +2025-10-31 11:03:17.933519: val_loss -0.9013 +2025-10-31 11:03:17.935378: Pseudo dice [np.float32(0.9843), np.float32(0.99), np.float32(0.9938), np.float32(0.7788)] +2025-10-31 11:03:17.937011: Epoch time: 21.68 s +2025-10-31 11:03:19.118091: +2025-10-31 11:03:19.120562: Epoch 240 +2025-10-31 11:03:19.122576: Current learning rate: 0.00781 +2025-10-31 11:03:41.957548: train_loss -0.9538 +2025-10-31 11:03:41.960969: val_loss -0.9005 +2025-10-31 11:03:41.962935: Pseudo dice [np.float32(0.9836), np.float32(0.9896), np.float32(0.993), np.float32(0.7768)] +2025-10-31 11:03:41.964889: Epoch time: 22.84 s +2025-10-31 11:03:43.826151: +2025-10-31 11:03:43.831527: Epoch 241 +2025-10-31 11:03:43.833327: Current learning rate: 0.0078 +2025-10-31 11:04:05.310274: train_loss -0.9631 +2025-10-31 11:04:05.313116: val_loss -0.9009 +2025-10-31 11:04:05.315109: Pseudo dice [np.float32(0.9857), np.float32(0.9907), np.float32(0.9883), np.float32(0.8073)] +2025-10-31 11:04:05.317177: Epoch time: 21.49 s +2025-10-31 11:04:06.394114: +2025-10-31 11:04:06.397097: Epoch 242 +2025-10-31 11:04:06.399235: Current learning rate: 0.00779 +2025-10-31 11:04:27.631313: train_loss -0.9615 +2025-10-31 11:04:27.636923: val_loss -0.9109 +2025-10-31 11:04:27.638859: Pseudo dice [np.float32(0.9833), np.float32(0.991), np.float32(0.995), np.float32(0.8107)] +2025-10-31 11:04:27.640761: Epoch time: 21.24 s +2025-10-31 11:04:28.824593: +2025-10-31 11:04:28.826446: Epoch 243 +2025-10-31 11:04:28.828632: Current learning rate: 0.00778 +2025-10-31 11:04:50.973366: train_loss -0.9721 +2025-10-31 11:04:50.977303: val_loss -0.9089 +2025-10-31 11:04:50.979136: Pseudo dice [np.float32(0.9834), np.float32(0.9913), np.float32(0.9953), np.float32(0.8119)] +2025-10-31 11:04:50.981204: Epoch time: 22.15 s +2025-10-31 11:04:52.154886: +2025-10-31 11:04:52.157219: Epoch 244 +2025-10-31 11:04:52.159129: Current learning rate: 0.00777 +2025-10-31 11:05:14.561250: train_loss -0.9788 +2025-10-31 11:05:14.563416: val_loss -0.9097 +2025-10-31 11:05:14.565150: Pseudo dice [np.float32(0.9835), np.float32(0.9913), np.float32(0.9952), np.float32(0.819)] +2025-10-31 11:05:14.566756: Epoch time: 22.41 s +2025-10-31 11:05:15.769081: +2025-10-31 11:05:15.774455: Epoch 245 +2025-10-31 11:05:15.776329: Current learning rate: 0.00777 +2025-10-31 11:05:36.338210: train_loss -0.9812 +2025-10-31 11:05:36.345164: val_loss -0.8974 +2025-10-31 11:05:36.347113: Pseudo dice [np.float32(0.9848), np.float32(0.9924), np.float32(0.9949), np.float32(0.7869)] +2025-10-31 11:05:36.349105: Epoch time: 20.57 s +2025-10-31 11:05:37.548258: +2025-10-31 11:05:37.550512: Epoch 246 +2025-10-31 11:05:37.552498: Current learning rate: 0.00776 +2025-10-31 11:05:59.499695: train_loss -0.9815 +2025-10-31 11:05:59.503080: val_loss -0.9109 +2025-10-31 11:05:59.504864: Pseudo dice [np.float32(0.9822), np.float32(0.992), np.float32(0.9957), np.float32(0.8247)] +2025-10-31 11:05:59.506579: Epoch time: 21.95 s +2025-10-31 11:06:00.738061: +2025-10-31 11:06:00.740508: Epoch 247 +2025-10-31 11:06:00.742498: Current learning rate: 0.00775 +2025-10-31 11:06:23.378953: train_loss -0.9837 +2025-10-31 11:06:23.382547: val_loss -0.8993 +2025-10-31 11:06:23.384584: Pseudo dice [np.float32(0.9853), np.float32(0.993), np.float32(0.995), np.float32(0.7896)] +2025-10-31 11:06:23.387185: Epoch time: 22.64 s +2025-10-31 11:06:24.453065: +2025-10-31 11:06:24.455417: Epoch 248 +2025-10-31 11:06:24.457431: Current learning rate: 0.00774 +2025-10-31 11:06:45.917621: train_loss -0.9847 +2025-10-31 11:06:45.920623: val_loss -0.9036 +2025-10-31 11:06:45.922632: Pseudo dice [np.float32(0.9847), np.float32(0.9923), np.float32(0.9948), np.float32(0.8061)] +2025-10-31 11:06:45.924460: Epoch time: 21.47 s +2025-10-31 11:06:47.046743: +2025-10-31 11:06:47.049121: Epoch 249 +2025-10-31 11:06:47.051232: Current learning rate: 0.00773 +2025-10-31 11:07:09.255572: train_loss -0.9848 +2025-10-31 11:07:09.259000: val_loss -0.9017 +2025-10-31 11:07:09.260846: Pseudo dice [np.float32(0.9859), np.float32(0.9933), np.float32(0.9956), np.float32(0.8037)] +2025-10-31 11:07:09.262746: Epoch time: 22.21 s +2025-10-31 11:07:11.683116: +2025-10-31 11:07:11.685426: Epoch 250 +2025-10-31 11:07:11.687649: Current learning rate: 0.00772 +2025-10-31 11:07:33.518640: train_loss -0.9847 +2025-10-31 11:07:33.521399: val_loss -0.8964 +2025-10-31 11:07:33.523432: Pseudo dice [np.float32(0.9844), np.float32(0.9918), np.float32(0.9953), np.float32(0.7954)] +2025-10-31 11:07:33.525485: Epoch time: 21.84 s +2025-10-31 11:07:34.532300: +2025-10-31 11:07:34.534759: Epoch 251 +2025-10-31 11:07:34.536817: Current learning rate: 0.00771 +2025-10-31 11:07:55.595920: train_loss -0.9858 +2025-10-31 11:07:55.598924: val_loss -0.9088 +2025-10-31 11:07:55.601357: Pseudo dice [np.float32(0.9857), np.float32(0.9929), np.float32(0.9954), np.float32(0.8168)] +2025-10-31 11:07:55.603656: Epoch time: 21.07 s +2025-10-31 11:07:56.725030: +2025-10-31 11:07:56.727787: Epoch 252 +2025-10-31 11:07:56.730178: Current learning rate: 0.0077 +2025-10-31 11:08:19.125715: train_loss -0.9844 +2025-10-31 11:08:19.128810: val_loss -0.8943 +2025-10-31 11:08:19.130749: Pseudo dice [np.float32(0.9847), np.float32(0.9926), np.float32(0.9944), np.float32(0.7899)] +2025-10-31 11:08:19.132862: Epoch time: 22.4 s +2025-10-31 11:08:20.366152: +2025-10-31 11:08:20.368508: Epoch 253 +2025-10-31 11:08:20.370478: Current learning rate: 0.00769 +2025-10-31 11:08:42.192387: train_loss -0.9844 +2025-10-31 11:08:42.194963: val_loss -0.9052 +2025-10-31 11:08:42.196868: Pseudo dice [np.float32(0.9861), np.float32(0.9927), np.float32(0.9949), np.float32(0.8108)] +2025-10-31 11:08:42.198885: Epoch time: 21.83 s +2025-10-31 11:08:44.151954: +2025-10-31 11:08:44.154393: Epoch 254 +2025-10-31 11:08:44.156531: Current learning rate: 0.00768 +2025-10-31 11:09:04.607225: train_loss -0.9838 +2025-10-31 11:09:04.610307: val_loss -0.9083 +2025-10-31 11:09:04.612405: Pseudo dice [np.float32(0.9845), np.float32(0.9916), np.float32(0.9954), np.float32(0.815)] +2025-10-31 11:09:04.614446: Epoch time: 20.46 s +2025-10-31 11:09:05.611283: +2025-10-31 11:09:05.613297: Epoch 255 +2025-10-31 11:09:05.615140: Current learning rate: 0.00767 +2025-10-31 11:09:27.852012: train_loss -0.9849 +2025-10-31 11:09:27.855298: val_loss -0.8954 +2025-10-31 11:09:27.857375: Pseudo dice [np.float32(0.9842), np.float32(0.9918), np.float32(0.9946), np.float32(0.7918)] +2025-10-31 11:09:27.859440: Epoch time: 22.24 s +2025-10-31 11:09:29.042812: +2025-10-31 11:09:29.045219: Epoch 256 +2025-10-31 11:09:29.047277: Current learning rate: 0.00766 +2025-10-31 11:09:51.231960: train_loss -0.9863 +2025-10-31 11:09:51.235747: val_loss -0.8978 +2025-10-31 11:09:51.237901: Pseudo dice [np.float32(0.9843), np.float32(0.9921), np.float32(0.9953), np.float32(0.7977)] +2025-10-31 11:09:51.240087: Epoch time: 22.19 s +2025-10-31 11:09:52.466613: +2025-10-31 11:09:52.469438: Epoch 257 +2025-10-31 11:09:52.471341: Current learning rate: 0.00765 +2025-10-31 11:10:13.968148: train_loss -0.985 +2025-10-31 11:10:13.970524: val_loss -0.8954 +2025-10-31 11:10:13.972309: Pseudo dice [np.float32(0.9844), np.float32(0.9915), np.float32(0.9948), np.float32(0.7984)] +2025-10-31 11:10:13.974076: Epoch time: 21.5 s +2025-10-31 11:10:15.147532: +2025-10-31 11:10:15.149399: Epoch 258 +2025-10-31 11:10:15.150960: Current learning rate: 0.00764 +2025-10-31 11:10:36.283815: train_loss -0.9864 +2025-10-31 11:10:36.287652: val_loss -0.9009 +2025-10-31 11:10:36.291571: Pseudo dice [np.float32(0.9856), np.float32(0.9928), np.float32(0.9951), np.float32(0.8031)] +2025-10-31 11:10:36.293790: Epoch time: 21.14 s +2025-10-31 11:10:37.827479: +2025-10-31 11:10:37.829257: Epoch 259 +2025-10-31 11:10:37.831033: Current learning rate: 0.00764 +2025-10-31 11:10:59.181549: train_loss -0.9865 +2025-10-31 11:10:59.188546: val_loss -0.9003 +2025-10-31 11:10:59.198788: Pseudo dice [np.float32(0.9859), np.float32(0.9924), np.float32(0.9952), np.float32(0.8035)] +2025-10-31 11:10:59.206460: Epoch time: 21.36 s +2025-10-31 11:11:00.348542: +2025-10-31 11:11:00.352435: Epoch 260 +2025-10-31 11:11:00.355099: Current learning rate: 0.00763 +2025-10-31 11:11:21.147634: train_loss -0.986 +2025-10-31 11:11:21.150378: val_loss -0.9122 +2025-10-31 11:11:21.152578: Pseudo dice [np.float32(0.9855), np.float32(0.9928), np.float32(0.996), np.float32(0.8276)] +2025-10-31 11:11:21.154702: Epoch time: 20.8 s +2025-10-31 11:11:22.203628: +2025-10-31 11:11:22.207504: Epoch 261 +2025-10-31 11:11:22.209538: Current learning rate: 0.00762 +2025-10-31 11:11:43.918177: train_loss -0.9865 +2025-10-31 11:11:43.921849: val_loss -0.8996 +2025-10-31 11:11:43.923813: Pseudo dice [np.float32(0.9845), np.float32(0.992), np.float32(0.9951), np.float32(0.8054)] +2025-10-31 11:11:43.925863: Epoch time: 21.72 s +2025-10-31 11:11:45.094454: +2025-10-31 11:11:45.096893: Epoch 262 +2025-10-31 11:11:45.099028: Current learning rate: 0.00761 +2025-10-31 11:12:07.132104: train_loss -0.9864 +2025-10-31 11:12:07.135019: val_loss -0.8966 +2025-10-31 11:12:07.137692: Pseudo dice [np.float32(0.9844), np.float32(0.9926), np.float32(0.9953), np.float32(0.8106)] +2025-10-31 11:12:07.139994: Epoch time: 22.04 s +2025-10-31 11:12:08.348381: +2025-10-31 11:12:08.350788: Epoch 263 +2025-10-31 11:12:08.352704: Current learning rate: 0.0076 +2025-10-31 11:12:30.468092: train_loss -0.9871 +2025-10-31 11:12:30.470956: val_loss -0.904 +2025-10-31 11:12:30.472939: Pseudo dice [np.float32(0.9862), np.float32(0.9932), np.float32(0.9952), np.float32(0.8061)] +2025-10-31 11:12:30.475565: Epoch time: 22.12 s +2025-10-31 11:12:31.668147: +2025-10-31 11:12:31.670245: Epoch 264 +2025-10-31 11:12:31.671976: Current learning rate: 0.00759 +2025-10-31 11:12:52.221536: train_loss -0.9842 +2025-10-31 11:12:52.225179: val_loss -0.8987 +2025-10-31 11:12:52.227129: Pseudo dice [np.float32(0.9863), np.float32(0.9933), np.float32(0.9953), np.float32(0.7937)] +2025-10-31 11:12:52.228920: Epoch time: 20.56 s +2025-10-31 11:12:53.473278: +2025-10-31 11:12:53.475662: Epoch 265 +2025-10-31 11:12:53.477747: Current learning rate: 0.00758 +2025-10-31 11:13:15.663085: train_loss -0.9861 +2025-10-31 11:13:15.665570: val_loss -0.8929 +2025-10-31 11:13:15.667298: Pseudo dice [np.float32(0.9839), np.float32(0.9916), np.float32(0.995), np.float32(0.7947)] +2025-10-31 11:13:15.669163: Epoch time: 22.19 s +2025-10-31 11:13:16.924819: +2025-10-31 11:13:16.927919: Epoch 266 +2025-10-31 11:13:16.930405: Current learning rate: 0.00757 +2025-10-31 11:13:38.459784: train_loss -0.9871 +2025-10-31 11:13:38.462646: val_loss -0.8931 +2025-10-31 11:13:38.464486: Pseudo dice [np.float32(0.985), np.float32(0.9924), np.float32(0.9949), np.float32(0.7922)] +2025-10-31 11:13:38.466264: Epoch time: 21.54 s +2025-10-31 11:13:40.307163: +2025-10-31 11:13:40.310292: Epoch 267 +2025-10-31 11:13:40.311783: Current learning rate: 0.00756 +2025-10-31 11:14:02.473106: train_loss -0.9872 +2025-10-31 11:14:02.476144: val_loss -0.894 +2025-10-31 11:14:02.478053: Pseudo dice [np.float32(0.9846), np.float32(0.9917), np.float32(0.9946), np.float32(0.796)] +2025-10-31 11:14:02.479698: Epoch time: 22.17 s +2025-10-31 11:14:03.577464: +2025-10-31 11:14:03.581055: Epoch 268 +2025-10-31 11:14:03.582537: Current learning rate: 0.00755 +2025-10-31 11:14:25.510458: train_loss -0.9831 +2025-10-31 11:14:25.513465: val_loss -0.9149 +2025-10-31 11:14:25.515629: Pseudo dice [np.float32(0.9863), np.float32(0.9927), np.float32(0.9954), np.float32(0.8311)] +2025-10-31 11:14:25.517977: Epoch time: 21.93 s +2025-10-31 11:14:26.725232: +2025-10-31 11:14:26.727631: Epoch 269 +2025-10-31 11:14:26.729870: Current learning rate: 0.00754 +2025-10-31 11:14:49.160028: train_loss -0.9804 +2025-10-31 11:14:49.162802: val_loss -0.9039 +2025-10-31 11:14:49.164861: Pseudo dice [np.float32(0.985), np.float32(0.9923), np.float32(0.9952), np.float32(0.8008)] +2025-10-31 11:14:49.166638: Epoch time: 22.44 s +2025-10-31 11:14:50.189410: +2025-10-31 11:14:50.191405: Epoch 270 +2025-10-31 11:14:50.193424: Current learning rate: 0.00753 +2025-10-31 11:15:12.085247: train_loss -0.9844 +2025-10-31 11:15:12.116575: val_loss -0.9042 +2025-10-31 11:15:12.133643: Pseudo dice [np.float32(0.9838), np.float32(0.9923), np.float32(0.9958), np.float32(0.821)] +2025-10-31 11:15:12.151386: Epoch time: 21.9 s +2025-10-31 11:15:13.069532: +2025-10-31 11:15:13.071450: Epoch 271 +2025-10-31 11:15:13.074100: Current learning rate: 0.00752 +2025-10-31 11:15:34.039535: train_loss -0.9849 +2025-10-31 11:15:34.041502: val_loss -0.899 +2025-10-31 11:15:34.042929: Pseudo dice [np.float32(0.984), np.float32(0.9916), np.float32(0.9949), np.float32(0.809)] +2025-10-31 11:15:34.044242: Epoch time: 20.97 s +2025-10-31 11:15:35.229725: +2025-10-31 11:15:35.231843: Epoch 272 +2025-10-31 11:15:35.233681: Current learning rate: 0.00751 +2025-10-31 11:15:56.707076: train_loss -0.9869 +2025-10-31 11:15:56.716322: val_loss -0.8955 +2025-10-31 11:15:56.718107: Pseudo dice [np.float32(0.985), np.float32(0.9927), np.float32(0.9951), np.float32(0.7963)] +2025-10-31 11:15:56.719980: Epoch time: 21.48 s +2025-10-31 11:15:58.007106: +2025-10-31 11:15:58.009671: Epoch 273 +2025-10-31 11:15:58.011716: Current learning rate: 0.00751 +2025-10-31 11:16:19.969797: train_loss -0.9869 +2025-10-31 11:16:19.973036: val_loss -0.9048 +2025-10-31 11:16:19.974823: Pseudo dice [np.float32(0.985), np.float32(0.9919), np.float32(0.9956), np.float32(0.8223)] +2025-10-31 11:16:19.976534: Epoch time: 21.97 s +2025-10-31 11:16:21.201924: +2025-10-31 11:16:21.204064: Epoch 274 +2025-10-31 11:16:21.205996: Current learning rate: 0.0075 +2025-10-31 11:16:42.788421: train_loss -0.9844 +2025-10-31 11:16:42.790989: val_loss -0.9025 +2025-10-31 11:16:42.792745: Pseudo dice [np.float32(0.9841), np.float32(0.9925), np.float32(0.9952), np.float32(0.8044)] +2025-10-31 11:16:42.794395: Epoch time: 21.59 s +2025-10-31 11:16:43.846254: +2025-10-31 11:16:43.847985: Epoch 275 +2025-10-31 11:16:43.849432: Current learning rate: 0.00749 +2025-10-31 11:17:06.238578: train_loss -0.9834 +2025-10-31 11:17:06.241457: val_loss -0.8885 +2025-10-31 11:17:06.243122: Pseudo dice [np.float32(0.9854), np.float32(0.9931), np.float32(0.9942), np.float32(0.7711)] +2025-10-31 11:17:06.244893: Epoch time: 22.39 s +2025-10-31 11:17:07.310187: +2025-10-31 11:17:07.312474: Epoch 276 +2025-10-31 11:17:07.315346: Current learning rate: 0.00748 +2025-10-31 11:17:29.421874: train_loss -0.9791 +2025-10-31 11:17:29.424635: val_loss -0.9054 +2025-10-31 11:17:29.426492: Pseudo dice [np.float32(0.9832), np.float32(0.9917), np.float32(0.9954), np.float32(0.8147)] +2025-10-31 11:17:29.428357: Epoch time: 22.11 s +2025-10-31 11:17:30.443662: +2025-10-31 11:17:30.446051: Epoch 277 +2025-10-31 11:17:30.448151: Current learning rate: 0.00747 +2025-10-31 11:17:50.986158: train_loss -0.9827 +2025-10-31 11:17:50.988757: val_loss -0.9058 +2025-10-31 11:17:50.990830: Pseudo dice [np.float32(0.9853), np.float32(0.9921), np.float32(0.9952), np.float32(0.8118)] +2025-10-31 11:17:50.992825: Epoch time: 20.54 s +2025-10-31 11:17:52.013219: +2025-10-31 11:17:52.015511: Epoch 278 +2025-10-31 11:17:52.018402: Current learning rate: 0.00746 +2025-10-31 11:18:12.848394: train_loss -0.9858 +2025-10-31 11:18:12.857430: val_loss -0.905 +2025-10-31 11:18:12.859670: Pseudo dice [np.float32(0.9867), np.float32(0.9919), np.float32(0.995), np.float32(0.8095)] +2025-10-31 11:18:12.861578: Epoch time: 20.84 s +2025-10-31 11:18:14.149991: +2025-10-31 11:18:14.152357: Epoch 279 +2025-10-31 11:18:14.154654: Current learning rate: 0.00745 +2025-10-31 11:18:36.087489: train_loss -0.9864 +2025-10-31 11:18:36.090564: val_loss -0.8978 +2025-10-31 11:18:36.092165: Pseudo dice [np.float32(0.9852), np.float32(0.9921), np.float32(0.9951), np.float32(0.7995)] +2025-10-31 11:18:36.093597: Epoch time: 21.94 s +2025-10-31 11:18:38.134773: +2025-10-31 11:18:38.137260: Epoch 280 +2025-10-31 11:18:38.139268: Current learning rate: 0.00744 +2025-10-31 11:19:00.477259: train_loss -0.9861 +2025-10-31 11:19:00.480071: val_loss -0.9009 +2025-10-31 11:19:00.482059: Pseudo dice [np.float32(0.9847), np.float32(0.9922), np.float32(0.9954), np.float32(0.81)] +2025-10-31 11:19:00.483819: Epoch time: 22.34 s +2025-10-31 11:19:01.641258: +2025-10-31 11:19:01.643836: Epoch 281 +2025-10-31 11:19:01.645714: Current learning rate: 0.00743 +2025-10-31 11:19:24.134749: train_loss -0.9861 +2025-10-31 11:19:24.138086: val_loss -0.8955 +2025-10-31 11:19:24.139952: Pseudo dice [np.float32(0.9837), np.float32(0.9922), np.float32(0.9952), np.float32(0.8006)] +2025-10-31 11:19:24.141776: Epoch time: 22.5 s +2025-10-31 11:19:25.378417: +2025-10-31 11:19:25.380408: Epoch 282 +2025-10-31 11:19:25.381984: Current learning rate: 0.00742 +2025-10-31 11:19:48.178236: train_loss -0.9858 +2025-10-31 11:19:48.181272: val_loss -0.8927 +2025-10-31 11:19:48.183095: Pseudo dice [np.float32(0.9837), np.float32(0.9924), np.float32(0.9952), np.float32(0.7973)] +2025-10-31 11:19:48.184799: Epoch time: 22.8 s +2025-10-31 11:19:49.315658: +2025-10-31 11:19:49.317642: Epoch 283 +2025-10-31 11:19:49.319744: Current learning rate: 0.00741 +2025-10-31 11:20:10.442423: train_loss -0.9865 +2025-10-31 11:20:10.446466: val_loss -0.9035 +2025-10-31 11:20:10.448383: Pseudo dice [np.float32(0.9855), np.float32(0.9918), np.float32(0.9955), np.float32(0.8124)] +2025-10-31 11:20:10.450295: Epoch time: 21.13 s +2025-10-31 11:20:11.702888: +2025-10-31 11:20:11.704920: Epoch 284 +2025-10-31 11:20:11.706942: Current learning rate: 0.0074 +2025-10-31 11:20:31.972078: train_loss -0.9868 +2025-10-31 11:20:31.974519: val_loss -0.9018 +2025-10-31 11:20:31.976335: Pseudo dice [np.float32(0.9855), np.float32(0.9929), np.float32(0.9952), np.float32(0.8078)] +2025-10-31 11:20:31.978107: Epoch time: 20.27 s +2025-10-31 11:20:33.117878: +2025-10-31 11:20:33.120703: Epoch 285 +2025-10-31 11:20:33.122550: Current learning rate: 0.00739 +2025-10-31 11:20:55.854746: train_loss -0.9875 +2025-10-31 11:20:55.858063: val_loss -0.9024 +2025-10-31 11:20:55.860109: Pseudo dice [np.float32(0.9848), np.float32(0.9929), np.float32(0.9951), np.float32(0.81)] +2025-10-31 11:20:55.861902: Epoch time: 22.74 s +2025-10-31 11:20:57.039995: +2025-10-31 11:20:57.041948: Epoch 286 +2025-10-31 11:20:57.043736: Current learning rate: 0.00738 +2025-10-31 11:21:19.094846: train_loss -0.9881 +2025-10-31 11:21:19.097528: val_loss -0.8942 +2025-10-31 11:21:19.099679: Pseudo dice [np.float32(0.9835), np.float32(0.9917), np.float32(0.995), np.float32(0.8023)] +2025-10-31 11:21:19.101723: Epoch time: 22.06 s +2025-10-31 11:21:20.228251: +2025-10-31 11:21:20.233427: Epoch 287 +2025-10-31 11:21:20.235427: Current learning rate: 0.00738 +2025-10-31 11:21:42.091415: train_loss -0.9875 +2025-10-31 11:21:42.095293: val_loss -0.8964 +2025-10-31 11:21:42.097445: Pseudo dice [np.float32(0.9858), np.float32(0.9933), np.float32(0.9954), np.float32(0.7935)] +2025-10-31 11:21:42.099359: Epoch time: 21.87 s +2025-10-31 11:21:43.360478: +2025-10-31 11:21:43.362543: Epoch 288 +2025-10-31 11:21:43.364262: Current learning rate: 0.00737 +2025-10-31 11:22:05.097206: train_loss -0.988 +2025-10-31 11:22:05.100828: val_loss -0.8889 +2025-10-31 11:22:05.102690: Pseudo dice [np.float32(0.9855), np.float32(0.9924), np.float32(0.9946), np.float32(0.7845)] +2025-10-31 11:22:05.104594: Epoch time: 21.74 s +2025-10-31 11:22:06.328479: +2025-10-31 11:22:06.330508: Epoch 289 +2025-10-31 11:22:06.332220: Current learning rate: 0.00736 +2025-10-31 11:22:27.950442: train_loss -0.9858 +2025-10-31 11:22:27.953123: val_loss -0.9002 +2025-10-31 11:22:27.956126: Pseudo dice [np.float32(0.9837), np.float32(0.9921), np.float32(0.9954), np.float32(0.804)] +2025-10-31 11:22:27.960148: Epoch time: 21.62 s +2025-10-31 11:22:29.200172: +2025-10-31 11:22:29.202485: Epoch 290 +2025-10-31 11:22:29.208721: Current learning rate: 0.00735 +2025-10-31 11:22:49.447121: train_loss -0.9878 +2025-10-31 11:22:49.450017: val_loss -0.8996 +2025-10-31 11:22:49.452018: Pseudo dice [np.float32(0.9842), np.float32(0.9916), np.float32(0.9953), np.float32(0.8159)] +2025-10-31 11:22:49.454142: Epoch time: 20.25 s +2025-10-31 11:22:50.604557: +2025-10-31 11:22:50.607075: Epoch 291 +2025-10-31 11:22:50.609521: Current learning rate: 0.00734 +2025-10-31 11:23:12.086385: train_loss -0.9873 +2025-10-31 11:23:12.092250: val_loss -0.8987 +2025-10-31 11:23:12.094476: Pseudo dice [np.float32(0.9856), np.float32(0.9929), np.float32(0.9949), np.float32(0.7995)] +2025-10-31 11:23:12.096545: Epoch time: 21.48 s +2025-10-31 11:23:13.249511: +2025-10-31 11:23:13.252128: Epoch 292 +2025-10-31 11:23:13.254210: Current learning rate: 0.00733 +2025-10-31 11:23:34.990845: train_loss -0.9882 +2025-10-31 11:23:34.993500: val_loss -0.8963 +2025-10-31 11:23:34.995356: Pseudo dice [np.float32(0.9845), np.float32(0.9921), np.float32(0.9951), np.float32(0.7938)] +2025-10-31 11:23:34.997530: Epoch time: 21.74 s +2025-10-31 11:23:36.740899: +2025-10-31 11:23:36.743655: Epoch 293 +2025-10-31 11:23:36.745924: Current learning rate: 0.00732 +2025-10-31 11:23:59.017594: train_loss -0.9874 +2025-10-31 11:23:59.021515: val_loss -0.8978 +2025-10-31 11:23:59.023710: Pseudo dice [np.float32(0.9849), np.float32(0.9925), np.float32(0.9951), np.float32(0.7992)] +2025-10-31 11:23:59.026716: Epoch time: 22.28 s +2025-10-31 11:24:00.223117: +2025-10-31 11:24:00.225358: Epoch 294 +2025-10-31 11:24:00.227125: Current learning rate: 0.00731 +2025-10-31 11:24:22.672197: train_loss -0.9885 +2025-10-31 11:24:22.676540: val_loss -0.8988 +2025-10-31 11:24:22.678571: Pseudo dice [np.float32(0.9856), np.float32(0.9934), np.float32(0.9953), np.float32(0.8043)] +2025-10-31 11:24:22.680719: Epoch time: 22.45 s +2025-10-31 11:24:23.884171: +2025-10-31 11:24:23.887047: Epoch 295 +2025-10-31 11:24:23.889362: Current learning rate: 0.0073 +2025-10-31 11:24:46.131694: train_loss -0.9888 +2025-10-31 11:24:46.134101: val_loss -0.8958 +2025-10-31 11:24:46.136154: Pseudo dice [np.float32(0.9843), np.float32(0.9921), np.float32(0.9947), np.float32(0.8062)] +2025-10-31 11:24:46.138173: Epoch time: 22.25 s +2025-10-31 11:24:47.301391: +2025-10-31 11:24:47.303461: Epoch 296 +2025-10-31 11:24:47.305465: Current learning rate: 0.00729 +2025-10-31 11:25:08.058046: train_loss -0.9893 +2025-10-31 11:25:08.060855: val_loss -0.8898 +2025-10-31 11:25:08.062842: Pseudo dice [np.float32(0.9843), np.float32(0.992), np.float32(0.9948), np.float32(0.7854)] +2025-10-31 11:25:08.064697: Epoch time: 20.76 s +2025-10-31 11:25:09.249967: +2025-10-31 11:25:09.252488: Epoch 297 +2025-10-31 11:25:09.254328: Current learning rate: 0.00728 +2025-10-31 11:25:29.515593: train_loss -0.9881 +2025-10-31 11:25:29.518802: val_loss -0.8849 +2025-10-31 11:25:29.520547: Pseudo dice [np.float32(0.9846), np.float32(0.9914), np.float32(0.9947), np.float32(0.7654)] +2025-10-31 11:25:29.522258: Epoch time: 20.27 s +2025-10-31 11:25:30.765074: +2025-10-31 11:25:30.767322: Epoch 298 +2025-10-31 11:25:30.769186: Current learning rate: 0.00727 +2025-10-31 11:25:52.697511: train_loss -0.988 +2025-10-31 11:25:52.700299: val_loss -0.8897 +2025-10-31 11:25:52.702364: Pseudo dice [np.float32(0.9842), np.float32(0.9921), np.float32(0.9948), np.float32(0.787)] +2025-10-31 11:25:52.704392: Epoch time: 21.93 s +2025-10-31 11:25:53.795812: +2025-10-31 11:25:53.797867: Epoch 299 +2025-10-31 11:25:53.800350: Current learning rate: 0.00726 +2025-10-31 11:26:15.753178: train_loss -0.9879 +2025-10-31 11:26:15.756315: val_loss -0.8988 +2025-10-31 11:26:15.758353: Pseudo dice [np.float32(0.9854), np.float32(0.9931), np.float32(0.9953), np.float32(0.7972)] +2025-10-31 11:26:15.760346: Epoch time: 21.96 s +2025-10-31 11:26:17.936538: +2025-10-31 11:26:17.939467: Epoch 300 +2025-10-31 11:26:17.941835: Current learning rate: 0.00725 +2025-10-31 11:26:40.064661: train_loss -0.9881 +2025-10-31 11:26:40.067770: val_loss -0.9018 +2025-10-31 11:26:40.069556: Pseudo dice [np.float32(0.9824), np.float32(0.9926), np.float32(0.9959), np.float32(0.8237)] +2025-10-31 11:26:40.071549: Epoch time: 22.13 s +2025-10-31 11:26:41.349677: +2025-10-31 11:26:41.352408: Epoch 301 +2025-10-31 11:26:41.354784: Current learning rate: 0.00724 +2025-10-31 11:27:03.165359: train_loss -0.9873 +2025-10-31 11:27:03.168216: val_loss -0.8978 +2025-10-31 11:27:03.170264: Pseudo dice [np.float32(0.9871), np.float32(0.9935), np.float32(0.9954), np.float32(0.794)] +2025-10-31 11:27:03.172222: Epoch time: 21.82 s +2025-10-31 11:27:04.410092: +2025-10-31 11:27:04.412189: Epoch 302 +2025-10-31 11:27:04.414085: Current learning rate: 0.00724 +2025-10-31 11:27:24.792380: train_loss -0.9862 +2025-10-31 11:27:24.794791: val_loss -0.8852 +2025-10-31 11:27:24.796604: Pseudo dice [np.float32(0.9849), np.float32(0.9916), np.float32(0.9945), np.float32(0.7679)] +2025-10-31 11:27:24.798572: Epoch time: 20.38 s +2025-10-31 11:27:25.916047: +2025-10-31 11:27:25.917880: Epoch 303 +2025-10-31 11:27:25.919540: Current learning rate: 0.00723 +2025-10-31 11:27:47.833131: train_loss -0.9838 +2025-10-31 11:27:47.836158: val_loss -0.8973 +2025-10-31 11:27:47.837763: Pseudo dice [np.float32(0.9853), np.float32(0.9925), np.float32(0.9954), np.float32(0.7963)] +2025-10-31 11:27:47.839442: Epoch time: 21.92 s +2025-10-31 11:27:49.029447: +2025-10-31 11:27:49.031746: Epoch 304 +2025-10-31 11:27:49.033979: Current learning rate: 0.00722 +2025-10-31 11:28:11.040972: train_loss -0.986 +2025-10-31 11:28:11.044042: val_loss -0.8953 +2025-10-31 11:28:11.046203: Pseudo dice [np.float32(0.9842), np.float32(0.9924), np.float32(0.9948), np.float32(0.7933)] +2025-10-31 11:28:11.048353: Epoch time: 22.01 s +2025-10-31 11:28:12.710950: +2025-10-31 11:28:12.713215: Epoch 305 +2025-10-31 11:28:12.715337: Current learning rate: 0.00721 +2025-10-31 11:28:35.168779: train_loss -0.9872 +2025-10-31 11:28:35.174918: val_loss -0.8957 +2025-10-31 11:28:35.176489: Pseudo dice [np.float32(0.9845), np.float32(0.9928), np.float32(0.9947), np.float32(0.8017)] +2025-10-31 11:28:35.177975: Epoch time: 22.46 s +2025-10-31 11:28:36.354267: +2025-10-31 11:28:36.356103: Epoch 306 +2025-10-31 11:28:36.357897: Current learning rate: 0.0072 +2025-10-31 11:28:58.808557: train_loss -0.9859 +2025-10-31 11:28:58.812334: val_loss -0.9053 +2025-10-31 11:28:58.813938: Pseudo dice [np.float32(0.9836), np.float32(0.9922), np.float32(0.9955), np.float32(0.8203)] +2025-10-31 11:28:58.815577: Epoch time: 22.46 s +2025-10-31 11:29:00.111147: +2025-10-31 11:29:00.113774: Epoch 307 +2025-10-31 11:29:00.116430: Current learning rate: 0.00719 +2025-10-31 11:29:22.373605: train_loss -0.9883 +2025-10-31 11:29:22.376686: val_loss -0.8964 +2025-10-31 11:29:22.378209: Pseudo dice [np.float32(0.9853), np.float32(0.9924), np.float32(0.9951), np.float32(0.7929)] +2025-10-31 11:29:22.379934: Epoch time: 22.26 s +2025-10-31 11:29:23.491569: +2025-10-31 11:29:23.493639: Epoch 308 +2025-10-31 11:29:23.495585: Current learning rate: 0.00718 +2025-10-31 11:29:45.562222: train_loss -0.9881 +2025-10-31 11:29:45.565306: val_loss -0.8952 +2025-10-31 11:29:45.567098: Pseudo dice [np.float32(0.9856), np.float32(0.9923), np.float32(0.9951), np.float32(0.7955)] +2025-10-31 11:29:45.569115: Epoch time: 22.07 s +2025-10-31 11:29:46.580858: +2025-10-31 11:29:46.583498: Epoch 309 +2025-10-31 11:29:46.585936: Current learning rate: 0.00717 +2025-10-31 11:30:07.354211: train_loss -0.9876 +2025-10-31 11:30:07.357972: val_loss -0.8892 +2025-10-31 11:30:07.359974: Pseudo dice [np.float32(0.9843), np.float32(0.9925), np.float32(0.9953), np.float32(0.788)] +2025-10-31 11:30:07.362037: Epoch time: 20.78 s +2025-10-31 11:30:08.385848: +2025-10-31 11:30:08.387952: Epoch 310 +2025-10-31 11:30:08.390219: Current learning rate: 0.00716 +2025-10-31 11:30:30.430759: train_loss -0.988 +2025-10-31 11:30:30.433413: val_loss -0.8919 +2025-10-31 11:30:30.435458: Pseudo dice [np.float32(0.9846), np.float32(0.9913), np.float32(0.9948), np.float32(0.792)] +2025-10-31 11:30:30.437451: Epoch time: 22.05 s +2025-10-31 11:30:31.620960: +2025-10-31 11:30:31.623307: Epoch 311 +2025-10-31 11:30:31.625516: Current learning rate: 0.00715 +2025-10-31 11:30:53.541183: train_loss -0.9877 +2025-10-31 11:30:53.544219: val_loss -0.8878 +2025-10-31 11:30:53.546170: Pseudo dice [np.float32(0.9833), np.float32(0.9927), np.float32(0.9952), np.float32(0.7761)] +2025-10-31 11:30:53.548197: Epoch time: 21.92 s +2025-10-31 11:30:54.607929: +2025-10-31 11:30:54.609915: Epoch 312 +2025-10-31 11:30:54.611986: Current learning rate: 0.00714 +2025-10-31 11:31:16.990131: train_loss -0.9881 +2025-10-31 11:31:16.993701: val_loss -0.9006 +2025-10-31 11:31:16.995584: Pseudo dice [np.float32(0.985), np.float32(0.9922), np.float32(0.9954), np.float32(0.8123)] +2025-10-31 11:31:16.997473: Epoch time: 22.38 s +2025-10-31 11:31:18.260905: +2025-10-31 11:31:18.275361: Epoch 313 +2025-10-31 11:31:18.277936: Current learning rate: 0.00713 +2025-10-31 11:31:40.471931: train_loss -0.9885 +2025-10-31 11:31:40.474809: val_loss -0.8849 +2025-10-31 11:31:40.476980: Pseudo dice [np.float32(0.9833), np.float32(0.9916), np.float32(0.9945), np.float32(0.7777)] +2025-10-31 11:31:40.479127: Epoch time: 22.21 s +2025-10-31 11:31:41.584197: +2025-10-31 11:31:41.586534: Epoch 314 +2025-10-31 11:31:41.588501: Current learning rate: 0.00712 +2025-10-31 11:32:03.584063: train_loss -0.988 +2025-10-31 11:32:03.589925: val_loss -0.8962 +2025-10-31 11:32:03.593935: Pseudo dice [np.float32(0.9853), np.float32(0.9925), np.float32(0.9951), np.float32(0.7963)] +2025-10-31 11:32:03.597366: Epoch time: 22.0 s +2025-10-31 11:32:04.612395: +2025-10-31 11:32:04.616212: Epoch 315 +2025-10-31 11:32:04.619239: Current learning rate: 0.00711 +2025-10-31 11:32:25.355787: train_loss -0.9881 +2025-10-31 11:32:25.359227: val_loss -0.8948 +2025-10-31 11:32:25.361346: Pseudo dice [np.float32(0.9837), np.float32(0.9927), np.float32(0.9949), np.float32(0.8025)] +2025-10-31 11:32:25.363032: Epoch time: 20.75 s +2025-10-31 11:32:26.537222: +2025-10-31 11:32:26.539385: Epoch 316 +2025-10-31 11:32:26.541315: Current learning rate: 0.0071 +2025-10-31 11:32:48.824144: train_loss -0.9891 +2025-10-31 11:32:48.827231: val_loss -0.8882 +2025-10-31 11:32:48.829528: Pseudo dice [np.float32(0.9849), np.float32(0.9923), np.float32(0.9949), np.float32(0.7848)] +2025-10-31 11:32:48.831570: Epoch time: 22.29 s +2025-10-31 11:32:50.188626: +2025-10-31 11:32:50.191071: Epoch 317 +2025-10-31 11:32:50.193387: Current learning rate: 0.0071 +2025-10-31 11:33:12.157006: train_loss -0.9878 +2025-10-31 11:33:12.159907: val_loss -0.9071 +2025-10-31 11:33:12.161798: Pseudo dice [np.float32(0.9853), np.float32(0.9925), np.float32(0.9957), np.float32(0.824)] +2025-10-31 11:33:12.164071: Epoch time: 21.97 s +2025-10-31 11:33:13.954606: +2025-10-31 11:33:13.956747: Epoch 318 +2025-10-31 11:33:13.958593: Current learning rate: 0.00709 +2025-10-31 11:33:35.925985: train_loss -0.9872 +2025-10-31 11:33:35.928911: val_loss -0.8928 +2025-10-31 11:33:35.930416: Pseudo dice [np.float32(0.9857), np.float32(0.9932), np.float32(0.995), np.float32(0.7943)] +2025-10-31 11:33:35.931939: Epoch time: 21.97 s +2025-10-31 11:33:36.989348: +2025-10-31 11:33:36.991755: Epoch 319 +2025-10-31 11:33:36.993860: Current learning rate: 0.00708 +2025-10-31 11:33:58.827887: train_loss -0.9878 +2025-10-31 11:33:58.833165: val_loss -0.8912 +2025-10-31 11:33:58.838292: Pseudo dice [np.float32(0.9853), np.float32(0.993), np.float32(0.9944), np.float32(0.7732)] +2025-10-31 11:33:58.843188: Epoch time: 21.84 s +2025-10-31 11:33:59.879931: +2025-10-31 11:33:59.881963: Epoch 320 +2025-10-31 11:33:59.884044: Current learning rate: 0.00707 +2025-10-31 11:34:21.523159: train_loss -0.9884 +2025-10-31 11:34:21.526532: val_loss -0.8927 +2025-10-31 11:34:21.528786: Pseudo dice [np.float32(0.9858), np.float32(0.9931), np.float32(0.9951), np.float32(0.7892)] +2025-10-31 11:34:21.531071: Epoch time: 21.65 s +2025-10-31 11:34:22.704614: +2025-10-31 11:34:22.706616: Epoch 321 +2025-10-31 11:34:22.708588: Current learning rate: 0.00706 +2025-10-31 11:34:43.917921: train_loss -0.9888 +2025-10-31 11:34:43.921374: val_loss -0.8894 +2025-10-31 11:34:43.924154: Pseudo dice [np.float32(0.9846), np.float32(0.9922), np.float32(0.9948), np.float32(0.7837)] +2025-10-31 11:34:43.926820: Epoch time: 21.21 s +2025-10-31 11:34:45.117537: +2025-10-31 11:34:45.120045: Epoch 322 +2025-10-31 11:34:45.122563: Current learning rate: 0.00705 +2025-10-31 11:35:07.006082: train_loss -0.9887 +2025-10-31 11:35:07.012111: val_loss -0.8907 +2025-10-31 11:35:07.014117: Pseudo dice [np.float32(0.9836), np.float32(0.992), np.float32(0.9949), np.float32(0.7892)] +2025-10-31 11:35:07.016076: Epoch time: 21.89 s +2025-10-31 11:35:08.249869: +2025-10-31 11:35:08.251945: Epoch 323 +2025-10-31 11:35:08.253721: Current learning rate: 0.00704 +2025-10-31 11:35:30.539658: train_loss -0.9889 +2025-10-31 11:35:30.542835: val_loss -0.8878 +2025-10-31 11:35:30.544789: Pseudo dice [np.float32(0.9846), np.float32(0.993), np.float32(0.9949), np.float32(0.7817)] +2025-10-31 11:35:30.546843: Epoch time: 22.29 s +2025-10-31 11:35:31.708717: +2025-10-31 11:35:31.710791: Epoch 324 +2025-10-31 11:35:31.712759: Current learning rate: 0.00703 +2025-10-31 11:35:53.565383: train_loss -0.9881 +2025-10-31 11:35:53.568135: val_loss -0.8904 +2025-10-31 11:35:53.570072: Pseudo dice [np.float32(0.9854), np.float32(0.9927), np.float32(0.9947), np.float32(0.7875)] +2025-10-31 11:35:53.571646: Epoch time: 21.86 s +2025-10-31 11:35:54.796346: +2025-10-31 11:35:54.798655: Epoch 325 +2025-10-31 11:35:54.800714: Current learning rate: 0.00702 +2025-10-31 11:36:17.526159: train_loss -0.988 +2025-10-31 11:36:17.528313: val_loss -0.9075 +2025-10-31 11:36:17.530084: Pseudo dice [np.float32(0.9843), np.float32(0.9922), np.float32(0.9954), np.float32(0.8236)] +2025-10-31 11:36:17.531658: Epoch time: 22.73 s +2025-10-31 11:36:18.741275: +2025-10-31 11:36:18.743499: Epoch 326 +2025-10-31 11:36:18.745764: Current learning rate: 0.00701 +2025-10-31 11:36:40.113915: train_loss -0.9886 +2025-10-31 11:36:40.116245: val_loss -0.8832 +2025-10-31 11:36:40.117857: Pseudo dice [np.float32(0.986), np.float32(0.9935), np.float32(0.9951), np.float32(0.7674)] +2025-10-31 11:36:40.119595: Epoch time: 21.37 s +2025-10-31 11:36:41.309157: +2025-10-31 11:36:41.311985: Epoch 327 +2025-10-31 11:36:41.314258: Current learning rate: 0.007 +2025-10-31 11:37:03.607648: train_loss -0.9884 +2025-10-31 11:37:03.611228: val_loss -0.888 +2025-10-31 11:37:03.613497: Pseudo dice [np.float32(0.9842), np.float32(0.993), np.float32(0.9954), np.float32(0.7845)] +2025-10-31 11:37:03.615608: Epoch time: 22.3 s +2025-10-31 11:37:04.843508: +2025-10-31 11:37:04.845846: Epoch 328 +2025-10-31 11:37:04.847781: Current learning rate: 0.00699 +2025-10-31 11:37:26.599038: train_loss -0.9879 +2025-10-31 11:37:26.601840: val_loss -0.8998 +2025-10-31 11:37:26.603845: Pseudo dice [np.float32(0.9842), np.float32(0.9923), np.float32(0.9953), np.float32(0.8125)] +2025-10-31 11:37:26.605818: Epoch time: 21.76 s +2025-10-31 11:37:27.809268: +2025-10-31 11:37:27.811946: Epoch 329 +2025-10-31 11:37:27.813840: Current learning rate: 0.00698 +2025-10-31 11:37:49.830264: train_loss -0.9879 +2025-10-31 11:37:49.833649: val_loss -0.8938 +2025-10-31 11:37:49.835612: Pseudo dice [np.float32(0.9845), np.float32(0.9926), np.float32(0.9952), np.float32(0.7924)] +2025-10-31 11:37:49.837545: Epoch time: 22.02 s +2025-10-31 11:37:51.506809: +2025-10-31 11:37:51.509317: Epoch 330 +2025-10-31 11:37:51.511377: Current learning rate: 0.00697 +2025-10-31 11:38:14.147772: train_loss -0.988 +2025-10-31 11:38:14.151399: val_loss -0.8895 +2025-10-31 11:38:14.153590: Pseudo dice [np.float32(0.9848), np.float32(0.9927), np.float32(0.9949), np.float32(0.7917)] +2025-10-31 11:38:14.155546: Epoch time: 22.64 s +2025-10-31 11:38:15.319673: +2025-10-31 11:38:15.321625: Epoch 331 +2025-10-31 11:38:15.323470: Current learning rate: 0.00696 +2025-10-31 11:38:37.012066: train_loss -0.9883 +2025-10-31 11:38:37.014495: val_loss -0.9045 +2025-10-31 11:38:37.016321: Pseudo dice [np.float32(0.9854), np.float32(0.9925), np.float32(0.9956), np.float32(0.8096)] +2025-10-31 11:38:37.018247: Epoch time: 21.69 s +2025-10-31 11:38:38.220323: +2025-10-31 11:38:38.222973: Epoch 332 +2025-10-31 11:38:38.225269: Current learning rate: 0.00696 +2025-10-31 11:39:00.519228: train_loss -0.9876 +2025-10-31 11:39:00.522014: val_loss -0.904 +2025-10-31 11:39:00.524232: Pseudo dice [np.float32(0.9862), np.float32(0.9925), np.float32(0.9958), np.float32(0.8066)] +2025-10-31 11:39:00.526564: Epoch time: 22.3 s +2025-10-31 11:39:01.667967: +2025-10-31 11:39:01.670164: Epoch 333 +2025-10-31 11:39:01.672094: Current learning rate: 0.00695 +2025-10-31 11:39:23.062668: train_loss -0.9865 +2025-10-31 11:39:23.065751: val_loss -0.8922 +2025-10-31 11:39:23.067549: Pseudo dice [np.float32(0.9856), np.float32(0.9924), np.float32(0.9949), np.float32(0.778)] +2025-10-31 11:39:23.069487: Epoch time: 21.4 s +2025-10-31 11:39:24.275045: +2025-10-31 11:39:24.277374: Epoch 334 +2025-10-31 11:39:24.279347: Current learning rate: 0.00694 +2025-10-31 11:39:45.739751: train_loss -0.9834 +2025-10-31 11:39:45.745819: val_loss -0.8895 +2025-10-31 11:39:45.748051: Pseudo dice [np.float32(0.9845), np.float32(0.9929), np.float32(0.9931), np.float32(0.7822)] +2025-10-31 11:39:45.750207: Epoch time: 21.47 s +2025-10-31 11:39:46.994525: +2025-10-31 11:39:46.999630: Epoch 335 +2025-10-31 11:39:47.001708: Current learning rate: 0.00693 +2025-10-31 11:40:08.595071: train_loss -0.9824 +2025-10-31 11:40:08.599229: val_loss -0.8963 +2025-10-31 11:40:08.601106: Pseudo dice [np.float32(0.984), np.float32(0.9922), np.float32(0.9952), np.float32(0.7935)] +2025-10-31 11:40:08.602990: Epoch time: 21.6 s +2025-10-31 11:40:09.798417: +2025-10-31 11:40:09.800983: Epoch 336 +2025-10-31 11:40:09.803198: Current learning rate: 0.00692 +2025-10-31 11:40:32.173447: train_loss -0.9809 +2025-10-31 11:40:32.176940: val_loss -0.9024 +2025-10-31 11:40:32.179614: Pseudo dice [np.float32(0.9841), np.float32(0.9914), np.float32(0.9945), np.float32(0.8175)] +2025-10-31 11:40:32.181603: Epoch time: 22.38 s +2025-10-31 11:40:33.415809: +2025-10-31 11:40:33.417840: Epoch 337 +2025-10-31 11:40:33.419924: Current learning rate: 0.00691 +2025-10-31 11:40:56.073900: train_loss -0.9633 +2025-10-31 11:40:56.076576: val_loss -0.9077 +2025-10-31 11:40:56.078575: Pseudo dice [np.float32(0.9816), np.float32(0.99), np.float32(0.9948), np.float32(0.8008)] +2025-10-31 11:40:56.080389: Epoch time: 22.66 s +2025-10-31 11:40:57.189344: +2025-10-31 11:40:57.191277: Epoch 338 +2025-10-31 11:40:57.193707: Current learning rate: 0.0069 +2025-10-31 11:41:18.617043: train_loss -0.9669 +2025-10-31 11:41:18.620574: val_loss -0.9041 +2025-10-31 11:41:18.623192: Pseudo dice [np.float32(0.9827), np.float32(0.9904), np.float32(0.9947), np.float32(0.797)] +2025-10-31 11:41:18.625471: Epoch time: 21.43 s +2025-10-31 11:41:19.876256: +2025-10-31 11:41:19.878524: Epoch 339 +2025-10-31 11:41:19.880465: Current learning rate: 0.00689 +2025-10-31 11:41:42.347455: train_loss -0.9783 +2025-10-31 11:41:42.351334: val_loss -0.9 +2025-10-31 11:41:42.353441: Pseudo dice [np.float32(0.9849), np.float32(0.9911), np.float32(0.9945), np.float32(0.7889)] +2025-10-31 11:41:42.355570: Epoch time: 22.47 s +2025-10-31 11:41:43.550302: +2025-10-31 11:41:43.552328: Epoch 340 +2025-10-31 11:41:43.554220: Current learning rate: 0.00688 +2025-10-31 11:42:05.175663: train_loss -0.9827 +2025-10-31 11:42:05.177807: val_loss -0.8956 +2025-10-31 11:42:05.180272: Pseudo dice [np.float32(0.985), np.float32(0.9919), np.float32(0.9948), np.float32(0.7815)] +2025-10-31 11:42:05.182030: Epoch time: 21.63 s +2025-10-31 11:42:06.271212: +2025-10-31 11:42:06.274014: Epoch 341 +2025-10-31 11:42:06.275899: Current learning rate: 0.00687 +2025-10-31 11:42:28.602227: train_loss -0.9847 +2025-10-31 11:42:28.605443: val_loss -0.8971 +2025-10-31 11:42:28.607698: Pseudo dice [np.float32(0.9832), np.float32(0.9915), np.float32(0.9947), np.float32(0.7934)] +2025-10-31 11:42:28.609839: Epoch time: 22.33 s +2025-10-31 11:42:29.672158: +2025-10-31 11:42:29.674260: Epoch 342 +2025-10-31 11:42:29.676076: Current learning rate: 0.00686 +2025-10-31 11:42:52.115434: train_loss -0.9824 +2025-10-31 11:42:52.119242: val_loss -0.9061 +2025-10-31 11:42:52.121539: Pseudo dice [np.float32(0.9825), np.float32(0.9915), np.float32(0.9955), np.float32(0.8176)] +2025-10-31 11:42:52.123920: Epoch time: 22.45 s +2025-10-31 11:42:54.348458: +2025-10-31 11:42:54.353054: Epoch 343 +2025-10-31 11:42:54.359453: Current learning rate: 0.00685 +2025-10-31 11:43:16.196665: train_loss -0.9808 +2025-10-31 11:43:16.199008: val_loss -0.8985 +2025-10-31 11:43:16.200948: Pseudo dice [np.float32(0.9834), np.float32(0.9915), np.float32(0.9945), np.float32(0.7987)] +2025-10-31 11:43:16.202893: Epoch time: 21.85 s +2025-10-31 11:43:17.214175: +2025-10-31 11:43:17.216093: Epoch 344 +2025-10-31 11:43:17.217966: Current learning rate: 0.00684 +2025-10-31 11:43:38.429611: train_loss -0.9794 +2025-10-31 11:43:38.431721: val_loss -0.8913 +2025-10-31 11:43:38.433254: Pseudo dice [np.float32(0.9852), np.float32(0.9926), np.float32(0.9945), np.float32(0.77)] +2025-10-31 11:43:38.434997: Epoch time: 21.22 s +2025-10-31 11:43:39.323561: +2025-10-31 11:43:39.325442: Epoch 345 +2025-10-31 11:43:39.327080: Current learning rate: 0.00683 +2025-10-31 11:44:01.246760: train_loss -0.9809 +2025-10-31 11:44:01.249188: val_loss -0.9093 +2025-10-31 11:44:01.251016: Pseudo dice [np.float32(0.9841), np.float32(0.9927), np.float32(0.9954), np.float32(0.8148)] +2025-10-31 11:44:01.252624: Epoch time: 21.92 s +2025-10-31 11:44:02.367615: +2025-10-31 11:44:02.372219: Epoch 346 +2025-10-31 11:44:02.374120: Current learning rate: 0.00682 +2025-10-31 11:44:24.765963: train_loss -0.9844 +2025-10-31 11:44:24.768651: val_loss -0.8999 +2025-10-31 11:44:24.771284: Pseudo dice [np.float32(0.9843), np.float32(0.9926), np.float32(0.9949), np.float32(0.7987)] +2025-10-31 11:44:24.773540: Epoch time: 22.4 s +2025-10-31 11:44:25.812824: +2025-10-31 11:44:25.815129: Epoch 347 +2025-10-31 11:44:25.817379: Current learning rate: 0.00681 +2025-10-31 11:44:47.467407: train_loss -0.9856 +2025-10-31 11:44:47.470330: val_loss -0.895 +2025-10-31 11:44:47.472102: Pseudo dice [np.float32(0.9845), np.float32(0.9928), np.float32(0.9953), np.float32(0.7885)] +2025-10-31 11:44:47.473952: Epoch time: 21.66 s +2025-10-31 11:44:48.720164: +2025-10-31 11:44:48.722689: Epoch 348 +2025-10-31 11:44:48.724574: Current learning rate: 0.0068 +2025-10-31 11:45:10.603357: train_loss -0.9874 +2025-10-31 11:45:10.606276: val_loss -0.9005 +2025-10-31 11:45:10.607898: Pseudo dice [np.float32(0.9855), np.float32(0.993), np.float32(0.9951), np.float32(0.7945)] +2025-10-31 11:45:10.609709: Epoch time: 21.88 s +2025-10-31 11:45:11.694818: +2025-10-31 11:45:11.696937: Epoch 349 +2025-10-31 11:45:11.699948: Current learning rate: 0.0068 +2025-10-31 11:45:34.327670: train_loss -0.987 +2025-10-31 11:45:34.330303: val_loss -0.9105 +2025-10-31 11:45:34.332281: Pseudo dice [np.float32(0.9856), np.float32(0.9937), np.float32(0.996), np.float32(0.8195)] +2025-10-31 11:45:34.334157: Epoch time: 22.63 s +2025-10-31 11:45:36.708785: +2025-10-31 11:45:36.710946: Epoch 350 +2025-10-31 11:45:36.712833: Current learning rate: 0.00679 +2025-10-31 11:45:57.650732: train_loss -0.9863 +2025-10-31 11:45:57.653599: val_loss -0.9052 +2025-10-31 11:45:57.655507: Pseudo dice [np.float32(0.9863), np.float32(0.9934), np.float32(0.9956), np.float32(0.8104)] +2025-10-31 11:45:57.657450: Epoch time: 20.94 s +2025-10-31 11:45:58.853032: +2025-10-31 11:45:58.855016: Epoch 351 +2025-10-31 11:45:58.856745: Current learning rate: 0.00678 +2025-10-31 11:46:21.273327: train_loss -0.9833 +2025-10-31 11:46:21.277007: val_loss -0.894 +2025-10-31 11:46:21.279034: Pseudo dice [np.float32(0.9867), np.float32(0.9921), np.float32(0.9945), np.float32(0.782)] +2025-10-31 11:46:21.282512: Epoch time: 22.42 s +2025-10-31 11:46:22.371006: +2025-10-31 11:46:22.373515: Epoch 352 +2025-10-31 11:46:22.375612: Current learning rate: 0.00677 +2025-10-31 11:46:44.581621: train_loss -0.9836 +2025-10-31 11:46:44.585339: val_loss -0.8979 +2025-10-31 11:46:44.587054: Pseudo dice [np.float32(0.9847), np.float32(0.9906), np.float32(0.9947), np.float32(0.7925)] +2025-10-31 11:46:44.588752: Epoch time: 22.21 s +2025-10-31 11:46:45.796477: +2025-10-31 11:46:45.798238: Epoch 353 +2025-10-31 11:46:45.799817: Current learning rate: 0.00676 +2025-10-31 11:47:07.282807: train_loss -0.9851 +2025-10-31 11:47:07.285866: val_loss -0.8982 +2025-10-31 11:47:07.287720: Pseudo dice [np.float32(0.9843), np.float32(0.9916), np.float32(0.9948), np.float32(0.7947)] +2025-10-31 11:47:07.289709: Epoch time: 21.49 s +2025-10-31 11:47:08.431886: +2025-10-31 11:47:08.434148: Epoch 354 +2025-10-31 11:47:08.436182: Current learning rate: 0.00675 +2025-10-31 11:47:29.781245: train_loss -0.9854 +2025-10-31 11:47:29.784022: val_loss -0.8939 +2025-10-31 11:47:29.785470: Pseudo dice [np.float32(0.9855), np.float32(0.9921), np.float32(0.9948), np.float32(0.7825)] +2025-10-31 11:47:29.787304: Epoch time: 21.35 s +2025-10-31 11:47:31.498668: +2025-10-31 11:47:31.500804: Epoch 355 +2025-10-31 11:47:31.502493: Current learning rate: 0.00674 +2025-10-31 11:47:53.910432: train_loss -0.9848 +2025-10-31 11:47:53.914049: val_loss -0.8896 +2025-10-31 11:47:53.916680: Pseudo dice [np.float32(0.9833), np.float32(0.9917), np.float32(0.9948), np.float32(0.7784)] +2025-10-31 11:47:53.919263: Epoch time: 22.41 s +2025-10-31 11:47:55.089871: +2025-10-31 11:47:55.091910: Epoch 356 +2025-10-31 11:47:55.093972: Current learning rate: 0.00673 +2025-10-31 11:48:16.616025: train_loss -0.9862 +2025-10-31 11:48:16.619953: val_loss -0.8958 +2025-10-31 11:48:16.621689: Pseudo dice [np.float32(0.9843), np.float32(0.9921), np.float32(0.995), np.float32(0.7946)] +2025-10-31 11:48:16.623366: Epoch time: 21.53 s +2025-10-31 11:48:17.841810: +2025-10-31 11:48:17.844252: Epoch 357 +2025-10-31 11:48:17.846467: Current learning rate: 0.00672 +2025-10-31 11:48:39.863039: train_loss -0.9859 +2025-10-31 11:48:39.866062: val_loss -0.8943 +2025-10-31 11:48:39.870665: Pseudo dice [np.float32(0.9852), np.float32(0.9933), np.float32(0.9952), np.float32(0.785)] +2025-10-31 11:48:39.872669: Epoch time: 22.02 s +2025-10-31 11:48:40.990020: +2025-10-31 11:48:40.992667: Epoch 358 +2025-10-31 11:48:40.994709: Current learning rate: 0.00671 +2025-10-31 11:49:02.723346: train_loss -0.988 +2025-10-31 11:49:02.725771: val_loss -0.8984 +2025-10-31 11:49:02.727514: Pseudo dice [np.float32(0.985), np.float32(0.9932), np.float32(0.9956), np.float32(0.7932)] +2025-10-31 11:49:02.729375: Epoch time: 21.73 s +2025-10-31 11:49:04.024691: +2025-10-31 11:49:04.026966: Epoch 359 +2025-10-31 11:49:04.029113: Current learning rate: 0.0067 +2025-10-31 11:49:25.228579: train_loss -0.9883 +2025-10-31 11:49:25.231270: val_loss -0.8936 +2025-10-31 11:49:25.233156: Pseudo dice [np.float32(0.9852), np.float32(0.9925), np.float32(0.9949), np.float32(0.7881)] +2025-10-31 11:49:25.234823: Epoch time: 21.21 s +2025-10-31 11:49:26.436230: +2025-10-31 11:49:26.438427: Epoch 360 +2025-10-31 11:49:26.440172: Current learning rate: 0.00669 +2025-10-31 11:49:48.511525: train_loss -0.9875 +2025-10-31 11:49:48.514626: val_loss -0.8806 +2025-10-31 11:49:48.516894: Pseudo dice [np.float32(0.9856), np.float32(0.9923), np.float32(0.9942), np.float32(0.7614)] +2025-10-31 11:49:48.518575: Epoch time: 22.08 s +2025-10-31 11:49:49.698737: +2025-10-31 11:49:49.700976: Epoch 361 +2025-10-31 11:49:49.702959: Current learning rate: 0.00668 +2025-10-31 11:50:11.645276: train_loss -0.986 +2025-10-31 11:50:11.647624: val_loss -0.8974 +2025-10-31 11:50:11.649741: Pseudo dice [np.float32(0.9833), np.float32(0.9912), np.float32(0.9953), np.float32(0.7966)] +2025-10-31 11:50:11.651946: Epoch time: 21.95 s +2025-10-31 11:50:12.796065: +2025-10-31 11:50:12.801147: Epoch 362 +2025-10-31 11:50:12.803106: Current learning rate: 0.00667 +2025-10-31 11:50:33.676779: train_loss -0.9878 +2025-10-31 11:50:33.679365: val_loss -0.897 +2025-10-31 11:50:33.681197: Pseudo dice [np.float32(0.9836), np.float32(0.9919), np.float32(0.9951), np.float32(0.7934)] +2025-10-31 11:50:33.683414: Epoch time: 20.88 s +2025-10-31 11:50:34.885387: +2025-10-31 11:50:34.887179: Epoch 363 +2025-10-31 11:50:34.888788: Current learning rate: 0.00666 +2025-10-31 11:50:57.040220: train_loss -0.9856 +2025-10-31 11:50:57.043377: val_loss -0.9004 +2025-10-31 11:50:57.045260: Pseudo dice [np.float32(0.9832), np.float32(0.9923), np.float32(0.995), np.float32(0.8037)] +2025-10-31 11:50:57.047071: Epoch time: 22.16 s +2025-10-31 11:50:58.299236: +2025-10-31 11:50:58.301085: Epoch 364 +2025-10-31 11:50:58.302755: Current learning rate: 0.00665 +2025-10-31 11:51:21.200645: train_loss -0.9875 +2025-10-31 11:51:21.203830: val_loss -0.8925 +2025-10-31 11:51:21.205377: Pseudo dice [np.float32(0.9849), np.float32(0.9917), np.float32(0.9952), np.float32(0.7866)] +2025-10-31 11:51:21.206885: Epoch time: 22.9 s +2025-10-31 11:51:22.474753: +2025-10-31 11:51:22.476794: Epoch 365 +2025-10-31 11:51:22.479495: Current learning rate: 0.00665 +2025-10-31 11:51:44.461201: train_loss -0.9877 +2025-10-31 11:51:44.463382: val_loss -0.8881 +2025-10-31 11:51:44.465116: Pseudo dice [np.float32(0.9833), np.float32(0.9924), np.float32(0.9949), np.float32(0.7749)] +2025-10-31 11:51:44.466614: Epoch time: 21.99 s +2025-10-31 11:51:45.582263: +2025-10-31 11:51:45.584011: Epoch 366 +2025-10-31 11:51:45.585594: Current learning rate: 0.00664 +2025-10-31 11:52:06.963018: train_loss -0.9885 +2025-10-31 11:52:06.968951: val_loss -0.893 +2025-10-31 11:52:06.970655: Pseudo dice [np.float32(0.9828), np.float32(0.9919), np.float32(0.9949), np.float32(0.7925)] +2025-10-31 11:52:06.972408: Epoch time: 21.38 s +2025-10-31 11:52:08.689387: +2025-10-31 11:52:08.691754: Epoch 367 +2025-10-31 11:52:08.694175: Current learning rate: 0.00663 +2025-10-31 11:52:30.908029: train_loss -0.9879 +2025-10-31 11:52:30.914018: val_loss -0.898 +2025-10-31 11:52:30.918825: Pseudo dice [np.float32(0.985), np.float32(0.9932), np.float32(0.9957), np.float32(0.8019)] +2025-10-31 11:52:30.920794: Epoch time: 22.22 s +2025-10-31 11:52:32.210253: +2025-10-31 11:52:32.212737: Epoch 368 +2025-10-31 11:52:32.214525: Current learning rate: 0.00662 +2025-10-31 11:52:53.326002: train_loss -0.9877 +2025-10-31 11:52:53.328757: val_loss -0.8983 +2025-10-31 11:52:53.330381: Pseudo dice [np.float32(0.9849), np.float32(0.9919), np.float32(0.9952), np.float32(0.8047)] +2025-10-31 11:52:53.332085: Epoch time: 21.12 s +2025-10-31 11:52:54.558716: +2025-10-31 11:52:54.561052: Epoch 369 +2025-10-31 11:52:54.562771: Current learning rate: 0.00661 +2025-10-31 11:53:17.375904: train_loss -0.9885 +2025-10-31 11:53:17.379436: val_loss -0.8909 +2025-10-31 11:53:17.380964: Pseudo dice [np.float32(0.9856), np.float32(0.9926), np.float32(0.9952), np.float32(0.7806)] +2025-10-31 11:53:17.382626: Epoch time: 22.82 s +2025-10-31 11:53:18.416949: +2025-10-31 11:53:18.419002: Epoch 370 +2025-10-31 11:53:18.420830: Current learning rate: 0.0066 +2025-10-31 11:53:40.663609: train_loss -0.989 +2025-10-31 11:53:40.665664: val_loss -0.8947 +2025-10-31 11:53:40.667338: Pseudo dice [np.float32(0.9845), np.float32(0.9925), np.float32(0.9955), np.float32(0.7941)] +2025-10-31 11:53:40.669049: Epoch time: 22.25 s +2025-10-31 11:53:41.805253: +2025-10-31 11:53:41.807422: Epoch 371 +2025-10-31 11:53:41.809130: Current learning rate: 0.00659 +2025-10-31 11:54:04.675202: train_loss -0.9886 +2025-10-31 11:54:04.681593: val_loss -0.8951 +2025-10-31 11:54:04.683335: Pseudo dice [np.float32(0.9844), np.float32(0.9922), np.float32(0.9952), np.float32(0.7951)] +2025-10-31 11:54:04.685087: Epoch time: 22.87 s +2025-10-31 11:54:05.862411: +2025-10-31 11:54:05.864381: Epoch 372 +2025-10-31 11:54:05.866045: Current learning rate: 0.00658 +2025-10-31 11:54:27.109713: train_loss -0.99 +2025-10-31 11:54:27.112608: val_loss -0.8987 +2025-10-31 11:54:27.114273: Pseudo dice [np.float32(0.9841), np.float32(0.9921), np.float32(0.9953), np.float32(0.8024)] +2025-10-31 11:54:27.115997: Epoch time: 21.25 s +2025-10-31 11:54:28.332280: +2025-10-31 11:54:28.334618: Epoch 373 +2025-10-31 11:54:28.336371: Current learning rate: 0.00657 +2025-10-31 11:54:50.278874: train_loss -0.9896 +2025-10-31 11:54:50.281580: val_loss -0.8874 +2025-10-31 11:54:50.283456: Pseudo dice [np.float32(0.9843), np.float32(0.9923), np.float32(0.9946), np.float32(0.7717)] +2025-10-31 11:54:50.285249: Epoch time: 21.95 s +2025-10-31 11:54:51.436786: +2025-10-31 11:54:51.438795: Epoch 374 +2025-10-31 11:54:51.440707: Current learning rate: 0.00656 +2025-10-31 11:55:13.399362: train_loss -0.9885 +2025-10-31 11:55:13.404159: val_loss -0.8895 +2025-10-31 11:55:13.406462: Pseudo dice [np.float32(0.9836), np.float32(0.9917), np.float32(0.995), np.float32(0.7832)] +2025-10-31 11:55:13.408737: Epoch time: 21.96 s +2025-10-31 11:55:14.508981: +2025-10-31 11:55:14.510922: Epoch 375 +2025-10-31 11:55:14.512648: Current learning rate: 0.00655 +2025-10-31 11:55:36.308584: train_loss -0.9897 +2025-10-31 11:55:36.310918: val_loss -0.8929 +2025-10-31 11:55:36.312452: Pseudo dice [np.float32(0.986), np.float32(0.9925), np.float32(0.9948), np.float32(0.7907)] +2025-10-31 11:55:36.313907: Epoch time: 21.8 s +2025-10-31 11:55:37.443926: +2025-10-31 11:55:37.445887: Epoch 376 +2025-10-31 11:55:37.447695: Current learning rate: 0.00654 +2025-10-31 11:55:59.751951: train_loss -0.9888 +2025-10-31 11:55:59.755436: val_loss -0.8935 +2025-10-31 11:55:59.757300: Pseudo dice [np.float32(0.9857), np.float32(0.9929), np.float32(0.9949), np.float32(0.7923)] +2025-10-31 11:55:59.759079: Epoch time: 22.31 s +2025-10-31 11:56:00.838499: +2025-10-31 11:56:00.840580: Epoch 377 +2025-10-31 11:56:00.842598: Current learning rate: 0.00653 +2025-10-31 11:56:22.983964: train_loss -0.9882 +2025-10-31 11:56:22.986699: val_loss -0.889 +2025-10-31 11:56:22.988750: Pseudo dice [np.float32(0.9858), np.float32(0.9922), np.float32(0.994), np.float32(0.7766)] +2025-10-31 11:56:22.990521: Epoch time: 22.15 s +2025-10-31 11:56:24.214009: +2025-10-31 11:56:24.215839: Epoch 378 +2025-10-31 11:56:24.217933: Current learning rate: 0.00652 +2025-10-31 11:56:46.156465: train_loss -0.9893 +2025-10-31 11:56:46.159670: val_loss -0.8994 +2025-10-31 11:56:46.161387: Pseudo dice [np.float32(0.9856), np.float32(0.9929), np.float32(0.9953), np.float32(0.8002)] +2025-10-31 11:56:46.163632: Epoch time: 21.94 s +2025-10-31 11:56:47.387630: +2025-10-31 11:56:47.389656: Epoch 379 +2025-10-31 11:56:47.391361: Current learning rate: 0.00651 +2025-10-31 11:57:09.320429: train_loss -0.9883 +2025-10-31 11:57:09.324737: val_loss -0.8915 +2025-10-31 11:57:09.326813: Pseudo dice [np.float32(0.9844), np.float32(0.9926), np.float32(0.9949), np.float32(0.7791)] +2025-10-31 11:57:09.328552: Epoch time: 21.93 s +2025-10-31 11:57:10.772676: +2025-10-31 11:57:10.774861: Epoch 380 +2025-10-31 11:57:10.776799: Current learning rate: 0.0065 +2025-10-31 11:57:31.949855: train_loss -0.9897 +2025-10-31 11:57:31.955078: val_loss -0.8921 +2025-10-31 11:57:31.956963: Pseudo dice [np.float32(0.9849), np.float32(0.9923), np.float32(0.9947), np.float32(0.7876)] +2025-10-31 11:57:31.958793: Epoch time: 21.18 s +2025-10-31 11:57:33.203698: +2025-10-31 11:57:33.206161: Epoch 381 +2025-10-31 11:57:33.211997: Current learning rate: 0.00649 +2025-10-31 11:57:55.592584: train_loss -0.989 +2025-10-31 11:57:55.597979: val_loss -0.8999 +2025-10-31 11:57:55.599619: Pseudo dice [np.float32(0.9858), np.float32(0.9923), np.float32(0.9951), np.float32(0.8058)] +2025-10-31 11:57:55.601148: Epoch time: 22.39 s +2025-10-31 11:57:56.819926: +2025-10-31 11:57:56.821690: Epoch 382 +2025-10-31 11:57:56.823193: Current learning rate: 0.00648 +2025-10-31 11:58:19.271525: train_loss -0.9892 +2025-10-31 11:58:19.275620: val_loss -0.9081 +2025-10-31 11:58:19.277981: Pseudo dice [np.float32(0.9846), np.float32(0.9923), np.float32(0.9955), np.float32(0.825)] +2025-10-31 11:58:19.281168: Epoch time: 22.45 s +2025-10-31 11:58:20.521211: +2025-10-31 11:58:20.523656: Epoch 383 +2025-10-31 11:58:20.525643: Current learning rate: 0.00648 +2025-10-31 11:58:42.143004: train_loss -0.9891 +2025-10-31 11:58:42.145607: val_loss -0.8927 +2025-10-31 11:58:42.147159: Pseudo dice [np.float32(0.9839), np.float32(0.9914), np.float32(0.995), np.float32(0.7954)] +2025-10-31 11:58:42.148775: Epoch time: 21.62 s +2025-10-31 11:58:43.370466: +2025-10-31 11:58:43.372591: Epoch 384 +2025-10-31 11:58:43.374480: Current learning rate: 0.00647 +2025-10-31 11:59:05.808214: train_loss -0.9895 +2025-10-31 11:59:05.811291: val_loss -0.8877 +2025-10-31 11:59:05.812710: Pseudo dice [np.float32(0.9849), np.float32(0.9917), np.float32(0.9944), np.float32(0.7755)] +2025-10-31 11:59:05.814130: Epoch time: 22.44 s +2025-10-31 11:59:06.857046: +2025-10-31 11:59:06.858706: Epoch 385 +2025-10-31 11:59:06.860298: Current learning rate: 0.00646 +2025-10-31 11:59:27.844871: train_loss -0.9886 +2025-10-31 11:59:27.847102: val_loss -0.8895 +2025-10-31 11:59:27.848845: Pseudo dice [np.float32(0.9847), np.float32(0.992), np.float32(0.9946), np.float32(0.7773)] +2025-10-31 11:59:27.850438: Epoch time: 20.99 s +2025-10-31 11:59:29.059014: +2025-10-31 11:59:29.061284: Epoch 386 +2025-10-31 11:59:29.063054: Current learning rate: 0.00645 +2025-10-31 11:59:50.408288: train_loss -0.9893 +2025-10-31 11:59:50.411153: val_loss -0.8902 +2025-10-31 11:59:50.413150: Pseudo dice [np.float32(0.9847), np.float32(0.9923), np.float32(0.9948), np.float32(0.7819)] +2025-10-31 11:59:50.415111: Epoch time: 21.35 s +2025-10-31 11:59:51.688853: +2025-10-31 11:59:51.690533: Epoch 387 +2025-10-31 11:59:51.691960: Current learning rate: 0.00644 +2025-10-31 12:00:13.648312: train_loss -0.9894 +2025-10-31 12:00:13.652330: val_loss -0.8929 +2025-10-31 12:00:13.654127: Pseudo dice [np.float32(0.9843), np.float32(0.9923), np.float32(0.9954), np.float32(0.7989)] +2025-10-31 12:00:13.656475: Epoch time: 21.96 s +2025-10-31 12:00:14.962770: +2025-10-31 12:00:14.964670: Epoch 388 +2025-10-31 12:00:14.966428: Current learning rate: 0.00643 +2025-10-31 12:00:37.049361: train_loss -0.9892 +2025-10-31 12:00:37.051768: val_loss -0.8916 +2025-10-31 12:00:37.053288: Pseudo dice [np.float32(0.9831), np.float32(0.9924), np.float32(0.9953), np.float32(0.7908)] +2025-10-31 12:00:37.054945: Epoch time: 22.09 s +2025-10-31 12:00:38.174234: +2025-10-31 12:00:38.176309: Epoch 389 +2025-10-31 12:00:38.178184: Current learning rate: 0.00642 +2025-10-31 12:01:00.545813: train_loss -0.9901 +2025-10-31 12:01:00.549028: val_loss -0.881 +2025-10-31 12:01:00.550802: Pseudo dice [np.float32(0.9827), np.float32(0.9911), np.float32(0.9944), np.float32(0.768)] +2025-10-31 12:01:00.552487: Epoch time: 22.37 s +2025-10-31 12:01:01.787326: +2025-10-31 12:01:01.789150: Epoch 390 +2025-10-31 12:01:01.790719: Current learning rate: 0.00641 +2025-10-31 12:01:23.334289: train_loss -0.9887 +2025-10-31 12:01:23.336895: val_loss -0.8797 +2025-10-31 12:01:23.338666: Pseudo dice [np.float32(0.9835), np.float32(0.9918), np.float32(0.9948), np.float32(0.7665)] +2025-10-31 12:01:23.340180: Epoch time: 21.55 s +2025-10-31 12:01:24.917946: +2025-10-31 12:01:24.919895: Epoch 391 +2025-10-31 12:01:24.921683: Current learning rate: 0.0064 +2025-10-31 12:01:46.312541: train_loss -0.9882 +2025-10-31 12:01:46.320646: val_loss -0.8916 +2025-10-31 12:01:46.324387: Pseudo dice [np.float32(0.9854), np.float32(0.9923), np.float32(0.9946), np.float32(0.7861)] +2025-10-31 12:01:46.354256: Epoch time: 21.4 s +2025-10-31 12:01:47.346393: +2025-10-31 12:01:47.348543: Epoch 392 +2025-10-31 12:01:47.350217: Current learning rate: 0.00639 +2025-10-31 12:02:06.366390: train_loss -0.9883 +2025-10-31 12:02:06.379704: val_loss -0.8856 +2025-10-31 12:02:06.386460: Pseudo dice [np.float32(0.9833), np.float32(0.9917), np.float32(0.9948), np.float32(0.7851)] +2025-10-31 12:02:06.393423: Epoch time: 19.02 s +2025-10-31 12:02:07.711224: +2025-10-31 12:02:07.713719: Epoch 393 +2025-10-31 12:02:07.716112: Current learning rate: 0.00638 +2025-10-31 12:02:29.046637: train_loss -0.9886 +2025-10-31 12:02:29.049441: val_loss -0.8868 +2025-10-31 12:02:29.051756: Pseudo dice [np.float32(0.9847), np.float32(0.9922), np.float32(0.9948), np.float32(0.7771)] +2025-10-31 12:02:29.053880: Epoch time: 21.34 s +2025-10-31 12:02:30.218264: +2025-10-31 12:02:30.219972: Epoch 394 +2025-10-31 12:02:30.221953: Current learning rate: 0.00637 +2025-10-31 12:02:52.656480: train_loss -0.989 +2025-10-31 12:02:52.659040: val_loss -0.891 +2025-10-31 12:02:52.661048: Pseudo dice [np.float32(0.9834), np.float32(0.9919), np.float32(0.9952), np.float32(0.7934)] +2025-10-31 12:02:52.663033: Epoch time: 22.44 s +2025-10-31 12:02:53.738458: +2025-10-31 12:02:53.740694: Epoch 395 +2025-10-31 12:02:53.742893: Current learning rate: 0.00636 +2025-10-31 12:03:15.944534: train_loss -0.9888 +2025-10-31 12:03:15.947449: val_loss -0.8957 +2025-10-31 12:03:15.948987: Pseudo dice [np.float32(0.9848), np.float32(0.9926), np.float32(0.9951), np.float32(0.7929)] +2025-10-31 12:03:15.950474: Epoch time: 22.21 s +2025-10-31 12:03:17.230515: +2025-10-31 12:03:17.232668: Epoch 396 +2025-10-31 12:03:17.234300: Current learning rate: 0.00635 +2025-10-31 12:03:39.291271: train_loss -0.9892 +2025-10-31 12:03:39.298173: val_loss -0.8917 +2025-10-31 12:03:39.300038: Pseudo dice [np.float32(0.9854), np.float32(0.9924), np.float32(0.9951), np.float32(0.7912)] +2025-10-31 12:03:39.301771: Epoch time: 22.06 s +2025-10-31 12:03:40.530578: +2025-10-31 12:03:40.532882: Epoch 397 +2025-10-31 12:03:40.534591: Current learning rate: 0.00634 +2025-10-31 12:04:03.325529: train_loss -0.9894 +2025-10-31 12:04:03.328980: val_loss -0.8984 +2025-10-31 12:04:03.330535: Pseudo dice [np.float32(0.9848), np.float32(0.9927), np.float32(0.9948), np.float32(0.7996)] +2025-10-31 12:04:03.332322: Epoch time: 22.8 s +2025-10-31 12:04:04.577601: +2025-10-31 12:04:04.580496: Epoch 398 +2025-10-31 12:04:04.582244: Current learning rate: 0.00633 +2025-10-31 12:04:24.445175: train_loss -0.9891 +2025-10-31 12:04:24.448952: val_loss -0.9003 +2025-10-31 12:04:24.450748: Pseudo dice [np.float32(0.9857), np.float32(0.9924), np.float32(0.9952), np.float32(0.8079)] +2025-10-31 12:04:24.452502: Epoch time: 19.87 s +2025-10-31 12:04:25.663800: +2025-10-31 12:04:25.665682: Epoch 399 +2025-10-31 12:04:25.667514: Current learning rate: 0.00632 +2025-10-31 12:04:48.203776: train_loss -0.9883 +2025-10-31 12:04:48.207533: val_loss -0.8999 +2025-10-31 12:04:48.209457: Pseudo dice [np.float32(0.9834), np.float32(0.9921), np.float32(0.9951), np.float32(0.8108)] +2025-10-31 12:04:48.211374: Epoch time: 22.54 s +2025-10-31 12:04:50.433334: +2025-10-31 12:04:50.435693: Epoch 400 +2025-10-31 12:04:50.437574: Current learning rate: 0.00631 +2025-10-31 12:05:12.258719: train_loss -0.9893 +2025-10-31 12:05:12.263145: val_loss -0.8935 +2025-10-31 12:05:12.265517: Pseudo dice [np.float32(0.9834), np.float32(0.9924), np.float32(0.995), np.float32(0.796)] +2025-10-31 12:05:12.267406: Epoch time: 21.83 s +2025-10-31 12:05:13.406520: +2025-10-31 12:05:13.408526: Epoch 401 +2025-10-31 12:05:13.410407: Current learning rate: 0.0063 +2025-10-31 12:05:35.721442: train_loss -0.9892 +2025-10-31 12:05:35.725879: val_loss -0.89 +2025-10-31 12:05:35.728333: Pseudo dice [np.float32(0.9835), np.float32(0.9928), np.float32(0.995), np.float32(0.7954)] +2025-10-31 12:05:35.730969: Epoch time: 22.32 s +2025-10-31 12:05:36.825450: +2025-10-31 12:05:36.827607: Epoch 402 +2025-10-31 12:05:36.829547: Current learning rate: 0.0063 +2025-10-31 12:05:59.383283: train_loss -0.9898 +2025-10-31 12:05:59.387098: val_loss -0.8912 +2025-10-31 12:05:59.388885: Pseudo dice [np.float32(0.9839), np.float32(0.9922), np.float32(0.9953), np.float32(0.802)] +2025-10-31 12:05:59.390521: Epoch time: 22.56 s +2025-10-31 12:06:01.082600: +2025-10-31 12:06:01.091864: Epoch 403 +2025-10-31 12:06:01.104856: Current learning rate: 0.00629 +2025-10-31 12:06:23.419211: train_loss -0.9888 +2025-10-31 12:06:23.421687: val_loss -0.8946 +2025-10-31 12:06:23.423244: Pseudo dice [np.float32(0.9844), np.float32(0.9924), np.float32(0.9949), np.float32(0.7937)] +2025-10-31 12:06:23.425808: Epoch time: 22.34 s +2025-10-31 12:06:24.669523: +2025-10-31 12:06:24.671276: Epoch 404 +2025-10-31 12:06:24.673161: Current learning rate: 0.00628 +2025-10-31 12:06:45.362582: train_loss -0.9896 +2025-10-31 12:06:45.364794: val_loss -0.8955 +2025-10-31 12:06:45.366603: Pseudo dice [np.float32(0.9842), np.float32(0.992), np.float32(0.9952), np.float32(0.7996)] +2025-10-31 12:06:45.368099: Epoch time: 20.69 s +2025-10-31 12:06:46.454862: +2025-10-31 12:06:46.456672: Epoch 405 +2025-10-31 12:06:46.458338: Current learning rate: 0.00627 +2025-10-31 12:07:08.139143: train_loss -0.99 +2025-10-31 12:07:08.143431: val_loss -0.894 +2025-10-31 12:07:08.145594: Pseudo dice [np.float32(0.9841), np.float32(0.9926), np.float32(0.9951), np.float32(0.798)] +2025-10-31 12:07:08.147566: Epoch time: 21.69 s +2025-10-31 12:07:09.275749: +2025-10-31 12:07:09.278252: Epoch 406 +2025-10-31 12:07:09.280270: Current learning rate: 0.00626 +2025-10-31 12:07:31.684065: train_loss -0.989 +2025-10-31 12:07:31.687892: val_loss -0.8952 +2025-10-31 12:07:31.689484: Pseudo dice [np.float32(0.985), np.float32(0.9925), np.float32(0.9951), np.float32(0.7978)] +2025-10-31 12:07:31.691329: Epoch time: 22.41 s +2025-10-31 12:07:32.870171: +2025-10-31 12:07:32.880226: Epoch 407 +2025-10-31 12:07:32.881707: Current learning rate: 0.00625 +2025-10-31 12:07:54.885857: train_loss -0.9896 +2025-10-31 12:07:54.889700: val_loss -0.8918 +2025-10-31 12:07:54.891471: Pseudo dice [np.float32(0.9853), np.float32(0.9924), np.float32(0.995), np.float32(0.7839)] +2025-10-31 12:07:54.893151: Epoch time: 22.02 s +2025-10-31 12:07:56.080415: +2025-10-31 12:07:56.082426: Epoch 408 +2025-10-31 12:07:56.084111: Current learning rate: 0.00624 +2025-10-31 12:08:18.139591: train_loss -0.9897 +2025-10-31 12:08:18.141971: val_loss -0.8964 +2025-10-31 12:08:18.143785: Pseudo dice [np.float32(0.9839), np.float32(0.9921), np.float32(0.995), np.float32(0.8001)] +2025-10-31 12:08:18.145351: Epoch time: 22.06 s +2025-10-31 12:08:19.446330: +2025-10-31 12:08:19.448365: Epoch 409 +2025-10-31 12:08:19.451062: Current learning rate: 0.00623 +2025-10-31 12:08:41.658574: train_loss -0.9892 +2025-10-31 12:08:41.661016: val_loss -0.8922 +2025-10-31 12:08:41.662656: Pseudo dice [np.float32(0.9849), np.float32(0.9925), np.float32(0.9949), np.float32(0.785)] +2025-10-31 12:08:41.664383: Epoch time: 22.21 s +2025-10-31 12:08:42.909304: +2025-10-31 12:08:42.919724: Epoch 410 +2025-10-31 12:08:42.921715: Current learning rate: 0.00622 +2025-10-31 12:09:03.385706: train_loss -0.9894 +2025-10-31 12:09:03.388604: val_loss -0.8893 +2025-10-31 12:09:03.390563: Pseudo dice [np.float32(0.9852), np.float32(0.9932), np.float32(0.9948), np.float32(0.78)] +2025-10-31 12:09:03.392802: Epoch time: 20.48 s +2025-10-31 12:09:04.507135: +2025-10-31 12:09:04.509364: Epoch 411 +2025-10-31 12:09:04.511468: Current learning rate: 0.00621 +2025-10-31 12:09:26.691819: train_loss -0.9887 +2025-10-31 12:09:26.693844: val_loss -0.8922 +2025-10-31 12:09:26.695802: Pseudo dice [np.float32(0.9832), np.float32(0.9913), np.float32(0.9947), np.float32(0.7935)] +2025-10-31 12:09:26.697505: Epoch time: 22.19 s +2025-10-31 12:09:27.831547: +2025-10-31 12:09:27.833883: Epoch 412 +2025-10-31 12:09:27.835573: Current learning rate: 0.0062 +2025-10-31 12:09:50.646177: train_loss -0.9889 +2025-10-31 12:09:50.651496: val_loss -0.8964 +2025-10-31 12:09:50.653071: Pseudo dice [np.float32(0.984), np.float32(0.9927), np.float32(0.9951), np.float32(0.7895)] +2025-10-31 12:09:50.654995: Epoch time: 22.82 s +2025-10-31 12:09:51.640453: +2025-10-31 12:09:51.644275: Epoch 413 +2025-10-31 12:09:51.645884: Current learning rate: 0.00619 +2025-10-31 12:10:13.493436: train_loss -0.9886 +2025-10-31 12:10:13.495912: val_loss -0.8871 +2025-10-31 12:10:13.497501: Pseudo dice [np.float32(0.9847), np.float32(0.9934), np.float32(0.995), np.float32(0.7771)] +2025-10-31 12:10:13.499181: Epoch time: 21.86 s +2025-10-31 12:10:14.691422: +2025-10-31 12:10:14.693316: Epoch 414 +2025-10-31 12:10:14.695063: Current learning rate: 0.00618 +2025-10-31 12:10:37.385594: train_loss -0.9895 +2025-10-31 12:10:37.388822: val_loss -0.8887 +2025-10-31 12:10:37.390283: Pseudo dice [np.float32(0.9848), np.float32(0.9926), np.float32(0.9948), np.float32(0.7805)] +2025-10-31 12:10:37.391908: Epoch time: 22.7 s +2025-10-31 12:10:38.970403: +2025-10-31 12:10:38.972196: Epoch 415 +2025-10-31 12:10:38.973902: Current learning rate: 0.00617 +2025-10-31 12:11:01.256516: train_loss -0.9893 +2025-10-31 12:11:01.260013: val_loss -0.8956 +2025-10-31 12:11:01.261798: Pseudo dice [np.float32(0.9846), np.float32(0.9927), np.float32(0.9952), np.float32(0.7927)] +2025-10-31 12:11:01.263530: Epoch time: 22.29 s +2025-10-31 12:11:02.506821: +2025-10-31 12:11:02.508696: Epoch 416 +2025-10-31 12:11:02.510471: Current learning rate: 0.00616 +2025-10-31 12:11:23.568896: train_loss -0.9897 +2025-10-31 12:11:23.572309: val_loss -0.8865 +2025-10-31 12:11:23.574032: Pseudo dice [np.float32(0.9843), np.float32(0.9923), np.float32(0.994), np.float32(0.7772)] +2025-10-31 12:11:23.575790: Epoch time: 21.06 s +2025-10-31 12:11:24.752887: +2025-10-31 12:11:24.754704: Epoch 417 +2025-10-31 12:11:24.756216: Current learning rate: 0.00615 +2025-10-31 12:11:46.444065: train_loss -0.9897 +2025-10-31 12:11:46.446831: val_loss -0.8854 +2025-10-31 12:11:46.448667: Pseudo dice [np.float32(0.9846), np.float32(0.9921), np.float32(0.9946), np.float32(0.775)] +2025-10-31 12:11:46.450283: Epoch time: 21.69 s +2025-10-31 12:11:47.628497: +2025-10-31 12:11:47.630745: Epoch 418 +2025-10-31 12:11:47.635067: Current learning rate: 0.00614 +2025-10-31 12:12:09.735404: train_loss -0.9905 +2025-10-31 12:12:09.737662: val_loss -0.894 +2025-10-31 12:12:09.739383: Pseudo dice [np.float32(0.9844), np.float32(0.9933), np.float32(0.9951), np.float32(0.7962)] +2025-10-31 12:12:09.741196: Epoch time: 22.11 s +2025-10-31 12:12:10.884946: +2025-10-31 12:12:10.887226: Epoch 419 +2025-10-31 12:12:10.889064: Current learning rate: 0.00613 +2025-10-31 12:12:33.889559: train_loss -0.9904 +2025-10-31 12:12:33.892902: val_loss -0.8995 +2025-10-31 12:12:33.894434: Pseudo dice [np.float32(0.9861), np.float32(0.9927), np.float32(0.9953), np.float32(0.8019)] +2025-10-31 12:12:33.895956: Epoch time: 23.01 s +2025-10-31 12:12:34.967614: +2025-10-31 12:12:34.969500: Epoch 420 +2025-10-31 12:12:34.971077: Current learning rate: 0.00612 +2025-10-31 12:12:57.567223: train_loss -0.9905 +2025-10-31 12:12:57.569884: val_loss -0.8912 +2025-10-31 12:12:57.572228: Pseudo dice [np.float32(0.9843), np.float32(0.9926), np.float32(0.9954), np.float32(0.7951)] +2025-10-31 12:12:57.573875: Epoch time: 22.6 s +2025-10-31 12:12:58.683431: +2025-10-31 12:12:58.685241: Epoch 421 +2025-10-31 12:12:58.686873: Current learning rate: 0.00612 +2025-10-31 12:13:20.745285: train_loss -0.9902 +2025-10-31 12:13:20.748442: val_loss -0.8923 +2025-10-31 12:13:20.750134: Pseudo dice [np.float32(0.9855), np.float32(0.993), np.float32(0.995), np.float32(0.7878)] +2025-10-31 12:13:20.751618: Epoch time: 22.06 s +2025-10-31 12:13:21.972934: +2025-10-31 12:13:21.974537: Epoch 422 +2025-10-31 12:13:21.976143: Current learning rate: 0.00611 +2025-10-31 12:13:43.667700: train_loss -0.9899 +2025-10-31 12:13:43.670359: val_loss -0.8907 +2025-10-31 12:13:43.673526: Pseudo dice [np.float32(0.9849), np.float32(0.9927), np.float32(0.9951), np.float32(0.7904)] +2025-10-31 12:13:43.675087: Epoch time: 21.7 s +2025-10-31 12:13:44.707469: +2025-10-31 12:13:44.708975: Epoch 423 +2025-10-31 12:13:44.710189: Current learning rate: 0.0061 +2025-10-31 12:14:05.697639: train_loss -0.9901 +2025-10-31 12:14:05.705166: val_loss -0.899 +2025-10-31 12:14:05.707596: Pseudo dice [np.float32(0.9853), np.float32(0.9928), np.float32(0.9952), np.float32(0.8019)] +2025-10-31 12:14:05.712590: Epoch time: 20.99 s +2025-10-31 12:14:07.003997: +2025-10-31 12:14:07.006032: Epoch 424 +2025-10-31 12:14:07.008098: Current learning rate: 0.00609 +2025-10-31 12:14:29.862439: train_loss -0.9883 +2025-10-31 12:14:29.865218: val_loss -0.8902 +2025-10-31 12:14:29.866753: Pseudo dice [np.float32(0.9854), np.float32(0.9931), np.float32(0.9951), np.float32(0.7769)] +2025-10-31 12:14:29.868272: Epoch time: 22.86 s +2025-10-31 12:14:30.917430: +2025-10-31 12:14:30.919406: Epoch 425 +2025-10-31 12:14:30.921320: Current learning rate: 0.00608 +2025-10-31 12:14:52.969093: train_loss -0.9898 +2025-10-31 12:14:52.971288: val_loss -0.8915 +2025-10-31 12:14:52.973076: Pseudo dice [np.float32(0.9844), np.float32(0.9925), np.float32(0.9952), np.float32(0.791)] +2025-10-31 12:14:52.974671: Epoch time: 22.05 s +2025-10-31 12:14:54.172758: +2025-10-31 12:14:54.174855: Epoch 426 +2025-10-31 12:14:54.176771: Current learning rate: 0.00607 +2025-10-31 12:15:16.225234: train_loss -0.9895 +2025-10-31 12:15:16.232224: val_loss -0.8991 +2025-10-31 12:15:16.234752: Pseudo dice [np.float32(0.9854), np.float32(0.9934), np.float32(0.9952), np.float32(0.7931)] +2025-10-31 12:15:16.236779: Epoch time: 22.05 s +2025-10-31 12:15:17.481392: +2025-10-31 12:15:17.483193: Epoch 427 +2025-10-31 12:15:17.484738: Current learning rate: 0.00606 +2025-10-31 12:15:39.672447: train_loss -0.9899 +2025-10-31 12:15:39.675841: val_loss -0.8914 +2025-10-31 12:15:39.678469: Pseudo dice [np.float32(0.9845), np.float32(0.9927), np.float32(0.9947), np.float32(0.7865)] +2025-10-31 12:15:39.680189: Epoch time: 22.19 s +2025-10-31 12:15:41.409283: +2025-10-31 12:15:41.412016: Epoch 428 +2025-10-31 12:15:41.414098: Current learning rate: 0.00605 +2025-10-31 12:16:02.297278: train_loss -0.9892 +2025-10-31 12:16:02.302700: val_loss -0.8877 +2025-10-31 12:16:02.304411: Pseudo dice [np.float32(0.9839), np.float32(0.993), np.float32(0.9948), np.float32(0.7907)] +2025-10-31 12:16:02.306173: Epoch time: 20.89 s +2025-10-31 12:16:03.448416: +2025-10-31 12:16:03.453834: Epoch 429 +2025-10-31 12:16:03.456013: Current learning rate: 0.00604 +2025-10-31 12:16:25.903112: train_loss -0.9893 +2025-10-31 12:16:25.905836: val_loss -0.8847 +2025-10-31 12:16:25.907479: Pseudo dice [np.float32(0.9835), np.float32(0.9922), np.float32(0.9948), np.float32(0.7773)] +2025-10-31 12:16:25.909051: Epoch time: 22.46 s +2025-10-31 12:16:27.145097: +2025-10-31 12:16:27.146935: Epoch 430 +2025-10-31 12:16:27.151466: Current learning rate: 0.00603 +2025-10-31 12:16:48.188967: train_loss -0.9903 +2025-10-31 12:16:48.191070: val_loss -0.8946 +2025-10-31 12:16:48.192765: Pseudo dice [np.float32(0.9848), np.float32(0.9924), np.float32(0.995), np.float32(0.7997)] +2025-10-31 12:16:48.194340: Epoch time: 21.05 s +2025-10-31 12:16:49.408279: +2025-10-31 12:16:49.410276: Epoch 431 +2025-10-31 12:16:49.412398: Current learning rate: 0.00602 +2025-10-31 12:17:11.596889: train_loss -0.9871 +2025-10-31 12:17:11.600498: val_loss -0.8946 +2025-10-31 12:17:11.602115: Pseudo dice [np.float32(0.9844), np.float32(0.9914), np.float32(0.9949), np.float32(0.7929)] +2025-10-31 12:17:11.603603: Epoch time: 22.19 s +2025-10-31 12:17:12.876580: +2025-10-31 12:17:12.878469: Epoch 432 +2025-10-31 12:17:12.880089: Current learning rate: 0.00601 +2025-10-31 12:17:35.249680: train_loss -0.9888 +2025-10-31 12:17:35.252153: val_loss -0.8933 +2025-10-31 12:17:35.253831: Pseudo dice [np.float32(0.9852), np.float32(0.9936), np.float32(0.9942), np.float32(0.7932)] +2025-10-31 12:17:35.255531: Epoch time: 22.37 s +2025-10-31 12:17:36.466604: +2025-10-31 12:17:36.469399: Epoch 433 +2025-10-31 12:17:36.471231: Current learning rate: 0.006 +2025-10-31 12:17:58.525116: train_loss -0.9885 +2025-10-31 12:17:58.528922: val_loss -0.896 +2025-10-31 12:17:58.530557: Pseudo dice [np.float32(0.9852), np.float32(0.9928), np.float32(0.9942), np.float32(0.7969)] +2025-10-31 12:17:58.532184: Epoch time: 22.06 s +2025-10-31 12:17:59.725001: +2025-10-31 12:17:59.726955: Epoch 434 +2025-10-31 12:17:59.728755: Current learning rate: 0.00599 +2025-10-31 12:18:21.636184: train_loss -0.9734 +2025-10-31 12:18:21.639851: val_loss -0.8498 +2025-10-31 12:18:21.641535: Pseudo dice [np.float32(0.9842), np.float32(0.9694), np.float32(0.9802), np.float32(0.762)] +2025-10-31 12:18:21.643124: Epoch time: 21.91 s +2025-10-31 12:18:22.834749: +2025-10-31 12:18:22.836352: Epoch 435 +2025-10-31 12:18:22.837887: Current learning rate: 0.00598 +2025-10-31 12:18:44.715037: train_loss -0.9349 +2025-10-31 12:18:44.718037: val_loss -0.9135 +2025-10-31 12:18:44.719663: Pseudo dice [np.float32(0.9831), np.float32(0.9905), np.float32(0.9949), np.float32(0.8037)] +2025-10-31 12:18:44.721349: Epoch time: 21.88 s +2025-10-31 12:18:45.935077: +2025-10-31 12:18:45.936846: Epoch 436 +2025-10-31 12:18:45.938403: Current learning rate: 0.00597 +2025-10-31 12:19:07.739703: train_loss -0.9534 +2025-10-31 12:19:07.741743: val_loss -0.9042 +2025-10-31 12:19:07.743302: Pseudo dice [np.float32(0.9833), np.float32(0.9908), np.float32(0.9947), np.float32(0.7854)] +2025-10-31 12:19:07.744725: Epoch time: 21.81 s +2025-10-31 12:19:08.939166: +2025-10-31 12:19:08.940961: Epoch 437 +2025-10-31 12:19:08.942536: Current learning rate: 0.00596 +2025-10-31 12:19:30.995702: train_loss -0.9717 +2025-10-31 12:19:30.998082: val_loss -0.8996 +2025-10-31 12:19:30.999774: Pseudo dice [np.float32(0.9837), np.float32(0.9918), np.float32(0.9947), np.float32(0.7897)] +2025-10-31 12:19:31.001381: Epoch time: 22.06 s +2025-10-31 12:19:32.195179: +2025-10-31 12:19:32.197607: Epoch 438 +2025-10-31 12:19:32.199537: Current learning rate: 0.00595 +2025-10-31 12:19:54.784699: train_loss -0.9712 +2025-10-31 12:19:54.787833: val_loss -0.9091 +2025-10-31 12:19:54.789498: Pseudo dice [np.float32(0.9833), np.float32(0.9861), np.float32(0.9931), np.float32(0.8246)] +2025-10-31 12:19:54.791183: Epoch time: 22.59 s +2025-10-31 12:19:55.796720: +2025-10-31 12:19:55.798884: Epoch 439 +2025-10-31 12:19:55.800893: Current learning rate: 0.00594 +2025-10-31 12:20:17.761412: train_loss -0.9571 +2025-10-31 12:20:17.763993: val_loss -0.9099 +2025-10-31 12:20:17.765710: Pseudo dice [np.float32(0.9786), np.float32(0.9897), np.float32(0.9952), np.float32(0.8159)] +2025-10-31 12:20:17.767366: Epoch time: 21.97 s +2025-10-31 12:20:18.797501: +2025-10-31 12:20:18.799311: Epoch 440 +2025-10-31 12:20:18.801050: Current learning rate: 0.00593 +2025-10-31 12:20:40.127908: train_loss -0.966 +2025-10-31 12:20:40.129985: val_loss -0.9035 +2025-10-31 12:20:40.132141: Pseudo dice [np.float32(0.9829), np.float32(0.9911), np.float32(0.9949), np.float32(0.7907)] +2025-10-31 12:20:40.133693: Epoch time: 21.33 s +2025-10-31 12:20:41.689358: +2025-10-31 12:20:41.691470: Epoch 441 +2025-10-31 12:20:41.693333: Current learning rate: 0.00592 +2025-10-31 12:21:03.666264: train_loss -0.975 +2025-10-31 12:21:03.671239: val_loss -0.9029 +2025-10-31 12:21:03.673894: Pseudo dice [np.float32(0.9847), np.float32(0.9923), np.float32(0.9955), np.float32(0.7896)] +2025-10-31 12:21:03.677127: Epoch time: 21.98 s +2025-10-31 12:21:04.839927: +2025-10-31 12:21:04.842239: Epoch 442 +2025-10-31 12:21:04.845688: Current learning rate: 0.00592 +2025-10-31 12:21:27.299419: train_loss -0.98 +2025-10-31 12:21:27.301687: val_loss -0.9103 +2025-10-31 12:21:27.303251: Pseudo dice [np.float32(0.9852), np.float32(0.992), np.float32(0.9951), np.float32(0.8114)] +2025-10-31 12:21:27.304683: Epoch time: 22.46 s +2025-10-31 12:21:28.493788: +2025-10-31 12:21:28.495584: Epoch 443 +2025-10-31 12:21:28.497280: Current learning rate: 0.00591 +2025-10-31 12:21:49.884022: train_loss -0.9819 +2025-10-31 12:21:49.888641: val_loss -0.8979 +2025-10-31 12:21:49.890659: Pseudo dice [np.float32(0.9826), np.float32(0.9914), np.float32(0.9952), np.float32(0.7936)] +2025-10-31 12:21:49.892373: Epoch time: 21.39 s +2025-10-31 12:21:51.083901: +2025-10-31 12:21:51.085843: Epoch 444 +2025-10-31 12:21:51.087587: Current learning rate: 0.0059 +2025-10-31 12:22:13.309455: train_loss -0.9848 +2025-10-31 12:22:13.313451: val_loss -0.8993 +2025-10-31 12:22:13.315242: Pseudo dice [np.float32(0.9829), np.float32(0.9925), np.float32(0.9952), np.float32(0.7958)] +2025-10-31 12:22:13.317044: Epoch time: 22.23 s +2025-10-31 12:22:14.520228: +2025-10-31 12:22:14.521966: Epoch 445 +2025-10-31 12:22:14.523813: Current learning rate: 0.00589 +2025-10-31 12:22:36.976613: train_loss -0.9857 +2025-10-31 12:22:36.978858: val_loss -0.9028 +2025-10-31 12:22:36.980643: Pseudo dice [np.float32(0.985), np.float32(0.9925), np.float32(0.9954), np.float32(0.8029)] +2025-10-31 12:22:36.982410: Epoch time: 22.46 s +2025-10-31 12:22:38.075837: +2025-10-31 12:22:38.077879: Epoch 446 +2025-10-31 12:22:38.079712: Current learning rate: 0.00588 +2025-10-31 12:22:59.532264: train_loss -0.9863 +2025-10-31 12:22:59.534854: val_loss -0.8932 +2025-10-31 12:22:59.536558: Pseudo dice [np.float32(0.9839), np.float32(0.9926), np.float32(0.9949), np.float32(0.7844)] +2025-10-31 12:22:59.538255: Epoch time: 21.46 s +2025-10-31 12:23:00.531513: +2025-10-31 12:23:00.533504: Epoch 447 +2025-10-31 12:23:00.535288: Current learning rate: 0.00587 +2025-10-31 12:23:22.817109: train_loss -0.9871 +2025-10-31 12:23:22.819773: val_loss -0.9013 +2025-10-31 12:23:22.821402: Pseudo dice [np.float32(0.984), np.float32(0.9915), np.float32(0.9951), np.float32(0.8087)] +2025-10-31 12:23:22.822995: Epoch time: 22.29 s +2025-10-31 12:23:23.923966: +2025-10-31 12:23:23.925997: Epoch 448 +2025-10-31 12:23:23.927662: Current learning rate: 0.00586 +2025-10-31 12:23:46.247502: train_loss -0.9875 +2025-10-31 12:23:46.249590: val_loss -0.8932 +2025-10-31 12:23:46.251344: Pseudo dice [np.float32(0.9844), np.float32(0.9921), np.float32(0.9946), np.float32(0.7866)] +2025-10-31 12:23:46.253134: Epoch time: 22.33 s +2025-10-31 12:23:47.235028: +2025-10-31 12:23:47.236914: Epoch 449 +2025-10-31 12:23:47.238748: Current learning rate: 0.00585 +2025-10-31 12:24:08.560900: train_loss -0.9874 +2025-10-31 12:24:08.567284: val_loss -0.8779 +2025-10-31 12:24:08.571268: Pseudo dice [np.float32(0.9836), np.float32(0.9919), np.float32(0.9945), np.float32(0.7552)] +2025-10-31 12:24:08.576486: Epoch time: 21.33 s +2025-10-31 12:24:10.983920: +2025-10-31 12:24:10.990981: Epoch 450 +2025-10-31 12:24:10.993343: Current learning rate: 0.00584 +2025-10-31 12:24:33.347207: train_loss -0.9872 +2025-10-31 12:24:33.351505: val_loss -0.8911 +2025-10-31 12:24:33.353643: Pseudo dice [np.float32(0.9839), np.float32(0.9921), np.float32(0.9947), np.float32(0.7786)] +2025-10-31 12:24:33.355747: Epoch time: 22.37 s +2025-10-31 12:24:34.406921: +2025-10-31 12:24:34.409058: Epoch 451 +2025-10-31 12:24:34.411012: Current learning rate: 0.00583 +2025-10-31 12:24:56.411083: train_loss -0.9882 +2025-10-31 12:24:56.413913: val_loss -0.8958 +2025-10-31 12:24:56.415811: Pseudo dice [np.float32(0.983), np.float32(0.9918), np.float32(0.9951), np.float32(0.799)] +2025-10-31 12:24:56.417722: Epoch time: 22.01 s +2025-10-31 12:24:57.534898: +2025-10-31 12:24:57.536752: Epoch 452 +2025-10-31 12:24:57.538354: Current learning rate: 0.00582 +2025-10-31 12:25:19.100507: train_loss -0.9877 +2025-10-31 12:25:19.102440: val_loss -0.891 +2025-10-31 12:25:19.104294: Pseudo dice [np.float32(0.9835), np.float32(0.9923), np.float32(0.9952), np.float32(0.7839)] +2025-10-31 12:25:19.105552: Epoch time: 21.57 s +2025-10-31 12:25:20.212718: +2025-10-31 12:25:20.214545: Epoch 453 +2025-10-31 12:25:20.215960: Current learning rate: 0.00581 +2025-10-31 12:25:42.152370: train_loss -0.9877 +2025-10-31 12:25:42.154672: val_loss -0.894 +2025-10-31 12:25:42.156344: Pseudo dice [np.float32(0.9824), np.float32(0.9917), np.float32(0.9947), np.float32(0.795)] +2025-10-31 12:25:42.158249: Epoch time: 21.94 s +2025-10-31 12:25:43.828009: +2025-10-31 12:25:43.830258: Epoch 454 +2025-10-31 12:25:43.832058: Current learning rate: 0.0058 +2025-10-31 12:26:05.863987: train_loss -0.9883 +2025-10-31 12:26:05.868746: val_loss -0.8959 +2025-10-31 12:26:05.870605: Pseudo dice [np.float32(0.9835), np.float32(0.9925), np.float32(0.9949), np.float32(0.8014)] +2025-10-31 12:26:05.872222: Epoch time: 22.04 s +2025-10-31 12:26:06.984787: +2025-10-31 12:26:06.986756: Epoch 455 +2025-10-31 12:26:06.988544: Current learning rate: 0.00579 +2025-10-31 12:26:28.326754: train_loss -0.9883 +2025-10-31 12:26:28.331181: val_loss -0.8908 +2025-10-31 12:26:28.332825: Pseudo dice [np.float32(0.9836), np.float32(0.9917), np.float32(0.9949), np.float32(0.7901)] +2025-10-31 12:26:28.334209: Epoch time: 21.34 s +2025-10-31 12:26:29.617200: +2025-10-31 12:26:29.621239: Epoch 456 +2025-10-31 12:26:29.625177: Current learning rate: 0.00578 +2025-10-31 12:26:51.413967: train_loss -0.9884 +2025-10-31 12:26:51.417016: val_loss -0.8861 +2025-10-31 12:26:51.422474: Pseudo dice [np.float32(0.9832), np.float32(0.9919), np.float32(0.9943), np.float32(0.771)] +2025-10-31 12:26:51.424211: Epoch time: 21.8 s +2025-10-31 12:26:52.586068: +2025-10-31 12:26:52.587812: Epoch 457 +2025-10-31 12:26:52.589405: Current learning rate: 0.00577 +2025-10-31 12:27:14.997988: train_loss -0.9823 +2025-10-31 12:27:15.000948: val_loss -0.8995 +2025-10-31 12:27:15.002378: Pseudo dice [np.float32(0.9823), np.float32(0.9904), np.float32(0.9951), np.float32(0.8112)] +2025-10-31 12:27:15.003976: Epoch time: 22.41 s +2025-10-31 12:27:16.192350: +2025-10-31 12:27:16.194432: Epoch 458 +2025-10-31 12:27:16.196516: Current learning rate: 0.00576 +2025-10-31 12:27:37.363938: train_loss -0.982 +2025-10-31 12:27:37.367370: val_loss -0.8916 +2025-10-31 12:27:37.369134: Pseudo dice [np.float32(0.985), np.float32(0.9929), np.float32(0.9949), np.float32(0.7815)] +2025-10-31 12:27:37.371526: Epoch time: 21.17 s +2025-10-31 12:27:38.416897: +2025-10-31 12:27:38.418850: Epoch 459 +2025-10-31 12:27:38.420650: Current learning rate: 0.00575 +2025-10-31 12:28:00.535266: train_loss -0.986 +2025-10-31 12:28:00.537992: val_loss -0.8813 +2025-10-31 12:28:00.540847: Pseudo dice [np.float32(0.9834), np.float32(0.9919), np.float32(0.9941), np.float32(0.764)] +2025-10-31 12:28:00.542381: Epoch time: 22.12 s +2025-10-31 12:28:01.716224: +2025-10-31 12:28:01.718289: Epoch 460 +2025-10-31 12:28:01.720261: Current learning rate: 0.00574 +2025-10-31 12:28:23.872177: train_loss -0.9862 +2025-10-31 12:28:23.874447: val_loss -0.9018 +2025-10-31 12:28:23.876161: Pseudo dice [np.float32(0.9844), np.float32(0.9919), np.float32(0.9954), np.float32(0.8116)] +2025-10-31 12:28:23.877842: Epoch time: 22.16 s +2025-10-31 12:28:25.020337: +2025-10-31 12:28:25.022366: Epoch 461 +2025-10-31 12:28:25.024055: Current learning rate: 0.00573 +2025-10-31 12:28:47.609250: train_loss -0.9878 +2025-10-31 12:28:47.613344: val_loss -0.882 +2025-10-31 12:28:47.615373: Pseudo dice [np.float32(0.9832), np.float32(0.9915), np.float32(0.9942), np.float32(0.7638)] +2025-10-31 12:28:47.617224: Epoch time: 22.59 s +2025-10-31 12:28:48.861509: +2025-10-31 12:28:48.863213: Epoch 462 +2025-10-31 12:28:48.865185: Current learning rate: 0.00572 +2025-10-31 12:29:09.761447: train_loss -0.9874 +2025-10-31 12:29:09.766258: val_loss -0.8872 +2025-10-31 12:29:09.768159: Pseudo dice [np.float32(0.9825), np.float32(0.9908), np.float32(0.9948), np.float32(0.7765)] +2025-10-31 12:29:09.770197: Epoch time: 20.9 s +2025-10-31 12:29:10.923344: +2025-10-31 12:29:10.925425: Epoch 463 +2025-10-31 12:29:10.927374: Current learning rate: 0.00571 +2025-10-31 12:29:33.565506: train_loss -0.9866 +2025-10-31 12:29:33.567637: val_loss -0.8939 +2025-10-31 12:29:33.569243: Pseudo dice [np.float32(0.9839), np.float32(0.9925), np.float32(0.9948), np.float32(0.7756)] +2025-10-31 12:29:33.570824: Epoch time: 22.64 s +2025-10-31 12:29:34.753983: +2025-10-31 12:29:34.755851: Epoch 464 +2025-10-31 12:29:34.757505: Current learning rate: 0.0057 +2025-10-31 12:29:56.043325: train_loss -0.9888 +2025-10-31 12:29:56.046796: val_loss -0.8964 +2025-10-31 12:29:56.048450: Pseudo dice [np.float32(0.9837), np.float32(0.9919), np.float32(0.9953), np.float32(0.7992)] +2025-10-31 12:29:56.050227: Epoch time: 21.29 s +2025-10-31 12:29:57.121539: +2025-10-31 12:29:57.123512: Epoch 465 +2025-10-31 12:29:57.125214: Current learning rate: 0.0057 +2025-10-31 12:30:19.370265: train_loss -0.9886 +2025-10-31 12:30:19.373044: val_loss -0.8937 +2025-10-31 12:30:19.375021: Pseudo dice [np.float32(0.9846), np.float32(0.9921), np.float32(0.9952), np.float32(0.799)] +2025-10-31 12:30:19.376758: Epoch time: 22.25 s +2025-10-31 12:30:20.618085: +2025-10-31 12:30:20.619874: Epoch 466 +2025-10-31 12:30:20.621534: Current learning rate: 0.00569 +2025-10-31 12:30:42.291342: train_loss -0.9896 +2025-10-31 12:30:42.293465: val_loss -0.9001 +2025-10-31 12:30:42.295215: Pseudo dice [np.float32(0.9831), np.float32(0.9917), np.float32(0.9954), np.float32(0.81)] +2025-10-31 12:30:42.299645: Epoch time: 21.67 s +2025-10-31 12:30:43.436883: +2025-10-31 12:30:43.438789: Epoch 467 +2025-10-31 12:30:43.440568: Current learning rate: 0.00568 +2025-10-31 12:31:06.197646: train_loss -0.9869 +2025-10-31 12:31:06.200436: val_loss -0.8958 +2025-10-31 12:31:06.202168: Pseudo dice [np.float32(0.9837), np.float32(0.9912), np.float32(0.9949), np.float32(0.791)] +2025-10-31 12:31:06.203940: Epoch time: 22.76 s +2025-10-31 12:31:07.036510: +2025-10-31 12:31:07.038493: Epoch 468 +2025-10-31 12:31:07.040423: Current learning rate: 0.00567 +2025-10-31 12:31:28.295017: train_loss -0.9867 +2025-10-31 12:31:28.300713: val_loss -0.8968 +2025-10-31 12:31:28.302890: Pseudo dice [np.float32(0.9841), np.float32(0.9919), np.float32(0.9954), np.float32(0.8054)] +2025-10-31 12:31:28.304585: Epoch time: 21.26 s +2025-10-31 12:31:29.474530: +2025-10-31 12:31:29.476208: Epoch 469 +2025-10-31 12:31:29.477793: Current learning rate: 0.00566 +2025-10-31 12:31:51.698390: train_loss -0.9884 +2025-10-31 12:31:51.700779: val_loss -0.8955 +2025-10-31 12:31:51.702410: Pseudo dice [np.float32(0.9831), np.float32(0.9917), np.float32(0.9951), np.float32(0.7982)] +2025-10-31 12:31:51.703926: Epoch time: 22.23 s +2025-10-31 12:31:52.808172: +2025-10-31 12:31:52.809988: Epoch 470 +2025-10-31 12:31:52.811515: Current learning rate: 0.00565 +2025-10-31 12:32:13.837882: train_loss -0.9883 +2025-10-31 12:32:13.840083: val_loss -0.8899 +2025-10-31 12:32:13.842014: Pseudo dice [np.float32(0.984), np.float32(0.992), np.float32(0.9956), np.float32(0.7885)] +2025-10-31 12:32:13.843927: Epoch time: 21.03 s +2025-10-31 12:32:14.838553: +2025-10-31 12:32:14.840700: Epoch 471 +2025-10-31 12:32:14.842486: Current learning rate: 0.00564 +2025-10-31 12:32:37.596276: train_loss -0.9878 +2025-10-31 12:32:37.599091: val_loss -0.8842 +2025-10-31 12:32:37.600912: Pseudo dice [np.float32(0.9849), np.float32(0.9919), np.float32(0.9945), np.float32(0.7653)] +2025-10-31 12:32:37.602715: Epoch time: 22.76 s +2025-10-31 12:32:38.718864: +2025-10-31 12:32:38.721443: Epoch 472 +2025-10-31 12:32:38.723233: Current learning rate: 0.00563 +2025-10-31 12:33:00.680822: train_loss -0.9887 +2025-10-31 12:33:00.684538: val_loss -0.8953 +2025-10-31 12:33:00.686316: Pseudo dice [np.float32(0.9856), np.float32(0.9925), np.float32(0.9952), np.float32(0.789)] +2025-10-31 12:33:00.688045: Epoch time: 21.96 s +2025-10-31 12:33:01.862940: +2025-10-31 12:33:01.865241: Epoch 473 +2025-10-31 12:33:01.867179: Current learning rate: 0.00562 +2025-10-31 12:33:24.157244: train_loss -0.9887 +2025-10-31 12:33:24.159437: val_loss -0.8901 +2025-10-31 12:33:24.160889: Pseudo dice [np.float32(0.9838), np.float32(0.992), np.float32(0.9945), np.float32(0.7877)] +2025-10-31 12:33:24.162353: Epoch time: 22.3 s +2025-10-31 12:33:25.376646: +2025-10-31 12:33:25.378782: Epoch 474 +2025-10-31 12:33:25.380545: Current learning rate: 0.00561 +2025-10-31 12:33:47.244759: train_loss -0.9887 +2025-10-31 12:33:47.254217: val_loss -0.8936 +2025-10-31 12:33:47.255892: Pseudo dice [np.float32(0.9827), np.float32(0.9911), np.float32(0.9952), np.float32(0.7991)] +2025-10-31 12:33:47.257260: Epoch time: 21.87 s +2025-10-31 12:33:48.414558: +2025-10-31 12:33:48.416424: Epoch 475 +2025-10-31 12:33:48.417906: Current learning rate: 0.0056 +2025-10-31 12:34:09.751598: train_loss -0.9893 +2025-10-31 12:34:09.754833: val_loss -0.8964 +2025-10-31 12:34:09.756685: Pseudo dice [np.float32(0.9849), np.float32(0.9927), np.float32(0.9948), np.float32(0.7933)] +2025-10-31 12:34:09.758231: Epoch time: 21.34 s +2025-10-31 12:34:10.889311: +2025-10-31 12:34:10.891651: Epoch 476 +2025-10-31 12:34:10.894056: Current learning rate: 0.00559 +2025-10-31 12:34:31.655584: train_loss -0.9892 +2025-10-31 12:34:31.657921: val_loss -0.903 +2025-10-31 12:34:31.661128: Pseudo dice [np.float32(0.9826), np.float32(0.9916), np.float32(0.9953), np.float32(0.8174)] +2025-10-31 12:34:31.663826: Epoch time: 20.77 s +2025-10-31 12:34:32.731993: +2025-10-31 12:34:32.733594: Epoch 477 +2025-10-31 12:34:32.735067: Current learning rate: 0.00558 +2025-10-31 12:34:54.853345: train_loss -0.9888 +2025-10-31 12:34:54.857934: val_loss -0.8879 +2025-10-31 12:34:54.859780: Pseudo dice [np.float32(0.9844), np.float32(0.9924), np.float32(0.9942), np.float32(0.7719)] +2025-10-31 12:34:54.862930: Epoch time: 22.12 s +2025-10-31 12:34:56.067272: +2025-10-31 12:34:56.069328: Epoch 478 +2025-10-31 12:34:56.071104: Current learning rate: 0.00557 +2025-10-31 12:35:18.038760: train_loss -0.9892 +2025-10-31 12:35:18.040690: val_loss -0.8894 +2025-10-31 12:35:18.042117: Pseudo dice [np.float32(0.9841), np.float32(0.9927), np.float32(0.9951), np.float32(0.7912)] +2025-10-31 12:35:18.043621: Epoch time: 21.97 s +2025-10-31 12:35:19.207951: +2025-10-31 12:35:19.210007: Epoch 479 +2025-10-31 12:35:19.211814: Current learning rate: 0.00556 +2025-10-31 12:35:41.272227: train_loss -0.9899 +2025-10-31 12:35:41.276115: val_loss -0.8923 +2025-10-31 12:35:41.277750: Pseudo dice [np.float32(0.985), np.float32(0.9926), np.float32(0.9952), np.float32(0.7933)] +2025-10-31 12:35:41.279465: Epoch time: 22.07 s +2025-10-31 12:35:42.690615: +2025-10-31 12:35:42.692717: Epoch 480 +2025-10-31 12:35:42.694460: Current learning rate: 0.00555 +2025-10-31 12:36:04.921799: train_loss -0.9897 +2025-10-31 12:36:04.924255: val_loss -0.8903 +2025-10-31 12:36:04.926155: Pseudo dice [np.float32(0.983), np.float32(0.9913), np.float32(0.9953), np.float32(0.7908)] +2025-10-31 12:36:04.927938: Epoch time: 22.23 s +2025-10-31 12:36:06.108068: +2025-10-31 12:36:06.110085: Epoch 481 +2025-10-31 12:36:06.111773: Current learning rate: 0.00554 +2025-10-31 12:36:27.589521: train_loss -0.989 +2025-10-31 12:36:27.595112: val_loss -0.8948 +2025-10-31 12:36:27.596831: Pseudo dice [np.float32(0.9837), np.float32(0.9922), np.float32(0.9952), np.float32(0.8016)] +2025-10-31 12:36:27.598492: Epoch time: 21.48 s +2025-10-31 12:36:28.779377: +2025-10-31 12:36:28.781572: Epoch 482 +2025-10-31 12:36:28.783404: Current learning rate: 0.00553 +2025-10-31 12:36:50.451213: train_loss -0.9898 +2025-10-31 12:36:50.453539: val_loss -0.894 +2025-10-31 12:36:50.455060: Pseudo dice [np.float32(0.9852), np.float32(0.992), np.float32(0.9949), np.float32(0.791)] +2025-10-31 12:36:50.456644: Epoch time: 21.67 s +2025-10-31 12:36:51.592660: +2025-10-31 12:36:51.594414: Epoch 483 +2025-10-31 12:36:51.596101: Current learning rate: 0.00552 +2025-10-31 12:37:14.109308: train_loss -0.9899 +2025-10-31 12:37:14.114269: val_loss -0.8919 +2025-10-31 12:37:14.116850: Pseudo dice [np.float32(0.9844), np.float32(0.992), np.float32(0.9948), np.float32(0.7932)] +2025-10-31 12:37:14.118795: Epoch time: 22.52 s +2025-10-31 12:37:15.059047: +2025-10-31 12:37:15.061090: Epoch 484 +2025-10-31 12:37:15.063218: Current learning rate: 0.00551 +2025-10-31 12:37:36.922264: train_loss -0.99 +2025-10-31 12:37:36.925137: val_loss -0.8923 +2025-10-31 12:37:36.926792: Pseudo dice [np.float32(0.9835), np.float32(0.9924), np.float32(0.9952), np.float32(0.7905)] +2025-10-31 12:37:36.928420: Epoch time: 21.87 s +2025-10-31 12:37:37.976365: +2025-10-31 12:37:37.978284: Epoch 485 +2025-10-31 12:37:37.979964: Current learning rate: 0.0055 +2025-10-31 12:38:00.372142: train_loss -0.9897 +2025-10-31 12:38:00.374221: val_loss -0.895 +2025-10-31 12:38:00.375607: Pseudo dice [np.float32(0.9852), np.float32(0.9927), np.float32(0.9952), np.float32(0.8001)] +2025-10-31 12:38:00.376841: Epoch time: 22.4 s +2025-10-31 12:38:01.233143: +2025-10-31 12:38:01.234949: Epoch 486 +2025-10-31 12:38:01.236369: Current learning rate: 0.00549 +2025-10-31 12:38:23.051178: train_loss -0.9905 +2025-10-31 12:38:23.053442: val_loss -0.8915 +2025-10-31 12:38:23.054820: Pseudo dice [np.float32(0.983), np.float32(0.9921), np.float32(0.995), np.float32(0.8002)] +2025-10-31 12:38:23.056087: Epoch time: 21.82 s +2025-10-31 12:38:24.056779: +2025-10-31 12:38:24.058873: Epoch 487 +2025-10-31 12:38:24.060498: Current learning rate: 0.00548 +2025-10-31 12:38:45.153334: train_loss -0.9904 +2025-10-31 12:38:45.155401: val_loss -0.8943 +2025-10-31 12:38:45.156879: Pseudo dice [np.float32(0.9829), np.float32(0.992), np.float32(0.9951), np.float32(0.8015)] +2025-10-31 12:38:45.158351: Epoch time: 21.1 s +2025-10-31 12:38:46.374865: +2025-10-31 12:38:46.376745: Epoch 488 +2025-10-31 12:38:46.378418: Current learning rate: 0.00547 +2025-10-31 12:39:07.784521: train_loss -0.99 +2025-10-31 12:39:07.787095: val_loss -0.8889 +2025-10-31 12:39:07.788457: Pseudo dice [np.float32(0.9844), np.float32(0.9927), np.float32(0.9954), np.float32(0.7879)] +2025-10-31 12:39:07.790173: Epoch time: 21.41 s +2025-10-31 12:39:08.716265: +2025-10-31 12:39:08.719106: Epoch 489 +2025-10-31 12:39:08.720905: Current learning rate: 0.00546 +2025-10-31 12:39:30.984394: train_loss -0.9903 +2025-10-31 12:39:30.990794: val_loss -0.8944 +2025-10-31 12:39:30.993391: Pseudo dice [np.float32(0.9842), np.float32(0.9921), np.float32(0.9951), np.float32(0.7994)] +2025-10-31 12:39:30.996159: Epoch time: 22.27 s +2025-10-31 12:39:32.210699: +2025-10-31 12:39:32.212670: Epoch 490 +2025-10-31 12:39:32.214449: Current learning rate: 0.00546 +2025-10-31 12:39:54.477898: train_loss -0.9897 +2025-10-31 12:39:54.480826: val_loss -0.8933 +2025-10-31 12:39:54.482682: Pseudo dice [np.float32(0.9832), np.float32(0.9917), np.float32(0.9952), np.float32(0.7942)] +2025-10-31 12:39:54.484521: Epoch time: 22.27 s +2025-10-31 12:39:55.724874: +2025-10-31 12:39:55.726813: Epoch 491 +2025-10-31 12:39:55.728753: Current learning rate: 0.00545 +2025-10-31 12:40:17.648851: train_loss -0.9898 +2025-10-31 12:40:17.651077: val_loss -0.8934 +2025-10-31 12:40:17.652596: Pseudo dice [np.float32(0.9841), np.float32(0.9919), np.float32(0.9952), np.float32(0.7938)] +2025-10-31 12:40:17.653983: Epoch time: 21.93 s +2025-10-31 12:40:18.725992: +2025-10-31 12:40:18.727721: Epoch 492 +2025-10-31 12:40:18.729330: Current learning rate: 0.00544 +2025-10-31 12:40:41.011585: train_loss -0.9901 +2025-10-31 12:40:41.015702: val_loss -0.9015 +2025-10-31 12:40:41.017390: Pseudo dice [np.float32(0.9852), np.float32(0.9927), np.float32(0.9956), np.float32(0.8005)] +2025-10-31 12:40:41.019382: Epoch time: 22.29 s +2025-10-31 12:40:42.207569: +2025-10-31 12:40:42.209873: Epoch 493 +2025-10-31 12:40:42.211627: Current learning rate: 0.00543 +2025-10-31 12:41:04.166621: train_loss -0.9902 +2025-10-31 12:41:04.168501: val_loss -0.8983 +2025-10-31 12:41:04.170082: Pseudo dice [np.float32(0.9854), np.float32(0.9933), np.float32(0.9952), np.float32(0.7941)] +2025-10-31 12:41:04.171529: Epoch time: 21.96 s +2025-10-31 12:41:05.684711: +2025-10-31 12:41:05.686717: Epoch 494 +2025-10-31 12:41:05.688563: Current learning rate: 0.00542 +2025-10-31 12:41:24.759300: train_loss -0.9906 +2025-10-31 12:41:24.762186: val_loss -0.8899 +2025-10-31 12:41:24.764301: Pseudo dice [np.float32(0.9835), np.float32(0.992), np.float32(0.9952), np.float32(0.7969)] +2025-10-31 12:41:24.766102: Epoch time: 19.08 s +2025-10-31 12:41:25.991941: +2025-10-31 12:41:25.995975: Epoch 495 +2025-10-31 12:41:25.997875: Current learning rate: 0.00541 +2025-10-31 12:41:48.096390: train_loss -0.9903 +2025-10-31 12:41:48.099344: val_loss -0.8978 +2025-10-31 12:41:48.101182: Pseudo dice [np.float32(0.9844), np.float32(0.9922), np.float32(0.9954), np.float32(0.8052)] +2025-10-31 12:41:48.102794: Epoch time: 22.11 s +2025-10-31 12:41:48.990091: +2025-10-31 12:41:48.993822: Epoch 496 +2025-10-31 12:41:48.995424: Current learning rate: 0.0054 +2025-10-31 12:42:10.928419: train_loss -0.9903 +2025-10-31 12:42:10.931630: val_loss -0.8961 +2025-10-31 12:42:10.933295: Pseudo dice [np.float32(0.9848), np.float32(0.993), np.float32(0.9956), np.float32(0.7951)] +2025-10-31 12:42:10.935122: Epoch time: 21.94 s +2025-10-31 12:42:12.029462: +2025-10-31 12:42:12.031554: Epoch 497 +2025-10-31 12:42:12.033289: Current learning rate: 0.00539 +2025-10-31 12:42:34.918862: train_loss -0.9896 +2025-10-31 12:42:34.921513: val_loss -0.8908 +2025-10-31 12:42:34.922995: Pseudo dice [np.float32(0.9832), np.float32(0.9916), np.float32(0.995), np.float32(0.7964)] +2025-10-31 12:42:34.924457: Epoch time: 22.89 s +2025-10-31 12:42:36.027593: +2025-10-31 12:42:36.029814: Epoch 498 +2025-10-31 12:42:36.031533: Current learning rate: 0.00538 +2025-10-31 12:42:58.497291: train_loss -0.9903 +2025-10-31 12:42:58.500244: val_loss -0.8913 +2025-10-31 12:42:58.501801: Pseudo dice [np.float32(0.9844), np.float32(0.9924), np.float32(0.995), np.float32(0.7878)] +2025-10-31 12:42:58.503305: Epoch time: 22.47 s +2025-10-31 12:42:59.725454: +2025-10-31 12:42:59.727245: Epoch 499 +2025-10-31 12:42:59.728905: Current learning rate: 0.00537 +2025-10-31 12:43:27.221273: train_loss -0.9902 +2025-10-31 12:43:27.223523: val_loss -0.894 +2025-10-31 12:43:27.225403: Pseudo dice [np.float32(0.9846), np.float32(0.9922), np.float32(0.9954), np.float32(0.7927)] +2025-10-31 12:43:27.227026: Epoch time: 27.5 s +2025-10-31 12:43:29.689816: +2025-10-31 12:43:29.692111: Epoch 500 +2025-10-31 12:43:29.694069: Current learning rate: 0.00536 +2025-10-31 12:43:56.725352: train_loss -0.9899 +2025-10-31 12:43:56.744313: val_loss -0.8905 +2025-10-31 12:43:56.750896: Pseudo dice [np.float32(0.9826), np.float32(0.9912), np.float32(0.9948), np.float32(0.799)] +2025-10-31 12:43:56.752566: Epoch time: 27.04 s +2025-10-31 12:43:57.914310: +2025-10-31 12:43:57.917995: Epoch 501 +2025-10-31 12:43:57.922342: Current learning rate: 0.00535 +2025-10-31 12:44:26.144588: train_loss -0.9904 +2025-10-31 12:44:26.149555: val_loss -0.883 +2025-10-31 12:44:26.151157: Pseudo dice [np.float32(0.9835), np.float32(0.9925), np.float32(0.9946), np.float32(0.7832)] +2025-10-31 12:44:26.152802: Epoch time: 28.23 s +2025-10-31 12:44:27.339047: +2025-10-31 12:44:27.341219: Epoch 502 +2025-10-31 12:44:27.342980: Current learning rate: 0.00534 +2025-10-31 12:44:55.424022: train_loss -0.9903 +2025-10-31 12:44:55.429380: val_loss -0.8929 +2025-10-31 12:44:55.431051: Pseudo dice [np.float32(0.9838), np.float32(0.9916), np.float32(0.9948), np.float32(0.7934)] +2025-10-31 12:44:55.432565: Epoch time: 28.09 s +2025-10-31 12:44:56.658328: +2025-10-31 12:44:56.660045: Epoch 503 +2025-10-31 12:44:56.661953: Current learning rate: 0.00533 +2025-10-31 12:45:24.815598: train_loss -0.9908 +2025-10-31 12:45:24.818418: val_loss -0.8952 +2025-10-31 12:45:24.820302: Pseudo dice [np.float32(0.9838), np.float32(0.992), np.float32(0.9953), np.float32(0.8055)] +2025-10-31 12:45:24.822257: Epoch time: 28.16 s +2025-10-31 12:45:26.007148: +2025-10-31 12:45:26.009447: Epoch 504 +2025-10-31 12:45:26.011214: Current learning rate: 0.00532 +2025-10-31 12:45:51.012747: train_loss -0.9904 +2025-10-31 12:45:51.019334: val_loss -0.8961 +2025-10-31 12:45:51.023242: Pseudo dice [np.float32(0.984), np.float32(0.9929), np.float32(0.9955), np.float32(0.8021)] +2025-10-31 12:45:51.026246: Epoch time: 25.01 s +2025-10-31 12:45:52.081553: +2025-10-31 12:45:52.083625: Epoch 505 +2025-10-31 12:45:52.085331: Current learning rate: 0.00531 +2025-10-31 12:46:15.465685: train_loss -0.9904 +2025-10-31 12:46:15.468112: val_loss -0.8917 +2025-10-31 12:46:15.469753: Pseudo dice [np.float32(0.9849), np.float32(0.992), np.float32(0.995), np.float32(0.7888)] +2025-10-31 12:46:15.471373: Epoch time: 23.39 s +2025-10-31 12:46:17.109520: +2025-10-31 12:46:17.111230: Epoch 506 +2025-10-31 12:46:17.112632: Current learning rate: 0.0053 +2025-10-31 12:46:42.931787: train_loss -0.9901 +2025-10-31 12:46:42.935503: val_loss -0.8826 +2025-10-31 12:46:42.937025: Pseudo dice [np.float32(0.9845), np.float32(0.9925), np.float32(0.9942), np.float32(0.7702)] +2025-10-31 12:46:42.938624: Epoch time: 25.82 s +2025-10-31 12:46:44.096925: +2025-10-31 12:46:44.098840: Epoch 507 +2025-10-31 12:46:44.100550: Current learning rate: 0.00529 +2025-10-31 12:47:08.401408: train_loss -0.9898 +2025-10-31 12:47:08.407170: val_loss -0.8988 +2025-10-31 12:47:08.410869: Pseudo dice [np.float32(0.9828), np.float32(0.9922), np.float32(0.9951), np.float32(0.8088)] +2025-10-31 12:47:08.413346: Epoch time: 24.31 s +2025-10-31 12:47:09.638919: +2025-10-31 12:47:09.641047: Epoch 508 +2025-10-31 12:47:09.642682: Current learning rate: 0.00528 +2025-10-31 12:47:36.792844: train_loss -0.9902 +2025-10-31 12:47:36.795089: val_loss -0.8968 +2025-10-31 12:47:36.796881: Pseudo dice [np.float32(0.9836), np.float32(0.9924), np.float32(0.9955), np.float32(0.8039)] +2025-10-31 12:47:36.798644: Epoch time: 27.16 s +2025-10-31 12:47:38.000246: +2025-10-31 12:47:38.001876: Epoch 509 +2025-10-31 12:47:38.003549: Current learning rate: 0.00527 +2025-10-31 12:48:03.770671: train_loss -0.9902 +2025-10-31 12:48:03.773614: val_loss -0.8973 +2025-10-31 12:48:03.775269: Pseudo dice [np.float32(0.9849), np.float32(0.9925), np.float32(0.9956), np.float32(0.8005)] +2025-10-31 12:48:03.777037: Epoch time: 25.77 s +2025-10-31 12:48:04.995589: +2025-10-31 12:48:04.997828: Epoch 510 +2025-10-31 12:48:04.999611: Current learning rate: 0.00526 +2025-10-31 12:48:32.267468: train_loss -0.9904 +2025-10-31 12:48:32.272465: val_loss -0.8796 +2025-10-31 12:48:32.274073: Pseudo dice [np.float32(0.9826), np.float32(0.9919), np.float32(0.9946), np.float32(0.7684)] +2025-10-31 12:48:32.275637: Epoch time: 27.27 s +2025-10-31 12:48:33.429162: +2025-10-31 12:48:33.431337: Epoch 511 +2025-10-31 12:48:33.433195: Current learning rate: 0.00525 +2025-10-31 12:49:00.995070: train_loss -0.9902 +2025-10-31 12:49:00.997684: val_loss -0.8917 +2025-10-31 12:49:00.999558: Pseudo dice [np.float32(0.9848), np.float32(0.9921), np.float32(0.9952), np.float32(0.7915)] +2025-10-31 12:49:01.001432: Epoch time: 27.57 s +2025-10-31 12:49:02.185592: +2025-10-31 12:49:02.187434: Epoch 512 +2025-10-31 12:49:02.189188: Current learning rate: 0.00524 +2025-10-31 12:49:28.781555: train_loss -0.9902 +2025-10-31 12:49:28.785493: val_loss -0.8974 +2025-10-31 12:49:28.787034: Pseudo dice [np.float32(0.9851), np.float32(0.9927), np.float32(0.9951), np.float32(0.7978)] +2025-10-31 12:49:28.788581: Epoch time: 26.6 s +2025-10-31 12:49:29.930583: +2025-10-31 12:49:29.932501: Epoch 513 +2025-10-31 12:49:29.934206: Current learning rate: 0.00523 +2025-10-31 12:49:56.707528: train_loss -0.9899 +2025-10-31 12:49:56.718811: val_loss -0.8973 +2025-10-31 12:49:56.720392: Pseudo dice [np.float32(0.9841), np.float32(0.9914), np.float32(0.995), np.float32(0.7983)] +2025-10-31 12:49:56.721887: Epoch time: 26.78 s +2025-10-31 12:49:57.872429: +2025-10-31 12:49:57.874129: Epoch 514 +2025-10-31 12:49:57.875545: Current learning rate: 0.00522 +2025-10-31 12:50:23.585027: train_loss -0.9906 +2025-10-31 12:50:23.592331: val_loss -0.8921 +2025-10-31 12:50:23.596308: Pseudo dice [np.float32(0.9843), np.float32(0.9915), np.float32(0.9951), np.float32(0.7969)] +2025-10-31 12:50:23.599843: Epoch time: 25.71 s +2025-10-31 12:50:24.774076: +2025-10-31 12:50:24.776791: Epoch 515 +2025-10-31 12:50:24.778645: Current learning rate: 0.00521 +2025-10-31 12:50:52.797440: train_loss -0.9902 +2025-10-31 12:50:52.803626: val_loss -0.8932 +2025-10-31 12:50:52.805289: Pseudo dice [np.float32(0.984), np.float32(0.9914), np.float32(0.9952), np.float32(0.8002)] +2025-10-31 12:50:52.807069: Epoch time: 28.03 s +2025-10-31 12:50:54.012280: +2025-10-31 12:50:54.014845: Epoch 516 +2025-10-31 12:50:54.017149: Current learning rate: 0.0052 +2025-10-31 12:51:18.296928: train_loss -0.9904 +2025-10-31 12:51:18.300241: val_loss -0.8879 +2025-10-31 12:51:18.302516: Pseudo dice [np.float32(0.9831), np.float32(0.9916), np.float32(0.9951), np.float32(0.7925)] +2025-10-31 12:51:18.304361: Epoch time: 24.29 s +2025-10-31 12:51:19.530786: +2025-10-31 12:51:19.532809: Epoch 517 +2025-10-31 12:51:19.534543: Current learning rate: 0.00519 +2025-10-31 12:51:46.693479: train_loss -0.99 +2025-10-31 12:51:46.697851: val_loss -0.9009 +2025-10-31 12:51:46.699553: Pseudo dice [np.float32(0.9854), np.float32(0.9928), np.float32(0.9954), np.float32(0.8055)] +2025-10-31 12:51:46.701087: Epoch time: 27.16 s +2025-10-31 12:51:47.921625: +2025-10-31 12:51:47.923392: Epoch 518 +2025-10-31 12:51:47.925123: Current learning rate: 0.00518 +2025-10-31 12:52:11.977499: train_loss -0.9902 +2025-10-31 12:52:11.979946: val_loss -0.8877 +2025-10-31 12:52:11.981468: Pseudo dice [np.float32(0.9845), np.float32(0.9923), np.float32(0.9951), np.float32(0.784)] +2025-10-31 12:52:11.983229: Epoch time: 24.06 s +2025-10-31 12:52:13.579710: +2025-10-31 12:52:13.581371: Epoch 519 +2025-10-31 12:52:13.582902: Current learning rate: 0.00518 +2025-10-31 12:52:40.120399: train_loss -0.9902 +2025-10-31 12:52:40.122935: val_loss -0.8825 +2025-10-31 12:52:40.124574: Pseudo dice [np.float32(0.9831), np.float32(0.9921), np.float32(0.9947), np.float32(0.7813)] +2025-10-31 12:52:40.126348: Epoch time: 26.54 s +2025-10-31 12:52:41.304441: +2025-10-31 12:52:41.321771: Epoch 520 +2025-10-31 12:52:41.338612: Current learning rate: 0.00517 +2025-10-31 12:53:06.908262: train_loss -0.9903 +2025-10-31 12:53:06.912634: val_loss -0.8903 +2025-10-31 12:53:06.914459: Pseudo dice [np.float32(0.984), np.float32(0.9922), np.float32(0.9949), np.float32(0.7845)] +2025-10-31 12:53:06.916498: Epoch time: 25.61 s +2025-10-31 12:53:08.198308: +2025-10-31 12:53:08.200687: Epoch 521 +2025-10-31 12:53:08.202804: Current learning rate: 0.00516 +2025-10-31 12:53:33.903314: train_loss -0.9902 +2025-10-31 12:53:33.907007: val_loss -0.897 +2025-10-31 12:53:33.908870: Pseudo dice [np.float32(0.9831), np.float32(0.9915), np.float32(0.9954), np.float32(0.807)] +2025-10-31 12:53:33.910611: Epoch time: 25.71 s +2025-10-31 12:53:35.117123: +2025-10-31 12:53:35.119070: Epoch 522 +2025-10-31 12:53:35.120831: Current learning rate: 0.00515 +2025-10-31 12:54:02.060322: train_loss -0.991 +2025-10-31 12:54:02.064130: val_loss -0.8848 +2025-10-31 12:54:02.065882: Pseudo dice [np.float32(0.9821), np.float32(0.9918), np.float32(0.9951), np.float32(0.778)] +2025-10-31 12:54:02.067714: Epoch time: 26.94 s +2025-10-31 12:54:03.301439: +2025-10-31 12:54:03.303587: Epoch 523 +2025-10-31 12:54:03.305331: Current learning rate: 0.00514 +2025-10-31 12:54:29.427222: train_loss -0.9903 +2025-10-31 12:54:29.431690: val_loss -0.8892 +2025-10-31 12:54:29.434495: Pseudo dice [np.float32(0.9846), np.float32(0.9922), np.float32(0.995), np.float32(0.7867)] +2025-10-31 12:54:29.436140: Epoch time: 26.13 s +2025-10-31 12:54:30.642372: +2025-10-31 12:54:30.644371: Epoch 524 +2025-10-31 12:54:30.646528: Current learning rate: 0.00513 +2025-10-31 12:54:57.038833: train_loss -0.9898 +2025-10-31 12:54:57.043323: val_loss -0.8989 +2025-10-31 12:54:57.045002: Pseudo dice [np.float32(0.9842), np.float32(0.9923), np.float32(0.9955), np.float32(0.8098)] +2025-10-31 12:54:57.046784: Epoch time: 26.4 s +2025-10-31 12:54:58.254803: +2025-10-31 12:54:58.256841: Epoch 525 +2025-10-31 12:54:58.258438: Current learning rate: 0.00512 +2025-10-31 12:55:23.678718: train_loss -0.9911 +2025-10-31 12:55:23.686646: val_loss -0.8949 +2025-10-31 12:55:23.688406: Pseudo dice [np.float32(0.9854), np.float32(0.9925), np.float32(0.9949), np.float32(0.7868)] +2025-10-31 12:55:23.690167: Epoch time: 25.43 s +2025-10-31 12:55:24.936448: +2025-10-31 12:55:24.938271: Epoch 526 +2025-10-31 12:55:24.939912: Current learning rate: 0.00511 +2025-10-31 12:55:50.718020: train_loss -0.9903 +2025-10-31 12:55:50.723064: val_loss -0.8887 +2025-10-31 12:55:50.724793: Pseudo dice [np.float32(0.9844), np.float32(0.9924), np.float32(0.9951), np.float32(0.7816)] +2025-10-31 12:55:50.726369: Epoch time: 25.78 s +2025-10-31 12:55:51.942552: +2025-10-31 12:55:51.944383: Epoch 527 +2025-10-31 12:55:51.946061: Current learning rate: 0.0051 +2025-10-31 12:56:15.107317: train_loss -0.9903 +2025-10-31 12:56:15.111698: val_loss -0.8898 +2025-10-31 12:56:15.113664: Pseudo dice [np.float32(0.9832), np.float32(0.9906), np.float32(0.9948), np.float32(0.7908)] +2025-10-31 12:56:15.115514: Epoch time: 23.17 s +2025-10-31 12:56:16.338734: +2025-10-31 12:56:16.340782: Epoch 528 +2025-10-31 12:56:16.342515: Current learning rate: 0.00509 +2025-10-31 12:56:43.255893: train_loss -0.9906 +2025-10-31 12:56:43.259180: val_loss -0.8973 +2025-10-31 12:56:43.260421: Pseudo dice [np.float32(0.9845), np.float32(0.9924), np.float32(0.9954), np.float32(0.8016)] +2025-10-31 12:56:43.261866: Epoch time: 26.92 s +2025-10-31 12:56:44.455072: +2025-10-31 12:56:44.456968: Epoch 529 +2025-10-31 12:56:44.458604: Current learning rate: 0.00508 +2025-10-31 12:57:11.152330: train_loss -0.9892 +2025-10-31 12:57:11.155346: val_loss -0.887 +2025-10-31 12:57:11.157697: Pseudo dice [np.float32(0.9836), np.float32(0.9922), np.float32(0.9948), np.float32(0.7858)] +2025-10-31 12:57:11.159787: Epoch time: 26.7 s +2025-10-31 12:57:12.339412: +2025-10-31 12:57:12.342066: Epoch 530 +2025-10-31 12:57:12.344008: Current learning rate: 0.00507 +2025-10-31 12:57:38.606876: train_loss -0.9904 +2025-10-31 12:57:38.609753: val_loss -0.8924 +2025-10-31 12:57:38.611792: Pseudo dice [np.float32(0.9847), np.float32(0.9917), np.float32(0.9949), np.float32(0.7943)] +2025-10-31 12:57:38.613698: Epoch time: 26.27 s +2025-10-31 12:57:39.837691: +2025-10-31 12:57:39.840011: Epoch 531 +2025-10-31 12:57:39.841910: Current learning rate: 0.00506 +2025-10-31 12:58:06.942339: train_loss -0.9901 +2025-10-31 12:58:06.946747: val_loss -0.8834 +2025-10-31 12:58:06.948325: Pseudo dice [np.float32(0.9829), np.float32(0.9916), np.float32(0.9946), np.float32(0.7783)] +2025-10-31 12:58:06.950037: Epoch time: 27.11 s +2025-10-31 12:58:08.755969: +2025-10-31 12:58:08.758015: Epoch 532 +2025-10-31 12:58:08.759695: Current learning rate: 0.00505 +2025-10-31 12:58:36.647772: train_loss -0.9906 +2025-10-31 12:58:36.649999: val_loss -0.8816 +2025-10-31 12:58:36.651479: Pseudo dice [np.float32(0.9836), np.float32(0.9919), np.float32(0.9947), np.float32(0.7793)] +2025-10-31 12:58:36.653005: Epoch time: 27.89 s +2025-10-31 12:58:37.873233: +2025-10-31 12:58:37.874949: Epoch 533 +2025-10-31 12:58:37.876500: Current learning rate: 0.00504 +2025-10-31 12:59:04.673313: train_loss -0.9912 +2025-10-31 12:59:04.677891: val_loss -0.9061 +2025-10-31 12:59:04.679490: Pseudo dice [np.float32(0.9839), np.float32(0.9923), np.float32(0.996), np.float32(0.8282)] +2025-10-31 12:59:04.680964: Epoch time: 26.8 s +2025-10-31 12:59:05.878669: +2025-10-31 12:59:05.880780: Epoch 534 +2025-10-31 12:59:05.882650: Current learning rate: 0.00503 +2025-10-31 12:59:30.977962: train_loss -0.9907 +2025-10-31 12:59:30.981910: val_loss -0.8861 +2025-10-31 12:59:30.983641: Pseudo dice [np.float32(0.984), np.float32(0.9924), np.float32(0.9947), np.float32(0.7749)] +2025-10-31 12:59:30.985210: Epoch time: 25.1 s +2025-10-31 12:59:32.197330: +2025-10-31 12:59:32.199512: Epoch 535 +2025-10-31 12:59:32.203217: Current learning rate: 0.00502 +2025-10-31 12:59:57.116346: train_loss -0.9909 +2025-10-31 12:59:57.118804: val_loss -0.8839 +2025-10-31 12:59:57.120347: Pseudo dice [np.float32(0.9836), np.float32(0.9921), np.float32(0.9949), np.float32(0.7815)] +2025-10-31 12:59:57.121841: Epoch time: 24.92 s +2025-10-31 12:59:58.299525: +2025-10-31 12:59:58.301856: Epoch 536 +2025-10-31 12:59:58.303929: Current learning rate: 0.00501 +2025-10-31 13:00:21.724840: train_loss -0.9905 +2025-10-31 13:00:21.728897: val_loss -0.8886 +2025-10-31 13:00:21.730638: Pseudo dice [np.float32(0.9841), np.float32(0.9925), np.float32(0.995), np.float32(0.787)] +2025-10-31 13:00:21.732368: Epoch time: 23.43 s +2025-10-31 13:00:22.911115: +2025-10-31 13:00:22.912830: Epoch 537 +2025-10-31 13:00:22.914457: Current learning rate: 0.005 +2025-10-31 13:00:48.818535: train_loss -0.9905 +2025-10-31 13:00:48.822897: val_loss -0.8897 +2025-10-31 13:00:48.824784: Pseudo dice [np.float32(0.9832), np.float32(0.9921), np.float32(0.9952), np.float32(0.7959)] +2025-10-31 13:00:48.826515: Epoch time: 25.91 s +2025-10-31 13:00:49.968762: +2025-10-31 13:00:49.970807: Epoch 538 +2025-10-31 13:00:49.972716: Current learning rate: 0.00499 +2025-10-31 13:01:16.795868: train_loss -0.9908 +2025-10-31 13:01:16.798026: val_loss -0.8932 +2025-10-31 13:01:16.799408: Pseudo dice [np.float32(0.9854), np.float32(0.9921), np.float32(0.9951), np.float32(0.8004)] +2025-10-31 13:01:16.800757: Epoch time: 26.83 s +2025-10-31 13:01:17.926230: +2025-10-31 13:01:17.928202: Epoch 539 +2025-10-31 13:01:17.929697: Current learning rate: 0.00498 +2025-10-31 13:01:42.742373: train_loss -0.9908 +2025-10-31 13:01:42.745372: val_loss -0.8908 +2025-10-31 13:01:42.747044: Pseudo dice [np.float32(0.9829), np.float32(0.9921), np.float32(0.9953), np.float32(0.7993)] +2025-10-31 13:01:42.748602: Epoch time: 24.82 s +2025-10-31 13:01:43.986547: +2025-10-31 13:01:44.007627: Epoch 540 +2025-10-31 13:01:44.028697: Current learning rate: 0.00497 +2025-10-31 13:02:09.176418: train_loss -0.9905 +2025-10-31 13:02:09.179217: val_loss -0.8923 +2025-10-31 13:02:09.181036: Pseudo dice [np.float32(0.9849), np.float32(0.9924), np.float32(0.9955), np.float32(0.7931)] +2025-10-31 13:02:09.183236: Epoch time: 25.19 s +2025-10-31 13:02:10.310312: +2025-10-31 13:02:10.312420: Epoch 541 +2025-10-31 13:02:10.314128: Current learning rate: 0.00496 +2025-10-31 13:02:37.640188: train_loss -0.9915 +2025-10-31 13:02:37.641968: val_loss -0.8909 +2025-10-31 13:02:37.643699: Pseudo dice [np.float32(0.9843), np.float32(0.9919), np.float32(0.995), np.float32(0.7962)] +2025-10-31 13:02:37.645195: Epoch time: 27.33 s +2025-10-31 13:02:38.754477: +2025-10-31 13:02:38.756312: Epoch 542 +2025-10-31 13:02:38.757858: Current learning rate: 0.00495 +2025-10-31 13:03:05.272554: train_loss -0.9911 +2025-10-31 13:03:05.275075: val_loss -0.888 +2025-10-31 13:03:05.276652: Pseudo dice [np.float32(0.9843), np.float32(0.9925), np.float32(0.9951), np.float32(0.7874)] +2025-10-31 13:03:05.278223: Epoch time: 26.52 s +2025-10-31 13:03:06.482304: +2025-10-31 13:03:06.484096: Epoch 543 +2025-10-31 13:03:06.485860: Current learning rate: 0.00494 +2025-10-31 13:03:32.991980: train_loss -0.9909 +2025-10-31 13:03:32.996697: val_loss -0.8916 +2025-10-31 13:03:32.998432: Pseudo dice [np.float32(0.9845), np.float32(0.9926), np.float32(0.9954), np.float32(0.7901)] +2025-10-31 13:03:33.000147: Epoch time: 26.51 s +2025-10-31 13:03:34.219324: +2025-10-31 13:03:34.221258: Epoch 544 +2025-10-31 13:03:34.222923: Current learning rate: 0.00493 +2025-10-31 13:03:59.547905: train_loss -0.9908 +2025-10-31 13:03:59.550375: val_loss -0.8952 +2025-10-31 13:03:59.552011: Pseudo dice [np.float32(0.9842), np.float32(0.9922), np.float32(0.9954), np.float32(0.8032)] +2025-10-31 13:03:59.553625: Epoch time: 25.33 s +2025-10-31 13:04:01.179851: +2025-10-31 13:04:01.182184: Epoch 545 +2025-10-31 13:04:01.184165: Current learning rate: 0.00492 +2025-10-31 13:04:26.006116: train_loss -0.9906 +2025-10-31 13:04:26.008706: val_loss -0.8951 +2025-10-31 13:04:26.010716: Pseudo dice [np.float32(0.9833), np.float32(0.9922), np.float32(0.995), np.float32(0.7947)] +2025-10-31 13:04:26.012599: Epoch time: 24.83 s +2025-10-31 13:04:27.256875: +2025-10-31 13:04:27.258721: Epoch 546 +2025-10-31 13:04:27.260766: Current learning rate: 0.00491 +2025-10-31 13:04:50.843156: train_loss -0.9911 +2025-10-31 13:04:50.849228: val_loss -0.882 +2025-10-31 13:04:50.851137: Pseudo dice [np.float32(0.9838), np.float32(0.9922), np.float32(0.9948), np.float32(0.7713)] +2025-10-31 13:04:50.853156: Epoch time: 23.59 s +2025-10-31 13:04:52.066225: +2025-10-31 13:04:52.068013: Epoch 547 +2025-10-31 13:04:52.069525: Current learning rate: 0.0049 +2025-10-31 13:05:16.561838: train_loss -0.9901 +2025-10-31 13:05:16.564981: val_loss -0.8984 +2025-10-31 13:05:16.566654: Pseudo dice [np.float32(0.9853), np.float32(0.9926), np.float32(0.9953), np.float32(0.8078)] +2025-10-31 13:05:16.568183: Epoch time: 24.5 s +2025-10-31 13:05:17.779468: +2025-10-31 13:05:17.784640: Epoch 548 +2025-10-31 13:05:17.786537: Current learning rate: 0.00489 +2025-10-31 13:05:44.441038: train_loss -0.991 +2025-10-31 13:05:44.443824: val_loss -0.8874 +2025-10-31 13:05:44.445542: Pseudo dice [np.float32(0.983), np.float32(0.9916), np.float32(0.9945), np.float32(0.7931)] +2025-10-31 13:05:44.447639: Epoch time: 26.66 s +2025-10-31 13:05:45.644611: +2025-10-31 13:05:45.646273: Epoch 549 +2025-10-31 13:05:45.647791: Current learning rate: 0.00488 +2025-10-31 13:06:10.353540: train_loss -0.9906 +2025-10-31 13:06:10.364790: val_loss -0.8862 +2025-10-31 13:06:10.369316: Pseudo dice [np.float32(0.9856), np.float32(0.9925), np.float32(0.9948), np.float32(0.7778)] +2025-10-31 13:06:10.371832: Epoch time: 24.71 s +2025-10-31 13:06:13.395331: +2025-10-31 13:06:13.405312: Epoch 550 +2025-10-31 13:06:13.407068: Current learning rate: 0.00487 +2025-10-31 13:06:38.765898: train_loss -0.9904 +2025-10-31 13:06:38.769169: val_loss -0.8819 +2025-10-31 13:06:38.771256: Pseudo dice [np.float32(0.9852), np.float32(0.9926), np.float32(0.995), np.float32(0.7628)] +2025-10-31 13:06:38.773277: Epoch time: 25.37 s +2025-10-31 13:06:39.949803: +2025-10-31 13:06:39.952315: Epoch 551 +2025-10-31 13:06:39.954323: Current learning rate: 0.00486 +2025-10-31 13:07:08.128407: train_loss -0.9907 +2025-10-31 13:07:08.132529: val_loss -0.8952 +2025-10-31 13:07:08.134614: Pseudo dice [np.float32(0.9835), np.float32(0.9925), np.float32(0.9954), np.float32(0.8005)] +2025-10-31 13:07:08.136517: Epoch time: 28.18 s +2025-10-31 13:07:09.335264: +2025-10-31 13:07:09.337370: Epoch 552 +2025-10-31 13:07:09.339453: Current learning rate: 0.00485 +2025-10-31 13:07:35.353832: train_loss -0.9904 +2025-10-31 13:07:35.356637: val_loss -0.8893 +2025-10-31 13:07:35.358777: Pseudo dice [np.float32(0.9834), np.float32(0.9925), np.float32(0.9953), np.float32(0.7967)] +2025-10-31 13:07:35.360605: Epoch time: 26.02 s +2025-10-31 13:07:36.617369: +2025-10-31 13:07:36.619295: Epoch 553 +2025-10-31 13:07:36.621107: Current learning rate: 0.00484 +2025-10-31 13:07:57.524005: train_loss -0.9909 +2025-10-31 13:07:57.527356: val_loss -0.8922 +2025-10-31 13:07:57.529079: Pseudo dice [np.float32(0.984), np.float32(0.9925), np.float32(0.9952), np.float32(0.7898)] +2025-10-31 13:07:57.530699: Epoch time: 20.91 s +2025-10-31 13:07:58.689384: +2025-10-31 13:07:58.691450: Epoch 554 +2025-10-31 13:07:58.693221: Current learning rate: 0.00484 +2025-10-31 13:08:23.545862: train_loss -0.991 +2025-10-31 13:08:23.549419: val_loss -0.8971 +2025-10-31 13:08:23.554927: Pseudo dice [np.float32(0.9841), np.float32(0.9931), np.float32(0.9957), np.float32(0.8075)] +2025-10-31 13:08:23.556594: Epoch time: 24.86 s +2025-10-31 13:08:24.596685: +2025-10-31 13:08:24.603687: Epoch 555 +2025-10-31 13:08:24.605635: Current learning rate: 0.00483 +2025-10-31 13:08:50.159998: train_loss -0.9912 +2025-10-31 13:08:50.162973: val_loss -0.8917 +2025-10-31 13:08:50.164623: Pseudo dice [np.float32(0.984), np.float32(0.9924), np.float32(0.9953), np.float32(0.7973)] +2025-10-31 13:08:50.166294: Epoch time: 25.57 s +2025-10-31 13:08:51.249042: +2025-10-31 13:08:51.251985: Epoch 556 +2025-10-31 13:08:51.253975: Current learning rate: 0.00482 +2025-10-31 13:09:17.058783: train_loss -0.9907 +2025-10-31 13:09:17.062760: val_loss -0.8875 +2025-10-31 13:09:17.064677: Pseudo dice [np.float32(0.983), np.float32(0.9927), np.float32(0.9952), np.float32(0.7862)] +2025-10-31 13:09:17.066426: Epoch time: 25.81 s +2025-10-31 13:09:18.256107: +2025-10-31 13:09:18.258138: Epoch 557 +2025-10-31 13:09:18.259970: Current learning rate: 0.00481 +2025-10-31 13:09:42.578716: train_loss -0.9904 +2025-10-31 13:09:42.586060: val_loss -0.8908 +2025-10-31 13:09:42.590442: Pseudo dice [np.float32(0.9835), np.float32(0.992), np.float32(0.995), np.float32(0.7935)] +2025-10-31 13:09:42.592585: Epoch time: 24.33 s +2025-10-31 13:09:44.300860: +2025-10-31 13:09:44.302940: Epoch 558 +2025-10-31 13:09:44.304936: Current learning rate: 0.0048 +2025-10-31 13:10:10.081658: train_loss -0.9906 +2025-10-31 13:10:10.084418: val_loss -0.8905 +2025-10-31 13:10:10.085856: Pseudo dice [np.float32(0.9841), np.float32(0.9922), np.float32(0.9954), np.float32(0.7943)] +2025-10-31 13:10:10.087576: Epoch time: 25.78 s +2025-10-31 13:10:11.275264: +2025-10-31 13:10:11.277608: Epoch 559 +2025-10-31 13:10:11.279509: Current learning rate: 0.00479 +2025-10-31 13:10:38.910438: train_loss -0.9914 +2025-10-31 13:10:38.917532: val_loss -0.8936 +2025-10-31 13:10:38.920501: Pseudo dice [np.float32(0.985), np.float32(0.9928), np.float32(0.9954), np.float32(0.8059)] +2025-10-31 13:10:38.922157: Epoch time: 27.64 s +2025-10-31 13:10:40.124203: +2025-10-31 13:10:40.126254: Epoch 560 +2025-10-31 13:10:40.128044: Current learning rate: 0.00478 +2025-10-31 13:11:05.474041: train_loss -0.9916 +2025-10-31 13:11:05.477100: val_loss -0.9051 +2025-10-31 13:11:05.482629: Pseudo dice [np.float32(0.9836), np.float32(0.9927), np.float32(0.9957), np.float32(0.8275)] +2025-10-31 13:11:05.484577: Epoch time: 25.35 s +2025-10-31 13:11:06.672791: +2025-10-31 13:11:06.674664: Epoch 561 +2025-10-31 13:11:06.676398: Current learning rate: 0.00477 +2025-10-31 13:11:33.013534: train_loss -0.99 +2025-10-31 13:11:33.017931: val_loss -0.8893 +2025-10-31 13:11:33.019610: Pseudo dice [np.float32(0.9836), np.float32(0.9931), np.float32(0.9952), np.float32(0.7815)] +2025-10-31 13:11:33.021213: Epoch time: 26.34 s +2025-10-31 13:11:34.297353: +2025-10-31 13:11:34.299531: Epoch 562 +2025-10-31 13:11:34.301532: Current learning rate: 0.00476 +2025-10-31 13:11:58.661590: train_loss -0.9914 +2025-10-31 13:11:58.664490: val_loss -0.8921 +2025-10-31 13:11:58.666464: Pseudo dice [np.float32(0.9854), np.float32(0.9924), np.float32(0.9953), np.float32(0.7967)] +2025-10-31 13:11:58.668143: Epoch time: 24.37 s +2025-10-31 13:11:59.859178: +2025-10-31 13:11:59.861256: Epoch 563 +2025-10-31 13:11:59.862800: Current learning rate: 0.00475 +2025-10-31 13:12:26.470540: train_loss -0.9914 +2025-10-31 13:12:26.474458: val_loss -0.893 +2025-10-31 13:12:26.476675: Pseudo dice [np.float32(0.9831), np.float32(0.9921), np.float32(0.9957), np.float32(0.8013)] +2025-10-31 13:12:26.478262: Epoch time: 26.61 s +2025-10-31 13:12:27.930943: +2025-10-31 13:12:27.933062: Epoch 564 +2025-10-31 13:12:27.934882: Current learning rate: 0.00474 +2025-10-31 13:12:50.959621: train_loss -0.9911 +2025-10-31 13:12:50.964947: val_loss -0.894 +2025-10-31 13:12:50.966553: Pseudo dice [np.float32(0.9848), np.float32(0.9929), np.float32(0.995), np.float32(0.7967)] +2025-10-31 13:12:50.968164: Epoch time: 23.03 s +2025-10-31 13:12:52.282766: +2025-10-31 13:12:52.285825: Epoch 565 +2025-10-31 13:12:52.287446: Current learning rate: 0.00473 +2025-10-31 13:13:18.730967: train_loss -0.9907 +2025-10-31 13:13:18.733815: val_loss -0.8861 +2025-10-31 13:13:18.735497: Pseudo dice [np.float32(0.9828), np.float32(0.9921), np.float32(0.9951), np.float32(0.7803)] +2025-10-31 13:13:18.737250: Epoch time: 26.45 s +2025-10-31 13:13:19.944860: +2025-10-31 13:13:19.947627: Epoch 566 +2025-10-31 13:13:19.949578: Current learning rate: 0.00472 +2025-10-31 13:13:44.302145: train_loss -0.9914 +2025-10-31 13:13:44.330921: val_loss -0.8837 +2025-10-31 13:13:44.347780: Pseudo dice [np.float32(0.9838), np.float32(0.993), np.float32(0.9949), np.float32(0.7774)] +2025-10-31 13:13:44.365758: Epoch time: 24.36 s +2025-10-31 13:13:45.457459: +2025-10-31 13:13:45.464645: Epoch 567 +2025-10-31 13:13:45.469324: Current learning rate: 0.00471 +2025-10-31 13:14:10.394135: train_loss -0.9913 +2025-10-31 13:14:10.396662: val_loss -0.8858 +2025-10-31 13:14:10.398097: Pseudo dice [np.float32(0.9838), np.float32(0.9922), np.float32(0.9948), np.float32(0.7879)] +2025-10-31 13:14:10.399447: Epoch time: 24.94 s +2025-10-31 13:14:11.523633: +2025-10-31 13:14:11.525792: Epoch 568 +2025-10-31 13:14:11.527814: Current learning rate: 0.0047 +2025-10-31 13:14:36.120409: train_loss -0.9909 +2025-10-31 13:14:36.123501: val_loss -0.8991 +2025-10-31 13:14:36.125464: Pseudo dice [np.float32(0.9842), np.float32(0.9922), np.float32(0.9954), np.float32(0.8073)] +2025-10-31 13:14:36.127233: Epoch time: 24.6 s +2025-10-31 13:14:37.289406: +2025-10-31 13:14:37.291624: Epoch 569 +2025-10-31 13:14:37.294180: Current learning rate: 0.00469 +2025-10-31 13:15:01.214322: train_loss -0.9915 +2025-10-31 13:15:01.224430: val_loss -0.8955 +2025-10-31 13:15:01.234294: Pseudo dice [np.float32(0.9844), np.float32(0.9927), np.float32(0.9951), np.float32(0.7954)] +2025-10-31 13:15:01.241951: Epoch time: 23.93 s +2025-10-31 13:15:02.602088: +2025-10-31 13:15:02.604766: Epoch 570 +2025-10-31 13:15:02.606940: Current learning rate: 0.00468 +2025-10-31 13:15:27.600148: train_loss -0.9917 +2025-10-31 13:15:27.606670: val_loss -0.8956 +2025-10-31 13:15:27.608507: Pseudo dice [np.float32(0.985), np.float32(0.9928), np.float32(0.9955), np.float32(0.8048)] +2025-10-31 13:15:27.610242: Epoch time: 25.0 s +2025-10-31 13:15:29.523096: +2025-10-31 13:15:29.524980: Epoch 571 +2025-10-31 13:15:29.526721: Current learning rate: 0.00467 +2025-10-31 13:15:53.388655: train_loss -0.9907 +2025-10-31 13:15:53.392160: val_loss -0.8743 +2025-10-31 13:15:53.394089: Pseudo dice [np.float32(0.9832), np.float32(0.9918), np.float32(0.9941), np.float32(0.7531)] +2025-10-31 13:15:53.396092: Epoch time: 23.87 s +2025-10-31 13:15:54.607696: +2025-10-31 13:15:54.610034: Epoch 572 +2025-10-31 13:15:54.612613: Current learning rate: 0.00466 +2025-10-31 13:16:20.915133: train_loss -0.9903 +2025-10-31 13:16:20.919117: val_loss -0.8809 +2025-10-31 13:16:20.920637: Pseudo dice [np.float32(0.9841), np.float32(0.9923), np.float32(0.9948), np.float32(0.7699)] +2025-10-31 13:16:20.922047: Epoch time: 26.31 s +2025-10-31 13:16:22.221335: +2025-10-31 13:16:22.223902: Epoch 573 +2025-10-31 13:16:22.226075: Current learning rate: 0.00465 +2025-10-31 13:16:44.072049: train_loss -0.9904 +2025-10-31 13:16:44.074604: val_loss -0.8864 +2025-10-31 13:16:44.076216: Pseudo dice [np.float32(0.9836), np.float32(0.992), np.float32(0.9952), np.float32(0.788)] +2025-10-31 13:16:44.077925: Epoch time: 21.85 s +2025-10-31 13:16:45.282084: +2025-10-31 13:16:45.284038: Epoch 574 +2025-10-31 13:16:45.285757: Current learning rate: 0.00464 +2025-10-31 13:17:08.879171: train_loss -0.9909 +2025-10-31 13:17:08.881558: val_loss -0.8972 +2025-10-31 13:17:08.883186: Pseudo dice [np.float32(0.9841), np.float32(0.9924), np.float32(0.996), np.float32(0.8109)] +2025-10-31 13:17:08.884818: Epoch time: 23.6 s +2025-10-31 13:17:10.067822: +2025-10-31 13:17:10.069992: Epoch 575 +2025-10-31 13:17:10.071866: Current learning rate: 0.00463 +2025-10-31 13:17:33.125135: train_loss -0.9909 +2025-10-31 13:17:33.129128: val_loss -0.8945 +2025-10-31 13:17:33.130759: Pseudo dice [np.float32(0.9829), np.float32(0.9917), np.float32(0.9954), np.float32(0.8022)] +2025-10-31 13:17:33.134027: Epoch time: 23.06 s +2025-10-31 13:17:34.300672: +2025-10-31 13:17:34.302486: Epoch 576 +2025-10-31 13:17:34.304042: Current learning rate: 0.00462 +2025-10-31 13:17:55.405587: train_loss -0.9914 +2025-10-31 13:17:55.414638: val_loss -0.8918 +2025-10-31 13:17:55.420239: Pseudo dice [np.float32(0.9834), np.float32(0.9925), np.float32(0.9955), np.float32(0.795)] +2025-10-31 13:17:55.428388: Epoch time: 21.11 s +2025-10-31 13:17:56.689333: +2025-10-31 13:17:56.691807: Epoch 577 +2025-10-31 13:17:56.693885: Current learning rate: 0.00461 +2025-10-31 13:18:20.673866: train_loss -0.9914 +2025-10-31 13:18:20.676461: val_loss -0.8837 +2025-10-31 13:18:20.678158: Pseudo dice [np.float32(0.9842), np.float32(0.9925), np.float32(0.995), np.float32(0.7769)] +2025-10-31 13:18:20.679760: Epoch time: 23.99 s +2025-10-31 13:18:21.920300: +2025-10-31 13:18:21.923367: Epoch 578 +2025-10-31 13:18:21.925284: Current learning rate: 0.0046 +2025-10-31 13:18:47.881838: train_loss -0.9911 +2025-10-31 13:18:47.885134: val_loss -0.8939 +2025-10-31 13:18:47.886647: Pseudo dice [np.float32(0.984), np.float32(0.9928), np.float32(0.9951), np.float32(0.799)] +2025-10-31 13:18:47.887954: Epoch time: 25.96 s +2025-10-31 13:18:49.059289: +2025-10-31 13:18:49.060954: Epoch 579 +2025-10-31 13:18:49.062352: Current learning rate: 0.00459 +2025-10-31 13:19:14.442101: train_loss -0.9911 +2025-10-31 13:19:14.445526: val_loss -0.8898 +2025-10-31 13:19:14.447935: Pseudo dice [np.float32(0.9853), np.float32(0.9924), np.float32(0.9949), np.float32(0.7822)] +2025-10-31 13:19:14.449855: Epoch time: 25.38 s +2025-10-31 13:19:15.654068: +2025-10-31 13:19:15.659586: Epoch 580 +2025-10-31 13:19:15.661676: Current learning rate: 0.00458 +2025-10-31 13:19:42.482839: train_loss -0.9905 +2025-10-31 13:19:42.490525: val_loss -0.8981 +2025-10-31 13:19:42.492000: Pseudo dice [np.float32(0.985), np.float32(0.9929), np.float32(0.9952), np.float32(0.8034)] +2025-10-31 13:19:42.496047: Epoch time: 26.83 s +2025-10-31 13:19:43.738895: +2025-10-31 13:19:43.742719: Epoch 581 +2025-10-31 13:19:43.749447: Current learning rate: 0.00457 +2025-10-31 13:20:09.174313: train_loss -0.9905 +2025-10-31 13:20:09.177022: val_loss -0.8959 +2025-10-31 13:20:09.178639: Pseudo dice [np.float32(0.9845), np.float32(0.9921), np.float32(0.9951), np.float32(0.7973)] +2025-10-31 13:20:09.180104: Epoch time: 25.44 s +2025-10-31 13:20:10.355339: +2025-10-31 13:20:10.357095: Epoch 582 +2025-10-31 13:20:10.358711: Current learning rate: 0.00456 +2025-10-31 13:20:35.825218: train_loss -0.9911 +2025-10-31 13:20:35.830688: val_loss -0.8908 +2025-10-31 13:20:35.832603: Pseudo dice [np.float32(0.9844), np.float32(0.9926), np.float32(0.9954), np.float32(0.7934)] +2025-10-31 13:20:35.834424: Epoch time: 25.47 s +2025-10-31 13:20:37.583230: +2025-10-31 13:20:37.585411: Epoch 583 +2025-10-31 13:20:37.587164: Current learning rate: 0.00455 +2025-10-31 13:21:04.336235: train_loss -0.9918 +2025-10-31 13:21:04.342542: val_loss -0.8932 +2025-10-31 13:21:04.344339: Pseudo dice [np.float32(0.9839), np.float32(0.992), np.float32(0.9953), np.float32(0.7949)] +2025-10-31 13:21:04.346494: Epoch time: 26.75 s +2025-10-31 13:21:05.645504: +2025-10-31 13:21:05.647900: Epoch 584 +2025-10-31 13:21:05.649580: Current learning rate: 0.00454 +2025-10-31 13:21:32.458541: train_loss -0.9915 +2025-10-31 13:21:32.462816: val_loss -0.8901 +2025-10-31 13:21:32.464688: Pseudo dice [np.float32(0.9852), np.float32(0.9926), np.float32(0.995), np.float32(0.7863)] +2025-10-31 13:21:32.466391: Epoch time: 26.82 s +2025-10-31 13:21:33.688523: +2025-10-31 13:21:33.690721: Epoch 585 +2025-10-31 13:21:33.692610: Current learning rate: 0.00453 +2025-10-31 13:22:00.241856: train_loss -0.9914 +2025-10-31 13:22:00.247203: val_loss -0.894 +2025-10-31 13:22:00.249007: Pseudo dice [np.float32(0.9823), np.float32(0.9926), np.float32(0.9954), np.float32(0.8073)] +2025-10-31 13:22:00.250757: Epoch time: 26.56 s +2025-10-31 13:22:01.463965: +2025-10-31 13:22:01.465837: Epoch 586 +2025-10-31 13:22:01.467777: Current learning rate: 0.00452 +2025-10-31 13:22:27.924934: train_loss -0.9914 +2025-10-31 13:22:27.929750: val_loss -0.8826 +2025-10-31 13:22:27.931347: Pseudo dice [np.float32(0.9823), np.float32(0.9916), np.float32(0.9947), np.float32(0.7808)] +2025-10-31 13:22:27.933033: Epoch time: 26.46 s +2025-10-31 13:22:29.193472: +2025-10-31 13:22:29.195488: Epoch 587 +2025-10-31 13:22:29.197317: Current learning rate: 0.00451 +2025-10-31 13:22:53.742851: train_loss -0.9906 +2025-10-31 13:22:53.753015: val_loss -0.8937 +2025-10-31 13:22:53.755205: Pseudo dice [np.float32(0.9851), np.float32(0.9928), np.float32(0.9954), np.float32(0.7939)] +2025-10-31 13:22:53.757870: Epoch time: 24.55 s +2025-10-31 13:22:55.065057: +2025-10-31 13:22:55.067624: Epoch 588 +2025-10-31 13:22:55.069583: Current learning rate: 0.0045 +2025-10-31 13:23:19.908579: train_loss -0.9912 +2025-10-31 13:23:19.913476: val_loss -0.8875 +2025-10-31 13:23:19.916655: Pseudo dice [np.float32(0.9851), np.float32(0.9928), np.float32(0.9949), np.float32(0.7812)] +2025-10-31 13:23:19.918609: Epoch time: 24.85 s +2025-10-31 13:23:21.185037: +2025-10-31 13:23:21.187441: Epoch 589 +2025-10-31 13:23:21.189483: Current learning rate: 0.00449 +2025-10-31 13:23:46.458137: train_loss -0.9908 +2025-10-31 13:23:46.465448: val_loss -0.8951 +2025-10-31 13:23:46.468619: Pseudo dice [np.float32(0.9857), np.float32(0.9923), np.float32(0.9953), np.float32(0.8004)] +2025-10-31 13:23:46.471637: Epoch time: 25.28 s +2025-10-31 13:23:47.680895: +2025-10-31 13:23:47.683259: Epoch 590 +2025-10-31 13:23:47.686260: Current learning rate: 0.00448 +2025-10-31 13:24:15.027297: train_loss -0.9914 +2025-10-31 13:24:15.032404: val_loss -0.8861 +2025-10-31 13:24:15.034633: Pseudo dice [np.float32(0.985), np.float32(0.9918), np.float32(0.995), np.float32(0.7879)] +2025-10-31 13:24:15.036375: Epoch time: 27.35 s +2025-10-31 13:24:16.272746: +2025-10-31 13:24:16.274677: Epoch 591 +2025-10-31 13:24:16.276543: Current learning rate: 0.00447 +2025-10-31 13:24:42.810502: train_loss -0.991 +2025-10-31 13:24:42.815476: val_loss -0.8976 +2025-10-31 13:24:42.818942: Pseudo dice [np.float32(0.9855), np.float32(0.9929), np.float32(0.9955), np.float32(0.8035)] +2025-10-31 13:24:42.822006: Epoch time: 26.54 s +2025-10-31 13:24:44.041924: +2025-10-31 13:24:44.044696: Epoch 592 +2025-10-31 13:24:44.046679: Current learning rate: 0.00446 +2025-10-31 13:25:08.549543: train_loss -0.9905 +2025-10-31 13:25:08.559093: val_loss -0.8975 +2025-10-31 13:25:08.565774: Pseudo dice [np.float32(0.9838), np.float32(0.9925), np.float32(0.9953), np.float32(0.8048)] +2025-10-31 13:25:08.569139: Epoch time: 24.51 s +2025-10-31 13:25:09.803861: +2025-10-31 13:25:09.805813: Epoch 593 +2025-10-31 13:25:09.807963: Current learning rate: 0.00445 +2025-10-31 13:25:33.385219: train_loss -0.9911 +2025-10-31 13:25:33.392335: val_loss -0.8866 +2025-10-31 13:25:33.395775: Pseudo dice [np.float32(0.9844), np.float32(0.9925), np.float32(0.9951), np.float32(0.7845)] +2025-10-31 13:25:33.398309: Epoch time: 23.58 s +2025-10-31 13:25:34.588495: +2025-10-31 13:25:34.591340: Epoch 594 +2025-10-31 13:25:34.593246: Current learning rate: 0.00444 +2025-10-31 13:25:59.940238: train_loss -0.9908 +2025-10-31 13:25:59.944368: val_loss -0.8869 +2025-10-31 13:25:59.945958: Pseudo dice [np.float32(0.9846), np.float32(0.9925), np.float32(0.995), np.float32(0.7843)] +2025-10-31 13:25:59.948234: Epoch time: 25.35 s +2025-10-31 13:26:01.093844: +2025-10-31 13:26:01.096833: Epoch 595 +2025-10-31 13:26:01.099339: Current learning rate: 0.00443 +2025-10-31 13:26:28.016762: train_loss -0.9902 +2025-10-31 13:26:28.026441: val_loss -0.8862 +2025-10-31 13:26:28.028871: Pseudo dice [np.float32(0.984), np.float32(0.9922), np.float32(0.9947), np.float32(0.7817)] +2025-10-31 13:26:28.030586: Epoch time: 26.92 s +2025-10-31 13:26:30.283850: +2025-10-31 13:26:30.286656: Epoch 596 +2025-10-31 13:26:30.288914: Current learning rate: 0.00442 +2025-10-31 13:26:58.118035: train_loss -0.9912 +2025-10-31 13:26:58.121336: val_loss -0.8808 +2025-10-31 13:26:58.123870: Pseudo dice [np.float32(0.9848), np.float32(0.9918), np.float32(0.9948), np.float32(0.7757)] +2025-10-31 13:26:58.125806: Epoch time: 27.84 s +2025-10-31 13:26:59.423343: +2025-10-31 13:26:59.426061: Epoch 597 +2025-10-31 13:26:59.427962: Current learning rate: 0.00441 +2025-10-31 13:27:25.553085: train_loss -0.992 +2025-10-31 13:27:25.564720: val_loss -0.8907 +2025-10-31 13:27:25.566839: Pseudo dice [np.float32(0.9834), np.float32(0.9922), np.float32(0.995), np.float32(0.791)] +2025-10-31 13:27:25.569202: Epoch time: 26.13 s +2025-10-31 13:27:26.790608: +2025-10-31 13:27:26.792673: Epoch 598 +2025-10-31 13:27:26.794674: Current learning rate: 0.0044 +2025-10-31 13:27:52.760549: train_loss -0.9919 +2025-10-31 13:27:52.764764: val_loss -0.8927 +2025-10-31 13:27:52.766609: Pseudo dice [np.float32(0.9833), np.float32(0.9919), np.float32(0.9952), np.float32(0.8019)] +2025-10-31 13:27:52.768408: Epoch time: 25.97 s +2025-10-31 13:27:54.019374: +2025-10-31 13:27:54.021165: Epoch 599 +2025-10-31 13:27:54.022697: Current learning rate: 0.00439 +2025-10-31 13:28:20.405488: train_loss -0.9914 +2025-10-31 13:28:20.408995: val_loss -0.8891 +2025-10-31 13:28:20.411235: Pseudo dice [np.float32(0.9849), np.float32(0.9923), np.float32(0.9952), np.float32(0.7916)] +2025-10-31 13:28:20.412943: Epoch time: 26.39 s +2025-10-31 13:28:23.028712: +2025-10-31 13:28:23.032227: Epoch 600 +2025-10-31 13:28:23.036397: Current learning rate: 0.00438 +2025-10-31 13:28:47.288942: train_loss -0.9917 +2025-10-31 13:28:47.295367: val_loss -0.89 +2025-10-31 13:28:47.297929: Pseudo dice [np.float32(0.9827), np.float32(0.9912), np.float32(0.9954), np.float32(0.7963)] +2025-10-31 13:28:47.299837: Epoch time: 24.26 s +2025-10-31 13:28:48.492421: +2025-10-31 13:28:48.494784: Epoch 601 +2025-10-31 13:28:48.497219: Current learning rate: 0.00437 +2025-10-31 13:29:14.106971: train_loss -0.9913 +2025-10-31 13:29:14.111232: val_loss -0.8872 +2025-10-31 13:29:14.113068: Pseudo dice [np.float32(0.9835), np.float32(0.992), np.float32(0.9948), np.float32(0.7909)] +2025-10-31 13:29:14.115768: Epoch time: 25.62 s +2025-10-31 13:29:15.320024: +2025-10-31 13:29:15.322488: Epoch 602 +2025-10-31 13:29:15.324765: Current learning rate: 0.00436 +2025-10-31 13:29:42.937336: train_loss -0.9918 +2025-10-31 13:29:42.941354: val_loss -0.8792 +2025-10-31 13:29:42.944178: Pseudo dice [np.float32(0.9836), np.float32(0.9914), np.float32(0.9945), np.float32(0.7644)] +2025-10-31 13:29:42.946679: Epoch time: 27.62 s +2025-10-31 13:29:44.069664: +2025-10-31 13:29:44.073733: Epoch 603 +2025-10-31 13:29:44.076047: Current learning rate: 0.00435 +2025-10-31 13:30:10.091358: train_loss -0.9906 +2025-10-31 13:30:10.095343: val_loss -0.8931 +2025-10-31 13:30:10.098311: Pseudo dice [np.float32(0.984), np.float32(0.9918), np.float32(0.9951), np.float32(0.7941)] +2025-10-31 13:30:10.100892: Epoch time: 26.02 s +2025-10-31 13:30:11.412962: +2025-10-31 13:30:11.416510: Epoch 604 +2025-10-31 13:30:11.419765: Current learning rate: 0.00434 +2025-10-31 13:30:38.707482: train_loss -0.9906 +2025-10-31 13:30:38.710698: val_loss -0.8799 +2025-10-31 13:30:38.712698: Pseudo dice [np.float32(0.9839), np.float32(0.9921), np.float32(0.9946), np.float32(0.7679)] +2025-10-31 13:30:38.714857: Epoch time: 27.3 s +2025-10-31 13:30:39.763650: +2025-10-31 13:30:39.765622: Epoch 605 +2025-10-31 13:30:39.767869: Current learning rate: 0.00433 +2025-10-31 13:31:05.730800: train_loss -0.9919 +2025-10-31 13:31:05.733788: val_loss -0.8906 +2025-10-31 13:31:05.735643: Pseudo dice [np.float32(0.985), np.float32(0.9918), np.float32(0.9948), np.float32(0.787)] +2025-10-31 13:31:05.738262: Epoch time: 25.97 s +2025-10-31 13:31:06.978678: +2025-10-31 13:31:06.981090: Epoch 606 +2025-10-31 13:31:06.983447: Current learning rate: 0.00432 +2025-10-31 13:31:32.341463: train_loss -0.9908 +2025-10-31 13:31:32.346102: val_loss -0.8912 +2025-10-31 13:31:32.348737: Pseudo dice [np.float32(0.9852), np.float32(0.9922), np.float32(0.9946), np.float32(0.7905)] +2025-10-31 13:31:32.351357: Epoch time: 25.36 s +2025-10-31 13:31:33.590475: +2025-10-31 13:31:33.596024: Epoch 607 +2025-10-31 13:31:33.597925: Current learning rate: 0.00431 +2025-10-31 13:31:58.330703: train_loss -0.9909 +2025-10-31 13:31:58.352489: val_loss -0.8868 +2025-10-31 13:31:58.386753: Pseudo dice [np.float32(0.9855), np.float32(0.993), np.float32(0.9948), np.float32(0.7712)] +2025-10-31 13:31:58.417732: Epoch time: 24.74 s +2025-10-31 13:32:00.347758: +2025-10-31 13:32:00.351059: Epoch 608 +2025-10-31 13:32:00.355630: Current learning rate: 0.0043 +2025-10-31 13:32:27.604523: train_loss -0.9903 +2025-10-31 13:32:27.608130: val_loss -0.8878 +2025-10-31 13:32:27.610573: Pseudo dice [np.float32(0.9854), np.float32(0.9919), np.float32(0.9949), np.float32(0.7763)] +2025-10-31 13:32:27.615840: Epoch time: 27.26 s +2025-10-31 13:32:28.640894: +2025-10-31 13:32:28.643676: Epoch 609 +2025-10-31 13:32:28.645621: Current learning rate: 0.00429 +2025-10-31 13:32:55.152132: train_loss -0.9919 +2025-10-31 13:32:55.156485: val_loss -0.892 +2025-10-31 13:32:55.158100: Pseudo dice [np.float32(0.9857), np.float32(0.9924), np.float32(0.9953), np.float32(0.7982)] +2025-10-31 13:32:55.159562: Epoch time: 26.51 s +2025-10-31 13:32:56.403915: +2025-10-31 13:32:56.405769: Epoch 610 +2025-10-31 13:32:56.408028: Current learning rate: 0.00429 +2025-10-31 13:33:23.402507: train_loss -0.9904 +2025-10-31 13:33:23.407360: val_loss -0.8801 +2025-10-31 13:33:23.409429: Pseudo dice [np.float32(0.9844), np.float32(0.9926), np.float32(0.9948), np.float32(0.7648)] +2025-10-31 13:33:23.411652: Epoch time: 27.0 s +2025-10-31 13:33:24.700650: +2025-10-31 13:33:24.702733: Epoch 611 +2025-10-31 13:33:24.704783: Current learning rate: 0.00428 +2025-10-31 13:33:49.968976: train_loss -0.9907 +2025-10-31 13:33:49.980530: val_loss -0.8836 +2025-10-31 13:33:49.984750: Pseudo dice [np.float32(0.9845), np.float32(0.9921), np.float32(0.9945), np.float32(0.7666)] +2025-10-31 13:33:49.988125: Epoch time: 25.27 s +2025-10-31 13:33:51.237929: +2025-10-31 13:33:51.240912: Epoch 612 +2025-10-31 13:33:51.243306: Current learning rate: 0.00427 +2025-10-31 13:34:17.606911: train_loss -0.9905 +2025-10-31 13:34:17.612777: val_loss -0.8936 +2025-10-31 13:34:17.614540: Pseudo dice [np.float32(0.984), np.float32(0.9918), np.float32(0.9953), np.float32(0.7991)] +2025-10-31 13:34:17.616078: Epoch time: 26.37 s +2025-10-31 13:34:18.860313: +2025-10-31 13:34:18.865537: Epoch 613 +2025-10-31 13:34:18.867859: Current learning rate: 0.00426 +2025-10-31 13:34:43.145297: train_loss -0.9915 +2025-10-31 13:34:43.148571: val_loss -0.8856 +2025-10-31 13:34:43.150558: Pseudo dice [np.float32(0.9841), np.float32(0.9912), np.float32(0.9948), np.float32(0.7876)] +2025-10-31 13:34:43.152127: Epoch time: 24.29 s +2025-10-31 13:34:44.337104: +2025-10-31 13:34:44.340502: Epoch 614 +2025-10-31 13:34:44.342682: Current learning rate: 0.00425 +2025-10-31 13:35:11.768504: train_loss -0.9918 +2025-10-31 13:35:11.773673: val_loss -0.8986 +2025-10-31 13:35:11.775453: Pseudo dice [np.float32(0.9853), np.float32(0.9932), np.float32(0.9957), np.float32(0.8094)] +2025-10-31 13:35:11.777256: Epoch time: 27.43 s +2025-10-31 13:35:13.040794: +2025-10-31 13:35:13.043444: Epoch 615 +2025-10-31 13:35:13.045672: Current learning rate: 0.00424 +2025-10-31 13:35:40.052498: train_loss -0.9915 +2025-10-31 13:35:40.055466: val_loss -0.894 +2025-10-31 13:35:40.057337: Pseudo dice [np.float32(0.984), np.float32(0.9919), np.float32(0.9953), np.float32(0.8026)] +2025-10-31 13:35:40.059022: Epoch time: 27.01 s +2025-10-31 13:35:41.274886: +2025-10-31 13:35:41.276718: Epoch 616 +2025-10-31 13:35:41.278516: Current learning rate: 0.00423 +2025-10-31 13:36:06.341198: train_loss -0.9916 +2025-10-31 13:36:06.344542: val_loss -0.894 +2025-10-31 13:36:06.346795: Pseudo dice [np.float32(0.9835), np.float32(0.9922), np.float32(0.995), np.float32(0.7954)] +2025-10-31 13:36:06.349166: Epoch time: 25.07 s +2025-10-31 13:36:07.563415: +2025-10-31 13:36:07.566712: Epoch 617 +2025-10-31 13:36:07.568611: Current learning rate: 0.00422 +2025-10-31 13:36:33.648659: train_loss -0.9913 +2025-10-31 13:36:33.652572: val_loss -0.8865 +2025-10-31 13:36:33.654361: Pseudo dice [np.float32(0.9849), np.float32(0.992), np.float32(0.995), np.float32(0.7825)] +2025-10-31 13:36:33.655878: Epoch time: 26.09 s +2025-10-31 13:36:34.934474: +2025-10-31 13:36:34.936739: Epoch 618 +2025-10-31 13:36:34.938948: Current learning rate: 0.00421 +2025-10-31 13:37:00.540154: train_loss -0.9915 +2025-10-31 13:37:00.552226: val_loss -0.8844 +2025-10-31 13:37:00.561367: Pseudo dice [np.float32(0.9853), np.float32(0.9918), np.float32(0.9946), np.float32(0.7846)] +2025-10-31 13:37:00.563689: Epoch time: 25.61 s +2025-10-31 13:37:01.833501: +2025-10-31 13:37:01.836409: Epoch 619 +2025-10-31 13:37:01.838986: Current learning rate: 0.0042 +2025-10-31 13:37:27.862400: train_loss -0.9911 +2025-10-31 13:37:27.870424: val_loss -0.888 +2025-10-31 13:37:27.872336: Pseudo dice [np.float32(0.9855), np.float32(0.9927), np.float32(0.9954), np.float32(0.7818)] +2025-10-31 13:37:27.873871: Epoch time: 26.03 s +2025-10-31 13:37:29.096676: +2025-10-31 13:37:29.098828: Epoch 620 +2025-10-31 13:37:29.100651: Current learning rate: 0.00419 +2025-10-31 13:37:51.700574: train_loss -0.9915 +2025-10-31 13:37:51.704684: val_loss -0.8898 +2025-10-31 13:37:51.706343: Pseudo dice [np.float32(0.9843), np.float32(0.9917), np.float32(0.9952), np.float32(0.7882)] +2025-10-31 13:37:51.707921: Epoch time: 22.61 s +2025-10-31 13:37:53.411944: +2025-10-31 13:37:53.414447: Epoch 621 +2025-10-31 13:37:53.416156: Current learning rate: 0.00418 +2025-10-31 13:38:20.080058: train_loss -0.9907 +2025-10-31 13:38:20.087164: val_loss -0.896 +2025-10-31 13:38:20.089026: Pseudo dice [np.float32(0.9834), np.float32(0.9918), np.float32(0.9952), np.float32(0.8034)] +2025-10-31 13:38:20.090796: Epoch time: 26.67 s +2025-10-31 13:38:21.357649: +2025-10-31 13:38:21.360543: Epoch 622 +2025-10-31 13:38:21.362737: Current learning rate: 0.00417 +2025-10-31 13:38:47.231384: train_loss -0.9914 +2025-10-31 13:38:47.234012: val_loss -0.8969 +2025-10-31 13:38:47.235773: Pseudo dice [np.float32(0.9848), np.float32(0.9923), np.float32(0.9953), np.float32(0.8007)] +2025-10-31 13:38:47.237452: Epoch time: 25.88 s +2025-10-31 13:38:48.499068: +2025-10-31 13:38:48.501859: Epoch 623 +2025-10-31 13:38:48.503872: Current learning rate: 0.00416 +2025-10-31 13:39:14.026294: train_loss -0.9916 +2025-10-31 13:39:14.029324: val_loss -0.8982 +2025-10-31 13:39:14.031277: Pseudo dice [np.float32(0.9852), np.float32(0.9929), np.float32(0.9952), np.float32(0.8001)] +2025-10-31 13:39:14.032912: Epoch time: 25.53 s +2025-10-31 13:39:15.268273: +2025-10-31 13:39:15.273069: Epoch 624 +2025-10-31 13:39:15.279071: Current learning rate: 0.00415 +2025-10-31 13:39:41.162988: train_loss -0.991 +2025-10-31 13:39:41.169388: val_loss -0.8985 +2025-10-31 13:39:41.174613: Pseudo dice [np.float32(0.9852), np.float32(0.9928), np.float32(0.9957), np.float32(0.8094)] +2025-10-31 13:39:41.178141: Epoch time: 25.9 s +2025-10-31 13:39:42.407438: +2025-10-31 13:39:42.409285: Epoch 625 +2025-10-31 13:39:42.411017: Current learning rate: 0.00414 +2025-10-31 13:40:08.563244: train_loss -0.9912 +2025-10-31 13:40:08.568973: val_loss -0.8977 +2025-10-31 13:40:08.571192: Pseudo dice [np.float32(0.9835), np.float32(0.992), np.float32(0.9954), np.float32(0.8112)] +2025-10-31 13:40:08.577665: Epoch time: 26.16 s +2025-10-31 13:40:09.720643: +2025-10-31 13:40:09.722475: Epoch 626 +2025-10-31 13:40:09.724017: Current learning rate: 0.00413 +2025-10-31 13:40:35.341025: train_loss -0.9917 +2025-10-31 13:40:35.343818: val_loss -0.8968 +2025-10-31 13:40:35.345621: Pseudo dice [np.float32(0.9849), np.float32(0.9924), np.float32(0.9951), np.float32(0.7981)] +2025-10-31 13:40:35.347300: Epoch time: 25.62 s +2025-10-31 13:40:36.497858: +2025-10-31 13:40:36.499934: Epoch 627 +2025-10-31 13:40:36.501998: Current learning rate: 0.00412 +2025-10-31 13:41:00.212186: train_loss -0.9913 +2025-10-31 13:41:00.215914: val_loss -0.8932 +2025-10-31 13:41:00.218006: Pseudo dice [np.float32(0.9843), np.float32(0.9919), np.float32(0.995), np.float32(0.7994)] +2025-10-31 13:41:00.219904: Epoch time: 23.72 s +2025-10-31 13:41:01.435931: +2025-10-31 13:41:01.438762: Epoch 628 +2025-10-31 13:41:01.440649: Current learning rate: 0.00411 +2025-10-31 13:41:27.775940: train_loss -0.9914 +2025-10-31 13:41:27.784225: val_loss -0.8907 +2025-10-31 13:41:27.787741: Pseudo dice [np.float32(0.985), np.float32(0.9924), np.float32(0.9952), np.float32(0.7926)] +2025-10-31 13:41:27.795472: Epoch time: 26.34 s +2025-10-31 13:41:29.012992: +2025-10-31 13:41:29.015230: Epoch 629 +2025-10-31 13:41:29.017051: Current learning rate: 0.0041 +2025-10-31 13:41:56.372968: train_loss -0.9916 +2025-10-31 13:41:56.375970: val_loss -0.9018 +2025-10-31 13:41:56.377520: Pseudo dice [np.float32(0.9843), np.float32(0.9925), np.float32(0.9957), np.float32(0.8107)] +2025-10-31 13:41:56.378949: Epoch time: 27.36 s +2025-10-31 13:41:57.603621: +2025-10-31 13:41:57.605775: Epoch 630 +2025-10-31 13:41:57.607610: Current learning rate: 0.00409 +2025-10-31 13:42:22.604296: train_loss -0.9906 +2025-10-31 13:42:22.611441: val_loss -0.8932 +2025-10-31 13:42:22.613205: Pseudo dice [np.float32(0.9839), np.float32(0.992), np.float32(0.9949), np.float32(0.7821)] +2025-10-31 13:42:22.614864: Epoch time: 25.0 s +2025-10-31 13:42:23.862693: +2025-10-31 13:42:23.864847: Epoch 631 +2025-10-31 13:42:23.866441: Current learning rate: 0.00408 +2025-10-31 13:42:48.019050: train_loss -0.9911 +2025-10-31 13:42:48.022561: val_loss -0.8829 +2025-10-31 13:42:48.024260: Pseudo dice [np.float32(0.984), np.float32(0.9918), np.float32(0.9946), np.float32(0.7738)] +2025-10-31 13:42:48.025995: Epoch time: 24.16 s +2025-10-31 13:42:49.089343: +2025-10-31 13:42:49.094504: Epoch 632 +2025-10-31 13:42:49.096244: Current learning rate: 0.00407 +2025-10-31 13:43:14.436893: train_loss -0.9918 +2025-10-31 13:43:14.445549: val_loss -0.8892 +2025-10-31 13:43:14.447592: Pseudo dice [np.float32(0.983), np.float32(0.9923), np.float32(0.9949), np.float32(0.7917)] +2025-10-31 13:43:14.449552: Epoch time: 25.35 s +2025-10-31 13:43:16.533700: +2025-10-31 13:43:16.536625: Epoch 633 +2025-10-31 13:43:16.539717: Current learning rate: 0.00406 +2025-10-31 13:43:40.509960: train_loss -0.9914 +2025-10-31 13:43:40.512747: val_loss -0.9009 +2025-10-31 13:43:40.514368: Pseudo dice [np.float32(0.983), np.float32(0.9919), np.float32(0.9952), np.float32(0.8086)] +2025-10-31 13:43:40.516077: Epoch time: 23.98 s +2025-10-31 13:43:41.743710: +2025-10-31 13:43:41.745887: Epoch 634 +2025-10-31 13:43:41.748603: Current learning rate: 0.00405 +2025-10-31 13:44:06.457765: train_loss -0.9909 +2025-10-31 13:44:06.460740: val_loss -0.8914 +2025-10-31 13:44:06.463992: Pseudo dice [np.float32(0.9844), np.float32(0.9924), np.float32(0.995), np.float32(0.797)] +2025-10-31 13:44:06.468678: Epoch time: 24.72 s +2025-10-31 13:44:07.718795: +2025-10-31 13:44:07.721073: Epoch 635 +2025-10-31 13:44:07.723335: Current learning rate: 0.00404 +2025-10-31 13:44:34.362350: train_loss -0.9912 +2025-10-31 13:44:34.368840: val_loss -0.8924 +2025-10-31 13:44:34.371176: Pseudo dice [np.float32(0.9847), np.float32(0.9924), np.float32(0.9952), np.float32(0.7875)] +2025-10-31 13:44:34.373254: Epoch time: 26.65 s +2025-10-31 13:44:35.593755: +2025-10-31 13:44:35.596438: Epoch 636 +2025-10-31 13:44:35.598754: Current learning rate: 0.00403 +2025-10-31 13:45:01.947814: train_loss -0.9917 +2025-10-31 13:45:01.960616: val_loss -0.8929 +2025-10-31 13:45:01.964113: Pseudo dice [np.float32(0.985), np.float32(0.9924), np.float32(0.9949), np.float32(0.7955)] +2025-10-31 13:45:01.965990: Epoch time: 26.36 s +2025-10-31 13:45:03.218818: +2025-10-31 13:45:03.220927: Epoch 637 +2025-10-31 13:45:03.222802: Current learning rate: 0.00402 +2025-10-31 13:45:31.097795: train_loss -0.9915 +2025-10-31 13:45:31.100159: val_loss -0.8874 +2025-10-31 13:45:31.101892: Pseudo dice [np.float32(0.9843), np.float32(0.9928), np.float32(0.9948), np.float32(0.7812)] +2025-10-31 13:45:31.104787: Epoch time: 27.88 s +2025-10-31 13:45:32.134940: +2025-10-31 13:45:32.138128: Epoch 638 +2025-10-31 13:45:32.140497: Current learning rate: 0.00401 +2025-10-31 13:45:57.934520: train_loss -0.9917 +2025-10-31 13:45:57.942505: val_loss -0.8918 +2025-10-31 13:45:57.947295: Pseudo dice [np.float32(0.9837), np.float32(0.9926), np.float32(0.9951), np.float32(0.7976)] +2025-10-31 13:45:57.953027: Epoch time: 25.8 s +2025-10-31 13:45:59.138232: +2025-10-31 13:45:59.140241: Epoch 639 +2025-10-31 13:45:59.142706: Current learning rate: 0.004 +2025-10-31 13:46:24.510349: train_loss -0.9912 +2025-10-31 13:46:24.516477: val_loss -0.891 +2025-10-31 13:46:24.518245: Pseudo dice [np.float32(0.9859), np.float32(0.9929), np.float32(0.9953), np.float32(0.7851)] +2025-10-31 13:46:24.520245: Epoch time: 25.37 s +2025-10-31 13:46:25.817101: +2025-10-31 13:46:25.819041: Epoch 640 +2025-10-31 13:46:25.821081: Current learning rate: 0.00399 +2025-10-31 13:46:49.782356: train_loss -0.9909 +2025-10-31 13:46:49.786332: val_loss -0.8925 +2025-10-31 13:46:49.788044: Pseudo dice [np.float32(0.9837), np.float32(0.9923), np.float32(0.9949), np.float32(0.7969)] +2025-10-31 13:46:49.789759: Epoch time: 23.97 s +2025-10-31 13:46:50.909985: +2025-10-31 13:46:50.912500: Epoch 641 +2025-10-31 13:46:50.914738: Current learning rate: 0.00398 +2025-10-31 13:47:15.169854: train_loss -0.9908 +2025-10-31 13:47:15.176718: val_loss -0.8913 +2025-10-31 13:47:15.179458: Pseudo dice [np.float32(0.9852), np.float32(0.9928), np.float32(0.9954), np.float32(0.7878)] +2025-10-31 13:47:15.181347: Epoch time: 24.26 s +2025-10-31 13:47:16.391437: +2025-10-31 13:47:16.393712: Epoch 642 +2025-10-31 13:47:16.395602: Current learning rate: 0.00397 +2025-10-31 13:47:42.176388: train_loss -0.9913 +2025-10-31 13:47:42.180521: val_loss -0.8901 +2025-10-31 13:47:42.182467: Pseudo dice [np.float32(0.9844), np.float32(0.9931), np.float32(0.9953), np.float32(0.7868)] +2025-10-31 13:47:42.184218: Epoch time: 25.79 s +2025-10-31 13:47:43.261356: +2025-10-31 13:47:43.263751: Epoch 643 +2025-10-31 13:47:43.265576: Current learning rate: 0.00396 +2025-10-31 13:48:08.141937: train_loss -0.9918 +2025-10-31 13:48:08.144949: val_loss -0.8878 +2025-10-31 13:48:08.147102: Pseudo dice [np.float32(0.9855), np.float32(0.9926), np.float32(0.9947), np.float32(0.7732)] +2025-10-31 13:48:08.148809: Epoch time: 24.88 s +2025-10-31 13:48:09.342913: +2025-10-31 13:48:09.345294: Epoch 644 +2025-10-31 13:48:09.347599: Current learning rate: 0.00395 +2025-10-31 13:48:36.524408: train_loss -0.9921 +2025-10-31 13:48:36.527709: val_loss -0.8901 +2025-10-31 13:48:36.529886: Pseudo dice [np.float32(0.986), np.float32(0.9929), np.float32(0.9951), np.float32(0.7842)] +2025-10-31 13:48:36.534067: Epoch time: 27.18 s +2025-10-31 13:48:37.772769: +2025-10-31 13:48:37.781217: Epoch 645 +2025-10-31 13:48:37.789522: Current learning rate: 0.00394 +2025-10-31 13:49:05.935751: train_loss -0.9923 +2025-10-31 13:49:05.938677: val_loss -0.8926 +2025-10-31 13:49:05.940467: Pseudo dice [np.float32(0.985), np.float32(0.9925), np.float32(0.9951), np.float32(0.7938)] +2025-10-31 13:49:05.942770: Epoch time: 28.16 s +2025-10-31 13:49:07.134435: +2025-10-31 13:49:07.137171: Epoch 646 +2025-10-31 13:49:07.139547: Current learning rate: 0.00393 +2025-10-31 13:49:33.016513: train_loss -0.9907 +2025-10-31 13:49:33.019201: val_loss -0.8954 +2025-10-31 13:49:33.020891: Pseudo dice [np.float32(0.9852), np.float32(0.993), np.float32(0.9956), np.float32(0.7963)] +2025-10-31 13:49:33.023844: Epoch time: 25.88 s +2025-10-31 13:49:34.278740: +2025-10-31 13:49:34.281053: Epoch 647 +2025-10-31 13:49:34.283324: Current learning rate: 0.00392 +2025-10-31 13:50:00.602141: train_loss -0.9824 +2025-10-31 13:50:00.605429: val_loss -0.8603 +2025-10-31 13:50:00.607297: Pseudo dice [np.float32(0.9836), np.float32(0.9604), np.float32(0.9823), np.float32(0.7824)] +2025-10-31 13:50:00.609299: Epoch time: 26.33 s +2025-10-31 13:50:01.796268: +2025-10-31 13:50:01.798962: Epoch 648 +2025-10-31 13:50:01.800779: Current learning rate: 0.00391 +2025-10-31 13:50:25.236822: train_loss -0.98 +2025-10-31 13:50:25.241078: val_loss -0.8973 +2025-10-31 13:50:25.243873: Pseudo dice [np.float32(0.9825), np.float32(0.9914), np.float32(0.9953), np.float32(0.7962)] +2025-10-31 13:50:25.246092: Epoch time: 23.44 s +2025-10-31 13:50:26.500809: +2025-10-31 13:50:26.503472: Epoch 649 +2025-10-31 13:50:26.506000: Current learning rate: 0.0039 +2025-10-31 13:50:49.708042: train_loss -0.9795 +2025-10-31 13:50:49.710431: val_loss -0.9038 +2025-10-31 13:50:49.712463: Pseudo dice [np.float32(0.9842), np.float32(0.9925), np.float32(0.9955), np.float32(0.8125)] +2025-10-31 13:50:49.714841: Epoch time: 23.21 s +2025-10-31 13:50:52.333387: +2025-10-31 13:50:52.336291: Epoch 650 +2025-10-31 13:50:52.338820: Current learning rate: 0.00389 +2025-10-31 13:51:18.399919: train_loss -0.9861 +2025-10-31 13:51:18.405890: val_loss -0.8997 +2025-10-31 13:51:18.409389: Pseudo dice [np.float32(0.9838), np.float32(0.9924), np.float32(0.9954), np.float32(0.7972)] +2025-10-31 13:51:18.412444: Epoch time: 26.07 s +2025-10-31 13:51:19.489058: +2025-10-31 13:51:19.490897: Epoch 651 +2025-10-31 13:51:19.492494: Current learning rate: 0.00388 +2025-10-31 13:51:44.557306: train_loss -0.988 +2025-10-31 13:51:44.560764: val_loss -0.8889 +2025-10-31 13:51:44.562877: Pseudo dice [np.float32(0.9824), np.float32(0.9919), np.float32(0.995), np.float32(0.7866)] +2025-10-31 13:51:44.564899: Epoch time: 25.07 s +2025-10-31 13:51:45.817414: +2025-10-31 13:51:45.820090: Epoch 652 +2025-10-31 13:51:45.822100: Current learning rate: 0.00387 +2025-10-31 13:52:13.035328: train_loss -0.9435 +2025-10-31 13:52:13.039611: val_loss -0.9103 +2025-10-31 13:52:13.041423: Pseudo dice [np.float32(0.9837), np.float32(0.9889), np.float32(0.9916), np.float32(0.8173)] +2025-10-31 13:52:13.043456: Epoch time: 27.22 s +2025-10-31 13:52:14.289766: +2025-10-31 13:52:14.293142: Epoch 653 +2025-10-31 13:52:14.295090: Current learning rate: 0.00386 +2025-10-31 13:52:39.091874: train_loss -0.9134 +2025-10-31 13:52:39.096806: val_loss -0.8648 +2025-10-31 13:52:39.098639: Pseudo dice [np.float32(0.9827), np.float32(0.9387), np.float32(0.9881), np.float32(0.837)] +2025-10-31 13:52:39.100474: Epoch time: 24.8 s +2025-10-31 13:52:40.432499: +2025-10-31 13:52:40.435768: Epoch 654 +2025-10-31 13:52:40.438151: Current learning rate: 0.00385 +2025-10-31 13:53:06.695485: train_loss -0.9268 +2025-10-31 13:53:06.700039: val_loss -0.8989 +2025-10-31 13:53:06.701947: Pseudo dice [np.float32(0.9783), np.float32(0.9873), np.float32(0.9901), np.float32(0.8089)] +2025-10-31 13:53:06.703802: Epoch time: 26.27 s +2025-10-31 13:53:07.951668: +2025-10-31 13:53:07.954150: Epoch 655 +2025-10-31 13:53:07.955978: Current learning rate: 0.00384 +2025-10-31 13:53:33.268968: train_loss -0.945 +2025-10-31 13:53:33.271874: val_loss -0.9147 +2025-10-31 13:53:33.273831: Pseudo dice [np.float32(0.9835), np.float32(0.9899), np.float32(0.9943), np.float32(0.8107)] +2025-10-31 13:53:33.277493: Epoch time: 25.32 s +2025-10-31 13:53:34.512500: +2025-10-31 13:53:34.525438: Epoch 656 +2025-10-31 13:53:34.531912: Current learning rate: 0.00383 +2025-10-31 13:53:58.199418: train_loss -0.9566 +2025-10-31 13:53:58.204284: val_loss -0.9087 +2025-10-31 13:53:58.206190: Pseudo dice [np.float32(0.9837), np.float32(0.9911), np.float32(0.9948), np.float32(0.7974)] +2025-10-31 13:53:58.207934: Epoch time: 23.69 s +2025-10-31 13:54:00.033501: +2025-10-31 13:54:00.037357: Epoch 657 +2025-10-31 13:54:00.041545: Current learning rate: 0.00382 +2025-10-31 13:54:25.789196: train_loss -0.9712 +2025-10-31 13:54:25.793536: val_loss -0.9135 +2025-10-31 13:54:25.795664: Pseudo dice [np.float32(0.9824), np.float32(0.9908), np.float32(0.9949), np.float32(0.8168)] +2025-10-31 13:54:25.797233: Epoch time: 25.76 s +2025-10-31 13:54:27.030049: +2025-10-31 13:54:27.031904: Epoch 658 +2025-10-31 13:54:27.034081: Current learning rate: 0.00381 +2025-10-31 13:54:53.040895: train_loss -0.9764 +2025-10-31 13:54:53.047344: val_loss -0.908 +2025-10-31 13:54:53.050543: Pseudo dice [np.float32(0.9813), np.float32(0.9908), np.float32(0.9954), np.float32(0.8101)] +2025-10-31 13:54:53.052433: Epoch time: 26.01 s +2025-10-31 13:54:54.341249: +2025-10-31 13:54:54.345035: Epoch 659 +2025-10-31 13:54:54.347162: Current learning rate: 0.0038 +2025-10-31 13:55:20.791310: train_loss -0.9818 +2025-10-31 13:55:20.794935: val_loss -0.8986 +2025-10-31 13:55:20.797713: Pseudo dice [np.float32(0.9834), np.float32(0.992), np.float32(0.9948), np.float32(0.78)] +2025-10-31 13:55:20.799882: Epoch time: 26.45 s +2025-10-31 13:55:22.030648: +2025-10-31 13:55:22.032499: Epoch 660 +2025-10-31 13:55:22.034053: Current learning rate: 0.00379 +2025-10-31 13:55:48.921882: train_loss -0.981 +2025-10-31 13:55:48.931434: val_loss -0.902 +2025-10-31 13:55:48.934334: Pseudo dice [np.float32(0.9824), np.float32(0.9914), np.float32(0.9953), np.float32(0.799)] +2025-10-31 13:55:48.935888: Epoch time: 26.89 s +2025-10-31 13:55:50.237692: +2025-10-31 13:55:50.239719: Epoch 661 +2025-10-31 13:55:50.241511: Current learning rate: 0.00378 +2025-10-31 13:56:15.774548: train_loss -0.9751 +2025-10-31 13:56:15.780062: val_loss -0.8917 +2025-10-31 13:56:15.782028: Pseudo dice [np.float32(0.9822), np.float32(0.9909), np.float32(0.9945), np.float32(0.7671)] +2025-10-31 13:56:15.786810: Epoch time: 25.54 s +2025-10-31 13:56:17.014511: +2025-10-31 13:56:17.016669: Epoch 662 +2025-10-31 13:56:17.018592: Current learning rate: 0.00377 +2025-10-31 13:56:43.680807: train_loss -0.9768 +2025-10-31 13:56:43.684604: val_loss -0.9036 +2025-10-31 13:56:43.686337: Pseudo dice [np.float32(0.9813), np.float32(0.9916), np.float32(0.9952), np.float32(0.7997)] +2025-10-31 13:56:43.689117: Epoch time: 26.67 s +2025-10-31 13:56:44.935840: +2025-10-31 13:56:44.937819: Epoch 663 +2025-10-31 13:56:44.939799: Current learning rate: 0.00376 +2025-10-31 13:57:11.116548: train_loss -0.9805 +2025-10-31 13:57:11.121520: val_loss -0.8967 +2025-10-31 13:57:11.123711: Pseudo dice [np.float32(0.9847), np.float32(0.9926), np.float32(0.995), np.float32(0.7871)] +2025-10-31 13:57:11.125412: Epoch time: 26.18 s +2025-10-31 13:57:12.351459: +2025-10-31 13:57:12.353610: Epoch 664 +2025-10-31 13:57:12.356160: Current learning rate: 0.00375 +2025-10-31 13:57:39.199725: train_loss -0.9844 +2025-10-31 13:57:39.202603: val_loss -0.8964 +2025-10-31 13:57:39.204298: Pseudo dice [np.float32(0.9848), np.float32(0.9923), np.float32(0.9951), np.float32(0.7832)] +2025-10-31 13:57:39.205845: Epoch time: 26.85 s +2025-10-31 13:57:40.278873: +2025-10-31 13:57:40.281185: Epoch 665 +2025-10-31 13:57:40.282649: Current learning rate: 0.00374 +2025-10-31 13:58:06.120955: train_loss -0.9849 +2025-10-31 13:58:06.123738: val_loss -0.8932 +2025-10-31 13:58:06.125598: Pseudo dice [np.float32(0.985), np.float32(0.9928), np.float32(0.9944), np.float32(0.7811)] +2025-10-31 13:58:06.127398: Epoch time: 25.84 s +2025-10-31 13:58:07.337555: +2025-10-31 13:58:07.340249: Epoch 666 +2025-10-31 13:58:07.342498: Current learning rate: 0.00373 +2025-10-31 13:58:32.166237: train_loss -0.9852 +2025-10-31 13:58:32.168861: val_loss -0.8878 +2025-10-31 13:58:32.171325: Pseudo dice [np.float32(0.9839), np.float32(0.9924), np.float32(0.9948), np.float32(0.7654)] +2025-10-31 13:58:32.173198: Epoch time: 24.83 s +2025-10-31 13:58:33.423905: +2025-10-31 13:58:33.425921: Epoch 667 +2025-10-31 13:58:33.428483: Current learning rate: 0.00372 +2025-10-31 13:59:00.226437: train_loss -0.9867 +2025-10-31 13:59:00.234248: val_loss -0.8944 +2025-10-31 13:59:00.236146: Pseudo dice [np.float32(0.9839), np.float32(0.9928), np.float32(0.9951), np.float32(0.7878)] +2025-10-31 13:59:00.238106: Epoch time: 26.8 s +2025-10-31 13:59:01.541021: +2025-10-31 13:59:01.543656: Epoch 668 +2025-10-31 13:59:01.545983: Current learning rate: 0.00371 +2025-10-31 13:59:29.162579: train_loss -0.9877 +2025-10-31 13:59:29.179865: val_loss -0.8842 +2025-10-31 13:59:29.188867: Pseudo dice [np.float32(0.9818), np.float32(0.9917), np.float32(0.9948), np.float32(0.775)] +2025-10-31 13:59:29.195253: Epoch time: 27.62 s +2025-10-31 13:59:31.225473: +2025-10-31 13:59:31.227242: Epoch 669 +2025-10-31 13:59:31.228838: Current learning rate: 0.0037 +2025-10-31 13:59:58.233588: train_loss -0.9881 +2025-10-31 13:59:58.236881: val_loss -0.8855 +2025-10-31 13:59:58.238672: Pseudo dice [np.float32(0.9845), np.float32(0.9928), np.float32(0.9948), np.float32(0.7677)] +2025-10-31 13:59:58.240498: Epoch time: 27.01 s +2025-10-31 13:59:59.507542: +2025-10-31 13:59:59.510593: Epoch 670 +2025-10-31 13:59:59.512918: Current learning rate: 0.00369 +2025-10-31 14:00:24.966935: train_loss -0.9881 +2025-10-31 14:00:24.969706: val_loss -0.8921 +2025-10-31 14:00:24.971949: Pseudo dice [np.float32(0.9831), np.float32(0.9923), np.float32(0.9952), np.float32(0.7881)] +2025-10-31 14:00:24.973917: Epoch time: 25.46 s +2025-10-31 14:00:26.239037: +2025-10-31 14:00:26.241694: Epoch 671 +2025-10-31 14:00:26.243923: Current learning rate: 0.00368 +2025-10-31 14:00:52.800235: train_loss -0.9884 +2025-10-31 14:00:52.804232: val_loss -0.9038 +2025-10-31 14:00:52.806250: Pseudo dice [np.float32(0.9839), np.float32(0.9925), np.float32(0.9952), np.float32(0.8041)] +2025-10-31 14:00:52.808594: Epoch time: 26.56 s +2025-10-31 14:00:54.091007: +2025-10-31 14:00:54.093493: Epoch 672 +2025-10-31 14:00:54.095671: Current learning rate: 0.00367 +2025-10-31 14:01:21.587567: train_loss -0.9864 +2025-10-31 14:01:21.590819: val_loss -0.9065 +2025-10-31 14:01:21.592753: Pseudo dice [np.float32(0.9822), np.float32(0.992), np.float32(0.9958), np.float32(0.8259)] +2025-10-31 14:01:21.594721: Epoch time: 27.5 s +2025-10-31 14:01:22.818174: +2025-10-31 14:01:22.820244: Epoch 673 +2025-10-31 14:01:22.822900: Current learning rate: 0.00366 +2025-10-31 14:01:48.536207: train_loss -0.9878 +2025-10-31 14:01:48.540000: val_loss -0.8881 +2025-10-31 14:01:48.542586: Pseudo dice [np.float32(0.9835), np.float32(0.9922), np.float32(0.9946), np.float32(0.7706)] +2025-10-31 14:01:48.544885: Epoch time: 25.72 s +2025-10-31 14:01:49.794911: +2025-10-31 14:01:49.796964: Epoch 674 +2025-10-31 14:01:49.798808: Current learning rate: 0.00365 +2025-10-31 14:02:17.327121: train_loss -0.988 +2025-10-31 14:02:17.331114: val_loss -0.8946 +2025-10-31 14:02:17.333135: Pseudo dice [np.float32(0.9832), np.float32(0.9923), np.float32(0.9947), np.float32(0.7873)] +2025-10-31 14:02:17.335158: Epoch time: 27.53 s +2025-10-31 14:02:18.524718: +2025-10-31 14:02:18.526738: Epoch 675 +2025-10-31 14:02:18.528674: Current learning rate: 0.00364 +2025-10-31 14:02:45.814402: train_loss -0.9885 +2025-10-31 14:02:45.821300: val_loss -0.9001 +2025-10-31 14:02:45.823984: Pseudo dice [np.float32(0.9838), np.float32(0.9927), np.float32(0.9953), np.float32(0.7983)] +2025-10-31 14:02:45.826902: Epoch time: 27.29 s +2025-10-31 14:02:47.079951: +2025-10-31 14:02:47.113496: Epoch 676 +2025-10-31 14:02:47.136538: Current learning rate: 0.00363 +2025-10-31 14:03:11.807173: train_loss -0.9895 +2025-10-31 14:03:11.811630: val_loss -0.899 +2025-10-31 14:03:11.814180: Pseudo dice [np.float32(0.9838), np.float32(0.9924), np.float32(0.9954), np.float32(0.81)] +2025-10-31 14:03:11.817451: Epoch time: 24.73 s +2025-10-31 14:03:13.024755: +2025-10-31 14:03:13.031708: Epoch 677 +2025-10-31 14:03:13.033925: Current learning rate: 0.00362 +2025-10-31 14:03:38.335315: train_loss -0.9884 +2025-10-31 14:03:38.339060: val_loss -0.8876 +2025-10-31 14:03:38.342692: Pseudo dice [np.float32(0.9842), np.float32(0.9927), np.float32(0.9949), np.float32(0.7791)] +2025-10-31 14:03:38.345329: Epoch time: 25.31 s +2025-10-31 14:03:39.599837: +2025-10-31 14:03:39.602669: Epoch 678 +2025-10-31 14:03:39.604420: Current learning rate: 0.00361 +2025-10-31 14:04:06.536706: train_loss -0.9893 +2025-10-31 14:04:06.545457: val_loss -0.8838 +2025-10-31 14:04:06.551408: Pseudo dice [np.float32(0.9828), np.float32(0.9924), np.float32(0.9943), np.float32(0.7705)] +2025-10-31 14:04:06.555357: Epoch time: 26.94 s +2025-10-31 14:04:07.801524: +2025-10-31 14:04:07.804202: Epoch 679 +2025-10-31 14:04:07.806651: Current learning rate: 0.0036 +2025-10-31 14:04:33.751794: train_loss -0.9891 +2025-10-31 14:04:33.762939: val_loss -0.8993 +2025-10-31 14:04:33.767991: Pseudo dice [np.float32(0.9829), np.float32(0.9926), np.float32(0.9955), np.float32(0.8079)] +2025-10-31 14:04:33.773257: Epoch time: 25.95 s +2025-10-31 14:04:35.041826: +2025-10-31 14:04:35.050413: Epoch 680 +2025-10-31 14:04:35.059007: Current learning rate: 0.00359 +2025-10-31 14:05:01.967566: train_loss -0.9888 +2025-10-31 14:05:01.984745: val_loss -0.8984 +2025-10-31 14:05:01.986898: Pseudo dice [np.float32(0.9835), np.float32(0.9923), np.float32(0.9957), np.float32(0.8072)] +2025-10-31 14:05:01.997495: Epoch time: 26.93 s +2025-10-31 14:05:03.669079: +2025-10-31 14:05:03.671665: Epoch 681 +2025-10-31 14:05:03.673242: Current learning rate: 0.00358 +2025-10-31 14:05:31.364619: train_loss -0.9901 +2025-10-31 14:05:31.369161: val_loss -0.8943 +2025-10-31 14:05:31.371230: Pseudo dice [np.float32(0.986), np.float32(0.9926), np.float32(0.9951), np.float32(0.7911)] +2025-10-31 14:05:31.373244: Epoch time: 27.7 s +2025-10-31 14:05:32.588814: +2025-10-31 14:05:32.590603: Epoch 682 +2025-10-31 14:05:32.592396: Current learning rate: 0.00357 +2025-10-31 14:05:59.721261: train_loss -0.9905 +2025-10-31 14:05:59.725607: val_loss -0.8902 +2025-10-31 14:05:59.727305: Pseudo dice [np.float32(0.9835), np.float32(0.9929), np.float32(0.9951), np.float32(0.7874)] +2025-10-31 14:05:59.728840: Epoch time: 27.13 s +2025-10-31 14:06:01.068442: +2025-10-31 14:06:01.070750: Epoch 683 +2025-10-31 14:06:01.073393: Current learning rate: 0.00356 +2025-10-31 14:06:26.799356: train_loss -0.9902 +2025-10-31 14:06:26.805898: val_loss -0.8835 +2025-10-31 14:06:26.807693: Pseudo dice [np.float32(0.9838), np.float32(0.9922), np.float32(0.9947), np.float32(0.7742)] +2025-10-31 14:06:26.809501: Epoch time: 25.73 s +2025-10-31 14:06:28.068775: +2025-10-31 14:06:28.071861: Epoch 684 +2025-10-31 14:06:28.074400: Current learning rate: 0.00355 +2025-10-31 14:06:52.868092: train_loss -0.9898 +2025-10-31 14:06:52.882277: val_loss -0.8877 +2025-10-31 14:06:52.888709: Pseudo dice [np.float32(0.9839), np.float32(0.9924), np.float32(0.9947), np.float32(0.78)] +2025-10-31 14:06:52.892183: Epoch time: 24.8 s +2025-10-31 14:06:53.790657: +2025-10-31 14:06:53.796208: Epoch 685 +2025-10-31 14:06:53.798358: Current learning rate: 0.00354 +2025-10-31 14:07:14.676418: train_loss -0.9907 +2025-10-31 14:07:14.687039: val_loss -0.8921 +2025-10-31 14:07:14.695871: Pseudo dice [np.float32(0.9842), np.float32(0.9929), np.float32(0.9951), np.float32(0.7945)] +2025-10-31 14:07:14.703672: Epoch time: 20.89 s +2025-10-31 14:07:15.939642: +2025-10-31 14:07:15.942492: Epoch 686 +2025-10-31 14:07:15.958596: Current learning rate: 0.00353 +2025-10-31 14:07:34.823655: train_loss -0.9899 +2025-10-31 14:07:34.830282: val_loss -0.8993 +2025-10-31 14:07:34.833326: Pseudo dice [np.float32(0.9851), np.float32(0.9934), np.float32(0.9958), np.float32(0.8115)] +2025-10-31 14:07:34.835187: Epoch time: 18.89 s +2025-10-31 14:07:35.994562: +2025-10-31 14:07:35.996758: Epoch 687 +2025-10-31 14:07:35.998617: Current learning rate: 0.00352 +2025-10-31 14:08:02.261364: train_loss -0.9897 +2025-10-31 14:08:02.263978: val_loss -0.8975 +2025-10-31 14:08:02.265594: Pseudo dice [np.float32(0.9845), np.float32(0.9928), np.float32(0.9956), np.float32(0.8028)] +2025-10-31 14:08:02.267258: Epoch time: 26.27 s +2025-10-31 14:08:03.481579: +2025-10-31 14:08:03.484077: Epoch 688 +2025-10-31 14:08:03.486251: Current learning rate: 0.00351 +2025-10-31 14:08:28.140037: train_loss -0.9908 +2025-10-31 14:08:28.143983: val_loss -0.8962 +2025-10-31 14:08:28.146112: Pseudo dice [np.float32(0.983), np.float32(0.9925), np.float32(0.9951), np.float32(0.8026)] +2025-10-31 14:08:28.148420: Epoch time: 24.66 s +2025-10-31 14:08:29.446855: +2025-10-31 14:08:29.449552: Epoch 689 +2025-10-31 14:08:29.451568: Current learning rate: 0.0035 +2025-10-31 14:08:56.646073: train_loss -0.9902 +2025-10-31 14:08:56.649145: val_loss -0.8903 +2025-10-31 14:08:56.651579: Pseudo dice [np.float32(0.982), np.float32(0.9917), np.float32(0.9951), np.float32(0.798)] +2025-10-31 14:08:56.653387: Epoch time: 27.2 s +2025-10-31 14:08:57.856968: +2025-10-31 14:08:57.858817: Epoch 690 +2025-10-31 14:08:57.860437: Current learning rate: 0.00349 +2025-10-31 14:09:24.606000: train_loss -0.9899 +2025-10-31 14:09:24.612916: val_loss -0.8861 +2025-10-31 14:09:24.615719: Pseudo dice [np.float32(0.9832), np.float32(0.9918), np.float32(0.9949), np.float32(0.7818)] +2025-10-31 14:09:24.617139: Epoch time: 26.75 s +2025-10-31 14:09:25.840158: +2025-10-31 14:09:25.842179: Epoch 691 +2025-10-31 14:09:25.844064: Current learning rate: 0.00348 +2025-10-31 14:09:49.075229: train_loss -0.9904 +2025-10-31 14:09:49.077860: val_loss -0.8823 +2025-10-31 14:09:49.080900: Pseudo dice [np.float32(0.9831), np.float32(0.9921), np.float32(0.9944), np.float32(0.7724)] +2025-10-31 14:09:49.083664: Epoch time: 23.24 s +2025-10-31 14:09:50.288774: +2025-10-31 14:09:50.290783: Epoch 692 +2025-10-31 14:09:50.292585: Current learning rate: 0.00346 +2025-10-31 14:10:16.614282: train_loss -0.9908 +2025-10-31 14:10:16.620716: val_loss -0.8862 +2025-10-31 14:10:16.622897: Pseudo dice [np.float32(0.9834), np.float32(0.9919), np.float32(0.9948), np.float32(0.783)] +2025-10-31 14:10:16.624597: Epoch time: 26.33 s +2025-10-31 14:10:17.938663: +2025-10-31 14:10:17.940927: Epoch 693 +2025-10-31 14:10:17.943624: Current learning rate: 0.00345 +2025-10-31 14:10:43.375579: train_loss -0.9907 +2025-10-31 14:10:43.379992: val_loss -0.8886 +2025-10-31 14:10:43.381922: Pseudo dice [np.float32(0.9852), np.float32(0.9922), np.float32(0.9952), np.float32(0.7849)] +2025-10-31 14:10:43.383685: Epoch time: 25.44 s +2025-10-31 14:10:45.147343: +2025-10-31 14:10:45.149266: Epoch 694 +2025-10-31 14:10:45.153040: Current learning rate: 0.00344 +2025-10-31 14:11:10.933911: train_loss -0.9913 +2025-10-31 14:11:10.936590: val_loss -0.88 +2025-10-31 14:11:10.938304: Pseudo dice [np.float32(0.9847), np.float32(0.9928), np.float32(0.9949), np.float32(0.7618)] +2025-10-31 14:11:10.939788: Epoch time: 25.79 s +2025-10-31 14:11:12.162942: +2025-10-31 14:11:12.165239: Epoch 695 +2025-10-31 14:11:12.167536: Current learning rate: 0.00343 +2025-10-31 14:11:38.607235: train_loss -0.9908 +2025-10-31 14:11:38.610569: val_loss -0.8871 +2025-10-31 14:11:38.612748: Pseudo dice [np.float32(0.9833), np.float32(0.9921), np.float32(0.9951), np.float32(0.7851)] +2025-10-31 14:11:38.614867: Epoch time: 26.45 s +2025-10-31 14:11:39.876013: +2025-10-31 14:11:39.878052: Epoch 696 +2025-10-31 14:11:39.879893: Current learning rate: 0.00342 +2025-10-31 14:12:05.281699: train_loss -0.9907 +2025-10-31 14:12:05.289109: val_loss -0.8897 +2025-10-31 14:12:05.293754: Pseudo dice [np.float32(0.9837), np.float32(0.992), np.float32(0.9949), np.float32(0.7906)] +2025-10-31 14:12:05.296674: Epoch time: 25.41 s +2025-10-31 14:12:06.474903: +2025-10-31 14:12:06.477150: Epoch 697 +2025-10-31 14:12:06.479345: Current learning rate: 0.00341 +2025-10-31 14:12:33.659530: train_loss -0.9908 +2025-10-31 14:12:33.662342: val_loss -0.8896 +2025-10-31 14:12:33.664294: Pseudo dice [np.float32(0.9832), np.float32(0.9925), np.float32(0.9951), np.float32(0.7885)] +2025-10-31 14:12:33.666953: Epoch time: 27.19 s +2025-10-31 14:12:34.957872: +2025-10-31 14:12:34.959889: Epoch 698 +2025-10-31 14:12:34.961855: Current learning rate: 0.0034 +2025-10-31 14:12:59.495442: train_loss -0.9905 +2025-10-31 14:12:59.498427: val_loss -0.8933 +2025-10-31 14:12:59.500152: Pseudo dice [np.float32(0.9835), np.float32(0.9923), np.float32(0.9951), np.float32(0.7953)] +2025-10-31 14:12:59.501945: Epoch time: 24.54 s +2025-10-31 14:13:00.587601: +2025-10-31 14:13:00.590428: Epoch 699 +2025-10-31 14:13:00.593039: Current learning rate: 0.00339 +2025-10-31 14:13:24.348539: train_loss -0.9914 +2025-10-31 14:13:24.351853: val_loss -0.8821 +2025-10-31 14:13:24.354114: Pseudo dice [np.float32(0.985), np.float32(0.9924), np.float32(0.9948), np.float32(0.7617)] +2025-10-31 14:13:24.356233: Epoch time: 23.76 s +2025-10-31 14:13:26.977716: +2025-10-31 14:13:26.985067: Epoch 700 +2025-10-31 14:13:26.995136: Current learning rate: 0.00338 +2025-10-31 14:13:51.989307: train_loss -0.9908 +2025-10-31 14:13:51.992242: val_loss -0.8825 +2025-10-31 14:13:51.993924: Pseudo dice [np.float32(0.9834), np.float32(0.9928), np.float32(0.9948), np.float32(0.7716)] +2025-10-31 14:13:51.995548: Epoch time: 25.01 s +2025-10-31 14:13:53.176842: +2025-10-31 14:13:53.178995: Epoch 701 +2025-10-31 14:13:53.181335: Current learning rate: 0.00337 +2025-10-31 14:14:18.154135: train_loss -0.9907 +2025-10-31 14:14:18.157641: val_loss -0.8842 +2025-10-31 14:14:18.160026: Pseudo dice [np.float32(0.9842), np.float32(0.9928), np.float32(0.9948), np.float32(0.7743)] +2025-10-31 14:14:18.162191: Epoch time: 24.98 s +2025-10-31 14:14:19.396502: +2025-10-31 14:14:19.399724: Epoch 702 +2025-10-31 14:14:19.402047: Current learning rate: 0.00336 +2025-10-31 14:14:44.996411: train_loss -0.9912 +2025-10-31 14:14:45.001601: val_loss -0.8892 +2025-10-31 14:14:45.003737: Pseudo dice [np.float32(0.984), np.float32(0.9925), np.float32(0.9952), np.float32(0.787)] +2025-10-31 14:14:45.006840: Epoch time: 25.6 s +2025-10-31 14:14:46.249154: +2025-10-31 14:14:46.252015: Epoch 703 +2025-10-31 14:14:46.254467: Current learning rate: 0.00335 +2025-10-31 14:15:12.320054: train_loss -0.9918 +2025-10-31 14:15:12.322783: val_loss -0.8885 +2025-10-31 14:15:12.325487: Pseudo dice [np.float32(0.9834), np.float32(0.9924), np.float32(0.9955), np.float32(0.789)] +2025-10-31 14:15:12.327467: Epoch time: 26.07 s +2025-10-31 14:15:13.568923: +2025-10-31 14:15:13.571213: Epoch 704 +2025-10-31 14:15:13.572671: Current learning rate: 0.00334 +2025-10-31 14:15:38.769445: train_loss -0.9916 +2025-10-31 14:15:38.772355: val_loss -0.8966 +2025-10-31 14:15:38.774408: Pseudo dice [np.float32(0.9851), np.float32(0.9931), np.float32(0.9955), np.float32(0.8059)] +2025-10-31 14:15:38.776797: Epoch time: 25.2 s +2025-10-31 14:15:40.152323: +2025-10-31 14:15:40.154768: Epoch 705 +2025-10-31 14:15:40.157052: Current learning rate: 0.00333 +2025-10-31 14:16:03.913274: train_loss -0.9918 +2025-10-31 14:16:03.930088: val_loss -0.8848 +2025-10-31 14:16:03.934041: Pseudo dice [np.float32(0.9836), np.float32(0.9921), np.float32(0.9948), np.float32(0.7733)] +2025-10-31 14:16:03.935869: Epoch time: 23.76 s +2025-10-31 14:16:06.019935: +2025-10-31 14:16:06.024909: Epoch 706 +2025-10-31 14:16:06.027379: Current learning rate: 0.00332 +2025-10-31 14:16:30.482193: train_loss -0.9908 +2025-10-31 14:16:30.484921: val_loss -0.8803 +2025-10-31 14:16:30.486800: Pseudo dice [np.float32(0.9837), np.float32(0.9924), np.float32(0.9948), np.float32(0.7692)] +2025-10-31 14:16:30.488560: Epoch time: 24.46 s +2025-10-31 14:16:31.629778: +2025-10-31 14:16:31.631953: Epoch 707 +2025-10-31 14:16:31.634551: Current learning rate: 0.00331 +2025-10-31 14:16:56.879315: train_loss -0.9915 +2025-10-31 14:16:56.883120: val_loss -0.8943 +2025-10-31 14:16:56.885288: Pseudo dice [np.float32(0.9852), np.float32(0.993), np.float32(0.9955), np.float32(0.7942)] +2025-10-31 14:16:56.887176: Epoch time: 25.25 s +2025-10-31 14:16:58.136742: +2025-10-31 14:16:58.139079: Epoch 708 +2025-10-31 14:16:58.141027: Current learning rate: 0.0033 +2025-10-31 14:17:23.406188: train_loss -0.9915 +2025-10-31 14:17:23.409920: val_loss -0.8852 +2025-10-31 14:17:23.412368: Pseudo dice [np.float32(0.9847), np.float32(0.9925), np.float32(0.9945), np.float32(0.7787)] +2025-10-31 14:17:23.414663: Epoch time: 25.27 s +2025-10-31 14:17:24.731918: +2025-10-31 14:17:24.736569: Epoch 709 +2025-10-31 14:17:24.739027: Current learning rate: 0.00329 +2025-10-31 14:17:50.351846: train_loss -0.9909 +2025-10-31 14:17:50.356294: val_loss -0.8871 +2025-10-31 14:17:50.358494: Pseudo dice [np.float32(0.9851), np.float32(0.9927), np.float32(0.995), np.float32(0.7757)] +2025-10-31 14:17:50.360289: Epoch time: 25.62 s +2025-10-31 14:17:51.561500: +2025-10-31 14:17:51.563565: Epoch 710 +2025-10-31 14:17:51.565345: Current learning rate: 0.00328 +2025-10-31 14:18:16.857734: train_loss -0.9916 +2025-10-31 14:18:16.860571: val_loss -0.889 +2025-10-31 14:18:16.862310: Pseudo dice [np.float32(0.9844), np.float32(0.9927), np.float32(0.995), np.float32(0.7812)] +2025-10-31 14:18:16.864165: Epoch time: 25.3 s +2025-10-31 14:18:18.047950: +2025-10-31 14:18:18.050060: Epoch 711 +2025-10-31 14:18:18.051878: Current learning rate: 0.00327 +2025-10-31 14:18:43.554970: train_loss -0.9913 +2025-10-31 14:18:43.559042: val_loss -0.892 +2025-10-31 14:18:43.560977: Pseudo dice [np.float32(0.9841), np.float32(0.9925), np.float32(0.995), np.float32(0.787)] +2025-10-31 14:18:43.563310: Epoch time: 25.51 s +2025-10-31 14:18:44.808974: +2025-10-31 14:18:44.811466: Epoch 712 +2025-10-31 14:18:44.813646: Current learning rate: 0.00326 +2025-10-31 14:19:07.629205: train_loss -0.9912 +2025-10-31 14:19:07.633815: val_loss -0.8808 +2025-10-31 14:19:07.635879: Pseudo dice [np.float32(0.9841), np.float32(0.9922), np.float32(0.9945), np.float32(0.7665)] +2025-10-31 14:19:07.637776: Epoch time: 22.82 s +2025-10-31 14:19:08.903328: +2025-10-31 14:19:08.905961: Epoch 713 +2025-10-31 14:19:08.908277: Current learning rate: 0.00325 +2025-10-31 14:19:34.893631: train_loss -0.9911 +2025-10-31 14:19:34.896523: val_loss -0.8896 +2025-10-31 14:19:34.898266: Pseudo dice [np.float32(0.9843), np.float32(0.9925), np.float32(0.9952), np.float32(0.7926)] +2025-10-31 14:19:34.900069: Epoch time: 25.99 s +2025-10-31 14:19:36.173341: +2025-10-31 14:19:36.175776: Epoch 714 +2025-10-31 14:19:36.178139: Current learning rate: 0.00324 +2025-10-31 14:20:03.290298: train_loss -0.9915 +2025-10-31 14:20:03.297422: val_loss -0.8815 +2025-10-31 14:20:03.300037: Pseudo dice [np.float32(0.9832), np.float32(0.9924), np.float32(0.9952), np.float32(0.7713)] +2025-10-31 14:20:03.302890: Epoch time: 27.12 s +2025-10-31 14:20:04.551512: +2025-10-31 14:20:04.556925: Epoch 715 +2025-10-31 14:20:04.559823: Current learning rate: 0.00323 +2025-10-31 14:20:28.413740: train_loss -0.9904 +2025-10-31 14:20:28.417585: val_loss -0.8831 +2025-10-31 14:20:28.420212: Pseudo dice [np.float32(0.9843), np.float32(0.9927), np.float32(0.9948), np.float32(0.7715)] +2025-10-31 14:20:28.422811: Epoch time: 23.86 s +2025-10-31 14:20:29.682960: +2025-10-31 14:20:29.685885: Epoch 716 +2025-10-31 14:20:29.687869: Current learning rate: 0.00322 +2025-10-31 14:20:54.516865: train_loss -0.9909 +2025-10-31 14:20:54.524952: val_loss -0.8866 +2025-10-31 14:20:54.526688: Pseudo dice [np.float32(0.9835), np.float32(0.9925), np.float32(0.9951), np.float32(0.7749)] +2025-10-31 14:20:54.528576: Epoch time: 24.84 s +2025-10-31 14:20:55.767684: +2025-10-31 14:20:55.776288: Epoch 717 +2025-10-31 14:20:55.782592: Current learning rate: 0.00321 +2025-10-31 14:21:20.363094: train_loss -0.991 +2025-10-31 14:21:20.365950: val_loss -0.8884 +2025-10-31 14:21:20.367624: Pseudo dice [np.float32(0.9838), np.float32(0.9927), np.float32(0.9952), np.float32(0.7851)] +2025-10-31 14:21:20.369689: Epoch time: 24.6 s +2025-10-31 14:21:22.273048: +2025-10-31 14:21:22.275556: Epoch 718 +2025-10-31 14:21:22.277894: Current learning rate: 0.0032 +2025-10-31 14:21:48.413147: train_loss -0.9916 +2025-10-31 14:21:48.417043: val_loss -0.8799 +2025-10-31 14:21:48.419774: Pseudo dice [np.float32(0.9822), np.float32(0.9921), np.float32(0.9948), np.float32(0.7699)] +2025-10-31 14:21:48.422317: Epoch time: 26.14 s +2025-10-31 14:21:49.700472: +2025-10-31 14:21:49.702683: Epoch 719 +2025-10-31 14:21:49.704678: Current learning rate: 0.00319 +2025-10-31 14:22:10.033403: train_loss -0.9915 +2025-10-31 14:22:10.037011: val_loss -0.8858 +2025-10-31 14:22:10.038919: Pseudo dice [np.float32(0.982), np.float32(0.9915), np.float32(0.9948), np.float32(0.7824)] +2025-10-31 14:22:10.040909: Epoch time: 20.33 s +2025-10-31 14:22:11.319857: +2025-10-31 14:22:11.321707: Epoch 720 +2025-10-31 14:22:11.323563: Current learning rate: 0.00318 +2025-10-31 14:22:35.315302: train_loss -0.9914 +2025-10-31 14:22:35.318584: val_loss -0.8816 +2025-10-31 14:22:35.321833: Pseudo dice [np.float32(0.9835), np.float32(0.9926), np.float32(0.9948), np.float32(0.7729)] +2025-10-31 14:22:35.325136: Epoch time: 24.0 s +2025-10-31 14:22:36.537242: +2025-10-31 14:22:36.539492: Epoch 721 +2025-10-31 14:22:36.541435: Current learning rate: 0.00317 +2025-10-31 14:23:00.809588: train_loss -0.991 +2025-10-31 14:23:00.812615: val_loss -0.8957 +2025-10-31 14:23:00.814850: Pseudo dice [np.float32(0.9852), np.float32(0.9928), np.float32(0.9957), np.float32(0.7952)] +2025-10-31 14:23:00.817245: Epoch time: 24.27 s +2025-10-31 14:23:02.037284: +2025-10-31 14:23:02.041408: Epoch 722 +2025-10-31 14:23:02.043856: Current learning rate: 0.00316 +2025-10-31 14:23:27.536641: train_loss -0.9916 +2025-10-31 14:23:27.540694: val_loss -0.8894 +2025-10-31 14:23:27.543507: Pseudo dice [np.float32(0.9827), np.float32(0.9921), np.float32(0.9953), np.float32(0.7963)] +2025-10-31 14:23:27.545839: Epoch time: 25.5 s +2025-10-31 14:23:28.780811: +2025-10-31 14:23:28.782899: Epoch 723 +2025-10-31 14:23:28.784655: Current learning rate: 0.00315 +2025-10-31 14:23:53.954180: train_loss -0.9917 +2025-10-31 14:23:53.956765: val_loss -0.8926 +2025-10-31 14:23:53.958384: Pseudo dice [np.float32(0.9835), np.float32(0.9923), np.float32(0.9954), np.float32(0.7987)] +2025-10-31 14:23:53.960091: Epoch time: 25.18 s +2025-10-31 14:23:55.174218: +2025-10-31 14:23:55.176138: Epoch 724 +2025-10-31 14:23:55.177926: Current learning rate: 0.00314 +2025-10-31 14:24:18.686107: train_loss -0.9919 +2025-10-31 14:24:18.688575: val_loss -0.8872 +2025-10-31 14:24:18.690214: Pseudo dice [np.float32(0.9827), np.float32(0.9918), np.float32(0.9952), np.float32(0.7904)] +2025-10-31 14:24:18.692347: Epoch time: 23.51 s +2025-10-31 14:24:19.976628: +2025-10-31 14:24:19.979446: Epoch 725 +2025-10-31 14:24:19.980895: Current learning rate: 0.00313 +2025-10-31 14:24:44.998105: train_loss -0.9912 +2025-10-31 14:24:45.014986: val_loss -0.887 +2025-10-31 14:24:45.028406: Pseudo dice [np.float32(0.9823), np.float32(0.9913), np.float32(0.9949), np.float32(0.7928)] +2025-10-31 14:24:45.036529: Epoch time: 25.03 s +2025-10-31 14:24:46.266810: +2025-10-31 14:24:46.271192: Epoch 726 +2025-10-31 14:24:46.274692: Current learning rate: 0.00312 +2025-10-31 14:25:08.710319: train_loss -0.992 +2025-10-31 14:25:08.714077: val_loss -0.8959 +2025-10-31 14:25:08.716034: Pseudo dice [np.float32(0.9861), np.float32(0.9927), np.float32(0.9953), np.float32(0.8026)] +2025-10-31 14:25:08.718006: Epoch time: 22.45 s +2025-10-31 14:25:09.880483: +2025-10-31 14:25:09.882902: Epoch 727 +2025-10-31 14:25:09.884911: Current learning rate: 0.00311 +2025-10-31 14:25:33.560598: train_loss -0.9921 +2025-10-31 14:25:33.576314: val_loss -0.8868 +2025-10-31 14:25:33.578246: Pseudo dice [np.float32(0.9841), np.float32(0.9924), np.float32(0.9953), np.float32(0.7876)] +2025-10-31 14:25:33.580131: Epoch time: 23.68 s +2025-10-31 14:25:34.819709: +2025-10-31 14:25:34.821874: Epoch 728 +2025-10-31 14:25:34.823721: Current learning rate: 0.0031 +2025-10-31 14:26:00.297146: train_loss -0.9917 +2025-10-31 14:26:00.302933: val_loss -0.8888 +2025-10-31 14:26:00.306234: Pseudo dice [np.float32(0.9837), np.float32(0.9922), np.float32(0.9952), np.float32(0.7905)] +2025-10-31 14:26:00.309020: Epoch time: 25.48 s +2025-10-31 14:26:01.373060: +2025-10-31 14:26:01.375091: Epoch 729 +2025-10-31 14:26:01.377144: Current learning rate: 0.00309 +2025-10-31 14:26:26.282725: train_loss -0.9915 +2025-10-31 14:26:26.285390: val_loss -0.8914 +2025-10-31 14:26:26.287023: Pseudo dice [np.float32(0.9831), np.float32(0.9926), np.float32(0.9952), np.float32(0.7946)] +2025-10-31 14:26:26.288572: Epoch time: 24.91 s +2025-10-31 14:26:27.531659: +2025-10-31 14:26:27.533962: Epoch 730 +2025-10-31 14:26:27.535795: Current learning rate: 0.00308 +2025-10-31 14:26:52.944467: train_loss -0.9924 +2025-10-31 14:26:52.947556: val_loss -0.8793 +2025-10-31 14:26:52.949368: Pseudo dice [np.float32(0.9818), np.float32(0.9913), np.float32(0.9947), np.float32(0.7654)] +2025-10-31 14:26:52.950988: Epoch time: 25.41 s +2025-10-31 14:26:54.241659: +2025-10-31 14:26:54.243398: Epoch 731 +2025-10-31 14:26:54.244916: Current learning rate: 0.00307 +2025-10-31 14:27:18.643549: train_loss -0.9917 +2025-10-31 14:27:18.646392: val_loss -0.8846 +2025-10-31 14:27:18.648226: Pseudo dice [np.float32(0.9842), np.float32(0.9923), np.float32(0.9951), np.float32(0.7747)] +2025-10-31 14:27:18.649970: Epoch time: 24.4 s +2025-10-31 14:27:19.759046: +2025-10-31 14:27:19.761433: Epoch 732 +2025-10-31 14:27:19.763871: Current learning rate: 0.00306 +2025-10-31 14:27:45.463860: train_loss -0.9914 +2025-10-31 14:27:45.466879: val_loss -0.8893 +2025-10-31 14:27:45.469019: Pseudo dice [np.float32(0.984), np.float32(0.9928), np.float32(0.9954), np.float32(0.7855)] +2025-10-31 14:27:45.471342: Epoch time: 25.71 s +2025-10-31 14:27:46.525146: +2025-10-31 14:27:46.527026: Epoch 733 +2025-10-31 14:27:46.529144: Current learning rate: 0.00305 +2025-10-31 14:28:11.395076: train_loss -0.9914 +2025-10-31 14:28:11.398501: val_loss -0.8855 +2025-10-31 14:28:11.400182: Pseudo dice [np.float32(0.9834), np.float32(0.9921), np.float32(0.9951), np.float32(0.7816)] +2025-10-31 14:28:11.401955: Epoch time: 24.87 s +2025-10-31 14:28:12.453295: +2025-10-31 14:28:12.455102: Epoch 734 +2025-10-31 14:28:12.457765: Current learning rate: 0.00304 +2025-10-31 14:28:35.900795: train_loss -0.9917 +2025-10-31 14:28:35.904164: val_loss -0.8816 +2025-10-31 14:28:35.906204: Pseudo dice [np.float32(0.9835), np.float32(0.9925), np.float32(0.9949), np.float32(0.7731)] +2025-10-31 14:28:35.908427: Epoch time: 23.45 s +2025-10-31 14:28:37.434668: +2025-10-31 14:28:37.437280: Epoch 735 +2025-10-31 14:28:37.439355: Current learning rate: 0.00303 +2025-10-31 14:29:02.219523: train_loss -0.9918 +2025-10-31 14:29:02.223392: val_loss -0.8813 +2025-10-31 14:29:02.225072: Pseudo dice [np.float32(0.9835), np.float32(0.9918), np.float32(0.9949), np.float32(0.7751)] +2025-10-31 14:29:02.226679: Epoch time: 24.79 s +2025-10-31 14:29:03.428444: +2025-10-31 14:29:03.430543: Epoch 736 +2025-10-31 14:29:03.432969: Current learning rate: 0.00302 +2025-10-31 14:29:29.630354: train_loss -0.9924 +2025-10-31 14:29:29.635456: val_loss -0.8925 +2025-10-31 14:29:29.638077: Pseudo dice [np.float32(0.9856), np.float32(0.9929), np.float32(0.9953), np.float32(0.7923)] +2025-10-31 14:29:29.639766: Epoch time: 26.2 s +2025-10-31 14:29:30.884032: +2025-10-31 14:29:30.886046: Epoch 737 +2025-10-31 14:29:30.888469: Current learning rate: 0.00301 +2025-10-31 14:29:55.475915: train_loss -0.9931 +2025-10-31 14:29:55.478236: val_loss -0.8873 +2025-10-31 14:29:55.479859: Pseudo dice [np.float32(0.9846), np.float32(0.9924), np.float32(0.9952), np.float32(0.7874)] +2025-10-31 14:29:55.481599: Epoch time: 24.59 s +2025-10-31 14:29:56.676034: +2025-10-31 14:29:56.677763: Epoch 738 +2025-10-31 14:29:56.680089: Current learning rate: 0.003 +2025-10-31 14:30:22.674183: train_loss -0.9922 +2025-10-31 14:30:22.678851: val_loss -0.8843 +2025-10-31 14:30:22.681316: Pseudo dice [np.float32(0.9828), np.float32(0.9918), np.float32(0.9949), np.float32(0.7795)] +2025-10-31 14:30:22.683232: Epoch time: 26.0 s +2025-10-31 14:30:23.909370: +2025-10-31 14:30:23.911330: Epoch 739 +2025-10-31 14:30:23.913081: Current learning rate: 0.00299 +2025-10-31 14:30:47.253924: train_loss -0.9918 +2025-10-31 14:30:47.256702: val_loss -0.8939 +2025-10-31 14:30:47.259429: Pseudo dice [np.float32(0.9849), np.float32(0.9933), np.float32(0.9953), np.float32(0.7911)] +2025-10-31 14:30:47.262898: Epoch time: 23.35 s +2025-10-31 14:30:48.549526: +2025-10-31 14:30:48.551461: Epoch 740 +2025-10-31 14:30:48.552837: Current learning rate: 0.00297 +2025-10-31 14:31:13.170686: train_loss -0.9919 +2025-10-31 14:31:13.173918: val_loss -0.8929 +2025-10-31 14:31:13.177481: Pseudo dice [np.float32(0.9846), np.float32(0.9926), np.float32(0.9952), np.float32(0.7973)] +2025-10-31 14:31:13.180081: Epoch time: 24.62 s +2025-10-31 14:31:14.264783: +2025-10-31 14:31:14.266939: Epoch 741 +2025-10-31 14:31:14.268750: Current learning rate: 0.00296 +2025-10-31 14:31:40.382459: train_loss -0.9922 +2025-10-31 14:31:40.388798: val_loss -0.8938 +2025-10-31 14:31:40.390459: Pseudo dice [np.float32(0.9854), np.float32(0.9931), np.float32(0.9954), np.float32(0.7961)] +2025-10-31 14:31:40.392472: Epoch time: 26.12 s +2025-10-31 14:31:41.611508: +2025-10-31 14:31:41.613909: Epoch 742 +2025-10-31 14:31:41.615983: Current learning rate: 0.00295 +2025-10-31 14:32:05.711819: train_loss -0.9923 +2025-10-31 14:32:05.714605: val_loss -0.8908 +2025-10-31 14:32:05.716561: Pseudo dice [np.float32(0.9833), np.float32(0.9922), np.float32(0.9953), np.float32(0.7948)] +2025-10-31 14:32:05.718601: Epoch time: 24.1 s +2025-10-31 14:32:06.983822: +2025-10-31 14:32:06.986353: Epoch 743 +2025-10-31 14:32:06.988608: Current learning rate: 0.00294 +2025-10-31 14:32:32.418377: train_loss -0.9926 +2025-10-31 14:32:32.428141: val_loss -0.8787 +2025-10-31 14:32:32.430858: Pseudo dice [np.float32(0.9839), np.float32(0.9926), np.float32(0.9948), np.float32(0.7643)] +2025-10-31 14:32:32.446606: Epoch time: 25.44 s +2025-10-31 14:32:33.737789: +2025-10-31 14:32:33.741060: Epoch 744 +2025-10-31 14:32:33.743200: Current learning rate: 0.00293 +2025-10-31 14:32:59.834193: train_loss -0.9926 +2025-10-31 14:32:59.837950: val_loss -0.8889 +2025-10-31 14:32:59.840698: Pseudo dice [np.float32(0.9835), np.float32(0.9931), np.float32(0.9954), np.float32(0.7882)] +2025-10-31 14:32:59.844101: Epoch time: 26.1 s +2025-10-31 14:33:01.162405: +2025-10-31 14:33:01.164823: Epoch 745 +2025-10-31 14:33:01.167183: Current learning rate: 0.00292 +2025-10-31 14:33:28.680163: train_loss -0.9923 +2025-10-31 14:33:28.683396: val_loss -0.8915 +2025-10-31 14:33:28.685153: Pseudo dice [np.float32(0.9843), np.float32(0.9922), np.float32(0.9953), np.float32(0.7992)] +2025-10-31 14:33:28.687149: Epoch time: 27.52 s +2025-10-31 14:33:29.907338: +2025-10-31 14:33:29.911025: Epoch 746 +2025-10-31 14:33:29.913819: Current learning rate: 0.00291 +2025-10-31 14:33:55.402230: train_loss -0.9918 +2025-10-31 14:33:55.409258: val_loss -0.885 +2025-10-31 14:33:55.411851: Pseudo dice [np.float32(0.9833), np.float32(0.9923), np.float32(0.9946), np.float32(0.7817)] +2025-10-31 14:33:55.413623: Epoch time: 25.5 s +2025-10-31 14:33:56.648586: +2025-10-31 14:33:56.650462: Epoch 747 +2025-10-31 14:33:56.652048: Current learning rate: 0.0029 +2025-10-31 14:34:22.164290: train_loss -0.9921 +2025-10-31 14:34:22.167142: val_loss -0.8837 +2025-10-31 14:34:22.170280: Pseudo dice [np.float32(0.9847), np.float32(0.9926), np.float32(0.9951), np.float32(0.7824)] +2025-10-31 14:34:22.173610: Epoch time: 25.52 s +2025-10-31 14:34:23.456409: +2025-10-31 14:34:23.458357: Epoch 748 +2025-10-31 14:34:23.460085: Current learning rate: 0.00289 +2025-10-31 14:34:48.756776: train_loss -0.9922 +2025-10-31 14:34:48.758904: val_loss -0.8899 +2025-10-31 14:34:48.761552: Pseudo dice [np.float32(0.9844), np.float32(0.9922), np.float32(0.9951), np.float32(0.7932)] +2025-10-31 14:34:48.763864: Epoch time: 25.3 s +2025-10-31 14:34:49.780120: +2025-10-31 14:34:49.782151: Epoch 749 +2025-10-31 14:34:49.784723: Current learning rate: 0.00288 +2025-10-31 14:35:15.677532: train_loss -0.9923 +2025-10-31 14:35:15.682086: val_loss -0.8892 +2025-10-31 14:35:15.684427: Pseudo dice [np.float32(0.9835), np.float32(0.9916), np.float32(0.995), np.float32(0.7925)] +2025-10-31 14:35:15.686488: Epoch time: 25.9 s +2025-10-31 14:35:18.322788: +2025-10-31 14:35:18.325681: Epoch 750 +2025-10-31 14:35:18.332656: Current learning rate: 0.00287 +2025-10-31 14:35:44.338107: train_loss -0.9924 +2025-10-31 14:35:44.344063: val_loss -0.8854 +2025-10-31 14:35:44.346059: Pseudo dice [np.float32(0.9852), np.float32(0.9931), np.float32(0.995), np.float32(0.7781)] +2025-10-31 14:35:44.347908: Epoch time: 26.02 s +2025-10-31 14:35:45.547500: +2025-10-31 14:35:45.549436: Epoch 751 +2025-10-31 14:35:45.553033: Current learning rate: 0.00286 +2025-10-31 14:36:12.315742: train_loss -0.9923 +2025-10-31 14:36:12.321035: val_loss -0.8857 +2025-10-31 14:36:12.325334: Pseudo dice [np.float32(0.9848), np.float32(0.9925), np.float32(0.9947), np.float32(0.7787)] +2025-10-31 14:36:12.328574: Epoch time: 26.77 s +2025-10-31 14:36:13.568660: +2025-10-31 14:36:13.572009: Epoch 752 +2025-10-31 14:36:13.574639: Current learning rate: 0.00285 +2025-10-31 14:36:38.693495: train_loss -0.9925 +2025-10-31 14:36:38.697156: val_loss -0.8865 +2025-10-31 14:36:38.701983: Pseudo dice [np.float32(0.9834), np.float32(0.9927), np.float32(0.9951), np.float32(0.7783)] +2025-10-31 14:36:38.705180: Epoch time: 25.13 s +2025-10-31 14:36:40.342110: +2025-10-31 14:36:40.344204: Epoch 753 +2025-10-31 14:36:40.346178: Current learning rate: 0.00284 +2025-10-31 14:37:06.276693: train_loss -0.9921 +2025-10-31 14:37:06.280486: val_loss -0.8897 +2025-10-31 14:37:06.282346: Pseudo dice [np.float32(0.985), np.float32(0.9923), np.float32(0.995), np.float32(0.7885)] +2025-10-31 14:37:06.284291: Epoch time: 25.94 s +2025-10-31 14:37:07.304117: +2025-10-31 14:37:07.307147: Epoch 754 +2025-10-31 14:37:07.309826: Current learning rate: 0.00283 +2025-10-31 14:37:31.687645: train_loss -0.9924 +2025-10-31 14:37:31.690131: val_loss -0.8876 +2025-10-31 14:37:31.691958: Pseudo dice [np.float32(0.9838), np.float32(0.9918), np.float32(0.9947), np.float32(0.7806)] +2025-10-31 14:37:31.693653: Epoch time: 24.38 s +2025-10-31 14:37:32.749155: +2025-10-31 14:37:32.757310: Epoch 755 +2025-10-31 14:37:32.760458: Current learning rate: 0.00282 +2025-10-31 14:37:55.800624: train_loss -0.9926 +2025-10-31 14:37:55.804221: val_loss -0.8881 +2025-10-31 14:37:55.806521: Pseudo dice [np.float32(0.9833), np.float32(0.9925), np.float32(0.9953), np.float32(0.7961)] +2025-10-31 14:37:55.809134: Epoch time: 23.05 s +2025-10-31 14:37:56.970936: +2025-10-31 14:37:56.973907: Epoch 756 +2025-10-31 14:37:56.977578: Current learning rate: 0.00281 +2025-10-31 14:38:24.369484: train_loss -0.9926 +2025-10-31 14:38:24.372722: val_loss -0.8914 +2025-10-31 14:38:24.374783: Pseudo dice [np.float32(0.9841), np.float32(0.9921), np.float32(0.9953), np.float32(0.7979)] +2025-10-31 14:38:24.376652: Epoch time: 27.4 s +2025-10-31 14:38:25.676661: +2025-10-31 14:38:25.678955: Epoch 757 +2025-10-31 14:38:25.680735: Current learning rate: 0.0028 +2025-10-31 14:38:49.191028: train_loss -0.9927 +2025-10-31 14:38:49.193328: val_loss -0.8931 +2025-10-31 14:38:49.195182: Pseudo dice [np.float32(0.9833), np.float32(0.9922), np.float32(0.9952), np.float32(0.8003)] +2025-10-31 14:38:49.197423: Epoch time: 23.52 s +2025-10-31 14:38:50.381895: +2025-10-31 14:38:50.387902: Epoch 758 +2025-10-31 14:38:50.390504: Current learning rate: 0.00279 +2025-10-31 14:39:15.205452: train_loss -0.9923 +2025-10-31 14:39:15.208767: val_loss -0.8901 +2025-10-31 14:39:15.211477: Pseudo dice [np.float32(0.9839), np.float32(0.9921), np.float32(0.9953), np.float32(0.7894)] +2025-10-31 14:39:15.213469: Epoch time: 24.83 s +2025-10-31 14:39:16.489242: +2025-10-31 14:39:16.491356: Epoch 759 +2025-10-31 14:39:16.493897: Current learning rate: 0.00278 +2025-10-31 14:39:40.629215: train_loss -0.9921 +2025-10-31 14:39:40.637825: val_loss -0.8944 +2025-10-31 14:39:40.647582: Pseudo dice [np.float32(0.9839), np.float32(0.993), np.float32(0.9956), np.float32(0.7999)] +2025-10-31 14:39:40.652574: Epoch time: 24.14 s +2025-10-31 14:39:41.703292: +2025-10-31 14:39:41.711536: Epoch 760 +2025-10-31 14:39:41.714132: Current learning rate: 0.00277 +2025-10-31 14:40:07.252411: train_loss -0.9926 +2025-10-31 14:40:07.255452: val_loss -0.8911 +2025-10-31 14:40:07.258305: Pseudo dice [np.float32(0.9837), np.float32(0.9928), np.float32(0.9955), np.float32(0.797)] +2025-10-31 14:40:07.261296: Epoch time: 25.55 s +2025-10-31 14:40:08.443077: +2025-10-31 14:40:08.445119: Epoch 761 +2025-10-31 14:40:08.447422: Current learning rate: 0.00276 +2025-10-31 14:40:33.544005: train_loss -0.9921 +2025-10-31 14:40:33.548770: val_loss -0.8897 +2025-10-31 14:40:33.550811: Pseudo dice [np.float32(0.9854), np.float32(0.9937), np.float32(0.9954), np.float32(0.7948)] +2025-10-31 14:40:33.552578: Epoch time: 25.1 s +2025-10-31 14:40:34.746343: +2025-10-31 14:40:34.748212: Epoch 762 +2025-10-31 14:40:34.749936: Current learning rate: 0.00275 +2025-10-31 14:40:59.766133: train_loss -0.9925 +2025-10-31 14:40:59.769738: val_loss -0.8861 +2025-10-31 14:40:59.772027: Pseudo dice [np.float32(0.9842), np.float32(0.9921), np.float32(0.995), np.float32(0.7872)] +2025-10-31 14:40:59.773910: Epoch time: 25.02 s +2025-10-31 14:41:01.083432: +2025-10-31 14:41:01.089217: Epoch 763 +2025-10-31 14:41:01.097809: Current learning rate: 0.00274 +2025-10-31 14:41:24.239135: train_loss -0.9919 +2025-10-31 14:41:24.242554: val_loss -0.89 +2025-10-31 14:41:24.244644: Pseudo dice [np.float32(0.9846), np.float32(0.9925), np.float32(0.9956), np.float32(0.7967)] +2025-10-31 14:41:24.246720: Epoch time: 23.16 s +2025-10-31 14:41:25.409390: +2025-10-31 14:41:25.411725: Epoch 764 +2025-10-31 14:41:25.413807: Current learning rate: 0.00273 +2025-10-31 14:41:50.475832: train_loss -0.9924 +2025-10-31 14:41:50.481809: val_loss -0.8875 +2025-10-31 14:41:50.483954: Pseudo dice [np.float32(0.9832), np.float32(0.9928), np.float32(0.9947), np.float32(0.7894)] +2025-10-31 14:41:50.486693: Epoch time: 25.07 s +2025-10-31 14:41:52.482192: +2025-10-31 14:41:52.485244: Epoch 765 +2025-10-31 14:41:52.487214: Current learning rate: 0.00272 +2025-10-31 14:42:19.176319: train_loss -0.992 +2025-10-31 14:42:19.178803: val_loss -0.8845 +2025-10-31 14:42:19.181861: Pseudo dice [np.float32(0.9844), np.float32(0.9931), np.float32(0.9952), np.float32(0.7797)] +2025-10-31 14:42:19.184543: Epoch time: 26.7 s +2025-10-31 14:42:20.486381: +2025-10-31 14:42:20.488112: Epoch 766 +2025-10-31 14:42:20.490117: Current learning rate: 0.00271 +2025-10-31 14:42:41.596492: train_loss -0.9924 +2025-10-31 14:42:41.599206: val_loss -0.8859 +2025-10-31 14:42:41.601146: Pseudo dice [np.float32(0.9839), np.float32(0.9922), np.float32(0.9951), np.float32(0.7892)] +2025-10-31 14:42:41.602922: Epoch time: 21.11 s +2025-10-31 14:42:42.849898: +2025-10-31 14:42:42.851786: Epoch 767 +2025-10-31 14:42:42.853670: Current learning rate: 0.0027 +2025-10-31 14:43:09.894946: train_loss -0.9926 +2025-10-31 14:43:09.898275: val_loss -0.8916 +2025-10-31 14:43:09.900922: Pseudo dice [np.float32(0.9854), np.float32(0.9931), np.float32(0.9953), np.float32(0.788)] +2025-10-31 14:43:09.903850: Epoch time: 27.05 s +2025-10-31 14:43:11.144396: +2025-10-31 14:43:11.146721: Epoch 768 +2025-10-31 14:43:11.148871: Current learning rate: 0.00268 +2025-10-31 14:43:33.721330: train_loss -0.9925 +2025-10-31 14:43:33.723897: val_loss -0.8795 +2025-10-31 14:43:33.725514: Pseudo dice [np.float32(0.9826), np.float32(0.9917), np.float32(0.9949), np.float32(0.7791)] +2025-10-31 14:43:33.727006: Epoch time: 22.58 s +2025-10-31 14:43:34.886095: +2025-10-31 14:43:34.888339: Epoch 769 +2025-10-31 14:43:34.890180: Current learning rate: 0.00267 +2025-10-31 14:43:59.436664: train_loss -0.9926 +2025-10-31 14:43:59.439550: val_loss -0.8868 +2025-10-31 14:43:59.441491: Pseudo dice [np.float32(0.9834), np.float32(0.9925), np.float32(0.9952), np.float32(0.7902)] +2025-10-31 14:43:59.443239: Epoch time: 24.55 s +2025-10-31 14:44:00.594779: +2025-10-31 14:44:00.596560: Epoch 770 +2025-10-31 14:44:00.598294: Current learning rate: 0.00266 +2025-10-31 14:44:25.384712: train_loss -0.9924 +2025-10-31 14:44:25.387887: val_loss -0.8804 +2025-10-31 14:44:25.390039: Pseudo dice [np.float32(0.985), np.float32(0.9926), np.float32(0.9947), np.float32(0.766)] +2025-10-31 14:44:25.391994: Epoch time: 24.79 s +2025-10-31 14:44:26.472081: +2025-10-31 14:44:26.473889: Epoch 771 +2025-10-31 14:44:26.476092: Current learning rate: 0.00265 +2025-10-31 14:44:47.293868: train_loss -0.9927 +2025-10-31 14:44:47.298650: val_loss -0.8815 +2025-10-31 14:44:47.300111: Pseudo dice [np.float32(0.9834), np.float32(0.9925), np.float32(0.9948), np.float32(0.7807)] +2025-10-31 14:44:47.301637: Epoch time: 20.82 s +2025-10-31 14:44:48.566692: +2025-10-31 14:44:48.571104: Epoch 772 +2025-10-31 14:44:48.573689: Current learning rate: 0.00264 +2025-10-31 14:45:07.095837: train_loss -0.9927 +2025-10-31 14:45:07.110254: val_loss -0.8902 +2025-10-31 14:45:07.117790: Pseudo dice [np.float32(0.9848), np.float32(0.9924), np.float32(0.9954), np.float32(0.7897)] +2025-10-31 14:45:07.129967: Epoch time: 18.53 s +2025-10-31 14:45:08.483841: +2025-10-31 14:45:08.497675: Epoch 773 +2025-10-31 14:45:08.505696: Current learning rate: 0.00263 +2025-10-31 14:45:32.332415: train_loss -0.9926 +2025-10-31 14:45:32.336468: val_loss -0.8843 +2025-10-31 14:45:32.338359: Pseudo dice [np.float32(0.9837), np.float32(0.9924), np.float32(0.9949), np.float32(0.778)] +2025-10-31 14:45:32.339894: Epoch time: 23.85 s +2025-10-31 14:45:33.586468: +2025-10-31 14:45:33.591979: Epoch 774 +2025-10-31 14:45:33.595612: Current learning rate: 0.00262 +2025-10-31 14:45:58.177368: train_loss -0.9929 +2025-10-31 14:45:58.180451: val_loss -0.8881 +2025-10-31 14:45:58.182341: Pseudo dice [np.float32(0.9843), np.float32(0.993), np.float32(0.9952), np.float32(0.7877)] +2025-10-31 14:45:58.184377: Epoch time: 24.59 s +2025-10-31 14:45:59.450465: +2025-10-31 14:45:59.454187: Epoch 775 +2025-10-31 14:45:59.456788: Current learning rate: 0.00261 +2025-10-31 14:46:26.908029: train_loss -0.9927 +2025-10-31 14:46:26.911427: val_loss -0.8883 +2025-10-31 14:46:26.913155: Pseudo dice [np.float32(0.9837), np.float32(0.9928), np.float32(0.9954), np.float32(0.7839)] +2025-10-31 14:46:26.914724: Epoch time: 27.46 s +2025-10-31 14:46:28.091895: +2025-10-31 14:46:28.095146: Epoch 776 +2025-10-31 14:46:28.097803: Current learning rate: 0.0026 +2025-10-31 14:46:54.227215: train_loss -0.9926 +2025-10-31 14:46:54.234116: val_loss -0.8887 +2025-10-31 14:46:54.235866: Pseudo dice [np.float32(0.983), np.float32(0.9926), np.float32(0.9957), np.float32(0.7964)] +2025-10-31 14:46:54.237583: Epoch time: 26.14 s +2025-10-31 14:46:56.114228: +2025-10-31 14:46:56.119002: Epoch 777 +2025-10-31 14:46:56.121973: Current learning rate: 0.00259 +2025-10-31 14:47:22.125668: train_loss -0.9927 +2025-10-31 14:47:22.129372: val_loss -0.8835 +2025-10-31 14:47:22.131270: Pseudo dice [np.float32(0.9848), np.float32(0.9928), np.float32(0.9951), np.float32(0.7777)] +2025-10-31 14:47:22.134583: Epoch time: 26.01 s +2025-10-31 14:47:23.388974: +2025-10-31 14:47:23.391244: Epoch 778 +2025-10-31 14:47:23.393137: Current learning rate: 0.00258 +2025-10-31 14:47:47.855024: train_loss -0.9928 +2025-10-31 14:47:47.859864: val_loss -0.8789 +2025-10-31 14:47:47.861550: Pseudo dice [np.float32(0.9848), np.float32(0.9924), np.float32(0.9949), np.float32(0.7698)] +2025-10-31 14:47:47.863153: Epoch time: 24.47 s +2025-10-31 14:47:49.123273: +2025-10-31 14:47:49.127469: Epoch 779 +2025-10-31 14:47:49.131306: Current learning rate: 0.00257 +2025-10-31 14:48:14.673923: train_loss -0.9928 +2025-10-31 14:48:14.676759: val_loss -0.887 +2025-10-31 14:48:14.678650: Pseudo dice [np.float32(0.9843), np.float32(0.9923), np.float32(0.9953), np.float32(0.7946)] +2025-10-31 14:48:14.680956: Epoch time: 25.55 s +2025-10-31 14:48:15.797557: +2025-10-31 14:48:15.799733: Epoch 780 +2025-10-31 14:48:15.801493: Current learning rate: 0.00256 +2025-10-31 14:48:41.757873: train_loss -0.9931 +2025-10-31 14:48:41.761480: val_loss -0.8849 +2025-10-31 14:48:41.763380: Pseudo dice [np.float32(0.9839), np.float32(0.9928), np.float32(0.9953), np.float32(0.7807)] +2025-10-31 14:48:41.765738: Epoch time: 25.96 s +2025-10-31 14:48:43.015400: +2025-10-31 14:48:43.017528: Epoch 781 +2025-10-31 14:48:43.020214: Current learning rate: 0.00255 +2025-10-31 14:49:09.212796: train_loss -0.9924 +2025-10-31 14:49:09.215551: val_loss -0.8926 +2025-10-31 14:49:09.217567: Pseudo dice [np.float32(0.984), np.float32(0.9927), np.float32(0.9954), np.float32(0.7939)] +2025-10-31 14:49:09.219525: Epoch time: 26.2 s +2025-10-31 14:49:10.607366: +2025-10-31 14:49:10.610684: Epoch 782 +2025-10-31 14:49:10.612511: Current learning rate: 0.00254 +2025-10-31 14:49:36.717752: train_loss -0.9924 +2025-10-31 14:49:36.721542: val_loss -0.889 +2025-10-31 14:49:36.723542: Pseudo dice [np.float32(0.9849), np.float32(0.993), np.float32(0.9951), np.float32(0.7925)] +2025-10-31 14:49:36.725403: Epoch time: 26.11 s +2025-10-31 14:49:38.037879: +2025-10-31 14:49:38.039862: Epoch 783 +2025-10-31 14:49:38.041911: Current learning rate: 0.00253 +2025-10-31 14:50:04.468671: train_loss -0.9928 +2025-10-31 14:50:04.473333: val_loss -0.8867 +2025-10-31 14:50:04.476123: Pseudo dice [np.float32(0.9837), np.float32(0.9925), np.float32(0.9953), np.float32(0.7877)] +2025-10-31 14:50:04.480699: Epoch time: 26.43 s +2025-10-31 14:50:05.718493: +2025-10-31 14:50:05.720961: Epoch 784 +2025-10-31 14:50:05.722677: Current learning rate: 0.00252 +2025-10-31 14:50:27.937454: train_loss -0.9919 +2025-10-31 14:50:27.939884: val_loss -0.8958 +2025-10-31 14:50:27.942219: Pseudo dice [np.float32(0.9841), np.float32(0.9926), np.float32(0.9955), np.float32(0.8029)] +2025-10-31 14:50:27.944451: Epoch time: 22.22 s +2025-10-31 14:50:29.171798: +2025-10-31 14:50:29.174055: Epoch 785 +2025-10-31 14:50:29.176008: Current learning rate: 0.00251 +2025-10-31 14:50:53.954906: train_loss -0.9932 +2025-10-31 14:50:53.957107: val_loss -0.886 +2025-10-31 14:50:53.958873: Pseudo dice [np.float32(0.9845), np.float32(0.993), np.float32(0.9953), np.float32(0.7829)] +2025-10-31 14:50:53.960733: Epoch time: 24.78 s +2025-10-31 14:50:55.137741: +2025-10-31 14:50:55.140083: Epoch 786 +2025-10-31 14:50:55.142073: Current learning rate: 0.0025 +2025-10-31 14:51:18.638932: train_loss -0.9925 +2025-10-31 14:51:18.646613: val_loss -0.8882 +2025-10-31 14:51:18.648492: Pseudo dice [np.float32(0.9849), np.float32(0.9926), np.float32(0.9951), np.float32(0.7889)] +2025-10-31 14:51:18.650337: Epoch time: 23.5 s +2025-10-31 14:51:19.903052: +2025-10-31 14:51:19.905102: Epoch 787 +2025-10-31 14:51:19.906897: Current learning rate: 0.00249 +2025-10-31 14:51:44.177189: train_loss -0.9927 +2025-10-31 14:51:44.180040: val_loss -0.8947 +2025-10-31 14:51:44.182159: Pseudo dice [np.float32(0.9836), np.float32(0.9921), np.float32(0.9954), np.float32(0.8034)] +2025-10-31 14:51:44.183911: Epoch time: 24.28 s +2025-10-31 14:51:45.384104: +2025-10-31 14:51:45.386030: Epoch 788 +2025-10-31 14:51:45.387746: Current learning rate: 0.00248 +2025-10-31 14:52:08.344868: train_loss -0.9926 +2025-10-31 14:52:08.348485: val_loss -0.8901 +2025-10-31 14:52:08.350627: Pseudo dice [np.float32(0.984), np.float32(0.9926), np.float32(0.9958), np.float32(0.7969)] +2025-10-31 14:52:08.352249: Epoch time: 22.96 s +2025-10-31 14:52:10.125660: +2025-10-31 14:52:10.128107: Epoch 789 +2025-10-31 14:52:10.130458: Current learning rate: 0.00247 +2025-10-31 14:52:34.800489: train_loss -0.992 +2025-10-31 14:52:34.806455: val_loss -0.8902 +2025-10-31 14:52:34.808717: Pseudo dice [np.float32(0.984), np.float32(0.9927), np.float32(0.9954), np.float32(0.7887)] +2025-10-31 14:52:34.810572: Epoch time: 24.68 s +2025-10-31 14:52:36.023231: +2025-10-31 14:52:36.025686: Epoch 790 +2025-10-31 14:52:36.027470: Current learning rate: 0.00245 +2025-10-31 14:53:02.081406: train_loss -0.993 +2025-10-31 14:53:02.085312: val_loss -0.8899 +2025-10-31 14:53:02.087137: Pseudo dice [np.float32(0.9833), np.float32(0.9926), np.float32(0.9956), np.float32(0.7922)] +2025-10-31 14:53:02.088867: Epoch time: 26.06 s +2025-10-31 14:53:03.354878: +2025-10-31 14:53:03.357319: Epoch 791 +2025-10-31 14:53:03.358960: Current learning rate: 0.00244 +2025-10-31 14:53:29.296655: train_loss -0.9927 +2025-10-31 14:53:29.299320: val_loss -0.8855 +2025-10-31 14:53:29.301106: Pseudo dice [np.float32(0.9843), np.float32(0.9926), np.float32(0.9951), np.float32(0.7836)] +2025-10-31 14:53:29.302811: Epoch time: 25.94 s +2025-10-31 14:53:30.565695: +2025-10-31 14:53:30.567408: Epoch 792 +2025-10-31 14:53:30.569192: Current learning rate: 0.00243 +2025-10-31 14:53:52.257454: train_loss -0.9933 +2025-10-31 14:53:52.260026: val_loss -0.8937 +2025-10-31 14:53:52.261685: Pseudo dice [np.float32(0.9844), np.float32(0.9927), np.float32(0.9957), np.float32(0.8023)] +2025-10-31 14:53:52.263369: Epoch time: 21.69 s +2025-10-31 14:53:53.513516: +2025-10-31 14:53:53.516144: Epoch 793 +2025-10-31 14:53:53.518643: Current learning rate: 0.00242 +2025-10-31 14:54:19.081672: train_loss -0.993 +2025-10-31 14:54:19.083688: val_loss -0.8879 +2025-10-31 14:54:19.085418: Pseudo dice [np.float32(0.9845), np.float32(0.9927), np.float32(0.9954), np.float32(0.7884)] +2025-10-31 14:54:19.087055: Epoch time: 25.57 s +2025-10-31 14:54:20.306136: +2025-10-31 14:54:20.308254: Epoch 794 +2025-10-31 14:54:20.309816: Current learning rate: 0.00241 +2025-10-31 14:54:45.970016: train_loss -0.9929 +2025-10-31 14:54:45.975880: val_loss -0.8819 +2025-10-31 14:54:45.977983: Pseudo dice [np.float32(0.9845), np.float32(0.9928), np.float32(0.9954), np.float32(0.7747)] +2025-10-31 14:54:45.980201: Epoch time: 25.67 s +2025-10-31 14:54:47.197476: +2025-10-31 14:54:47.199333: Epoch 795 +2025-10-31 14:54:47.200992: Current learning rate: 0.0024 +2025-10-31 14:55:12.577962: train_loss -0.9927 +2025-10-31 14:55:12.580556: val_loss -0.891 +2025-10-31 14:55:12.582206: Pseudo dice [np.float32(0.9842), np.float32(0.9928), np.float32(0.9955), np.float32(0.8019)] +2025-10-31 14:55:12.584101: Epoch time: 25.38 s +2025-10-31 14:55:13.845815: +2025-10-31 14:55:13.847658: Epoch 796 +2025-10-31 14:55:13.849347: Current learning rate: 0.00239 +2025-10-31 14:55:39.303006: train_loss -0.9925 +2025-10-31 14:55:39.305100: val_loss -0.889 +2025-10-31 14:55:39.307018: Pseudo dice [np.float32(0.9843), np.float32(0.9922), np.float32(0.9955), np.float32(0.7931)] +2025-10-31 14:55:39.308544: Epoch time: 25.46 s +2025-10-31 14:55:40.504132: +2025-10-31 14:55:40.505997: Epoch 797 +2025-10-31 14:55:40.507866: Current learning rate: 0.00238 +2025-10-31 14:56:06.187867: train_loss -0.9936 +2025-10-31 14:56:06.190472: val_loss -0.8851 +2025-10-31 14:56:06.193063: Pseudo dice [np.float32(0.9833), np.float32(0.9927), np.float32(0.9952), np.float32(0.7861)] +2025-10-31 14:56:06.194582: Epoch time: 25.69 s +2025-10-31 14:56:07.439006: +2025-10-31 14:56:07.442725: Epoch 798 +2025-10-31 14:56:07.444813: Current learning rate: 0.00237 +2025-10-31 14:56:33.077790: train_loss -0.9926 +2025-10-31 14:56:33.084812: val_loss -0.8908 +2025-10-31 14:56:33.086550: Pseudo dice [np.float32(0.9851), np.float32(0.9929), np.float32(0.9954), np.float32(0.7955)] +2025-10-31 14:56:33.088047: Epoch time: 25.64 s +2025-10-31 14:56:34.341876: +2025-10-31 14:56:34.343930: Epoch 799 +2025-10-31 14:56:34.345927: Current learning rate: 0.00236 +2025-10-31 14:56:58.087940: train_loss -0.9932 +2025-10-31 14:56:58.090939: val_loss -0.8879 +2025-10-31 14:56:58.092515: Pseudo dice [np.float32(0.9842), np.float32(0.9925), np.float32(0.9955), np.float32(0.7879)] +2025-10-31 14:56:58.093952: Epoch time: 23.75 s +2025-10-31 14:57:00.727226: +2025-10-31 14:57:00.730669: Epoch 800 +2025-10-31 14:57:00.733177: Current learning rate: 0.00235 +2025-10-31 14:57:25.593237: train_loss -0.9931 +2025-10-31 14:57:25.595842: val_loss -0.8855 +2025-10-31 14:57:25.597464: Pseudo dice [np.float32(0.9849), np.float32(0.9929), np.float32(0.9952), np.float32(0.78)] +2025-10-31 14:57:25.599124: Epoch time: 24.87 s +2025-10-31 14:57:27.329140: +2025-10-31 14:57:27.331398: Epoch 801 +2025-10-31 14:57:27.333476: Current learning rate: 0.00234 +2025-10-31 14:57:53.292072: train_loss -0.9925 +2025-10-31 14:57:53.295808: val_loss -0.8869 +2025-10-31 14:57:53.297338: Pseudo dice [np.float32(0.9833), np.float32(0.9923), np.float32(0.9953), np.float32(0.787)] +2025-10-31 14:57:53.298742: Epoch time: 25.96 s +2025-10-31 14:57:54.474526: +2025-10-31 14:57:54.476574: Epoch 802 +2025-10-31 14:57:54.478322: Current learning rate: 0.00233 +2025-10-31 14:58:19.068369: train_loss -0.9928 +2025-10-31 14:58:19.070663: val_loss -0.8902 +2025-10-31 14:58:19.073246: Pseudo dice [np.float32(0.9853), np.float32(0.9932), np.float32(0.9955), np.float32(0.7956)] +2025-10-31 14:58:19.076237: Epoch time: 24.6 s +2025-10-31 14:58:20.368607: +2025-10-31 14:58:20.370718: Epoch 803 +2025-10-31 14:58:20.372614: Current learning rate: 0.00232 +2025-10-31 14:58:44.994186: train_loss -0.9933 +2025-10-31 14:58:44.999980: val_loss -0.8808 +2025-10-31 14:58:45.003295: Pseudo dice [np.float32(0.984), np.float32(0.9926), np.float32(0.9951), np.float32(0.7722)] +2025-10-31 14:58:45.006648: Epoch time: 24.63 s +2025-10-31 14:58:46.287236: +2025-10-31 14:58:46.289142: Epoch 804 +2025-10-31 14:58:46.290806: Current learning rate: 0.00231 +2025-10-31 14:59:09.526650: train_loss -0.9929 +2025-10-31 14:59:09.530475: val_loss -0.8898 +2025-10-31 14:59:09.532405: Pseudo dice [np.float32(0.9839), np.float32(0.9928), np.float32(0.9955), np.float32(0.7924)] +2025-10-31 14:59:09.534152: Epoch time: 23.24 s +2025-10-31 14:59:10.775470: +2025-10-31 14:59:10.777256: Epoch 805 +2025-10-31 14:59:10.779368: Current learning rate: 0.0023 +2025-10-31 14:59:33.783922: train_loss -0.9926 +2025-10-31 14:59:33.786746: val_loss -0.8959 +2025-10-31 14:59:33.789182: Pseudo dice [np.float32(0.984), np.float32(0.9924), np.float32(0.9958), np.float32(0.8108)] +2025-10-31 14:59:33.792331: Epoch time: 23.01 s +2025-10-31 14:59:35.061528: +2025-10-31 14:59:35.064055: Epoch 806 +2025-10-31 14:59:35.066147: Current learning rate: 0.00229 +2025-10-31 14:59:57.008295: train_loss -0.993 +2025-10-31 14:59:57.011208: val_loss -0.8851 +2025-10-31 14:59:57.012959: Pseudo dice [np.float32(0.9848), np.float32(0.9924), np.float32(0.9953), np.float32(0.7878)] +2025-10-31 14:59:57.014626: Epoch time: 21.95 s +2025-10-31 14:59:58.241396: +2025-10-31 14:59:58.243917: Epoch 807 +2025-10-31 14:59:58.245703: Current learning rate: 0.00228 +2025-10-31 15:00:23.102064: train_loss -0.9934 +2025-10-31 15:00:23.108084: val_loss -0.8932 +2025-10-31 15:00:23.110039: Pseudo dice [np.float32(0.9842), np.float32(0.993), np.float32(0.9955), np.float32(0.7981)] +2025-10-31 15:00:23.112542: Epoch time: 24.86 s +2025-10-31 15:00:24.286506: +2025-10-31 15:00:24.288801: Epoch 808 +2025-10-31 15:00:24.290555: Current learning rate: 0.00226 +2025-10-31 15:00:49.892461: train_loss -0.9935 +2025-10-31 15:00:49.897719: val_loss -0.8932 +2025-10-31 15:00:49.899291: Pseudo dice [np.float32(0.9835), np.float32(0.9929), np.float32(0.9955), np.float32(0.808)] +2025-10-31 15:00:49.901093: Epoch time: 25.61 s +2025-10-31 15:00:51.164355: +2025-10-31 15:00:51.166239: Epoch 809 +2025-10-31 15:00:51.167996: Current learning rate: 0.00225 +2025-10-31 15:01:15.292778: train_loss -0.9935 +2025-10-31 15:01:15.295763: val_loss -0.8946 +2025-10-31 15:01:15.297568: Pseudo dice [np.float32(0.9844), np.float32(0.9925), np.float32(0.9955), np.float32(0.8097)] +2025-10-31 15:01:15.299306: Epoch time: 24.13 s +2025-10-31 15:01:16.489247: +2025-10-31 15:01:16.491296: Epoch 810 +2025-10-31 15:01:16.492953: Current learning rate: 0.00224 +2025-10-31 15:01:40.957797: train_loss -0.9929 +2025-10-31 15:01:40.960763: val_loss -0.8881 +2025-10-31 15:01:40.962413: Pseudo dice [np.float32(0.9853), np.float32(0.9932), np.float32(0.9951), np.float32(0.7895)] +2025-10-31 15:01:40.964195: Epoch time: 24.47 s +2025-10-31 15:01:42.215879: +2025-10-31 15:01:42.219407: Epoch 811 +2025-10-31 15:01:42.221256: Current learning rate: 0.00223 +2025-10-31 15:02:07.886275: train_loss -0.9935 +2025-10-31 15:02:07.890616: val_loss -0.8911 +2025-10-31 15:02:07.895682: Pseudo dice [np.float32(0.985), np.float32(0.9925), np.float32(0.9954), np.float32(0.7908)] +2025-10-31 15:02:07.897411: Epoch time: 25.67 s +2025-10-31 15:02:09.707415: +2025-10-31 15:02:09.709427: Epoch 812 +2025-10-31 15:02:09.711143: Current learning rate: 0.00222 +2025-10-31 15:02:35.812986: train_loss -0.9931 +2025-10-31 15:02:35.818137: val_loss -0.893 +2025-10-31 15:02:35.819930: Pseudo dice [np.float32(0.985), np.float32(0.9928), np.float32(0.9957), np.float32(0.7979)] +2025-10-31 15:02:35.821642: Epoch time: 26.11 s +2025-10-31 15:02:36.976328: +2025-10-31 15:02:36.978298: Epoch 813 +2025-10-31 15:02:36.980004: Current learning rate: 0.00221 +2025-10-31 15:03:00.801403: train_loss -0.9928 +2025-10-31 15:03:00.804321: val_loss -0.8912 +2025-10-31 15:03:00.806183: Pseudo dice [np.float32(0.9848), np.float32(0.9924), np.float32(0.9951), np.float32(0.7976)] +2025-10-31 15:03:00.808040: Epoch time: 23.83 s +2025-10-31 15:03:02.049986: +2025-10-31 15:03:02.052032: Epoch 814 +2025-10-31 15:03:02.053816: Current learning rate: 0.0022 +2025-10-31 15:03:26.355515: train_loss -0.9928 +2025-10-31 15:03:26.358606: val_loss -0.888 +2025-10-31 15:03:26.360218: Pseudo dice [np.float32(0.9847), np.float32(0.9926), np.float32(0.9951), np.float32(0.7858)] +2025-10-31 15:03:26.361820: Epoch time: 24.31 s +2025-10-31 15:03:27.663998: +2025-10-31 15:03:27.667149: Epoch 815 +2025-10-31 15:03:27.669253: Current learning rate: 0.00219 +2025-10-31 15:03:52.693809: train_loss -0.993 +2025-10-31 15:03:52.701195: val_loss -0.8897 +2025-10-31 15:03:52.702820: Pseudo dice [np.float32(0.9844), np.float32(0.9931), np.float32(0.9954), np.float32(0.7901)] +2025-10-31 15:03:52.704445: Epoch time: 25.03 s +2025-10-31 15:03:53.948521: +2025-10-31 15:03:53.950788: Epoch 816 +2025-10-31 15:03:53.952391: Current learning rate: 0.00218 +2025-10-31 15:04:19.260226: train_loss -0.9931 +2025-10-31 15:04:19.268548: val_loss -0.8923 +2025-10-31 15:04:19.270094: Pseudo dice [np.float32(0.9853), np.float32(0.993), np.float32(0.9955), np.float32(0.7991)] +2025-10-31 15:04:19.271875: Epoch time: 25.31 s +2025-10-31 15:04:20.526301: +2025-10-31 15:04:20.528013: Epoch 817 +2025-10-31 15:04:20.529490: Current learning rate: 0.00217 +2025-10-31 15:04:46.109294: train_loss -0.9934 +2025-10-31 15:04:46.115512: val_loss -0.89 +2025-10-31 15:04:46.117241: Pseudo dice [np.float32(0.9851), np.float32(0.9932), np.float32(0.9954), np.float32(0.7899)] +2025-10-31 15:04:46.118937: Epoch time: 25.58 s +2025-10-31 15:04:47.377491: +2025-10-31 15:04:47.379934: Epoch 818 +2025-10-31 15:04:47.381675: Current learning rate: 0.00216 +2025-10-31 15:05:14.460557: train_loss -0.9931 +2025-10-31 15:05:14.465092: val_loss -0.8882 +2025-10-31 15:05:14.467077: Pseudo dice [np.float32(0.9853), np.float32(0.9929), np.float32(0.9953), np.float32(0.7821)] +2025-10-31 15:05:14.469020: Epoch time: 27.08 s +2025-10-31 15:05:15.768794: +2025-10-31 15:05:15.770842: Epoch 819 +2025-10-31 15:05:15.773198: Current learning rate: 0.00215 +2025-10-31 15:05:39.764394: train_loss -0.9935 +2025-10-31 15:05:39.768846: val_loss -0.8896 +2025-10-31 15:05:39.770759: Pseudo dice [np.float32(0.986), np.float32(0.9931), np.float32(0.9953), np.float32(0.7862)] +2025-10-31 15:05:39.772620: Epoch time: 24.0 s +2025-10-31 15:05:40.968104: +2025-10-31 15:05:40.969822: Epoch 820 +2025-10-31 15:05:40.971479: Current learning rate: 0.00214 +2025-10-31 15:06:06.962802: train_loss -0.9932 +2025-10-31 15:06:06.968432: val_loss -0.8903 +2025-10-31 15:06:06.970203: Pseudo dice [np.float32(0.9848), np.float32(0.9932), np.float32(0.9954), np.float32(0.792)] +2025-10-31 15:06:06.972528: Epoch time: 26.0 s +2025-10-31 15:06:08.114783: +2025-10-31 15:06:08.116658: Epoch 821 +2025-10-31 15:06:08.118899: Current learning rate: 0.00213 +2025-10-31 15:06:34.285125: train_loss -0.9927 +2025-10-31 15:06:34.291701: val_loss -0.8986 +2025-10-31 15:06:34.293642: Pseudo dice [np.float32(0.9844), np.float32(0.9932), np.float32(0.9955), np.float32(0.8123)] +2025-10-31 15:06:34.295612: Epoch time: 26.17 s +2025-10-31 15:06:35.428118: +2025-10-31 15:06:35.430435: Epoch 822 +2025-10-31 15:06:35.432386: Current learning rate: 0.00212 +2025-10-31 15:06:59.742098: train_loss -0.9932 +2025-10-31 15:06:59.745659: val_loss -0.8988 +2025-10-31 15:06:59.747308: Pseudo dice [np.float32(0.984), np.float32(0.9925), np.float32(0.9957), np.float32(0.8132)] +2025-10-31 15:06:59.748895: Epoch time: 24.32 s +2025-10-31 15:07:00.989294: +2025-10-31 15:07:00.991448: Epoch 823 +2025-10-31 15:07:00.993094: Current learning rate: 0.0021 +2025-10-31 15:07:25.269928: train_loss -0.9937 +2025-10-31 15:07:25.273062: val_loss -0.8952 +2025-10-31 15:07:25.274662: Pseudo dice [np.float32(0.9846), np.float32(0.9931), np.float32(0.9958), np.float32(0.8055)] +2025-10-31 15:07:25.276295: Epoch time: 24.28 s +2025-10-31 15:07:26.536168: +2025-10-31 15:07:26.537976: Epoch 824 +2025-10-31 15:07:26.539581: Current learning rate: 0.00209 +2025-10-31 15:07:51.583636: train_loss -0.9932 +2025-10-31 15:07:51.586556: val_loss -0.8892 +2025-10-31 15:07:51.588088: Pseudo dice [np.float32(0.9836), np.float32(0.9919), np.float32(0.9954), np.float32(0.7955)] +2025-10-31 15:07:51.589635: Epoch time: 25.05 s +2025-10-31 15:07:53.258136: +2025-10-31 15:07:53.260210: Epoch 825 +2025-10-31 15:07:53.261796: Current learning rate: 0.00208 +2025-10-31 15:08:18.126455: train_loss -0.9933 +2025-10-31 15:08:18.129116: val_loss -0.8924 +2025-10-31 15:08:18.130894: Pseudo dice [np.float32(0.9845), np.float32(0.993), np.float32(0.9957), np.float32(0.7969)] +2025-10-31 15:08:18.133198: Epoch time: 24.87 s +2025-10-31 15:08:19.362115: +2025-10-31 15:08:19.364953: Epoch 826 +2025-10-31 15:08:19.366900: Current learning rate: 0.00207 +2025-10-31 15:08:44.753331: train_loss -0.9934 +2025-10-31 15:08:44.759660: val_loss -0.8865 +2025-10-31 15:08:44.761679: Pseudo dice [np.float32(0.9848), np.float32(0.9926), np.float32(0.995), np.float32(0.7855)] +2025-10-31 15:08:44.763598: Epoch time: 25.39 s +2025-10-31 15:08:46.005425: +2025-10-31 15:08:46.007404: Epoch 827 +2025-10-31 15:08:46.009256: Current learning rate: 0.00206 +2025-10-31 15:09:11.699247: train_loss -0.9934 +2025-10-31 15:09:11.701874: val_loss -0.8899 +2025-10-31 15:09:11.703465: Pseudo dice [np.float32(0.9852), np.float32(0.9926), np.float32(0.9951), np.float32(0.7888)] +2025-10-31 15:09:11.705040: Epoch time: 25.7 s +2025-10-31 15:09:12.971289: +2025-10-31 15:09:12.973253: Epoch 828 +2025-10-31 15:09:12.974987: Current learning rate: 0.00205 +2025-10-31 15:09:36.698926: train_loss -0.9932 +2025-10-31 15:09:36.705386: val_loss -0.8869 +2025-10-31 15:09:36.707215: Pseudo dice [np.float32(0.9855), np.float32(0.9931), np.float32(0.9952), np.float32(0.7797)] +2025-10-31 15:09:36.708834: Epoch time: 23.73 s +2025-10-31 15:09:37.917019: +2025-10-31 15:09:37.919069: Epoch 829 +2025-10-31 15:09:37.920737: Current learning rate: 0.00204 +2025-10-31 15:10:02.796860: train_loss -0.9937 +2025-10-31 15:10:02.802499: val_loss -0.8828 +2025-10-31 15:10:02.804266: Pseudo dice [np.float32(0.9848), np.float32(0.9929), np.float32(0.995), np.float32(0.7801)] +2025-10-31 15:10:02.805984: Epoch time: 24.88 s +2025-10-31 15:10:03.972960: +2025-10-31 15:10:03.979314: Epoch 830 +2025-10-31 15:10:03.982424: Current learning rate: 0.00203 +2025-10-31 15:10:28.250502: train_loss -0.9934 +2025-10-31 15:10:28.256660: val_loss -0.889 +2025-10-31 15:10:28.258430: Pseudo dice [np.float32(0.9855), np.float32(0.9932), np.float32(0.9952), np.float32(0.7907)] +2025-10-31 15:10:28.260186: Epoch time: 24.28 s +2025-10-31 15:10:29.443391: +2025-10-31 15:10:29.445273: Epoch 831 +2025-10-31 15:10:29.447018: Current learning rate: 0.00202 +2025-10-31 15:10:54.156046: train_loss -0.9929 +2025-10-31 15:10:54.159009: val_loss -0.8745 +2025-10-31 15:10:54.160720: Pseudo dice [np.float32(0.9837), np.float32(0.992), np.float32(0.9945), np.float32(0.7581)] +2025-10-31 15:10:54.162508: Epoch time: 24.71 s +2025-10-31 15:10:55.391419: +2025-10-31 15:10:55.393212: Epoch 832 +2025-10-31 15:10:55.394858: Current learning rate: 0.00201 +2025-10-31 15:11:21.556901: train_loss -0.9932 +2025-10-31 15:11:21.559593: val_loss -0.8818 +2025-10-31 15:11:21.561499: Pseudo dice [np.float32(0.9848), np.float32(0.9921), np.float32(0.9948), np.float32(0.7812)] +2025-10-31 15:11:21.563673: Epoch time: 26.17 s +2025-10-31 15:11:22.769339: +2025-10-31 15:11:22.771654: Epoch 833 +2025-10-31 15:11:22.773499: Current learning rate: 0.002 +2025-10-31 15:11:45.285156: train_loss -0.9931 +2025-10-31 15:11:45.288306: val_loss -0.8794 +2025-10-31 15:11:45.290246: Pseudo dice [np.float32(0.9846), np.float32(0.9925), np.float32(0.995), np.float32(0.7697)] +2025-10-31 15:11:45.291965: Epoch time: 22.52 s +2025-10-31 15:11:46.493562: +2025-10-31 15:11:46.495699: Epoch 834 +2025-10-31 15:11:46.497428: Current learning rate: 0.00199 +2025-10-31 15:12:11.131371: train_loss -0.9927 +2025-10-31 15:12:11.134686: val_loss -0.8904 +2025-10-31 15:12:11.136351: Pseudo dice [np.float32(0.9844), np.float32(0.9929), np.float32(0.9954), np.float32(0.7922)] +2025-10-31 15:12:11.138040: Epoch time: 24.64 s +2025-10-31 15:12:12.390196: +2025-10-31 15:12:12.392578: Epoch 835 +2025-10-31 15:12:12.394550: Current learning rate: 0.00198 +2025-10-31 15:12:38.446843: train_loss -0.9928 +2025-10-31 15:12:38.449288: val_loss -0.8851 +2025-10-31 15:12:38.450980: Pseudo dice [np.float32(0.9844), np.float32(0.9923), np.float32(0.9947), np.float32(0.7791)] +2025-10-31 15:12:38.452633: Epoch time: 26.06 s +2025-10-31 15:12:39.632707: +2025-10-31 15:12:39.634995: Epoch 836 +2025-10-31 15:12:39.638126: Current learning rate: 0.00196 +2025-10-31 15:13:06.091546: train_loss -0.9932 +2025-10-31 15:13:06.094548: val_loss -0.8911 +2025-10-31 15:13:06.096328: Pseudo dice [np.float32(0.985), np.float32(0.9928), np.float32(0.9954), np.float32(0.7947)] +2025-10-31 15:13:06.097806: Epoch time: 26.46 s +2025-10-31 15:13:07.322637: +2025-10-31 15:13:07.324594: Epoch 837 +2025-10-31 15:13:07.326241: Current learning rate: 0.00195 +2025-10-31 15:13:33.721493: train_loss -0.9929 +2025-10-31 15:13:33.725775: val_loss -0.889 +2025-10-31 15:13:33.727600: Pseudo dice [np.float32(0.9854), np.float32(0.993), np.float32(0.9952), np.float32(0.7846)] +2025-10-31 15:13:33.729712: Epoch time: 26.4 s +2025-10-31 15:13:35.353128: +2025-10-31 15:13:35.356222: Epoch 838 +2025-10-31 15:13:35.358113: Current learning rate: 0.00194 +2025-10-31 15:14:00.434685: train_loss -0.9932 +2025-10-31 15:14:00.436988: val_loss -0.8875 +2025-10-31 15:14:00.438657: Pseudo dice [np.float32(0.9846), np.float32(0.9927), np.float32(0.9953), np.float32(0.7838)] +2025-10-31 15:14:00.440336: Epoch time: 25.08 s +2025-10-31 15:14:01.658406: +2025-10-31 15:14:01.660320: Epoch 839 +2025-10-31 15:14:01.662352: Current learning rate: 0.00193 +2025-10-31 15:14:26.357360: train_loss -0.9934 +2025-10-31 15:14:26.359876: val_loss -0.8906 +2025-10-31 15:14:26.361773: Pseudo dice [np.float32(0.984), np.float32(0.9922), np.float32(0.9954), np.float32(0.7984)] +2025-10-31 15:14:26.363483: Epoch time: 24.7 s +2025-10-31 15:14:27.530353: +2025-10-31 15:14:27.532878: Epoch 840 +2025-10-31 15:14:27.534505: Current learning rate: 0.00192 +2025-10-31 15:14:51.330046: train_loss -0.9932 +2025-10-31 15:14:51.334292: val_loss -0.8935 +2025-10-31 15:14:51.336043: Pseudo dice [np.float32(0.9852), np.float32(0.993), np.float32(0.9955), np.float32(0.7981)] +2025-10-31 15:14:51.339420: Epoch time: 23.8 s +2025-10-31 15:14:52.557647: +2025-10-31 15:14:52.560285: Epoch 841 +2025-10-31 15:14:52.562295: Current learning rate: 0.00191 +2025-10-31 15:15:17.083558: train_loss -0.9938 +2025-10-31 15:15:17.086642: val_loss -0.8889 +2025-10-31 15:15:17.088886: Pseudo dice [np.float32(0.9837), np.float32(0.9922), np.float32(0.9953), np.float32(0.7941)] +2025-10-31 15:15:17.091007: Epoch time: 24.53 s +2025-10-31 15:15:18.304221: +2025-10-31 15:15:18.306795: Epoch 842 +2025-10-31 15:15:18.308832: Current learning rate: 0.0019 +2025-10-31 15:15:42.679771: train_loss -0.9937 +2025-10-31 15:15:42.685685: val_loss -0.8854 +2025-10-31 15:15:42.687417: Pseudo dice [np.float32(0.9849), np.float32(0.993), np.float32(0.9952), np.float32(0.7812)] +2025-10-31 15:15:42.689267: Epoch time: 24.38 s +2025-10-31 15:15:43.907955: +2025-10-31 15:15:43.909947: Epoch 843 +2025-10-31 15:15:43.911805: Current learning rate: 0.00189 +2025-10-31 15:16:09.092856: train_loss -0.9941 +2025-10-31 15:16:09.095155: val_loss -0.8868 +2025-10-31 15:16:09.096821: Pseudo dice [np.float32(0.9849), np.float32(0.9925), np.float32(0.9953), np.float32(0.7898)] +2025-10-31 15:16:09.098556: Epoch time: 25.19 s +2025-10-31 15:16:10.304615: +2025-10-31 15:16:10.306494: Epoch 844 +2025-10-31 15:16:10.308282: Current learning rate: 0.00188 +2025-10-31 15:16:35.366702: train_loss -0.9936 +2025-10-31 15:16:35.373802: val_loss -0.8917 +2025-10-31 15:16:35.375604: Pseudo dice [np.float32(0.9842), np.float32(0.9918), np.float32(0.9951), np.float32(0.8004)] +2025-10-31 15:16:35.377362: Epoch time: 25.06 s +2025-10-31 15:16:36.630431: +2025-10-31 15:16:36.632469: Epoch 845 +2025-10-31 15:16:36.634355: Current learning rate: 0.00187 +2025-10-31 15:17:01.116719: train_loss -0.9932 +2025-10-31 15:17:01.121287: val_loss -0.8897 +2025-10-31 15:17:01.124278: Pseudo dice [np.float32(0.9841), np.float32(0.9924), np.float32(0.9953), np.float32(0.7977)] +2025-10-31 15:17:01.126580: Epoch time: 24.49 s +2025-10-31 15:17:02.288995: +2025-10-31 15:17:02.291623: Epoch 846 +2025-10-31 15:17:02.293510: Current learning rate: 0.00186 +2025-10-31 15:17:26.346628: train_loss -0.9936 +2025-10-31 15:17:26.349279: val_loss -0.8854 +2025-10-31 15:17:26.350908: Pseudo dice [np.float32(0.9847), np.float32(0.9933), np.float32(0.9952), np.float32(0.7826)] +2025-10-31 15:17:26.352417: Epoch time: 24.06 s +2025-10-31 15:17:27.563869: +2025-10-31 15:17:27.566182: Epoch 847 +2025-10-31 15:17:27.567965: Current learning rate: 0.00185 +2025-10-31 15:17:52.565339: train_loss -0.9938 +2025-10-31 15:17:52.568044: val_loss -0.8915 +2025-10-31 15:17:52.569793: Pseudo dice [np.float32(0.9865), np.float32(0.9935), np.float32(0.9954), np.float32(0.7909)] +2025-10-31 15:17:52.571954: Epoch time: 25.0 s +2025-10-31 15:17:53.822471: +2025-10-31 15:17:53.824397: Epoch 848 +2025-10-31 15:17:53.826077: Current learning rate: 0.00184 +2025-10-31 15:18:18.272836: train_loss -0.9937 +2025-10-31 15:18:18.275159: val_loss -0.8956 +2025-10-31 15:18:18.277098: Pseudo dice [np.float32(0.9847), np.float32(0.9926), np.float32(0.9956), np.float32(0.8069)] +2025-10-31 15:18:18.278989: Epoch time: 24.45 s +2025-10-31 15:18:19.384627: +2025-10-31 15:18:19.386478: Epoch 849 +2025-10-31 15:18:19.388279: Current learning rate: 0.00182 +2025-10-31 15:18:45.116028: train_loss -0.9934 +2025-10-31 15:18:45.122137: val_loss -0.8848 +2025-10-31 15:18:45.124018: Pseudo dice [np.float32(0.9844), np.float32(0.9924), np.float32(0.9947), np.float32(0.7797)] +2025-10-31 15:18:45.125542: Epoch time: 25.73 s +2025-10-31 15:18:47.972559: +2025-10-31 15:18:47.975174: Epoch 850 +2025-10-31 15:18:47.977077: Current learning rate: 0.00181 +2025-10-31 15:19:11.461035: train_loss -0.9936 +2025-10-31 15:19:11.464199: val_loss -0.8892 +2025-10-31 15:19:11.465909: Pseudo dice [np.float32(0.9849), np.float32(0.9923), np.float32(0.9952), np.float32(0.7904)] +2025-10-31 15:19:11.467635: Epoch time: 23.49 s +2025-10-31 15:19:12.709505: +2025-10-31 15:19:12.711821: Epoch 851 +2025-10-31 15:19:12.713590: Current learning rate: 0.0018 +2025-10-31 15:19:40.772743: train_loss -0.9936 +2025-10-31 15:19:40.779084: val_loss -0.886 +2025-10-31 15:19:40.780984: Pseudo dice [np.float32(0.9857), np.float32(0.9931), np.float32(0.9951), np.float32(0.7751)] +2025-10-31 15:19:40.783434: Epoch time: 28.06 s +2025-10-31 15:19:41.998983: +2025-10-31 15:19:42.001234: Epoch 852 +2025-10-31 15:19:42.003443: Current learning rate: 0.00179 +2025-10-31 15:20:08.697920: train_loss -0.9932 +2025-10-31 15:20:08.700956: val_loss -0.8897 +2025-10-31 15:20:08.702491: Pseudo dice [np.float32(0.9856), np.float32(0.9927), np.float32(0.9952), np.float32(0.7888)] +2025-10-31 15:20:08.704237: Epoch time: 26.7 s +2025-10-31 15:20:09.895344: +2025-10-31 15:20:09.897664: Epoch 853 +2025-10-31 15:20:09.899325: Current learning rate: 0.00178 +2025-10-31 15:20:36.153033: train_loss -0.9939 +2025-10-31 15:20:36.154987: val_loss -0.8755 +2025-10-31 15:20:36.157021: Pseudo dice [np.float32(0.9846), np.float32(0.9923), np.float32(0.9949), np.float32(0.7634)] +2025-10-31 15:20:36.158698: Epoch time: 26.26 s +2025-10-31 15:20:37.326065: +2025-10-31 15:20:37.328057: Epoch 854 +2025-10-31 15:20:37.329863: Current learning rate: 0.00177 +2025-10-31 15:21:01.508421: train_loss -0.9932 +2025-10-31 15:21:01.511412: val_loss -0.8903 +2025-10-31 15:21:01.513365: Pseudo dice [np.float32(0.9853), np.float32(0.9923), np.float32(0.9952), np.float32(0.8032)] +2025-10-31 15:21:01.515975: Epoch time: 24.18 s +2025-10-31 15:21:02.727919: +2025-10-31 15:21:02.730086: Epoch 855 +2025-10-31 15:21:02.731741: Current learning rate: 0.00176 +2025-10-31 15:21:28.297704: train_loss -0.9935 +2025-10-31 15:21:28.300026: val_loss -0.8805 +2025-10-31 15:21:28.301441: Pseudo dice [np.float32(0.9857), np.float32(0.9927), np.float32(0.9948), np.float32(0.7719)] +2025-10-31 15:21:28.303229: Epoch time: 25.57 s +2025-10-31 15:21:29.501984: +2025-10-31 15:21:29.503595: Epoch 856 +2025-10-31 15:21:29.504939: Current learning rate: 0.00175 +2025-10-31 15:21:56.204871: train_loss -0.9939 +2025-10-31 15:21:56.216064: val_loss -0.8882 +2025-10-31 15:21:56.220812: Pseudo dice [np.float32(0.9857), np.float32(0.9928), np.float32(0.9953), np.float32(0.7819)] +2025-10-31 15:21:56.229300: Epoch time: 26.7 s +2025-10-31 15:21:57.477202: +2025-10-31 15:21:57.479441: Epoch 857 +2025-10-31 15:21:57.481455: Current learning rate: 0.00174 +2025-10-31 15:22:22.575918: train_loss -0.9939 +2025-10-31 15:22:22.579059: val_loss -0.8888 +2025-10-31 15:22:22.581328: Pseudo dice [np.float32(0.9853), np.float32(0.9927), np.float32(0.9955), np.float32(0.7892)] +2025-10-31 15:22:22.583148: Epoch time: 25.1 s +2025-10-31 15:22:23.851248: +2025-10-31 15:22:23.853485: Epoch 858 +2025-10-31 15:22:23.855368: Current learning rate: 0.00173 +2025-10-31 15:22:50.387373: train_loss -0.9937 +2025-10-31 15:22:50.389683: val_loss -0.8838 +2025-10-31 15:22:50.391265: Pseudo dice [np.float32(0.9843), np.float32(0.9927), np.float32(0.9952), np.float32(0.7784)] +2025-10-31 15:22:50.392789: Epoch time: 26.54 s +2025-10-31 15:22:51.596290: +2025-10-31 15:22:51.598089: Epoch 859 +2025-10-31 15:22:51.599973: Current learning rate: 0.00172 +2025-10-31 15:23:15.843627: train_loss -0.9938 +2025-10-31 15:23:15.845858: val_loss -0.8835 +2025-10-31 15:23:15.847457: Pseudo dice [np.float32(0.9852), np.float32(0.9928), np.float32(0.9947), np.float32(0.7809)] +2025-10-31 15:23:15.848989: Epoch time: 24.25 s +2025-10-31 15:23:17.064789: +2025-10-31 15:23:17.066876: Epoch 860 +2025-10-31 15:23:17.068664: Current learning rate: 0.0017 +2025-10-31 15:23:43.474530: train_loss -0.9939 +2025-10-31 15:23:43.483958: val_loss -0.884 +2025-10-31 15:23:43.485645: Pseudo dice [np.float32(0.986), np.float32(0.9931), np.float32(0.995), np.float32(0.7802)] +2025-10-31 15:23:43.487357: Epoch time: 26.41 s +2025-10-31 15:23:44.775895: +2025-10-31 15:23:44.777606: Epoch 861 +2025-10-31 15:23:44.779124: Current learning rate: 0.00169 +2025-10-31 15:24:08.894084: train_loss -0.9936 +2025-10-31 15:24:08.910159: val_loss -0.8868 +2025-10-31 15:24:08.913049: Pseudo dice [np.float32(0.9863), np.float32(0.9932), np.float32(0.9953), np.float32(0.7828)] +2025-10-31 15:24:08.915261: Epoch time: 24.12 s +2025-10-31 15:24:10.144415: +2025-10-31 15:24:10.146128: Epoch 862 +2025-10-31 15:24:10.148039: Current learning rate: 0.00168 +2025-10-31 15:24:34.305641: train_loss -0.9939 +2025-10-31 15:24:34.308163: val_loss -0.8829 +2025-10-31 15:24:34.309801: Pseudo dice [np.float32(0.9864), np.float32(0.9927), np.float32(0.9949), np.float32(0.7717)] +2025-10-31 15:24:34.311510: Epoch time: 24.16 s +2025-10-31 15:24:35.536139: +2025-10-31 15:24:35.540226: Epoch 863 +2025-10-31 15:24:35.542578: Current learning rate: 0.00167 +2025-10-31 15:25:00.712743: train_loss -0.9938 +2025-10-31 15:25:00.715321: val_loss -0.8866 +2025-10-31 15:25:00.717325: Pseudo dice [np.float32(0.9845), np.float32(0.9924), np.float32(0.9951), np.float32(0.7837)] +2025-10-31 15:25:00.719085: Epoch time: 25.18 s +2025-10-31 15:25:02.332125: +2025-10-31 15:25:02.334127: Epoch 864 +2025-10-31 15:25:02.335865: Current learning rate: 0.00166 +2025-10-31 15:25:26.038528: train_loss -0.9933 +2025-10-31 15:25:26.041598: val_loss -0.8919 +2025-10-31 15:25:26.043320: Pseudo dice [np.float32(0.9866), np.float32(0.9931), np.float32(0.9955), np.float32(0.7873)] +2025-10-31 15:25:26.045151: Epoch time: 23.71 s +2025-10-31 15:25:27.286535: +2025-10-31 15:25:27.288693: Epoch 865 +2025-10-31 15:25:27.290803: Current learning rate: 0.00165 +2025-10-31 15:25:54.131565: train_loss -0.9937 +2025-10-31 15:25:54.133770: val_loss -0.8911 +2025-10-31 15:25:54.135446: Pseudo dice [np.float32(0.9845), np.float32(0.993), np.float32(0.9952), np.float32(0.7969)] +2025-10-31 15:25:54.136938: Epoch time: 26.85 s +2025-10-31 15:25:55.353649: +2025-10-31 15:25:55.355732: Epoch 866 +2025-10-31 15:25:55.357398: Current learning rate: 0.00164 +2025-10-31 15:26:19.746037: train_loss -0.9939 +2025-10-31 15:26:19.752106: val_loss -0.8886 +2025-10-31 15:26:19.754027: Pseudo dice [np.float32(0.9847), np.float32(0.9926), np.float32(0.9954), np.float32(0.7898)] +2025-10-31 15:26:19.755772: Epoch time: 24.39 s +2025-10-31 15:26:20.948439: +2025-10-31 15:26:20.954901: Epoch 867 +2025-10-31 15:26:20.964243: Current learning rate: 0.00163 +2025-10-31 15:26:45.791991: train_loss -0.9938 +2025-10-31 15:26:45.794602: val_loss -0.8916 +2025-10-31 15:26:45.796862: Pseudo dice [np.float32(0.9842), np.float32(0.9924), np.float32(0.9954), np.float32(0.7983)] +2025-10-31 15:26:45.798777: Epoch time: 24.84 s +2025-10-31 15:26:47.059597: +2025-10-31 15:26:47.062115: Epoch 868 +2025-10-31 15:26:47.064078: Current learning rate: 0.00162 +2025-10-31 15:27:13.729539: train_loss -0.9934 +2025-10-31 15:27:13.732817: val_loss -0.8889 +2025-10-31 15:27:13.735054: Pseudo dice [np.float32(0.9853), np.float32(0.9928), np.float32(0.9952), np.float32(0.7932)] +2025-10-31 15:27:13.737450: Epoch time: 26.67 s +2025-10-31 15:27:14.942779: +2025-10-31 15:27:14.944896: Epoch 869 +2025-10-31 15:27:14.946435: Current learning rate: 0.00161 +2025-10-31 15:27:39.764300: train_loss -0.994 +2025-10-31 15:27:39.768113: val_loss -0.8888 +2025-10-31 15:27:39.770308: Pseudo dice [np.float32(0.9852), np.float32(0.9926), np.float32(0.9954), np.float32(0.7941)] +2025-10-31 15:27:39.772491: Epoch time: 24.82 s +2025-10-31 15:27:40.967410: +2025-10-31 15:27:40.969566: Epoch 870 +2025-10-31 15:27:40.971403: Current learning rate: 0.00159 +2025-10-31 15:28:05.177506: train_loss -0.9938 +2025-10-31 15:28:05.182991: val_loss -0.883 +2025-10-31 15:28:05.184459: Pseudo dice [np.float32(0.9855), np.float32(0.9931), np.float32(0.9951), np.float32(0.7792)] +2025-10-31 15:28:05.185830: Epoch time: 24.21 s +2025-10-31 15:28:06.324536: +2025-10-31 15:28:06.326358: Epoch 871 +2025-10-31 15:28:06.328047: Current learning rate: 0.00158 +2025-10-31 15:28:27.319142: train_loss -0.9934 +2025-10-31 15:28:27.322252: val_loss -0.8852 +2025-10-31 15:28:27.324249: Pseudo dice [np.float32(0.9856), np.float32(0.9929), np.float32(0.995), np.float32(0.7795)] +2025-10-31 15:28:27.326208: Epoch time: 21.0 s +2025-10-31 15:28:28.415011: +2025-10-31 15:28:28.417292: Epoch 872 +2025-10-31 15:28:28.419075: Current learning rate: 0.00157 +2025-10-31 15:28:52.621976: train_loss -0.9941 +2025-10-31 15:28:52.625152: val_loss -0.8869 +2025-10-31 15:28:52.627025: Pseudo dice [np.float32(0.9853), np.float32(0.993), np.float32(0.9952), np.float32(0.7917)] +2025-10-31 15:28:52.628897: Epoch time: 24.21 s +2025-10-31 15:28:53.823059: +2025-10-31 15:28:53.825132: Epoch 873 +2025-10-31 15:28:53.826899: Current learning rate: 0.00156 +2025-10-31 15:29:17.912963: train_loss -0.9939 +2025-10-31 15:29:17.916736: val_loss -0.8936 +2025-10-31 15:29:17.918642: Pseudo dice [np.float32(0.9852), np.float32(0.9928), np.float32(0.9957), np.float32(0.7975)] +2025-10-31 15:29:17.920578: Epoch time: 24.09 s +2025-10-31 15:29:19.149000: +2025-10-31 15:29:19.151028: Epoch 874 +2025-10-31 15:29:19.152889: Current learning rate: 0.00155 +2025-10-31 15:29:44.433406: train_loss -0.9933 +2025-10-31 15:29:44.436631: val_loss -0.8923 +2025-10-31 15:29:44.438783: Pseudo dice [np.float32(0.9857), np.float32(0.9928), np.float32(0.9954), np.float32(0.8)] +2025-10-31 15:29:44.441263: Epoch time: 25.29 s +2025-10-31 15:29:45.729086: +2025-10-31 15:29:45.730981: Epoch 875 +2025-10-31 15:29:45.732973: Current learning rate: 0.00154 +2025-10-31 15:30:11.928259: train_loss -0.9939 +2025-10-31 15:30:11.933840: val_loss -0.8811 +2025-10-31 15:30:11.935381: Pseudo dice [np.float32(0.985), np.float32(0.9923), np.float32(0.9949), np.float32(0.7732)] +2025-10-31 15:30:11.936947: Epoch time: 26.2 s +2025-10-31 15:30:13.170594: +2025-10-31 15:30:13.172770: Epoch 876 +2025-10-31 15:30:13.174446: Current learning rate: 0.00153 +2025-10-31 15:30:39.351953: train_loss -0.993 +2025-10-31 15:30:39.356191: val_loss -0.8905 +2025-10-31 15:30:39.358002: Pseudo dice [np.float32(0.9847), np.float32(0.9928), np.float32(0.9956), np.float32(0.7965)] +2025-10-31 15:30:39.359950: Epoch time: 26.18 s +2025-10-31 15:30:41.048507: +2025-10-31 15:30:41.050802: Epoch 877 +2025-10-31 15:30:41.052890: Current learning rate: 0.00152 +2025-10-31 15:31:06.704227: train_loss -0.9941 +2025-10-31 15:31:06.706598: val_loss -0.8826 +2025-10-31 15:31:06.708708: Pseudo dice [np.float32(0.9859), np.float32(0.9929), np.float32(0.995), np.float32(0.7753)] +2025-10-31 15:31:06.710736: Epoch time: 25.66 s +2025-10-31 15:31:07.892914: +2025-10-31 15:31:07.894883: Epoch 878 +2025-10-31 15:31:07.896623: Current learning rate: 0.00151 +2025-10-31 15:31:34.848082: train_loss -0.9945 +2025-10-31 15:31:34.851627: val_loss -0.8741 +2025-10-31 15:31:34.853512: Pseudo dice [np.float32(0.9853), np.float32(0.9927), np.float32(0.9945), np.float32(0.7592)] +2025-10-31 15:31:34.855449: Epoch time: 26.96 s +2025-10-31 15:31:36.010603: +2025-10-31 15:31:36.013131: Epoch 879 +2025-10-31 15:31:36.015532: Current learning rate: 0.00149 +2025-10-31 15:31:59.579850: train_loss -0.9936 +2025-10-31 15:31:59.585335: val_loss -0.8829 +2025-10-31 15:31:59.586766: Pseudo dice [np.float32(0.9845), np.float32(0.9924), np.float32(0.9947), np.float32(0.772)] +2025-10-31 15:31:59.588240: Epoch time: 23.57 s +2025-10-31 15:32:00.855146: +2025-10-31 15:32:00.866512: Epoch 880 +2025-10-31 15:32:00.874600: Current learning rate: 0.00148 +2025-10-31 15:32:23.535303: train_loss -0.9937 +2025-10-31 15:32:23.538053: val_loss -0.8845 +2025-10-31 15:32:23.540263: Pseudo dice [np.float32(0.9846), np.float32(0.9927), np.float32(0.9947), np.float32(0.7814)] +2025-10-31 15:32:23.542123: Epoch time: 22.68 s +2025-10-31 15:32:24.639267: +2025-10-31 15:32:24.641187: Epoch 881 +2025-10-31 15:32:24.643435: Current learning rate: 0.00147 +2025-10-31 15:32:49.186450: train_loss -0.9936 +2025-10-31 15:32:49.189473: val_loss -0.879 +2025-10-31 15:32:49.191320: Pseudo dice [np.float32(0.9844), np.float32(0.9926), np.float32(0.9943), np.float32(0.772)] +2025-10-31 15:32:49.192886: Epoch time: 24.55 s +2025-10-31 15:32:50.417442: +2025-10-31 15:32:50.428659: Epoch 882 +2025-10-31 15:32:50.436215: Current learning rate: 0.00146 +2025-10-31 15:33:15.545416: train_loss -0.9935 +2025-10-31 15:33:15.547963: val_loss -0.8872 +2025-10-31 15:33:15.549563: Pseudo dice [np.float32(0.9853), np.float32(0.9929), np.float32(0.995), np.float32(0.7865)] +2025-10-31 15:33:15.551139: Epoch time: 25.13 s +2025-10-31 15:33:16.832891: +2025-10-31 15:33:16.834836: Epoch 883 +2025-10-31 15:33:16.836548: Current learning rate: 0.00145 +2025-10-31 15:33:42.072954: train_loss -0.9944 +2025-10-31 15:33:42.075796: val_loss -0.8818 +2025-10-31 15:33:42.077642: Pseudo dice [np.float32(0.9857), np.float32(0.9932), np.float32(0.995), np.float32(0.7749)] +2025-10-31 15:33:42.079427: Epoch time: 25.24 s +2025-10-31 15:33:43.193228: +2025-10-31 15:33:43.195243: Epoch 884 +2025-10-31 15:33:43.196943: Current learning rate: 0.00144 +2025-10-31 15:34:09.305565: train_loss -0.9936 +2025-10-31 15:34:09.309880: val_loss -0.8869 +2025-10-31 15:34:09.312004: Pseudo dice [np.float32(0.986), np.float32(0.9933), np.float32(0.995), np.float32(0.7879)] +2025-10-31 15:34:09.314254: Epoch time: 26.11 s +2025-10-31 15:34:10.516050: +2025-10-31 15:34:10.518146: Epoch 885 +2025-10-31 15:34:10.519983: Current learning rate: 0.00143 +2025-10-31 15:34:36.959938: train_loss -0.9937 +2025-10-31 15:34:36.963798: val_loss -0.8844 +2025-10-31 15:34:36.965491: Pseudo dice [np.float32(0.9859), np.float32(0.9932), np.float32(0.9949), np.float32(0.7764)] +2025-10-31 15:34:36.967136: Epoch time: 26.45 s +2025-10-31 15:34:38.193034: +2025-10-31 15:34:38.195961: Epoch 886 +2025-10-31 15:34:38.198085: Current learning rate: 0.00142 +2025-10-31 15:35:01.744939: train_loss -0.994 +2025-10-31 15:35:01.747302: val_loss -0.8869 +2025-10-31 15:35:01.749040: Pseudo dice [np.float32(0.9851), np.float32(0.993), np.float32(0.9953), np.float32(0.7888)] +2025-10-31 15:35:01.750698: Epoch time: 23.55 s +2025-10-31 15:35:03.008234: +2025-10-31 15:35:03.011133: Epoch 887 +2025-10-31 15:35:03.015191: Current learning rate: 0.00141 +2025-10-31 15:35:28.258564: train_loss -0.9941 +2025-10-31 15:35:28.263342: val_loss -0.8845 +2025-10-31 15:35:28.265549: Pseudo dice [np.float32(0.9839), np.float32(0.9927), np.float32(0.9951), np.float32(0.7873)] +2025-10-31 15:35:28.267515: Epoch time: 25.25 s +2025-10-31 15:35:29.486980: +2025-10-31 15:35:29.489110: Epoch 888 +2025-10-31 15:35:29.490957: Current learning rate: 0.00139 +2025-10-31 15:35:54.545858: train_loss -0.9939 +2025-10-31 15:35:54.550075: val_loss -0.8865 +2025-10-31 15:35:54.552483: Pseudo dice [np.float32(0.9845), np.float32(0.9929), np.float32(0.9951), np.float32(0.7875)] +2025-10-31 15:35:54.559246: Epoch time: 25.06 s +2025-10-31 15:35:55.836285: +2025-10-31 15:35:55.849553: Epoch 889 +2025-10-31 15:35:55.857598: Current learning rate: 0.00138 +2025-10-31 15:36:22.647336: train_loss -0.9938 +2025-10-31 15:36:22.649653: val_loss -0.8862 +2025-10-31 15:36:22.651505: Pseudo dice [np.float32(0.9851), np.float32(0.9928), np.float32(0.9952), np.float32(0.78)] +2025-10-31 15:36:22.653238: Epoch time: 26.81 s +2025-10-31 15:36:24.227541: +2025-10-31 15:36:24.229617: Epoch 890 +2025-10-31 15:36:24.231510: Current learning rate: 0.00137 +2025-10-31 15:36:49.136940: train_loss -0.9942 +2025-10-31 15:36:49.139985: val_loss -0.8835 +2025-10-31 15:36:49.141819: Pseudo dice [np.float32(0.9857), np.float32(0.9929), np.float32(0.9951), np.float32(0.7757)] +2025-10-31 15:36:49.143717: Epoch time: 24.91 s +2025-10-31 15:36:50.380094: +2025-10-31 15:36:50.382131: Epoch 891 +2025-10-31 15:36:50.383929: Current learning rate: 0.00136 +2025-10-31 15:37:15.740634: train_loss -0.9938 +2025-10-31 15:37:15.744195: val_loss -0.8828 +2025-10-31 15:37:15.746520: Pseudo dice [np.float32(0.986), np.float32(0.9932), np.float32(0.9949), np.float32(0.7765)] +2025-10-31 15:37:15.748118: Epoch time: 25.36 s +2025-10-31 15:37:16.937040: +2025-10-31 15:37:16.938935: Epoch 892 +2025-10-31 15:37:16.940670: Current learning rate: 0.00135 +2025-10-31 15:37:43.389624: train_loss -0.9936 +2025-10-31 15:37:43.392858: val_loss -0.8873 +2025-10-31 15:37:43.395064: Pseudo dice [np.float32(0.9859), np.float32(0.9932), np.float32(0.9952), np.float32(0.7831)] +2025-10-31 15:37:43.397222: Epoch time: 26.45 s +2025-10-31 15:37:44.612813: +2025-10-31 15:37:44.614806: Epoch 893 +2025-10-31 15:37:44.616818: Current learning rate: 0.00134 +2025-10-31 15:38:07.337019: train_loss -0.9942 +2025-10-31 15:38:07.340427: val_loss -0.8835 +2025-10-31 15:38:07.342623: Pseudo dice [np.float32(0.985), np.float32(0.993), np.float32(0.9952), np.float32(0.7832)] +2025-10-31 15:38:07.344583: Epoch time: 22.73 s +2025-10-31 15:38:08.552629: +2025-10-31 15:38:08.555176: Epoch 894 +2025-10-31 15:38:08.557390: Current learning rate: 0.00133 +2025-10-31 15:38:34.216119: train_loss -0.9938 +2025-10-31 15:38:34.219219: val_loss -0.8866 +2025-10-31 15:38:34.221031: Pseudo dice [np.float32(0.9855), np.float32(0.9933), np.float32(0.9951), np.float32(0.7847)] +2025-10-31 15:38:34.223323: Epoch time: 25.67 s +2025-10-31 15:38:35.502655: +2025-10-31 15:38:35.504566: Epoch 895 +2025-10-31 15:38:35.506343: Current learning rate: 0.00132 +2025-10-31 15:39:01.324589: train_loss -0.9931 +2025-10-31 15:39:01.328868: val_loss -0.8796 +2025-10-31 15:39:01.330382: Pseudo dice [np.float32(0.9863), np.float32(0.993), np.float32(0.9947), np.float32(0.7657)] +2025-10-31 15:39:01.331861: Epoch time: 25.82 s +2025-10-31 15:39:02.537154: +2025-10-31 15:39:02.539423: Epoch 896 +2025-10-31 15:39:02.541180: Current learning rate: 0.0013 +2025-10-31 15:39:28.210843: train_loss -0.9938 +2025-10-31 15:39:28.213853: val_loss -0.8827 +2025-10-31 15:39:28.215503: Pseudo dice [np.float32(0.985), np.float32(0.9929), np.float32(0.9952), np.float32(0.7828)] +2025-10-31 15:39:28.217185: Epoch time: 25.68 s +2025-10-31 15:39:29.399637: +2025-10-31 15:39:29.402175: Epoch 897 +2025-10-31 15:39:29.404205: Current learning rate: 0.00129 +2025-10-31 15:39:54.828983: train_loss -0.9944 +2025-10-31 15:39:54.831591: val_loss -0.8803 +2025-10-31 15:39:54.833260: Pseudo dice [np.float32(0.9862), np.float32(0.9936), np.float32(0.9947), np.float32(0.7659)] +2025-10-31 15:39:54.834788: Epoch time: 25.43 s +2025-10-31 15:39:56.073007: +2025-10-31 15:39:56.075063: Epoch 898 +2025-10-31 15:39:56.077343: Current learning rate: 0.00128 +2025-10-31 15:40:21.943264: train_loss -0.9945 +2025-10-31 15:40:21.945629: val_loss -0.8903 +2025-10-31 15:40:21.947478: Pseudo dice [np.float32(0.9868), np.float32(0.9938), np.float32(0.9956), np.float32(0.7902)] +2025-10-31 15:40:21.949201: Epoch time: 25.87 s +2025-10-31 15:40:23.104041: +2025-10-31 15:40:23.106152: Epoch 899 +2025-10-31 15:40:23.107690: Current learning rate: 0.00127 +2025-10-31 15:40:46.531608: train_loss -0.9943 +2025-10-31 15:40:46.534606: val_loss -0.8842 +2025-10-31 15:40:46.536501: Pseudo dice [np.float32(0.9855), np.float32(0.9931), np.float32(0.9953), np.float32(0.7799)] +2025-10-31 15:40:46.541539: Epoch time: 23.43 s +2025-10-31 15:40:49.058557: +2025-10-31 15:40:49.060398: Epoch 900 +2025-10-31 15:40:49.061893: Current learning rate: 0.00126 +2025-10-31 15:41:11.352711: train_loss -0.994 +2025-10-31 15:41:11.358920: val_loss -0.8776 +2025-10-31 15:41:11.360781: Pseudo dice [np.float32(0.9858), np.float32(0.9931), np.float32(0.9946), np.float32(0.764)] +2025-10-31 15:41:11.362587: Epoch time: 22.3 s +2025-10-31 15:41:12.520354: +2025-10-31 15:41:12.522535: Epoch 901 +2025-10-31 15:41:12.524913: Current learning rate: 0.00125 +2025-10-31 15:41:39.471989: train_loss -0.9944 +2025-10-31 15:41:39.473967: val_loss -0.8867 +2025-10-31 15:41:39.475435: Pseudo dice [np.float32(0.9854), np.float32(0.9926), np.float32(0.9952), np.float32(0.7851)] +2025-10-31 15:41:39.476862: Epoch time: 26.95 s +2025-10-31 15:41:40.688318: +2025-10-31 15:41:40.690392: Epoch 902 +2025-10-31 15:41:40.692313: Current learning rate: 0.00124 +2025-10-31 15:42:06.421278: train_loss -0.9943 +2025-10-31 15:42:06.423833: val_loss -0.8902 +2025-10-31 15:42:06.425832: Pseudo dice [np.float32(0.9856), np.float32(0.9929), np.float32(0.9955), np.float32(0.7926)] +2025-10-31 15:42:06.427538: Epoch time: 25.74 s +2025-10-31 15:42:08.251575: +2025-10-31 15:42:08.253915: Epoch 903 +2025-10-31 15:42:08.255922: Current learning rate: 0.00122 +2025-10-31 15:42:33.096879: train_loss -0.9943 +2025-10-31 15:42:33.105636: val_loss -0.8832 +2025-10-31 15:42:33.107573: Pseudo dice [np.float32(0.9851), np.float32(0.9926), np.float32(0.995), np.float32(0.7789)] +2025-10-31 15:42:33.109499: Epoch time: 24.85 s +2025-10-31 15:42:34.286350: +2025-10-31 15:42:34.291660: Epoch 904 +2025-10-31 15:42:34.303918: Current learning rate: 0.00121 +2025-10-31 15:43:00.247255: train_loss -0.9944 +2025-10-31 15:43:00.250273: val_loss -0.8889 +2025-10-31 15:43:00.251972: Pseudo dice [np.float32(0.9856), np.float32(0.9931), np.float32(0.9955), np.float32(0.7918)] +2025-10-31 15:43:00.255842: Epoch time: 25.97 s +2025-10-31 15:43:01.828662: +2025-10-31 15:43:01.831913: Epoch 905 +2025-10-31 15:43:01.833600: Current learning rate: 0.0012 +2025-10-31 15:43:24.843784: train_loss -0.9944 +2025-10-31 15:43:24.856820: val_loss -0.8879 +2025-10-31 15:43:24.864534: Pseudo dice [np.float32(0.9855), np.float32(0.9931), np.float32(0.9955), np.float32(0.7853)] +2025-10-31 15:43:24.872177: Epoch time: 23.02 s +2025-10-31 15:43:26.127581: +2025-10-31 15:43:26.134629: Epoch 906 +2025-10-31 15:43:26.142530: Current learning rate: 0.00119 +2025-10-31 15:43:47.041433: train_loss -0.9941 +2025-10-31 15:43:47.044093: val_loss -0.888 +2025-10-31 15:43:47.045691: Pseudo dice [np.float32(0.9848), np.float32(0.9926), np.float32(0.9954), np.float32(0.7973)] +2025-10-31 15:43:47.047550: Epoch time: 20.92 s +2025-10-31 15:43:48.278155: +2025-10-31 15:43:48.281854: Epoch 907 +2025-10-31 15:43:48.284019: Current learning rate: 0.00118 +2025-10-31 15:44:11.449420: train_loss -0.9942 +2025-10-31 15:44:11.455307: val_loss -0.8874 +2025-10-31 15:44:11.459763: Pseudo dice [np.float32(0.986), np.float32(0.9933), np.float32(0.9955), np.float32(0.7931)] +2025-10-31 15:44:11.461910: Epoch time: 23.18 s +2025-10-31 15:44:12.690175: +2025-10-31 15:44:12.692189: Epoch 908 +2025-10-31 15:44:12.694222: Current learning rate: 0.00117 +2025-10-31 15:44:37.806432: train_loss -0.9941 +2025-10-31 15:44:37.808813: val_loss -0.882 +2025-10-31 15:44:37.810710: Pseudo dice [np.float32(0.9851), np.float32(0.9929), np.float32(0.9949), np.float32(0.7796)] +2025-10-31 15:44:37.815440: Epoch time: 25.12 s +2025-10-31 15:44:38.949941: +2025-10-31 15:44:38.952264: Epoch 909 +2025-10-31 15:44:38.954090: Current learning rate: 0.00116 +2025-10-31 15:45:06.681901: train_loss -0.9936 +2025-10-31 15:45:06.684987: val_loss -0.8827 +2025-10-31 15:45:06.686944: Pseudo dice [np.float32(0.9856), np.float32(0.9924), np.float32(0.9949), np.float32(0.7795)] +2025-10-31 15:45:06.688802: Epoch time: 27.73 s +2025-10-31 15:45:07.915428: +2025-10-31 15:45:07.917801: Epoch 910 +2025-10-31 15:45:07.919607: Current learning rate: 0.00115 +2025-10-31 15:45:34.550642: train_loss -0.9939 +2025-10-31 15:45:34.552803: val_loss -0.8889 +2025-10-31 15:45:34.554214: Pseudo dice [np.float32(0.9852), np.float32(0.9928), np.float32(0.9953), np.float32(0.7943)] +2025-10-31 15:45:34.555677: Epoch time: 26.64 s +2025-10-31 15:45:35.768412: +2025-10-31 15:45:35.772218: Epoch 911 +2025-10-31 15:45:35.775270: Current learning rate: 0.00113 +2025-10-31 15:46:02.386840: train_loss -0.9943 +2025-10-31 15:46:02.389657: val_loss -0.8857 +2025-10-31 15:46:02.391345: Pseudo dice [np.float32(0.9848), np.float32(0.9925), np.float32(0.995), np.float32(0.7876)] +2025-10-31 15:46:02.392920: Epoch time: 26.62 s +2025-10-31 15:46:03.756814: +2025-10-31 15:46:03.758613: Epoch 912 +2025-10-31 15:46:03.760003: Current learning rate: 0.00112 +2025-10-31 15:46:30.880012: train_loss -0.994 +2025-10-31 15:46:30.882919: val_loss -0.8845 +2025-10-31 15:46:30.884400: Pseudo dice [np.float32(0.9851), np.float32(0.9928), np.float32(0.9951), np.float32(0.784)] +2025-10-31 15:46:30.885964: Epoch time: 27.13 s +2025-10-31 15:46:32.046588: +2025-10-31 15:46:32.048305: Epoch 913 +2025-10-31 15:46:32.049874: Current learning rate: 0.00111 +2025-10-31 15:46:59.130190: train_loss -0.9942 +2025-10-31 15:46:59.132603: val_loss -0.8891 +2025-10-31 15:46:59.134494: Pseudo dice [np.float32(0.9857), np.float32(0.9929), np.float32(0.9954), np.float32(0.7959)] +2025-10-31 15:46:59.136260: Epoch time: 27.08 s +2025-10-31 15:47:00.354924: +2025-10-31 15:47:00.358345: Epoch 914 +2025-10-31 15:47:00.362269: Current learning rate: 0.0011 +2025-10-31 15:47:22.976141: train_loss -0.9945 +2025-10-31 15:47:22.981719: val_loss -0.885 +2025-10-31 15:47:22.983447: Pseudo dice [np.float32(0.9854), np.float32(0.9927), np.float32(0.9952), np.float32(0.78)] +2025-10-31 15:47:22.984978: Epoch time: 22.62 s +2025-10-31 15:47:24.173816: +2025-10-31 15:47:24.182765: Epoch 915 +2025-10-31 15:47:24.184635: Current learning rate: 0.00109 +2025-10-31 15:47:49.781953: train_loss -0.9943 +2025-10-31 15:47:49.785122: val_loss -0.8832 +2025-10-31 15:47:49.788590: Pseudo dice [np.float32(0.984), np.float32(0.9927), np.float32(0.9952), np.float32(0.787)] +2025-10-31 15:47:49.791380: Epoch time: 25.61 s +2025-10-31 15:47:50.887949: +2025-10-31 15:47:50.889820: Epoch 916 +2025-10-31 15:47:50.895239: Current learning rate: 0.00108 +2025-10-31 15:48:17.985944: train_loss -0.9937 +2025-10-31 15:48:17.988177: val_loss -0.8758 +2025-10-31 15:48:17.993466: Pseudo dice [np.float32(0.9861), np.float32(0.9934), np.float32(0.9948), np.float32(0.7602)] +2025-10-31 15:48:17.995245: Epoch time: 27.1 s +2025-10-31 15:48:19.760384: +2025-10-31 15:48:19.762766: Epoch 917 +2025-10-31 15:48:19.764656: Current learning rate: 0.00106 +2025-10-31 15:48:45.150877: train_loss -0.9945 +2025-10-31 15:48:45.153262: val_loss -0.888 +2025-10-31 15:48:45.154940: Pseudo dice [np.float32(0.9857), np.float32(0.9934), np.float32(0.9955), np.float32(0.7889)] +2025-10-31 15:48:45.156547: Epoch time: 25.39 s +2025-10-31 15:48:46.321560: +2025-10-31 15:48:46.323325: Epoch 918 +2025-10-31 15:48:46.324876: Current learning rate: 0.00105 +2025-10-31 15:49:11.158784: train_loss -0.9941 +2025-10-31 15:49:11.161439: val_loss -0.8848 +2025-10-31 15:49:11.163355: Pseudo dice [np.float32(0.9859), np.float32(0.9932), np.float32(0.9955), np.float32(0.7827)] +2025-10-31 15:49:11.165129: Epoch time: 24.84 s +2025-10-31 15:49:12.437579: +2025-10-31 15:49:12.440158: Epoch 919 +2025-10-31 15:49:12.441735: Current learning rate: 0.00104 +2025-10-31 15:49:37.974166: train_loss -0.9943 +2025-10-31 15:49:37.977246: val_loss -0.8865 +2025-10-31 15:49:37.979159: Pseudo dice [np.float32(0.9853), np.float32(0.9925), np.float32(0.9951), np.float32(0.791)] +2025-10-31 15:49:37.980903: Epoch time: 25.54 s +2025-10-31 15:49:39.111192: +2025-10-31 15:49:39.113376: Epoch 920 +2025-10-31 15:49:39.115368: Current learning rate: 0.00103 +2025-10-31 15:50:04.281955: train_loss -0.9946 +2025-10-31 15:50:04.284277: val_loss -0.8807 +2025-10-31 15:50:04.286330: Pseudo dice [np.float32(0.9853), np.float32(0.9929), np.float32(0.9951), np.float32(0.7754)] +2025-10-31 15:50:04.288158: Epoch time: 25.17 s +2025-10-31 15:50:05.375261: +2025-10-31 15:50:05.377511: Epoch 921 +2025-10-31 15:50:05.379231: Current learning rate: 0.00102 +2025-10-31 15:50:30.312666: train_loss -0.9939 +2025-10-31 15:50:30.315104: val_loss -0.885 +2025-10-31 15:50:30.317008: Pseudo dice [np.float32(0.9856), np.float32(0.9933), np.float32(0.9951), np.float32(0.7876)] +2025-10-31 15:50:30.318498: Epoch time: 24.94 s +2025-10-31 15:50:31.573186: +2025-10-31 15:50:31.575259: Epoch 922 +2025-10-31 15:50:31.577534: Current learning rate: 0.00101 +2025-10-31 15:50:54.683743: train_loss -0.9942 +2025-10-31 15:50:54.687464: val_loss -0.8841 +2025-10-31 15:50:54.689482: Pseudo dice [np.float32(0.9869), np.float32(0.9935), np.float32(0.995), np.float32(0.7783)] +2025-10-31 15:50:54.691567: Epoch time: 23.11 s +2025-10-31 15:50:55.924961: +2025-10-31 15:50:55.927479: Epoch 923 +2025-10-31 15:50:55.930158: Current learning rate: 0.001 +2025-10-31 15:51:20.803958: train_loss -0.9942 +2025-10-31 15:51:20.807281: val_loss -0.889 +2025-10-31 15:51:20.809132: Pseudo dice [np.float32(0.9846), np.float32(0.993), np.float32(0.9956), np.float32(0.7965)] +2025-10-31 15:51:20.811018: Epoch time: 24.88 s +2025-10-31 15:51:22.046154: +2025-10-31 15:51:22.047994: Epoch 924 +2025-10-31 15:51:22.049961: Current learning rate: 0.00098 +2025-10-31 15:51:49.206903: train_loss -0.9948 +2025-10-31 15:51:49.210098: val_loss -0.8811 +2025-10-31 15:51:49.211823: Pseudo dice [np.float32(0.9857), np.float32(0.9928), np.float32(0.9951), np.float32(0.7778)] +2025-10-31 15:51:49.213491: Epoch time: 27.16 s +2025-10-31 15:51:50.428276: +2025-10-31 15:51:50.430234: Epoch 925 +2025-10-31 15:51:50.431937: Current learning rate: 0.00097 +2025-10-31 15:52:17.637687: train_loss -0.9947 +2025-10-31 15:52:17.640040: val_loss -0.8775 +2025-10-31 15:52:17.641762: Pseudo dice [np.float32(0.9859), np.float32(0.9929), np.float32(0.9948), np.float32(0.7636)] +2025-10-31 15:52:17.643302: Epoch time: 27.21 s +2025-10-31 15:52:18.805042: +2025-10-31 15:52:18.806747: Epoch 926 +2025-10-31 15:52:18.808502: Current learning rate: 0.00096 +2025-10-31 15:52:45.346574: train_loss -0.9948 +2025-10-31 15:52:45.349300: val_loss -0.889 +2025-10-31 15:52:45.352275: Pseudo dice [np.float32(0.9868), np.float32(0.9933), np.float32(0.9954), np.float32(0.7864)] +2025-10-31 15:52:45.354147: Epoch time: 26.54 s +2025-10-31 15:52:46.554933: +2025-10-31 15:52:46.556513: Epoch 927 +2025-10-31 15:52:46.558162: Current learning rate: 0.00095 +2025-10-31 15:53:12.448797: train_loss -0.9945 +2025-10-31 15:53:12.454096: val_loss -0.8899 +2025-10-31 15:53:12.458578: Pseudo dice [np.float32(0.9859), np.float32(0.993), np.float32(0.9954), np.float32(0.7901)] +2025-10-31 15:53:12.462169: Epoch time: 25.89 s +2025-10-31 15:53:13.581476: +2025-10-31 15:53:13.596221: Epoch 928 +2025-10-31 15:53:13.613951: Current learning rate: 0.00094 +2025-10-31 15:53:39.054016: train_loss -0.9947 +2025-10-31 15:53:39.056391: val_loss -0.8778 +2025-10-31 15:53:39.057961: Pseudo dice [np.float32(0.9857), np.float32(0.9928), np.float32(0.9949), np.float32(0.7685)] +2025-10-31 15:53:39.059446: Epoch time: 25.47 s +2025-10-31 15:53:40.181537: +2025-10-31 15:53:40.183297: Epoch 929 +2025-10-31 15:53:40.184953: Current learning rate: 0.00092 +2025-10-31 15:54:04.646910: train_loss -0.9946 +2025-10-31 15:54:04.649259: val_loss -0.886 +2025-10-31 15:54:04.650900: Pseudo dice [np.float32(0.9849), np.float32(0.9929), np.float32(0.9953), np.float32(0.7879)] +2025-10-31 15:54:04.652576: Epoch time: 24.47 s +2025-10-31 15:54:06.426569: +2025-10-31 15:54:06.428557: Epoch 930 +2025-10-31 15:54:06.430295: Current learning rate: 0.00091 +2025-10-31 15:54:30.591531: train_loss -0.9942 +2025-10-31 15:54:30.593774: val_loss -0.8826 +2025-10-31 15:54:30.595275: Pseudo dice [np.float32(0.9856), np.float32(0.9927), np.float32(0.9952), np.float32(0.7788)] +2025-10-31 15:54:30.596756: Epoch time: 24.17 s +2025-10-31 15:54:31.917608: +2025-10-31 15:54:31.920538: Epoch 931 +2025-10-31 15:54:31.922431: Current learning rate: 0.0009 +2025-10-31 15:54:57.366393: train_loss -0.9945 +2025-10-31 15:54:57.369471: val_loss -0.8807 +2025-10-31 15:54:57.371166: Pseudo dice [np.float32(0.9853), np.float32(0.9927), np.float32(0.9951), np.float32(0.7763)] +2025-10-31 15:54:57.373225: Epoch time: 25.45 s +2025-10-31 15:54:58.634870: +2025-10-31 15:54:58.636881: Epoch 932 +2025-10-31 15:54:58.638705: Current learning rate: 0.00089 +2025-10-31 15:55:25.316015: train_loss -0.9943 +2025-10-31 15:55:25.319835: val_loss -0.887 +2025-10-31 15:55:25.322014: Pseudo dice [np.float32(0.9862), np.float32(0.993), np.float32(0.9953), np.float32(0.7903)] +2025-10-31 15:55:25.323797: Epoch time: 26.68 s +2025-10-31 15:55:26.555026: +2025-10-31 15:55:26.557049: Epoch 933 +2025-10-31 15:55:26.559075: Current learning rate: 0.00088 +2025-10-31 15:55:51.351395: train_loss -0.9946 +2025-10-31 15:55:51.354036: val_loss -0.8786 +2025-10-31 15:55:51.355901: Pseudo dice [np.float32(0.9855), np.float32(0.9932), np.float32(0.9949), np.float32(0.7706)] +2025-10-31 15:55:51.357712: Epoch time: 24.8 s +2025-10-31 15:55:52.421131: +2025-10-31 15:55:52.423843: Epoch 934 +2025-10-31 15:55:52.426007: Current learning rate: 0.00087 +2025-10-31 15:56:14.728838: train_loss -0.9946 +2025-10-31 15:56:14.731062: val_loss -0.8843 +2025-10-31 15:56:14.732553: Pseudo dice [np.float32(0.986), np.float32(0.9932), np.float32(0.9952), np.float32(0.7799)] +2025-10-31 15:56:14.734849: Epoch time: 22.31 s +2025-10-31 15:56:15.943503: +2025-10-31 15:56:15.945533: Epoch 935 +2025-10-31 15:56:15.947177: Current learning rate: 0.00085 +2025-10-31 15:56:41.228123: train_loss -0.9946 +2025-10-31 15:56:41.230887: val_loss -0.8857 +2025-10-31 15:56:41.232597: Pseudo dice [np.float32(0.9858), np.float32(0.9932), np.float32(0.995), np.float32(0.7833)] +2025-10-31 15:56:41.234459: Epoch time: 25.29 s +2025-10-31 15:56:42.316015: +2025-10-31 15:56:42.318274: Epoch 936 +2025-10-31 15:56:42.320688: Current learning rate: 0.00084 +2025-10-31 15:57:06.292266: train_loss -0.995 +2025-10-31 15:57:06.294858: val_loss -0.8846 +2025-10-31 15:57:06.297313: Pseudo dice [np.float32(0.9851), np.float32(0.9931), np.float32(0.9952), np.float32(0.7858)] +2025-10-31 15:57:06.299088: Epoch time: 23.98 s +2025-10-31 15:57:07.528122: +2025-10-31 15:57:07.530240: Epoch 937 +2025-10-31 15:57:07.532813: Current learning rate: 0.00083 +2025-10-31 15:57:31.662159: train_loss -0.9942 +2025-10-31 15:57:31.667575: val_loss -0.8887 +2025-10-31 15:57:31.669337: Pseudo dice [np.float32(0.986), np.float32(0.9934), np.float32(0.9956), np.float32(0.7934)] +2025-10-31 15:57:31.671133: Epoch time: 24.14 s +2025-10-31 15:57:32.907980: +2025-10-31 15:57:32.920884: Epoch 938 +2025-10-31 15:57:32.923116: Current learning rate: 0.00082 +2025-10-31 15:57:58.681362: train_loss -0.9947 +2025-10-31 15:57:58.684113: val_loss -0.8799 +2025-10-31 15:57:58.686123: Pseudo dice [np.float32(0.9856), np.float32(0.9931), np.float32(0.995), np.float32(0.7745)] +2025-10-31 15:57:58.687782: Epoch time: 25.78 s +2025-10-31 15:57:59.913500: +2025-10-31 15:57:59.915517: Epoch 939 +2025-10-31 15:57:59.917322: Current learning rate: 0.00081 +2025-10-31 15:58:24.104394: train_loss -0.9949 +2025-10-31 15:58:24.107234: val_loss -0.8856 +2025-10-31 15:58:24.108649: Pseudo dice [np.float32(0.9859), np.float32(0.9926), np.float32(0.9953), np.float32(0.7869)] +2025-10-31 15:58:24.110144: Epoch time: 24.19 s +2025-10-31 15:58:25.391784: +2025-10-31 15:58:25.394107: Epoch 940 +2025-10-31 15:58:25.395867: Current learning rate: 0.00079 +2025-10-31 15:58:52.336493: train_loss -0.9946 +2025-10-31 15:58:52.339209: val_loss -0.8952 +2025-10-31 15:58:52.340873: Pseudo dice [np.float32(0.9849), np.float32(0.9927), np.float32(0.996), np.float32(0.8143)] +2025-10-31 15:58:52.342482: Epoch time: 26.95 s +2025-10-31 15:58:53.556839: +2025-10-31 15:58:53.558707: Epoch 941 +2025-10-31 15:58:53.560613: Current learning rate: 0.00078 +2025-10-31 15:59:18.619372: train_loss -0.9941 +2025-10-31 15:59:18.622189: val_loss -0.8823 +2025-10-31 15:59:18.623978: Pseudo dice [np.float32(0.9864), np.float32(0.9929), np.float32(0.9951), np.float32(0.7784)] +2025-10-31 15:59:18.625842: Epoch time: 25.06 s +2025-10-31 15:59:19.718894: +2025-10-31 15:59:19.720795: Epoch 942 +2025-10-31 15:59:19.722921: Current learning rate: 0.00077 +2025-10-31 15:59:44.331364: train_loss -0.9946 +2025-10-31 15:59:44.334095: val_loss -0.884 +2025-10-31 15:59:44.335669: Pseudo dice [np.float32(0.9849), np.float32(0.9925), np.float32(0.9951), np.float32(0.7883)] +2025-10-31 15:59:44.337543: Epoch time: 24.61 s +2025-10-31 15:59:45.485065: +2025-10-31 15:59:45.487160: Epoch 943 +2025-10-31 15:59:45.489007: Current learning rate: 0.00076 +2025-10-31 16:00:10.213022: train_loss -0.9942 +2025-10-31 16:00:10.215042: val_loss -0.8878 +2025-10-31 16:00:10.216594: Pseudo dice [np.float32(0.986), np.float32(0.9936), np.float32(0.9954), np.float32(0.7923)] +2025-10-31 16:00:10.218977: Epoch time: 24.73 s +2025-10-31 16:00:11.740539: +2025-10-31 16:00:11.742712: Epoch 944 +2025-10-31 16:00:11.744356: Current learning rate: 0.00075 +2025-10-31 16:00:37.957079: train_loss -0.9949 +2025-10-31 16:00:37.960023: val_loss -0.8836 +2025-10-31 16:00:37.961642: Pseudo dice [np.float32(0.9857), np.float32(0.9931), np.float32(0.9952), np.float32(0.7819)] +2025-10-31 16:00:37.963000: Epoch time: 26.22 s +2025-10-31 16:00:39.148546: +2025-10-31 16:00:39.150250: Epoch 945 +2025-10-31 16:00:39.151889: Current learning rate: 0.00074 +2025-10-31 16:01:05.246625: train_loss -0.9949 +2025-10-31 16:01:05.249465: val_loss -0.8848 +2025-10-31 16:01:05.251803: Pseudo dice [np.float32(0.9852), np.float32(0.9931), np.float32(0.9953), np.float32(0.7844)] +2025-10-31 16:01:05.253897: Epoch time: 26.1 s +2025-10-31 16:01:06.485889: +2025-10-31 16:01:06.488301: Epoch 946 +2025-10-31 16:01:06.490074: Current learning rate: 0.00072 +2025-10-31 16:01:32.306370: train_loss -0.995 +2025-10-31 16:01:32.308500: val_loss -0.8831 +2025-10-31 16:01:32.310091: Pseudo dice [np.float32(0.9863), np.float32(0.9936), np.float32(0.9953), np.float32(0.7845)] +2025-10-31 16:01:32.311647: Epoch time: 25.82 s +2025-10-31 16:01:33.542527: +2025-10-31 16:01:33.544378: Epoch 947 +2025-10-31 16:01:33.545971: Current learning rate: 0.00071 +2025-10-31 16:01:58.855264: train_loss -0.9944 +2025-10-31 16:01:58.858217: val_loss -0.8866 +2025-10-31 16:01:58.859697: Pseudo dice [np.float32(0.9852), np.float32(0.9929), np.float32(0.9952), np.float32(0.79)] +2025-10-31 16:01:58.861453: Epoch time: 25.31 s +2025-10-31 16:02:00.034644: +2025-10-31 16:02:00.036493: Epoch 948 +2025-10-31 16:02:00.038510: Current learning rate: 0.0007 +2025-10-31 16:02:26.158046: train_loss -0.9945 +2025-10-31 16:02:26.160718: val_loss -0.8875 +2025-10-31 16:02:26.162546: Pseudo dice [np.float32(0.9854), np.float32(0.9933), np.float32(0.9954), np.float32(0.7933)] +2025-10-31 16:02:26.164260: Epoch time: 26.12 s +2025-10-31 16:02:27.360387: +2025-10-31 16:02:27.362425: Epoch 949 +2025-10-31 16:02:27.364421: Current learning rate: 0.00069 +2025-10-31 16:02:54.879397: train_loss -0.9952 +2025-10-31 16:02:54.881119: val_loss -0.8829 +2025-10-31 16:02:54.882754: Pseudo dice [np.float32(0.9856), np.float32(0.9928), np.float32(0.9949), np.float32(0.7809)] +2025-10-31 16:02:54.884398: Epoch time: 27.52 s +2025-10-31 16:02:57.204907: +2025-10-31 16:02:57.208845: Epoch 950 +2025-10-31 16:02:57.211500: Current learning rate: 0.00067 +2025-10-31 16:03:18.908110: train_loss -0.995 +2025-10-31 16:03:18.911110: val_loss -0.8847 +2025-10-31 16:03:18.912879: Pseudo dice [np.float32(0.9862), np.float32(0.9934), np.float32(0.9952), np.float32(0.7838)] +2025-10-31 16:03:18.915058: Epoch time: 21.71 s +2025-10-31 16:03:20.071657: +2025-10-31 16:03:20.073642: Epoch 951 +2025-10-31 16:03:20.075426: Current learning rate: 0.00066 +2025-10-31 16:03:45.786757: train_loss -0.9948 +2025-10-31 16:03:45.789640: val_loss -0.886 +2025-10-31 16:03:45.791860: Pseudo dice [np.float32(0.9861), np.float32(0.993), np.float32(0.9951), np.float32(0.7873)] +2025-10-31 16:03:45.794097: Epoch time: 25.72 s +2025-10-31 16:03:47.030175: +2025-10-31 16:03:47.034237: Epoch 952 +2025-10-31 16:03:47.035950: Current learning rate: 0.00065 +2025-10-31 16:04:11.074599: train_loss -0.9945 +2025-10-31 16:04:11.086965: val_loss -0.8847 +2025-10-31 16:04:11.088958: Pseudo dice [np.float32(0.9866), np.float32(0.9932), np.float32(0.9955), np.float32(0.7824)] +2025-10-31 16:04:11.090765: Epoch time: 24.05 s +2025-10-31 16:04:12.331163: +2025-10-31 16:04:12.332773: Epoch 953 +2025-10-31 16:04:12.334448: Current learning rate: 0.00064 +2025-10-31 16:04:36.912237: train_loss -0.9947 +2025-10-31 16:04:36.914683: val_loss -0.8829 +2025-10-31 16:04:36.916449: Pseudo dice [np.float32(0.9852), np.float32(0.9928), np.float32(0.9953), np.float32(0.7818)] +2025-10-31 16:04:36.918315: Epoch time: 24.58 s +2025-10-31 16:04:38.139999: +2025-10-31 16:04:38.141950: Epoch 954 +2025-10-31 16:04:38.143707: Current learning rate: 0.00063 +2025-10-31 16:05:03.812801: train_loss -0.9946 +2025-10-31 16:05:03.815163: val_loss -0.8848 +2025-10-31 16:05:03.816831: Pseudo dice [np.float32(0.9859), np.float32(0.9931), np.float32(0.9953), np.float32(0.7855)] +2025-10-31 16:05:03.818273: Epoch time: 25.67 s +2025-10-31 16:05:04.829937: +2025-10-31 16:05:04.834071: Epoch 955 +2025-10-31 16:05:04.837325: Current learning rate: 0.00061 +2025-10-31 16:05:29.540443: train_loss -0.9949 +2025-10-31 16:05:29.542355: val_loss -0.8916 +2025-10-31 16:05:29.544208: Pseudo dice [np.float32(0.9862), np.float32(0.9933), np.float32(0.9957), np.float32(0.8022)] +2025-10-31 16:05:29.546099: Epoch time: 24.71 s +2025-10-31 16:05:30.676327: +2025-10-31 16:05:30.678127: Epoch 956 +2025-10-31 16:05:30.679786: Current learning rate: 0.0006 +2025-10-31 16:05:57.944026: train_loss -0.9951 +2025-10-31 16:05:57.947255: val_loss -0.8867 +2025-10-31 16:05:57.948675: Pseudo dice [np.float32(0.9854), np.float32(0.9928), np.float32(0.9957), np.float32(0.7927)] +2025-10-31 16:05:57.950083: Epoch time: 27.27 s +2025-10-31 16:05:59.187236: +2025-10-31 16:05:59.188903: Epoch 957 +2025-10-31 16:05:59.190180: Current learning rate: 0.00059 +2025-10-31 16:06:23.663250: train_loss -0.9952 +2025-10-31 16:06:23.665746: val_loss -0.8852 +2025-10-31 16:06:23.667539: Pseudo dice [np.float32(0.9849), np.float32(0.9928), np.float32(0.9952), np.float32(0.7891)] +2025-10-31 16:06:23.669311: Epoch time: 24.48 s +2025-10-31 16:06:24.775386: +2025-10-31 16:06:24.777533: Epoch 958 +2025-10-31 16:06:24.779743: Current learning rate: 0.00058 +2025-10-31 16:06:47.875736: train_loss -0.9946 +2025-10-31 16:06:47.878241: val_loss -0.8848 +2025-10-31 16:06:47.879690: Pseudo dice [np.float32(0.9864), np.float32(0.9931), np.float32(0.9952), np.float32(0.7821)] +2025-10-31 16:06:47.881332: Epoch time: 23.1 s +2025-10-31 16:06:49.037913: +2025-10-31 16:06:49.040392: Epoch 959 +2025-10-31 16:06:49.042497: Current learning rate: 0.00056 +2025-10-31 16:07:14.062628: train_loss -0.9949 +2025-10-31 16:07:14.067304: val_loss -0.8858 +2025-10-31 16:07:14.069151: Pseudo dice [np.float32(0.985), np.float32(0.9927), np.float32(0.9952), np.float32(0.7899)] +2025-10-31 16:07:14.071091: Epoch time: 25.03 s +2025-10-31 16:07:15.138106: +2025-10-31 16:07:15.140319: Epoch 960 +2025-10-31 16:07:15.142188: Current learning rate: 0.00055 +2025-10-31 16:07:41.490352: train_loss -0.995 +2025-10-31 16:07:41.493293: val_loss -0.8859 +2025-10-31 16:07:41.494927: Pseudo dice [np.float32(0.9859), np.float32(0.993), np.float32(0.9953), np.float32(0.7844)] +2025-10-31 16:07:41.496589: Epoch time: 26.35 s +2025-10-31 16:07:42.817832: +2025-10-31 16:07:42.820116: Epoch 961 +2025-10-31 16:07:42.821737: Current learning rate: 0.00054 +2025-10-31 16:08:05.979601: train_loss -0.9949 +2025-10-31 16:08:05.982843: val_loss -0.8869 +2025-10-31 16:08:05.985828: Pseudo dice [np.float32(0.9855), np.float32(0.993), np.float32(0.9954), np.float32(0.7906)] +2025-10-31 16:08:05.987467: Epoch time: 23.16 s +2025-10-31 16:08:07.291663: +2025-10-31 16:08:07.293697: Epoch 962 +2025-10-31 16:08:07.295678: Current learning rate: 0.00053 +2025-10-31 16:08:31.542614: train_loss -0.995 +2025-10-31 16:08:31.545107: val_loss -0.8893 +2025-10-31 16:08:31.546522: Pseudo dice [np.float32(0.9856), np.float32(0.9929), np.float32(0.9955), np.float32(0.7981)] +2025-10-31 16:08:31.547982: Epoch time: 24.25 s +2025-10-31 16:08:32.750528: +2025-10-31 16:08:32.752243: Epoch 963 +2025-10-31 16:08:32.753984: Current learning rate: 0.00051 +2025-10-31 16:08:57.467150: train_loss -0.9947 +2025-10-31 16:08:57.470586: val_loss -0.8859 +2025-10-31 16:08:57.472265: Pseudo dice [np.float32(0.9854), np.float32(0.9929), np.float32(0.9952), np.float32(0.7891)] +2025-10-31 16:08:57.473610: Epoch time: 24.72 s +2025-10-31 16:08:58.709419: +2025-10-31 16:08:58.711427: Epoch 964 +2025-10-31 16:08:58.713109: Current learning rate: 0.0005 +2025-10-31 16:09:23.951900: train_loss -0.9951 +2025-10-31 16:09:23.954263: val_loss -0.8889 +2025-10-31 16:09:23.956311: Pseudo dice [np.float32(0.9857), np.float32(0.9933), np.float32(0.9955), np.float32(0.795)] +2025-10-31 16:09:23.957966: Epoch time: 25.24 s +2025-10-31 16:09:25.188823: +2025-10-31 16:09:25.190744: Epoch 965 +2025-10-31 16:09:25.192449: Current learning rate: 0.00049 +2025-10-31 16:09:49.251414: train_loss -0.9951 +2025-10-31 16:09:49.254235: val_loss -0.8859 +2025-10-31 16:09:49.256660: Pseudo dice [np.float32(0.9858), np.float32(0.993), np.float32(0.9953), np.float32(0.7881)] +2025-10-31 16:09:49.258418: Epoch time: 24.06 s +2025-10-31 16:09:50.434677: +2025-10-31 16:09:50.443013: Epoch 966 +2025-10-31 16:09:50.448881: Current learning rate: 0.00048 +2025-10-31 16:10:17.100150: train_loss -0.995 +2025-10-31 16:10:17.103390: val_loss -0.8873 +2025-10-31 16:10:17.105055: Pseudo dice [np.float32(0.986), np.float32(0.9932), np.float32(0.9955), np.float32(0.785)] +2025-10-31 16:10:17.106639: Epoch time: 26.67 s +2025-10-31 16:10:18.300145: +2025-10-31 16:10:18.302007: Epoch 967 +2025-10-31 16:10:18.303483: Current learning rate: 0.00046 +2025-10-31 16:10:44.367931: train_loss -0.9953 +2025-10-31 16:10:44.371195: val_loss -0.8894 +2025-10-31 16:10:44.374106: Pseudo dice [np.float32(0.9853), np.float32(0.9929), np.float32(0.9955), np.float32(0.7957)] +2025-10-31 16:10:44.378099: Epoch time: 26.07 s +2025-10-31 16:10:45.656529: +2025-10-31 16:10:45.658450: Epoch 968 +2025-10-31 16:10:45.659891: Current learning rate: 0.00045 +2025-10-31 16:11:07.652177: train_loss -0.9952 +2025-10-31 16:11:07.654040: val_loss -0.8797 +2025-10-31 16:11:07.655317: Pseudo dice [np.float32(0.9861), np.float32(0.9934), np.float32(0.995), np.float32(0.7768)] +2025-10-31 16:11:07.656616: Epoch time: 22.0 s +2025-10-31 16:11:08.834944: +2025-10-31 16:11:08.837057: Epoch 969 +2025-10-31 16:11:08.838580: Current learning rate: 0.00044 +2025-10-31 16:11:34.838448: train_loss -0.9954 +2025-10-31 16:11:34.841764: val_loss -0.8908 +2025-10-31 16:11:34.843536: Pseudo dice [np.float32(0.9857), np.float32(0.9932), np.float32(0.9956), np.float32(0.798)] +2025-10-31 16:11:34.845241: Epoch time: 26.01 s +2025-10-31 16:11:36.085067: +2025-10-31 16:11:36.086965: Epoch 970 +2025-10-31 16:11:36.088872: Current learning rate: 0.00043 +2025-10-31 16:12:02.086261: train_loss -0.9947 +2025-10-31 16:12:02.088545: val_loss -0.8882 +2025-10-31 16:12:02.090358: Pseudo dice [np.float32(0.986), np.float32(0.993), np.float32(0.9955), np.float32(0.7914)] +2025-10-31 16:12:02.092135: Epoch time: 26.0 s +2025-10-31 16:12:03.307850: +2025-10-31 16:12:03.309526: Epoch 971 +2025-10-31 16:12:03.310965: Current learning rate: 0.00041 +2025-10-31 16:12:28.060888: train_loss -0.9956 +2025-10-31 16:12:28.063363: val_loss -0.8892 +2025-10-31 16:12:28.064851: Pseudo dice [np.float32(0.9859), np.float32(0.9929), np.float32(0.9955), np.float32(0.7959)] +2025-10-31 16:12:28.066324: Epoch time: 24.76 s +2025-10-31 16:12:29.303042: +2025-10-31 16:12:29.304919: Epoch 972 +2025-10-31 16:12:29.306647: Current learning rate: 0.0004 +2025-10-31 16:12:50.967548: train_loss -0.9951 +2025-10-31 16:12:50.970152: val_loss -0.8871 +2025-10-31 16:12:50.971834: Pseudo dice [np.float32(0.9857), np.float32(0.9932), np.float32(0.9955), np.float32(0.7954)] +2025-10-31 16:12:50.973477: Epoch time: 21.67 s +2025-10-31 16:12:52.227416: +2025-10-31 16:12:52.229165: Epoch 973 +2025-10-31 16:12:52.232088: Current learning rate: 0.00039 +2025-10-31 16:13:17.967062: train_loss -0.9953 +2025-10-31 16:13:17.969377: val_loss -0.8842 +2025-10-31 16:13:17.970763: Pseudo dice [np.float32(0.9863), np.float32(0.993), np.float32(0.9952), np.float32(0.7819)] +2025-10-31 16:13:17.972283: Epoch time: 25.74 s +2025-10-31 16:13:19.191235: +2025-10-31 16:13:19.193603: Epoch 974 +2025-10-31 16:13:19.195627: Current learning rate: 0.00037 +2025-10-31 16:13:46.365923: train_loss -0.9952 +2025-10-31 16:13:46.371987: val_loss -0.8843 +2025-10-31 16:13:46.373347: Pseudo dice [np.float32(0.9857), np.float32(0.9928), np.float32(0.9952), np.float32(0.7837)] +2025-10-31 16:13:46.375078: Epoch time: 27.18 s +2025-10-31 16:13:47.636734: +2025-10-31 16:13:47.638523: Epoch 975 +2025-10-31 16:13:47.640099: Current learning rate: 0.00036 +2025-10-31 16:14:10.478660: train_loss -0.9952 +2025-10-31 16:14:10.481102: val_loss -0.8845 +2025-10-31 16:14:10.483090: Pseudo dice [np.float32(0.9856), np.float32(0.993), np.float32(0.9954), np.float32(0.786)] +2025-10-31 16:14:10.484576: Epoch time: 22.84 s +2025-10-31 16:14:11.682702: +2025-10-31 16:14:11.684366: Epoch 976 +2025-10-31 16:14:11.685873: Current learning rate: 0.00035 +2025-10-31 16:14:35.695779: train_loss -0.9953 +2025-10-31 16:14:35.700065: val_loss -0.8868 +2025-10-31 16:14:35.701642: Pseudo dice [np.float32(0.9859), np.float32(0.9933), np.float32(0.9954), np.float32(0.79)] +2025-10-31 16:14:35.703326: Epoch time: 24.01 s +2025-10-31 16:14:36.949146: +2025-10-31 16:14:36.950762: Epoch 977 +2025-10-31 16:14:36.952131: Current learning rate: 0.00034 +2025-10-31 16:15:04.385930: train_loss -0.9953 +2025-10-31 16:15:04.391844: val_loss -0.8841 +2025-10-31 16:15:04.395070: Pseudo dice [np.float32(0.9864), np.float32(0.9934), np.float32(0.9954), np.float32(0.7812)] +2025-10-31 16:15:04.397074: Epoch time: 27.44 s +2025-10-31 16:15:05.651416: +2025-10-31 16:15:05.653089: Epoch 978 +2025-10-31 16:15:05.654870: Current learning rate: 0.00032 +2025-10-31 16:15:32.737719: train_loss -0.9951 +2025-10-31 16:15:32.740484: val_loss -0.8845 +2025-10-31 16:15:32.742052: Pseudo dice [np.float32(0.9858), np.float32(0.9929), np.float32(0.9954), np.float32(0.7888)] +2025-10-31 16:15:32.743808: Epoch time: 27.09 s +2025-10-31 16:15:33.951425: +2025-10-31 16:15:33.954182: Epoch 979 +2025-10-31 16:15:33.955800: Current learning rate: 0.00031 +2025-10-31 16:15:57.581234: train_loss -0.9955 +2025-10-31 16:15:57.585792: val_loss -0.8866 +2025-10-31 16:15:57.587408: Pseudo dice [np.float32(0.9861), np.float32(0.9929), np.float32(0.9953), np.float32(0.7904)] +2025-10-31 16:15:57.589092: Epoch time: 23.63 s +2025-10-31 16:15:58.733368: +2025-10-31 16:15:58.735194: Epoch 980 +2025-10-31 16:15:58.736821: Current learning rate: 0.0003 +2025-10-31 16:16:22.970887: train_loss -0.9951 +2025-10-31 16:16:22.973483: val_loss -0.885 +2025-10-31 16:16:22.975206: Pseudo dice [np.float32(0.9854), np.float32(0.9932), np.float32(0.9954), np.float32(0.7887)] +2025-10-31 16:16:22.976670: Epoch time: 24.24 s +2025-10-31 16:16:24.191800: +2025-10-31 16:16:24.193761: Epoch 981 +2025-10-31 16:16:24.195381: Current learning rate: 0.00028 +2025-10-31 16:16:51.242601: train_loss -0.9948 +2025-10-31 16:16:51.245074: val_loss -0.881 +2025-10-31 16:16:51.246724: Pseudo dice [np.float32(0.9861), np.float32(0.9934), np.float32(0.995), np.float32(0.7791)] +2025-10-31 16:16:51.248486: Epoch time: 27.05 s +2025-10-31 16:16:53.060338: +2025-10-31 16:16:53.062031: Epoch 982 +2025-10-31 16:16:53.063758: Current learning rate: 0.00027 +2025-10-31 16:17:20.189482: train_loss -0.995 +2025-10-31 16:17:20.191537: val_loss -0.8856 +2025-10-31 16:17:20.193100: Pseudo dice [np.float32(0.9857), np.float32(0.9929), np.float32(0.9955), np.float32(0.7915)] +2025-10-31 16:17:20.194977: Epoch time: 27.13 s +2025-10-31 16:17:21.390638: +2025-10-31 16:17:21.392614: Epoch 983 +2025-10-31 16:17:21.395081: Current learning rate: 0.00026 +2025-10-31 16:17:46.371317: train_loss -0.9953 +2025-10-31 16:17:46.373693: val_loss -0.8822 +2025-10-31 16:17:46.375554: Pseudo dice [np.float32(0.9867), np.float32(0.9933), np.float32(0.9952), np.float32(0.7807)] +2025-10-31 16:17:46.377063: Epoch time: 24.98 s +2025-10-31 16:17:47.504602: +2025-10-31 16:17:47.506389: Epoch 984 +2025-10-31 16:17:47.507987: Current learning rate: 0.00024 +2025-10-31 16:18:14.392721: train_loss -0.9951 +2025-10-31 16:18:14.397349: val_loss -0.8888 +2025-10-31 16:18:14.399018: Pseudo dice [np.float32(0.9856), np.float32(0.9936), np.float32(0.9954), np.float32(0.7976)] +2025-10-31 16:18:14.400652: Epoch time: 26.89 s +2025-10-31 16:18:15.482309: +2025-10-31 16:18:15.484473: Epoch 985 +2025-10-31 16:18:15.486210: Current learning rate: 0.00023 +2025-10-31 16:18:42.557742: train_loss -0.9953 +2025-10-31 16:18:42.560244: val_loss -0.8862 +2025-10-31 16:18:42.561833: Pseudo dice [np.float32(0.9858), np.float32(0.9929), np.float32(0.9955), np.float32(0.7946)] +2025-10-31 16:18:42.563349: Epoch time: 27.08 s +2025-10-31 16:18:43.756422: +2025-10-31 16:18:43.758393: Epoch 986 +2025-10-31 16:18:43.759967: Current learning rate: 0.00021 +2025-10-31 16:19:07.892260: train_loss -0.9951 +2025-10-31 16:19:07.896855: val_loss -0.8829 +2025-10-31 16:19:07.899060: Pseudo dice [np.float32(0.9862), np.float32(0.9934), np.float32(0.9951), np.float32(0.78)] +2025-10-31 16:19:07.901560: Epoch time: 24.14 s +2025-10-31 16:19:08.959990: +2025-10-31 16:19:08.962077: Epoch 987 +2025-10-31 16:19:08.964308: Current learning rate: 0.0002 +2025-10-31 16:19:35.708932: train_loss -0.9955 +2025-10-31 16:19:35.712243: val_loss -0.8908 +2025-10-31 16:19:35.713891: Pseudo dice [np.float32(0.9855), np.float32(0.9931), np.float32(0.9957), np.float32(0.8004)] +2025-10-31 16:19:35.715621: Epoch time: 26.75 s +2025-10-31 16:19:36.863849: +2025-10-31 16:19:36.865638: Epoch 988 +2025-10-31 16:19:36.867163: Current learning rate: 0.00019 +2025-10-31 16:20:01.927015: train_loss -0.9952 +2025-10-31 16:20:01.930244: val_loss -0.8874 +2025-10-31 16:20:01.932142: Pseudo dice [np.float32(0.9861), np.float32(0.9938), np.float32(0.9955), np.float32(0.7953)] +2025-10-31 16:20:01.933877: Epoch time: 25.06 s +2025-10-31 16:20:03.162798: +2025-10-31 16:20:03.164975: Epoch 989 +2025-10-31 16:20:03.167922: Current learning rate: 0.00017 +2025-10-31 16:20:29.446612: train_loss -0.9951 +2025-10-31 16:20:29.449508: val_loss -0.8913 +2025-10-31 16:20:29.451528: Pseudo dice [np.float32(0.9868), np.float32(0.9934), np.float32(0.9958), np.float32(0.7983)] +2025-10-31 16:20:29.453604: Epoch time: 26.29 s +2025-10-31 16:20:30.673179: +2025-10-31 16:20:30.675414: Epoch 990 +2025-10-31 16:20:30.677761: Current learning rate: 0.00016 +2025-10-31 16:20:56.005266: train_loss -0.9951 +2025-10-31 16:20:56.016375: val_loss -0.8831 +2025-10-31 16:20:56.018189: Pseudo dice [np.float32(0.9858), np.float32(0.9931), np.float32(0.9952), np.float32(0.7805)] +2025-10-31 16:20:56.019721: Epoch time: 25.33 s +2025-10-31 16:20:57.228049: +2025-10-31 16:20:57.229860: Epoch 991 +2025-10-31 16:20:57.231791: Current learning rate: 0.00014 +2025-10-31 16:21:21.561871: train_loss -0.9955 +2025-10-31 16:21:21.564227: val_loss -0.8829 +2025-10-31 16:21:21.566251: Pseudo dice [np.float32(0.986), np.float32(0.9931), np.float32(0.9953), np.float32(0.7798)] +2025-10-31 16:21:21.568150: Epoch time: 24.34 s +2025-10-31 16:21:22.675871: +2025-10-31 16:21:22.678334: Epoch 992 +2025-10-31 16:21:22.680858: Current learning rate: 0.00013 +2025-10-31 16:21:47.527249: train_loss -0.9953 +2025-10-31 16:21:47.529334: val_loss -0.8868 +2025-10-31 16:21:47.530670: Pseudo dice [np.float32(0.9846), np.float32(0.9929), np.float32(0.9955), np.float32(0.7953)] +2025-10-31 16:21:47.532079: Epoch time: 24.85 s +2025-10-31 16:21:48.743359: +2025-10-31 16:21:48.745421: Epoch 993 +2025-10-31 16:21:48.747053: Current learning rate: 0.00011 +2025-10-31 16:22:12.999547: train_loss -0.9956 +2025-10-31 16:22:13.007898: val_loss -0.882 +2025-10-31 16:22:13.016925: Pseudo dice [np.float32(0.9861), np.float32(0.9936), np.float32(0.9953), np.float32(0.777)] +2025-10-31 16:22:13.027554: Epoch time: 24.26 s +2025-10-31 16:22:14.323051: +2025-10-31 16:22:14.325210: Epoch 994 +2025-10-31 16:22:14.327695: Current learning rate: 0.0001 +2025-10-31 16:22:37.631587: train_loss -0.9953 +2025-10-31 16:22:37.634097: val_loss -0.8811 +2025-10-31 16:22:37.635819: Pseudo dice [np.float32(0.9862), np.float32(0.9933), np.float32(0.9951), np.float32(0.7797)] +2025-10-31 16:22:37.637526: Epoch time: 23.31 s +2025-10-31 16:22:38.810920: +2025-10-31 16:22:38.813245: Epoch 995 +2025-10-31 16:22:38.814961: Current learning rate: 8e-05 +2025-10-31 16:23:02.561037: train_loss -0.9955 +2025-10-31 16:23:02.563520: val_loss -0.8894 +2025-10-31 16:23:02.565207: Pseudo dice [np.float32(0.9863), np.float32(0.9931), np.float32(0.9958), np.float32(0.8007)] +2025-10-31 16:23:02.566948: Epoch time: 23.75 s +2025-10-31 16:23:04.296325: +2025-10-31 16:23:04.300520: Epoch 996 +2025-10-31 16:23:04.304293: Current learning rate: 7e-05 +2025-10-31 16:23:29.725750: train_loss -0.9954 +2025-10-31 16:23:29.728175: val_loss -0.8789 +2025-10-31 16:23:29.729801: Pseudo dice [np.float32(0.9867), np.float32(0.9937), np.float32(0.9951), np.float32(0.7753)] +2025-10-31 16:23:29.731503: Epoch time: 25.43 s +2025-10-31 16:23:30.763375: +2025-10-31 16:23:30.766086: Epoch 997 +2025-10-31 16:23:30.767952: Current learning rate: 5e-05 +2025-10-31 16:23:54.880445: train_loss -0.9958 +2025-10-31 16:23:54.882596: val_loss -0.8923 +2025-10-31 16:23:54.884019: Pseudo dice [np.float32(0.9858), np.float32(0.9934), np.float32(0.9958), np.float32(0.8026)] +2025-10-31 16:23:54.885569: Epoch time: 24.12 s +2025-10-31 16:23:55.948040: +2025-10-31 16:23:55.949962: Epoch 998 +2025-10-31 16:23:55.951814: Current learning rate: 4e-05 +2025-10-31 16:24:22.812298: train_loss -0.9955 +2025-10-31 16:24:22.814820: val_loss -0.884 +2025-10-31 16:24:22.816439: Pseudo dice [np.float32(0.9864), np.float32(0.9935), np.float32(0.9952), np.float32(0.785)] +2025-10-31 16:24:22.817962: Epoch time: 26.87 s +2025-10-31 16:24:24.092097: +2025-10-31 16:24:24.094001: Epoch 999 +2025-10-31 16:24:24.095987: Current learning rate: 2e-05 +2025-10-31 16:24:49.186224: train_loss -0.9958 +2025-10-31 16:24:49.188610: val_loss -0.884 +2025-10-31 16:24:49.190349: Pseudo dice [np.float32(0.9863), np.float32(0.9933), np.float32(0.9954), np.float32(0.7871)] +2025-10-31 16:24:49.191913: Epoch time: 25.1 s +2025-10-31 16:24:51.580935: Training done. +2025-10-31 16:24:51.646198: Using splits from existing split file: /hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/splits_final.json +2025-10-31 16:24:51.658535: The split file contains 5 splits. +2025-10-31 16:24:51.660641: Desired fold for training: 4 +2025-10-31 16:24:51.662286: This split has 87 training and 21 validation cases. +2025-10-31 16:24:51.664205: predicting fish0001 +2025-10-31 16:24:51.672710: fish0001, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 16:25:02.691928: predicting fish0010 +2025-10-31 16:25:02.703837: fish0010, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 16:25:02.758305: predicting fish0011 +2025-10-31 16:25:02.762577: fish0011, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 16:25:02.820054: predicting fish0014 +2025-10-31 16:25:02.832897: fish0014, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 16:25:02.888773: predicting fish0029 +2025-10-31 16:25:02.892746: fish0029, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 16:25:02.928244: predicting fish0034 +2025-10-31 16:25:02.934964: fish0034, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 16:25:02.966605: predicting fish0036 +2025-10-31 16:25:02.971828: fish0036, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 16:25:03.030057: predicting fish0038 +2025-10-31 16:25:03.034624: fish0038, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 16:25:03.116054: predicting fish0041 +2025-10-31 16:25:03.120050: fish0041, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 16:25:03.212018: predicting fish0059 +2025-10-31 16:25:03.217216: fish0059, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 16:25:03.297909: predicting fish0073 +2025-10-31 16:25:03.302266: fish0073, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 16:25:03.343422: predicting fish0077 +2025-10-31 16:25:03.355118: fish0077, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 16:25:03.394720: predicting fish0080 +2025-10-31 16:25:03.401488: fish0080, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 16:25:03.464429: predicting fish0081 +2025-10-31 16:25:03.470609: fish0081, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 16:25:03.532546: predicting fish0082 +2025-10-31 16:25:03.540271: fish0082, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 16:25:03.592642: predicting fish0091 +2025-10-31 16:25:03.598888: fish0091, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 16:25:03.659556: predicting fish0098 +2025-10-31 16:25:03.665738: fish0098, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 16:25:03.722453: predicting fish0101 +2025-10-31 16:25:03.729768: fish0101, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 16:25:03.786725: predicting fish0104 +2025-10-31 16:25:03.802416: fish0104, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 16:25:03.864500: predicting fish0105 +2025-10-31 16:25:03.876118: fish0105, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 16:25:03.928179: predicting fish0106 +2025-10-31 16:25:03.949052: fish0106, shape torch.Size([1, 1, 1024, 102]), rank 0 +2025-10-31 16:25:11.873353: Validation complete +2025-10-31 16:25:11.880648: Mean Validation Dice: 0.9398154395628253 diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0001.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0001.png new file mode 100644 index 0000000000000000000000000000000000000000..944c47ff161e528901d266674fc4cfca8abb4fdd Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0001.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0010.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0010.png new file mode 100644 index 0000000000000000000000000000000000000000..c632131e6decaf714e5a658a745f1d4dd15daeca Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0010.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0011.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0011.png new file mode 100644 index 0000000000000000000000000000000000000000..34a05350bc8595d93e1e0adda0e1e9a8c1f41874 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0011.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0014.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0014.png new file mode 100644 index 0000000000000000000000000000000000000000..6f8b977862e92ceafcefea79640d889e50f739ec Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0014.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0029.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0029.png new file mode 100644 index 0000000000000000000000000000000000000000..8f9d91b03f13754543a6c8872c6050c7294c5982 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0029.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0034.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0034.png new file mode 100644 index 0000000000000000000000000000000000000000..9b1448358554e5fdcb8cbf49a247be795f9671f8 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0034.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0036.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0036.png new file mode 100644 index 0000000000000000000000000000000000000000..b26f45fe50c5b10613c3cffe8fe9378ff1de8c37 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0036.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0038.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0038.png new file mode 100644 index 0000000000000000000000000000000000000000..c67913a77cd5b03a48f5570b63fd582929b7f53b Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0038.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0041.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0041.png new file mode 100644 index 0000000000000000000000000000000000000000..b9da5015ec5f8b390084ff77c29cae76a611e883 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0041.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0059.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0059.png new file mode 100644 index 0000000000000000000000000000000000000000..647af462bd1b812abeaf04434f10c6f2d84346db Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0059.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0073.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0073.png new file mode 100644 index 0000000000000000000000000000000000000000..b73a9f72de48d2a466ba66ae5feea6e6dfb638bb Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0073.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0077.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0077.png new file mode 100644 index 0000000000000000000000000000000000000000..d3b836fdaea9d5549517631d76ffe230f39248a5 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0077.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0080.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0080.png new file mode 100644 index 0000000000000000000000000000000000000000..853ab045f8e8a736698749211b68e0fbc727f6c2 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0080.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0081.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0081.png new file mode 100644 index 0000000000000000000000000000000000000000..7a85e9c0ac4e8d68f2c9bec02708425b8fbeae44 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0081.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0082.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0082.png new file mode 100644 index 0000000000000000000000000000000000000000..ae3d6f28962229d089e1e58f252af431a4c1cfda Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0082.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0091.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0091.png new file mode 100644 index 0000000000000000000000000000000000000000..989cbd0c83abb28be8f3e6251a8e2f257a3d483e Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0091.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0098.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0098.png new file mode 100644 index 0000000000000000000000000000000000000000..76e298b36956e4f8e16d7174f107220a24e5ce29 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0098.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0101.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0101.png new file mode 100644 index 0000000000000000000000000000000000000000..debde2293ec62ab66aabd3d91876c36a919e47d0 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0101.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0104.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0104.png new file mode 100644 index 0000000000000000000000000000000000000000..edd25fc8c6f84bea3e3fbf63707e11c689821d21 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0104.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0105.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0105.png new file mode 100644 index 0000000000000000000000000000000000000000..b659dc7897aaf2ba61af6126018982d1688c4eb9 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0105.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0106.png b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0106.png new file mode 100644 index 0000000000000000000000000000000000000000..ff519b021ab5ebf55fec897fd82ad9d416c48148 Binary files /dev/null and b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0106.png differ diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/summary.json b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/summary.json new file mode 100644 index 0000000000000000000000000000000000000000..2db8729163134309b1412347e3cf8f5012775a77 --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/summary.json @@ -0,0 +1,1022 @@ +{ + "foreground_mean": { + "Dice": 0.9398154395628253, + "FN": 117.27380952380952, + "FP": 113.5595238095238, + "IoU": 0.9013875992639482, + "TN": 92638.44047619047, + "TP": 11578.72619047619, + "n_pred": 11692.285714285716, + "n_ref": 11696.0 + }, + "mean": { + "1": { + "Dice": 0.9858878859664855, + "FN": 104.61904761904762, + "FP": 69.52380952380952, + "IoU": 0.9722923448112942, + "TN": 98190.47619047618, + "TP": 6083.380952380952, + "n_pred": 6152.9047619047615, + "n_ref": 6188.0 + }, + "2": { + "Dice": 0.993460605478835, + "FN": 61.666666666666664, + "FP": 80.04761904761905, + "IoU": 0.9870392707229272, + "TN": 93575.38095238095, + "TP": 10730.904761904761, + "n_pred": 10810.952380952382, + "n_ref": 10792.57142857143 + }, + "3": { + "Dice": 0.9952267328411339, + "FN": 85.71428571428571, + "FP": 187.28571428571428, + "IoU": 0.9905118729493959, + "TN": 75302.42857142857, + "TP": 28872.571428571428, + "n_pred": 29059.85714285714, + "n_ref": 28958.285714285714 + }, + "4": { + "Dice": 0.7846865339648471, + "FN": 217.0952380952381, + "FP": 117.38095238095238, + "IoU": 0.6557069085721754, + "TN": 103485.47619047618, + "TP": 628.047619047619, + "n_pred": 745.4285714285714, + "n_ref": 845.1428571428571 + } + }, + "metric_per_case": [ + { + "metrics": { + "1": { + "Dice": 0.9943520309477756, + "FN": 0, + "FP": 73, + "IoU": 0.988767502692722, + "TN": 97949, + "TP": 6426, + "n_pred": 6499, + "n_ref": 6426 + }, + "2": { + "Dice": 0.9957145386931114, + "FN": 121, + "FP": 0, + "IoU": 0.9914656510086048, + "TN": 90270, + "TP": 14057, + "n_pred": 14057, + "n_ref": 14178 + }, + "3": { + "Dice": 0.9898107714701602, + "FN": 0, + "FP": 714, + "IoU": 0.9798270893371758, + "TN": 69054, + "TP": 34680, + "n_pred": 35394, + "n_ref": 34680 + }, + "4": { + "Dice": 0.6666666666666666, + "FN": 714, + "FP": 0, + "IoU": 0.5, + "TN": 103020, + "TP": 714, + "n_pred": 714, + "n_ref": 1428 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0001.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0001.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9857414448669202, + "FN": 102, + "FP": 78, + "IoU": 0.971883786316776, + "TN": 98046, + "TP": 6222, + "n_pred": 6300, + "n_ref": 6324 + }, + "2": { + "Dice": 0.9938650306748467, + "FN": 0, + "FP": 102, + "IoU": 0.9878048780487805, + "TN": 96084, + "TP": 8262, + "n_pred": 8364, + "n_ref": 8262 + }, + "3": { + "Dice": 0.9889470622454916, + "FN": 0, + "FP": 570, + "IoU": 0.9781357882623706, + "TN": 78378, + "TP": 25500, + "n_pred": 26070, + "n_ref": 25500 + }, + "4": { + "Dice": 0.6216216216216216, + "FN": 570, + "FP": 102, + "IoU": 0.45098039215686275, + "TN": 103224, + "TP": 552, + "n_pred": 654, + "n_ref": 1122 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0010.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0010.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9911504424778761, + "FN": 0, + "FP": 102, + "IoU": 0.9824561403508771, + "TN": 98634, + "TP": 5712, + "n_pred": 5814, + "n_ref": 5712 + }, + "2": { + "Dice": 0.9984251968503937, + "FN": 34, + "FP": 0, + "IoU": 0.9968553459119497, + "TN": 93636, + "TP": 10778, + "n_pred": 10778, + "n_ref": 10812 + }, + "3": { + "Dice": 0.9985989905980454, + "FN": 0, + "FP": 83, + "IoU": 0.9972019013585949, + "TN": 74785, + "TP": 29580, + "n_pred": 29663, + "n_ref": 29580 + }, + "4": { + "Dice": 0.8401768793430195, + "FN": 253, + "FP": 0, + "IoU": 0.724400871459695, + "TN": 103530, + "TP": 665, + "n_pred": 665, + "n_ref": 918 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0011.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0011.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9705378020265004, + "FN": 302, + "FP": 76, + "IoU": 0.9427619624470018, + "TN": 97844, + "TP": 6226, + "n_pred": 6302, + "n_ref": 6528 + }, + "2": { + "Dice": 0.9929664273801755, + "FN": 178, + "FP": 16, + "IoU": 0.9860311059907834, + "TN": 90560, + "TP": 13694, + "n_pred": 13710, + "n_ref": 13872 + }, + "3": { + "Dice": 0.9983385191674471, + "FN": 0, + "FP": 110, + "IoU": 0.9966825502141263, + "TN": 71290, + "TP": 33048, + "n_pred": 33158, + "n_ref": 33048 + }, + "4": { + "Dice": 0.9430051813471503, + "FN": 110, + "FP": 0, + "IoU": 0.8921568627450981, + "TN": 103428, + "TP": 910, + "n_pred": 910, + "n_ref": 1020 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0014.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0014.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9914642153644123, + "FN": 39, + "FP": 78, + "IoU": 0.9830729166666666, + "TN": 97536, + "TP": 6795, + "n_pred": 6873, + "n_ref": 6834 + }, + "2": { + "Dice": 0.9902515344806836, + "FN": 204, + "FP": 39, + "IoU": 0.9806912991656734, + "TN": 91863, + "TP": 12342, + "n_pred": 12381, + "n_ref": 12546 + }, + "3": { + "Dice": 0.9963173117956661, + "FN": 0, + "FP": 233, + "IoU": 0.9926616484520172, + "TN": 72697, + "TP": 31518, + "n_pred": 31751, + "n_ref": 31518 + }, + "4": { + "Dice": 0.8710570005534034, + "FN": 233, + "FP": 0, + "IoU": 0.7715686274509804, + "TN": 103428, + "TP": 787, + "n_pred": 787, + "n_ref": 1020 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0029.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0029.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9743589743589743, + "FN": 204, + "FP": 102, + "IoU": 0.95, + "TN": 98328, + "TP": 5814, + "n_pred": 5916, + "n_ref": 6018 + }, + "2": { + "Dice": 0.9888975762314308, + "FN": 102, + "FP": 182, + "IoU": 0.9780389730900093, + "TN": 91516, + "TP": 12648, + "n_pred": 12830, + "n_ref": 12750 + }, + "3": { + "Dice": 0.9935001515508706, + "FN": 182, + "FP": 204, + "IoU": 0.9870842534966205, + "TN": 74562, + "TP": 29500, + "n_pred": 29704, + "n_ref": 29682 + }, + "4": { + "Dice": 0.7692307692307693, + "FN": 204, + "FP": 102, + "IoU": 0.625, + "TN": 103632, + "TP": 510, + "n_pred": 612, + "n_ref": 714 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0034.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0034.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9880111155220326, + "FN": 0, + "FP": 151, + "IoU": 0.9763062921700926, + "TN": 98075, + "TP": 6222, + "n_pred": 6373, + "n_ref": 6222 + }, + "2": { + "Dice": 0.9997523649150611, + "FN": 5, + "FP": 0, + "IoU": 0.9995048524460289, + "TN": 94350, + "TP": 10093, + "n_pred": 10093, + "n_ref": 10098 + }, + "3": { + "Dice": 0.9982046678635548, + "FN": 0, + "FP": 102, + "IoU": 0.996415770609319, + "TN": 75990, + "TP": 28356, + "n_pred": 28458, + "n_ref": 28356 + }, + "4": { + "Dice": 0.8826291079812206, + "FN": 150, + "FP": 0, + "IoU": 0.7899159663865546, + "TN": 103734, + "TP": 564, + "n_pred": 564, + "n_ref": 714 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0036.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0036.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9772798495769351, + "FN": 189, + "FP": 101, + "IoU": 0.9555691741994791, + "TN": 97921, + "TP": 6237, + "n_pred": 6338, + "n_ref": 6426 + }, + "2": { + "Dice": 0.9906347554630593, + "FN": 0, + "FP": 189, + "IoU": 0.9814432989690721, + "TN": 94263, + "TP": 9996, + "n_pred": 10185, + "n_ref": 9996 + }, + "3": { + "Dice": 0.9955970505543472, + "FN": 0, + "FP": 249, + "IoU": 0.9912327030738354, + "TN": 76047, + "TP": 28152, + "n_pred": 28401, + "n_ref": 28152 + }, + "4": { + "Dice": 0.7921847246891652, + "FN": 351, + "FP": 0, + "IoU": 0.6558823529411765, + "TN": 103428, + "TP": 669, + "n_pred": 669, + "n_ref": 1020 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0038.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0038.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9711763178395222, + "FN": 0, + "FP": 333, + "IoU": 0.9439676930843008, + "TN": 98505, + "TP": 5610, + "n_pred": 5943, + "n_ref": 5610 + }, + "2": { + "Dice": 0.9894846615103849, + "FN": 140, + "FP": 102, + "IoU": 0.979188166494668, + "TN": 92820, + "TP": 11386, + "n_pred": 11488, + "n_ref": 11526 + }, + "3": { + "Dice": 0.9960663530908421, + "FN": 235, + "FP": 0, + "IoU": 0.9921635320794985, + "TN": 74460, + "TP": 29753, + "n_pred": 29753, + "n_ref": 29988 + }, + "4": { + "Dice": 0.8579040852575488, + "FN": 27, + "FP": 133, + "IoU": 0.7511664074650077, + "TN": 103805, + "TP": 483, + "n_pred": 616, + "n_ref": 510 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0041.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0041.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9725625798692025, + "FN": 365, + "FP": 0, + "IoU": 0.9465905765291192, + "TN": 97614, + "TP": 6469, + "n_pred": 6469, + "n_ref": 6834 + }, + "2": { + "Dice": 0.9858217051363586, + "FN": 84, + "FP": 295, + "IoU": 0.9720398376982663, + "TN": 90893, + "TP": 13176, + "n_pred": 13471, + "n_ref": 13260 + }, + "3": { + "Dice": 0.9974395276681628, + "FN": 38, + "FP": 132, + "IoU": 0.9948921338861847, + "TN": 71166, + "TP": 33112, + "n_pred": 33244, + "n_ref": 33150 + }, + "4": { + "Dice": 0.9328214971209213, + "FN": 48, + "FP": 92, + "IoU": 0.8741007194244604, + "TN": 103336, + "TP": 972, + "n_pred": 1064, + "n_ref": 1020 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0059.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0059.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9918847451445245, + "FN": 69, + "FP": 20, + "IoU": 0.9839001447178003, + "TN": 98920, + "TP": 5439, + "n_pred": 5459, + "n_ref": 5508 + }, + "2": { + "Dice": 0.9888817065287654, + "FN": 103, + "FP": 69, + "IoU": 0.978007927375016, + "TN": 96627, + "TP": 7649, + "n_pred": 7718, + "n_ref": 7752 + }, + "3": { + "Dice": 0.9956333747163834, + "FN": 101, + "FP": 103, + "IoU": 0.9913047184689485, + "TN": 80987, + "TP": 23257, + "n_pred": 23360, + "n_ref": 23358 + }, + "4": { + "Dice": 0.769811320754717, + "FN": 0, + "FP": 305, + "IoU": 0.6257668711656442, + "TN": 103633, + "TP": 510, + "n_pred": 815, + "n_ref": 510 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0073.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0073.png" + }, + { + "metrics": { + "1": { + "Dice": 0.991869918699187, + "FN": 102, + "FP": 0, + "IoU": 0.9838709677419355, + "TN": 98124, + "TP": 6222, + "n_pred": 6222, + "n_ref": 6324 + }, + "2": { + "Dice": 0.9957893952379178, + "FN": 0, + "FP": 113, + "IoU": 0.9916141001855288, + "TN": 90973, + "TP": 13362, + "n_pred": 13475, + "n_ref": 13362 + }, + "3": { + "Dice": 0.9980381516884418, + "FN": 141, + "FP": 0, + "IoU": 0.9960839860023329, + "TN": 68442, + "TP": 35865, + "n_pred": 35865, + "n_ref": 36006 + }, + "4": { + "Dice": 0.8301119023397762, + "FN": 204, + "FP": 130, + "IoU": 0.7095652173913043, + "TN": 103298, + "TP": 816, + "n_pred": 946, + "n_ref": 1020 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0077.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0077.png" + }, + { + "metrics": { + "1": { + "Dice": 0.992, + "FN": 0, + "FP": 102, + "IoU": 0.9841269841269841, + "TN": 98022, + "TP": 6324, + "n_pred": 6426, + "n_ref": 6324 + }, + "2": { + "Dice": 0.9876543209876543, + "FN": 102, + "FP": 102, + "IoU": 0.975609756097561, + "TN": 96084, + "TP": 8160, + "n_pred": 8262, + "n_ref": 8262 + }, + "3": { + "Dice": 0.9938714354760754, + "FN": 102, + "FP": 215, + "IoU": 0.98781753199339, + "TN": 78427, + "TP": 25704, + "n_pred": 25919, + "n_ref": 25806 + }, + "4": { + "Dice": 0.5903345724907063, + "FN": 215, + "FP": 336, + "IoU": 0.41877637130801687, + "TN": 103500, + "TP": 397, + "n_pred": 733, + "n_ref": 612 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0080.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0080.png" + }, + { + "metrics": { + "1": { + "Dice": 0.991869918699187, + "FN": 102, + "FP": 0, + "IoU": 0.9838709677419355, + "TN": 98124, + "TP": 6222, + "n_pred": 6222, + "n_ref": 6324 + }, + "2": { + "Dice": 0.9974908318857364, + "FN": 0, + "FP": 39, + "IoU": 0.9949942241047363, + "TN": 96657, + "TP": 7752, + "n_pred": 7791, + "n_ref": 7752 + }, + "3": { + "Dice": 0.9983026188166828, + "FN": 84, + "FP": 0, + "IoU": 0.9966109900750424, + "TN": 79662, + "TP": 24702, + "n_pred": 24702, + "n_ref": 24786 + }, + "4": { + "Dice": 0.884125144843569, + "FN": 155, + "FP": 45, + "IoU": 0.7923156801661475, + "TN": 103485, + "TP": 763, + "n_pred": 808, + "n_ref": 918 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0081.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0081.png" + }, + { + "metrics": { + "1": { + "Dice": 0.991675338189386, + "FN": 96, + "FP": 0, + "IoU": 0.9834881320949432, + "TN": 98634, + "TP": 5718, + "n_pred": 5718, + "n_ref": 5814 + }, + "2": { + "Dice": 0.9959183673469387, + "FN": 0, + "FP": 102, + "IoU": 0.991869918699187, + "TN": 91902, + "TP": 12444, + "n_pred": 12546, + "n_ref": 12444 + }, + "3": { + "Dice": 0.9942427141953585, + "FN": 355, + "FP": 0, + "IoU": 0.9885513415892673, + "TN": 73440, + "TP": 30653, + "n_pred": 30653, + "n_ref": 31008 + }, + "4": { + "Dice": 0.7751741608613046, + "FN": 0, + "FP": 355, + "IoU": 0.6328852119958635, + "TN": 103481, + "TP": 612, + "n_pred": 967, + "n_ref": 612 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0082.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0082.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9976336961665878, + "FN": 0, + "FP": 30, + "IoU": 0.9952785646836638, + "TN": 98094, + "TP": 6324, + "n_pred": 6354, + "n_ref": 6324 + }, + "2": { + "Dice": 0.9988761519442572, + "FN": 30, + "FP": 0, + "IoU": 0.9977548271216884, + "TN": 91086, + "TP": 13332, + "n_pred": 13332, + "n_ref": 13362 + }, + "3": { + "Dice": 0.9953775038520801, + "FN": 0, + "FP": 306, + "IoU": 0.99079754601227, + "TN": 71196, + "TP": 32946, + "n_pred": 33252, + "n_ref": 32946 + }, + "4": { + "Dice": 0.7619047619047619, + "FN": 510, + "FP": 0, + "IoU": 0.6153846153846154, + "TN": 103122, + "TP": 816, + "n_pred": 816, + "n_ref": 1326 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0091.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0091.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9839080459770115, + "FN": 210, + "FP": 0, + "IoU": 0.9683257918552036, + "TN": 97818, + "TP": 6420, + "n_pred": 6420, + "n_ref": 6630 + }, + "2": { + "Dice": 1.0, + "FN": 0, + "FP": 0, + "IoU": 1.0, + "TN": 96288, + "TP": 8160, + "n_pred": 8160, + "n_ref": 8160 + }, + "3": { + "Dice": 0.9928987473071093, + "FN": 0, + "FP": 356, + "IoU": 0.9858976390429409, + "TN": 79204, + "TP": 24888, + "n_pred": 25244, + "n_ref": 24888 + }, + "4": { + "Dice": 0.7385019710906702, + "FN": 356, + "FP": 42, + "IoU": 0.5854166666666667, + "TN": 103488, + "TP": 562, + "n_pred": 604, + "n_ref": 918 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0098.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0098.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9838543455857094, + "FN": 86, + "FP": 102, + "IoU": 0.9682217714672076, + "TN": 98532, + "TP": 5728, + "n_pred": 5830, + "n_ref": 5814 + }, + "2": { + "Dice": 0.9900822958430049, + "FN": 102, + "FP": 86, + "IoU": 0.9803593815294609, + "TN": 94876, + "TP": 9384, + "n_pred": 9470, + "n_ref": 9486 + }, + "3": { + "Dice": 0.9951407665109947, + "FN": 0, + "FP": 257, + "IoU": 0.9903285289579649, + "TN": 77875, + "TP": 26316, + "n_pred": 26573, + "n_ref": 26316 + }, + "4": { + "Dice": 0.802013422818792, + "FN": 236, + "FP": 0, + "IoU": 0.6694677871148459, + "TN": 103734, + "TP": 478, + "n_pred": 478, + "n_ref": 714 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0101.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0101.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9824868651488616, + "FN": 102, + "FP": 98, + "IoU": 0.9655765920826161, + "TN": 98638, + "TP": 5610, + "n_pred": 5708, + "n_ref": 5712 + }, + "2": { + "Dice": 0.9937106918238994, + "FN": 0, + "FP": 102, + "IoU": 0.9875, + "TN": 96288, + "TP": 8058, + "n_pred": 8160, + "n_ref": 8058 + }, + "3": { + "Dice": 0.9930940982078549, + "FN": 326, + "FP": 0, + "IoU": 0.9862829251872423, + "TN": 80682, + "TP": 23440, + "n_pred": 23440, + "n_ref": 23766 + }, + "4": { + "Dice": 0.6289825282631039, + "FN": 0, + "FP": 361, + "IoU": 0.4587706146926537, + "TN": 103781, + "TP": 306, + "n_pred": 667, + "n_ref": 306 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0104.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0104.png" + }, + { + "metrics": { + "1": { + "Dice": 0.986527450319973, + "FN": 160, + "FP": 0, + "IoU": 0.9734130940511798, + "TN": 98430, + "TP": 5858, + "n_pred": 5858, + "n_ref": 6018 + }, + "2": { + "Dice": 0.9927747223120889, + "FN": 76, + "FP": 58, + "IoU": 0.9856531049250535, + "TN": 95108, + "TP": 9206, + "n_pred": 9264, + "n_ref": 9282 + }, + "3": { + "Dice": 0.9947285187137586, + "FN": 204, + "FP": 76, + "IoU": 0.989512323020451, + "TN": 77750, + "TP": 26418, + "n_pred": 26494, + "n_ref": 26622 + }, + "4": { + "Dice": 0.7479376718606783, + "FN": 0, + "FP": 275, + "IoU": 0.5973645680819912, + "TN": 103765, + "TP": 408, + "n_pred": 683, + "n_ref": 408 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0105.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0105.png" + }, + { + "metrics": { + "1": { + "Dice": 0.9933005085156187, + "FN": 69, + "FP": 14, + "IoU": 0.9866901860166774, + "TN": 98212, + "TP": 6153, + "n_pred": 6167, + "n_ref": 6222 + }, + "2": { + "Dice": 0.9956804398097648, + "FN": 14, + "FP": 85, + "IoU": 0.9913980363194022, + "TN": 92939, + "TP": 11410, + "n_pred": 11495, + "n_ref": 11424 + }, + "3": { + "Dice": 0.99561305417448, + "FN": 32, + "FP": 223, + "IoU": 0.9912644308177178, + "TN": 75257, + "TP": 28936, + "n_pred": 29159, + "n_ref": 28968 + }, + "4": { + "Dice": 0.7722222222222223, + "FN": 223, + "FP": 187, + "IoU": 0.6289592760180995, + "TN": 103343, + "TP": 695, + "n_pred": 882, + "n_ref": 918 + } + }, + "prediction_file": "/hpc/rlav440/NNUNET_DATA/results/Dataset001_zebrafish/nnUNetTrainer__nnUNetPlans__2d/fold_4/validation/fish0106.png", + "reference_file": "/hpc/rlav440/NNUNET_DATA/processed/Dataset001_zebrafish/gt_segmentations/fish0106.png" + } + ] +} \ No newline at end of file diff --git a/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/plans.json b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/plans.json new file mode 100644 index 0000000000000000000000000000000000000000..70918bac88c22dabb48fbe5f718884ca5f59e4f5 --- /dev/null +++ b/Dataset002_zebrafish/nnUNetTrainer__nnUNetPlans__2d/plans.json @@ -0,0 +1,207 @@ +{ + "dataset_name": "Dataset001_zebrafish", + "plans_name": "nnUNetPlans", + "original_median_spacing_after_transp": [ + 999.0, + 1.0, + 1.0 + ], + "original_median_shape_after_transp": [ + 1, + 1024, + 102 + ], + "image_reader_writer": "NaturalImage2DIO", + "transpose_forward": [ + 0, + 1, + 2 + ], + "transpose_backward": [ + 0, + 1, + 2 + ], + "configurations": { + "2d": { + "data_identifier": "nnUNetPlans_2d", + "preprocessor_name": "DefaultPreprocessor", + "batch_size": 5, + "patch_size": [ + 1024, + 112 + ], + "median_image_size_in_voxels": [ + 1024.0, + 102.0 + ], + "spacing": [ + 1.0, + 1.0 + ], + "normalization_schemes": [ + "ZScoreNormalization" + ], + "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": null + }, + "resampling_fn_seg_kwargs": { + "is_seg": true, + "order": 1, + "order_z": 0, + "force_separate_z": null + }, + "resampling_fn_probabilities": "resample_data_or_seg_to_shape", + "resampling_fn_probabilities_kwargs": { + "is_seg": false, + "order": 1, + "order_z": 0, + "force_separate_z": null + }, + "architecture": { + "network_class_name": "dynamic_network_architectures.architectures.unet.PlainConvUNet", + "arch_kwargs": { + "n_stages": 8, + "features_per_stage": [ + 32, + 64, + 128, + 256, + 512, + 512, + 512, + 512 + ], + "conv_op": "torch.nn.modules.conv.Conv2d", + "kernel_sizes": [ + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ] + ], + "strides": [ + [ + 1, + 1 + ], + [ + 2, + 2 + ], + [ + 2, + 2 + ], + [ + 2, + 2 + ], + [ + 2, + 2 + ], + [ + 2, + 1 + ], + [ + 2, + 1 + ], + [ + 2, + 1 + ] + ], + "n_conv_per_stage": [ + 2, + 2, + 2, + 2, + 2, + 2, + 2, + 2 + ], + "n_conv_per_stage_decoder": [ + 2, + 2, + 2, + 2, + 2, + 2, + 2 + ], + "conv_bias": true, + "norm_op": "torch.nn.modules.instancenorm.InstanceNorm2d", + "norm_op_kwargs": { + "eps": 1e-05, + "affine": true + }, + "dropout_op": null, + "dropout_op_kwargs": null, + "nonlin": "torch.nn.LeakyReLU", + "nonlin_kwargs": { + "inplace": true + } + }, + "_kw_requires_import": [ + "conv_op", + "norm_op", + "dropout_op", + "nonlin" + ] + }, + "batch_dice": true + } + }, + "experiment_planner_used": "ExperimentPlanner", + "label_manager": "LabelManager", + "foreground_intensity_properties_per_channel": { + "0": { + "max": 255.0, + "mean": 49.659568786621094, + "median": 45.0, + "min": 0.0, + "percentile_00_5": 10.0, + "percentile_99_5": 163.0, + "std": 24.689043045043945 + } + } +} \ No newline at end of file