diff --git "a/training_log_2023_5_26_12_19_26.txt" "b/training_log_2023_5_26_12_19_26.txt" new file mode 100644--- /dev/null +++ "b/training_log_2023_5_26_12_19_26.txt" @@ -0,0 +1,7344 @@ + +####################################################################### +Please cite the following paper when using nnU-Net: +Isensee, F., Jaeger, P. F., Kohl, S. A., Petersen, J., & Maier-Hein, K. H. (2021). nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nature methods, 18(2), 203-211. +####################################################################### + + +This is the configuration used by this training: +Configuration name: 2d + {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 49, 'patch_size': [256, 256], 'median_image_size_in_voxels': [256.0, 256.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['ZScoreNormalization'], 'use_mask_for_norm': [False], 'UNet_class_name': 'PlainConvUNet', 'UNet_base_num_features': 32, 'n_conv_per_stage_encoder': [2, 2, 2, 2, 2, 2, 2], 'n_conv_per_stage_decoder': [2, 2, 2, 2, 2, 2], 'num_pool_per_axis': [6, 6], 'pool_op_kernel_sizes': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2]], 'conv_kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'unet_max_num_features': 512, '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}, 'batch_dice': True} + +These are the global plan.json settings: + {'dataset_name': 'Dataset001_CAMUS', 'plans_name': 'nnUNetPlans', 'original_median_spacing_after_transp': [999.0, 1.0, 1.0], 'original_median_shape_after_transp': [1, 256, 256], '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': 83.52889251708984, 'median': 77.0, 'min': 0.0, 'percentile_00_5': 0.0, 'percentile_99_5': 226.0, 'std': 43.63010787963867}}} + +2023-05-26 12:19:48.607948: unpacking dataset... +2023-05-26 12:19:49.565891: unpacking done... +2023-05-26 12:19:49.566520: do_dummy_2d_data_aug: False +2023-05-26 12:19:49.578200: Using splits from existing split file: /home/gillesv/data/nnUNet_preprocessed/Dataset001_CAMUS/splits_final.json +2023-05-26 12:19:49.581342: The split file contains 10 splits. +2023-05-26 12:19:49.581432: Desired fold for training: 0 +2023-05-26 12:19:49.581470: This split has 1600 training and 200 validation cases. +2023-05-26 12:20:20.132755: +2023-05-26 12:20:20.133029: Epoch 0 +2023-05-26 12:20:20.133389: Current learning rate: 0.01 +2023-05-26 12:21:07.437562: train_loss 0.0757 +2023-05-26 12:21:07.437933: val_loss -0.5183 +2023-05-26 12:21:07.438057: Pseudo dice [0.8632, 0.7206, 0.7609] +2023-05-26 12:21:07.438168: Epoch time: 47.31 s +2023-05-26 12:21:07.438258: Yayy! New best EMA pseudo Dice: 0.7816 +2023-05-26 12:21:09.313835: +2023-05-26 12:21:09.314148: Epoch 1 +2023-05-26 12:21:09.314288: Current learning rate: 0.00999 +2023-05-26 12:21:41.313178: train_loss -0.608 +2023-05-26 12:21:41.313439: val_loss -0.6545 +2023-05-26 12:21:41.313552: Pseudo dice [0.8891, 0.788, 0.8456] +2023-05-26 12:21:41.313651: Epoch time: 32.0 s +2023-05-26 12:21:41.313734: Yayy! New best EMA pseudo Dice: 0.7875 +2023-05-26 12:21:44.308617: +2023-05-26 12:21:44.309056: Epoch 2 +2023-05-26 12:21:44.309280: Current learning rate: 0.00998 +2023-05-26 12:22:18.476561: train_loss -0.7083 +2023-05-26 12:22:18.476881: val_loss -0.7 +2023-05-26 12:22:18.477011: Pseudo dice [0.9038, 0.8084, 0.8659] +2023-05-26 12:22:18.477108: Epoch time: 34.17 s +2023-05-26 12:22:18.477185: Yayy! New best EMA pseudo Dice: 0.7947 +2023-05-26 12:22:21.343277: +2023-05-26 12:22:21.343697: Epoch 3 +2023-05-26 12:22:21.343919: Current learning rate: 0.00997 +2023-05-26 12:22:54.530505: train_loss -0.7468 +2023-05-26 12:22:54.534238: val_loss -0.7214 +2023-05-26 12:22:54.534516: Pseudo dice [0.9092, 0.8231, 0.8741] +2023-05-26 12:22:54.534671: Epoch time: 33.19 s +2023-05-26 12:22:54.534796: Yayy! New best EMA pseudo Dice: 0.8021 +2023-05-26 12:22:57.380894: +2023-05-26 12:22:57.381101: Epoch 4 +2023-05-26 12:22:57.381220: Current learning rate: 0.00996 +2023-05-26 12:23:30.261922: train_loss -0.769 +2023-05-26 12:23:30.262199: val_loss -0.7397 +2023-05-26 12:23:30.262367: Pseudo dice [0.9173, 0.8303, 0.8851] +2023-05-26 12:23:30.262480: Epoch time: 32.88 s +2023-05-26 12:23:30.262713: Yayy! New best EMA pseudo Dice: 0.8097 +2023-05-26 12:23:33.034216: +2023-05-26 12:23:33.034506: Epoch 5 +2023-05-26 12:23:33.034715: Current learning rate: 0.00995 +2023-05-26 12:24:05.638813: train_loss -0.7841 +2023-05-26 12:24:05.639095: val_loss -0.7434 +2023-05-26 12:24:05.639609: Pseudo dice [0.9144, 0.8327, 0.8945] +2023-05-26 12:24:05.639717: Epoch time: 32.61 s +2023-05-26 12:24:05.639797: Yayy! New best EMA pseudo Dice: 0.8167 +2023-05-26 12:24:08.581486: +2023-05-26 12:24:08.581810: Epoch 6 +2023-05-26 12:24:08.582066: Current learning rate: 0.00995 +2023-05-26 12:24:42.414718: train_loss -0.7942 +2023-05-26 12:24:42.415024: val_loss -0.752 +2023-05-26 12:24:42.415149: Pseudo dice [0.9215, 0.8394, 0.8977] +2023-05-26 12:24:42.415242: Epoch time: 33.83 s +2023-05-26 12:24:42.415315: Yayy! New best EMA pseudo Dice: 0.8237 +2023-05-26 12:24:45.344031: +2023-05-26 12:24:45.344210: Epoch 7 +2023-05-26 12:24:45.344657: Current learning rate: 0.00994 +2023-05-26 12:25:19.561022: train_loss -0.8031 +2023-05-26 12:25:19.561306: val_loss -0.7547 +2023-05-26 12:25:19.561439: Pseudo dice [0.9225, 0.8428, 0.8935] +2023-05-26 12:25:19.561533: Epoch time: 34.22 s +2023-05-26 12:25:19.561607: Yayy! New best EMA pseudo Dice: 0.8299 +2023-05-26 12:25:22.834550: +2023-05-26 12:25:22.834743: Epoch 8 +2023-05-26 12:25:22.834887: Current learning rate: 0.00993 +2023-05-26 12:25:56.182307: train_loss -0.8092 +2023-05-26 12:25:56.182573: val_loss -0.7632 +2023-05-26 12:25:56.182690: Pseudo dice [0.9281, 0.8486, 0.8957] +2023-05-26 12:25:56.182777: Epoch time: 33.35 s +2023-05-26 12:25:56.182869: Yayy! New best EMA pseudo Dice: 0.836 +2023-05-26 12:25:59.089313: +2023-05-26 12:25:59.089536: Epoch 9 +2023-05-26 12:25:59.089681: Current learning rate: 0.00992 +2023-05-26 12:26:31.925332: train_loss -0.8163 +2023-05-26 12:26:31.925589: val_loss -0.7518 +2023-05-26 12:26:31.925719: Pseudo dice [0.9252, 0.8445, 0.8918] +2023-05-26 12:26:31.925809: Epoch time: 32.84 s +2023-05-26 12:26:31.925881: Yayy! New best EMA pseudo Dice: 0.8411 +2023-05-26 12:26:35.180249: +2023-05-26 12:26:35.180433: Epoch 10 +2023-05-26 12:26:35.180557: Current learning rate: 0.00991 +2023-05-26 12:27:07.816105: train_loss -0.8224 +2023-05-26 12:27:07.816378: val_loss -0.7462 +2023-05-26 12:27:07.816530: Pseudo dice [0.9235, 0.8391, 0.8922] +2023-05-26 12:27:07.816832: Epoch time: 32.64 s +2023-05-26 12:27:07.817261: Yayy! New best EMA pseudo Dice: 0.8455 +2023-05-26 12:27:10.771349: +2023-05-26 12:27:10.771545: Epoch 11 +2023-05-26 12:27:10.771679: Current learning rate: 0.0099 +2023-05-26 12:27:43.705895: train_loss -0.8243 +2023-05-26 12:27:43.706122: val_loss -0.7655 +2023-05-26 12:27:43.706237: Pseudo dice [0.9278, 0.8516, 0.9008] +2023-05-26 12:27:43.706340: Epoch time: 32.94 s +2023-05-26 12:27:43.706409: Yayy! New best EMA pseudo Dice: 0.8503 +2023-05-26 12:27:46.563260: +2023-05-26 12:27:46.563424: Epoch 12 +2023-05-26 12:27:46.563543: Current learning rate: 0.00989 +2023-05-26 12:28:19.402983: train_loss -0.831 +2023-05-26 12:28:19.403231: val_loss -0.7549 +2023-05-26 12:28:19.403364: Pseudo dice [0.9261, 0.8469, 0.8972] +2023-05-26 12:28:19.403478: Epoch time: 32.84 s +2023-05-26 12:28:19.403553: Yayy! New best EMA pseudo Dice: 0.8543 +2023-05-26 12:28:22.399861: +2023-05-26 12:28:22.400024: Epoch 13 +2023-05-26 12:28:22.400153: Current learning rate: 0.00988 +2023-05-26 12:28:55.172387: train_loss -0.8376 +2023-05-26 12:28:55.172651: val_loss -0.7551 +2023-05-26 12:28:55.172798: Pseudo dice [0.9274, 0.8458, 0.8956] +2023-05-26 12:28:55.173071: Epoch time: 32.77 s +2023-05-26 12:28:55.173345: Yayy! New best EMA pseudo Dice: 0.8578 +2023-05-26 12:28:58.582024: +2023-05-26 12:28:58.582468: Epoch 14 +2023-05-26 12:28:58.582866: Current learning rate: 0.00987 +2023-05-26 12:29:31.351827: train_loss -0.8413 +2023-05-26 12:29:31.352184: val_loss -0.7489 +2023-05-26 12:29:31.352340: Pseudo dice [0.9244, 0.8445, 0.894] +2023-05-26 12:29:31.352470: Epoch time: 32.77 s +2023-05-26 12:29:31.352555: Yayy! New best EMA pseudo Dice: 0.8608 +2023-05-26 12:29:34.217328: +2023-05-26 12:29:34.217503: Epoch 15 +2023-05-26 12:29:34.217623: Current learning rate: 0.00986 +2023-05-26 12:30:06.951694: train_loss -0.8414 +2023-05-26 12:30:06.951934: val_loss -0.7623 +2023-05-26 12:30:06.959350: Pseudo dice [0.926, 0.8485, 0.9011] +2023-05-26 12:30:06.959765: Epoch time: 32.74 s +2023-05-26 12:30:06.960024: Yayy! New best EMA pseudo Dice: 0.8639 +2023-05-26 12:30:10.001066: +2023-05-26 12:30:10.001553: Epoch 16 +2023-05-26 12:30:10.001681: Current learning rate: 0.00986 +2023-05-26 12:30:42.707352: train_loss -0.8472 +2023-05-26 12:30:42.707599: val_loss -0.7605 +2023-05-26 12:30:42.708221: Pseudo dice [0.9295, 0.8528, 0.8992] +2023-05-26 12:30:42.708321: Epoch time: 32.71 s +2023-05-26 12:30:42.708395: Yayy! New best EMA pseudo Dice: 0.8669 +2023-05-26 12:30:45.504407: +2023-05-26 12:30:45.504874: Epoch 17 +2023-05-26 12:30:45.505135: Current learning rate: 0.00985 +2023-05-26 12:31:18.379353: train_loss -0.852 +2023-05-26 12:31:18.379626: val_loss -0.755 +2023-05-26 12:31:18.379776: Pseudo dice [0.9285, 0.8481, 0.8986] +2023-05-26 12:31:18.379943: Epoch time: 32.88 s +2023-05-26 12:31:18.380025: Yayy! New best EMA pseudo Dice: 0.8694 +2023-05-26 12:31:21.528251: +2023-05-26 12:31:21.528404: Epoch 18 +2023-05-26 12:31:21.528514: Current learning rate: 0.00984 +2023-05-26 12:31:54.507842: train_loss -0.8563 +2023-05-26 12:31:54.508098: val_loss -0.7524 +2023-05-26 12:31:54.508230: Pseudo dice [0.9276, 0.8529, 0.894] +2023-05-26 12:31:54.508338: Epoch time: 32.98 s +2023-05-26 12:31:54.508420: Yayy! New best EMA pseudo Dice: 0.8716 +2023-05-26 12:31:58.125802: +2023-05-26 12:31:58.126120: Epoch 19 +2023-05-26 12:31:58.126331: Current learning rate: 0.00983 +2023-05-26 12:32:31.721945: train_loss -0.858 +2023-05-26 12:32:31.722288: val_loss -0.7518 +2023-05-26 12:32:31.722409: Pseudo dice [0.9296, 0.8499, 0.8964] +2023-05-26 12:32:31.722500: Epoch time: 33.6 s +2023-05-26 12:32:31.722578: Yayy! New best EMA pseudo Dice: 0.8736 +2023-05-26 12:32:34.694108: +2023-05-26 12:32:34.694340: Epoch 20 +2023-05-26 12:32:34.694469: Current learning rate: 0.00982 +2023-05-26 12:33:07.533309: train_loss -0.8594 +2023-05-26 12:33:07.533574: val_loss -0.7516 +2023-05-26 12:33:07.533720: Pseudo dice [0.9294, 0.8502, 0.8986] +2023-05-26 12:33:07.533825: Epoch time: 32.84 s +2023-05-26 12:33:07.533911: Yayy! New best EMA pseudo Dice: 0.8755 +2023-05-26 12:33:10.400497: +2023-05-26 12:33:10.400700: Epoch 21 +2023-05-26 12:33:10.400904: Current learning rate: 0.00981 +2023-05-26 12:33:43.230804: train_loss -0.8628 +2023-05-26 12:33:43.231139: val_loss -0.7577 +2023-05-26 12:33:43.231265: Pseudo dice [0.9308, 0.8519, 0.8994] +2023-05-26 12:33:43.231354: Epoch time: 32.83 s +2023-05-26 12:33:43.231425: Yayy! New best EMA pseudo Dice: 0.8774 +2023-05-26 12:33:46.177202: +2023-05-26 12:33:46.177583: Epoch 22 +2023-05-26 12:33:46.177712: Current learning rate: 0.0098 +2023-05-26 12:34:18.845626: train_loss -0.8643 +2023-05-26 12:34:18.845891: val_loss -0.7529 +2023-05-26 12:34:18.846011: Pseudo dice [0.93, 0.8506, 0.9017] +2023-05-26 12:34:18.846096: Epoch time: 32.67 s +2023-05-26 12:34:18.846163: Yayy! New best EMA pseudo Dice: 0.8791 +2023-05-26 12:34:22.651089: +2023-05-26 12:34:22.651269: Epoch 23 +2023-05-26 12:34:22.651390: Current learning rate: 0.00979 +2023-05-26 12:34:55.291244: train_loss -0.8677 +2023-05-26 12:34:55.291515: val_loss -0.7566 +2023-05-26 12:34:55.291647: Pseudo dice [0.9331, 0.8543, 0.8998] +2023-05-26 12:34:55.291758: Epoch time: 32.64 s +2023-05-26 12:34:55.291832: Yayy! New best EMA pseudo Dice: 0.8807 +2023-05-26 12:34:58.015812: +2023-05-26 12:34:58.015960: Epoch 24 +2023-05-26 12:34:58.016059: Current learning rate: 0.00978 +2023-05-26 12:35:30.631356: train_loss -0.87 +2023-05-26 12:35:30.631682: val_loss -0.7412 +2023-05-26 12:35:30.631819: Pseudo dice [0.9266, 0.8517, 0.8964] +2023-05-26 12:35:30.631924: Epoch time: 32.62 s +2023-05-26 12:35:30.632007: Yayy! New best EMA pseudo Dice: 0.8818 +2023-05-26 12:35:33.549664: +2023-05-26 12:35:33.549945: Epoch 25 +2023-05-26 12:35:33.550087: Current learning rate: 0.00977 +2023-05-26 12:36:06.200224: train_loss -0.8707 +2023-05-26 12:36:06.200497: val_loss -0.7531 +2023-05-26 12:36:06.200625: Pseudo dice [0.9311, 0.8538, 0.9022] +2023-05-26 12:36:06.200720: Epoch time: 32.65 s +2023-05-26 12:36:06.200799: Yayy! New best EMA pseudo Dice: 0.8832 +2023-05-26 12:36:09.326748: +2023-05-26 12:36:09.326984: Epoch 26 +2023-05-26 12:36:09.327123: Current learning rate: 0.00977 +2023-05-26 12:36:41.957173: train_loss -0.8728 +2023-05-26 12:36:41.957479: val_loss -0.7442 +2023-05-26 12:36:41.957612: Pseudo dice [0.9301, 0.8521, 0.8985] +2023-05-26 12:36:41.957751: Epoch time: 32.63 s +2023-05-26 12:36:41.957830: Yayy! New best EMA pseudo Dice: 0.8842 +2023-05-26 12:36:44.535317: +2023-05-26 12:36:44.535690: Epoch 27 +2023-05-26 12:36:44.535871: Current learning rate: 0.00976 +2023-05-26 12:37:17.569151: train_loss -0.8757 +2023-05-26 12:37:17.569486: val_loss -0.7428 +2023-05-26 12:37:17.569621: Pseudo dice [0.9296, 0.8531, 0.8951] +2023-05-26 12:37:17.569717: Epoch time: 33.04 s +2023-05-26 12:37:17.569790: Yayy! New best EMA pseudo Dice: 0.8851 +2023-05-26 12:37:20.311875: +2023-05-26 12:37:20.312041: Epoch 28 +2023-05-26 12:37:20.312145: Current learning rate: 0.00975 +2023-05-26 12:37:53.145057: train_loss -0.8785 +2023-05-26 12:37:53.145370: val_loss -0.7429 +2023-05-26 12:37:53.145569: Pseudo dice [0.9316, 0.8518, 0.8996] +2023-05-26 12:37:53.145721: Epoch time: 32.83 s +2023-05-26 12:37:53.145849: Yayy! New best EMA pseudo Dice: 0.886 +2023-05-26 12:37:56.095517: +2023-05-26 12:37:56.095692: Epoch 29 +2023-05-26 12:37:56.095818: Current learning rate: 0.00974 +2023-05-26 12:38:29.393201: train_loss -0.8791 +2023-05-26 12:38:29.393521: val_loss -0.7445 +2023-05-26 12:38:29.393756: Pseudo dice [0.9304, 0.8514, 0.9012] +2023-05-26 12:38:29.393948: Epoch time: 33.3 s +2023-05-26 12:38:29.394100: Yayy! New best EMA pseudo Dice: 0.8868 +2023-05-26 12:38:32.238688: +2023-05-26 12:38:32.239503: Epoch 30 +2023-05-26 12:38:32.239834: Current learning rate: 0.00973 +2023-05-26 12:39:05.003427: train_loss -0.8795 +2023-05-26 12:39:05.003662: val_loss -0.7455 +2023-05-26 12:39:05.003781: Pseudo dice [0.9304, 0.8528, 0.8989] +2023-05-26 12:39:05.003881: Epoch time: 32.77 s +2023-05-26 12:39:05.003953: Yayy! New best EMA pseudo Dice: 0.8876 +2023-05-26 12:39:07.687067: +2023-05-26 12:39:07.687227: Epoch 31 +2023-05-26 12:39:07.687355: Current learning rate: 0.00972 +2023-05-26 12:39:40.340310: train_loss -0.8779 +2023-05-26 12:39:40.340593: val_loss -0.744 +2023-05-26 12:39:40.341217: Pseudo dice [0.928, 0.853, 0.8987] +2023-05-26 12:39:40.341368: Epoch time: 32.65 s +2023-05-26 12:39:40.341456: Yayy! New best EMA pseudo Dice: 0.8881 +2023-05-26 12:39:43.479433: +2023-05-26 12:39:43.479631: Epoch 32 +2023-05-26 12:39:43.479740: Current learning rate: 0.00971 +2023-05-26 12:40:16.168122: train_loss -0.8824 +2023-05-26 12:40:16.168352: val_loss -0.7362 +2023-05-26 12:40:16.168464: Pseudo dice [0.9275, 0.8497, 0.9018] +2023-05-26 12:40:16.168567: Epoch time: 32.69 s +2023-05-26 12:40:16.168635: Yayy! New best EMA pseudo Dice: 0.8886 +2023-05-26 12:40:18.858373: +2023-05-26 12:40:18.858552: Epoch 33 +2023-05-26 12:40:18.858670: Current learning rate: 0.0097 +2023-05-26 12:40:51.670283: train_loss -0.8857 +2023-05-26 12:40:51.670555: val_loss -0.7506 +2023-05-26 12:40:51.670682: Pseudo dice [0.9341, 0.8562, 0.901] +2023-05-26 12:40:51.670775: Epoch time: 32.81 s +2023-05-26 12:40:51.670881: Yayy! New best EMA pseudo Dice: 0.8895 +2023-05-26 12:40:54.669188: +2023-05-26 12:40:54.669542: Epoch 34 +2023-05-26 12:40:54.669780: Current learning rate: 0.00969 +2023-05-26 12:41:27.420040: train_loss -0.8855 +2023-05-26 12:41:27.420278: val_loss -0.7381 +2023-05-26 12:41:27.420400: Pseudo dice [0.9301, 0.8524, 0.8954] +2023-05-26 12:41:27.420484: Epoch time: 32.75 s +2023-05-26 12:41:27.420565: Yayy! New best EMA pseudo Dice: 0.8898 +2023-05-26 12:41:30.440362: +2023-05-26 12:41:30.440685: Epoch 35 +2023-05-26 12:41:30.440907: Current learning rate: 0.00968 +2023-05-26 12:42:03.250428: train_loss -0.8853 +2023-05-26 12:42:03.250922: val_loss -0.7389 +2023-05-26 12:42:03.251104: Pseudo dice [0.9318, 0.8533, 0.8995] +2023-05-26 12:42:03.251199: Epoch time: 32.81 s +2023-05-26 12:42:03.251276: Yayy! New best EMA pseudo Dice: 0.8903 +2023-05-26 12:42:06.088307: +2023-05-26 12:42:06.088765: Epoch 36 +2023-05-26 12:42:06.088909: Current learning rate: 0.00968 +2023-05-26 12:42:38.864350: train_loss -0.8875 +2023-05-26 12:42:38.864617: val_loss -0.7456 +2023-05-26 12:42:38.864747: Pseudo dice [0.9308, 0.8578, 0.9009] +2023-05-26 12:42:38.864857: Epoch time: 32.78 s +2023-05-26 12:42:38.864937: Yayy! New best EMA pseudo Dice: 0.8909 +2023-05-26 12:42:41.494173: +2023-05-26 12:42:41.494539: Epoch 37 +2023-05-26 12:42:41.494682: Current learning rate: 0.00967 +2023-05-26 12:43:14.618531: train_loss -0.8909 +2023-05-26 12:43:14.618766: val_loss -0.7349 +2023-05-26 12:43:14.618914: Pseudo dice [0.9322, 0.8541, 0.8982] +2023-05-26 12:43:14.619005: Epoch time: 33.13 s +2023-05-26 12:43:14.619078: Yayy! New best EMA pseudo Dice: 0.8913 +2023-05-26 12:43:17.573220: +2023-05-26 12:43:17.573586: Epoch 38 +2023-05-26 12:43:17.573818: Current learning rate: 0.00966 +2023-05-26 12:43:50.409337: train_loss -0.8896 +2023-05-26 12:43:50.409579: val_loss -0.735 +2023-05-26 12:43:50.409723: Pseudo dice [0.9302, 0.8527, 0.9006] +2023-05-26 12:43:50.409830: Epoch time: 32.84 s +2023-05-26 12:43:50.409903: Yayy! New best EMA pseudo Dice: 0.8916 +2023-05-26 12:43:53.236653: +2023-05-26 12:43:53.236828: Epoch 39 +2023-05-26 12:43:53.236949: Current learning rate: 0.00965 +2023-05-26 12:44:25.969700: train_loss -0.8919 +2023-05-26 12:44:25.969982: val_loss -0.7313 +2023-05-26 12:44:25.970104: Pseudo dice [0.9306, 0.8515, 0.8997] +2023-05-26 12:44:25.970203: Epoch time: 32.73 s +2023-05-26 12:44:25.970280: Yayy! New best EMA pseudo Dice: 0.8919 +2023-05-26 12:44:28.978746: +2023-05-26 12:44:28.979344: Epoch 40 +2023-05-26 12:44:28.979487: Current learning rate: 0.00964 +2023-05-26 12:45:01.625461: train_loss -0.893 +2023-05-26 12:45:01.625775: val_loss -0.7381 +2023-05-26 12:45:01.625904: Pseudo dice [0.9303, 0.8567, 0.8983] +2023-05-26 12:45:01.626003: Epoch time: 32.65 s +2023-05-26 12:45:01.626081: Yayy! New best EMA pseudo Dice: 0.8922 +2023-05-26 12:45:04.629716: +2023-05-26 12:45:04.629911: Epoch 41 +2023-05-26 12:45:04.630026: Current learning rate: 0.00963 +2023-05-26 12:45:37.343695: train_loss -0.8938 +2023-05-26 12:45:37.343921: val_loss -0.7359 +2023-05-26 12:45:37.344031: Pseudo dice [0.9305, 0.856, 0.9008] +2023-05-26 12:45:37.344133: Epoch time: 32.72 s +2023-05-26 12:45:37.344200: Yayy! New best EMA pseudo Dice: 0.8925 +2023-05-26 12:45:40.683510: +2023-05-26 12:45:40.683702: Epoch 42 +2023-05-26 12:45:40.683833: Current learning rate: 0.00962 +2023-05-26 12:46:13.349310: train_loss -0.8953 +2023-05-26 12:46:13.349593: val_loss -0.7312 +2023-05-26 12:46:13.349738: Pseudo dice [0.9338, 0.8557, 0.902] +2023-05-26 12:46:13.349833: Epoch time: 32.67 s +2023-05-26 12:46:13.349913: Yayy! New best EMA pseudo Dice: 0.893 +2023-05-26 12:46:16.480006: +2023-05-26 12:46:16.480359: Epoch 43 +2023-05-26 12:46:16.480669: Current learning rate: 0.00961 +2023-05-26 12:46:49.304391: train_loss -0.8972 +2023-05-26 12:46:49.304710: val_loss -0.7295 +2023-05-26 12:46:49.304839: Pseudo dice [0.9323, 0.8565, 0.8999] +2023-05-26 12:46:49.304930: Epoch time: 32.83 s +2023-05-26 12:46:49.305007: Yayy! New best EMA pseudo Dice: 0.8933 +2023-05-26 12:46:51.994072: +2023-05-26 12:46:51.994418: Epoch 44 +2023-05-26 12:46:51.994610: Current learning rate: 0.0096 +2023-05-26 12:47:24.787314: train_loss -0.8975 +2023-05-26 12:47:24.787647: val_loss -0.7198 +2023-05-26 12:47:24.787798: Pseudo dice [0.9269, 0.851, 0.9003] +2023-05-26 12:47:24.787909: Epoch time: 32.79 s +2023-05-26 12:47:26.376701: +2023-05-26 12:47:26.376914: Epoch 45 +2023-05-26 12:47:26.377028: Current learning rate: 0.00959 +2023-05-26 12:47:59.301596: train_loss -0.8983 +2023-05-26 12:47:59.301906: val_loss -0.7306 +2023-05-26 12:47:59.302046: Pseudo dice [0.931, 0.8551, 0.9034] +2023-05-26 12:47:59.302158: Epoch time: 32.93 s +2023-05-26 12:47:59.302253: Yayy! New best EMA pseudo Dice: 0.8936 +2023-05-26 12:48:02.195431: +2023-05-26 12:48:02.195827: Epoch 46 +2023-05-26 12:48:02.196105: Current learning rate: 0.00959 +2023-05-26 12:48:34.984631: train_loss -0.8994 +2023-05-26 12:48:34.984837: val_loss -0.7244 +2023-05-26 12:48:34.984959: Pseudo dice [0.9314, 0.853, 0.901] +2023-05-26 12:48:34.985044: Epoch time: 32.79 s +2023-05-26 12:48:34.985121: Yayy! New best EMA pseudo Dice: 0.8937 +2023-05-26 12:48:38.173968: +2023-05-26 12:48:38.174125: Epoch 47 +2023-05-26 12:48:38.174230: Current learning rate: 0.00958 +2023-05-26 12:49:10.926614: train_loss -0.8989 +2023-05-26 12:49:10.926860: val_loss -0.7241 +2023-05-26 12:49:10.926986: Pseudo dice [0.9298, 0.8519, 0.9019] +2023-05-26 12:49:10.927094: Epoch time: 32.75 s +2023-05-26 12:49:10.927169: Yayy! New best EMA pseudo Dice: 0.8938 +2023-05-26 12:49:13.840447: +2023-05-26 12:49:13.840704: Epoch 48 +2023-05-26 12:49:13.840898: Current learning rate: 0.00957 +2023-05-26 12:49:46.538392: train_loss -0.9013 +2023-05-26 12:49:46.538782: val_loss -0.7231 +2023-05-26 12:49:46.538934: Pseudo dice [0.9315, 0.8519, 0.9015] +2023-05-26 12:49:46.539042: Epoch time: 32.7 s +2023-05-26 12:49:46.539121: Yayy! New best EMA pseudo Dice: 0.8939 +2023-05-26 12:49:49.244549: +2023-05-26 12:49:49.244719: Epoch 49 +2023-05-26 12:49:49.244840: Current learning rate: 0.00956 +2023-05-26 12:50:22.496968: train_loss -0.9013 +2023-05-26 12:50:22.497271: val_loss -0.718 +2023-05-26 12:50:22.497410: Pseudo dice [0.93, 0.8535, 0.901] +2023-05-26 12:50:22.497495: Epoch time: 33.25 s +2023-05-26 12:50:22.939109: Yayy! New best EMA pseudo Dice: 0.894 +2023-05-26 12:50:25.549477: +2023-05-26 12:50:25.549700: Epoch 50 +2023-05-26 12:50:25.549814: Current learning rate: 0.00955 +2023-05-26 12:50:58.364594: train_loss -0.9025 +2023-05-26 12:50:58.364823: val_loss -0.7233 +2023-05-26 12:50:58.364928: Pseudo dice [0.9306, 0.8554, 0.9] +2023-05-26 12:50:58.365032: Epoch time: 32.82 s +2023-05-26 12:50:58.365103: Yayy! New best EMA pseudo Dice: 0.8942 +2023-05-26 12:51:01.245111: +2023-05-26 12:51:01.245287: Epoch 51 +2023-05-26 12:51:01.245391: Current learning rate: 0.00954 +2023-05-26 12:51:34.045137: train_loss -0.9033 +2023-05-26 12:51:34.045335: val_loss -0.7231 +2023-05-26 12:51:34.045436: Pseudo dice [0.9324, 0.8536, 0.9013] +2023-05-26 12:51:34.045536: Epoch time: 32.8 s +2023-05-26 12:51:34.045621: Yayy! New best EMA pseudo Dice: 0.8943 +2023-05-26 12:51:37.431889: +2023-05-26 12:51:37.432508: Epoch 52 +2023-05-26 12:51:37.432745: Current learning rate: 0.00953 +2023-05-26 12:52:10.030586: train_loss -0.9036 +2023-05-26 12:52:10.030919: val_loss -0.7194 +2023-05-26 12:52:10.031429: Pseudo dice [0.9314, 0.8582, 0.897] +2023-05-26 12:52:10.031530: Epoch time: 32.6 s +2023-05-26 12:52:10.031602: Yayy! New best EMA pseudo Dice: 0.8944 +2023-05-26 12:52:12.768863: +2023-05-26 12:52:12.769292: Epoch 53 +2023-05-26 12:52:12.769521: Current learning rate: 0.00952 +2023-05-26 12:52:45.488324: train_loss -0.9044 +2023-05-26 12:52:45.488753: val_loss -0.7145 +2023-05-26 12:52:45.488902: Pseudo dice [0.931, 0.8538, 0.8977] +2023-05-26 12:52:45.489018: Epoch time: 32.72 s +2023-05-26 12:52:46.980921: +2023-05-26 12:52:46.981228: Epoch 54 +2023-05-26 12:52:46.981591: Current learning rate: 0.00951 +2023-05-26 12:53:19.847945: train_loss -0.9069 +2023-05-26 12:53:19.848271: val_loss -0.7083 +2023-05-26 12:53:19.848400: Pseudo dice [0.9311, 0.855, 0.8987] +2023-05-26 12:53:19.848490: Epoch time: 32.87 s +2023-05-26 12:53:19.848564: Yayy! New best EMA pseudo Dice: 0.8945 +2023-05-26 12:53:22.829817: +2023-05-26 12:53:22.829983: Epoch 55 +2023-05-26 12:53:22.830089: Current learning rate: 0.0095 +2023-05-26 12:53:55.875407: train_loss -0.9068 +2023-05-26 12:53:55.875834: val_loss -0.7194 +2023-05-26 12:53:55.876214: Pseudo dice [0.9333, 0.858, 0.8993] +2023-05-26 12:53:55.876314: Epoch time: 33.05 s +2023-05-26 12:53:55.876389: Yayy! New best EMA pseudo Dice: 0.8947 +2023-05-26 12:53:58.764371: +2023-05-26 12:53:58.764580: Epoch 56 +2023-05-26 12:53:58.764710: Current learning rate: 0.00949 +2023-05-26 12:54:31.668504: train_loss -0.9066 +2023-05-26 12:54:31.668761: val_loss -0.7122 +2023-05-26 12:54:31.668896: Pseudo dice [0.9308, 0.8546, 0.8985] +2023-05-26 12:54:31.668982: Epoch time: 32.91 s +2023-05-26 12:54:33.186886: +2023-05-26 12:54:33.187070: Epoch 57 +2023-05-26 12:54:33.187177: Current learning rate: 0.00949 +2023-05-26 12:55:05.839261: train_loss -0.9059 +2023-05-26 12:55:05.839571: val_loss -0.7225 +2023-05-26 12:55:05.839719: Pseudo dice [0.9319, 0.8564, 0.901] +2023-05-26 12:55:05.840075: Epoch time: 32.65 s +2023-05-26 12:55:05.840331: Yayy! New best EMA pseudo Dice: 0.8949 +2023-05-26 12:55:08.804366: +2023-05-26 12:55:08.805031: Epoch 58 +2023-05-26 12:55:08.805369: Current learning rate: 0.00948 +2023-05-26 12:55:41.657644: train_loss -0.9063 +2023-05-26 12:55:41.657898: val_loss -0.7115 +2023-05-26 12:55:41.658026: Pseudo dice [0.9308, 0.8548, 0.8972] +2023-05-26 12:55:41.658114: Epoch time: 32.85 s +2023-05-26 12:55:43.149058: +2023-05-26 12:55:43.149280: Epoch 59 +2023-05-26 12:55:43.149428: Current learning rate: 0.00947 +2023-05-26 12:56:15.872844: train_loss -0.9068 +2023-05-26 12:56:15.873175: val_loss -0.711 +2023-05-26 12:56:15.873305: Pseudo dice [0.93, 0.8542, 0.9011] +2023-05-26 12:56:15.873398: Epoch time: 32.72 s +2023-05-26 12:56:17.465307: +2023-05-26 12:56:17.465545: Epoch 60 +2023-05-26 12:56:17.465705: Current learning rate: 0.00946 +2023-05-26 12:56:50.187049: train_loss -0.9093 +2023-05-26 12:56:50.187424: val_loss -0.7095 +2023-05-26 12:56:50.187555: Pseudo dice [0.9313, 0.8561, 0.8964] +2023-05-26 12:56:50.187656: Epoch time: 32.72 s +2023-05-26 12:56:51.719191: +2023-05-26 12:56:51.719374: Epoch 61 +2023-05-26 12:56:51.719491: Current learning rate: 0.00945 +2023-05-26 12:57:24.584331: train_loss -0.9084 +2023-05-26 12:57:24.584711: val_loss -0.7155 +2023-05-26 12:57:24.584980: Pseudo dice [0.9312, 0.8553, 0.9023] +2023-05-26 12:57:24.585160: Epoch time: 32.87 s +2023-05-26 12:57:24.585340: Yayy! New best EMA pseudo Dice: 0.895 +2023-05-26 12:57:27.758624: +2023-05-26 12:57:27.758982: Epoch 62 +2023-05-26 12:57:27.759290: Current learning rate: 0.00944 +2023-05-26 12:58:00.877796: train_loss -0.9093 +2023-05-26 12:58:00.878097: val_loss -0.7123 +2023-05-26 12:58:00.878218: Pseudo dice [0.9312, 0.8561, 0.9014] +2023-05-26 12:58:00.878307: Epoch time: 33.12 s +2023-05-26 12:58:00.878376: Yayy! New best EMA pseudo Dice: 0.8951 +2023-05-26 12:58:03.817831: +2023-05-26 12:58:03.818454: Epoch 63 +2023-05-26 12:58:03.818875: Current learning rate: 0.00943 +2023-05-26 12:58:36.628411: train_loss -0.9095 +2023-05-26 12:58:36.628686: val_loss -0.7147 +2023-05-26 12:58:36.628809: Pseudo dice [0.9315, 0.8573, 0.9004] +2023-05-26 12:58:36.628899: Epoch time: 32.81 s +2023-05-26 12:58:36.628968: Yayy! New best EMA pseudo Dice: 0.8952 +2023-05-26 12:58:39.566077: +2023-05-26 12:58:39.566321: Epoch 64 +2023-05-26 12:58:39.566482: Current learning rate: 0.00942 +2023-05-26 12:59:12.330943: train_loss -0.909 +2023-05-26 12:59:12.331214: val_loss -0.7174 +2023-05-26 12:59:12.331353: Pseudo dice [0.933, 0.858, 0.9019] +2023-05-26 12:59:12.331450: Epoch time: 32.77 s +2023-05-26 12:59:12.331533: Yayy! New best EMA pseudo Dice: 0.8955 +2023-05-26 12:59:15.248767: +2023-05-26 12:59:15.248978: Epoch 65 +2023-05-26 12:59:15.249101: Current learning rate: 0.00941 +2023-05-26 12:59:47.974495: train_loss -0.9083 +2023-05-26 12:59:47.974760: val_loss -0.7264 +2023-05-26 12:59:47.974900: Pseudo dice [0.9342, 0.8581, 0.9051] +2023-05-26 12:59:47.974987: Epoch time: 32.73 s +2023-05-26 12:59:47.975056: Yayy! New best EMA pseudo Dice: 0.8958 +2023-05-26 12:59:50.545417: +2023-05-26 12:59:50.545907: Epoch 66 +2023-05-26 12:59:50.546053: Current learning rate: 0.0094 +2023-05-26 13:00:23.286558: train_loss -0.9095 +2023-05-26 13:00:23.286784: val_loss -0.7111 +2023-05-26 13:00:23.286917: Pseudo dice [0.9328, 0.8569, 0.8999] +2023-05-26 13:00:23.287019: Epoch time: 32.74 s +2023-05-26 13:00:23.287092: Yayy! New best EMA pseudo Dice: 0.8959 +2023-05-26 13:00:26.258524: +2023-05-26 13:00:26.259252: Epoch 67 +2023-05-26 13:00:26.259417: Current learning rate: 0.00939 +2023-05-26 13:00:58.956681: train_loss -0.9107 +2023-05-26 13:00:58.956926: val_loss -0.7061 +2023-05-26 13:00:58.957036: Pseudo dice [0.9313, 0.8555, 0.8986] +2023-05-26 13:00:58.957133: Epoch time: 32.7 s +2023-05-26 13:01:00.619235: +2023-05-26 13:01:00.619401: Epoch 68 +2023-05-26 13:01:00.619498: Current learning rate: 0.00939 +2023-05-26 13:01:33.318044: train_loss -0.9117 +2023-05-26 13:01:33.318311: val_loss -0.7128 +2023-05-26 13:01:33.318427: Pseudo dice [0.933, 0.8565, 0.9018] +2023-05-26 13:01:33.318527: Epoch time: 32.7 s +2023-05-26 13:01:33.318596: Yayy! New best EMA pseudo Dice: 0.8959 +2023-05-26 13:01:36.457582: +2023-05-26 13:01:36.457983: Epoch 69 +2023-05-26 13:01:36.458401: Current learning rate: 0.00938 +2023-05-26 13:02:09.792557: train_loss -0.913 +2023-05-26 13:02:09.792938: val_loss -0.7118 +2023-05-26 13:02:09.793175: Pseudo dice [0.93, 0.8561, 0.9043] +2023-05-26 13:02:09.793347: Epoch time: 33.34 s +2023-05-26 13:02:09.793473: Yayy! New best EMA pseudo Dice: 0.896 +2023-05-26 13:02:13.173054: +2023-05-26 13:02:13.173235: Epoch 70 +2023-05-26 13:02:13.173357: Current learning rate: 0.00937 +2023-05-26 13:02:46.055917: train_loss -0.9132 +2023-05-26 13:02:46.056193: val_loss -0.7165 +2023-05-26 13:02:46.056418: Pseudo dice [0.933, 0.8587, 0.9043] +2023-05-26 13:02:46.056735: Epoch time: 32.88 s +2023-05-26 13:02:46.056866: Yayy! New best EMA pseudo Dice: 0.8963 +2023-05-26 13:02:49.023530: +2023-05-26 13:02:49.024055: Epoch 71 +2023-05-26 13:02:49.024229: Current learning rate: 0.00936 +2023-05-26 13:03:21.708062: train_loss -0.9148 +2023-05-26 13:03:21.708337: val_loss -0.7026 +2023-05-26 13:03:21.708458: Pseudo dice [0.9327, 0.8554, 0.9001] +2023-05-26 13:03:21.708545: Epoch time: 32.69 s +2023-05-26 13:03:23.311449: +2023-05-26 13:03:23.311622: Epoch 72 +2023-05-26 13:03:23.311736: Current learning rate: 0.00935 +2023-05-26 13:03:55.924186: train_loss -0.9156 +2023-05-26 13:03:55.924459: val_loss -0.7126 +2023-05-26 13:03:55.924597: Pseudo dice [0.9345, 0.858, 0.8989] +2023-05-26 13:03:55.924684: Epoch time: 32.61 s +2023-05-26 13:03:55.924752: Yayy! New best EMA pseudo Dice: 0.8964 +2023-05-26 13:03:58.865735: +2023-05-26 13:03:58.865951: Epoch 73 +2023-05-26 13:03:58.866088: Current learning rate: 0.00934 +2023-05-26 13:04:31.667287: train_loss -0.9129 +2023-05-26 13:04:31.667543: val_loss -0.7098 +2023-05-26 13:04:31.667674: Pseudo dice [0.9322, 0.8556, 0.897] +2023-05-26 13:04:31.667773: Epoch time: 32.8 s +2023-05-26 13:04:33.427574: +2023-05-26 13:04:33.428188: Epoch 74 +2023-05-26 13:04:33.428323: Current learning rate: 0.00933 +2023-05-26 13:05:06.221787: train_loss -0.9123 +2023-05-26 13:05:06.222063: val_loss -0.7061 +2023-05-26 13:05:06.222182: Pseudo dice [0.9311, 0.8566, 0.9019] +2023-05-26 13:05:06.222286: Epoch time: 32.8 s +2023-05-26 13:05:07.864737: +2023-05-26 13:05:07.864950: Epoch 75 +2023-05-26 13:05:07.865069: Current learning rate: 0.00932 +2023-05-26 13:05:40.582978: train_loss -0.9131 +2023-05-26 13:05:40.583241: val_loss -0.7085 +2023-05-26 13:05:40.583374: Pseudo dice [0.9329, 0.857, 0.9029] +2023-05-26 13:05:40.583485: Epoch time: 32.72 s +2023-05-26 13:05:40.583566: Yayy! New best EMA pseudo Dice: 0.8964 +2023-05-26 13:05:43.310097: +2023-05-26 13:05:43.310819: Epoch 76 +2023-05-26 13:05:43.310975: Current learning rate: 0.00931 +2023-05-26 13:06:16.077012: train_loss -0.9156 +2023-05-26 13:06:16.077278: val_loss -0.6981 +2023-05-26 13:06:16.077407: Pseudo dice [0.9325, 0.8553, 0.896] +2023-05-26 13:06:16.077500: Epoch time: 32.77 s +2023-05-26 13:06:17.695198: +2023-05-26 13:06:17.695426: Epoch 77 +2023-05-26 13:06:17.695530: Current learning rate: 0.0093 +2023-05-26 13:06:50.633670: train_loss -0.9167 +2023-05-26 13:06:50.633947: val_loss -0.7095 +2023-05-26 13:06:50.634073: Pseudo dice [0.9329, 0.8587, 0.9027] +2023-05-26 13:06:50.634157: Epoch time: 32.94 s +2023-05-26 13:06:50.634226: Yayy! New best EMA pseudo Dice: 0.8964 +2023-05-26 13:06:53.689571: +2023-05-26 13:06:53.689775: Epoch 78 +2023-05-26 13:06:53.689930: Current learning rate: 0.0093 +2023-05-26 13:07:26.462664: train_loss -0.9165 +2023-05-26 13:07:26.462938: val_loss -0.7038 +2023-05-26 13:07:26.463062: Pseudo dice [0.9321, 0.8585, 0.9003] +2023-05-26 13:07:26.463164: Epoch time: 32.77 s +2023-05-26 13:07:26.463236: Yayy! New best EMA pseudo Dice: 0.8965 +2023-05-26 13:07:29.373199: +2023-05-26 13:07:29.373895: Epoch 79 +2023-05-26 13:07:29.374140: Current learning rate: 0.00929 +2023-05-26 13:08:02.180965: train_loss -0.9176 +2023-05-26 13:08:02.181214: val_loss -0.7041 +2023-05-26 13:08:02.181338: Pseudo dice [0.9326, 0.8572, 0.9013] +2023-05-26 13:08:02.181437: Epoch time: 32.81 s +2023-05-26 13:08:02.181508: Yayy! New best EMA pseudo Dice: 0.8965 +2023-05-26 13:08:05.224793: +2023-05-26 13:08:05.225094: Epoch 80 +2023-05-26 13:08:05.225259: Current learning rate: 0.00928 +2023-05-26 13:08:37.943575: train_loss -0.9164 +2023-05-26 13:08:37.943809: val_loss -0.7013 +2023-05-26 13:08:37.943931: Pseudo dice [0.9314, 0.8576, 0.8976] +2023-05-26 13:08:37.944036: Epoch time: 32.72 s +2023-05-26 13:08:39.432443: +2023-05-26 13:08:39.432622: Epoch 81 +2023-05-26 13:08:39.432740: Current learning rate: 0.00927 +2023-05-26 13:09:12.193443: train_loss -0.9174 +2023-05-26 13:09:12.193715: val_loss -0.6997 +2023-05-26 13:09:12.193842: Pseudo dice [0.9325, 0.8552, 0.9009] +2023-05-26 13:09:12.193937: Epoch time: 32.76 s +2023-05-26 13:09:13.756454: +2023-05-26 13:09:13.756788: Epoch 82 +2023-05-26 13:09:13.757014: Current learning rate: 0.00926 +2023-05-26 13:09:46.466455: train_loss -0.9192 +2023-05-26 13:09:46.466710: val_loss -0.6983 +2023-05-26 13:09:46.466816: Pseudo dice [0.9319, 0.8568, 0.9002] +2023-05-26 13:09:46.466938: Epoch time: 32.71 s +2023-05-26 13:09:47.849399: +2023-05-26 13:09:47.849886: Epoch 83 +2023-05-26 13:09:47.850221: Current learning rate: 0.00925 +2023-05-26 13:10:20.496069: train_loss -0.92 +2023-05-26 13:10:20.496500: val_loss -0.6922 +2023-05-26 13:10:20.496626: Pseudo dice [0.9329, 0.8551, 0.8992] +2023-05-26 13:10:20.496733: Epoch time: 32.65 s +2023-05-26 13:10:22.017261: +2023-05-26 13:10:22.017426: Epoch 84 +2023-05-26 13:10:22.017531: Current learning rate: 0.00924 +2023-05-26 13:10:54.539361: train_loss -0.9197 +2023-05-26 13:10:54.539613: val_loss -0.6891 +2023-05-26 13:10:54.539745: Pseudo dice [0.9303, 0.8551, 0.8987] +2023-05-26 13:10:54.539870: Epoch time: 32.52 s +2023-05-26 13:10:56.021548: +2023-05-26 13:10:56.021835: Epoch 85 +2023-05-26 13:10:56.022063: Current learning rate: 0.00923 +2023-05-26 13:11:28.450201: train_loss -0.9191 +2023-05-26 13:11:28.450458: val_loss -0.7065 +2023-05-26 13:11:28.450600: Pseudo dice [0.9345, 0.8612, 0.9025] +2023-05-26 13:11:28.450700: Epoch time: 32.43 s +2023-05-26 13:11:29.981508: +2023-05-26 13:11:29.981833: Epoch 86 +2023-05-26 13:11:29.982135: Current learning rate: 0.00922 +2023-05-26 13:12:03.095375: train_loss -0.9202 +2023-05-26 13:12:03.095634: val_loss -0.6988 +2023-05-26 13:12:03.095766: Pseudo dice [0.9325, 0.8575, 0.9048] +2023-05-26 13:12:03.095876: Epoch time: 33.11 s +2023-05-26 13:12:03.095960: Yayy! New best EMA pseudo Dice: 0.8967 +2023-05-26 13:12:06.091610: +2023-05-26 13:12:06.091790: Epoch 87 +2023-05-26 13:12:06.091911: Current learning rate: 0.00921 +2023-05-26 13:12:38.882867: train_loss -0.9208 +2023-05-26 13:12:38.883249: val_loss -0.7007 +2023-05-26 13:12:38.883359: Pseudo dice [0.9337, 0.858, 0.9035] +2023-05-26 13:12:38.883446: Epoch time: 32.79 s +2023-05-26 13:12:38.883517: Yayy! New best EMA pseudo Dice: 0.8968 +2023-05-26 13:12:42.175628: +2023-05-26 13:12:42.175935: Epoch 88 +2023-05-26 13:12:42.176164: Current learning rate: 0.0092 +2023-05-26 13:13:15.017350: train_loss -0.9207 +2023-05-26 13:13:15.017582: val_loss -0.6994 +2023-05-26 13:13:15.017710: Pseudo dice [0.9321, 0.8569, 0.9019] +2023-05-26 13:13:15.017816: Epoch time: 32.84 s +2023-05-26 13:13:15.017889: Yayy! New best EMA pseudo Dice: 0.8968 +2023-05-26 13:13:17.782119: +2023-05-26 13:13:17.782616: Epoch 89 +2023-05-26 13:13:17.782846: Current learning rate: 0.0092 +2023-05-26 13:13:50.399089: train_loss -0.9209 +2023-05-26 13:13:50.399359: val_loss -0.6924 +2023-05-26 13:13:50.399481: Pseudo dice [0.9328, 0.8569, 0.8969] +2023-05-26 13:13:50.399570: Epoch time: 32.62 s +2023-05-26 13:13:51.882905: +2023-05-26 13:13:51.883104: Epoch 90 +2023-05-26 13:13:51.883240: Current learning rate: 0.00919 +2023-05-26 13:14:24.441378: train_loss -0.9213 +2023-05-26 13:14:24.441653: val_loss -0.6953 +2023-05-26 13:14:24.441796: Pseudo dice [0.9317, 0.857, 0.9032] +2023-05-26 13:14:24.441894: Epoch time: 32.56 s +2023-05-26 13:14:25.955974: +2023-05-26 13:14:25.956311: Epoch 91 +2023-05-26 13:14:25.956658: Current learning rate: 0.00918 +2023-05-26 13:14:58.519161: train_loss -0.9228 +2023-05-26 13:14:58.519615: val_loss -0.6903 +2023-05-26 13:14:58.519828: Pseudo dice [0.9309, 0.856, 0.9001] +2023-05-26 13:14:58.519998: Epoch time: 32.56 s +2023-05-26 13:14:59.988521: +2023-05-26 13:14:59.988707: Epoch 92 +2023-05-26 13:14:59.988819: Current learning rate: 0.00917 +2023-05-26 13:15:32.621976: train_loss -0.9224 +2023-05-26 13:15:32.622283: val_loss -0.6911 +2023-05-26 13:15:32.622416: Pseudo dice [0.9331, 0.8557, 0.901] +2023-05-26 13:15:32.622517: Epoch time: 32.63 s +2023-05-26 13:15:34.423305: +2023-05-26 13:15:34.423553: Epoch 93 +2023-05-26 13:15:34.423702: Current learning rate: 0.00916 +2023-05-26 13:16:07.371311: train_loss -0.9232 +2023-05-26 13:16:07.371570: val_loss -0.6944 +2023-05-26 13:16:07.371700: Pseudo dice [0.9335, 0.8548, 0.8993] +2023-05-26 13:16:07.371788: Epoch time: 32.95 s +2023-05-26 13:16:08.971426: +2023-05-26 13:16:08.971610: Epoch 94 +2023-05-26 13:16:08.971720: Current learning rate: 0.00915 +2023-05-26 13:16:41.575774: train_loss -0.9235 +2023-05-26 13:16:41.576006: val_loss -0.6891 +2023-05-26 13:16:41.576118: Pseudo dice [0.9325, 0.8562, 0.9022] +2023-05-26 13:16:41.576217: Epoch time: 32.61 s +2023-05-26 13:16:42.920530: +2023-05-26 13:16:42.920690: Epoch 95 +2023-05-26 13:16:42.920796: Current learning rate: 0.00914 +2023-05-26 13:17:16.142240: train_loss -0.9232 +2023-05-26 13:17:16.142515: val_loss -0.6895 +2023-05-26 13:17:16.142977: Pseudo dice [0.9327, 0.8582, 0.9011] +2023-05-26 13:17:16.143092: Epoch time: 33.22 s +2023-05-26 13:17:17.586064: +2023-05-26 13:17:17.586400: Epoch 96 +2023-05-26 13:17:17.586624: Current learning rate: 0.00913 +2023-05-26 13:17:50.755790: train_loss -0.9242 +2023-05-26 13:17:50.756031: val_loss -0.6922 +2023-05-26 13:17:50.756150: Pseudo dice [0.9344, 0.8565, 0.9049] +2023-05-26 13:17:50.756248: Epoch time: 33.17 s +2023-05-26 13:17:50.756319: Yayy! New best EMA pseudo Dice: 0.8969 +2023-05-26 13:17:53.746035: +2023-05-26 13:17:53.746243: Epoch 97 +2023-05-26 13:17:53.746392: Current learning rate: 0.00912 +2023-05-26 13:18:26.438108: train_loss -0.9232 +2023-05-26 13:18:26.438379: val_loss -0.6871 +2023-05-26 13:18:26.438512: Pseudo dice [0.933, 0.8549, 0.9039] +2023-05-26 13:18:26.438619: Epoch time: 32.69 s +2023-05-26 13:18:26.438713: Yayy! New best EMA pseudo Dice: 0.8969 +2023-05-26 13:18:29.259434: +2023-05-26 13:18:29.259625: Epoch 98 +2023-05-26 13:18:29.259763: Current learning rate: 0.00911 +2023-05-26 13:19:02.010386: train_loss -0.9239 +2023-05-26 13:19:02.010681: val_loss -0.6882 +2023-05-26 13:19:02.010820: Pseudo dice [0.9319, 0.8569, 0.9009] +2023-05-26 13:19:02.010987: Epoch time: 32.75 s +2023-05-26 13:19:03.446699: +2023-05-26 13:19:03.447141: Epoch 99 +2023-05-26 13:19:03.447487: Current learning rate: 0.0091 +2023-05-26 13:19:36.082926: train_loss -0.9235 +2023-05-26 13:19:36.083148: val_loss -0.7003 +2023-05-26 13:19:36.083248: Pseudo dice [0.9337, 0.8585, 0.908] +2023-05-26 13:19:36.083341: Epoch time: 32.64 s +2023-05-26 13:19:37.278546: Yayy! New best EMA pseudo Dice: 0.8972 +2023-05-26 13:19:40.487099: +2023-05-26 13:19:40.487353: Epoch 100 +2023-05-26 13:19:40.487489: Current learning rate: 0.0091 +2023-05-26 13:20:13.299610: train_loss -0.9246 +2023-05-26 13:20:13.300187: val_loss -0.6884 +2023-05-26 13:20:13.300558: Pseudo dice [0.9338, 0.859, 0.9026] +2023-05-26 13:20:13.300864: Epoch time: 32.81 s +2023-05-26 13:20:13.301126: Yayy! New best EMA pseudo Dice: 0.8973 +2023-05-26 13:20:16.127362: +2023-05-26 13:20:16.127943: Epoch 101 +2023-05-26 13:20:16.128337: Current learning rate: 0.00909 +2023-05-26 13:20:48.666860: train_loss -0.9225 +2023-05-26 13:20:48.667159: val_loss -0.7001 +2023-05-26 13:20:48.667296: Pseudo dice [0.9343, 0.8601, 0.9048] +2023-05-26 13:20:48.667399: Epoch time: 32.54 s +2023-05-26 13:20:48.667482: Yayy! New best EMA pseudo Dice: 0.8976 +2023-05-26 13:20:51.438253: +2023-05-26 13:20:51.438552: Epoch 102 +2023-05-26 13:20:51.438787: Current learning rate: 0.00908 +2023-05-26 13:21:24.105334: train_loss -0.9253 +2023-05-26 13:21:24.105601: val_loss -0.6884 +2023-05-26 13:21:24.105708: Pseudo dice [0.9328, 0.8578, 0.9032] +2023-05-26 13:21:24.105809: Epoch time: 32.67 s +2023-05-26 13:21:24.105880: Yayy! New best EMA pseudo Dice: 0.8976 +2023-05-26 13:21:26.880502: +2023-05-26 13:21:26.880890: Epoch 103 +2023-05-26 13:21:26.881166: Current learning rate: 0.00907 +2023-05-26 13:21:59.566445: train_loss -0.9229 +2023-05-26 13:21:59.566760: val_loss -0.6932 +2023-05-26 13:21:59.567206: Pseudo dice [0.9328, 0.8583, 0.9007] +2023-05-26 13:21:59.567327: Epoch time: 32.69 s +2023-05-26 13:22:00.932714: +2023-05-26 13:22:00.932870: Epoch 104 +2023-05-26 13:22:00.932970: Current learning rate: 0.00906 +2023-05-26 13:22:33.583390: train_loss -0.9222 +2023-05-26 13:22:33.583625: val_loss -0.696 +2023-05-26 13:22:33.583759: Pseudo dice [0.9303, 0.8562, 0.9035] +2023-05-26 13:22:33.583853: Epoch time: 32.65 s +2023-05-26 13:22:35.190185: +2023-05-26 13:22:35.190430: Epoch 105 +2023-05-26 13:22:35.190621: Current learning rate: 0.00905 +2023-05-26 13:23:07.892562: train_loss -0.9234 +2023-05-26 13:23:07.893690: val_loss -0.68 +2023-05-26 13:23:07.894308: Pseudo dice [0.9315, 0.856, 0.9008] +2023-05-26 13:23:07.895032: Epoch time: 32.7 s +2023-05-26 13:23:09.697476: +2023-05-26 13:23:09.697674: Epoch 106 +2023-05-26 13:23:09.697806: Current learning rate: 0.00904 +2023-05-26 13:23:42.527417: train_loss -0.9251 +2023-05-26 13:23:42.527657: val_loss -0.692 +2023-05-26 13:23:42.527767: Pseudo dice [0.9327, 0.858, 0.9043] +2023-05-26 13:23:42.527858: Epoch time: 32.83 s +2023-05-26 13:23:43.942637: +2023-05-26 13:23:43.942952: Epoch 107 +2023-05-26 13:23:43.943128: Current learning rate: 0.00903 +2023-05-26 13:24:16.604707: train_loss -0.9248 +2023-05-26 13:24:16.604944: val_loss -0.6964 +2023-05-26 13:24:16.605067: Pseudo dice [0.9332, 0.8569, 0.9074] +2023-05-26 13:24:16.605190: Epoch time: 32.66 s +2023-05-26 13:24:16.605259: Yayy! New best EMA pseudo Dice: 0.8976 +2023-05-26 13:24:19.447912: +2023-05-26 13:24:19.448132: Epoch 108 +2023-05-26 13:24:19.448260: Current learning rate: 0.00902 +2023-05-26 13:24:52.159925: train_loss -0.9242 +2023-05-26 13:24:52.160917: val_loss -0.6913 +2023-05-26 13:24:52.161240: Pseudo dice [0.9331, 0.8583, 0.8987] +2023-05-26 13:24:52.161753: Epoch time: 32.71 s +2023-05-26 13:24:53.686486: +2023-05-26 13:24:53.687117: Epoch 109 +2023-05-26 13:24:53.687295: Current learning rate: 0.00901 +2023-05-26 13:25:26.327650: train_loss -0.9203 +2023-05-26 13:25:26.327937: val_loss -0.6959 +2023-05-26 13:25:26.328086: Pseudo dice [0.9318, 0.854, 0.9022] +2023-05-26 13:25:26.328198: Epoch time: 32.64 s +2023-05-26 13:25:27.908319: +2023-05-26 13:25:27.908516: Epoch 110 +2023-05-26 13:25:27.908646: Current learning rate: 0.009 +2023-05-26 13:26:00.627459: train_loss -0.9244 +2023-05-26 13:26:00.627762: val_loss -0.6895 +2023-05-26 13:26:00.627891: Pseudo dice [0.9316, 0.856, 0.9016] +2023-05-26 13:26:00.627986: Epoch time: 32.72 s +2023-05-26 13:26:02.102787: +2023-05-26 13:26:02.103262: Epoch 111 +2023-05-26 13:26:02.103731: Current learning rate: 0.009 +2023-05-26 13:26:34.920799: train_loss -0.9255 +2023-05-26 13:26:34.921167: val_loss -0.6903 +2023-05-26 13:26:34.921291: Pseudo dice [0.933, 0.8586, 0.9] +2023-05-26 13:26:34.921377: Epoch time: 32.82 s +2023-05-26 13:26:36.647104: +2023-05-26 13:26:36.647523: Epoch 112 +2023-05-26 13:26:36.647673: Current learning rate: 0.00899 +2023-05-26 13:27:09.494318: train_loss -0.9269 +2023-05-26 13:27:09.494563: val_loss -0.6924 +2023-05-26 13:27:09.494681: Pseudo dice [0.9329, 0.8578, 0.9025] +2023-05-26 13:27:09.494781: Epoch time: 32.85 s +2023-05-26 13:27:11.002515: +2023-05-26 13:27:11.002753: Epoch 113 +2023-05-26 13:27:11.002911: Current learning rate: 0.00898 +2023-05-26 13:27:43.847646: train_loss -0.9284 +2023-05-26 13:27:43.848024: val_loss -0.6873 +2023-05-26 13:27:43.848237: Pseudo dice [0.9328, 0.8588, 0.9033] +2023-05-26 13:27:43.848378: Epoch time: 32.85 s +2023-05-26 13:27:45.418520: +2023-05-26 13:27:45.418760: Epoch 114 +2023-05-26 13:27:45.418936: Current learning rate: 0.00897 +2023-05-26 13:28:18.740886: train_loss -0.9277 +2023-05-26 13:28:18.741303: val_loss -0.6894 +2023-05-26 13:28:18.741530: Pseudo dice [0.9335, 0.8596, 0.9056] +2023-05-26 13:28:18.741722: Epoch time: 33.32 s +2023-05-26 13:28:18.741829: Yayy! New best EMA pseudo Dice: 0.8976 +2023-05-26 13:28:21.378721: +2023-05-26 13:28:21.379405: Epoch 115 +2023-05-26 13:28:21.379600: Current learning rate: 0.00896 +2023-05-26 13:28:54.168853: train_loss -0.9267 +2023-05-26 13:28:54.169084: val_loss -0.6969 +2023-05-26 13:28:54.169198: Pseudo dice [0.9362, 0.8631, 0.9031] +2023-05-26 13:28:54.169294: Epoch time: 32.79 s +2023-05-26 13:28:54.169360: Yayy! New best EMA pseudo Dice: 0.8979 +2023-05-26 13:28:56.874271: +2023-05-26 13:28:56.874436: Epoch 116 +2023-05-26 13:28:56.874543: Current learning rate: 0.00895 +2023-05-26 13:29:29.601806: train_loss -0.9275 +2023-05-26 13:29:29.602105: val_loss -0.6939 +2023-05-26 13:29:29.602216: Pseudo dice [0.9344, 0.862, 0.9017] +2023-05-26 13:29:29.602298: Epoch time: 32.73 s +2023-05-26 13:29:29.602380: Yayy! New best EMA pseudo Dice: 0.8981 +2023-05-26 13:29:32.368425: +2023-05-26 13:29:32.368607: Epoch 117 +2023-05-26 13:29:32.368756: Current learning rate: 0.00894 +2023-05-26 13:30:05.136278: train_loss -0.9273 +2023-05-26 13:30:05.136602: val_loss -0.689 +2023-05-26 13:30:05.136761: Pseudo dice [0.9339, 0.8608, 0.8991] +2023-05-26 13:30:05.136884: Epoch time: 32.77 s +2023-05-26 13:30:06.666014: +2023-05-26 13:30:06.666246: Epoch 118 +2023-05-26 13:30:06.666416: Current learning rate: 0.00893 +2023-05-26 13:30:39.349101: train_loss -0.9269 +2023-05-26 13:30:39.349426: val_loss -0.6802 +2023-05-26 13:30:39.349524: Pseudo dice [0.9323, 0.8566, 0.8981] +2023-05-26 13:30:39.349615: Epoch time: 32.68 s +2023-05-26 13:30:41.313748: +2023-05-26 13:30:41.313953: Epoch 119 +2023-05-26 13:30:41.314098: Current learning rate: 0.00892 +2023-05-26 13:31:14.154849: train_loss -0.9264 +2023-05-26 13:31:14.155349: val_loss -0.6983 +2023-05-26 13:31:14.155574: Pseudo dice [0.9325, 0.8561, 0.9065] +2023-05-26 13:31:14.156356: Epoch time: 32.84 s +2023-05-26 13:31:15.733384: +2023-05-26 13:31:15.733744: Epoch 120 +2023-05-26 13:31:15.734000: Current learning rate: 0.00891 +2023-05-26 13:31:48.580082: train_loss -0.928 +2023-05-26 13:31:48.580410: val_loss -0.6951 +2023-05-26 13:31:48.580545: Pseudo dice [0.9351, 0.8611, 0.9042] +2023-05-26 13:31:48.580649: Epoch time: 32.85 s +2023-05-26 13:31:48.580736: Yayy! New best EMA pseudo Dice: 0.8981 +2023-05-26 13:31:51.550312: +2023-05-26 13:31:51.550667: Epoch 121 +2023-05-26 13:31:51.550868: Current learning rate: 0.0089 +2023-05-26 13:32:24.363943: train_loss -0.9294 +2023-05-26 13:32:24.364209: val_loss -0.69 +2023-05-26 13:32:24.364342: Pseudo dice [0.9343, 0.8595, 0.9036] +2023-05-26 13:32:24.364451: Epoch time: 32.81 s +2023-05-26 13:32:24.364534: Yayy! New best EMA pseudo Dice: 0.8982 +2023-05-26 13:32:27.240699: +2023-05-26 13:32:27.240878: Epoch 122 +2023-05-26 13:32:27.240996: Current learning rate: 0.00889 +2023-05-26 13:33:00.244028: train_loss -0.929 +2023-05-26 13:33:00.244254: val_loss -0.6907 +2023-05-26 13:33:00.244370: Pseudo dice [0.9335, 0.8597, 0.9053] +2023-05-26 13:33:00.244473: Epoch time: 33.0 s +2023-05-26 13:33:00.244544: Yayy! New best EMA pseudo Dice: 0.8983 +2023-05-26 13:33:03.670478: +2023-05-26 13:33:03.670659: Epoch 123 +2023-05-26 13:33:03.670776: Current learning rate: 0.00889 +2023-05-26 13:33:37.047303: train_loss -0.93 +2023-05-26 13:33:37.047575: val_loss -0.6852 +2023-05-26 13:33:37.047708: Pseudo dice [0.9328, 0.8575, 0.8995] +2023-05-26 13:33:37.047796: Epoch time: 33.38 s +2023-05-26 13:33:38.454234: +2023-05-26 13:33:38.454609: Epoch 124 +2023-05-26 13:33:38.454735: Current learning rate: 0.00888 +2023-05-26 13:34:11.164129: train_loss -0.9292 +2023-05-26 13:34:11.164576: val_loss -0.6874 +2023-05-26 13:34:11.164834: Pseudo dice [0.9316, 0.8596, 0.9035] +2023-05-26 13:34:11.164930: Epoch time: 32.71 s +2023-05-26 13:34:12.863442: +2023-05-26 13:34:12.863620: Epoch 125 +2023-05-26 13:34:12.863727: Current learning rate: 0.00887 +2023-05-26 13:34:45.619605: train_loss -0.9299 +2023-05-26 13:34:45.619871: val_loss -0.6854 +2023-05-26 13:34:45.619998: Pseudo dice [0.9339, 0.8592, 0.9031] +2023-05-26 13:34:45.620102: Epoch time: 32.76 s +2023-05-26 13:34:47.133584: +2023-05-26 13:34:47.133817: Epoch 126 +2023-05-26 13:34:47.133956: Current learning rate: 0.00886 +2023-05-26 13:35:19.882499: train_loss -0.9305 +2023-05-26 13:35:19.882866: val_loss -0.6864 +2023-05-26 13:35:19.883011: Pseudo dice [0.9328, 0.8586, 0.9014] +2023-05-26 13:35:19.883130: Epoch time: 32.75 s +2023-05-26 13:35:21.283681: +2023-05-26 13:35:21.283878: Epoch 127 +2023-05-26 13:35:21.284001: Current learning rate: 0.00885 +2023-05-26 13:35:53.913368: train_loss -0.931 +2023-05-26 13:35:53.913635: val_loss -0.6903 +2023-05-26 13:35:53.913772: Pseudo dice [0.9346, 0.858, 0.9046] +2023-05-26 13:35:53.913859: Epoch time: 32.63 s +2023-05-26 13:35:55.538995: +2023-05-26 13:35:55.539157: Epoch 128 +2023-05-26 13:35:55.539260: Current learning rate: 0.00884 +2023-05-26 13:36:28.265873: train_loss -0.9301 +2023-05-26 13:36:28.266104: val_loss -0.6814 +2023-05-26 13:36:28.266222: Pseudo dice [0.9319, 0.8578, 0.9038] +2023-05-26 13:36:28.266318: Epoch time: 32.73 s +2023-05-26 13:36:29.821669: +2023-05-26 13:36:29.822440: Epoch 129 +2023-05-26 13:36:29.822755: Current learning rate: 0.00883 +2023-05-26 13:37:02.557056: train_loss -0.9288 +2023-05-26 13:37:02.557332: val_loss -0.6837 +2023-05-26 13:37:02.557458: Pseudo dice [0.9327, 0.8565, 0.9027] +2023-05-26 13:37:02.557550: Epoch time: 32.74 s +2023-05-26 13:37:04.136622: +2023-05-26 13:37:04.136862: Epoch 130 +2023-05-26 13:37:04.136995: Current learning rate: 0.00882 +2023-05-26 13:37:37.125981: train_loss -0.9279 +2023-05-26 13:37:37.126244: val_loss -0.6979 +2023-05-26 13:37:37.126366: Pseudo dice [0.9346, 0.862, 0.9028] +2023-05-26 13:37:37.126453: Epoch time: 32.99 s +2023-05-26 13:37:38.612718: +2023-05-26 13:37:38.612895: Epoch 131 +2023-05-26 13:37:38.613004: Current learning rate: 0.00881 +2023-05-26 13:38:11.419871: train_loss -0.9293 +2023-05-26 13:38:11.420110: val_loss -0.6863 +2023-05-26 13:38:11.420223: Pseudo dice [0.9338, 0.8575, 0.9022] +2023-05-26 13:38:11.420325: Epoch time: 32.81 s +2023-05-26 13:38:13.252437: +2023-05-26 13:38:13.253142: Epoch 132 +2023-05-26 13:38:13.253425: Current learning rate: 0.0088 +2023-05-26 13:38:46.039418: train_loss -0.9308 +2023-05-26 13:38:46.039714: val_loss -0.6925 +2023-05-26 13:38:46.039843: Pseudo dice [0.9336, 0.8599, 0.9043] +2023-05-26 13:38:46.039937: Epoch time: 32.79 s +2023-05-26 13:38:46.040031: Yayy! New best EMA pseudo Dice: 0.8983 +2023-05-26 13:38:48.756598: +2023-05-26 13:38:48.756928: Epoch 133 +2023-05-26 13:38:48.757240: Current learning rate: 0.00879 +2023-05-26 13:39:21.487367: train_loss -0.9318 +2023-05-26 13:39:21.487611: val_loss -0.6799 +2023-05-26 13:39:21.487756: Pseudo dice [0.9334, 0.8584, 0.9022] +2023-05-26 13:39:21.487868: Epoch time: 32.73 s +2023-05-26 13:39:23.024756: +2023-05-26 13:39:23.024966: Epoch 134 +2023-05-26 13:39:23.025089: Current learning rate: 0.00879 +2023-05-26 13:39:55.784221: train_loss -0.9316 +2023-05-26 13:39:55.784585: val_loss -0.684 +2023-05-26 13:39:55.784977: Pseudo dice [0.9335, 0.8592, 0.9026] +2023-05-26 13:39:55.785119: Epoch time: 32.76 s +2023-05-26 13:39:57.277156: +2023-05-26 13:39:57.277393: Epoch 135 +2023-05-26 13:39:57.277614: Current learning rate: 0.00878 +2023-05-26 13:40:30.000421: train_loss -0.9294 +2023-05-26 13:40:30.000669: val_loss -0.6872 +2023-05-26 13:40:30.000800: Pseudo dice [0.9337, 0.8589, 0.9029] +2023-05-26 13:40:30.000916: Epoch time: 32.72 s +2023-05-26 13:40:31.502810: +2023-05-26 13:40:31.503012: Epoch 136 +2023-05-26 13:40:31.503129: Current learning rate: 0.00877 +2023-05-26 13:41:04.243208: train_loss -0.9302 +2023-05-26 13:41:04.243480: val_loss -0.6918 +2023-05-26 13:41:04.243619: Pseudo dice [0.9349, 0.8618, 0.9035] +2023-05-26 13:41:04.243723: Epoch time: 32.74 s +2023-05-26 13:41:04.243798: Yayy! New best EMA pseudo Dice: 0.8985 +2023-05-26 13:41:07.180570: +2023-05-26 13:41:07.180777: Epoch 137 +2023-05-26 13:41:07.180956: Current learning rate: 0.00876 +2023-05-26 13:41:40.025219: train_loss -0.9311 +2023-05-26 13:41:40.025449: val_loss -0.6886 +2023-05-26 13:41:40.025552: Pseudo dice [0.9359, 0.863, 0.9024] +2023-05-26 13:41:40.025660: Epoch time: 32.85 s +2023-05-26 13:41:40.025724: Yayy! New best EMA pseudo Dice: 0.8987 +2023-05-26 13:41:42.991874: +2023-05-26 13:41:42.992291: Epoch 138 +2023-05-26 13:41:42.992539: Current learning rate: 0.00875 +2023-05-26 13:42:15.953492: train_loss -0.9313 +2023-05-26 13:42:15.953751: val_loss -0.6827 +2023-05-26 13:42:15.953882: Pseudo dice [0.9347, 0.8602, 0.9007] +2023-05-26 13:42:15.954007: Epoch time: 32.96 s +2023-05-26 13:42:17.547134: +2023-05-26 13:42:17.547461: Epoch 139 +2023-05-26 13:42:17.547646: Current learning rate: 0.00874 +2023-05-26 13:42:51.405063: train_loss -0.932 +2023-05-26 13:42:51.405325: val_loss -0.6843 +2023-05-26 13:42:51.405465: Pseudo dice [0.9353, 0.8598, 0.9006] +2023-05-26 13:42:51.405565: Epoch time: 33.86 s +2023-05-26 13:42:52.973106: +2023-05-26 13:42:52.973308: Epoch 140 +2023-05-26 13:42:52.973446: Current learning rate: 0.00873 +2023-05-26 13:43:25.832499: train_loss -0.9332 +2023-05-26 13:43:25.832751: val_loss -0.6824 +2023-05-26 13:43:25.832892: Pseudo dice [0.9327, 0.8567, 0.9042] +2023-05-26 13:43:25.832996: Epoch time: 32.86 s +2023-05-26 13:43:27.370606: +2023-05-26 13:43:27.370775: Epoch 141 +2023-05-26 13:43:27.370900: Current learning rate: 0.00872 +2023-05-26 13:44:00.217289: train_loss -0.9333 +2023-05-26 13:44:00.217577: val_loss -0.6821 +2023-05-26 13:44:00.217717: Pseudo dice [0.9342, 0.8613, 0.902] +2023-05-26 13:44:00.217816: Epoch time: 32.85 s +2023-05-26 13:44:01.814687: +2023-05-26 13:44:01.815507: Epoch 142 +2023-05-26 13:44:01.815701: Current learning rate: 0.00871 +2023-05-26 13:44:34.564997: train_loss -0.9326 +2023-05-26 13:44:34.565293: val_loss -0.6764 +2023-05-26 13:44:34.565460: Pseudo dice [0.9303, 0.8562, 0.9024] +2023-05-26 13:44:34.565584: Epoch time: 32.75 s +2023-05-26 13:44:36.139426: +2023-05-26 13:44:36.139602: Epoch 143 +2023-05-26 13:44:36.139715: Current learning rate: 0.0087 +2023-05-26 13:45:08.874696: train_loss -0.9321 +2023-05-26 13:45:08.874934: val_loss -0.6826 +2023-05-26 13:45:08.875041: Pseudo dice [0.934, 0.8589, 0.8996] +2023-05-26 13:45:08.875139: Epoch time: 32.74 s +2023-05-26 13:45:10.424538: +2023-05-26 13:45:10.424716: Epoch 144 +2023-05-26 13:45:10.424841: Current learning rate: 0.00869 +2023-05-26 13:45:43.201096: train_loss -0.9335 +2023-05-26 13:45:43.201425: val_loss -0.6811 +2023-05-26 13:45:43.201560: Pseudo dice [0.9325, 0.8586, 0.9034] +2023-05-26 13:45:43.201675: Epoch time: 32.78 s +2023-05-26 13:45:45.018507: +2023-05-26 13:45:45.018873: Epoch 145 +2023-05-26 13:45:45.019103: Current learning rate: 0.00868 +2023-05-26 13:46:18.059810: train_loss -0.9343 +2023-05-26 13:46:18.060082: val_loss -0.6707 +2023-05-26 13:46:18.060197: Pseudo dice [0.9333, 0.8576, 0.9022] +2023-05-26 13:46:18.060292: Epoch time: 33.04 s +2023-05-26 13:46:19.612355: +2023-05-26 13:46:19.612684: Epoch 146 +2023-05-26 13:46:19.612905: Current learning rate: 0.00868 +2023-05-26 13:46:52.676702: train_loss -0.9334 +2023-05-26 13:46:52.676957: val_loss -0.6772 +2023-05-26 13:46:52.677071: Pseudo dice [0.9323, 0.8605, 0.9039] +2023-05-26 13:46:52.677169: Epoch time: 33.07 s +2023-05-26 13:46:54.065377: +2023-05-26 13:46:54.065572: Epoch 147 +2023-05-26 13:46:54.065709: Current learning rate: 0.00867 +2023-05-26 13:47:26.928191: train_loss -0.9349 +2023-05-26 13:47:26.928478: val_loss -0.6819 +2023-05-26 13:47:26.928634: Pseudo dice [0.9316, 0.8596, 0.904] +2023-05-26 13:47:26.928748: Epoch time: 32.86 s +2023-05-26 13:47:28.385627: +2023-05-26 13:47:28.386087: Epoch 148 +2023-05-26 13:47:28.386313: Current learning rate: 0.00866 +2023-05-26 13:48:00.952020: train_loss -0.9347 +2023-05-26 13:48:00.952244: val_loss -0.6817 +2023-05-26 13:48:00.952354: Pseudo dice [0.9331, 0.8589, 0.9041] +2023-05-26 13:48:00.952448: Epoch time: 32.57 s +2023-05-26 13:48:02.308038: +2023-05-26 13:48:02.308200: Epoch 149 +2023-05-26 13:48:02.308301: Current learning rate: 0.00865 +2023-05-26 13:48:35.002738: train_loss -0.9353 +2023-05-26 13:48:35.003088: val_loss -0.6729 +2023-05-26 13:48:35.003214: Pseudo dice [0.9325, 0.8574, 0.9024] +2023-05-26 13:48:35.003300: Epoch time: 32.7 s +2023-05-26 13:48:37.841005: +2023-05-26 13:48:37.841160: Epoch 150 +2023-05-26 13:48:37.841264: Current learning rate: 0.00864 +2023-05-26 13:49:10.834175: train_loss -0.9363 +2023-05-26 13:49:10.834419: val_loss -0.6809 +2023-05-26 13:49:10.834530: Pseudo dice [0.9331, 0.8578, 0.9062] +2023-05-26 13:49:10.834632: Epoch time: 32.99 s +2023-05-26 13:49:12.440687: +2023-05-26 13:49:12.441120: Epoch 151 +2023-05-26 13:49:12.441440: Current learning rate: 0.00863 +2023-05-26 13:49:45.669266: train_loss -0.935 +2023-05-26 13:49:45.669515: val_loss -0.6751 +2023-05-26 13:49:45.669613: Pseudo dice [0.9327, 0.8574, 0.9066] +2023-05-26 13:49:45.669705: Epoch time: 33.23 s +2023-05-26 13:49:47.269643: +2023-05-26 13:49:47.269832: Epoch 152 +2023-05-26 13:49:47.269957: Current learning rate: 0.00862 +2023-05-26 13:50:19.973099: train_loss -0.935 +2023-05-26 13:50:19.973304: val_loss -0.6748 +2023-05-26 13:50:19.973408: Pseudo dice [0.9327, 0.8574, 0.9043] +2023-05-26 13:50:19.973494: Epoch time: 32.7 s +2023-05-26 13:50:21.386564: +2023-05-26 13:50:21.387132: Epoch 153 +2023-05-26 13:50:21.387557: Current learning rate: 0.00861 +2023-05-26 13:50:54.134723: train_loss -0.9349 +2023-05-26 13:50:54.134980: val_loss -0.6819 +2023-05-26 13:50:54.135089: Pseudo dice [0.9347, 0.8619, 0.9038] +2023-05-26 13:50:54.135178: Epoch time: 32.75 s +2023-05-26 13:50:55.570504: +2023-05-26 13:50:55.570672: Epoch 154 +2023-05-26 13:50:55.570773: Current learning rate: 0.0086 +2023-05-26 13:51:28.258997: train_loss -0.9351 +2023-05-26 13:51:28.259534: val_loss -0.6837 +2023-05-26 13:51:28.259836: Pseudo dice [0.9356, 0.86, 0.9043] +2023-05-26 13:51:28.260014: Epoch time: 32.69 s +2023-05-26 13:51:29.616006: +2023-05-26 13:51:29.616536: Epoch 155 +2023-05-26 13:51:29.616713: Current learning rate: 0.00859 +2023-05-26 13:52:02.185744: train_loss -0.935 +2023-05-26 13:52:02.186083: val_loss -0.6801 +2023-05-26 13:52:02.186228: Pseudo dice [0.9352, 0.8613, 0.903] +2023-05-26 13:52:02.186329: Epoch time: 32.57 s +2023-05-26 13:52:02.186409: Yayy! New best EMA pseudo Dice: 0.8988 +2023-05-26 13:52:05.254039: +2023-05-26 13:52:05.254218: Epoch 156 +2023-05-26 13:52:05.254350: Current learning rate: 0.00858 +2023-05-26 13:52:37.927949: train_loss -0.9355 +2023-05-26 13:52:37.928351: val_loss -0.6817 +2023-05-26 13:52:37.928461: Pseudo dice [0.933, 0.8585, 0.904] +2023-05-26 13:52:37.928538: Epoch time: 32.68 s +2023-05-26 13:52:39.430573: +2023-05-26 13:52:39.430774: Epoch 157 +2023-05-26 13:52:39.430917: Current learning rate: 0.00858 +2023-05-26 13:53:12.367515: train_loss -0.9353 +2023-05-26 13:53:12.367768: val_loss -0.6789 +2023-05-26 13:53:12.367882: Pseudo dice [0.9324, 0.8609, 0.9038] +2023-05-26 13:53:12.367977: Epoch time: 32.94 s +2023-05-26 13:53:13.882970: +2023-05-26 13:53:13.883188: Epoch 158 +2023-05-26 13:53:13.883334: Current learning rate: 0.00857 +2023-05-26 13:53:46.725322: train_loss -0.9358 +2023-05-26 13:53:46.725571: val_loss -0.6819 +2023-05-26 13:53:46.725689: Pseudo dice [0.9339, 0.8581, 0.9051] +2023-05-26 13:53:46.725789: Epoch time: 32.84 s +2023-05-26 13:53:46.726305: Yayy! New best EMA pseudo Dice: 0.8988 +2023-05-26 13:53:49.839071: +2023-05-26 13:53:49.839428: Epoch 159 +2023-05-26 13:53:49.839692: Current learning rate: 0.00856 +2023-05-26 13:54:22.995344: train_loss -0.9356 +2023-05-26 13:54:22.995580: val_loss -0.6678 +2023-05-26 13:54:22.995705: Pseudo dice [0.9307, 0.857, 0.9025] +2023-05-26 13:54:22.995812: Epoch time: 33.16 s +2023-05-26 13:54:24.568209: +2023-05-26 13:54:24.568433: Epoch 160 +2023-05-26 13:54:24.568563: Current learning rate: 0.00855 +2023-05-26 13:54:57.230739: train_loss -0.9365 +2023-05-26 13:54:57.231000: val_loss -0.6782 +2023-05-26 13:54:57.231123: Pseudo dice [0.9341, 0.8599, 0.9017] +2023-05-26 13:54:57.231227: Epoch time: 32.66 s +2023-05-26 13:54:58.677793: +2023-05-26 13:54:58.677996: Epoch 161 +2023-05-26 13:54:58.678194: Current learning rate: 0.00854 +2023-05-26 13:55:31.409564: train_loss -0.9365 +2023-05-26 13:55:31.409847: val_loss -0.6764 +2023-05-26 13:55:31.409992: Pseudo dice [0.9327, 0.8578, 0.9047] +2023-05-26 13:55:31.410082: Epoch time: 32.73 s +2023-05-26 13:55:32.925946: +2023-05-26 13:55:32.926156: Epoch 162 +2023-05-26 13:55:32.926295: Current learning rate: 0.00853 +2023-05-26 13:56:05.617663: train_loss -0.9364 +2023-05-26 13:56:05.617960: val_loss -0.6851 +2023-05-26 13:56:05.618057: Pseudo dice [0.9338, 0.8607, 0.9061] +2023-05-26 13:56:05.618145: Epoch time: 32.69 s +2023-05-26 13:56:07.328772: +2023-05-26 13:56:07.328943: Epoch 163 +2023-05-26 13:56:07.329046: Current learning rate: 0.00852 +2023-05-26 13:56:40.132309: train_loss -0.9368 +2023-05-26 13:56:40.132583: val_loss -0.6654 +2023-05-26 13:56:40.132709: Pseudo dice [0.9324, 0.8579, 0.8973] +2023-05-26 13:56:40.132799: Epoch time: 32.8 s +2023-05-26 13:56:41.761955: +2023-05-26 13:56:41.762195: Epoch 164 +2023-05-26 13:56:41.762330: Current learning rate: 0.00851 +2023-05-26 13:57:14.434878: train_loss -0.9377 +2023-05-26 13:57:14.435213: val_loss -0.6674 +2023-05-26 13:57:14.435339: Pseudo dice [0.9328, 0.858, 0.9018] +2023-05-26 13:57:14.435430: Epoch time: 32.67 s +2023-05-26 13:57:15.888022: +2023-05-26 13:57:15.888359: Epoch 165 +2023-05-26 13:57:15.888586: Current learning rate: 0.0085 +2023-05-26 13:57:49.195865: train_loss -0.938 +2023-05-26 13:57:49.196230: val_loss -0.6748 +2023-05-26 13:57:49.196451: Pseudo dice [0.9337, 0.8604, 0.9033] +2023-05-26 13:57:49.196617: Epoch time: 33.31 s +2023-05-26 13:57:50.832722: +2023-05-26 13:57:50.832922: Epoch 166 +2023-05-26 13:57:50.833032: Current learning rate: 0.00849 +2023-05-26 13:58:23.724292: train_loss -0.9371 +2023-05-26 13:58:23.724538: val_loss -0.6771 +2023-05-26 13:58:23.724653: Pseudo dice [0.9344, 0.8605, 0.9016] +2023-05-26 13:58:23.724759: Epoch time: 32.89 s +2023-05-26 13:58:25.184830: +2023-05-26 13:58:25.185029: Epoch 167 +2023-05-26 13:58:25.185208: Current learning rate: 0.00848 +2023-05-26 13:58:58.341595: train_loss -0.9368 +2023-05-26 13:58:58.341904: val_loss -0.6734 +2023-05-26 13:58:58.342015: Pseudo dice [0.9336, 0.8598, 0.9047] +2023-05-26 13:58:58.342116: Epoch time: 33.16 s +2023-05-26 13:58:59.867328: +2023-05-26 13:58:59.867493: Epoch 168 +2023-05-26 13:58:59.867608: Current learning rate: 0.00847 +2023-05-26 13:59:32.543236: train_loss -0.9372 +2023-05-26 13:59:32.543494: val_loss -0.6717 +2023-05-26 13:59:32.543608: Pseudo dice [0.9334, 0.858, 0.9018] +2023-05-26 13:59:32.543710: Epoch time: 32.68 s +2023-05-26 13:59:33.979708: +2023-05-26 13:59:33.979889: Epoch 169 +2023-05-26 13:59:33.980015: Current learning rate: 0.00847 +2023-05-26 14:00:06.570064: train_loss -0.9369 +2023-05-26 14:00:06.570427: val_loss -0.677 +2023-05-26 14:00:06.570573: Pseudo dice [0.9345, 0.8602, 0.899] +2023-05-26 14:00:06.570674: Epoch time: 32.59 s +2023-05-26 14:00:08.314761: +2023-05-26 14:00:08.314982: Epoch 170 +2023-05-26 14:00:08.315107: Current learning rate: 0.00846 +2023-05-26 14:00:41.110357: train_loss -0.9379 +2023-05-26 14:00:41.110589: val_loss -0.6901 +2023-05-26 14:00:41.110703: Pseudo dice [0.9347, 0.8631, 0.9058] +2023-05-26 14:00:41.110806: Epoch time: 32.8 s +2023-05-26 14:00:42.511262: +2023-05-26 14:00:42.511422: Epoch 171 +2023-05-26 14:00:42.511525: Current learning rate: 0.00845 +2023-05-26 14:01:15.215233: train_loss -0.9384 +2023-05-26 14:01:15.215485: val_loss -0.6771 +2023-05-26 14:01:15.215609: Pseudo dice [0.9341, 0.8589, 0.9039] +2023-05-26 14:01:15.215713: Epoch time: 32.71 s +2023-05-26 14:01:16.726819: +2023-05-26 14:01:16.726996: Epoch 172 +2023-05-26 14:01:16.727110: Current learning rate: 0.00844 +2023-05-26 14:01:49.453936: train_loss -0.9371 +2023-05-26 14:01:49.454356: val_loss -0.6739 +2023-05-26 14:01:49.454527: Pseudo dice [0.9342, 0.8597, 0.8944] +2023-05-26 14:01:49.454659: Epoch time: 32.73 s +2023-05-26 14:01:50.943409: +2023-05-26 14:01:50.943618: Epoch 173 +2023-05-26 14:01:50.943772: Current learning rate: 0.00843 +2023-05-26 14:02:23.701715: train_loss -0.9362 +2023-05-26 14:02:23.702013: val_loss -0.6837 +2023-05-26 14:02:23.702168: Pseudo dice [0.9355, 0.8606, 0.9016] +2023-05-26 14:02:23.702275: Epoch time: 32.76 s +2023-05-26 14:02:25.110299: +2023-05-26 14:02:25.110711: Epoch 174 +2023-05-26 14:02:25.111649: Current learning rate: 0.00842 +2023-05-26 14:02:57.826606: train_loss -0.9366 +2023-05-26 14:02:57.826963: val_loss -0.6811 +2023-05-26 14:02:57.827155: Pseudo dice [0.9366, 0.8619, 0.9017] +2023-05-26 14:02:57.827348: Epoch time: 32.72 s +2023-05-26 14:02:59.352445: +2023-05-26 14:02:59.352775: Epoch 175 +2023-05-26 14:02:59.352987: Current learning rate: 0.00841 +2023-05-26 14:03:32.420006: train_loss -0.9369 +2023-05-26 14:03:32.420238: val_loss -0.6788 +2023-05-26 14:03:32.420358: Pseudo dice [0.9352, 0.8594, 0.9042] +2023-05-26 14:03:32.420462: Epoch time: 33.07 s +2023-05-26 14:03:34.252452: +2023-05-26 14:03:34.252660: Epoch 176 +2023-05-26 14:03:34.252778: Current learning rate: 0.0084 +2023-05-26 14:04:07.198072: train_loss -0.9378 +2023-05-26 14:04:07.198303: val_loss -0.6793 +2023-05-26 14:04:07.198403: Pseudo dice [0.9336, 0.8587, 0.9028] +2023-05-26 14:04:07.198485: Epoch time: 32.95 s +2023-05-26 14:04:08.525167: +2023-05-26 14:04:08.525341: Epoch 177 +2023-05-26 14:04:08.525458: Current learning rate: 0.00839 +2023-05-26 14:04:41.307582: train_loss -0.937 +2023-05-26 14:04:41.307792: val_loss -0.6788 +2023-05-26 14:04:41.307899: Pseudo dice [0.9353, 0.8608, 0.9039] +2023-05-26 14:04:41.307974: Epoch time: 32.78 s +2023-05-26 14:04:41.308036: Yayy! New best EMA pseudo Dice: 0.8989 +2023-05-26 14:04:44.109011: +2023-05-26 14:04:44.109194: Epoch 178 +2023-05-26 14:04:44.109314: Current learning rate: 0.00838 +2023-05-26 14:05:16.931628: train_loss -0.9379 +2023-05-26 14:05:16.932395: val_loss -0.6803 +2023-05-26 14:05:16.932565: Pseudo dice [0.9357, 0.8609, 0.9049] +2023-05-26 14:05:16.932706: Epoch time: 32.82 s +2023-05-26 14:05:16.932806: Yayy! New best EMA pseudo Dice: 0.899 +2023-05-26 14:05:19.756039: +2023-05-26 14:05:19.756409: Epoch 179 +2023-05-26 14:05:19.756593: Current learning rate: 0.00837 +2023-05-26 14:05:52.489273: train_loss -0.9384 +2023-05-26 14:05:52.489500: val_loss -0.6791 +2023-05-26 14:05:52.489612: Pseudo dice [0.9345, 0.8615, 0.8989] +2023-05-26 14:05:52.489712: Epoch time: 32.73 s +2023-05-26 14:05:53.895680: +2023-05-26 14:05:53.895965: Epoch 180 +2023-05-26 14:05:53.896226: Current learning rate: 0.00836 +2023-05-26 14:06:26.596023: train_loss -0.9372 +2023-05-26 14:06:26.596249: val_loss -0.6766 +2023-05-26 14:06:26.596356: Pseudo dice [0.9324, 0.8602, 0.9019] +2023-05-26 14:06:26.596455: Epoch time: 32.7 s +2023-05-26 14:06:27.994178: +2023-05-26 14:06:27.994334: Epoch 181 +2023-05-26 14:06:27.994672: Current learning rate: 0.00836 +2023-05-26 14:07:00.640329: train_loss -0.9376 +2023-05-26 14:07:00.640619: val_loss -0.6711 +2023-05-26 14:07:00.640730: Pseudo dice [0.9349, 0.86, 0.8993] +2023-05-26 14:07:00.640814: Epoch time: 32.65 s +2023-05-26 14:07:02.127371: +2023-05-26 14:07:02.128096: Epoch 182 +2023-05-26 14:07:02.128318: Current learning rate: 0.00835 +2023-05-26 14:07:35.136049: train_loss -0.9386 +2023-05-26 14:07:35.136314: val_loss -0.6607 +2023-05-26 14:07:35.136436: Pseudo dice [0.9326, 0.8592, 0.9013] +2023-05-26 14:07:35.136547: Epoch time: 33.01 s +2023-05-26 14:07:36.580893: +2023-05-26 14:07:36.581222: Epoch 183 +2023-05-26 14:07:36.581404: Current learning rate: 0.00834 +2023-05-26 14:08:09.819794: train_loss -0.9391 +2023-05-26 14:08:09.820105: val_loss -0.6676 +2023-05-26 14:08:09.820276: Pseudo dice [0.9331, 0.8589, 0.9012] +2023-05-26 14:08:09.820394: Epoch time: 33.24 s +2023-05-26 14:08:11.371296: +2023-05-26 14:08:11.371629: Epoch 184 +2023-05-26 14:08:11.371757: Current learning rate: 0.00833 +2023-05-26 14:08:44.060842: train_loss -0.9385 +2023-05-26 14:08:44.061188: val_loss -0.6708 +2023-05-26 14:08:44.061336: Pseudo dice [0.9352, 0.8609, 0.9] +2023-05-26 14:08:44.061445: Epoch time: 32.69 s +2023-05-26 14:08:45.621192: +2023-05-26 14:08:45.621655: Epoch 185 +2023-05-26 14:08:45.622516: Current learning rate: 0.00832 +2023-05-26 14:09:19.030313: train_loss -0.9399 +2023-05-26 14:09:19.031003: val_loss -0.661 +2023-05-26 14:09:19.031146: Pseudo dice [0.9314, 0.8571, 0.9038] +2023-05-26 14:09:19.031250: Epoch time: 33.41 s +2023-05-26 14:09:20.479464: +2023-05-26 14:09:20.479664: Epoch 186 +2023-05-26 14:09:20.479798: Current learning rate: 0.00831 +2023-05-26 14:09:53.967957: train_loss -0.9397 +2023-05-26 14:09:53.968246: val_loss -0.6624 +2023-05-26 14:09:53.968395: Pseudo dice [0.9348, 0.8604, 0.902] +2023-05-26 14:09:53.968504: Epoch time: 33.49 s +2023-05-26 14:09:55.647170: +2023-05-26 14:09:55.647542: Epoch 187 +2023-05-26 14:09:55.647676: Current learning rate: 0.0083 +2023-05-26 14:10:29.901559: train_loss -0.939 +2023-05-26 14:10:29.901795: val_loss -0.6723 +2023-05-26 14:10:29.901904: Pseudo dice [0.9339, 0.8626, 0.8992] +2023-05-26 14:10:29.902006: Epoch time: 34.26 s +2023-05-26 14:10:31.338334: +2023-05-26 14:10:31.338515: Epoch 188 +2023-05-26 14:10:31.338631: Current learning rate: 0.00829 +2023-05-26 14:11:04.495245: train_loss -0.9397 +2023-05-26 14:11:04.495507: val_loss -0.677 +2023-05-26 14:11:04.495643: Pseudo dice [0.9347, 0.8607, 0.9046] +2023-05-26 14:11:04.495732: Epoch time: 33.16 s +2023-05-26 14:11:06.278659: +2023-05-26 14:11:06.278865: Epoch 189 +2023-05-26 14:11:06.278979: Current learning rate: 0.00828 +2023-05-26 14:11:38.971081: train_loss -0.939 +2023-05-26 14:11:38.971321: val_loss -0.6763 +2023-05-26 14:11:38.971782: Pseudo dice [0.9339, 0.859, 0.9046] +2023-05-26 14:11:38.971879: Epoch time: 32.69 s +2023-05-26 14:11:40.484898: +2023-05-26 14:11:40.485232: Epoch 190 +2023-05-26 14:11:40.485541: Current learning rate: 0.00827 +2023-05-26 14:12:13.170098: train_loss -0.9379 +2023-05-26 14:12:13.170398: val_loss -0.6767 +2023-05-26 14:12:13.170578: Pseudo dice [0.9338, 0.8601, 0.9016] +2023-05-26 14:12:13.170676: Epoch time: 32.69 s +2023-05-26 14:12:14.663831: +2023-05-26 14:12:14.664423: Epoch 191 +2023-05-26 14:12:14.664528: Current learning rate: 0.00826 +2023-05-26 14:12:47.361398: train_loss -0.9386 +2023-05-26 14:12:47.361707: val_loss -0.6803 +2023-05-26 14:12:47.361915: Pseudo dice [0.9342, 0.8618, 0.9035] +2023-05-26 14:12:47.362081: Epoch time: 32.7 s +2023-05-26 14:12:48.853773: +2023-05-26 14:12:48.854109: Epoch 192 +2023-05-26 14:12:48.854336: Current learning rate: 0.00825 +2023-05-26 14:13:21.604669: train_loss -0.94 +2023-05-26 14:13:21.604890: val_loss -0.6721 +2023-05-26 14:13:21.604999: Pseudo dice [0.9328, 0.8578, 0.9061] +2023-05-26 14:13:21.605098: Epoch time: 32.75 s +2023-05-26 14:13:23.197330: +2023-05-26 14:13:23.197598: Epoch 193 +2023-05-26 14:13:23.197817: Current learning rate: 0.00824 +2023-05-26 14:13:56.128897: train_loss -0.9405 +2023-05-26 14:13:56.129156: val_loss -0.6709 +2023-05-26 14:13:56.129279: Pseudo dice [0.9333, 0.861, 0.9047] +2023-05-26 14:13:56.129365: Epoch time: 32.93 s +2023-05-26 14:13:57.590358: +2023-05-26 14:13:57.590535: Epoch 194 +2023-05-26 14:13:57.590647: Current learning rate: 0.00824 +2023-05-26 14:14:30.164809: train_loss -0.9401 +2023-05-26 14:14:30.165041: val_loss -0.6735 +2023-05-26 14:14:30.165148: Pseudo dice [0.9332, 0.8604, 0.903] +2023-05-26 14:14:30.165247: Epoch time: 32.58 s +2023-05-26 14:14:31.861540: +2023-05-26 14:14:31.861959: Epoch 195 +2023-05-26 14:14:31.862147: Current learning rate: 0.00823 +2023-05-26 14:15:04.534612: train_loss -0.9404 +2023-05-26 14:15:04.535043: val_loss -0.6725 +2023-05-26 14:15:04.535261: Pseudo dice [0.9359, 0.861, 0.9002] +2023-05-26 14:15:04.535419: Epoch time: 32.67 s +2023-05-26 14:15:05.949423: +2023-05-26 14:15:05.949689: Epoch 196 +2023-05-26 14:15:05.949982: Current learning rate: 0.00822 +2023-05-26 14:15:38.528826: train_loss -0.9397 +2023-05-26 14:15:38.529311: val_loss -0.6725 +2023-05-26 14:15:38.529588: Pseudo dice [0.935, 0.8626, 0.9053] +2023-05-26 14:15:38.529678: Epoch time: 32.58 s +2023-05-26 14:15:38.529744: Yayy! New best EMA pseudo Dice: 0.8991 +2023-05-26 14:15:41.663217: +2023-05-26 14:15:41.663429: Epoch 197 +2023-05-26 14:15:41.663556: Current learning rate: 0.00821 +2023-05-26 14:16:14.348693: train_loss -0.9406 +2023-05-26 14:16:14.349125: val_loss -0.6685 +2023-05-26 14:16:14.349317: Pseudo dice [0.9332, 0.8583, 0.9018] +2023-05-26 14:16:14.349435: Epoch time: 32.69 s +2023-05-26 14:16:15.788964: +2023-05-26 14:16:15.789232: Epoch 198 +2023-05-26 14:16:15.789387: Current learning rate: 0.0082 +2023-05-26 14:16:48.530252: train_loss -0.9391 +2023-05-26 14:16:48.530576: val_loss -0.6754 +2023-05-26 14:16:48.530717: Pseudo dice [0.9326, 0.8612, 0.9015] +2023-05-26 14:16:48.530810: Epoch time: 32.74 s +2023-05-26 14:16:50.021226: +2023-05-26 14:16:50.021607: Epoch 199 +2023-05-26 14:16:50.021833: Current learning rate: 0.00819 +2023-05-26 14:17:22.621854: train_loss -0.9393 +2023-05-26 14:17:22.622084: val_loss -0.6615 +2023-05-26 14:17:22.622187: Pseudo dice [0.9338, 0.8576, 0.9008] +2023-05-26 14:17:22.622287: Epoch time: 32.6 s +2023-05-26 14:17:25.535817: +2023-05-26 14:17:25.536124: Epoch 200 +2023-05-26 14:17:25.536378: Current learning rate: 0.00818 +2023-05-26 14:17:58.180515: train_loss -0.939 +2023-05-26 14:17:58.180980: val_loss -0.6748 +2023-05-26 14:17:58.181219: Pseudo dice [0.9329, 0.8579, 0.9027] +2023-05-26 14:17:58.181395: Epoch time: 32.65 s +2023-05-26 14:17:59.982083: +2023-05-26 14:17:59.982408: Epoch 201 +2023-05-26 14:17:59.982605: Current learning rate: 0.00817 +2023-05-26 14:18:32.707433: train_loss -0.9399 +2023-05-26 14:18:32.707650: val_loss -0.6725 +2023-05-26 14:18:32.707754: Pseudo dice [0.9354, 0.8613, 0.8998] +2023-05-26 14:18:32.707847: Epoch time: 32.73 s +2023-05-26 14:18:34.141817: +2023-05-26 14:18:34.141984: Epoch 202 +2023-05-26 14:18:34.142082: Current learning rate: 0.00816 +2023-05-26 14:19:06.861270: train_loss -0.9394 +2023-05-26 14:19:06.861519: val_loss -0.6693 +2023-05-26 14:19:06.861632: Pseudo dice [0.9345, 0.86, 0.8972] +2023-05-26 14:19:06.861736: Epoch time: 32.72 s +2023-05-26 14:19:08.417302: +2023-05-26 14:19:08.417966: Epoch 203 +2023-05-26 14:19:08.418184: Current learning rate: 0.00815 +2023-05-26 14:19:41.399896: train_loss -0.9404 +2023-05-26 14:19:41.400142: val_loss -0.6739 +2023-05-26 14:19:41.400258: Pseudo dice [0.9358, 0.8605, 0.9035] +2023-05-26 14:19:41.400361: Epoch time: 32.98 s +2023-05-26 14:19:43.016941: +2023-05-26 14:19:43.017129: Epoch 204 +2023-05-26 14:19:43.017251: Current learning rate: 0.00814 +2023-05-26 14:20:15.688365: train_loss -0.9411 +2023-05-26 14:20:15.688686: val_loss -0.6713 +2023-05-26 14:20:15.688849: Pseudo dice [0.9349, 0.8604, 0.8993] +2023-05-26 14:20:15.688997: Epoch time: 32.67 s +2023-05-26 14:20:17.161015: +2023-05-26 14:20:17.161191: Epoch 205 +2023-05-26 14:20:17.161293: Current learning rate: 0.00813 +2023-05-26 14:20:49.995724: train_loss -0.9407 +2023-05-26 14:20:49.995952: val_loss -0.6688 +2023-05-26 14:20:49.996084: Pseudo dice [0.9339, 0.8602, 0.9038] +2023-05-26 14:20:49.996190: Epoch time: 32.84 s +2023-05-26 14:20:51.396126: +2023-05-26 14:20:51.396319: Epoch 206 +2023-05-26 14:20:51.396436: Current learning rate: 0.00813 +2023-05-26 14:21:24.024837: train_loss -0.9399 +2023-05-26 14:21:24.025187: val_loss -0.6673 +2023-05-26 14:21:24.025414: Pseudo dice [0.9343, 0.8595, 0.9019] +2023-05-26 14:21:24.025595: Epoch time: 32.63 s +2023-05-26 14:21:25.282887: +2023-05-26 14:21:25.283043: Epoch 207 +2023-05-26 14:21:25.283261: Current learning rate: 0.00812 +2023-05-26 14:21:58.143178: train_loss -0.9406 +2023-05-26 14:21:58.143409: val_loss -0.6708 +2023-05-26 14:21:58.143528: Pseudo dice [0.9339, 0.8588, 0.9052] +2023-05-26 14:21:58.143635: Epoch time: 32.86 s +2023-05-26 14:21:59.509732: +2023-05-26 14:21:59.509887: Epoch 208 +2023-05-26 14:21:59.509986: Current learning rate: 0.00811 +2023-05-26 14:22:32.336498: train_loss -0.9398 +2023-05-26 14:22:32.336807: val_loss -0.6723 +2023-05-26 14:22:32.336931: Pseudo dice [0.9336, 0.8607, 0.8996] +2023-05-26 14:22:32.337023: Epoch time: 32.83 s +2023-05-26 14:22:33.845970: +2023-05-26 14:22:33.846310: Epoch 209 +2023-05-26 14:22:33.846509: Current learning rate: 0.0081 +2023-05-26 14:23:06.671266: train_loss -0.9375 +2023-05-26 14:23:06.671510: val_loss -0.6851 +2023-05-26 14:23:06.671629: Pseudo dice [0.9336, 0.86, 0.904] +2023-05-26 14:23:06.671729: Epoch time: 32.83 s +2023-05-26 14:23:08.114928: +2023-05-26 14:23:08.115305: Epoch 210 +2023-05-26 14:23:08.115730: Current learning rate: 0.00809 +2023-05-26 14:23:40.900302: train_loss -0.9388 +2023-05-26 14:23:40.900585: val_loss -0.6729 +2023-05-26 14:23:40.900725: Pseudo dice [0.9349, 0.8611, 0.9023] +2023-05-26 14:23:40.900830: Epoch time: 32.79 s +2023-05-26 14:23:42.419020: +2023-05-26 14:23:42.419396: Epoch 211 +2023-05-26 14:23:42.419684: Current learning rate: 0.00808 +2023-05-26 14:24:14.947356: train_loss -0.9392 +2023-05-26 14:24:14.947717: val_loss -0.6709 +2023-05-26 14:24:14.947820: Pseudo dice [0.9331, 0.8591, 0.9017] +2023-05-26 14:24:14.947896: Epoch time: 32.53 s +2023-05-26 14:24:16.291226: +2023-05-26 14:24:16.291397: Epoch 212 +2023-05-26 14:24:16.291497: Current learning rate: 0.00807 +2023-05-26 14:24:48.885764: train_loss -0.9408 +2023-05-26 14:24:48.886012: val_loss -0.6648 +2023-05-26 14:24:48.886125: Pseudo dice [0.9329, 0.8585, 0.9015] +2023-05-26 14:24:48.886216: Epoch time: 32.6 s +2023-05-26 14:24:50.420059: +2023-05-26 14:24:50.420377: Epoch 213 +2023-05-26 14:24:50.420549: Current learning rate: 0.00806 +2023-05-26 14:25:23.610428: train_loss -0.9407 +2023-05-26 14:25:23.610641: val_loss -0.6772 +2023-05-26 14:25:23.610745: Pseudo dice [0.9336, 0.8601, 0.9016] +2023-05-26 14:25:23.610850: Epoch time: 33.19 s +2023-05-26 14:25:25.117512: +2023-05-26 14:25:25.117836: Epoch 214 +2023-05-26 14:25:25.118163: Current learning rate: 0.00805 +2023-05-26 14:25:58.094399: train_loss -0.9405 +2023-05-26 14:25:58.094661: val_loss -0.6681 +2023-05-26 14:25:58.094815: Pseudo dice [0.9319, 0.8597, 0.9015] +2023-05-26 14:25:58.094913: Epoch time: 32.98 s +2023-05-26 14:25:59.334934: +2023-05-26 14:25:59.335222: Epoch 215 +2023-05-26 14:25:59.335395: Current learning rate: 0.00804 +2023-05-26 14:26:32.643771: train_loss -0.9405 +2023-05-26 14:26:32.643989: val_loss -0.6704 +2023-05-26 14:26:32.644108: Pseudo dice [0.9328, 0.8591, 0.9036] +2023-05-26 14:26:32.644194: Epoch time: 33.31 s +2023-05-26 14:26:33.872327: +2023-05-26 14:26:33.872651: Epoch 216 +2023-05-26 14:26:33.872808: Current learning rate: 0.00803 +2023-05-26 14:27:06.659446: train_loss -0.942 +2023-05-26 14:27:06.659690: val_loss -0.6735 +2023-05-26 14:27:06.659808: Pseudo dice [0.9339, 0.8619, 0.9042] +2023-05-26 14:27:06.659909: Epoch time: 32.79 s +2023-05-26 14:27:07.893258: +2023-05-26 14:27:07.893402: Epoch 217 +2023-05-26 14:27:07.893505: Current learning rate: 0.00802 +2023-05-26 14:27:40.632005: train_loss -0.9421 +2023-05-26 14:27:40.632234: val_loss -0.6661 +2023-05-26 14:27:40.632350: Pseudo dice [0.9324, 0.8602, 0.9025] +2023-05-26 14:27:40.632451: Epoch time: 32.74 s +2023-05-26 14:27:41.915308: +2023-05-26 14:27:41.915580: Epoch 218 +2023-05-26 14:27:41.915815: Current learning rate: 0.00801 +2023-05-26 14:28:14.606988: train_loss -0.9426 +2023-05-26 14:28:14.607219: val_loss -0.6693 +2023-05-26 14:28:14.607330: Pseudo dice [0.9347, 0.8599, 0.9043] +2023-05-26 14:28:14.607427: Epoch time: 32.69 s +2023-05-26 14:28:15.883453: +2023-05-26 14:28:15.883588: Epoch 219 +2023-05-26 14:28:15.883687: Current learning rate: 0.00801 +2023-05-26 14:28:48.471086: train_loss -0.9431 +2023-05-26 14:28:48.471385: val_loss -0.6658 +2023-05-26 14:28:48.471515: Pseudo dice [0.9332, 0.8612, 0.9016] +2023-05-26 14:28:48.471615: Epoch time: 32.59 s +2023-05-26 14:28:49.924393: +2023-05-26 14:28:49.924740: Epoch 220 +2023-05-26 14:28:49.925006: Current learning rate: 0.008 +2023-05-26 14:29:22.590914: train_loss -0.9429 +2023-05-26 14:29:22.591155: val_loss -0.6686 +2023-05-26 14:29:22.591261: Pseudo dice [0.9358, 0.8609, 0.9003] +2023-05-26 14:29:22.591357: Epoch time: 32.67 s +2023-05-26 14:29:24.202179: +2023-05-26 14:29:24.202341: Epoch 221 +2023-05-26 14:29:24.202448: Current learning rate: 0.00799 +2023-05-26 14:29:57.129272: train_loss -0.9431 +2023-05-26 14:29:57.129672: val_loss -0.6681 +2023-05-26 14:29:57.129939: Pseudo dice [0.9346, 0.8621, 0.9014] +2023-05-26 14:29:57.130154: Epoch time: 32.93 s +2023-05-26 14:29:58.564870: +2023-05-26 14:29:58.565021: Epoch 222 +2023-05-26 14:29:58.565152: Current learning rate: 0.00798 +2023-05-26 14:30:31.639956: train_loss -0.9427 +2023-05-26 14:30:31.640258: val_loss -0.6667 +2023-05-26 14:30:31.640384: Pseudo dice [0.935, 0.8623, 0.901] +2023-05-26 14:30:31.640475: Epoch time: 33.08 s +2023-05-26 14:30:32.983726: +2023-05-26 14:30:32.984097: Epoch 223 +2023-05-26 14:30:32.984646: Current learning rate: 0.00797 +2023-05-26 14:31:05.710004: train_loss -0.943 +2023-05-26 14:31:05.710337: val_loss -0.6678 +2023-05-26 14:31:05.710493: Pseudo dice [0.9352, 0.8619, 0.9038] +2023-05-26 14:31:05.710605: Epoch time: 32.73 s +2023-05-26 14:31:07.194551: +2023-05-26 14:31:07.194768: Epoch 224 +2023-05-26 14:31:07.195008: Current learning rate: 0.00796 +2023-05-26 14:31:39.918545: train_loss -0.9438 +2023-05-26 14:31:39.918807: val_loss -0.667 +2023-05-26 14:31:39.918963: Pseudo dice [0.9344, 0.8624, 0.9033] +2023-05-26 14:31:39.919064: Epoch time: 32.73 s +2023-05-26 14:31:41.395220: +2023-05-26 14:31:41.395439: Epoch 225 +2023-05-26 14:31:41.395564: Current learning rate: 0.00795 +2023-05-26 14:32:14.178252: train_loss -0.9435 +2023-05-26 14:32:14.178469: val_loss -0.6719 +2023-05-26 14:32:14.178576: Pseudo dice [0.9352, 0.8628, 0.9052] +2023-05-26 14:32:14.178662: Epoch time: 32.78 s +2023-05-26 14:32:14.178953: Yayy! New best EMA pseudo Dice: 0.8993 +2023-05-26 14:32:17.037621: +2023-05-26 14:32:17.037760: Epoch 226 +2023-05-26 14:32:17.037860: Current learning rate: 0.00794 +2023-05-26 14:32:49.721647: train_loss -0.9433 +2023-05-26 14:32:49.721902: val_loss -0.6702 +2023-05-26 14:32:49.722018: Pseudo dice [0.9342, 0.8585, 0.9031] +2023-05-26 14:32:49.722116: Epoch time: 32.69 s +2023-05-26 14:32:51.459436: +2023-05-26 14:32:51.459719: Epoch 227 +2023-05-26 14:32:51.459991: Current learning rate: 0.00793 +2023-05-26 14:33:24.172032: train_loss -0.943 +2023-05-26 14:33:24.172300: val_loss -0.6648 +2023-05-26 14:33:24.172448: Pseudo dice [0.9332, 0.8592, 0.9042] +2023-05-26 14:33:24.172534: Epoch time: 32.71 s +2023-05-26 14:33:25.461657: +2023-05-26 14:33:25.461931: Epoch 228 +2023-05-26 14:33:25.462132: Current learning rate: 0.00792 +2023-05-26 14:33:58.121036: train_loss -0.9424 +2023-05-26 14:33:58.121272: val_loss -0.6683 +2023-05-26 14:33:58.121391: Pseudo dice [0.933, 0.8592, 0.903] +2023-05-26 14:33:58.121494: Epoch time: 32.66 s +2023-05-26 14:33:59.543159: +2023-05-26 14:33:59.543396: Epoch 229 +2023-05-26 14:33:59.543552: Current learning rate: 0.00791 +2023-05-26 14:34:32.376705: train_loss -0.9436 +2023-05-26 14:34:32.376945: val_loss -0.663 +2023-05-26 14:34:32.377061: Pseudo dice [0.9331, 0.8614, 0.9017] +2023-05-26 14:34:32.377158: Epoch time: 32.83 s +2023-05-26 14:34:33.839401: +2023-05-26 14:34:33.839619: Epoch 230 +2023-05-26 14:34:33.839762: Current learning rate: 0.0079 +2023-05-26 14:35:06.523999: train_loss -0.9436 +2023-05-26 14:35:06.524275: val_loss -0.6627 +2023-05-26 14:35:06.524402: Pseudo dice [0.9353, 0.8602, 0.9048] +2023-05-26 14:35:06.524494: Epoch time: 32.69 s +2023-05-26 14:35:07.952219: +2023-05-26 14:35:07.952423: Epoch 231 +2023-05-26 14:35:07.952579: Current learning rate: 0.00789 +2023-05-26 14:35:41.773426: train_loss -0.9434 +2023-05-26 14:35:41.773664: val_loss -0.6646 +2023-05-26 14:35:41.773782: Pseudo dice [0.9331, 0.86, 0.9016] +2023-05-26 14:35:41.773882: Epoch time: 33.82 s +2023-05-26 14:35:43.129253: +2023-05-26 14:35:43.129411: Epoch 232 +2023-05-26 14:35:43.129515: Current learning rate: 0.00789 +2023-05-26 14:36:15.830339: train_loss -0.9439 +2023-05-26 14:36:15.830615: val_loss -0.6592 +2023-05-26 14:36:15.830729: Pseudo dice [0.9343, 0.861, 0.9022] +2023-05-26 14:36:15.830820: Epoch time: 32.7 s +2023-05-26 14:36:17.291491: +2023-05-26 14:36:17.291682: Epoch 233 +2023-05-26 14:36:17.291812: Current learning rate: 0.00788 +2023-05-26 14:36:49.944948: train_loss -0.9429 +2023-05-26 14:36:49.945210: val_loss -0.6735 +2023-05-26 14:36:49.945332: Pseudo dice [0.9332, 0.861, 0.9037] +2023-05-26 14:36:49.945415: Epoch time: 32.65 s +2023-05-26 14:36:51.734281: +2023-05-26 14:36:51.734682: Epoch 234 +2023-05-26 14:36:51.735001: Current learning rate: 0.00787 +2023-05-26 14:37:24.449749: train_loss -0.9419 +2023-05-26 14:37:24.450042: val_loss -0.6661 +2023-05-26 14:37:24.450176: Pseudo dice [0.9343, 0.8615, 0.9026] +2023-05-26 14:37:24.450281: Epoch time: 32.72 s +2023-05-26 14:37:25.842658: +2023-05-26 14:37:25.842857: Epoch 235 +2023-05-26 14:37:25.842974: Current learning rate: 0.00786 +2023-05-26 14:37:58.521571: train_loss -0.9426 +2023-05-26 14:37:58.521889: val_loss -0.6632 +2023-05-26 14:37:58.522002: Pseudo dice [0.9349, 0.86, 0.9004] +2023-05-26 14:37:58.522090: Epoch time: 32.68 s +2023-05-26 14:38:00.044981: +2023-05-26 14:38:00.045575: Epoch 236 +2023-05-26 14:38:00.046157: Current learning rate: 0.00785 +2023-05-26 14:38:32.825919: train_loss -0.9439 +2023-05-26 14:38:32.826213: val_loss -0.663 +2023-05-26 14:38:32.826313: Pseudo dice [0.9338, 0.8619, 0.9013] +2023-05-26 14:38:32.826405: Epoch time: 32.78 s +2023-05-26 14:38:34.367477: +2023-05-26 14:38:34.367838: Epoch 237 +2023-05-26 14:38:34.368037: Current learning rate: 0.00784 +2023-05-26 14:39:07.022588: train_loss -0.9437 +2023-05-26 14:39:07.022856: val_loss -0.665 +2023-05-26 14:39:07.022968: Pseudo dice [0.9342, 0.86, 0.9026] +2023-05-26 14:39:07.023060: Epoch time: 32.66 s +2023-05-26 14:39:08.465816: +2023-05-26 14:39:08.466027: Epoch 238 +2023-05-26 14:39:08.466148: Current learning rate: 0.00783 +2023-05-26 14:39:40.992146: train_loss -0.9435 +2023-05-26 14:39:40.992370: val_loss -0.6608 +2023-05-26 14:39:40.992470: Pseudo dice [0.934, 0.8608, 0.8976] +2023-05-26 14:39:40.992563: Epoch time: 32.53 s +2023-05-26 14:39:42.431118: +2023-05-26 14:39:42.431509: Epoch 239 +2023-05-26 14:39:42.431771: Current learning rate: 0.00782 +2023-05-26 14:40:14.994237: train_loss -0.9429 +2023-05-26 14:40:14.994615: val_loss -0.6697 +2023-05-26 14:40:14.994823: Pseudo dice [0.9324, 0.8585, 0.9016] +2023-05-26 14:40:14.994989: Epoch time: 32.56 s +2023-05-26 14:40:16.401036: +2023-05-26 14:40:16.401186: Epoch 240 +2023-05-26 14:40:16.401317: Current learning rate: 0.00781 +2023-05-26 14:40:49.124346: train_loss -0.9407 +2023-05-26 14:40:49.124675: val_loss -0.6748 +2023-05-26 14:40:49.124807: Pseudo dice [0.9358, 0.8606, 0.9059] +2023-05-26 14:40:49.124904: Epoch time: 32.72 s +2023-05-26 14:40:50.902694: +2023-05-26 14:40:50.903041: Epoch 241 +2023-05-26 14:40:50.903348: Current learning rate: 0.0078 +2023-05-26 14:41:23.907731: train_loss -0.9428 +2023-05-26 14:41:23.908006: val_loss -0.6613 +2023-05-26 14:41:23.908141: Pseudo dice [0.9339, 0.8584, 0.8959] +2023-05-26 14:41:23.908239: Epoch time: 33.01 s +2023-05-26 14:41:25.401245: +2023-05-26 14:41:25.401421: Epoch 242 +2023-05-26 14:41:25.401538: Current learning rate: 0.00779 +2023-05-26 14:41:58.143523: train_loss -0.9445 +2023-05-26 14:41:58.143761: val_loss -0.6685 +2023-05-26 14:41:58.143870: Pseudo dice [0.9348, 0.8612, 0.9039] +2023-05-26 14:41:58.143970: Epoch time: 32.74 s +2023-05-26 14:41:59.639512: +2023-05-26 14:41:59.639732: Epoch 243 +2023-05-26 14:41:59.639857: Current learning rate: 0.00778 +2023-05-26 14:42:32.211408: train_loss -0.9445 +2023-05-26 14:42:32.211772: val_loss -0.6646 +2023-05-26 14:42:32.211917: Pseudo dice [0.9356, 0.8625, 0.8971] +2023-05-26 14:42:32.212006: Epoch time: 32.57 s +2023-05-26 14:42:33.492181: +2023-05-26 14:42:33.492346: Epoch 244 +2023-05-26 14:42:33.492458: Current learning rate: 0.00777 +2023-05-26 14:43:06.172049: train_loss -0.9442 +2023-05-26 14:43:06.172276: val_loss -0.6629 +2023-05-26 14:43:06.172380: Pseudo dice [0.9345, 0.8605, 0.9008] +2023-05-26 14:43:06.172482: Epoch time: 32.68 s +2023-05-26 14:43:07.537688: +2023-05-26 14:43:07.537999: Epoch 245 +2023-05-26 14:43:07.538115: Current learning rate: 0.00777 +2023-05-26 14:43:40.322220: train_loss -0.9437 +2023-05-26 14:43:40.322450: val_loss -0.6654 +2023-05-26 14:43:40.322572: Pseudo dice [0.9346, 0.8601, 0.9011] +2023-05-26 14:43:40.322675: Epoch time: 32.79 s +2023-05-26 14:43:41.641022: +2023-05-26 14:43:41.641165: Epoch 246 +2023-05-26 14:43:41.641260: Current learning rate: 0.00776 +2023-05-26 14:44:14.930478: train_loss -0.9435 +2023-05-26 14:44:14.930758: val_loss -0.6768 +2023-05-26 14:44:14.930884: Pseudo dice [0.9336, 0.8628, 0.9001] +2023-05-26 14:44:14.930964: Epoch time: 33.29 s +2023-05-26 14:44:16.394190: +2023-05-26 14:44:16.394750: Epoch 247 +2023-05-26 14:44:16.395015: Current learning rate: 0.00775 +2023-05-26 14:44:49.648571: train_loss -0.9437 +2023-05-26 14:44:49.648882: val_loss -0.666 +2023-05-26 14:44:49.649029: Pseudo dice [0.9349, 0.8606, 0.9049] +2023-05-26 14:44:49.649119: Epoch time: 33.26 s +2023-05-26 14:44:51.056509: +2023-05-26 14:44:51.056674: Epoch 248 +2023-05-26 14:44:51.056779: Current learning rate: 0.00774 +2023-05-26 14:45:23.699231: train_loss -0.9448 +2023-05-26 14:45:23.699455: val_loss -0.6605 +2023-05-26 14:45:23.699577: Pseudo dice [0.9348, 0.8588, 0.9031] +2023-05-26 14:45:23.699679: Epoch time: 32.64 s +2023-05-26 14:45:24.970137: +2023-05-26 14:45:24.970698: Epoch 249 +2023-05-26 14:45:24.971125: Current learning rate: 0.00773 +2023-05-26 14:45:57.683396: train_loss -0.9437 +2023-05-26 14:45:57.683892: val_loss -0.6655 +2023-05-26 14:45:57.683999: Pseudo dice [0.9355, 0.8613, 0.9019] +2023-05-26 14:45:57.684084: Epoch time: 32.71 s +2023-05-26 14:46:01.100726: +2023-05-26 14:46:01.101092: Epoch 250 +2023-05-26 14:46:01.101277: Current learning rate: 0.00772 +2023-05-26 14:46:34.092225: train_loss -0.9453 +2023-05-26 14:46:34.092507: val_loss -0.6657 +2023-05-26 14:46:34.092654: Pseudo dice [0.9359, 0.8615, 0.9034] +2023-05-26 14:46:34.092754: Epoch time: 32.99 s +2023-05-26 14:46:35.586831: +2023-05-26 14:46:35.587076: Epoch 251 +2023-05-26 14:46:35.587190: Current learning rate: 0.00771 +2023-05-26 14:47:08.340547: train_loss -0.9448 +2023-05-26 14:47:08.340780: val_loss -0.6703 +2023-05-26 14:47:08.340897: Pseudo dice [0.9345, 0.862, 0.901] +2023-05-26 14:47:08.341001: Epoch time: 32.75 s +2023-05-26 14:47:09.777636: +2023-05-26 14:47:09.777792: Epoch 252 +2023-05-26 14:47:09.777893: Current learning rate: 0.0077 +2023-05-26 14:47:42.459170: train_loss -0.9449 +2023-05-26 14:47:42.459414: val_loss -0.6601 +2023-05-26 14:47:42.459550: Pseudo dice [0.9337, 0.8587, 0.8997] +2023-05-26 14:47:42.459651: Epoch time: 32.68 s +2023-05-26 14:47:43.900352: +2023-05-26 14:47:43.900605: Epoch 253 +2023-05-26 14:47:43.900815: Current learning rate: 0.00769 +2023-05-26 14:48:16.537927: train_loss -0.9455 +2023-05-26 14:48:16.538204: val_loss -0.6549 +2023-05-26 14:48:16.538339: Pseudo dice [0.9342, 0.8592, 0.8991] +2023-05-26 14:48:16.538430: Epoch time: 32.64 s +2023-05-26 14:48:18.320315: +2023-05-26 14:48:18.320482: Epoch 254 +2023-05-26 14:48:18.320596: Current learning rate: 0.00768 +2023-05-26 14:48:50.996747: train_loss -0.9455 +2023-05-26 14:48:50.996977: val_loss -0.6574 +2023-05-26 14:48:50.997093: Pseudo dice [0.9348, 0.8598, 0.8992] +2023-05-26 14:48:50.997187: Epoch time: 32.68 s +2023-05-26 14:48:52.401498: +2023-05-26 14:48:52.401891: Epoch 255 +2023-05-26 14:48:52.402231: Current learning rate: 0.00767 +2023-05-26 14:49:25.017479: train_loss -0.9458 +2023-05-26 14:49:25.017739: val_loss -0.6646 +2023-05-26 14:49:25.017845: Pseudo dice [0.935, 0.8611, 0.9008] +2023-05-26 14:49:25.017942: Epoch time: 32.62 s +2023-05-26 14:49:26.440074: +2023-05-26 14:49:26.440257: Epoch 256 +2023-05-26 14:49:26.440387: Current learning rate: 0.00766 +2023-05-26 14:49:59.047643: train_loss -0.9451 +2023-05-26 14:49:59.047899: val_loss -0.6623 +2023-05-26 14:49:59.048037: Pseudo dice [0.9349, 0.8608, 0.9005] +2023-05-26 14:49:59.048133: Epoch time: 32.61 s +2023-05-26 14:50:00.586594: +2023-05-26 14:50:00.586890: Epoch 257 +2023-05-26 14:50:00.587122: Current learning rate: 0.00765 +2023-05-26 14:50:33.308153: train_loss -0.9456 +2023-05-26 14:50:33.308394: val_loss -0.6644 +2023-05-26 14:50:33.308516: Pseudo dice [0.9359, 0.8633, 0.9022] +2023-05-26 14:50:33.308618: Epoch time: 32.72 s +2023-05-26 14:50:34.789967: +2023-05-26 14:50:34.790112: Epoch 258 +2023-05-26 14:50:34.790233: Current learning rate: 0.00764 +2023-05-26 14:51:07.695750: train_loss -0.9455 +2023-05-26 14:51:07.695974: val_loss -0.6577 +2023-05-26 14:51:07.696089: Pseudo dice [0.9337, 0.8588, 0.9033] +2023-05-26 14:51:07.696193: Epoch time: 32.91 s +2023-05-26 14:51:09.090612: +2023-05-26 14:51:09.090768: Epoch 259 +2023-05-26 14:51:09.090901: Current learning rate: 0.00764 +2023-05-26 14:51:41.746640: train_loss -0.945 +2023-05-26 14:51:41.746878: val_loss -0.6595 +2023-05-26 14:51:41.746997: Pseudo dice [0.9344, 0.8593, 0.9003] +2023-05-26 14:51:41.747099: Epoch time: 32.66 s +2023-05-26 14:51:43.108779: +2023-05-26 14:51:43.109497: Epoch 260 +2023-05-26 14:51:43.109853: Current learning rate: 0.00763 +2023-05-26 14:52:16.100496: train_loss -0.9448 +2023-05-26 14:52:16.100753: val_loss -0.6758 +2023-05-26 14:52:16.100871: Pseudo dice [0.9361, 0.8617, 0.9031] +2023-05-26 14:52:16.100952: Epoch time: 32.99 s +2023-05-26 14:52:17.566794: +2023-05-26 14:52:17.567271: Epoch 261 +2023-05-26 14:52:17.567480: Current learning rate: 0.00762 +2023-05-26 14:52:51.315218: train_loss -0.9448 +2023-05-26 14:52:51.315454: val_loss -0.6685 +2023-05-26 14:52:51.315563: Pseudo dice [0.9345, 0.8609, 0.9004] +2023-05-26 14:52:51.315658: Epoch time: 33.75 s +2023-05-26 14:52:52.889299: +2023-05-26 14:52:52.889481: Epoch 262 +2023-05-26 14:52:52.889596: Current learning rate: 0.00761 +2023-05-26 14:53:25.436105: train_loss -0.9433 +2023-05-26 14:53:25.436351: val_loss -0.6713 +2023-05-26 14:53:25.436466: Pseudo dice [0.9347, 0.8614, 0.9036] +2023-05-26 14:53:25.436572: Epoch time: 32.55 s +2023-05-26 14:53:26.855259: +2023-05-26 14:53:26.855413: Epoch 263 +2023-05-26 14:53:26.855579: Current learning rate: 0.0076 +2023-05-26 14:53:59.582913: train_loss -0.9443 +2023-05-26 14:53:59.583148: val_loss -0.6661 +2023-05-26 14:53:59.583271: Pseudo dice [0.9351, 0.8613, 0.9048] +2023-05-26 14:53:59.583380: Epoch time: 32.73 s +2023-05-26 14:54:00.928456: +2023-05-26 14:54:00.928652: Epoch 264 +2023-05-26 14:54:00.928780: Current learning rate: 0.00759 +2023-05-26 14:54:33.533775: train_loss -0.9451 +2023-05-26 14:54:33.534038: val_loss -0.6583 +2023-05-26 14:54:33.534165: Pseudo dice [0.9351, 0.8612, 0.8996] +2023-05-26 14:54:33.534269: Epoch time: 32.61 s +2023-05-26 14:54:34.972633: +2023-05-26 14:54:34.972784: Epoch 265 +2023-05-26 14:54:34.972894: Current learning rate: 0.00758 +2023-05-26 14:55:07.564355: train_loss -0.9464 +2023-05-26 14:55:07.564573: val_loss -0.6582 +2023-05-26 14:55:07.564683: Pseudo dice [0.9335, 0.8599, 0.9006] +2023-05-26 14:55:07.564784: Epoch time: 32.59 s +2023-05-26 14:55:08.930127: +2023-05-26 14:55:08.930374: Epoch 266 +2023-05-26 14:55:08.930556: Current learning rate: 0.00757 +2023-05-26 14:55:41.755775: train_loss -0.9435 +2023-05-26 14:55:41.756115: val_loss -0.6735 +2023-05-26 14:55:41.756243: Pseudo dice [0.9363, 0.8629, 0.9039] +2023-05-26 14:55:41.756329: Epoch time: 32.83 s +2023-05-26 14:55:43.574537: +2023-05-26 14:55:43.574795: Epoch 267 +2023-05-26 14:55:43.574942: Current learning rate: 0.00756 +2023-05-26 14:56:16.914783: train_loss -0.9453 +2023-05-26 14:56:16.915034: val_loss -0.6698 +2023-05-26 14:56:16.915154: Pseudo dice [0.9372, 0.8625, 0.9034] +2023-05-26 14:56:16.915253: Epoch time: 33.34 s +2023-05-26 14:56:16.915322: Yayy! New best EMA pseudo Dice: 0.8994 +2023-05-26 14:56:20.370885: +2023-05-26 14:56:20.371029: Epoch 268 +2023-05-26 14:56:20.371137: Current learning rate: 0.00755 +2023-05-26 14:56:53.057485: train_loss -0.9452 +2023-05-26 14:56:53.057890: val_loss -0.6619 +2023-05-26 14:56:53.058042: Pseudo dice [0.9323, 0.8597, 0.9029] +2023-05-26 14:56:53.058275: Epoch time: 32.69 s +2023-05-26 14:56:54.478751: +2023-05-26 14:56:54.479068: Epoch 269 +2023-05-26 14:56:54.479260: Current learning rate: 0.00754 +2023-05-26 14:57:27.130908: train_loss -0.9465 +2023-05-26 14:57:27.131543: val_loss -0.6676 +2023-05-26 14:57:27.131932: Pseudo dice [0.9351, 0.8609, 0.9054] +2023-05-26 14:57:27.132101: Epoch time: 32.65 s +2023-05-26 14:57:27.132236: Yayy! New best EMA pseudo Dice: 0.8994 +2023-05-26 14:57:30.008903: +2023-05-26 14:57:30.009262: Epoch 270 +2023-05-26 14:57:30.009387: Current learning rate: 0.00753 +2023-05-26 14:58:02.683866: train_loss -0.946 +2023-05-26 14:58:02.684098: val_loss -0.6602 +2023-05-26 14:58:02.684217: Pseudo dice [0.9354, 0.8609, 0.9053] +2023-05-26 14:58:02.684321: Epoch time: 32.68 s +2023-05-26 14:58:02.684390: Yayy! New best EMA pseudo Dice: 0.8995 +2023-05-26 14:58:05.702481: +2023-05-26 14:58:05.702649: Epoch 271 +2023-05-26 14:58:05.702753: Current learning rate: 0.00752 +2023-05-26 14:58:38.474602: train_loss -0.9456 +2023-05-26 14:58:38.474814: val_loss -0.6654 +2023-05-26 14:58:38.474932: Pseudo dice [0.935, 0.8621, 0.9062] +2023-05-26 14:58:38.475054: Epoch time: 32.77 s +2023-05-26 14:58:38.475127: Yayy! New best EMA pseudo Dice: 0.8997 +2023-05-26 14:58:41.207232: +2023-05-26 14:58:41.207428: Epoch 272 +2023-05-26 14:58:41.207526: Current learning rate: 0.00751 +2023-05-26 14:59:14.364216: train_loss -0.9466 +2023-05-26 14:59:14.364475: val_loss -0.6644 +2023-05-26 14:59:14.364588: Pseudo dice [0.9356, 0.8614, 0.9028] +2023-05-26 14:59:14.364694: Epoch time: 33.16 s +2023-05-26 14:59:14.364755: Yayy! New best EMA pseudo Dice: 0.8997 +2023-05-26 14:59:17.143380: +2023-05-26 14:59:17.144063: Epoch 273 +2023-05-26 14:59:17.144288: Current learning rate: 0.00751 +2023-05-26 14:59:49.774949: train_loss -0.9455 +2023-05-26 14:59:49.775161: val_loss -0.6551 +2023-05-26 14:59:49.775260: Pseudo dice [0.9343, 0.8601, 0.8993] +2023-05-26 14:59:49.775352: Epoch time: 32.63 s +2023-05-26 14:59:51.404250: +2023-05-26 14:59:51.404432: Epoch 274 +2023-05-26 14:59:51.404559: Current learning rate: 0.0075 +2023-05-26 15:00:24.483366: train_loss -0.9458 +2023-05-26 15:00:24.483619: val_loss -0.6571 +2023-05-26 15:00:24.483748: Pseudo dice [0.9337, 0.8602, 0.9007] +2023-05-26 15:00:24.483858: Epoch time: 33.08 s +2023-05-26 15:00:25.990070: +2023-05-26 15:00:25.990372: Epoch 275 +2023-05-26 15:00:25.990520: Current learning rate: 0.00749 +2023-05-26 15:00:58.750656: train_loss -0.9455 +2023-05-26 15:00:58.750929: val_loss -0.6621 +2023-05-26 15:00:58.751045: Pseudo dice [0.9349, 0.8612, 0.8982] +2023-05-26 15:00:58.751151: Epoch time: 32.76 s +2023-05-26 15:01:00.151535: +2023-05-26 15:01:00.151860: Epoch 276 +2023-05-26 15:01:00.152067: Current learning rate: 0.00748 +2023-05-26 15:01:32.739553: train_loss -0.9444 +2023-05-26 15:01:32.739820: val_loss -0.6594 +2023-05-26 15:01:32.739925: Pseudo dice [0.9352, 0.861, 0.895] +2023-05-26 15:01:32.740046: Epoch time: 32.59 s +2023-05-26 15:01:34.118148: +2023-05-26 15:01:34.118380: Epoch 277 +2023-05-26 15:01:34.118630: Current learning rate: 0.00747 +2023-05-26 15:02:06.849740: train_loss -0.9454 +2023-05-26 15:02:06.849999: val_loss -0.6612 +2023-05-26 15:02:06.850117: Pseudo dice [0.9357, 0.8618, 0.9019] +2023-05-26 15:02:06.850276: Epoch time: 32.73 s +2023-05-26 15:02:08.193914: +2023-05-26 15:02:08.194100: Epoch 278 +2023-05-26 15:02:08.194222: Current learning rate: 0.00746 +2023-05-26 15:02:40.902730: train_loss -0.9459 +2023-05-26 15:02:40.903034: val_loss -0.6597 +2023-05-26 15:02:40.903149: Pseudo dice [0.9361, 0.8613, 0.9022] +2023-05-26 15:02:40.903223: Epoch time: 32.71 s +2023-05-26 15:02:42.305526: +2023-05-26 15:02:42.305855: Epoch 279 +2023-05-26 15:02:42.305964: Current learning rate: 0.00745 +2023-05-26 15:03:14.952561: train_loss -0.9461 +2023-05-26 15:03:14.952755: val_loss -0.6604 +2023-05-26 15:03:14.952870: Pseudo dice [0.9355, 0.8628, 0.9009] +2023-05-26 15:03:14.952958: Epoch time: 32.65 s +2023-05-26 15:03:16.372059: +2023-05-26 15:03:16.372219: Epoch 280 +2023-05-26 15:03:16.372335: Current learning rate: 0.00744 +2023-05-26 15:03:49.143064: train_loss -0.9475 +2023-05-26 15:03:49.143267: val_loss -0.647 +2023-05-26 15:03:49.143380: Pseudo dice [0.9321, 0.8568, 0.9013] +2023-05-26 15:03:49.143466: Epoch time: 32.77 s +2023-05-26 15:03:50.421951: +2023-05-26 15:03:50.422115: Epoch 281 +2023-05-26 15:03:50.422218: Current learning rate: 0.00743 +2023-05-26 15:04:23.136492: train_loss -0.9464 +2023-05-26 15:04:23.136756: val_loss -0.6682 +2023-05-26 15:04:23.136872: Pseudo dice [0.9363, 0.8632, 0.9049] +2023-05-26 15:04:23.136968: Epoch time: 32.72 s +2023-05-26 15:04:24.575191: +2023-05-26 15:04:24.575356: Epoch 282 +2023-05-26 15:04:24.575582: Current learning rate: 0.00742 +2023-05-26 15:04:57.801600: train_loss -0.9463 +2023-05-26 15:04:57.801850: val_loss -0.6607 +2023-05-26 15:04:57.801965: Pseudo dice [0.9349, 0.8611, 0.9027] +2023-05-26 15:04:57.802075: Epoch time: 33.23 s +2023-05-26 15:04:59.225240: +2023-05-26 15:04:59.225718: Epoch 283 +2023-05-26 15:04:59.225849: Current learning rate: 0.00741 +2023-05-26 15:05:31.831621: train_loss -0.9462 +2023-05-26 15:05:31.831831: val_loss -0.6593 +2023-05-26 15:05:31.831998: Pseudo dice [0.9339, 0.8607, 0.9035] +2023-05-26 15:05:31.832096: Epoch time: 32.61 s +2023-05-26 15:05:33.106663: +2023-05-26 15:05:33.107033: Epoch 284 +2023-05-26 15:05:33.107181: Current learning rate: 0.0074 +2023-05-26 15:06:05.755671: train_loss -0.9473 +2023-05-26 15:06:05.755886: val_loss -0.6633 +2023-05-26 15:06:05.755994: Pseudo dice [0.9348, 0.8604, 0.9017] +2023-05-26 15:06:05.756085: Epoch time: 32.65 s +2023-05-26 15:06:06.986696: +2023-05-26 15:06:06.986831: Epoch 285 +2023-05-26 15:06:06.986948: Current learning rate: 0.00739 +2023-05-26 15:06:39.640772: train_loss -0.9468 +2023-05-26 15:06:39.641045: val_loss -0.6636 +2023-05-26 15:06:39.641150: Pseudo dice [0.933, 0.86, 0.9008] +2023-05-26 15:06:39.641250: Epoch time: 32.66 s +2023-05-26 15:06:40.908614: +2023-05-26 15:06:40.908779: Epoch 286 +2023-05-26 15:06:40.908896: Current learning rate: 0.00738 +2023-05-26 15:07:13.492748: train_loss -0.9471 +2023-05-26 15:07:13.492955: val_loss -0.6648 +2023-05-26 15:07:13.493049: Pseudo dice [0.9335, 0.8593, 0.9059] +2023-05-26 15:07:13.493141: Epoch time: 32.59 s +2023-05-26 15:07:14.992558: +2023-05-26 15:07:14.992809: Epoch 287 +2023-05-26 15:07:14.993094: Current learning rate: 0.00738 +2023-05-26 15:07:47.588450: train_loss -0.9448 +2023-05-26 15:07:47.589054: val_loss -0.6678 +2023-05-26 15:07:47.589274: Pseudo dice [0.9359, 0.863, 0.9023] +2023-05-26 15:07:47.589507: Epoch time: 32.6 s +2023-05-26 15:07:48.916668: +2023-05-26 15:07:48.916982: Epoch 288 +2023-05-26 15:07:48.917135: Current learning rate: 0.00737 +2023-05-26 15:08:21.620819: train_loss -0.9453 +2023-05-26 15:08:21.621054: val_loss -0.6713 +2023-05-26 15:08:21.621168: Pseudo dice [0.9357, 0.8619, 0.9039] +2023-05-26 15:08:21.621265: Epoch time: 32.71 s +2023-05-26 15:08:22.997375: +2023-05-26 15:08:22.997967: Epoch 289 +2023-05-26 15:08:22.998101: Current learning rate: 0.00736 +2023-05-26 15:08:55.818805: train_loss -0.9466 +2023-05-26 15:08:55.819096: val_loss -0.6658 +2023-05-26 15:08:55.819219: Pseudo dice [0.9365, 0.8611, 0.9031] +2023-05-26 15:08:55.819305: Epoch time: 32.82 s +2023-05-26 15:08:57.225011: +2023-05-26 15:08:57.225186: Epoch 290 +2023-05-26 15:08:57.225349: Current learning rate: 0.00735 +2023-05-26 15:09:29.858855: train_loss -0.9461 +2023-05-26 15:09:29.859083: val_loss -0.6625 +2023-05-26 15:09:29.859196: Pseudo dice [0.9338, 0.8581, 0.9034] +2023-05-26 15:09:29.859299: Epoch time: 32.63 s +2023-05-26 15:09:31.371764: +2023-05-26 15:09:31.371920: Epoch 291 +2023-05-26 15:09:31.372018: Current learning rate: 0.00734 +2023-05-26 15:10:04.131764: train_loss -0.9404 +2023-05-26 15:10:04.132293: val_loss -0.6809 +2023-05-26 15:10:04.132540: Pseudo dice [0.934, 0.8621, 0.8993] +2023-05-26 15:10:04.132766: Epoch time: 32.76 s +2023-05-26 15:10:05.732244: +2023-05-26 15:10:05.732390: Epoch 292 +2023-05-26 15:10:05.732493: Current learning rate: 0.00733 +2023-05-26 15:10:38.638268: train_loss -0.9409 +2023-05-26 15:10:38.638511: val_loss -0.6858 +2023-05-26 15:10:38.638627: Pseudo dice [0.9351, 0.8601, 0.904] +2023-05-26 15:10:38.638740: Epoch time: 32.91 s +2023-05-26 15:10:40.045849: +2023-05-26 15:10:40.046230: Epoch 293 +2023-05-26 15:10:40.046544: Current learning rate: 0.00732 +2023-05-26 15:11:13.136539: train_loss -0.9392 +2023-05-26 15:11:13.136818: val_loss -0.6803 +2023-05-26 15:11:13.136948: Pseudo dice [0.9365, 0.8628, 0.9016] +2023-05-26 15:11:13.137034: Epoch time: 33.09 s +2023-05-26 15:11:14.618358: +2023-05-26 15:11:14.618528: Epoch 294 +2023-05-26 15:11:14.618631: Current learning rate: 0.00731 +2023-05-26 15:11:47.510675: train_loss -0.9428 +2023-05-26 15:11:47.510923: val_loss -0.6583 +2023-05-26 15:11:47.511039: Pseudo dice [0.9336, 0.8584, 0.899] +2023-05-26 15:11:47.511144: Epoch time: 32.89 s +2023-05-26 15:11:48.876513: +2023-05-26 15:11:48.877151: Epoch 295 +2023-05-26 15:11:48.877293: Current learning rate: 0.0073 +2023-05-26 15:12:29.911326: train_loss -0.9455 +2023-05-26 15:12:29.911703: val_loss -0.6607 +2023-05-26 15:12:29.911911: Pseudo dice [0.9346, 0.8593, 0.9004] +2023-05-26 15:12:29.912081: Epoch time: 41.04 s +2023-05-26 15:12:31.542821: +2023-05-26 15:12:31.543060: Epoch 296 +2023-05-26 15:12:31.543199: Current learning rate: 0.00729 +2023-05-26 15:13:08.355731: train_loss -0.9465 +2023-05-26 15:13:08.355965: val_loss -0.6581 +2023-05-26 15:13:08.356080: Pseudo dice [0.9341, 0.8604, 0.9005] +2023-05-26 15:13:08.356183: Epoch time: 36.81 s +2023-05-26 15:13:09.923337: +2023-05-26 15:13:09.923552: Epoch 297 +2023-05-26 15:13:09.923686: Current learning rate: 0.00728 +2023-05-26 15:13:47.218600: train_loss -0.9469 +2023-05-26 15:13:47.218878: val_loss -0.6652 +2023-05-26 15:13:47.219028: Pseudo dice [0.9348, 0.8623, 0.9028] +2023-05-26 15:13:47.219124: Epoch time: 37.3 s +2023-05-26 15:13:48.889439: +2023-05-26 15:13:48.889618: Epoch 298 +2023-05-26 15:13:48.889740: Current learning rate: 0.00727 +2023-05-26 15:14:26.655579: train_loss -0.9468 +2023-05-26 15:14:26.655854: val_loss -0.663 +2023-05-26 15:14:26.655970: Pseudo dice [0.9342, 0.8605, 0.9026] +2023-05-26 15:14:26.656063: Epoch time: 37.77 s +2023-05-26 15:14:28.285980: +2023-05-26 15:14:28.286425: Epoch 299 +2023-05-26 15:14:28.286557: Current learning rate: 0.00726 +2023-05-26 15:15:05.792717: train_loss -0.9471 +2023-05-26 15:15:05.792983: val_loss -0.6633 +2023-05-26 15:15:05.793102: Pseudo dice [0.9351, 0.8609, 0.9028] +2023-05-26 15:15:05.793188: Epoch time: 37.51 s +2023-05-26 15:15:09.213078: +2023-05-26 15:15:09.213281: Epoch 300 +2023-05-26 15:15:09.213414: Current learning rate: 0.00725 +2023-05-26 15:15:46.994185: train_loss -0.9486 +2023-05-26 15:15:46.994429: val_loss -0.6556 +2023-05-26 15:15:46.994539: Pseudo dice [0.9357, 0.8621, 0.897] +2023-05-26 15:15:46.994622: Epoch time: 37.78 s +2023-05-26 15:15:48.746872: +2023-05-26 15:15:48.747340: Epoch 301 +2023-05-26 15:15:48.747483: Current learning rate: 0.00724 +2023-05-26 15:16:26.197574: train_loss -0.9488 +2023-05-26 15:16:26.197831: val_loss -0.6556 +2023-05-26 15:16:26.197959: Pseudo dice [0.9336, 0.8611, 0.9018] +2023-05-26 15:16:26.198119: Epoch time: 37.45 s +2023-05-26 15:16:27.864877: +2023-05-26 15:16:27.865522: Epoch 302 +2023-05-26 15:16:27.865701: Current learning rate: 0.00724 +2023-05-26 15:17:05.538079: train_loss -0.9489 +2023-05-26 15:17:05.538331: val_loss -0.6632 +2023-05-26 15:17:05.538455: Pseudo dice [0.9356, 0.8632, 0.9002] +2023-05-26 15:17:05.538568: Epoch time: 37.67 s +2023-05-26 15:17:07.093870: +2023-05-26 15:17:07.094087: Epoch 303 +2023-05-26 15:17:07.094211: Current learning rate: 0.00723 +2023-05-26 15:17:44.537169: train_loss -0.9493 +2023-05-26 15:17:44.537467: val_loss -0.6568 +2023-05-26 15:17:44.537588: Pseudo dice [0.9378, 0.8625, 0.8991] +2023-05-26 15:17:44.537677: Epoch time: 37.44 s +2023-05-26 15:17:46.217161: +2023-05-26 15:17:46.217601: Epoch 304 +2023-05-26 15:17:46.217798: Current learning rate: 0.00722 +2023-05-26 15:18:22.945325: train_loss -0.9487 +2023-05-26 15:18:22.945668: val_loss -0.6503 +2023-05-26 15:18:22.945805: Pseudo dice [0.9334, 0.8613, 0.8979] +2023-05-26 15:18:22.945892: Epoch time: 36.73 s +2023-05-26 15:18:24.598260: +2023-05-26 15:18:24.598562: Epoch 305 +2023-05-26 15:18:24.598798: Current learning rate: 0.00721 +2023-05-26 15:19:02.329811: train_loss -0.949 +2023-05-26 15:19:02.330071: val_loss -0.6498 +2023-05-26 15:19:02.330208: Pseudo dice [0.9342, 0.8601, 0.9001] +2023-05-26 15:19:02.330318: Epoch time: 37.73 s +2023-05-26 15:19:04.184807: +2023-05-26 15:19:04.185598: Epoch 306 +2023-05-26 15:19:04.186208: Current learning rate: 0.0072 +2023-05-26 15:19:41.948997: train_loss -0.9488 +2023-05-26 15:19:41.949271: val_loss -0.6502 +2023-05-26 15:19:41.949398: Pseudo dice [0.9327, 0.8604, 0.9004] +2023-05-26 15:19:41.949512: Epoch time: 37.77 s +2023-05-26 15:19:43.659546: +2023-05-26 15:19:43.659848: Epoch 307 +2023-05-26 15:19:43.660066: Current learning rate: 0.00719 +2023-05-26 15:20:21.237025: train_loss -0.9487 +2023-05-26 15:20:21.237284: val_loss -0.6559 +2023-05-26 15:20:21.237406: Pseudo dice [0.9345, 0.8609, 0.8997] +2023-05-26 15:20:21.237515: Epoch time: 37.58 s +2023-05-26 15:20:22.737134: +2023-05-26 15:20:22.737421: Epoch 308 +2023-05-26 15:20:22.737626: Current learning rate: 0.00718 +2023-05-26 15:21:00.244288: train_loss -0.9499 +2023-05-26 15:21:00.244520: val_loss -0.6472 +2023-05-26 15:21:00.244649: Pseudo dice [0.9341, 0.8592, 0.899] +2023-05-26 15:21:00.244752: Epoch time: 37.51 s +2023-05-26 15:21:01.748564: +2023-05-26 15:21:01.748744: Epoch 309 +2023-05-26 15:21:01.748857: Current learning rate: 0.00717 +2023-05-26 15:21:39.411361: train_loss -0.9496 +2023-05-26 15:21:39.411615: val_loss -0.6525 +2023-05-26 15:21:39.411733: Pseudo dice [0.9341, 0.86, 0.9017] +2023-05-26 15:21:39.411832: Epoch time: 37.66 s +2023-05-26 15:21:40.864857: +2023-05-26 15:21:40.865025: Epoch 310 +2023-05-26 15:21:40.865142: Current learning rate: 0.00716 +2023-05-26 15:22:18.528349: train_loss -0.9486 +2023-05-26 15:22:18.528623: val_loss -0.6593 +2023-05-26 15:22:18.528831: Pseudo dice [0.9346, 0.8606, 0.902] +2023-05-26 15:22:18.528951: Epoch time: 37.66 s +2023-05-26 15:22:19.995013: +2023-05-26 15:22:19.995178: Epoch 311 +2023-05-26 15:22:19.995295: Current learning rate: 0.00715 +2023-05-26 15:22:57.541539: train_loss -0.9489 +2023-05-26 15:22:57.541830: val_loss -0.6498 +2023-05-26 15:22:57.541955: Pseudo dice [0.9345, 0.8598, 0.9012] +2023-05-26 15:22:57.542044: Epoch time: 37.55 s +2023-05-26 15:22:59.129387: +2023-05-26 15:22:59.129603: Epoch 312 +2023-05-26 15:22:59.129741: Current learning rate: 0.00714 +2023-05-26 15:23:37.032143: train_loss -0.9496 +2023-05-26 15:23:37.032565: val_loss -0.6526 +2023-05-26 15:23:37.032791: Pseudo dice [0.9352, 0.8605, 0.903] +2023-05-26 15:23:37.032977: Epoch time: 37.9 s +2023-05-26 15:23:39.007156: +2023-05-26 15:23:39.007388: Epoch 313 +2023-05-26 15:23:39.007537: Current learning rate: 0.00713 +2023-05-26 15:24:16.961587: train_loss -0.9491 +2023-05-26 15:24:16.961853: val_loss -0.6583 +2023-05-26 15:24:16.961968: Pseudo dice [0.9352, 0.8615, 0.9019] +2023-05-26 15:24:16.962069: Epoch time: 37.96 s +2023-05-26 15:24:18.557920: +2023-05-26 15:24:18.558228: Epoch 314 +2023-05-26 15:24:18.558551: Current learning rate: 0.00712 +2023-05-26 15:24:56.306731: train_loss -0.9497 +2023-05-26 15:24:56.307027: val_loss -0.6531 +2023-05-26 15:24:56.307146: Pseudo dice [0.9348, 0.8607, 0.9033] +2023-05-26 15:24:56.307724: Epoch time: 37.75 s +2023-05-26 15:24:57.997909: +2023-05-26 15:24:57.998092: Epoch 315 +2023-05-26 15:24:57.998205: Current learning rate: 0.00711 +2023-05-26 15:25:35.879555: train_loss -0.9494 +2023-05-26 15:25:35.880018: val_loss -0.662 +2023-05-26 15:25:35.880133: Pseudo dice [0.9359, 0.8607, 0.9043] +2023-05-26 15:25:35.880220: Epoch time: 37.88 s +2023-05-26 15:25:37.538171: +2023-05-26 15:25:37.538795: Epoch 316 +2023-05-26 15:25:37.539071: Current learning rate: 0.0071 +2023-05-26 15:26:15.392155: train_loss -0.9504 +2023-05-26 15:26:15.392380: val_loss -0.6546 +2023-05-26 15:26:15.392491: Pseudo dice [0.9355, 0.8613, 0.9024] +2023-05-26 15:26:15.392591: Epoch time: 37.86 s +2023-05-26 15:26:16.939077: +2023-05-26 15:26:16.939713: Epoch 317 +2023-05-26 15:26:16.940165: Current learning rate: 0.0071 +2023-05-26 15:26:54.549284: train_loss -0.9496 +2023-05-26 15:26:54.549553: val_loss -0.6509 +2023-05-26 15:26:54.549682: Pseudo dice [0.9359, 0.8601, 0.903] +2023-05-26 15:26:54.549779: Epoch time: 37.61 s +2023-05-26 15:26:56.414820: +2023-05-26 15:26:56.415135: Epoch 318 +2023-05-26 15:26:56.415365: Current learning rate: 0.00709 +2023-05-26 15:27:34.552560: train_loss -0.9504 +2023-05-26 15:27:34.552792: val_loss -0.6584 +2023-05-26 15:27:34.552911: Pseudo dice [0.9363, 0.8605, 0.9044] +2023-05-26 15:27:34.553016: Epoch time: 38.14 s +2023-05-26 15:27:36.458139: +2023-05-26 15:27:36.458719: Epoch 319 +2023-05-26 15:27:36.459179: Current learning rate: 0.00708 +2023-05-26 15:28:14.530802: train_loss -0.9497 +2023-05-26 15:28:14.531059: val_loss -0.6456 +2023-05-26 15:28:14.531180: Pseudo dice [0.9351, 0.8608, 0.8981] +2023-05-26 15:28:14.531278: Epoch time: 38.07 s +2023-05-26 15:28:16.099135: +2023-05-26 15:28:16.099403: Epoch 320 +2023-05-26 15:28:16.099626: Current learning rate: 0.00707 +2023-05-26 15:28:53.821087: train_loss -0.9493 +2023-05-26 15:28:53.821465: val_loss -0.6534 +2023-05-26 15:28:53.821627: Pseudo dice [0.9349, 0.8601, 0.9003] +2023-05-26 15:28:53.821740: Epoch time: 37.72 s +2023-05-26 15:28:55.479191: +2023-05-26 15:28:55.479387: Epoch 321 +2023-05-26 15:28:55.479504: Current learning rate: 0.00706 +2023-05-26 15:29:32.861707: train_loss -0.9501 +2023-05-26 15:29:32.861954: val_loss -0.6492 +2023-05-26 15:29:32.862077: Pseudo dice [0.9354, 0.8637, 0.8987] +2023-05-26 15:29:32.862181: Epoch time: 37.38 s +2023-05-26 15:29:34.301947: +2023-05-26 15:29:34.302609: Epoch 322 +2023-05-26 15:29:34.302883: Current learning rate: 0.00705 +2023-05-26 15:30:11.418209: train_loss -0.9495 +2023-05-26 15:30:11.418507: val_loss -0.6509 +2023-05-26 15:30:11.418683: Pseudo dice [0.9353, 0.86, 0.9012] +2023-05-26 15:30:11.418796: Epoch time: 37.12 s +2023-05-26 15:30:13.082086: +2023-05-26 15:30:13.082680: Epoch 323 +2023-05-26 15:30:13.082812: Current learning rate: 0.00704 +2023-05-26 15:30:50.572306: train_loss -0.9503 +2023-05-26 15:30:50.572722: val_loss -0.6555 +2023-05-26 15:30:50.572942: Pseudo dice [0.9343, 0.861, 0.9016] +2023-05-26 15:30:50.573111: Epoch time: 37.49 s +2023-05-26 15:30:52.173196: +2023-05-26 15:30:52.173387: Epoch 324 +2023-05-26 15:30:52.173529: Current learning rate: 0.00703 +2023-05-26 15:31:29.940567: train_loss -0.9505 +2023-05-26 15:31:29.940826: val_loss -0.6537 +2023-05-26 15:31:29.941022: Pseudo dice [0.9347, 0.8626, 0.9015] +2023-05-26 15:31:29.941129: Epoch time: 37.77 s +2023-05-26 15:31:31.776928: +2023-05-26 15:31:31.777423: Epoch 325 +2023-05-26 15:31:31.777777: Current learning rate: 0.00702 +2023-05-26 15:32:09.203553: train_loss -0.95 +2023-05-26 15:32:09.203803: val_loss -0.6526 +2023-05-26 15:32:09.203932: Pseudo dice [0.9336, 0.8609, 0.9037] +2023-05-26 15:32:09.204045: Epoch time: 37.43 s +2023-05-26 15:32:10.647643: +2023-05-26 15:32:10.647849: Epoch 326 +2023-05-26 15:32:10.647974: Current learning rate: 0.00701 +2023-05-26 15:32:48.217193: train_loss -0.9501 +2023-05-26 15:32:48.217480: val_loss -0.6536 +2023-05-26 15:32:48.217625: Pseudo dice [0.9351, 0.8623, 0.9011] +2023-05-26 15:32:48.217724: Epoch time: 37.57 s +2023-05-26 15:32:49.883022: +2023-05-26 15:32:49.883247: Epoch 327 +2023-05-26 15:32:49.883376: Current learning rate: 0.007 +2023-05-26 15:33:27.514605: train_loss -0.9507 +2023-05-26 15:33:27.514942: val_loss -0.6534 +2023-05-26 15:33:27.515083: Pseudo dice [0.9347, 0.8612, 0.9012] +2023-05-26 15:33:27.515174: Epoch time: 37.63 s +2023-05-26 15:33:29.072694: +2023-05-26 15:33:29.072886: Epoch 328 +2023-05-26 15:33:29.073003: Current learning rate: 0.00699 +2023-05-26 15:34:06.669766: train_loss -0.9506 +2023-05-26 15:34:06.670046: val_loss -0.6504 +2023-05-26 15:34:06.670188: Pseudo dice [0.9353, 0.861, 0.9018] +2023-05-26 15:34:06.670285: Epoch time: 37.6 s +2023-05-26 15:34:08.299028: +2023-05-26 15:34:08.299209: Epoch 329 +2023-05-26 15:34:08.299326: Current learning rate: 0.00698 +2023-05-26 15:34:45.817033: train_loss -0.9505 +2023-05-26 15:34:45.817287: val_loss -0.6578 +2023-05-26 15:34:45.817422: Pseudo dice [0.9361, 0.8622, 0.9004] +2023-05-26 15:34:45.817515: Epoch time: 37.52 s +2023-05-26 15:34:47.520314: +2023-05-26 15:34:47.520488: Epoch 330 +2023-05-26 15:34:47.520606: Current learning rate: 0.00697 +2023-05-26 15:35:24.829764: train_loss -0.9505 +2023-05-26 15:35:24.830053: val_loss -0.6593 +2023-05-26 15:35:24.830357: Pseudo dice [0.9359, 0.8621, 0.9034] +2023-05-26 15:35:24.830503: Epoch time: 37.31 s +2023-05-26 15:35:26.559724: +2023-05-26 15:35:26.560282: Epoch 331 +2023-05-26 15:35:26.560423: Current learning rate: 0.00696 +2023-05-26 15:36:04.379370: train_loss -0.9511 +2023-05-26 15:36:04.379705: val_loss -0.6612 +2023-05-26 15:36:04.379865: Pseudo dice [0.9356, 0.8634, 0.9039] +2023-05-26 15:36:04.380027: Epoch time: 37.82 s +2023-05-26 15:36:06.203164: +2023-05-26 15:36:06.203351: Epoch 332 +2023-05-26 15:36:06.203480: Current learning rate: 0.00696 +2023-05-26 15:36:43.902967: train_loss -0.9509 +2023-05-26 15:36:43.903238: val_loss -0.6454 +2023-05-26 15:36:43.903368: Pseudo dice [0.935, 0.8605, 0.896] +2023-05-26 15:36:43.903461: Epoch time: 37.7 s +2023-05-26 15:36:45.762242: +2023-05-26 15:36:45.762617: Epoch 333 +2023-05-26 15:36:45.762837: Current learning rate: 0.00695 +2023-05-26 15:37:23.367470: train_loss -0.9512 +2023-05-26 15:37:23.367731: val_loss -0.6474 +2023-05-26 15:37:23.367854: Pseudo dice [0.9354, 0.8601, 0.902] +2023-05-26 15:37:23.367937: Epoch time: 37.61 s +2023-05-26 15:37:24.973247: +2023-05-26 15:37:24.973578: Epoch 334 +2023-05-26 15:37:24.973815: Current learning rate: 0.00694 +2023-05-26 15:38:02.848467: train_loss -0.9506 +2023-05-26 15:38:02.848739: val_loss -0.6423 +2023-05-26 15:38:02.848851: Pseudo dice [0.9344, 0.8607, 0.8987] +2023-05-26 15:38:02.848951: Epoch time: 37.88 s +2023-05-26 15:38:04.517285: +2023-05-26 15:38:04.517483: Epoch 335 +2023-05-26 15:38:04.517608: Current learning rate: 0.00693 +2023-05-26 15:38:42.357851: train_loss -0.9503 +2023-05-26 15:38:42.358285: val_loss -0.6552 +2023-05-26 15:38:42.358566: Pseudo dice [0.9353, 0.861, 0.899] +2023-05-26 15:38:42.358670: Epoch time: 37.84 s +2023-05-26 15:38:44.044420: +2023-05-26 15:38:44.044585: Epoch 336 +2023-05-26 15:38:44.044701: Current learning rate: 0.00692 +2023-05-26 15:39:21.599277: train_loss -0.9505 +2023-05-26 15:39:21.599614: val_loss -0.6515 +2023-05-26 15:39:21.599761: Pseudo dice [0.9343, 0.8609, 0.8984] +2023-05-26 15:39:21.599868: Epoch time: 37.56 s +2023-05-26 15:39:23.179116: +2023-05-26 15:39:23.179439: Epoch 337 +2023-05-26 15:39:23.179708: Current learning rate: 0.00691 +2023-05-26 15:40:01.121264: train_loss -0.9508 +2023-05-26 15:40:01.121512: val_loss -0.6501 +2023-05-26 15:40:01.121638: Pseudo dice [0.9361, 0.8633, 0.8976] +2023-05-26 15:40:01.121742: Epoch time: 37.94 s +2023-05-26 15:40:03.036501: +2023-05-26 15:40:03.036883: Epoch 338 +2023-05-26 15:40:03.037150: Current learning rate: 0.0069 +2023-05-26 15:40:40.347552: train_loss -0.9517 +2023-05-26 15:40:40.348095: val_loss -0.651 +2023-05-26 15:40:40.348217: Pseudo dice [0.9357, 0.8617, 0.9016] +2023-05-26 15:40:40.348310: Epoch time: 37.31 s +2023-05-26 15:40:41.970268: +2023-05-26 15:40:41.970446: Epoch 339 +2023-05-26 15:40:41.970573: Current learning rate: 0.00689 +2023-05-26 15:41:20.181714: train_loss -0.9505 +2023-05-26 15:41:20.181983: val_loss -0.6532 +2023-05-26 15:41:20.182139: Pseudo dice [0.9355, 0.8612, 0.9008] +2023-05-26 15:41:20.182231: Epoch time: 38.21 s +2023-05-26 15:41:21.819269: +2023-05-26 15:41:21.819651: Epoch 340 +2023-05-26 15:41:21.819847: Current learning rate: 0.00688 +2023-05-26 15:41:59.410413: train_loss -0.951 +2023-05-26 15:41:59.410645: val_loss -0.6581 +2023-05-26 15:41:59.410754: Pseudo dice [0.9371, 0.8627, 0.9026] +2023-05-26 15:41:59.410868: Epoch time: 37.59 s +2023-05-26 15:42:01.016784: +2023-05-26 15:42:01.017299: Epoch 341 +2023-05-26 15:42:01.017555: Current learning rate: 0.00687 +2023-05-26 15:42:38.816557: train_loss -0.9522 +2023-05-26 15:42:38.816912: val_loss -0.6505 +2023-05-26 15:42:38.817058: Pseudo dice [0.9374, 0.8638, 0.9005] +2023-05-26 15:42:38.817178: Epoch time: 37.8 s +2023-05-26 15:42:40.482777: +2023-05-26 15:42:40.482971: Epoch 342 +2023-05-26 15:42:40.483093: Current learning rate: 0.00686 +2023-05-26 15:43:18.093385: train_loss -0.9519 +2023-05-26 15:43:18.093673: val_loss -0.6429 +2023-05-26 15:43:18.093803: Pseudo dice [0.935, 0.8593, 0.8993] +2023-05-26 15:43:18.093898: Epoch time: 37.61 s +2023-05-26 15:43:19.692633: +2023-05-26 15:43:19.692970: Epoch 343 +2023-05-26 15:43:19.693261: Current learning rate: 0.00685 +2023-05-26 15:43:57.410978: train_loss -0.9515 +2023-05-26 15:43:57.411273: val_loss -0.639 +2023-05-26 15:43:57.411413: Pseudo dice [0.9352, 0.8608, 0.8984] +2023-05-26 15:43:57.411508: Epoch time: 37.72 s +2023-05-26 15:43:59.344275: +2023-05-26 15:43:59.344675: Epoch 344 +2023-05-26 15:43:59.344878: Current learning rate: 0.00684 +2023-05-26 15:44:36.862322: train_loss -0.951 +2023-05-26 15:44:36.862597: val_loss -0.6569 +2023-05-26 15:44:36.862705: Pseudo dice [0.9356, 0.8618, 0.9017] +2023-05-26 15:44:36.862796: Epoch time: 37.52 s +2023-05-26 15:44:38.463784: +2023-05-26 15:44:38.464088: Epoch 345 +2023-05-26 15:44:38.464372: Current learning rate: 0.00683 +2023-05-26 15:45:16.070674: train_loss -0.9492 +2023-05-26 15:45:16.071450: val_loss -0.6572 +2023-05-26 15:45:16.071779: Pseudo dice [0.9353, 0.8608, 0.8997] +2023-05-26 15:45:16.072006: Epoch time: 37.61 s +2023-05-26 15:45:17.726529: +2023-05-26 15:45:17.726740: Epoch 346 +2023-05-26 15:45:17.726865: Current learning rate: 0.00682 +2023-05-26 15:45:55.298042: train_loss -0.9504 +2023-05-26 15:45:55.298338: val_loss -0.6511 +2023-05-26 15:45:55.298488: Pseudo dice [0.9362, 0.8604, 0.9001] +2023-05-26 15:45:55.298589: Epoch time: 37.57 s +2023-05-26 15:45:56.901578: +2023-05-26 15:45:56.901790: Epoch 347 +2023-05-26 15:45:56.901918: Current learning rate: 0.00681 +2023-05-26 15:46:34.751919: train_loss -0.95 +2023-05-26 15:46:34.752132: val_loss -0.6443 +2023-05-26 15:46:34.752233: Pseudo dice [0.935, 0.8607, 0.899] +2023-05-26 15:46:34.752313: Epoch time: 37.85 s +2023-05-26 15:46:36.372931: +2023-05-26 15:46:36.373290: Epoch 348 +2023-05-26 15:46:36.373530: Current learning rate: 0.0068 +2023-05-26 15:47:14.472527: train_loss -0.9507 +2023-05-26 15:47:14.472812: val_loss -0.656 +2023-05-26 15:47:14.472948: Pseudo dice [0.9356, 0.8585, 0.9032] +2023-05-26 15:47:14.473060: Epoch time: 38.1 s +2023-05-26 15:47:16.207560: +2023-05-26 15:47:16.207753: Epoch 349 +2023-05-26 15:47:16.207877: Current learning rate: 0.0068 +2023-05-26 15:47:53.695523: train_loss -0.9509 +2023-05-26 15:47:53.696134: val_loss -0.6568 +2023-05-26 15:47:53.696352: Pseudo dice [0.9374, 0.8628, 0.9023] +2023-05-26 15:47:53.696504: Epoch time: 37.49 s +2023-05-26 15:47:57.167150: +2023-05-26 15:47:57.167681: Epoch 350 +2023-05-26 15:47:57.168021: Current learning rate: 0.00679 +2023-05-26 15:48:34.848920: train_loss -0.9508 +2023-05-26 15:48:34.849291: val_loss -0.6464 +2023-05-26 15:48:34.849431: Pseudo dice [0.9346, 0.8602, 0.9008] +2023-05-26 15:48:34.849653: Epoch time: 37.68 s +2023-05-26 15:48:36.429477: +2023-05-26 15:48:36.429881: Epoch 351 +2023-05-26 15:48:36.430032: Current learning rate: 0.00678 +2023-05-26 15:49:14.140141: train_loss -0.9502 +2023-05-26 15:49:14.140475: val_loss -0.6545 +2023-05-26 15:49:14.140602: Pseudo dice [0.9358, 0.8633, 0.9008] +2023-05-26 15:49:14.140697: Epoch time: 37.71 s +2023-05-26 15:49:15.947504: +2023-05-26 15:49:15.947689: Epoch 352 +2023-05-26 15:49:15.947806: Current learning rate: 0.00677 +2023-05-26 15:49:53.710304: train_loss -0.9512 +2023-05-26 15:49:53.710593: val_loss -0.646 +2023-05-26 15:49:53.710712: Pseudo dice [0.9338, 0.8592, 0.8996] +2023-05-26 15:49:53.710804: Epoch time: 37.76 s +2023-05-26 15:49:55.394927: +2023-05-26 15:49:55.395278: Epoch 353 +2023-05-26 15:49:55.395473: Current learning rate: 0.00676 +2023-05-26 15:50:33.146118: train_loss -0.9526 +2023-05-26 15:50:33.146421: val_loss -0.6441 +2023-05-26 15:50:33.146547: Pseudo dice [0.9345, 0.8597, 0.9009] +2023-05-26 15:50:33.146640: Epoch time: 37.75 s +2023-05-26 15:50:34.795356: +2023-05-26 15:50:34.795644: Epoch 354 +2023-05-26 15:50:34.795799: Current learning rate: 0.00675 +2023-05-26 15:51:12.338697: train_loss -0.952 +2023-05-26 15:51:12.338966: val_loss -0.6527 +2023-05-26 15:51:12.339084: Pseudo dice [0.9345, 0.8622, 0.9028] +2023-05-26 15:51:12.339182: Epoch time: 37.55 s +2023-05-26 15:51:14.110343: +2023-05-26 15:51:14.110553: Epoch 355 +2023-05-26 15:51:14.110690: Current learning rate: 0.00674 +2023-05-26 15:51:51.661949: train_loss -0.9508 +2023-05-26 15:51:51.662173: val_loss -0.6507 +2023-05-26 15:51:51.662301: Pseudo dice [0.936, 0.8638, 0.9038] +2023-05-26 15:51:51.662399: Epoch time: 37.55 s +2023-05-26 15:51:53.191766: +2023-05-26 15:51:53.192141: Epoch 356 +2023-05-26 15:51:53.192398: Current learning rate: 0.00673 +2023-05-26 15:52:30.930813: train_loss -0.9511 +2023-05-26 15:52:30.931128: val_loss -0.648 +2023-05-26 15:52:30.931249: Pseudo dice [0.9346, 0.8609, 0.9013] +2023-05-26 15:52:30.931342: Epoch time: 37.74 s +2023-05-26 15:52:32.984768: +2023-05-26 15:52:32.984993: Epoch 357 +2023-05-26 15:52:32.985101: Current learning rate: 0.00672 +2023-05-26 15:53:10.935848: train_loss -0.9516 +2023-05-26 15:53:10.936381: val_loss -0.6524 +2023-05-26 15:53:10.936483: Pseudo dice [0.9361, 0.8619, 0.9013] +2023-05-26 15:53:10.936568: Epoch time: 37.95 s +2023-05-26 15:53:12.622186: +2023-05-26 15:53:12.622458: Epoch 358 +2023-05-26 15:53:12.622588: Current learning rate: 0.00671 +2023-05-26 15:53:50.137915: train_loss -0.9514 +2023-05-26 15:53:50.138216: val_loss -0.6522 +2023-05-26 15:53:50.138352: Pseudo dice [0.9363, 0.8613, 0.9028] +2023-05-26 15:53:50.138454: Epoch time: 37.52 s +2023-05-26 15:53:51.677093: +2023-05-26 15:53:51.677270: Epoch 359 +2023-05-26 15:53:51.677385: Current learning rate: 0.0067 +2023-05-26 15:54:29.590685: train_loss -0.9522 +2023-05-26 15:54:29.591106: val_loss -0.6523 +2023-05-26 15:54:29.591366: Pseudo dice [0.9355, 0.8619, 0.9033] +2023-05-26 15:54:29.591577: Epoch time: 37.91 s +2023-05-26 15:54:31.268641: +2023-05-26 15:54:31.268824: Epoch 360 +2023-05-26 15:54:31.268947: Current learning rate: 0.00669 +2023-05-26 15:55:08.949357: train_loss -0.9524 +2023-05-26 15:55:08.949635: val_loss -0.6536 +2023-05-26 15:55:08.949762: Pseudo dice [0.9359, 0.8621, 0.9008] +2023-05-26 15:55:08.949848: Epoch time: 37.68 s +2023-05-26 15:55:10.439303: +2023-05-26 15:55:10.439455: Epoch 361 +2023-05-26 15:55:10.439560: Current learning rate: 0.00668 +2023-05-26 15:55:48.064073: train_loss -0.9524 +2023-05-26 15:55:48.064345: val_loss -0.6469 +2023-05-26 15:55:48.064468: Pseudo dice [0.9347, 0.8633, 0.9031] +2023-05-26 15:55:48.064571: Epoch time: 37.63 s +2023-05-26 15:55:49.684944: +2023-05-26 15:55:49.685108: Epoch 362 +2023-05-26 15:55:49.685227: Current learning rate: 0.00667 +2023-05-26 15:56:27.596898: train_loss -0.9518 +2023-05-26 15:56:27.597137: val_loss -0.6405 +2023-05-26 15:56:27.597255: Pseudo dice [0.9345, 0.8601, 0.8995] +2023-05-26 15:56:27.597360: Epoch time: 37.91 s +2023-05-26 15:56:29.706911: +2023-05-26 15:56:29.707085: Epoch 363 +2023-05-26 15:56:29.707196: Current learning rate: 0.00666 +2023-05-26 15:57:07.273435: train_loss -0.9527 +2023-05-26 15:57:07.273665: val_loss -0.6423 +2023-05-26 15:57:07.273796: Pseudo dice [0.934, 0.8615, 0.9038] +2023-05-26 15:57:07.273896: Epoch time: 37.57 s +2023-05-26 15:57:08.894792: +2023-05-26 15:57:08.894995: Epoch 364 +2023-05-26 15:57:08.895121: Current learning rate: 0.00665 +2023-05-26 15:57:47.637506: train_loss -0.9518 +2023-05-26 15:57:47.638300: val_loss -0.6461 +2023-05-26 15:57:47.638470: Pseudo dice [0.9345, 0.8597, 0.8988] +2023-05-26 15:57:47.638590: Epoch time: 38.74 s +2023-05-26 15:57:49.448607: +2023-05-26 15:57:49.448783: Epoch 365 +2023-05-26 15:57:49.448956: Current learning rate: 0.00665 +2023-05-26 15:58:27.575855: train_loss -0.9516 +2023-05-26 15:58:27.576112: val_loss -0.6513 +2023-05-26 15:58:27.576249: Pseudo dice [0.9357, 0.861, 0.9035] +2023-05-26 15:58:27.576356: Epoch time: 38.13 s +2023-05-26 15:58:29.202477: +2023-05-26 15:58:29.202840: Epoch 366 +2023-05-26 15:58:29.203153: Current learning rate: 0.00664 +2023-05-26 15:59:06.821236: train_loss -0.9521 +2023-05-26 15:59:06.821558: val_loss -0.643 +2023-05-26 15:59:06.821700: Pseudo dice [0.9339, 0.8599, 0.8993] +2023-05-26 15:59:06.821801: Epoch time: 37.62 s +2023-05-26 15:59:08.455721: +2023-05-26 15:59:08.455980: Epoch 367 +2023-05-26 15:59:08.456122: Current learning rate: 0.00663 +2023-05-26 15:59:46.338761: train_loss -0.9517 +2023-05-26 15:59:46.339042: val_loss -0.6514 +2023-05-26 15:59:46.339178: Pseudo dice [0.936, 0.861, 0.8986] +2023-05-26 15:59:46.339271: Epoch time: 37.88 s +2023-05-26 15:59:47.900428: +2023-05-26 15:59:47.900598: Epoch 368 +2023-05-26 15:59:47.900710: Current learning rate: 0.00662 +2023-05-26 16:00:25.817245: train_loss -0.9524 +2023-05-26 16:00:25.817504: val_loss -0.6532 +2023-05-26 16:00:25.817609: Pseudo dice [0.9363, 0.8609, 0.9032] +2023-05-26 16:00:25.817696: Epoch time: 37.92 s +2023-05-26 16:00:27.460797: +2023-05-26 16:00:27.461119: Epoch 369 +2023-05-26 16:00:27.461236: Current learning rate: 0.00661 +2023-05-26 16:01:05.125741: train_loss -0.9519 +2023-05-26 16:01:05.126007: val_loss -0.6603 +2023-05-26 16:01:05.126134: Pseudo dice [0.9382, 0.8661, 0.9002] +2023-05-26 16:01:05.126238: Epoch time: 37.67 s +2023-05-26 16:01:07.050974: +2023-05-26 16:01:07.051183: Epoch 370 +2023-05-26 16:01:07.051320: Current learning rate: 0.0066 +2023-05-26 16:01:44.679288: train_loss -0.9517 +2023-05-26 16:01:44.680699: val_loss -0.6469 +2023-05-26 16:01:44.680947: Pseudo dice [0.9355, 0.8626, 0.8999] +2023-05-26 16:01:44.681128: Epoch time: 37.63 s +2023-05-26 16:01:46.299855: +2023-05-26 16:01:46.300230: Epoch 371 +2023-05-26 16:01:46.300396: Current learning rate: 0.00659 +2023-05-26 16:02:24.131155: train_loss -0.9525 +2023-05-26 16:02:24.131526: val_loss -0.648 +2023-05-26 16:02:24.131731: Pseudo dice [0.9358, 0.8626, 0.8972] +2023-05-26 16:02:24.131822: Epoch time: 37.83 s +2023-05-26 16:02:25.660213: +2023-05-26 16:02:25.660467: Epoch 372 +2023-05-26 16:02:25.660621: Current learning rate: 0.00658 +2023-05-26 16:03:03.512952: train_loss -0.9518 +2023-05-26 16:03:03.513193: val_loss -0.6611 +2023-05-26 16:03:03.513307: Pseudo dice [0.9374, 0.8636, 0.9035] +2023-05-26 16:03:03.513411: Epoch time: 37.85 s +2023-05-26 16:03:05.271307: +2023-05-26 16:03:05.271916: Epoch 373 +2023-05-26 16:03:05.272099: Current learning rate: 0.00657 +2023-05-26 16:03:42.618781: train_loss -0.953 +2023-05-26 16:03:42.619040: val_loss -0.6622 +2023-05-26 16:03:42.619164: Pseudo dice [0.9368, 0.8652, 0.9027] +2023-05-26 16:03:42.619268: Epoch time: 37.35 s +2023-05-26 16:03:42.619345: Yayy! New best EMA pseudo Dice: 0.8998 +2023-05-26 16:03:45.532256: +2023-05-26 16:03:45.533093: Epoch 374 +2023-05-26 16:03:45.533234: Current learning rate: 0.00656 +2023-05-26 16:04:23.374561: train_loss -0.9528 +2023-05-26 16:04:23.374972: val_loss -0.6469 +2023-05-26 16:04:23.375234: Pseudo dice [0.9354, 0.8628, 0.9008] +2023-05-26 16:04:23.375376: Epoch time: 37.84 s +2023-05-26 16:04:25.014807: +2023-05-26 16:04:25.014999: Epoch 375 +2023-05-26 16:04:25.015112: Current learning rate: 0.00655 +2023-05-26 16:05:02.677723: train_loss -0.9532 +2023-05-26 16:05:02.677981: val_loss -0.6537 +2023-05-26 16:05:02.678113: Pseudo dice [0.9377, 0.8633, 0.902] +2023-05-26 16:05:02.678207: Epoch time: 37.66 s +2023-05-26 16:05:02.678279: Yayy! New best EMA pseudo Dice: 0.8999 +2023-05-26 16:05:06.243245: +2023-05-26 16:05:06.243454: Epoch 376 +2023-05-26 16:05:06.243581: Current learning rate: 0.00654 +2023-05-26 16:05:44.111246: train_loss -0.9536 +2023-05-26 16:05:44.111508: val_loss -0.65 +2023-05-26 16:05:44.111635: Pseudo dice [0.9376, 0.8624, 0.9045] +2023-05-26 16:05:44.111742: Epoch time: 37.87 s +2023-05-26 16:05:44.111814: Yayy! New best EMA pseudo Dice: 0.9 +2023-05-26 16:05:47.488399: +2023-05-26 16:05:47.488597: Epoch 377 +2023-05-26 16:05:47.488724: Current learning rate: 0.00653 +2023-05-26 16:06:26.149303: train_loss -0.9527 +2023-05-26 16:06:26.149565: val_loss -0.6484 +2023-05-26 16:06:26.149687: Pseudo dice [0.9351, 0.8616, 0.9036] +2023-05-26 16:06:26.149771: Epoch time: 38.66 s +2023-05-26 16:06:26.149838: Yayy! New best EMA pseudo Dice: 0.9 +2023-05-26 16:06:29.253091: +2023-05-26 16:06:29.253759: Epoch 378 +2023-05-26 16:06:29.254312: Current learning rate: 0.00652 +2023-05-26 16:07:06.848867: train_loss -0.953 +2023-05-26 16:07:06.849070: val_loss -0.6427 +2023-05-26 16:07:06.849169: Pseudo dice [0.9363, 0.8611, 0.8996] +2023-05-26 16:07:06.849252: Epoch time: 37.6 s +2023-05-26 16:07:08.279682: +2023-05-26 16:07:08.279855: Epoch 379 +2023-05-26 16:07:08.279982: Current learning rate: 0.00651 +2023-05-26 16:07:45.770090: train_loss -0.9521 +2023-05-26 16:07:45.770426: val_loss -0.6594 +2023-05-26 16:07:45.770758: Pseudo dice [0.9367, 0.8635, 0.903] +2023-05-26 16:07:45.771201: Epoch time: 37.49 s +2023-05-26 16:07:45.771461: Yayy! New best EMA pseudo Dice: 0.9001 +2023-05-26 16:07:49.064553: +2023-05-26 16:07:49.064744: Epoch 380 +2023-05-26 16:07:49.064864: Current learning rate: 0.0065 +2023-05-26 16:08:26.490448: train_loss -0.9527 +2023-05-26 16:08:26.490736: val_loss -0.6495 +2023-05-26 16:08:26.490895: Pseudo dice [0.9349, 0.8611, 0.9029] +2023-05-26 16:08:26.490993: Epoch time: 37.43 s +2023-05-26 16:08:28.452561: +2023-05-26 16:08:28.452745: Epoch 381 +2023-05-26 16:08:28.452867: Current learning rate: 0.00649 +2023-05-26 16:09:05.775025: train_loss -0.9532 +2023-05-26 16:09:05.775295: val_loss -0.6537 +2023-05-26 16:09:05.775469: Pseudo dice [0.9372, 0.8626, 0.9047] +2023-05-26 16:09:05.775570: Epoch time: 37.32 s +2023-05-26 16:09:05.775652: Yayy! New best EMA pseudo Dice: 0.9002 +2023-05-26 16:09:08.935807: +2023-05-26 16:09:08.936018: Epoch 382 +2023-05-26 16:09:08.936151: Current learning rate: 0.00648 +2023-05-26 16:09:47.167360: train_loss -0.9531 +2023-05-26 16:09:47.167641: val_loss -0.6571 +2023-05-26 16:09:47.167787: Pseudo dice [0.9366, 0.863, 0.9035] +2023-05-26 16:09:47.167886: Epoch time: 38.23 s +2023-05-26 16:09:47.167970: Yayy! New best EMA pseudo Dice: 0.9002 +2023-05-26 16:09:50.564198: +2023-05-26 16:09:50.564419: Epoch 383 +2023-05-26 16:09:50.564572: Current learning rate: 0.00648 +2023-05-26 16:10:28.476321: train_loss -0.953 +2023-05-26 16:10:28.476638: val_loss -0.6524 +2023-05-26 16:10:28.476782: Pseudo dice [0.9345, 0.8612, 0.9038] +2023-05-26 16:10:28.476888: Epoch time: 37.91 s +2023-05-26 16:10:30.197304: +2023-05-26 16:10:30.197494: Epoch 384 +2023-05-26 16:10:30.197642: Current learning rate: 0.00647 +2023-05-26 16:11:08.170866: train_loss -0.9532 +2023-05-26 16:11:08.171184: val_loss -0.6521 +2023-05-26 16:11:08.171300: Pseudo dice [0.9361, 0.8618, 0.9065] +2023-05-26 16:11:08.171401: Epoch time: 37.97 s +2023-05-26 16:11:08.171482: Yayy! New best EMA pseudo Dice: 0.9003 +2023-05-26 16:11:11.205504: +2023-05-26 16:11:11.205685: Epoch 385 +2023-05-26 16:11:11.205806: Current learning rate: 0.00646 +2023-05-26 16:11:48.698923: train_loss -0.9537 +2023-05-26 16:11:48.699282: val_loss -0.6439 +2023-05-26 16:11:48.699469: Pseudo dice [0.9351, 0.8609, 0.8983] +2023-05-26 16:11:48.699628: Epoch time: 37.49 s +2023-05-26 16:11:50.533842: +2023-05-26 16:11:50.534034: Epoch 386 +2023-05-26 16:11:50.534149: Current learning rate: 0.00645 +2023-05-26 16:12:28.033786: train_loss -0.9527 +2023-05-26 16:12:28.034144: val_loss -0.6538 +2023-05-26 16:12:28.034464: Pseudo dice [0.9368, 0.8635, 0.9025] +2023-05-26 16:12:28.034556: Epoch time: 37.5 s +2023-05-26 16:12:29.943371: +2023-05-26 16:12:29.943721: Epoch 387 +2023-05-26 16:12:29.943937: Current learning rate: 0.00644 +2023-05-26 16:13:07.452136: train_loss -0.9529 +2023-05-26 16:13:07.452405: val_loss -0.6562 +2023-05-26 16:13:07.452525: Pseudo dice [0.9368, 0.8617, 0.9053] +2023-05-26 16:13:07.452608: Epoch time: 37.51 s +2023-05-26 16:13:09.090415: +2023-05-26 16:13:09.090755: Epoch 388 +2023-05-26 16:13:09.090974: Current learning rate: 0.00643 +2023-05-26 16:13:46.878479: train_loss -0.9537 +2023-05-26 16:13:46.878787: val_loss -0.648 +2023-05-26 16:13:46.878928: Pseudo dice [0.9375, 0.8664, 0.8985] +2023-05-26 16:13:46.879036: Epoch time: 37.79 s +2023-05-26 16:13:46.879129: Yayy! New best EMA pseudo Dice: 0.9004 +2023-05-26 16:13:49.860664: +2023-05-26 16:13:49.860989: Epoch 389 +2023-05-26 16:13:49.861239: Current learning rate: 0.00642 +2023-05-26 16:14:27.481800: train_loss -0.9535 +2023-05-26 16:14:27.482073: val_loss -0.6454 +2023-05-26 16:14:27.482205: Pseudo dice [0.9365, 0.8615, 0.9028] +2023-05-26 16:14:27.482307: Epoch time: 37.62 s +2023-05-26 16:14:29.135938: +2023-05-26 16:14:29.136137: Epoch 390 +2023-05-26 16:14:29.136262: Current learning rate: 0.00641 +2023-05-26 16:15:06.915245: train_loss -0.9535 +2023-05-26 16:15:06.915545: val_loss -0.6466 +2023-05-26 16:15:06.915669: Pseudo dice [0.9358, 0.8614, 0.9069] +2023-05-26 16:15:06.915757: Epoch time: 37.78 s +2023-05-26 16:15:06.915826: Yayy! New best EMA pseudo Dice: 0.9004 +2023-05-26 16:15:10.343928: +2023-05-26 16:15:10.344106: Epoch 391 +2023-05-26 16:15:10.344225: Current learning rate: 0.0064 +2023-05-26 16:15:48.170892: train_loss -0.9542 +2023-05-26 16:15:48.171257: val_loss -0.6498 +2023-05-26 16:15:48.171420: Pseudo dice [0.9358, 0.8627, 0.9006] +2023-05-26 16:15:48.171555: Epoch time: 37.83 s +2023-05-26 16:15:49.838021: +2023-05-26 16:15:49.838220: Epoch 392 +2023-05-26 16:15:49.838417: Current learning rate: 0.00639 +2023-05-26 16:16:27.686534: train_loss -0.9531 +2023-05-26 16:16:27.686769: val_loss -0.6494 +2023-05-26 16:16:27.686879: Pseudo dice [0.9348, 0.8614, 0.9035] +2023-05-26 16:16:27.686974: Epoch time: 37.85 s +2023-05-26 16:16:29.514722: +2023-05-26 16:16:29.514938: Epoch 393 +2023-05-26 16:16:29.515057: Current learning rate: 0.00638 +2023-05-26 16:17:07.396403: train_loss -0.9524 +2023-05-26 16:17:07.396643: val_loss -0.6581 +2023-05-26 16:17:07.396765: Pseudo dice [0.9372, 0.8632, 0.9029] +2023-05-26 16:17:07.396863: Epoch time: 37.88 s +2023-05-26 16:17:09.164023: +2023-05-26 16:17:09.164458: Epoch 394 +2023-05-26 16:17:09.164648: Current learning rate: 0.00637 +2023-05-26 16:17:46.870015: train_loss -0.9528 +2023-05-26 16:17:46.870242: val_loss -0.6469 +2023-05-26 16:17:46.870349: Pseudo dice [0.936, 0.8619, 0.9044] +2023-05-26 16:17:46.870471: Epoch time: 37.71 s +2023-05-26 16:17:48.368652: +2023-05-26 16:17:48.368814: Epoch 395 +2023-05-26 16:17:48.368919: Current learning rate: 0.00636 +2023-05-26 16:18:25.895828: train_loss -0.9532 +2023-05-26 16:18:25.896200: val_loss -0.6411 +2023-05-26 16:18:25.896319: Pseudo dice [0.9355, 0.8605, 0.8994] +2023-05-26 16:18:25.896419: Epoch time: 37.53 s +2023-05-26 16:18:27.750275: +2023-05-26 16:18:27.750469: Epoch 396 +2023-05-26 16:18:27.750590: Current learning rate: 0.00635 +2023-05-26 16:19:05.373534: train_loss -0.9528 +2023-05-26 16:19:05.373767: val_loss -0.6472 +2023-05-26 16:19:05.373885: Pseudo dice [0.9344, 0.8613, 0.9055] +2023-05-26 16:19:05.373986: Epoch time: 37.62 s +2023-05-26 16:19:06.980847: +2023-05-26 16:19:06.981157: Epoch 397 +2023-05-26 16:19:06.981465: Current learning rate: 0.00634 +2023-05-26 16:19:44.435940: train_loss -0.9525 +2023-05-26 16:19:44.436189: val_loss -0.6532 +2023-05-26 16:19:44.436316: Pseudo dice [0.9346, 0.8593, 0.9056] +2023-05-26 16:19:44.436410: Epoch time: 37.46 s +2023-05-26 16:19:46.142149: +2023-05-26 16:19:46.142471: Epoch 398 +2023-05-26 16:19:46.142592: Current learning rate: 0.00633 +2023-05-26 16:20:23.576613: train_loss -0.9536 +2023-05-26 16:20:23.576889: val_loss -0.6462 +2023-05-26 16:20:23.577006: Pseudo dice [0.9351, 0.861, 0.9031] +2023-05-26 16:20:23.577089: Epoch time: 37.44 s +2023-05-26 16:20:25.607262: +2023-05-26 16:20:25.607621: Epoch 399 +2023-05-26 16:20:25.607798: Current learning rate: 0.00632 +2023-05-26 16:21:04.066527: train_loss -0.9539 +2023-05-26 16:21:04.066954: val_loss -0.6422 +2023-05-26 16:21:04.067088: Pseudo dice [0.9341, 0.8603, 0.9049] +2023-05-26 16:21:04.067189: Epoch time: 38.46 s +2023-05-26 16:21:07.337274: +2023-05-26 16:21:07.337564: Epoch 400 +2023-05-26 16:21:07.337832: Current learning rate: 0.00631 +2023-05-26 16:21:44.894985: train_loss -0.954 +2023-05-26 16:21:44.895185: val_loss -0.6523 +2023-05-26 16:21:44.895295: Pseudo dice [0.9356, 0.8606, 0.9019] +2023-05-26 16:21:44.895397: Epoch time: 37.56 s +2023-05-26 16:21:46.403537: +2023-05-26 16:21:46.403732: Epoch 401 +2023-05-26 16:21:46.403892: Current learning rate: 0.0063 +2023-05-26 16:22:24.099413: train_loss -0.9535 +2023-05-26 16:22:24.099649: val_loss -0.6437 +2023-05-26 16:22:24.099769: Pseudo dice [0.9353, 0.8619, 0.901] +2023-05-26 16:22:24.099871: Epoch time: 37.7 s +2023-05-26 16:22:25.695691: +2023-05-26 16:22:25.696219: Epoch 402 +2023-05-26 16:22:25.696459: Current learning rate: 0.0063 +2023-05-26 16:23:03.205318: train_loss -0.9542 +2023-05-26 16:23:03.205634: val_loss -0.6477 +2023-05-26 16:23:03.205767: Pseudo dice [0.9355, 0.861, 0.9031] +2023-05-26 16:23:03.205866: Epoch time: 37.51 s +2023-05-26 16:23:04.834555: +2023-05-26 16:23:04.834785: Epoch 403 +2023-05-26 16:23:04.834934: Current learning rate: 0.00629 +2023-05-26 16:23:42.290930: train_loss -0.9538 +2023-05-26 16:23:42.291349: val_loss -0.6582 +2023-05-26 16:23:42.291463: Pseudo dice [0.9351, 0.8629, 0.906] +2023-05-26 16:23:42.291552: Epoch time: 37.46 s +2023-05-26 16:23:43.967594: +2023-05-26 16:23:43.968042: Epoch 404 +2023-05-26 16:23:43.968318: Current learning rate: 0.00628 +2023-05-26 16:24:21.487306: train_loss -0.9537 +2023-05-26 16:24:21.487643: val_loss -0.6513 +2023-05-26 16:24:21.487780: Pseudo dice [0.9339, 0.8597, 0.9028] +2023-05-26 16:24:21.487889: Epoch time: 37.52 s +2023-05-26 16:24:23.423007: +2023-05-26 16:24:23.423502: Epoch 405 +2023-05-26 16:24:23.423737: Current learning rate: 0.00627 +2023-05-26 16:25:01.065069: train_loss -0.9547 +2023-05-26 16:25:01.065349: val_loss -0.6493 +2023-05-26 16:25:01.065479: Pseudo dice [0.9357, 0.86, 0.9026] +2023-05-26 16:25:01.065591: Epoch time: 37.64 s +2023-05-26 16:25:02.622834: +2023-05-26 16:25:02.623044: Epoch 406 +2023-05-26 16:25:02.623163: Current learning rate: 0.00626 +2023-05-26 16:25:40.336598: train_loss -0.9535 +2023-05-26 16:25:40.336880: val_loss -0.6504 +2023-05-26 16:25:40.337013: Pseudo dice [0.9362, 0.8631, 0.9006] +2023-05-26 16:25:40.337102: Epoch time: 37.72 s +2023-05-26 16:25:42.087898: +2023-05-26 16:25:42.088157: Epoch 407 +2023-05-26 16:25:42.088500: Current learning rate: 0.00625 +2023-05-26 16:26:20.778856: train_loss -0.9536 +2023-05-26 16:26:20.779207: val_loss -0.6508 +2023-05-26 16:26:20.779433: Pseudo dice [0.9354, 0.8631, 0.9005] +2023-05-26 16:26:20.779642: Epoch time: 38.69 s +2023-05-26 16:26:22.537439: +2023-05-26 16:26:22.537624: Epoch 408 +2023-05-26 16:26:22.537749: Current learning rate: 0.00624 +2023-05-26 16:27:00.685943: train_loss -0.9547 +2023-05-26 16:27:00.686375: val_loss -0.6427 +2023-05-26 16:27:00.686557: Pseudo dice [0.9353, 0.8611, 0.8983] +2023-05-26 16:27:00.686704: Epoch time: 38.15 s +2023-05-26 16:27:02.325515: +2023-05-26 16:27:02.325669: Epoch 409 +2023-05-26 16:27:02.325780: Current learning rate: 0.00623 +2023-05-26 16:27:40.151675: train_loss -0.9529 +2023-05-26 16:27:40.151913: val_loss -0.6425 +2023-05-26 16:27:40.152012: Pseudo dice [0.9338, 0.86, 0.9025] +2023-05-26 16:27:40.152107: Epoch time: 37.83 s +2023-05-26 16:27:41.816035: +2023-05-26 16:27:41.816509: Epoch 410 +2023-05-26 16:27:41.816655: Current learning rate: 0.00622 +2023-05-26 16:28:19.394831: train_loss -0.9531 +2023-05-26 16:28:19.395110: val_loss -0.6388 +2023-05-26 16:28:19.395240: Pseudo dice [0.9352, 0.8621, 0.8999] +2023-05-26 16:28:19.395327: Epoch time: 37.58 s +2023-05-26 16:28:20.877217: +2023-05-26 16:28:20.877554: Epoch 411 +2023-05-26 16:28:20.877715: Current learning rate: 0.00621 +2023-05-26 16:28:59.011493: train_loss -0.9537 +2023-05-26 16:28:59.011846: val_loss -0.6504 +2023-05-26 16:28:59.011966: Pseudo dice [0.9356, 0.8614, 0.9047] +2023-05-26 16:28:59.012060: Epoch time: 38.14 s +2023-05-26 16:29:00.667588: +2023-05-26 16:29:00.667781: Epoch 412 +2023-05-26 16:29:00.667898: Current learning rate: 0.0062 +2023-05-26 16:29:38.605780: train_loss -0.9538 +2023-05-26 16:29:38.606084: val_loss -0.6492 +2023-05-26 16:29:38.606225: Pseudo dice [0.9366, 0.8616, 0.9044] +2023-05-26 16:29:38.606331: Epoch time: 37.94 s +2023-05-26 16:29:40.156563: +2023-05-26 16:29:40.156822: Epoch 413 +2023-05-26 16:29:40.156946: Current learning rate: 0.00619 +2023-05-26 16:30:17.783710: train_loss -0.9547 +2023-05-26 16:30:17.784248: val_loss -0.6444 +2023-05-26 16:30:17.784648: Pseudo dice [0.9349, 0.8597, 0.904] +2023-05-26 16:30:17.784956: Epoch time: 37.63 s +2023-05-26 16:30:19.641507: +2023-05-26 16:30:19.641984: Epoch 414 +2023-05-26 16:30:19.642126: Current learning rate: 0.00618 +2023-05-26 16:30:57.816941: train_loss -0.9539 +2023-05-26 16:30:57.817201: val_loss -0.644 +2023-05-26 16:30:57.817312: Pseudo dice [0.9342, 0.8608, 0.9054] +2023-05-26 16:30:57.817421: Epoch time: 38.18 s +2023-05-26 16:30:59.381372: +2023-05-26 16:30:59.381681: Epoch 415 +2023-05-26 16:30:59.382009: Current learning rate: 0.00617 +2023-05-26 16:31:37.367632: train_loss -0.9536 +2023-05-26 16:31:37.367892: val_loss -0.6531 +2023-05-26 16:31:37.368023: Pseudo dice [0.9361, 0.8605, 0.9016] +2023-05-26 16:31:37.368132: Epoch time: 37.99 s +2023-05-26 16:31:39.055904: +2023-05-26 16:31:39.056396: Epoch 416 +2023-05-26 16:31:39.056635: Current learning rate: 0.00616 +2023-05-26 16:32:17.065102: train_loss -0.9525 +2023-05-26 16:32:17.065358: val_loss -0.6516 +2023-05-26 16:32:17.065482: Pseudo dice [0.9353, 0.8606, 0.9035] +2023-05-26 16:32:17.065579: Epoch time: 38.01 s +2023-05-26 16:32:18.685521: +2023-05-26 16:32:18.686178: Epoch 417 +2023-05-26 16:32:18.686548: Current learning rate: 0.00615 +2023-05-26 16:32:56.485740: train_loss -0.9528 +2023-05-26 16:32:56.486072: val_loss -0.6539 +2023-05-26 16:32:56.486226: Pseudo dice [0.9364, 0.8623, 0.9038] +2023-05-26 16:32:56.486349: Epoch time: 37.8 s +2023-05-26 16:32:58.339489: +2023-05-26 16:32:58.339954: Epoch 418 +2023-05-26 16:32:58.340182: Current learning rate: 0.00614 +2023-05-26 16:33:36.077501: train_loss -0.9545 +2023-05-26 16:33:36.077770: val_loss -0.6395 +2023-05-26 16:33:36.077888: Pseudo dice [0.935, 0.8603, 0.8996] +2023-05-26 16:33:36.077985: Epoch time: 37.74 s +2023-05-26 16:33:37.740026: +2023-05-26 16:33:37.740376: Epoch 419 +2023-05-26 16:33:37.740572: Current learning rate: 0.00613 +2023-05-26 16:34:15.301094: train_loss -0.9543 +2023-05-26 16:34:15.301342: val_loss -0.6467 +2023-05-26 16:34:15.301488: Pseudo dice [0.9349, 0.8611, 0.9055] +2023-05-26 16:34:15.301587: Epoch time: 37.56 s +2023-05-26 16:34:16.860039: +2023-05-26 16:34:16.860228: Epoch 420 +2023-05-26 16:34:16.860348: Current learning rate: 0.00612 +2023-05-26 16:34:54.486971: train_loss -0.9547 +2023-05-26 16:34:54.487536: val_loss -0.651 +2023-05-26 16:34:54.487672: Pseudo dice [0.9371, 0.8638, 0.9061] +2023-05-26 16:34:54.487760: Epoch time: 37.63 s +2023-05-26 16:34:56.079421: +2023-05-26 16:34:56.079605: Epoch 421 +2023-05-26 16:34:56.079716: Current learning rate: 0.00612 +2023-05-26 16:35:34.040226: train_loss -0.9535 +2023-05-26 16:35:34.041015: val_loss -0.6561 +2023-05-26 16:35:34.041241: Pseudo dice [0.9363, 0.8642, 0.8989] +2023-05-26 16:35:34.041415: Epoch time: 37.96 s +2023-05-26 16:35:35.632354: +2023-05-26 16:35:35.632544: Epoch 422 +2023-05-26 16:35:35.632662: Current learning rate: 0.00611 +2023-05-26 16:36:13.106713: train_loss -0.9542 +2023-05-26 16:36:13.107206: val_loss -0.65 +2023-05-26 16:36:13.107635: Pseudo dice [0.9352, 0.8615, 0.9039] +2023-05-26 16:36:13.107914: Epoch time: 37.48 s +2023-05-26 16:36:14.867489: +2023-05-26 16:36:14.867785: Epoch 423 +2023-05-26 16:36:14.868003: Current learning rate: 0.0061 +2023-05-26 16:36:53.409286: train_loss -0.9549 +2023-05-26 16:36:53.409610: val_loss -0.6535 +2023-05-26 16:36:53.409743: Pseudo dice [0.9364, 0.8626, 0.9028] +2023-05-26 16:36:53.409843: Epoch time: 38.54 s +2023-05-26 16:36:55.005383: +2023-05-26 16:36:55.005620: Epoch 424 +2023-05-26 16:36:55.005767: Current learning rate: 0.00609 +2023-05-26 16:37:33.204010: train_loss -0.9547 +2023-05-26 16:37:33.204307: val_loss -0.6481 +2023-05-26 16:37:33.204431: Pseudo dice [0.9364, 0.8631, 0.8996] +2023-05-26 16:37:33.204527: Epoch time: 38.2 s +2023-05-26 16:37:35.177231: +2023-05-26 16:37:35.177743: Epoch 425 +2023-05-26 16:37:35.177999: Current learning rate: 0.00608 +2023-05-26 16:38:13.323818: train_loss -0.9548 +2023-05-26 16:38:13.324078: val_loss -0.6578 +2023-05-26 16:38:13.324210: Pseudo dice [0.9368, 0.8625, 0.9046] +2023-05-26 16:38:13.324298: Epoch time: 38.15 s +2023-05-26 16:38:14.913234: +2023-05-26 16:38:14.913458: Epoch 426 +2023-05-26 16:38:14.913603: Current learning rate: 0.00607 +2023-05-26 16:38:52.865022: train_loss -0.9545 +2023-05-26 16:38:52.865269: val_loss -0.6472 +2023-05-26 16:38:52.865399: Pseudo dice [0.9353, 0.8623, 0.9044] +2023-05-26 16:38:52.865487: Epoch time: 37.95 s +2023-05-26 16:38:54.464295: +2023-05-26 16:38:54.464510: Epoch 427 +2023-05-26 16:38:54.464706: Current learning rate: 0.00606 +2023-05-26 16:39:35.220738: train_loss -0.9547 +2023-05-26 16:39:35.221010: val_loss -0.6433 +2023-05-26 16:39:35.221144: Pseudo dice [0.9353, 0.8594, 0.8995] +2023-05-26 16:39:35.221234: Epoch time: 40.76 s +2023-05-26 16:39:36.844783: +2023-05-26 16:39:36.845413: Epoch 428 +2023-05-26 16:39:36.845550: Current learning rate: 0.00605 +2023-05-26 16:40:15.932407: train_loss -0.9549 +2023-05-26 16:40:15.932953: val_loss -0.6491 +2023-05-26 16:40:15.933293: Pseudo dice [0.9361, 0.8628, 0.9031] +2023-05-26 16:40:15.933570: Epoch time: 39.09 s +2023-05-26 16:40:17.587891: +2023-05-26 16:40:17.588158: Epoch 429 +2023-05-26 16:40:17.588283: Current learning rate: 0.00604 +2023-05-26 16:40:55.578110: train_loss -0.9543 +2023-05-26 16:40:55.578467: val_loss -0.6394 +2023-05-26 16:40:55.578602: Pseudo dice [0.9347, 0.8601, 0.8964] +2023-05-26 16:40:55.578687: Epoch time: 37.99 s +2023-05-26 16:40:57.173107: +2023-05-26 16:40:57.173382: Epoch 430 +2023-05-26 16:40:57.173635: Current learning rate: 0.00603 +2023-05-26 16:41:34.892148: train_loss -0.9537 +2023-05-26 16:41:34.892425: val_loss -0.6624 +2023-05-26 16:41:34.892550: Pseudo dice [0.9385, 0.8634, 0.9009] +2023-05-26 16:41:34.892637: Epoch time: 37.72 s +2023-05-26 16:41:36.644850: +2023-05-26 16:41:36.645087: Epoch 431 +2023-05-26 16:41:36.645200: Current learning rate: 0.00602 +2023-05-26 16:42:14.215381: train_loss -0.947 +2023-05-26 16:42:14.215671: val_loss -0.6672 +2023-05-26 16:42:14.215804: Pseudo dice [0.9354, 0.8606, 0.9029] +2023-05-26 16:42:14.215917: Epoch time: 37.57 s +2023-05-26 16:42:15.861318: +2023-05-26 16:42:15.861722: Epoch 432 +2023-05-26 16:42:15.862051: Current learning rate: 0.00601 +2023-05-26 16:42:54.259871: train_loss -0.9516 +2023-05-26 16:42:54.260123: val_loss -0.6578 +2023-05-26 16:42:54.260254: Pseudo dice [0.9357, 0.8619, 0.9033] +2023-05-26 16:42:54.260360: Epoch time: 38.4 s +2023-05-26 16:42:55.658107: +2023-05-26 16:42:55.658465: Epoch 433 +2023-05-26 16:42:55.658768: Current learning rate: 0.006 +2023-05-26 16:43:33.095263: train_loss -0.9536 +2023-05-26 16:43:33.095495: val_loss -0.6455 +2023-05-26 16:43:33.095616: Pseudo dice [0.9342, 0.8607, 0.9016] +2023-05-26 16:43:33.095721: Epoch time: 37.44 s +2023-05-26 16:43:34.607157: +2023-05-26 16:43:34.607324: Epoch 434 +2023-05-26 16:43:34.607440: Current learning rate: 0.00599 +2023-05-26 16:44:12.578701: train_loss -0.9544 +2023-05-26 16:44:12.579260: val_loss -0.6518 +2023-05-26 16:44:12.579423: Pseudo dice [0.9344, 0.8603, 0.9029] +2023-05-26 16:44:12.579513: Epoch time: 37.97 s +2023-05-26 16:44:14.225809: +2023-05-26 16:44:14.226017: Epoch 435 +2023-05-26 16:44:14.226152: Current learning rate: 0.00598 +2023-05-26 16:44:52.118441: train_loss -0.9544 +2023-05-26 16:44:52.118682: val_loss -0.6475 +2023-05-26 16:44:52.118801: Pseudo dice [0.9354, 0.8619, 0.9003] +2023-05-26 16:44:52.118925: Epoch time: 37.89 s +2023-05-26 16:44:53.655228: +2023-05-26 16:44:53.655380: Epoch 436 +2023-05-26 16:44:53.655490: Current learning rate: 0.00597 +2023-05-26 16:45:31.330661: train_loss -0.9551 +2023-05-26 16:45:31.330924: val_loss -0.644 +2023-05-26 16:45:31.331050: Pseudo dice [0.9366, 0.8614, 0.9013] +2023-05-26 16:45:31.331151: Epoch time: 37.68 s +2023-05-26 16:45:32.942351: +2023-05-26 16:45:32.942529: Epoch 437 +2023-05-26 16:45:32.942651: Current learning rate: 0.00596 +2023-05-26 16:46:10.430341: train_loss -0.9557 +2023-05-26 16:46:10.430598: val_loss -0.6399 +2023-05-26 16:46:10.430743: Pseudo dice [0.9363, 0.8617, 0.9043] +2023-05-26 16:46:10.430855: Epoch time: 37.49 s +2023-05-26 16:46:12.390326: +2023-05-26 16:46:12.390698: Epoch 438 +2023-05-26 16:46:12.390966: Current learning rate: 0.00595 +2023-05-26 16:46:50.646934: train_loss -0.9546 +2023-05-26 16:46:50.647333: val_loss -0.6486 +2023-05-26 16:46:50.647683: Pseudo dice [0.9362, 0.8607, 0.9063] +2023-05-26 16:46:50.647803: Epoch time: 38.26 s +2023-05-26 16:46:52.326465: +2023-05-26 16:46:52.326820: Epoch 439 +2023-05-26 16:46:52.326978: Current learning rate: 0.00594 +2023-05-26 16:47:30.486121: train_loss -0.955 +2023-05-26 16:47:30.486375: val_loss -0.6384 +2023-05-26 16:47:30.486513: Pseudo dice [0.9379, 0.8636, 0.8983] +2023-05-26 16:47:30.486606: Epoch time: 38.16 s +2023-05-26 16:47:32.191939: +2023-05-26 16:47:32.192292: Epoch 440 +2023-05-26 16:47:32.192531: Current learning rate: 0.00593 +2023-05-26 16:48:09.916391: train_loss -0.955 +2023-05-26 16:48:09.916684: val_loss -0.648 +2023-05-26 16:48:09.916801: Pseudo dice [0.9353, 0.8607, 0.9059] +2023-05-26 16:48:09.916893: Epoch time: 37.73 s +2023-05-26 16:48:11.512144: +2023-05-26 16:48:11.512358: Epoch 441 +2023-05-26 16:48:11.512498: Current learning rate: 0.00592 +2023-05-26 16:48:49.199385: train_loss -0.9553 +2023-05-26 16:48:49.199601: val_loss -0.6534 +2023-05-26 16:48:49.199710: Pseudo dice [0.937, 0.8627, 0.9046] +2023-05-26 16:48:49.199811: Epoch time: 37.69 s +2023-05-26 16:48:50.720364: +2023-05-26 16:48:50.720752: Epoch 442 +2023-05-26 16:48:50.721085: Current learning rate: 0.00592 +2023-05-26 16:49:28.391186: train_loss -0.9545 +2023-05-26 16:49:28.391406: val_loss -0.6517 +2023-05-26 16:49:28.391507: Pseudo dice [0.936, 0.8621, 0.9051] +2023-05-26 16:49:28.391607: Epoch time: 37.67 s +2023-05-26 16:49:29.840454: +2023-05-26 16:49:29.840720: Epoch 443 +2023-05-26 16:49:29.840905: Current learning rate: 0.00591 +2023-05-26 16:50:07.553857: train_loss -0.955 +2023-05-26 16:50:07.554165: val_loss -0.6447 +2023-05-26 16:50:07.554308: Pseudo dice [0.9357, 0.8601, 0.9042] +2023-05-26 16:50:07.554404: Epoch time: 37.72 s +2023-05-26 16:50:09.425004: +2023-05-26 16:50:09.425173: Epoch 444 +2023-05-26 16:50:09.425307: Current learning rate: 0.0059 +2023-05-26 16:50:48.339077: train_loss -0.9548 +2023-05-26 16:50:48.339316: val_loss -0.6485 +2023-05-26 16:50:48.339436: Pseudo dice [0.9365, 0.8622, 0.905] +2023-05-26 16:50:48.339538: Epoch time: 38.92 s +2023-05-26 16:50:49.910517: +2023-05-26 16:50:49.911025: Epoch 445 +2023-05-26 16:50:49.911316: Current learning rate: 0.00589 +2023-05-26 16:51:28.063956: train_loss -0.9548 +2023-05-26 16:51:28.064257: val_loss -0.6491 +2023-05-26 16:51:28.064385: Pseudo dice [0.9357, 0.8614, 0.8991] +2023-05-26 16:51:28.064530: Epoch time: 38.15 s +2023-05-26 16:51:29.733182: +2023-05-26 16:51:29.733414: Epoch 446 +2023-05-26 16:51:29.733574: Current learning rate: 0.00588 +2023-05-26 16:52:08.434085: train_loss -0.9503 +2023-05-26 16:52:08.434326: val_loss -0.6795 +2023-05-26 16:52:08.434440: Pseudo dice [0.9358, 0.861, 0.9003] +2023-05-26 16:52:08.434557: Epoch time: 38.7 s +2023-05-26 16:52:10.078339: +2023-05-26 16:52:10.078534: Epoch 447 +2023-05-26 16:52:10.078661: Current learning rate: 0.00587 +2023-05-26 16:52:48.019365: train_loss -0.946 +2023-05-26 16:52:48.019641: val_loss -0.6845 +2023-05-26 16:52:48.019813: Pseudo dice [0.9365, 0.8641, 0.9001] +2023-05-26 16:52:48.020097: Epoch time: 37.94 s +2023-05-26 16:52:49.657581: +2023-05-26 16:52:49.657890: Epoch 448 +2023-05-26 16:52:49.658148: Current learning rate: 0.00586 +2023-05-26 16:53:27.816954: train_loss -0.9478 +2023-05-26 16:53:27.817239: val_loss -0.6695 +2023-05-26 16:53:27.817382: Pseudo dice [0.9358, 0.8629, 0.9065] +2023-05-26 16:53:27.817477: Epoch time: 38.16 s +2023-05-26 16:53:29.384538: +2023-05-26 16:53:29.384700: Epoch 449 +2023-05-26 16:53:29.384807: Current learning rate: 0.00585 +2023-05-26 16:54:07.183993: train_loss -0.9517 +2023-05-26 16:54:07.184262: val_loss -0.6492 +2023-05-26 16:54:07.184383: Pseudo dice [0.9351, 0.8629, 0.8987] +2023-05-26 16:54:07.184468: Epoch time: 37.8 s +2023-05-26 16:54:10.234213: +2023-05-26 16:54:10.234398: Epoch 450 +2023-05-26 16:54:10.234527: Current learning rate: 0.00584 +2023-05-26 16:54:50.979618: train_loss -0.9533 +2023-05-26 16:54:50.979859: val_loss -0.6598 +2023-05-26 16:54:50.979980: Pseudo dice [0.9379, 0.8642, 0.9031] +2023-05-26 16:54:50.980083: Epoch time: 40.75 s +2023-05-26 16:54:52.725910: +2023-05-26 16:54:52.726554: Epoch 451 +2023-05-26 16:54:52.726861: Current learning rate: 0.00583 +2023-05-26 16:55:31.953336: train_loss -0.9543 +2023-05-26 16:55:31.953574: val_loss -0.6476 +2023-05-26 16:55:31.953700: Pseudo dice [0.9354, 0.8615, 0.903] +2023-05-26 16:55:31.953827: Epoch time: 39.23 s +2023-05-26 16:55:33.421703: +2023-05-26 16:55:33.422072: Epoch 452 +2023-05-26 16:55:33.422190: Current learning rate: 0.00582 +2023-05-26 16:56:11.686962: train_loss -0.9556 +2023-05-26 16:56:11.687200: val_loss -0.6469 +2023-05-26 16:56:11.687319: Pseudo dice [0.9347, 0.8598, 0.9006] +2023-05-26 16:56:11.687426: Epoch time: 38.27 s +2023-05-26 16:56:13.252497: +2023-05-26 16:56:13.252858: Epoch 453 +2023-05-26 16:56:13.253200: Current learning rate: 0.00581 +2023-05-26 16:56:50.965263: train_loss -0.9548 +2023-05-26 16:56:50.965530: val_loss -0.6424 +2023-05-26 16:56:50.965662: Pseudo dice [0.9348, 0.8611, 0.9027] +2023-05-26 16:56:50.965752: Epoch time: 37.71 s +2023-05-26 16:56:52.669138: +2023-05-26 16:56:52.669534: Epoch 454 +2023-05-26 16:56:52.669742: Current learning rate: 0.0058 +2023-05-26 16:57:30.190149: train_loss -0.9547 +2023-05-26 16:57:30.190387: val_loss -0.6446 +2023-05-26 16:57:30.190511: Pseudo dice [0.935, 0.859, 0.9012] +2023-05-26 16:57:30.190614: Epoch time: 37.52 s +2023-05-26 16:57:31.663694: +2023-05-26 16:57:31.663907: Epoch 455 +2023-05-26 16:57:31.664066: Current learning rate: 0.00579 +2023-05-26 16:58:09.446948: train_loss -0.9534 +2023-05-26 16:58:09.447184: val_loss -0.6566 +2023-05-26 16:58:09.447302: Pseudo dice [0.934, 0.8611, 0.906] +2023-05-26 16:58:09.447404: Epoch time: 37.78 s +2023-05-26 16:58:11.116196: +2023-05-26 16:58:11.116382: Epoch 456 +2023-05-26 16:58:11.116499: Current learning rate: 0.00578 +2023-05-26 16:58:48.569186: train_loss -0.9523 +2023-05-26 16:58:48.569559: val_loss -0.666 +2023-05-26 16:58:48.569680: Pseudo dice [0.9347, 0.8599, 0.9041] +2023-05-26 16:58:48.569788: Epoch time: 37.45 s +2023-05-26 16:58:50.104131: +2023-05-26 16:58:50.104486: Epoch 457 +2023-05-26 16:58:50.104648: Current learning rate: 0.00577 +2023-05-26 16:59:28.752406: train_loss -0.9515 +2023-05-26 16:59:28.752820: val_loss -0.6518 +2023-05-26 16:59:28.753052: Pseudo dice [0.936, 0.8621, 0.9053] +2023-05-26 16:59:28.753260: Epoch time: 38.65 s +2023-05-26 16:59:30.794428: +2023-05-26 16:59:30.794730: Epoch 458 +2023-05-26 16:59:30.795062: Current learning rate: 0.00576 +2023-05-26 17:00:08.071715: train_loss -0.9539 +2023-05-26 17:00:08.072066: val_loss -0.6445 +2023-05-26 17:00:08.072239: Pseudo dice [0.9353, 0.8623, 0.9056] +2023-05-26 17:00:08.072383: Epoch time: 37.28 s +2023-05-26 17:00:09.526461: +2023-05-26 17:00:09.526812: Epoch 459 +2023-05-26 17:00:09.526973: Current learning rate: 0.00575 +2023-05-26 17:00:46.913841: train_loss -0.9551 +2023-05-26 17:00:46.914065: val_loss -0.6465 +2023-05-26 17:00:46.914167: Pseudo dice [0.937, 0.862, 0.9027] +2023-05-26 17:00:46.914265: Epoch time: 37.39 s +2023-05-26 17:00:48.275498: +2023-05-26 17:00:48.275854: Epoch 460 +2023-05-26 17:00:48.276039: Current learning rate: 0.00574 +2023-05-26 17:01:26.114416: train_loss -0.9551 +2023-05-26 17:01:26.114693: val_loss -0.647 +2023-05-26 17:01:26.114796: Pseudo dice [0.9372, 0.863, 0.9049] +2023-05-26 17:01:26.114911: Epoch time: 37.84 s +2023-05-26 17:01:27.733586: +2023-05-26 17:01:27.733869: Epoch 461 +2023-05-26 17:01:27.734083: Current learning rate: 0.00573 +2023-05-26 17:02:05.522155: train_loss -0.9555 +2023-05-26 17:02:05.522417: val_loss -0.6406 +2023-05-26 17:02:05.522530: Pseudo dice [0.9359, 0.8609, 0.9026] +2023-05-26 17:02:05.522624: Epoch time: 37.79 s +2023-05-26 17:02:07.159296: +2023-05-26 17:02:07.159588: Epoch 462 +2023-05-26 17:02:07.159756: Current learning rate: 0.00572 +2023-05-26 17:02:44.780571: train_loss -0.9562 +2023-05-26 17:02:44.781395: val_loss -0.6565 +2023-05-26 17:02:44.781536: Pseudo dice [0.9381, 0.8666, 0.9066] +2023-05-26 17:02:44.781634: Epoch time: 37.62 s +2023-05-26 17:02:44.781711: Yayy! New best EMA pseudo Dice: 0.9006 +2023-05-26 17:02:47.855266: +2023-05-26 17:02:47.855471: Epoch 463 +2023-05-26 17:02:47.855601: Current learning rate: 0.00571 +2023-05-26 17:03:25.279623: train_loss -0.9564 +2023-05-26 17:03:25.280065: val_loss -0.6499 +2023-05-26 17:03:25.280304: Pseudo dice [0.9367, 0.8621, 0.9082] +2023-05-26 17:03:25.280478: Epoch time: 37.43 s +2023-05-26 17:03:25.280679: Yayy! New best EMA pseudo Dice: 0.9008 +2023-05-26 17:03:28.512620: +2023-05-26 17:03:28.512995: Epoch 464 +2023-05-26 17:03:28.513193: Current learning rate: 0.0057 +2023-05-26 17:04:06.281201: train_loss -0.9565 +2023-05-26 17:04:06.281459: val_loss -0.6466 +2023-05-26 17:04:06.281580: Pseudo dice [0.9359, 0.8625, 0.9032] +2023-05-26 17:04:06.281689: Epoch time: 37.77 s +2023-05-26 17:04:07.890334: +2023-05-26 17:04:07.890668: Epoch 465 +2023-05-26 17:04:07.890860: Current learning rate: 0.0057 +2023-05-26 17:04:45.421323: train_loss -0.9566 +2023-05-26 17:04:45.421608: val_loss -0.6395 +2023-05-26 17:04:45.421757: Pseudo dice [0.9359, 0.861, 0.9049] +2023-05-26 17:04:45.421858: Epoch time: 37.53 s +2023-05-26 17:04:46.947685: +2023-05-26 17:04:46.947927: Epoch 466 +2023-05-26 17:04:46.948082: Current learning rate: 0.00569 +2023-05-26 17:05:24.705750: train_loss -0.9569 +2023-05-26 17:05:24.705983: val_loss -0.6409 +2023-05-26 17:05:24.706160: Pseudo dice [0.9362, 0.8606, 0.9041] +2023-05-26 17:05:24.706266: Epoch time: 37.76 s +2023-05-26 17:05:26.177236: +2023-05-26 17:05:26.177552: Epoch 467 +2023-05-26 17:05:26.177716: Current learning rate: 0.00568 +2023-05-26 17:06:03.648243: train_loss -0.9566 +2023-05-26 17:06:03.648469: val_loss -0.6468 +2023-05-26 17:06:03.648588: Pseudo dice [0.9374, 0.8645, 0.9006] +2023-05-26 17:06:03.648705: Epoch time: 37.47 s +2023-05-26 17:06:05.302373: +2023-05-26 17:06:05.302693: Epoch 468 +2023-05-26 17:06:05.302943: Current learning rate: 0.00567 +2023-05-26 17:06:44.682211: train_loss -0.9563 +2023-05-26 17:06:44.682528: val_loss -0.6451 +2023-05-26 17:06:44.682731: Pseudo dice [0.9368, 0.8623, 0.9014] +2023-05-26 17:06:44.683222: Epoch time: 39.38 s +2023-05-26 17:06:46.432514: +2023-05-26 17:06:46.432801: Epoch 469 +2023-05-26 17:06:46.433016: Current learning rate: 0.00566 +2023-05-26 17:07:25.507481: train_loss -0.9565 +2023-05-26 17:07:25.507716: val_loss -0.6459 +2023-05-26 17:07:25.507832: Pseudo dice [0.9379, 0.8635, 0.905] +2023-05-26 17:07:25.507931: Epoch time: 39.08 s +2023-05-26 17:07:25.508002: Yayy! New best EMA pseudo Dice: 0.9008 +2023-05-26 17:07:28.594509: +2023-05-26 17:07:28.594907: Epoch 470 +2023-05-26 17:07:28.595114: Current learning rate: 0.00565 +2023-05-26 17:08:08.570950: train_loss -0.9566 +2023-05-26 17:08:08.571357: val_loss -0.6529 +2023-05-26 17:08:08.571555: Pseudo dice [0.9366, 0.8634, 0.9041] +2023-05-26 17:08:08.571722: Epoch time: 39.98 s +2023-05-26 17:08:08.571878: Yayy! New best EMA pseudo Dice: 0.9009 +2023-05-26 17:08:11.978673: +2023-05-26 17:08:11.979392: Epoch 471 +2023-05-26 17:08:11.979611: Current learning rate: 0.00564 +2023-05-26 17:08:49.605899: train_loss -0.9568 +2023-05-26 17:08:49.606163: val_loss -0.6405 +2023-05-26 17:08:49.606286: Pseudo dice [0.9368, 0.8634, 0.9025] +2023-05-26 17:08:49.606369: Epoch time: 37.63 s +2023-05-26 17:08:49.606437: Yayy! New best EMA pseudo Dice: 0.9009 +2023-05-26 17:08:52.652053: +2023-05-26 17:08:52.652568: Epoch 472 +2023-05-26 17:08:52.652955: Current learning rate: 0.00563 +2023-05-26 17:09:30.482537: train_loss -0.9577 +2023-05-26 17:09:30.482815: val_loss -0.6406 +2023-05-26 17:09:30.482968: Pseudo dice [0.9368, 0.8628, 0.9017] +2023-05-26 17:09:30.483088: Epoch time: 37.83 s +2023-05-26 17:09:32.555822: +2023-05-26 17:09:32.556183: Epoch 473 +2023-05-26 17:09:32.556446: Current learning rate: 0.00562 +2023-05-26 17:10:10.554062: train_loss -0.9565 +2023-05-26 17:10:10.554313: val_loss -0.6509 +2023-05-26 17:10:10.554433: Pseudo dice [0.938, 0.8658, 0.9035] +2023-05-26 17:10:10.554534: Epoch time: 38.0 s +2023-05-26 17:10:10.554736: Yayy! New best EMA pseudo Dice: 0.901 +2023-05-26 17:10:13.575631: +2023-05-26 17:10:13.575808: Epoch 474 +2023-05-26 17:10:13.575944: Current learning rate: 0.00561 +2023-05-26 17:10:51.360641: train_loss -0.9567 +2023-05-26 17:10:51.360907: val_loss -0.6396 +2023-05-26 17:10:51.361050: Pseudo dice [0.9368, 0.8613, 0.9035] +2023-05-26 17:10:51.361148: Epoch time: 37.79 s +2023-05-26 17:10:52.966011: +2023-05-26 17:10:52.966246: Epoch 475 +2023-05-26 17:10:52.966400: Current learning rate: 0.0056 +2023-05-26 17:11:31.187142: train_loss -0.9567 +2023-05-26 17:11:31.187372: val_loss -0.6474 +2023-05-26 17:11:31.187490: Pseudo dice [0.9364, 0.8618, 0.9061] +2023-05-26 17:11:31.187591: Epoch time: 38.22 s +2023-05-26 17:11:31.187665: Yayy! New best EMA pseudo Dice: 0.901 +2023-05-26 17:11:34.024430: +2023-05-26 17:11:34.024752: Epoch 476 +2023-05-26 17:11:34.024949: Current learning rate: 0.00559 +2023-05-26 17:12:12.250180: train_loss -0.957 +2023-05-26 17:12:12.250572: val_loss -0.6356 +2023-05-26 17:12:12.250780: Pseudo dice [0.9346, 0.8595, 0.9042] +2023-05-26 17:12:12.250977: Epoch time: 38.23 s +2023-05-26 17:12:14.212188: +2023-05-26 17:12:14.212481: Epoch 477 +2023-05-26 17:12:14.212685: Current learning rate: 0.00558 +2023-05-26 17:12:51.836730: train_loss -0.9573 +2023-05-26 17:12:51.837226: val_loss -0.6405 +2023-05-26 17:12:51.837434: Pseudo dice [0.9367, 0.863, 0.9031] +2023-05-26 17:12:51.837579: Epoch time: 37.63 s +2023-05-26 17:12:53.397645: +2023-05-26 17:12:53.398603: Epoch 478 +2023-05-26 17:12:53.398797: Current learning rate: 0.00557 +2023-05-26 17:13:31.044232: train_loss -0.9572 +2023-05-26 17:13:31.044641: val_loss -0.6421 +2023-05-26 17:13:31.044844: Pseudo dice [0.9357, 0.8609, 0.9054] +2023-05-26 17:13:31.045009: Epoch time: 37.65 s +2023-05-26 17:13:32.670031: +2023-05-26 17:13:32.670228: Epoch 479 +2023-05-26 17:13:32.670345: Current learning rate: 0.00556 +2023-05-26 17:14:10.580991: train_loss -0.9576 +2023-05-26 17:14:10.581251: val_loss -0.6411 +2023-05-26 17:14:10.581394: Pseudo dice [0.9353, 0.8614, 0.904] +2023-05-26 17:14:10.581491: Epoch time: 37.91 s +2023-05-26 17:14:12.129025: +2023-05-26 17:14:12.129223: Epoch 480 +2023-05-26 17:14:12.129379: Current learning rate: 0.00555 +2023-05-26 17:14:50.033421: train_loss -0.9574 +2023-05-26 17:14:50.033671: val_loss -0.6382 +2023-05-26 17:14:50.033798: Pseudo dice [0.9356, 0.8613, 0.9024] +2023-05-26 17:14:50.033885: Epoch time: 37.91 s +2023-05-26 17:14:51.715309: +2023-05-26 17:14:51.715642: Epoch 481 +2023-05-26 17:14:51.715782: Current learning rate: 0.00554 +2023-05-26 17:15:29.143516: train_loss -0.9577 +2023-05-26 17:15:29.143742: val_loss -0.6394 +2023-05-26 17:15:29.143862: Pseudo dice [0.9363, 0.8607, 0.9054] +2023-05-26 17:15:29.143970: Epoch time: 37.43 s +2023-05-26 17:15:30.772995: +2023-05-26 17:15:30.773417: Epoch 482 +2023-05-26 17:15:30.773616: Current learning rate: 0.00553 +2023-05-26 17:16:08.475199: train_loss -0.9572 +2023-05-26 17:16:08.475469: val_loss -0.6465 +2023-05-26 17:16:08.475602: Pseudo dice [0.9369, 0.8634, 0.9056] +2023-05-26 17:16:08.475688: Epoch time: 37.7 s +2023-05-26 17:16:10.005881: +2023-05-26 17:16:10.006058: Epoch 483 +2023-05-26 17:16:10.006176: Current learning rate: 0.00552 +2023-05-26 17:16:48.108798: train_loss -0.9573 +2023-05-26 17:16:48.109023: val_loss -0.6466 +2023-05-26 17:16:48.109133: Pseudo dice [0.9378, 0.8636, 0.9017] +2023-05-26 17:16:48.109241: Epoch time: 38.1 s +2023-05-26 17:16:49.931680: +2023-05-26 17:16:49.932201: Epoch 484 +2023-05-26 17:16:49.932389: Current learning rate: 0.00551 +2023-05-26 17:17:27.739039: train_loss -0.9576 +2023-05-26 17:17:27.739364: val_loss -0.6354 +2023-05-26 17:17:27.739590: Pseudo dice [0.9356, 0.8594, 0.9057] +2023-05-26 17:17:27.739822: Epoch time: 37.81 s +2023-05-26 17:17:29.468752: +2023-05-26 17:17:29.468943: Epoch 485 +2023-05-26 17:17:29.469063: Current learning rate: 0.0055 +2023-05-26 17:18:07.079798: train_loss -0.956 +2023-05-26 17:18:07.080043: val_loss -0.6387 +2023-05-26 17:18:07.080242: Pseudo dice [0.9351, 0.861, 0.9004] +2023-05-26 17:18:07.080349: Epoch time: 37.61 s +2023-05-26 17:18:08.703054: +2023-05-26 17:18:08.703271: Epoch 486 +2023-05-26 17:18:08.703403: Current learning rate: 0.00549 +2023-05-26 17:18:46.435765: train_loss -0.9546 +2023-05-26 17:18:46.436013: val_loss -0.6561 +2023-05-26 17:18:46.436144: Pseudo dice [0.9354, 0.8624, 0.9063] +2023-05-26 17:18:46.436240: Epoch time: 37.73 s +2023-05-26 17:18:47.952413: +2023-05-26 17:18:47.952694: Epoch 487 +2023-05-26 17:18:47.952875: Current learning rate: 0.00548 +2023-05-26 17:19:25.864824: train_loss -0.9556 +2023-05-26 17:19:25.865092: val_loss -0.6491 +2023-05-26 17:19:25.865241: Pseudo dice [0.9373, 0.8637, 0.901] +2023-05-26 17:19:25.865343: Epoch time: 37.91 s +2023-05-26 17:19:27.479965: +2023-05-26 17:19:27.480142: Epoch 488 +2023-05-26 17:19:27.480333: Current learning rate: 0.00547 +2023-05-26 17:20:06.565638: train_loss -0.9551 +2023-05-26 17:20:06.565962: val_loss -0.6488 +2023-05-26 17:20:06.566111: Pseudo dice [0.934, 0.8601, 0.9038] +2023-05-26 17:20:06.566225: Epoch time: 39.09 s +2023-05-26 17:20:08.071225: +2023-05-26 17:20:08.071423: Epoch 489 +2023-05-26 17:20:08.071545: Current learning rate: 0.00546 +2023-05-26 17:20:45.962505: train_loss -0.9545 +2023-05-26 17:20:45.962755: val_loss -0.6428 +2023-05-26 17:20:45.962901: Pseudo dice [0.9352, 0.8586, 0.9015] +2023-05-26 17:20:45.963022: Epoch time: 37.89 s +2023-05-26 17:20:47.424072: +2023-05-26 17:20:47.424226: Epoch 490 +2023-05-26 17:20:47.424358: Current learning rate: 0.00546 +2023-05-26 17:21:25.520489: train_loss -0.9554 +2023-05-26 17:21:25.520890: val_loss -0.6365 +2023-05-26 17:21:25.521228: Pseudo dice [0.9353, 0.8618, 0.9017] +2023-05-26 17:21:25.521375: Epoch time: 38.1 s +2023-05-26 17:21:27.536422: +2023-05-26 17:21:27.536643: Epoch 491 +2023-05-26 17:21:27.536763: Current learning rate: 0.00545 +2023-05-26 17:22:05.740532: train_loss -0.9567 +2023-05-26 17:22:05.740885: val_loss -0.635 +2023-05-26 17:22:05.741011: Pseudo dice [0.936, 0.8615, 0.9026] +2023-05-26 17:22:05.741102: Epoch time: 38.21 s +2023-05-26 17:22:07.357285: +2023-05-26 17:22:07.357615: Epoch 492 +2023-05-26 17:22:07.357931: Current learning rate: 0.00544 +2023-05-26 17:22:45.042155: train_loss -0.9574 +2023-05-26 17:22:45.042452: val_loss -0.6376 +2023-05-26 17:22:45.042576: Pseudo dice [0.9368, 0.8634, 0.9017] +2023-05-26 17:22:45.042669: Epoch time: 37.69 s +2023-05-26 17:22:46.637258: +2023-05-26 17:22:46.637456: Epoch 493 +2023-05-26 17:22:46.637576: Current learning rate: 0.00543 +2023-05-26 17:23:24.662442: train_loss -0.9579 +2023-05-26 17:23:24.662686: val_loss -0.6336 +2023-05-26 17:23:24.662783: Pseudo dice [0.9357, 0.8626, 0.898] +2023-05-26 17:23:24.662927: Epoch time: 38.03 s +2023-05-26 17:23:26.230902: +2023-05-26 17:23:26.231114: Epoch 494 +2023-05-26 17:23:26.231254: Current learning rate: 0.00542 +2023-05-26 17:24:03.932728: train_loss -0.9582 +2023-05-26 17:24:03.933088: val_loss -0.6273 +2023-05-26 17:24:03.933226: Pseudo dice [0.9344, 0.8608, 0.8989] +2023-05-26 17:24:03.933315: Epoch time: 37.7 s +2023-05-26 17:24:05.440120: +2023-05-26 17:24:05.440350: Epoch 495 +2023-05-26 17:24:05.440498: Current learning rate: 0.00541 +2023-05-26 17:24:43.660980: train_loss -0.9572 +2023-05-26 17:24:43.661278: val_loss -0.6404 +2023-05-26 17:24:43.661410: Pseudo dice [0.9361, 0.8626, 0.9006] +2023-05-26 17:24:43.661500: Epoch time: 38.22 s +2023-05-26 17:24:45.238030: +2023-05-26 17:24:45.239094: Epoch 496 +2023-05-26 17:24:45.239467: Current learning rate: 0.0054 +2023-05-26 17:25:23.407691: train_loss -0.9569 +2023-05-26 17:25:23.408111: val_loss -0.6322 +2023-05-26 17:25:23.408311: Pseudo dice [0.9353, 0.8605, 0.8998] +2023-05-26 17:25:23.408410: Epoch time: 38.17 s +2023-05-26 17:25:24.963996: +2023-05-26 17:25:24.964329: Epoch 497 +2023-05-26 17:25:24.964531: Current learning rate: 0.00539 +2023-05-26 17:26:02.951681: train_loss -0.9572 +2023-05-26 17:26:02.952085: val_loss -0.6365 +2023-05-26 17:26:02.952236: Pseudo dice [0.9343, 0.8596, 0.9012] +2023-05-26 17:26:02.952362: Epoch time: 37.99 s +2023-05-26 17:26:04.786959: +2023-05-26 17:26:04.787443: Epoch 498 +2023-05-26 17:26:04.787756: Current learning rate: 0.00538 +2023-05-26 17:26:42.565776: train_loss -0.9571 +2023-05-26 17:26:42.566093: val_loss -0.6347 +2023-05-26 17:26:42.566228: Pseudo dice [0.9359, 0.8611, 0.9027] +2023-05-26 17:26:42.566316: Epoch time: 37.78 s +2023-05-26 17:26:44.131202: +2023-05-26 17:26:44.131387: Epoch 499 +2023-05-26 17:26:44.131509: Current learning rate: 0.00537 +2023-05-26 17:27:21.708367: train_loss -0.9577 +2023-05-26 17:27:21.708591: val_loss -0.6365 +2023-05-26 17:27:21.708694: Pseudo dice [0.9359, 0.8621, 0.9032] +2023-05-26 17:27:21.708809: Epoch time: 37.58 s +2023-05-26 17:27:24.981862: +2023-05-26 17:27:24.982214: Epoch 500 +2023-05-26 17:27:24.982457: Current learning rate: 0.00536 +2023-05-26 17:28:02.645187: train_loss -0.9578 +2023-05-26 17:28:02.645469: val_loss -0.643 +2023-05-26 17:28:02.645594: Pseudo dice [0.9364, 0.8642, 0.9017] +2023-05-26 17:28:02.645688: Epoch time: 37.66 s +2023-05-26 17:28:04.212394: +2023-05-26 17:28:04.212602: Epoch 501 +2023-05-26 17:28:04.212729: Current learning rate: 0.00535 +2023-05-26 17:28:41.687508: train_loss -0.958 +2023-05-26 17:28:41.687836: val_loss -0.6466 +2023-05-26 17:28:41.687964: Pseudo dice [0.9363, 0.8619, 0.9044] +2023-05-26 17:28:41.688064: Epoch time: 37.48 s +2023-05-26 17:28:43.159657: +2023-05-26 17:28:43.160025: Epoch 502 +2023-05-26 17:28:43.160231: Current learning rate: 0.00534 +2023-05-26 17:29:20.891055: train_loss -0.958 +2023-05-26 17:29:20.891310: val_loss -0.6427 +2023-05-26 17:29:20.891435: Pseudo dice [0.9369, 0.8625, 0.9034] +2023-05-26 17:29:20.891525: Epoch time: 37.73 s +2023-05-26 17:29:22.648661: +2023-05-26 17:29:22.648887: Epoch 503 +2023-05-26 17:29:22.649037: Current learning rate: 0.00533 +2023-05-26 17:30:00.406139: train_loss -0.9578 +2023-05-26 17:30:00.406454: val_loss -0.6431 +2023-05-26 17:30:00.406618: Pseudo dice [0.9374, 0.8621, 0.9043] +2023-05-26 17:30:00.406762: Epoch time: 37.76 s +2023-05-26 17:30:02.362291: +2023-05-26 17:30:02.362616: Epoch 504 +2023-05-26 17:30:02.362853: Current learning rate: 0.00532 +2023-05-26 17:30:40.242620: train_loss -0.9575 +2023-05-26 17:30:40.242895: val_loss -0.6401 +2023-05-26 17:30:40.243614: Pseudo dice [0.9379, 0.8626, 0.8978] +2023-05-26 17:30:40.243717: Epoch time: 37.88 s +2023-05-26 17:30:41.832333: +2023-05-26 17:30:41.832522: Epoch 505 +2023-05-26 17:30:41.832638: Current learning rate: 0.00531 +2023-05-26 17:31:19.543565: train_loss -0.9574 +2023-05-26 17:31:19.543854: val_loss -0.6273 +2023-05-26 17:31:19.544011: Pseudo dice [0.9341, 0.8595, 0.8976] +2023-05-26 17:31:19.544123: Epoch time: 37.71 s +2023-05-26 17:31:21.181085: +2023-05-26 17:31:21.181421: Epoch 506 +2023-05-26 17:31:21.181563: Current learning rate: 0.0053 +2023-05-26 17:31:58.835275: train_loss -0.9577 +2023-05-26 17:31:58.835539: val_loss -0.6476 +2023-05-26 17:31:58.835653: Pseudo dice [0.9362, 0.8618, 0.9078] +2023-05-26 17:31:58.835783: Epoch time: 37.66 s +2023-05-26 17:32:00.430961: +2023-05-26 17:32:00.431320: Epoch 507 +2023-05-26 17:32:00.431536: Current learning rate: 0.00529 +2023-05-26 17:32:37.967422: train_loss -0.9587 +2023-05-26 17:32:37.967728: val_loss -0.6328 +2023-05-26 17:32:37.967883: Pseudo dice [0.935, 0.8614, 0.9018] +2023-05-26 17:32:37.968019: Epoch time: 37.54 s +2023-05-26 17:32:39.595178: +2023-05-26 17:32:39.595556: Epoch 508 +2023-05-26 17:32:39.595839: Current learning rate: 0.00528 +2023-05-26 17:33:17.256628: train_loss -0.959 +2023-05-26 17:33:17.256907: val_loss -0.6306 +2023-05-26 17:33:17.257031: Pseudo dice [0.9356, 0.8612, 0.9036] +2023-05-26 17:33:17.257118: Epoch time: 37.66 s +2023-05-26 17:33:18.848355: +2023-05-26 17:33:18.848787: Epoch 509 +2023-05-26 17:33:18.850504: Current learning rate: 0.00527 +2023-05-26 17:33:56.921730: train_loss -0.959 +2023-05-26 17:33:56.922017: val_loss -0.6452 +2023-05-26 17:33:56.922143: Pseudo dice [0.9373, 0.8638, 0.9049] +2023-05-26 17:33:56.922232: Epoch time: 38.07 s +2023-05-26 17:33:58.959826: +2023-05-26 17:33:58.960229: Epoch 510 +2023-05-26 17:33:58.960429: Current learning rate: 0.00526 +2023-05-26 17:34:36.650538: train_loss -0.9582 +2023-05-26 17:34:36.650807: val_loss -0.6208 +2023-05-26 17:34:36.650980: Pseudo dice [0.9338, 0.8587, 0.8998] +2023-05-26 17:34:36.651070: Epoch time: 37.69 s +2023-05-26 17:34:38.155518: +2023-05-26 17:34:38.155701: Epoch 511 +2023-05-26 17:34:38.155826: Current learning rate: 0.00525 +2023-05-26 17:35:15.796018: train_loss -0.9584 +2023-05-26 17:35:15.796400: val_loss -0.6342 +2023-05-26 17:35:15.796538: Pseudo dice [0.9343, 0.8616, 0.9036] +2023-05-26 17:35:15.796633: Epoch time: 37.64 s +2023-05-26 17:35:17.331314: +2023-05-26 17:35:17.331496: Epoch 512 +2023-05-26 17:35:17.331623: Current learning rate: 0.00524 +2023-05-26 17:35:54.965229: train_loss -0.9585 +2023-05-26 17:35:54.965479: val_loss -0.6334 +2023-05-26 17:35:54.965600: Pseudo dice [0.9362, 0.8615, 0.9034] +2023-05-26 17:35:54.965704: Epoch time: 37.64 s +2023-05-26 17:35:56.476744: +2023-05-26 17:35:56.477233: Epoch 513 +2023-05-26 17:35:56.477462: Current learning rate: 0.00523 +2023-05-26 17:36:34.341349: train_loss -0.9585 +2023-05-26 17:36:34.341683: val_loss -0.631 +2023-05-26 17:36:34.341805: Pseudo dice [0.934, 0.86, 0.9047] +2023-05-26 17:36:34.341892: Epoch time: 37.87 s +2023-05-26 17:36:35.882719: +2023-05-26 17:36:35.882925: Epoch 514 +2023-05-26 17:36:35.883048: Current learning rate: 0.00522 +2023-05-26 17:37:13.659854: train_loss -0.959 +2023-05-26 17:37:13.660744: val_loss -0.625 +2023-05-26 17:37:13.660950: Pseudo dice [0.9351, 0.8579, 0.8978] +2023-05-26 17:37:13.661082: Epoch time: 37.78 s +2023-05-26 17:37:15.235335: +2023-05-26 17:37:15.235521: Epoch 515 +2023-05-26 17:37:15.235646: Current learning rate: 0.00521 +2023-05-26 17:37:52.725791: train_loss -0.9594 +2023-05-26 17:37:52.726029: val_loss -0.6319 +2023-05-26 17:37:52.726141: Pseudo dice [0.9358, 0.8628, 0.9009] +2023-05-26 17:37:52.726243: Epoch time: 37.49 s +2023-05-26 17:37:54.241992: +2023-05-26 17:37:54.242368: Epoch 516 +2023-05-26 17:37:54.242650: Current learning rate: 0.0052 +2023-05-26 17:38:32.052209: train_loss -0.9583 +2023-05-26 17:38:32.052512: val_loss -0.6265 +2023-05-26 17:38:32.052656: Pseudo dice [0.9349, 0.8605, 0.9015] +2023-05-26 17:38:32.052748: Epoch time: 37.81 s +2023-05-26 17:38:33.919879: +2023-05-26 17:38:33.920307: Epoch 517 +2023-05-26 17:38:33.920473: Current learning rate: 0.00519 +2023-05-26 17:39:12.260847: train_loss -0.9591 +2023-05-26 17:39:12.261122: val_loss -0.6332 +2023-05-26 17:39:12.261246: Pseudo dice [0.9362, 0.8614, 0.9009] +2023-05-26 17:39:12.261328: Epoch time: 38.34 s +2023-05-26 17:39:13.779419: +2023-05-26 17:39:13.779811: Epoch 518 +2023-05-26 17:39:13.780289: Current learning rate: 0.00518 +2023-05-26 17:39:51.062169: train_loss -0.9593 +2023-05-26 17:39:51.062442: val_loss -0.6294 +2023-05-26 17:39:51.062609: Pseudo dice [0.9365, 0.862, 0.8988] +2023-05-26 17:39:51.062696: Epoch time: 37.28 s +2023-05-26 17:39:52.665052: +2023-05-26 17:39:52.665554: Epoch 519 +2023-05-26 17:39:52.665695: Current learning rate: 0.00518 +2023-05-26 17:40:30.213697: train_loss -0.9585 +2023-05-26 17:40:30.214049: val_loss -0.6308 +2023-05-26 17:40:30.214314: Pseudo dice [0.936, 0.8616, 0.9015] +2023-05-26 17:40:30.214491: Epoch time: 37.55 s +2023-05-26 17:40:31.816228: +2023-05-26 17:40:31.816576: Epoch 520 +2023-05-26 17:40:31.816836: Current learning rate: 0.00517 +2023-05-26 17:41:09.686236: train_loss -0.9591 +2023-05-26 17:41:09.686470: val_loss -0.6283 +2023-05-26 17:41:09.686592: Pseudo dice [0.9353, 0.8615, 0.8974] +2023-05-26 17:41:09.686695: Epoch time: 37.87 s +2023-05-26 17:41:11.401677: +2023-05-26 17:41:11.401913: Epoch 521 +2023-05-26 17:41:11.402063: Current learning rate: 0.00516 +2023-05-26 17:41:48.972947: train_loss -0.9591 +2023-05-26 17:41:48.973231: val_loss -0.6345 +2023-05-26 17:41:48.973369: Pseudo dice [0.9364, 0.8607, 0.9027] +2023-05-26 17:41:48.973467: Epoch time: 37.57 s +2023-05-26 17:41:50.556406: +2023-05-26 17:41:50.556619: Epoch 522 +2023-05-26 17:41:50.556774: Current learning rate: 0.00515 +2023-05-26 17:42:28.144793: train_loss -0.9589 +2023-05-26 17:42:28.145066: val_loss -0.6267 +2023-05-26 17:42:28.145171: Pseudo dice [0.9364, 0.862, 0.9047] +2023-05-26 17:42:28.145257: Epoch time: 37.59 s +2023-05-26 17:42:29.646972: +2023-05-26 17:42:29.647144: Epoch 523 +2023-05-26 17:42:29.647261: Current learning rate: 0.00514 +2023-05-26 17:43:07.660300: train_loss -0.9594 +2023-05-26 17:43:07.660537: val_loss -0.6287 +2023-05-26 17:43:07.660648: Pseudo dice [0.9353, 0.8616, 0.9006] +2023-05-26 17:43:07.660744: Epoch time: 38.01 s +2023-05-26 17:43:09.355135: +2023-05-26 17:43:09.355329: Epoch 524 +2023-05-26 17:43:09.355444: Current learning rate: 0.00513 +2023-05-26 17:43:47.237202: train_loss -0.959 +2023-05-26 17:43:47.237434: val_loss -0.6292 +2023-05-26 17:43:47.237555: Pseudo dice [0.9369, 0.8624, 0.8969] +2023-05-26 17:43:47.237662: Epoch time: 37.88 s +2023-05-26 17:43:48.851300: +2023-05-26 17:43:48.851535: Epoch 525 +2023-05-26 17:43:48.851696: Current learning rate: 0.00512 +2023-05-26 17:44:26.590681: train_loss -0.9593 +2023-05-26 17:44:26.590999: val_loss -0.63 +2023-05-26 17:44:26.591105: Pseudo dice [0.9365, 0.8606, 0.8967] +2023-05-26 17:44:26.591236: Epoch time: 37.74 s +2023-05-26 17:44:28.286786: +2023-05-26 17:44:28.287216: Epoch 526 +2023-05-26 17:44:28.287682: Current learning rate: 0.00511 +2023-05-26 17:45:05.625129: train_loss -0.9599 +2023-05-26 17:45:05.625814: val_loss -0.6363 +2023-05-26 17:45:05.625952: Pseudo dice [0.9355, 0.8632, 0.9028] +2023-05-26 17:45:05.626044: Epoch time: 37.34 s +2023-05-26 17:45:07.201167: +2023-05-26 17:45:07.201393: Epoch 527 +2023-05-26 17:45:07.201528: Current learning rate: 0.0051 +2023-05-26 17:45:44.674871: train_loss -0.9597 +2023-05-26 17:45:44.675183: val_loss -0.6247 +2023-05-26 17:45:44.675291: Pseudo dice [0.9363, 0.8618, 0.897] +2023-05-26 17:45:44.675374: Epoch time: 37.48 s +2023-05-26 17:45:46.274323: +2023-05-26 17:45:46.274531: Epoch 528 +2023-05-26 17:45:46.274645: Current learning rate: 0.00509 +2023-05-26 17:46:23.992236: train_loss -0.9593 +2023-05-26 17:46:23.992506: val_loss -0.63 +2023-05-26 17:46:23.992644: Pseudo dice [0.9353, 0.8608, 0.9013] +2023-05-26 17:46:23.992738: Epoch time: 37.72 s +2023-05-26 17:46:25.620200: +2023-05-26 17:46:25.620386: Epoch 529 +2023-05-26 17:46:25.620504: Current learning rate: 0.00508 +2023-05-26 17:47:03.440641: train_loss -0.9587 +2023-05-26 17:47:03.440916: val_loss -0.6296 +2023-05-26 17:47:03.441076: Pseudo dice [0.9353, 0.8614, 0.8962] +2023-05-26 17:47:03.441228: Epoch time: 37.82 s +2023-05-26 17:47:05.371269: +2023-05-26 17:47:05.371467: Epoch 530 +2023-05-26 17:47:05.371596: Current learning rate: 0.00507 +2023-05-26 17:47:43.326048: train_loss -0.9589 +2023-05-26 17:47:43.326355: val_loss -0.6367 +2023-05-26 17:47:43.326497: Pseudo dice [0.9362, 0.8609, 0.9049] +2023-05-26 17:47:43.326598: Epoch time: 37.96 s +2023-05-26 17:47:44.948292: +2023-05-26 17:47:44.948607: Epoch 531 +2023-05-26 17:47:44.948835: Current learning rate: 0.00506 +2023-05-26 17:48:22.363337: train_loss -0.9591 +2023-05-26 17:48:22.363597: val_loss -0.6335 +2023-05-26 17:48:22.363719: Pseudo dice [0.9368, 0.8609, 0.9038] +2023-05-26 17:48:22.363824: Epoch time: 37.42 s +2023-05-26 17:48:23.835252: +2023-05-26 17:48:23.835454: Epoch 532 +2023-05-26 17:48:23.835583: Current learning rate: 0.00505 +2023-05-26 17:49:01.318318: train_loss -0.9593 +2023-05-26 17:49:01.318836: val_loss -0.6213 +2023-05-26 17:49:01.318950: Pseudo dice [0.9354, 0.8604, 0.9005] +2023-05-26 17:49:01.319043: Epoch time: 37.48 s +2023-05-26 17:49:03.053740: +2023-05-26 17:49:03.054210: Epoch 533 +2023-05-26 17:49:03.054736: Current learning rate: 0.00504 +2023-05-26 17:49:40.839119: train_loss -0.9594 +2023-05-26 17:49:40.839374: val_loss -0.6303 +2023-05-26 17:49:40.839510: Pseudo dice [0.9365, 0.8625, 0.8992] +2023-05-26 17:49:40.839600: Epoch time: 37.79 s +2023-05-26 17:49:42.589402: +2023-05-26 17:49:42.589610: Epoch 534 +2023-05-26 17:49:42.589765: Current learning rate: 0.00503 +2023-05-26 17:50:20.397887: train_loss -0.96 +2023-05-26 17:50:20.398175: val_loss -0.6311 +2023-05-26 17:50:20.398315: Pseudo dice [0.9384, 0.8642, 0.9002] +2023-05-26 17:50:20.398413: Epoch time: 37.81 s +2023-05-26 17:50:21.972662: +2023-05-26 17:50:21.972841: Epoch 535 +2023-05-26 17:50:21.972968: Current learning rate: 0.00502 +2023-05-26 17:50:59.550215: train_loss -0.9604 +2023-05-26 17:50:59.550493: val_loss -0.6239 +2023-05-26 17:50:59.550618: Pseudo dice [0.9345, 0.8609, 0.8973] +2023-05-26 17:50:59.550709: Epoch time: 37.58 s +2023-05-26 17:51:01.095326: +2023-05-26 17:51:01.095770: Epoch 536 +2023-05-26 17:51:01.096063: Current learning rate: 0.00501 +2023-05-26 17:51:38.874319: train_loss -0.9597 +2023-05-26 17:51:38.874560: val_loss -0.6291 +2023-05-26 17:51:38.874671: Pseudo dice [0.9358, 0.8625, 0.8977] +2023-05-26 17:51:38.874772: Epoch time: 37.78 s +2023-05-26 17:51:40.812768: +2023-05-26 17:51:40.812984: Epoch 537 +2023-05-26 17:51:40.813116: Current learning rate: 0.005 +2023-05-26 17:52:18.498515: train_loss -0.9599 +2023-05-26 17:52:18.498763: val_loss -0.6297 +2023-05-26 17:52:18.498929: Pseudo dice [0.9351, 0.8598, 0.9029] +2023-05-26 17:52:18.499029: Epoch time: 37.69 s +2023-05-26 17:52:19.964356: +2023-05-26 17:52:19.964749: Epoch 538 +2023-05-26 17:52:19.964959: Current learning rate: 0.00499 +2023-05-26 17:52:57.402618: train_loss -0.9605 +2023-05-26 17:52:57.402976: val_loss -0.63 +2023-05-26 17:52:57.403104: Pseudo dice [0.9361, 0.8617, 0.902] +2023-05-26 17:52:57.403395: Epoch time: 37.44 s +2023-05-26 17:52:59.093989: +2023-05-26 17:52:59.094213: Epoch 539 +2023-05-26 17:52:59.094595: Current learning rate: 0.00498 +2023-05-26 17:53:36.884504: train_loss -0.9604 +2023-05-26 17:53:36.884759: val_loss -0.627 +2023-05-26 17:53:36.884913: Pseudo dice [0.9365, 0.8626, 0.8975] +2023-05-26 17:53:36.885000: Epoch time: 37.79 s +2023-05-26 17:53:38.536909: +2023-05-26 17:53:38.537087: Epoch 540 +2023-05-26 17:53:38.537207: Current learning rate: 0.00497 +2023-05-26 17:54:16.401875: train_loss -0.96 +2023-05-26 17:54:16.402102: val_loss -0.629 +2023-05-26 17:54:16.402219: Pseudo dice [0.9373, 0.863, 0.9046] +2023-05-26 17:54:16.402327: Epoch time: 37.87 s +2023-05-26 17:54:17.977407: +2023-05-26 17:54:17.977832: Epoch 541 +2023-05-26 17:54:17.978097: Current learning rate: 0.00496 +2023-05-26 17:54:55.569910: train_loss -0.9606 +2023-05-26 17:54:55.570201: val_loss -0.6278 +2023-05-26 17:54:55.573619: Pseudo dice [0.9358, 0.8626, 0.9006] +2023-05-26 17:54:55.573736: Epoch time: 37.59 s +2023-05-26 17:54:57.359842: +2023-05-26 17:54:57.360183: Epoch 542 +2023-05-26 17:54:57.360391: Current learning rate: 0.00495 +2023-05-26 17:55:35.059966: train_loss -0.96 +2023-05-26 17:55:35.060247: val_loss -0.619 +2023-05-26 17:55:35.060382: Pseudo dice [0.9356, 0.8609, 0.8981] +2023-05-26 17:55:35.060479: Epoch time: 37.7 s +2023-05-26 17:55:36.916989: +2023-05-26 17:55:36.918089: Epoch 543 +2023-05-26 17:55:36.918338: Current learning rate: 0.00494 +2023-05-26 17:56:14.613236: train_loss -0.9601 +2023-05-26 17:56:14.613473: val_loss -0.6431 +2023-05-26 17:56:14.613584: Pseudo dice [0.9377, 0.8621, 0.9037] +2023-05-26 17:56:14.613678: Epoch time: 37.7 s +2023-05-26 17:56:16.239528: +2023-05-26 17:56:16.240156: Epoch 544 +2023-05-26 17:56:16.240716: Current learning rate: 0.00493 +2023-05-26 17:56:53.181123: train_loss -0.96 +2023-05-26 17:56:53.181434: val_loss -0.6356 +2023-05-26 17:56:53.181563: Pseudo dice [0.9362, 0.8614, 0.9042] +2023-05-26 17:56:53.181647: Epoch time: 36.94 s +2023-05-26 17:56:54.924725: +2023-05-26 17:56:54.925152: Epoch 545 +2023-05-26 17:56:54.925367: Current learning rate: 0.00492 +2023-05-26 17:57:32.659192: train_loss -0.9604 +2023-05-26 17:57:32.659450: val_loss -0.6287 +2023-05-26 17:57:32.660253: Pseudo dice [0.9358, 0.861, 0.9007] +2023-05-26 17:57:32.660403: Epoch time: 37.74 s +2023-05-26 17:57:34.160799: +2023-05-26 17:57:34.161005: Epoch 546 +2023-05-26 17:57:34.161141: Current learning rate: 0.00491 +2023-05-26 17:58:11.764617: train_loss -0.9601 +2023-05-26 17:58:11.764865: val_loss -0.6202 +2023-05-26 17:58:11.764975: Pseudo dice [0.936, 0.8603, 0.8968] +2023-05-26 17:58:11.765079: Epoch time: 37.6 s +2023-05-26 17:58:13.321999: +2023-05-26 17:58:13.322373: Epoch 547 +2023-05-26 17:58:13.322628: Current learning rate: 0.0049 +2023-05-26 17:58:51.230356: train_loss -0.9609 +2023-05-26 17:58:51.230609: val_loss -0.6326 +2023-05-26 17:58:51.230754: Pseudo dice [0.9357, 0.861, 0.9033] +2023-05-26 17:58:51.230871: Epoch time: 37.91 s +2023-05-26 17:58:52.890702: +2023-05-26 17:58:52.891186: Epoch 548 +2023-05-26 17:58:52.891486: Current learning rate: 0.00489 +2023-05-26 17:59:30.640697: train_loss -0.9607 +2023-05-26 17:59:30.641079: val_loss -0.634 +2023-05-26 17:59:30.641391: Pseudo dice [0.9352, 0.8615, 0.9052] +2023-05-26 17:59:30.641521: Epoch time: 37.75 s +2023-05-26 17:59:32.207770: +2023-05-26 17:59:32.207957: Epoch 549 +2023-05-26 17:59:32.208069: Current learning rate: 0.00488 +2023-05-26 18:00:09.967673: train_loss -0.9599 +2023-05-26 18:00:09.967962: val_loss -0.6375 +2023-05-26 18:00:09.968544: Pseudo dice [0.9367, 0.8623, 0.9028] +2023-05-26 18:00:09.968731: Epoch time: 37.76 s +2023-05-26 18:00:13.262065: +2023-05-26 18:00:13.262354: Epoch 550 +2023-05-26 18:00:13.262497: Current learning rate: 0.00487 +2023-05-26 18:00:50.981421: train_loss -0.9602 +2023-05-26 18:00:50.981742: val_loss -0.6318 +2023-05-26 18:00:50.981930: Pseudo dice [0.9348, 0.8608, 0.8999] +2023-05-26 18:00:50.982067: Epoch time: 37.72 s +2023-05-26 18:00:52.432574: +2023-05-26 18:00:52.432960: Epoch 551 +2023-05-26 18:00:52.433139: Current learning rate: 0.00486 +2023-05-26 18:01:30.356992: train_loss -0.96 +2023-05-26 18:01:30.357243: val_loss -0.6237 +2023-05-26 18:01:30.357376: Pseudo dice [0.9373, 0.8628, 0.8975] +2023-05-26 18:01:30.357503: Epoch time: 37.93 s +2023-05-26 18:01:31.914690: +2023-05-26 18:01:31.915168: Epoch 552 +2023-05-26 18:01:31.915289: Current learning rate: 0.00485 +2023-05-26 18:02:08.966541: train_loss -0.9606 +2023-05-26 18:02:08.966924: val_loss -0.6276 +2023-05-26 18:02:08.967043: Pseudo dice [0.9344, 0.86, 0.9026] +2023-05-26 18:02:08.967136: Epoch time: 37.05 s +2023-05-26 18:02:10.520187: +2023-05-26 18:02:10.520481: Epoch 553 +2023-05-26 18:02:10.520652: Current learning rate: 0.00484 +2023-05-26 18:02:48.195872: train_loss -0.9606 +2023-05-26 18:02:48.196240: val_loss -0.6243 +2023-05-26 18:02:48.196362: Pseudo dice [0.9354, 0.8593, 0.902] +2023-05-26 18:02:48.196462: Epoch time: 37.68 s +2023-05-26 18:02:49.740181: +2023-05-26 18:02:49.740669: Epoch 554 +2023-05-26 18:02:49.740863: Current learning rate: 0.00484 +2023-05-26 18:03:27.113002: train_loss -0.9607 +2023-05-26 18:03:27.113284: val_loss -0.6305 +2023-05-26 18:03:27.113627: Pseudo dice [0.9364, 0.8629, 0.901] +2023-05-26 18:03:27.113726: Epoch time: 37.37 s +2023-05-26 18:03:28.754604: +2023-05-26 18:03:28.755058: Epoch 555 +2023-05-26 18:03:28.755343: Current learning rate: 0.00483 +2023-05-26 18:04:06.729584: train_loss -0.9604 +2023-05-26 18:04:06.729860: val_loss -0.6301 +2023-05-26 18:04:06.729981: Pseudo dice [0.9362, 0.8624, 0.8997] +2023-05-26 18:04:06.730069: Epoch time: 37.98 s +2023-05-26 18:04:08.736095: +2023-05-26 18:04:08.736464: Epoch 556 +2023-05-26 18:04:08.736773: Current learning rate: 0.00482 +2023-05-26 18:04:46.648720: train_loss -0.9596 +2023-05-26 18:04:46.649090: val_loss -0.6364 +2023-05-26 18:04:46.649242: Pseudo dice [0.9363, 0.863, 0.9024] +2023-05-26 18:04:46.649380: Epoch time: 37.92 s +2023-05-26 18:04:48.330735: +2023-05-26 18:04:48.331315: Epoch 557 +2023-05-26 18:04:48.331724: Current learning rate: 0.00481 +2023-05-26 18:05:25.974377: train_loss -0.9607 +2023-05-26 18:05:25.974659: val_loss -0.636 +2023-05-26 18:05:25.974797: Pseudo dice [0.9355, 0.8632, 0.9031] +2023-05-26 18:05:25.974905: Epoch time: 37.64 s +2023-05-26 18:05:27.586151: +2023-05-26 18:05:27.586545: Epoch 558 +2023-05-26 18:05:27.586786: Current learning rate: 0.0048 +2023-05-26 18:06:05.165022: train_loss -0.9608 +2023-05-26 18:06:05.165292: val_loss -0.6337 +2023-05-26 18:06:05.165428: Pseudo dice [0.9358, 0.8625, 0.9029] +2023-05-26 18:06:05.165542: Epoch time: 37.58 s +2023-05-26 18:06:06.644864: +2023-05-26 18:06:06.645239: Epoch 559 +2023-05-26 18:06:06.645414: Current learning rate: 0.00479 +2023-05-26 18:06:44.354127: train_loss -0.9608 +2023-05-26 18:06:44.354390: val_loss -0.6253 +2023-05-26 18:06:44.354508: Pseudo dice [0.935, 0.8616, 0.9022] +2023-05-26 18:06:44.354607: Epoch time: 37.71 s +2023-05-26 18:06:45.838884: +2023-05-26 18:06:45.839060: Epoch 560 +2023-05-26 18:06:45.839173: Current learning rate: 0.00478 +2023-05-26 18:07:23.642952: train_loss -0.9609 +2023-05-26 18:07:23.643214: val_loss -0.6209 +2023-05-26 18:07:23.643333: Pseudo dice [0.9347, 0.8616, 0.902] +2023-05-26 18:07:23.643431: Epoch time: 37.81 s +2023-05-26 18:07:25.189143: +2023-05-26 18:07:25.189915: Epoch 561 +2023-05-26 18:07:25.190208: Current learning rate: 0.00477 +2023-05-26 18:08:02.548622: train_loss -0.9609 +2023-05-26 18:08:02.548958: val_loss -0.6254 +2023-05-26 18:08:02.549144: Pseudo dice [0.936, 0.8634, 0.9002] +2023-05-26 18:08:02.549290: Epoch time: 37.36 s +2023-05-26 18:08:04.119987: +2023-05-26 18:08:04.120140: Epoch 562 +2023-05-26 18:08:04.120279: Current learning rate: 0.00476 +2023-05-26 18:08:41.528598: train_loss -0.9614 +2023-05-26 18:08:41.529067: val_loss -0.6303 +2023-05-26 18:08:41.529222: Pseudo dice [0.9358, 0.8616, 0.9038] +2023-05-26 18:08:41.529343: Epoch time: 37.41 s +2023-05-26 18:08:43.466461: +2023-05-26 18:08:43.466634: Epoch 563 +2023-05-26 18:08:43.466762: Current learning rate: 0.00475 +2023-05-26 18:09:21.272733: train_loss -0.9614 +2023-05-26 18:09:21.272955: val_loss -0.6189 +2023-05-26 18:09:21.273085: Pseudo dice [0.9348, 0.8603, 0.8997] +2023-05-26 18:09:21.273188: Epoch time: 37.81 s +2023-05-26 18:09:22.988411: +2023-05-26 18:09:22.988640: Epoch 564 +2023-05-26 18:09:22.988764: Current learning rate: 0.00474 +2023-05-26 18:10:00.882490: train_loss -0.9608 +2023-05-26 18:10:00.882738: val_loss -0.6354 +2023-05-26 18:10:00.882881: Pseudo dice [0.9374, 0.8629, 0.9047] +2023-05-26 18:10:00.882992: Epoch time: 37.9 s +2023-05-26 18:10:02.452321: +2023-05-26 18:10:02.452871: Epoch 565 +2023-05-26 18:10:02.453264: Current learning rate: 0.00473 +2023-05-26 18:10:40.102392: train_loss -0.9609 +2023-05-26 18:10:40.102672: val_loss -0.6268 +2023-05-26 18:10:40.102829: Pseudo dice [0.9365, 0.8626, 0.9046] +2023-05-26 18:10:40.102957: Epoch time: 37.65 s +2023-05-26 18:10:41.636908: +2023-05-26 18:10:41.637298: Epoch 566 +2023-05-26 18:10:41.637573: Current learning rate: 0.00472 +2023-05-26 18:11:19.121187: train_loss -0.961 +2023-05-26 18:11:19.121449: val_loss -0.622 +2023-05-26 18:11:19.121565: Pseudo dice [0.9341, 0.8584, 0.8999] +2023-05-26 18:11:19.121668: Epoch time: 37.49 s +2023-05-26 18:11:20.607572: +2023-05-26 18:11:20.607948: Epoch 567 +2023-05-26 18:11:20.608132: Current learning rate: 0.00471 +2023-05-26 18:11:58.344483: train_loss -0.961 +2023-05-26 18:11:58.344761: val_loss -0.6193 +2023-05-26 18:11:58.344900: Pseudo dice [0.9369, 0.8619, 0.8994] +2023-05-26 18:11:58.345005: Epoch time: 37.74 s +2023-05-26 18:11:59.860491: +2023-05-26 18:11:59.860656: Epoch 568 +2023-05-26 18:11:59.860766: Current learning rate: 0.0047 +2023-05-26 18:12:37.499557: train_loss -0.9612 +2023-05-26 18:12:37.499851: val_loss -0.6314 +2023-05-26 18:12:37.499979: Pseudo dice [0.9364, 0.8623, 0.9051] +2023-05-26 18:12:37.500150: Epoch time: 37.64 s +2023-05-26 18:12:39.108067: +2023-05-26 18:12:39.108403: Epoch 569 +2023-05-26 18:12:39.108578: Current learning rate: 0.00469 +2023-05-26 18:13:16.547002: train_loss -0.9613 +2023-05-26 18:13:16.547280: val_loss -0.6367 +2023-05-26 18:13:16.547416: Pseudo dice [0.9368, 0.8637, 0.9034] +2023-05-26 18:13:16.547517: Epoch time: 37.44 s +2023-05-26 18:13:18.270449: +2023-05-26 18:13:18.270736: Epoch 570 +2023-05-26 18:13:18.270972: Current learning rate: 0.00468 +2023-05-26 18:13:55.877508: train_loss -0.9612 +2023-05-26 18:13:55.877748: val_loss -0.6261 +2023-05-26 18:13:55.877861: Pseudo dice [0.9366, 0.8629, 0.9002] +2023-05-26 18:13:55.877962: Epoch time: 37.61 s +2023-05-26 18:13:57.443450: +2023-05-26 18:13:57.443826: Epoch 571 +2023-05-26 18:13:57.443954: Current learning rate: 0.00467 +2023-05-26 18:14:35.283060: train_loss -0.9607 +2023-05-26 18:14:35.283304: val_loss -0.6294 +2023-05-26 18:14:35.283430: Pseudo dice [0.9359, 0.8616, 0.9042] +2023-05-26 18:14:35.283527: Epoch time: 37.84 s +2023-05-26 18:14:36.990993: +2023-05-26 18:14:36.991221: Epoch 572 +2023-05-26 18:14:36.991388: Current learning rate: 0.00466 +2023-05-26 18:15:14.615000: train_loss -0.961 +2023-05-26 18:15:14.615277: val_loss -0.6369 +2023-05-26 18:15:14.615421: Pseudo dice [0.9377, 0.863, 0.9061] +2023-05-26 18:15:14.615521: Epoch time: 37.63 s +2023-05-26 18:15:16.192208: +2023-05-26 18:15:16.192396: Epoch 573 +2023-05-26 18:15:16.192527: Current learning rate: 0.00465 +2023-05-26 18:15:53.815449: train_loss -0.9612 +2023-05-26 18:15:53.815713: val_loss -0.6304 +2023-05-26 18:15:53.815840: Pseudo dice [0.9369, 0.8634, 0.9038] +2023-05-26 18:15:53.815944: Epoch time: 37.62 s +2023-05-26 18:15:55.306326: +2023-05-26 18:15:55.306750: Epoch 574 +2023-05-26 18:15:55.307032: Current learning rate: 0.00464 +2023-05-26 18:16:33.055742: train_loss -0.9607 +2023-05-26 18:16:33.056017: val_loss -0.6395 +2023-05-26 18:16:33.056144: Pseudo dice [0.9355, 0.8628, 0.904] +2023-05-26 18:16:33.056257: Epoch time: 37.75 s +2023-05-26 18:16:34.639093: +2023-05-26 18:16:34.639298: Epoch 575 +2023-05-26 18:16:34.639426: Current learning rate: 0.00463 +2023-05-26 18:17:12.451462: train_loss -0.9611 +2023-05-26 18:17:12.451786: val_loss -0.6243 +2023-05-26 18:17:12.451976: Pseudo dice [0.9355, 0.8618, 0.9025] +2023-05-26 18:17:12.452131: Epoch time: 37.81 s +2023-05-26 18:17:14.210881: +2023-05-26 18:17:14.211051: Epoch 576 +2023-05-26 18:17:14.211185: Current learning rate: 0.00462 +2023-05-26 18:17:51.948707: train_loss -0.9619 +2023-05-26 18:17:51.948989: val_loss -0.6231 +2023-05-26 18:17:51.949138: Pseudo dice [0.9358, 0.8625, 0.9007] +2023-05-26 18:17:51.949239: Epoch time: 37.74 s +2023-05-26 18:17:53.681946: +2023-05-26 18:17:53.682595: Epoch 577 +2023-05-26 18:17:53.682815: Current learning rate: 0.00461 +2023-05-26 18:18:31.491886: train_loss -0.9615 +2023-05-26 18:18:31.492190: val_loss -0.6227 +2023-05-26 18:18:31.492317: Pseudo dice [0.9374, 0.8625, 0.8968] +2023-05-26 18:18:31.492412: Epoch time: 37.81 s +2023-05-26 18:18:32.883488: +2023-05-26 18:18:32.883653: Epoch 578 +2023-05-26 18:18:32.883791: Current learning rate: 0.0046 +2023-05-26 18:19:10.039275: train_loss -0.9617 +2023-05-26 18:19:10.039515: val_loss -0.6256 +2023-05-26 18:19:10.039635: Pseudo dice [0.936, 0.8613, 0.9011] +2023-05-26 18:19:10.039735: Epoch time: 37.16 s +2023-05-26 18:19:11.774500: +2023-05-26 18:19:11.774706: Epoch 579 +2023-05-26 18:19:11.774820: Current learning rate: 0.00459 +2023-05-26 18:19:49.511286: train_loss -0.9616 +2023-05-26 18:19:49.511580: val_loss -0.6261 +2023-05-26 18:19:49.511817: Pseudo dice [0.936, 0.863, 0.9043] +2023-05-26 18:19:49.512480: Epoch time: 37.74 s +2023-05-26 18:19:51.134450: +2023-05-26 18:19:51.134666: Epoch 580 +2023-05-26 18:19:51.134790: Current learning rate: 0.00458 +2023-05-26 18:20:28.742018: train_loss -0.9614 +2023-05-26 18:20:28.742319: val_loss -0.6234 +2023-05-26 18:20:28.742426: Pseudo dice [0.9365, 0.8626, 0.9035] +2023-05-26 18:20:28.742518: Epoch time: 37.61 s +2023-05-26 18:20:30.405154: +2023-05-26 18:20:30.405447: Epoch 581 +2023-05-26 18:20:30.405659: Current learning rate: 0.00457 +2023-05-26 18:21:08.117560: train_loss -0.9604 +2023-05-26 18:21:08.117783: val_loss -0.6337 +2023-05-26 18:21:08.117919: Pseudo dice [0.9338, 0.8597, 0.8994] +2023-05-26 18:21:08.118242: Epoch time: 37.71 s +2023-05-26 18:21:09.693251: +2023-05-26 18:21:09.693435: Epoch 582 +2023-05-26 18:21:09.693718: Current learning rate: 0.00456 +2023-05-26 18:21:47.485821: train_loss -0.9583 +2023-05-26 18:21:47.486052: val_loss -0.6215 +2023-05-26 18:21:47.486153: Pseudo dice [0.9346, 0.859, 0.8986] +2023-05-26 18:21:47.486243: Epoch time: 37.79 s +2023-05-26 18:21:49.370939: +2023-05-26 18:21:49.371280: Epoch 583 +2023-05-26 18:21:49.371593: Current learning rate: 0.00455 +2023-05-26 18:22:27.116400: train_loss -0.9595 +2023-05-26 18:22:27.116658: val_loss -0.6248 +2023-05-26 18:22:27.116791: Pseudo dice [0.9361, 0.8598, 0.9009] +2023-05-26 18:22:27.116899: Epoch time: 37.75 s +2023-05-26 18:22:28.668435: +2023-05-26 18:22:28.668768: Epoch 584 +2023-05-26 18:22:28.669167: Current learning rate: 0.00454 +2023-05-26 18:23:06.484508: train_loss -0.9606 +2023-05-26 18:23:06.484784: val_loss -0.6366 +2023-05-26 18:23:06.484921: Pseudo dice [0.9371, 0.8624, 0.9022] +2023-05-26 18:23:06.485014: Epoch time: 37.82 s +2023-05-26 18:23:08.113818: +2023-05-26 18:23:08.114015: Epoch 585 +2023-05-26 18:23:08.114141: Current learning rate: 0.00453 +2023-05-26 18:23:45.657322: train_loss -0.9609 +2023-05-26 18:23:45.657625: val_loss -0.6352 +2023-05-26 18:23:45.657765: Pseudo dice [0.9372, 0.8629, 0.9052] +2023-05-26 18:23:45.657881: Epoch time: 37.54 s +2023-05-26 18:23:47.307525: +2023-05-26 18:23:47.307797: Epoch 586 +2023-05-26 18:23:47.307933: Current learning rate: 0.00452 +2023-05-26 18:24:24.814082: train_loss -0.96 +2023-05-26 18:24:24.814366: val_loss -0.6351 +2023-05-26 18:24:24.814501: Pseudo dice [0.9359, 0.8607, 0.8992] +2023-05-26 18:24:24.814618: Epoch time: 37.51 s +2023-05-26 18:24:26.531274: +2023-05-26 18:24:26.532023: Epoch 587 +2023-05-26 18:24:26.532375: Current learning rate: 0.00451 +2023-05-26 18:25:04.347785: train_loss -0.9605 +2023-05-26 18:25:04.348178: val_loss -0.6242 +2023-05-26 18:25:04.348305: Pseudo dice [0.9352, 0.862, 0.9024] +2023-05-26 18:25:04.348401: Epoch time: 37.82 s +2023-05-26 18:25:05.971746: +2023-05-26 18:25:05.972317: Epoch 588 +2023-05-26 18:25:05.972561: Current learning rate: 0.0045 +2023-05-26 18:25:43.668247: train_loss -0.961 +2023-05-26 18:25:43.668505: val_loss -0.6322 +2023-05-26 18:25:43.668635: Pseudo dice [0.937, 0.864, 0.9008] +2023-05-26 18:25:43.668718: Epoch time: 37.7 s +2023-05-26 18:25:45.507160: +2023-05-26 18:25:45.507500: Epoch 589 +2023-05-26 18:25:45.507707: Current learning rate: 0.00449 +2023-05-26 18:26:23.084480: train_loss -0.9608 +2023-05-26 18:26:23.084831: val_loss -0.6321 +2023-05-26 18:26:23.084982: Pseudo dice [0.9351, 0.861, 0.9046] +2023-05-26 18:26:23.085111: Epoch time: 37.58 s +2023-05-26 18:26:24.848210: +2023-05-26 18:26:24.849058: Epoch 590 +2023-05-26 18:26:24.849355: Current learning rate: 0.00448 +2023-05-26 18:27:02.486930: train_loss -0.9605 +2023-05-26 18:27:02.487504: val_loss -0.6218 +2023-05-26 18:27:02.487921: Pseudo dice [0.9357, 0.8623, 0.8975] +2023-05-26 18:27:02.488102: Epoch time: 37.64 s +2023-05-26 18:27:04.140416: +2023-05-26 18:27:04.140665: Epoch 591 +2023-05-26 18:27:04.140832: Current learning rate: 0.00447 +2023-05-26 18:27:41.776833: train_loss -0.961 +2023-05-26 18:27:41.777169: val_loss -0.6314 +2023-05-26 18:27:41.777304: Pseudo dice [0.9367, 0.8631, 0.898] +2023-05-26 18:27:41.777406: Epoch time: 37.64 s +2023-05-26 18:27:43.419250: +2023-05-26 18:27:43.419817: Epoch 592 +2023-05-26 18:27:43.420170: Current learning rate: 0.00446 +2023-05-26 18:28:21.100327: train_loss -0.9613 +2023-05-26 18:28:21.100756: val_loss -0.6258 +2023-05-26 18:28:21.100936: Pseudo dice [0.9355, 0.8603, 0.9019] +2023-05-26 18:28:21.101032: Epoch time: 37.68 s +2023-05-26 18:28:22.632112: +2023-05-26 18:28:22.632286: Epoch 593 +2023-05-26 18:28:22.632411: Current learning rate: 0.00445 +2023-05-26 18:29:00.334091: train_loss -0.9618 +2023-05-26 18:29:00.334353: val_loss -0.6242 +2023-05-26 18:29:00.334486: Pseudo dice [0.936, 0.8628, 0.9012] +2023-05-26 18:29:00.334592: Epoch time: 37.7 s +2023-05-26 18:29:02.085113: +2023-05-26 18:29:02.085430: Epoch 594 +2023-05-26 18:29:02.085557: Current learning rate: 0.00444 +2023-05-26 18:29:39.709711: train_loss -0.9621 +2023-05-26 18:29:39.709992: val_loss -0.6183 +2023-05-26 18:29:39.710140: Pseudo dice [0.9346, 0.8591, 0.9045] +2023-05-26 18:29:39.710238: Epoch time: 37.63 s +2023-05-26 18:29:41.255664: +2023-05-26 18:29:41.255894: Epoch 595 +2023-05-26 18:29:41.256048: Current learning rate: 0.00443 +2023-05-26 18:30:18.990119: train_loss -0.9626 +2023-05-26 18:30:18.990359: val_loss -0.63 +2023-05-26 18:30:18.990474: Pseudo dice [0.9374, 0.8647, 0.9011] +2023-05-26 18:30:18.990572: Epoch time: 37.74 s +2023-05-26 18:30:21.038082: +2023-05-26 18:30:21.038666: Epoch 596 +2023-05-26 18:30:21.039009: Current learning rate: 0.00442 +2023-05-26 18:30:58.925015: train_loss -0.9622 +2023-05-26 18:30:58.925337: val_loss -0.6148 +2023-05-26 18:30:58.925503: Pseudo dice [0.9361, 0.8622, 0.9005] +2023-05-26 18:30:58.925620: Epoch time: 37.89 s +2023-05-26 18:31:00.529392: +2023-05-26 18:31:00.529581: Epoch 597 +2023-05-26 18:31:00.529699: Current learning rate: 0.00441 +2023-05-26 18:31:38.358809: train_loss -0.9625 +2023-05-26 18:31:38.359172: val_loss -0.6302 +2023-05-26 18:31:38.359309: Pseudo dice [0.9375, 0.8632, 0.903] +2023-05-26 18:31:38.359413: Epoch time: 37.83 s +2023-05-26 18:31:39.887985: +2023-05-26 18:31:39.888457: Epoch 598 +2023-05-26 18:31:39.888725: Current learning rate: 0.0044 +2023-05-26 18:32:17.550050: train_loss -0.963 +2023-05-26 18:32:17.550348: val_loss -0.6257 +2023-05-26 18:32:17.550509: Pseudo dice [0.9356, 0.8634, 0.901] +2023-05-26 18:32:17.550622: Epoch time: 37.66 s +2023-05-26 18:32:19.084265: +2023-05-26 18:32:19.084465: Epoch 599 +2023-05-26 18:32:19.084577: Current learning rate: 0.00439 +2023-05-26 18:32:56.729243: train_loss -0.9625 +2023-05-26 18:32:56.729529: val_loss -0.6186 +2023-05-26 18:32:56.729663: Pseudo dice [0.934, 0.8608, 0.9002] +2023-05-26 18:32:56.729763: Epoch time: 37.65 s +2023-05-26 18:33:00.077727: +2023-05-26 18:33:00.078160: Epoch 600 +2023-05-26 18:33:00.078288: Current learning rate: 0.00438 +2023-05-26 18:33:37.839096: train_loss -0.9628 +2023-05-26 18:33:37.839357: val_loss -0.6265 +2023-05-26 18:33:37.839499: Pseudo dice [0.9372, 0.8629, 0.9026] +2023-05-26 18:33:37.839590: Epoch time: 37.76 s +2023-05-26 18:33:39.474394: +2023-05-26 18:33:39.474551: Epoch 601 +2023-05-26 18:33:39.474659: Current learning rate: 0.00437 +2023-05-26 18:34:17.180068: train_loss -0.9628 +2023-05-26 18:34:17.180315: val_loss -0.6181 +2023-05-26 18:34:17.180449: Pseudo dice [0.9356, 0.8613, 0.9003] +2023-05-26 18:34:17.180550: Epoch time: 37.71 s +2023-05-26 18:34:18.905731: +2023-05-26 18:34:18.906074: Epoch 602 +2023-05-26 18:34:18.906279: Current learning rate: 0.00436 +2023-05-26 18:34:56.541621: train_loss -0.9627 +2023-05-26 18:34:56.542024: val_loss -0.6164 +2023-05-26 18:34:56.542395: Pseudo dice [0.935, 0.8607, 0.9005] +2023-05-26 18:34:56.542560: Epoch time: 37.64 s +2023-05-26 18:34:58.279059: +2023-05-26 18:34:58.279282: Epoch 603 +2023-05-26 18:34:58.279484: Current learning rate: 0.00435 +2023-05-26 18:35:35.923483: train_loss -0.9624 +2023-05-26 18:35:35.923751: val_loss -0.6225 +2023-05-26 18:35:35.923890: Pseudo dice [0.9364, 0.8614, 0.9021] +2023-05-26 18:35:35.923979: Epoch time: 37.65 s +2023-05-26 18:35:37.566830: +2023-05-26 18:35:37.567208: Epoch 604 +2023-05-26 18:35:37.567534: Current learning rate: 0.00434 +2023-05-26 18:36:15.386476: train_loss -0.962 +2023-05-26 18:36:15.386737: val_loss -0.6178 +2023-05-26 18:36:15.386910: Pseudo dice [0.9351, 0.8611, 0.8987] +2023-05-26 18:36:15.387015: Epoch time: 37.82 s +2023-05-26 18:36:16.956962: +2023-05-26 18:36:16.957127: Epoch 605 +2023-05-26 18:36:16.957241: Current learning rate: 0.00433 +2023-05-26 18:36:54.843738: train_loss -0.9623 +2023-05-26 18:36:54.844058: val_loss -0.622 +2023-05-26 18:36:54.844201: Pseudo dice [0.9366, 0.8626, 0.8982] +2023-05-26 18:36:54.844297: Epoch time: 37.89 s +2023-05-26 18:36:56.472528: +2023-05-26 18:36:56.472844: Epoch 606 +2023-05-26 18:36:56.473119: Current learning rate: 0.00432 +2023-05-26 18:37:34.436021: train_loss -0.9627 +2023-05-26 18:37:34.436373: val_loss -0.6266 +2023-05-26 18:37:34.436607: Pseudo dice [0.9369, 0.8644, 0.9012] +2023-05-26 18:37:34.436947: Epoch time: 37.96 s +2023-05-26 18:37:36.198075: +2023-05-26 18:37:36.198261: Epoch 607 +2023-05-26 18:37:36.198386: Current learning rate: 0.00431 +2023-05-26 18:38:13.855415: train_loss -0.9623 +2023-05-26 18:38:13.855669: val_loss -0.6244 +2023-05-26 18:38:13.855792: Pseudo dice [0.9362, 0.8632, 0.9012] +2023-05-26 18:38:13.855893: Epoch time: 37.66 s +2023-05-26 18:38:15.445938: +2023-05-26 18:38:15.446182: Epoch 608 +2023-05-26 18:38:15.446335: Current learning rate: 0.0043 +2023-05-26 18:38:53.373891: train_loss -0.9629 +2023-05-26 18:38:53.374151: val_loss -0.627 +2023-05-26 18:38:53.374269: Pseudo dice [0.936, 0.8638, 0.9026] +2023-05-26 18:38:53.374371: Epoch time: 37.93 s +2023-05-26 18:38:55.385768: +2023-05-26 18:38:55.386199: Epoch 609 +2023-05-26 18:38:55.386499: Current learning rate: 0.00429 +2023-05-26 18:39:33.215645: train_loss -0.9632 +2023-05-26 18:39:33.215869: val_loss -0.6297 +2023-05-26 18:39:33.215988: Pseudo dice [0.937, 0.864, 0.9048] +2023-05-26 18:39:33.216092: Epoch time: 37.83 s +2023-05-26 18:39:34.712130: +2023-05-26 18:39:34.712319: Epoch 610 +2023-05-26 18:39:34.712435: Current learning rate: 0.00429 +2023-05-26 18:40:13.384015: train_loss -0.963 +2023-05-26 18:40:13.384290: val_loss -0.6332 +2023-05-26 18:40:13.384411: Pseudo dice [0.9364, 0.8632, 0.9053] +2023-05-26 18:40:13.384520: Epoch time: 38.67 s +2023-05-26 18:40:14.923062: +2023-05-26 18:40:14.923261: Epoch 611 +2023-05-26 18:40:14.923381: Current learning rate: 0.00428 +2023-05-26 18:40:53.086648: train_loss -0.9631 +2023-05-26 18:40:53.086926: val_loss -0.6244 +2023-05-26 18:40:53.087041: Pseudo dice [0.9371, 0.8634, 0.9021] +2023-05-26 18:40:53.087140: Epoch time: 38.16 s +2023-05-26 18:40:54.668863: +2023-05-26 18:40:54.669271: Epoch 612 +2023-05-26 18:40:54.669397: Current learning rate: 0.00427 +2023-05-26 18:41:32.003196: train_loss -0.9632 +2023-05-26 18:41:32.003725: val_loss -0.6198 +2023-05-26 18:41:32.003868: Pseudo dice [0.9347, 0.8602, 0.9012] +2023-05-26 18:41:32.003973: Epoch time: 37.34 s +2023-05-26 18:41:33.620832: +2023-05-26 18:41:33.621179: Epoch 613 +2023-05-26 18:41:33.621424: Current learning rate: 0.00426 +2023-05-26 18:42:11.104104: train_loss -0.9635 +2023-05-26 18:42:11.104359: val_loss -0.6178 +2023-05-26 18:42:11.104495: Pseudo dice [0.9365, 0.8615, 0.901] +2023-05-26 18:42:11.104595: Epoch time: 37.48 s +2023-05-26 18:42:12.779594: +2023-05-26 18:42:12.780157: Epoch 614 +2023-05-26 18:42:12.780618: Current learning rate: 0.00425 +2023-05-26 18:42:50.635760: train_loss -0.9631 +2023-05-26 18:42:50.636105: val_loss -0.6285 +2023-05-26 18:42:50.636224: Pseudo dice [0.9371, 0.8627, 0.9017] +2023-05-26 18:42:50.636330: Epoch time: 37.86 s +2023-05-26 18:42:52.608926: +2023-05-26 18:42:52.609128: Epoch 615 +2023-05-26 18:42:52.609255: Current learning rate: 0.00424 +2023-05-26 18:43:30.375874: train_loss -0.9638 +2023-05-26 18:43:30.376144: val_loss -0.621 +2023-05-26 18:43:30.376269: Pseudo dice [0.9355, 0.8615, 0.9056] +2023-05-26 18:43:30.376363: Epoch time: 37.77 s +2023-05-26 18:43:31.973122: +2023-05-26 18:43:31.973332: Epoch 616 +2023-05-26 18:43:31.973461: Current learning rate: 0.00423 +2023-05-26 18:44:09.729512: train_loss -0.9633 +2023-05-26 18:44:09.729973: val_loss -0.6207 +2023-05-26 18:44:09.730078: Pseudo dice [0.9357, 0.8611, 0.9017] +2023-05-26 18:44:09.730180: Epoch time: 37.76 s +2023-05-26 18:44:11.413817: +2023-05-26 18:44:11.414037: Epoch 617 +2023-05-26 18:44:11.414183: Current learning rate: 0.00422 +2023-05-26 18:44:49.087008: train_loss -0.9629 +2023-05-26 18:44:49.087230: val_loss -0.6155 +2023-05-26 18:44:49.087351: Pseudo dice [0.9355, 0.8616, 0.9018] +2023-05-26 18:44:49.087452: Epoch time: 37.67 s +2023-05-26 18:44:50.657500: +2023-05-26 18:44:50.657676: Epoch 618 +2023-05-26 18:44:50.657830: Current learning rate: 0.00421 +2023-05-26 18:45:28.574095: train_loss -0.9634 +2023-05-26 18:45:28.575104: val_loss -0.6188 +2023-05-26 18:45:28.575411: Pseudo dice [0.9336, 0.8624, 0.9006] +2023-05-26 18:45:28.575857: Epoch time: 37.92 s +2023-05-26 18:45:30.360880: +2023-05-26 18:45:30.361191: Epoch 619 +2023-05-26 18:45:30.361341: Current learning rate: 0.0042 +2023-05-26 18:46:08.249377: train_loss -0.963 +2023-05-26 18:46:08.249807: val_loss -0.6245 +2023-05-26 18:46:08.249923: Pseudo dice [0.9359, 0.8617, 0.9052] +2023-05-26 18:46:08.250012: Epoch time: 37.89 s +2023-05-26 18:46:09.889632: +2023-05-26 18:46:09.889849: Epoch 620 +2023-05-26 18:46:09.889993: Current learning rate: 0.00419 +2023-05-26 18:46:47.676043: train_loss -0.9629 +2023-05-26 18:46:47.676324: val_loss -0.6267 +2023-05-26 18:46:47.676520: Pseudo dice [0.9364, 0.8625, 0.9047] +2023-05-26 18:46:47.676660: Epoch time: 37.79 s +2023-05-26 18:46:49.545682: +2023-05-26 18:46:49.546147: Epoch 621 +2023-05-26 18:46:49.546592: Current learning rate: 0.00418 +2023-05-26 18:47:28.601079: train_loss -0.963 +2023-05-26 18:47:28.601322: val_loss -0.624 +2023-05-26 18:47:28.601456: Pseudo dice [0.9355, 0.8609, 0.902] +2023-05-26 18:47:28.601570: Epoch time: 39.06 s +2023-05-26 18:47:30.488889: +2023-05-26 18:47:30.489293: Epoch 622 +2023-05-26 18:47:30.489601: Current learning rate: 0.00417 +2023-05-26 18:48:08.186489: train_loss -0.9633 +2023-05-26 18:48:08.186817: val_loss -0.6139 +2023-05-26 18:48:08.187015: Pseudo dice [0.9336, 0.8591, 0.9037] +2023-05-26 18:48:08.187117: Epoch time: 37.7 s +2023-05-26 18:48:09.885748: +2023-05-26 18:48:09.885971: Epoch 623 +2023-05-26 18:48:09.886090: Current learning rate: 0.00416 +2023-05-26 18:48:47.548648: train_loss -0.963 +2023-05-26 18:48:47.548928: val_loss -0.6271 +2023-05-26 18:48:47.549076: Pseudo dice [0.9366, 0.8624, 0.9018] +2023-05-26 18:48:47.549176: Epoch time: 37.66 s +2023-05-26 18:48:49.262322: +2023-05-26 18:48:49.262735: Epoch 624 +2023-05-26 18:48:49.262889: Current learning rate: 0.00415 +2023-05-26 18:49:26.971234: train_loss -0.9637 +2023-05-26 18:49:26.971482: val_loss -0.6172 +2023-05-26 18:49:26.971592: Pseudo dice [0.9348, 0.8605, 0.9022] +2023-05-26 18:49:26.971702: Epoch time: 37.71 s +2023-05-26 18:49:28.547574: +2023-05-26 18:49:28.547884: Epoch 625 +2023-05-26 18:49:28.548095: Current learning rate: 0.00414 +2023-05-26 18:50:06.336739: train_loss -0.9634 +2023-05-26 18:50:06.336985: val_loss -0.6116 +2023-05-26 18:50:06.337131: Pseudo dice [0.9335, 0.8572, 0.9046] +2023-05-26 18:50:06.337242: Epoch time: 37.79 s +2023-05-26 18:50:08.046071: +2023-05-26 18:50:08.046259: Epoch 626 +2023-05-26 18:50:08.046396: Current learning rate: 0.00413 +2023-05-26 18:50:46.268354: train_loss -0.9632 +2023-05-26 18:50:46.268615: val_loss -0.6251 +2023-05-26 18:50:46.268744: Pseudo dice [0.9361, 0.8611, 0.9059] +2023-05-26 18:50:46.268831: Epoch time: 38.22 s +2023-05-26 18:50:47.857720: +2023-05-26 18:50:47.857884: Epoch 627 +2023-05-26 18:50:47.857999: Current learning rate: 0.00412 +2023-05-26 18:51:25.749590: train_loss -0.9631 +2023-05-26 18:51:25.749856: val_loss -0.6214 +2023-05-26 18:51:25.749969: Pseudo dice [0.936, 0.8601, 0.9027] +2023-05-26 18:51:25.750046: Epoch time: 37.89 s +2023-05-26 18:51:27.699807: +2023-05-26 18:51:27.700050: Epoch 628 +2023-05-26 18:51:27.700201: Current learning rate: 0.00411 +2023-05-26 18:52:05.357097: train_loss -0.9631 +2023-05-26 18:52:05.357357: val_loss -0.6241 +2023-05-26 18:52:05.357664: Pseudo dice [0.9357, 0.8604, 0.9035] +2023-05-26 18:52:05.358002: Epoch time: 37.66 s +2023-05-26 18:52:06.944475: +2023-05-26 18:52:06.944655: Epoch 629 +2023-05-26 18:52:06.944763: Current learning rate: 0.0041 +2023-05-26 18:52:45.105005: train_loss -0.9625 +2023-05-26 18:52:45.105239: val_loss -0.6167 +2023-05-26 18:52:45.105357: Pseudo dice [0.935, 0.8591, 0.9017] +2023-05-26 18:52:45.105461: Epoch time: 38.16 s +2023-05-26 18:52:46.772220: +2023-05-26 18:52:46.772593: Epoch 630 +2023-05-26 18:52:46.772765: Current learning rate: 0.00409 +2023-05-26 18:53:24.482074: train_loss -0.9633 +2023-05-26 18:53:24.482360: val_loss -0.6257 +2023-05-26 18:53:24.482501: Pseudo dice [0.9378, 0.8631, 0.9045] +2023-05-26 18:53:24.482592: Epoch time: 37.71 s +2023-05-26 18:53:26.108135: +2023-05-26 18:53:26.108455: Epoch 631 +2023-05-26 18:53:26.108760: Current learning rate: 0.00408 +2023-05-26 18:54:03.834569: train_loss -0.9634 +2023-05-26 18:54:03.834857: val_loss -0.6247 +2023-05-26 18:54:03.834987: Pseudo dice [0.9369, 0.8614, 0.9028] +2023-05-26 18:54:03.835077: Epoch time: 37.73 s +2023-05-26 18:54:05.416435: +2023-05-26 18:54:05.416754: Epoch 632 +2023-05-26 18:54:05.417012: Current learning rate: 0.00407 +2023-05-26 18:54:43.212577: train_loss -0.9636 +2023-05-26 18:54:43.212800: val_loss -0.616 +2023-05-26 18:54:43.212906: Pseudo dice [0.937, 0.8603, 0.8999] +2023-05-26 18:54:43.212996: Epoch time: 37.8 s +2023-05-26 18:54:44.835748: +2023-05-26 18:54:44.836026: Epoch 633 +2023-05-26 18:54:44.836258: Current learning rate: 0.00406 +2023-05-26 18:55:22.577225: train_loss -0.9639 +2023-05-26 18:55:22.577559: val_loss -0.6192 +2023-05-26 18:55:22.577693: Pseudo dice [0.9361, 0.8597, 0.9035] +2023-05-26 18:55:22.577790: Epoch time: 37.74 s +2023-05-26 18:55:24.159592: +2023-05-26 18:55:24.160859: Epoch 634 +2023-05-26 18:55:24.161091: Current learning rate: 0.00405 +2023-05-26 18:56:01.753473: train_loss -0.964 +2023-05-26 18:56:01.753890: val_loss -0.6177 +2023-05-26 18:56:01.754164: Pseudo dice [0.9363, 0.861, 0.9038] +2023-05-26 18:56:01.754262: Epoch time: 37.6 s +2023-05-26 18:56:03.769341: +2023-05-26 18:56:03.769572: Epoch 635 +2023-05-26 18:56:03.769712: Current learning rate: 0.00404 +2023-05-26 18:56:41.538117: train_loss -0.9638 +2023-05-26 18:56:41.538498: val_loss -0.6182 +2023-05-26 18:56:41.538704: Pseudo dice [0.935, 0.8607, 0.9043] +2023-05-26 18:56:41.538884: Epoch time: 37.77 s +2023-05-26 18:56:43.424999: +2023-05-26 18:56:43.425218: Epoch 636 +2023-05-26 18:56:43.425356: Current learning rate: 0.00403 +2023-05-26 18:57:21.053647: train_loss -0.9641 +2023-05-26 18:57:21.053925: val_loss -0.6128 +2023-05-26 18:57:21.054044: Pseudo dice [0.9349, 0.8607, 0.8988] +2023-05-26 18:57:21.054128: Epoch time: 37.63 s +2023-05-26 18:57:22.815433: +2023-05-26 18:57:22.815693: Epoch 637 +2023-05-26 18:57:22.815909: Current learning rate: 0.00402 +2023-05-26 18:58:00.908278: train_loss -0.9635 +2023-05-26 18:58:00.908583: val_loss -0.6122 +2023-05-26 18:58:00.908707: Pseudo dice [0.9355, 0.8616, 0.897] +2023-05-26 18:58:00.908808: Epoch time: 38.09 s +2023-05-26 18:58:02.580932: +2023-05-26 18:58:02.581254: Epoch 638 +2023-05-26 18:58:02.581454: Current learning rate: 0.00401 +2023-05-26 18:58:40.044902: train_loss -0.9639 +2023-05-26 18:58:40.045227: val_loss -0.623 +2023-05-26 18:58:40.045363: Pseudo dice [0.9353, 0.8614, 0.9016] +2023-05-26 18:58:40.045466: Epoch time: 37.47 s +2023-05-26 18:58:41.748784: +2023-05-26 18:58:41.749004: Epoch 639 +2023-05-26 18:58:41.749147: Current learning rate: 0.004 +2023-05-26 18:59:19.341943: train_loss -0.9627 +2023-05-26 18:59:19.342422: val_loss -0.6194 +2023-05-26 18:59:19.342560: Pseudo dice [0.9353, 0.8613, 0.9029] +2023-05-26 18:59:19.342684: Epoch time: 37.59 s +2023-05-26 18:59:20.992776: +2023-05-26 18:59:20.993142: Epoch 640 +2023-05-26 18:59:20.993377: Current learning rate: 0.00399 +2023-05-26 18:59:58.865334: train_loss -0.9637 +2023-05-26 18:59:58.865672: val_loss -0.6214 +2023-05-26 18:59:58.865820: Pseudo dice [0.9361, 0.8635, 0.8999] +2023-05-26 18:59:58.865998: Epoch time: 37.87 s +2023-05-26 19:00:00.569960: +2023-05-26 19:00:00.570319: Epoch 641 +2023-05-26 19:00:00.570452: Current learning rate: 0.00398 +2023-05-26 19:00:38.159836: train_loss -0.9632 +2023-05-26 19:00:38.160071: val_loss -0.6146 +2023-05-26 19:00:38.160183: Pseudo dice [0.9356, 0.8626, 0.8991] +2023-05-26 19:00:38.160283: Epoch time: 37.59 s +2023-05-26 19:00:40.225621: +2023-05-26 19:00:40.225815: Epoch 642 +2023-05-26 19:00:40.225926: Current learning rate: 0.00397 +2023-05-26 19:01:17.838603: train_loss -0.964 +2023-05-26 19:01:17.838904: val_loss -0.6163 +2023-05-26 19:01:17.839053: Pseudo dice [0.9348, 0.8617, 0.8975] +2023-05-26 19:01:17.839159: Epoch time: 37.61 s +2023-05-26 19:01:19.539210: +2023-05-26 19:01:19.539495: Epoch 643 +2023-05-26 19:01:19.539662: Current learning rate: 0.00396 +2023-05-26 19:01:57.368442: train_loss -0.9635 +2023-05-26 19:01:57.368745: val_loss -0.6245 +2023-05-26 19:01:57.368924: Pseudo dice [0.9365, 0.8624, 0.9013] +2023-05-26 19:01:57.369074: Epoch time: 37.83 s +2023-05-26 19:01:59.128221: +2023-05-26 19:01:59.128404: Epoch 644 +2023-05-26 19:01:59.128525: Current learning rate: 0.00395 +2023-05-26 19:02:37.166382: train_loss -0.9626 +2023-05-26 19:02:37.166872: val_loss -0.623 +2023-05-26 19:02:37.167081: Pseudo dice [0.9374, 0.8636, 0.9009] +2023-05-26 19:02:37.167254: Epoch time: 38.04 s +2023-05-26 19:02:38.955142: +2023-05-26 19:02:38.955391: Epoch 645 +2023-05-26 19:02:38.955527: Current learning rate: 0.00394 +2023-05-26 19:03:16.324211: train_loss -0.9642 +2023-05-26 19:03:16.324561: val_loss -0.6276 +2023-05-26 19:03:16.324697: Pseudo dice [0.9372, 0.8636, 0.9046] +2023-05-26 19:03:16.324783: Epoch time: 37.37 s +2023-05-26 19:03:17.948325: +2023-05-26 19:03:17.948525: Epoch 646 +2023-05-26 19:03:17.948655: Current learning rate: 0.00393 +2023-05-26 19:03:55.748099: train_loss -0.964 +2023-05-26 19:03:55.748459: val_loss -0.6211 +2023-05-26 19:03:55.748580: Pseudo dice [0.9371, 0.8633, 0.9002] +2023-05-26 19:03:55.748669: Epoch time: 37.8 s +2023-05-26 19:03:57.429249: +2023-05-26 19:03:57.429424: Epoch 647 +2023-05-26 19:03:57.429531: Current learning rate: 0.00392 +2023-05-26 19:04:35.331441: train_loss -0.9629 +2023-05-26 19:04:35.331712: val_loss -0.6206 +2023-05-26 19:04:35.331835: Pseudo dice [0.9368, 0.8652, 0.8987] +2023-05-26 19:04:35.331922: Epoch time: 37.9 s +2023-05-26 19:04:37.301657: +2023-05-26 19:04:37.301912: Epoch 648 +2023-05-26 19:04:37.302055: Current learning rate: 0.00391 +2023-05-26 19:05:15.101328: train_loss -0.9639 +2023-05-26 19:05:15.101753: val_loss -0.6142 +2023-05-26 19:05:15.102001: Pseudo dice [0.9353, 0.8606, 0.8977] +2023-05-26 19:05:15.102203: Epoch time: 37.8 s +2023-05-26 19:05:16.727714: +2023-05-26 19:05:16.727933: Epoch 649 +2023-05-26 19:05:16.728062: Current learning rate: 0.0039 +2023-05-26 19:05:54.327547: train_loss -0.9638 +2023-05-26 19:05:54.327949: val_loss -0.6187 +2023-05-26 19:05:54.328190: Pseudo dice [0.9359, 0.8616, 0.9002] +2023-05-26 19:05:54.328383: Epoch time: 37.6 s +2023-05-26 19:05:57.610483: +2023-05-26 19:05:57.610675: Epoch 650 +2023-05-26 19:05:57.610793: Current learning rate: 0.00389 +2023-05-26 19:06:35.271551: train_loss -0.9642 +2023-05-26 19:06:35.271797: val_loss -0.6238 +2023-05-26 19:06:35.271914: Pseudo dice [0.9363, 0.8623, 0.9007] +2023-05-26 19:06:35.272016: Epoch time: 37.66 s +2023-05-26 19:06:36.879787: +2023-05-26 19:06:36.880099: Epoch 651 +2023-05-26 19:06:36.880284: Current learning rate: 0.00388 +2023-05-26 19:07:14.550768: train_loss -0.9644 +2023-05-26 19:07:14.551050: val_loss -0.6145 +2023-05-26 19:07:14.551171: Pseudo dice [0.9369, 0.8625, 0.8997] +2023-05-26 19:07:14.551270: Epoch time: 37.67 s +2023-05-26 19:07:16.111104: +2023-05-26 19:07:16.111424: Epoch 652 +2023-05-26 19:07:16.111725: Current learning rate: 0.00387 +2023-05-26 19:07:53.752764: train_loss -0.9647 +2023-05-26 19:07:53.753023: val_loss -0.6162 +2023-05-26 19:07:53.753155: Pseudo dice [0.9357, 0.861, 0.9055] +2023-05-26 19:07:53.753264: Epoch time: 37.64 s +2023-05-26 19:07:55.274529: +2023-05-26 19:07:55.274741: Epoch 653 +2023-05-26 19:07:55.274861: Current learning rate: 0.00386 +2023-05-26 19:08:32.695460: train_loss -0.9644 +2023-05-26 19:08:32.695692: val_loss -0.6196 +2023-05-26 19:08:32.695813: Pseudo dice [0.9352, 0.8624, 0.9008] +2023-05-26 19:08:32.695919: Epoch time: 37.42 s +2023-05-26 19:08:34.499244: +2023-05-26 19:08:34.499421: Epoch 654 +2023-05-26 19:08:34.499538: Current learning rate: 0.00385 +2023-05-26 19:09:11.909873: train_loss -0.9647 +2023-05-26 19:09:11.910170: val_loss -0.6108 +2023-05-26 19:09:11.910315: Pseudo dice [0.9352, 0.861, 0.9006] +2023-05-26 19:09:11.910415: Epoch time: 37.41 s +2023-05-26 19:09:13.458699: +2023-05-26 19:09:13.459116: Epoch 655 +2023-05-26 19:09:13.459289: Current learning rate: 0.00384 +2023-05-26 19:09:51.146969: train_loss -0.9643 +2023-05-26 19:09:51.147350: val_loss -0.6103 +2023-05-26 19:09:51.147489: Pseudo dice [0.9333, 0.8597, 0.9014] +2023-05-26 19:09:51.147591: Epoch time: 37.69 s +2023-05-26 19:09:52.878968: +2023-05-26 19:09:52.879282: Epoch 656 +2023-05-26 19:09:52.879485: Current learning rate: 0.00383 +2023-05-26 19:10:30.533205: train_loss -0.9642 +2023-05-26 19:10:30.533444: val_loss -0.6211 +2023-05-26 19:10:30.533566: Pseudo dice [0.9362, 0.8608, 0.9025] +2023-05-26 19:10:30.533690: Epoch time: 37.66 s +2023-05-26 19:10:32.218219: +2023-05-26 19:10:32.218556: Epoch 657 +2023-05-26 19:10:32.218786: Current learning rate: 0.00382 +2023-05-26 19:11:09.791931: train_loss -0.9648 +2023-05-26 19:11:09.792196: val_loss -0.6101 +2023-05-26 19:11:09.792313: Pseudo dice [0.9348, 0.8602, 0.9011] +2023-05-26 19:11:09.792402: Epoch time: 37.57 s +2023-05-26 19:11:11.449322: +2023-05-26 19:11:11.449805: Epoch 658 +2023-05-26 19:11:11.450071: Current learning rate: 0.00381 +2023-05-26 19:11:49.113136: train_loss -0.9652 +2023-05-26 19:11:49.113430: val_loss -0.6225 +2023-05-26 19:11:49.113572: Pseudo dice [0.9367, 0.8629, 0.9045] +2023-05-26 19:11:49.113683: Epoch time: 37.67 s +2023-05-26 19:11:50.862738: +2023-05-26 19:11:50.862931: Epoch 659 +2023-05-26 19:11:50.863072: Current learning rate: 0.0038 +2023-05-26 19:12:28.802715: train_loss -0.9645 +2023-05-26 19:12:28.803008: val_loss -0.6192 +2023-05-26 19:12:28.803144: Pseudo dice [0.9361, 0.8627, 0.9] +2023-05-26 19:12:28.803256: Epoch time: 37.94 s +2023-05-26 19:12:30.496235: +2023-05-26 19:12:30.496501: Epoch 660 +2023-05-26 19:12:30.496692: Current learning rate: 0.00379 +2023-05-26 19:13:08.191514: train_loss -0.9648 +2023-05-26 19:13:08.191815: val_loss -0.6139 +2023-05-26 19:13:08.191952: Pseudo dice [0.935, 0.8605, 0.9041] +2023-05-26 19:13:08.192065: Epoch time: 37.7 s +2023-05-26 19:13:10.185651: +2023-05-26 19:13:10.186072: Epoch 661 +2023-05-26 19:13:10.186330: Current learning rate: 0.00378 +2023-05-26 19:13:48.007839: train_loss -0.9655 +2023-05-26 19:13:48.008140: val_loss -0.6065 +2023-05-26 19:13:48.008273: Pseudo dice [0.9352, 0.8616, 0.8994] +2023-05-26 19:13:48.008367: Epoch time: 37.82 s +2023-05-26 19:13:49.699446: +2023-05-26 19:13:49.699826: Epoch 662 +2023-05-26 19:13:49.700095: Current learning rate: 0.00377 +2023-05-26 19:14:27.480077: train_loss -0.9653 +2023-05-26 19:14:27.480451: val_loss -0.6146 +2023-05-26 19:14:27.480648: Pseudo dice [0.9364, 0.8631, 0.9011] +2023-05-26 19:14:27.480807: Epoch time: 37.78 s +2023-05-26 19:14:29.318190: +2023-05-26 19:14:29.318727: Epoch 663 +2023-05-26 19:14:29.319004: Current learning rate: 0.00376 +2023-05-26 19:15:06.996260: train_loss -0.9648 +2023-05-26 19:15:06.996558: val_loss -0.6295 +2023-05-26 19:15:06.996692: Pseudo dice [0.9367, 0.8645, 0.9056] +2023-05-26 19:15:06.996781: Epoch time: 37.68 s +2023-05-26 19:15:08.675474: +2023-05-26 19:15:08.675703: Epoch 664 +2023-05-26 19:15:08.675841: Current learning rate: 0.00375 +2023-05-26 19:15:46.546105: train_loss -0.9653 +2023-05-26 19:15:46.546436: val_loss -0.6188 +2023-05-26 19:15:46.546567: Pseudo dice [0.9364, 0.8631, 0.9044] +2023-05-26 19:15:46.546659: Epoch time: 37.87 s +2023-05-26 19:15:48.218261: +2023-05-26 19:15:48.218485: Epoch 665 +2023-05-26 19:15:48.218912: Current learning rate: 0.00374 +2023-05-26 19:16:25.784758: train_loss -0.965 +2023-05-26 19:16:25.784986: val_loss -0.6142 +2023-05-26 19:16:25.785080: Pseudo dice [0.9363, 0.8626, 0.9013] +2023-05-26 19:16:25.785171: Epoch time: 37.57 s +2023-05-26 19:16:27.163482: +2023-05-26 19:16:27.163644: Epoch 666 +2023-05-26 19:16:27.163778: Current learning rate: 0.00373 +2023-05-26 19:17:04.808847: train_loss -0.9652 +2023-05-26 19:17:04.809101: val_loss -0.6156 +2023-05-26 19:17:04.809217: Pseudo dice [0.9359, 0.863, 0.9023] +2023-05-26 19:17:04.809320: Epoch time: 37.65 s +2023-05-26 19:17:06.547554: +2023-05-26 19:17:06.547868: Epoch 667 +2023-05-26 19:17:06.548040: Current learning rate: 0.00372 +2023-05-26 19:17:44.346863: train_loss -0.9654 +2023-05-26 19:17:44.347141: val_loss -0.6202 +2023-05-26 19:17:44.347279: Pseudo dice [0.9358, 0.8638, 0.9015] +2023-05-26 19:17:44.347368: Epoch time: 37.8 s +2023-05-26 19:17:46.295302: +2023-05-26 19:17:46.295786: Epoch 668 +2023-05-26 19:17:46.295923: Current learning rate: 0.00371 +2023-05-26 19:18:23.932760: train_loss -0.9654 +2023-05-26 19:18:23.933038: val_loss -0.6139 +2023-05-26 19:18:23.933230: Pseudo dice [0.9357, 0.863, 0.9052] +2023-05-26 19:18:23.933344: Epoch time: 37.64 s +2023-05-26 19:18:25.632492: +2023-05-26 19:18:25.632804: Epoch 669 +2023-05-26 19:18:25.632933: Current learning rate: 0.0037 +2023-05-26 19:19:03.351723: train_loss -0.9652 +2023-05-26 19:19:03.351998: val_loss -0.6069 +2023-05-26 19:19:03.352123: Pseudo dice [0.9356, 0.8611, 0.9015] +2023-05-26 19:19:03.352212: Epoch time: 37.72 s +2023-05-26 19:19:04.971676: +2023-05-26 19:19:04.972161: Epoch 670 +2023-05-26 19:19:04.972805: Current learning rate: 0.00369 +2023-05-26 19:19:42.936683: train_loss -0.9653 +2023-05-26 19:19:42.936980: val_loss -0.6061 +2023-05-26 19:19:42.937107: Pseudo dice [0.935, 0.8591, 0.901] +2023-05-26 19:19:42.937200: Epoch time: 37.97 s +2023-05-26 19:19:44.580324: +2023-05-26 19:19:44.580730: Epoch 671 +2023-05-26 19:19:44.580967: Current learning rate: 0.00368 +2023-05-26 19:20:22.261313: train_loss -0.9651 +2023-05-26 19:20:22.261677: val_loss -0.6172 +2023-05-26 19:20:22.262782: Pseudo dice [0.937, 0.8635, 0.9029] +2023-05-26 19:20:22.263054: Epoch time: 37.68 s +2023-05-26 19:20:23.887007: +2023-05-26 19:20:23.887680: Epoch 672 +2023-05-26 19:20:23.887907: Current learning rate: 0.00367 +2023-05-26 19:21:01.829915: train_loss -0.9654 +2023-05-26 19:21:01.830186: val_loss -0.6193 +2023-05-26 19:21:01.830611: Pseudo dice [0.9368, 0.8636, 0.9029] +2023-05-26 19:21:01.830717: Epoch time: 37.94 s +2023-05-26 19:21:03.530909: +2023-05-26 19:21:03.531738: Epoch 673 +2023-05-26 19:21:03.531883: Current learning rate: 0.00366 +2023-05-26 19:21:41.318270: train_loss -0.9652 +2023-05-26 19:21:41.318791: val_loss -0.627 +2023-05-26 19:21:41.319203: Pseudo dice [0.9381, 0.8633, 0.906] +2023-05-26 19:21:41.319333: Epoch time: 37.79 s +2023-05-26 19:21:43.351168: +2023-05-26 19:21:43.351372: Epoch 674 +2023-05-26 19:21:43.351493: Current learning rate: 0.00365 +2023-05-26 19:22:20.877713: train_loss -0.9652 +2023-05-26 19:22:20.877946: val_loss -0.6145 +2023-05-26 19:22:20.878051: Pseudo dice [0.9368, 0.8625, 0.9014] +2023-05-26 19:22:20.878155: Epoch time: 37.53 s +2023-05-26 19:22:22.444731: +2023-05-26 19:22:22.444935: Epoch 675 +2023-05-26 19:22:22.445084: Current learning rate: 0.00364 +2023-05-26 19:23:00.012751: train_loss -0.9654 +2023-05-26 19:23:00.013027: val_loss -0.6123 +2023-05-26 19:23:00.013147: Pseudo dice [0.9365, 0.8606, 0.9014] +2023-05-26 19:23:00.013240: Epoch time: 37.57 s +2023-05-26 19:23:01.726591: +2023-05-26 19:23:01.726960: Epoch 676 +2023-05-26 19:23:01.727185: Current learning rate: 0.00363 +2023-05-26 19:23:39.401693: train_loss -0.9646 +2023-05-26 19:23:39.402051: val_loss -0.6136 +2023-05-26 19:23:39.402217: Pseudo dice [0.9361, 0.8614, 0.902] +2023-05-26 19:23:39.402343: Epoch time: 37.68 s +2023-05-26 19:23:40.984993: +2023-05-26 19:23:40.985412: Epoch 677 +2023-05-26 19:23:40.985633: Current learning rate: 0.00362 +2023-05-26 19:24:19.248850: train_loss -0.9649 +2023-05-26 19:24:19.249132: val_loss -0.6161 +2023-05-26 19:24:19.249274: Pseudo dice [0.9351, 0.86, 0.9026] +2023-05-26 19:24:19.249381: Epoch time: 38.27 s +2023-05-26 19:24:20.921363: +2023-05-26 19:24:20.921710: Epoch 678 +2023-05-26 19:24:20.921856: Current learning rate: 0.00361 +2023-05-26 19:24:58.691452: train_loss -0.9653 +2023-05-26 19:24:58.691715: val_loss -0.6303 +2023-05-26 19:24:58.691846: Pseudo dice [0.9378, 0.8627, 0.9069] +2023-05-26 19:24:58.691944: Epoch time: 37.77 s +2023-05-26 19:25:00.318875: +2023-05-26 19:25:00.319054: Epoch 679 +2023-05-26 19:25:00.319180: Current learning rate: 0.0036 +2023-05-26 19:25:37.391368: train_loss -0.9656 +2023-05-26 19:25:37.391642: val_loss -0.6118 +2023-05-26 19:25:37.391772: Pseudo dice [0.9374, 0.8628, 0.9004] +2023-05-26 19:25:37.392623: Epoch time: 37.07 s +2023-05-26 19:25:39.301656: +2023-05-26 19:25:39.301987: Epoch 680 +2023-05-26 19:25:39.302241: Current learning rate: 0.00359 +2023-05-26 19:26:17.355155: train_loss -0.965 +2023-05-26 19:26:17.355379: val_loss -0.6203 +2023-05-26 19:26:17.355496: Pseudo dice [0.9375, 0.8633, 0.9037] +2023-05-26 19:26:17.355599: Epoch time: 38.05 s +2023-05-26 19:26:18.941633: +2023-05-26 19:26:18.942038: Epoch 681 +2023-05-26 19:26:18.942212: Current learning rate: 0.00358 +2023-05-26 19:26:56.636566: train_loss -0.9657 +2023-05-26 19:26:56.636822: val_loss -0.61 +2023-05-26 19:26:56.636948: Pseudo dice [0.9361, 0.8621, 0.9002] +2023-05-26 19:26:56.637238: Epoch time: 37.7 s +2023-05-26 19:26:58.317814: +2023-05-26 19:26:58.318032: Epoch 682 +2023-05-26 19:26:58.318151: Current learning rate: 0.00357 +2023-05-26 19:27:36.018699: train_loss -0.9657 +2023-05-26 19:27:36.019010: val_loss -0.6108 +2023-05-26 19:27:36.019144: Pseudo dice [0.9354, 0.8613, 0.902] +2023-05-26 19:27:36.019278: Epoch time: 37.7 s +2023-05-26 19:27:37.728835: +2023-05-26 19:27:37.729019: Epoch 683 +2023-05-26 19:27:37.729154: Current learning rate: 0.00356 +2023-05-26 19:28:15.478458: train_loss -0.9654 +2023-05-26 19:28:15.478986: val_loss -0.6071 +2023-05-26 19:28:15.479161: Pseudo dice [0.9364, 0.8614, 0.9017] +2023-05-26 19:28:15.479264: Epoch time: 37.75 s +2023-05-26 19:28:17.083197: +2023-05-26 19:28:17.083378: Epoch 684 +2023-05-26 19:28:17.083493: Current learning rate: 0.00355 +2023-05-26 19:28:54.795335: train_loss -0.9654 +2023-05-26 19:28:54.795558: val_loss -0.6161 +2023-05-26 19:28:54.795671: Pseudo dice [0.9373, 0.8621, 0.9024] +2023-05-26 19:28:54.795774: Epoch time: 37.71 s +2023-05-26 19:28:56.429052: +2023-05-26 19:28:56.429448: Epoch 685 +2023-05-26 19:28:56.429754: Current learning rate: 0.00354 +2023-05-26 19:29:34.385234: train_loss -0.9654 +2023-05-26 19:29:34.385468: val_loss -0.6201 +2023-05-26 19:29:34.385580: Pseudo dice [0.9365, 0.8643, 0.9037] +2023-05-26 19:29:34.385682: Epoch time: 37.96 s +2023-05-26 19:29:35.884372: +2023-05-26 19:29:35.884647: Epoch 686 +2023-05-26 19:29:35.884783: Current learning rate: 0.00353 +2023-05-26 19:30:13.728651: train_loss -0.9653 +2023-05-26 19:30:13.728902: val_loss -0.625 +2023-05-26 19:30:13.729014: Pseudo dice [0.9374, 0.8639, 0.9069] +2023-05-26 19:30:13.729111: Epoch time: 37.85 s +2023-05-26 19:30:15.859932: +2023-05-26 19:30:15.860398: Epoch 687 +2023-05-26 19:30:15.860745: Current learning rate: 0.00352 +2023-05-26 19:30:53.830830: train_loss -0.9655 +2023-05-26 19:30:53.831220: val_loss -0.6227 +2023-05-26 19:30:53.831351: Pseudo dice [0.9381, 0.8641, 0.9027] +2023-05-26 19:30:53.831448: Epoch time: 37.97 s +2023-05-26 19:30:55.561075: +2023-05-26 19:30:55.561294: Epoch 688 +2023-05-26 19:30:55.561423: Current learning rate: 0.00351 +2023-05-26 19:31:33.008927: train_loss -0.9657 +2023-05-26 19:31:33.009211: val_loss -0.6237 +2023-05-26 19:31:33.009340: Pseudo dice [0.9361, 0.8622, 0.9042] +2023-05-26 19:31:33.009438: Epoch time: 37.45 s +2023-05-26 19:31:34.649556: +2023-05-26 19:31:34.649903: Epoch 689 +2023-05-26 19:31:34.650141: Current learning rate: 0.0035 +2023-05-26 19:32:12.164125: train_loss -0.9652 +2023-05-26 19:32:12.164410: val_loss -0.6243 +2023-05-26 19:32:12.164520: Pseudo dice [0.9382, 0.8644, 0.9014] +2023-05-26 19:32:12.164603: Epoch time: 37.52 s +2023-05-26 19:32:13.818173: +2023-05-26 19:32:13.818375: Epoch 690 +2023-05-26 19:32:13.818504: Current learning rate: 0.00349 +2023-05-26 19:32:51.616299: train_loss -0.9653 +2023-05-26 19:32:51.616583: val_loss -0.6127 +2023-05-26 19:32:51.616720: Pseudo dice [0.9364, 0.8611, 0.9008] +2023-05-26 19:32:51.616818: Epoch time: 37.8 s +2023-05-26 19:32:53.364622: +2023-05-26 19:32:53.364966: Epoch 691 +2023-05-26 19:32:53.365205: Current learning rate: 0.00348 +2023-05-26 19:33:31.337106: train_loss -0.9658 +2023-05-26 19:33:31.337719: val_loss -0.6136 +2023-05-26 19:33:31.337945: Pseudo dice [0.9364, 0.8633, 0.9039] +2023-05-26 19:33:31.338100: Epoch time: 37.97 s +2023-05-26 19:33:33.152769: +2023-05-26 19:33:33.152939: Epoch 692 +2023-05-26 19:33:33.153062: Current learning rate: 0.00346 +2023-05-26 19:34:10.902300: train_loss -0.9658 +2023-05-26 19:34:10.902589: val_loss -0.6137 +2023-05-26 19:34:10.902706: Pseudo dice [0.9368, 0.8608, 0.9016] +2023-05-26 19:34:10.902800: Epoch time: 37.75 s +2023-05-26 19:34:12.796961: +2023-05-26 19:34:12.797153: Epoch 693 +2023-05-26 19:34:12.797273: Current learning rate: 0.00345 +2023-05-26 19:34:50.625618: train_loss -0.9661 +2023-05-26 19:34:50.625938: val_loss -0.6025 +2023-05-26 19:34:50.626052: Pseudo dice [0.9367, 0.862, 0.8977] +2023-05-26 19:34:50.626135: Epoch time: 37.83 s +2023-05-26 19:34:52.297091: +2023-05-26 19:34:52.297718: Epoch 694 +2023-05-26 19:34:52.297864: Current learning rate: 0.00344 +2023-05-26 19:35:30.002669: train_loss -0.9658 +2023-05-26 19:35:30.002981: val_loss -0.608 +2023-05-26 19:35:30.003114: Pseudo dice [0.9353, 0.8621, 0.9025] +2023-05-26 19:35:30.003237: Epoch time: 37.71 s +2023-05-26 19:35:31.659353: +2023-05-26 19:35:31.659555: Epoch 695 +2023-05-26 19:35:31.659679: Current learning rate: 0.00343 +2023-05-26 19:36:09.667772: train_loss -0.9661 +2023-05-26 19:36:09.668040: val_loss -0.6116 +2023-05-26 19:36:09.668152: Pseudo dice [0.9348, 0.8621, 0.9022] +2023-05-26 19:36:09.668254: Epoch time: 38.01 s +2023-05-26 19:36:11.309199: +2023-05-26 19:36:11.309428: Epoch 696 +2023-05-26 19:36:11.309534: Current learning rate: 0.00342 +2023-05-26 19:36:48.900844: train_loss -0.9661 +2023-05-26 19:36:48.901108: val_loss -0.6134 +2023-05-26 19:36:48.901236: Pseudo dice [0.937, 0.8626, 0.9039] +2023-05-26 19:36:48.901407: Epoch time: 37.59 s +2023-05-26 19:36:50.494408: +2023-05-26 19:36:50.494618: Epoch 697 +2023-05-26 19:36:50.494761: Current learning rate: 0.00341 +2023-05-26 19:37:28.307976: train_loss -0.9664 +2023-05-26 19:37:28.308270: val_loss -0.6124 +2023-05-26 19:37:28.308430: Pseudo dice [0.9364, 0.8613, 0.906] +2023-05-26 19:37:28.308528: Epoch time: 37.81 s +2023-05-26 19:37:29.945626: +2023-05-26 19:37:29.946239: Epoch 698 +2023-05-26 19:37:29.946388: Current learning rate: 0.0034 +2023-05-26 19:38:07.682423: train_loss -0.9662 +2023-05-26 19:38:07.682771: val_loss -0.6148 +2023-05-26 19:38:07.682914: Pseudo dice [0.9373, 0.8639, 0.9028] +2023-05-26 19:38:07.683011: Epoch time: 37.74 s +2023-05-26 19:38:09.664350: +2023-05-26 19:38:09.664787: Epoch 699 +2023-05-26 19:38:09.664973: Current learning rate: 0.00339 +2023-05-26 19:38:47.475094: train_loss -0.9671 +2023-05-26 19:38:47.475807: val_loss -0.6129 +2023-05-26 19:38:47.475948: Pseudo dice [0.9356, 0.863, 0.906] +2023-05-26 19:38:47.476047: Epoch time: 37.81 s +2023-05-26 19:38:50.564549: +2023-05-26 19:38:50.565416: Epoch 700 +2023-05-26 19:38:50.565957: Current learning rate: 0.00338 +2023-05-26 19:39:28.619404: train_loss -0.9658 +2023-05-26 19:39:28.619724: val_loss -0.6166 +2023-05-26 19:39:28.619853: Pseudo dice [0.937, 0.8631, 0.9042] +2023-05-26 19:39:28.619945: Epoch time: 38.06 s +2023-05-26 19:39:30.323067: +2023-05-26 19:39:30.323402: Epoch 701 +2023-05-26 19:39:30.323601: Current learning rate: 0.00337 +2023-05-26 19:40:08.060916: train_loss -0.9658 +2023-05-26 19:40:08.061154: val_loss -0.6114 +2023-05-26 19:40:08.061275: Pseudo dice [0.935, 0.862, 0.9033] +2023-05-26 19:40:08.061378: Epoch time: 37.74 s +2023-05-26 19:40:09.782072: +2023-05-26 19:40:09.782523: Epoch 702 +2023-05-26 19:40:09.782715: Current learning rate: 0.00336 +2023-05-26 19:40:47.444337: train_loss -0.9662 +2023-05-26 19:40:47.444600: val_loss -0.608 +2023-05-26 19:40:47.444706: Pseudo dice [0.9355, 0.8604, 0.9044] +2023-05-26 19:40:47.444805: Epoch time: 37.66 s +2023-05-26 19:40:49.028456: +2023-05-26 19:40:49.028672: Epoch 703 +2023-05-26 19:40:49.028809: Current learning rate: 0.00335 +2023-05-26 19:41:26.774296: train_loss -0.9661 +2023-05-26 19:41:26.774530: val_loss -0.6148 +2023-05-26 19:41:26.774642: Pseudo dice [0.9374, 0.8642, 0.9018] +2023-05-26 19:41:26.774743: Epoch time: 37.75 s +2023-05-26 19:41:28.496855: +2023-05-26 19:41:28.497026: Epoch 704 +2023-05-26 19:41:28.497139: Current learning rate: 0.00334 +2023-05-26 19:42:05.806523: train_loss -0.9667 +2023-05-26 19:42:05.806803: val_loss -0.6119 +2023-05-26 19:42:05.806963: Pseudo dice [0.9381, 0.8642, 0.9034] +2023-05-26 19:42:05.807056: Epoch time: 37.31 s +2023-05-26 19:42:07.647829: +2023-05-26 19:42:07.648484: Epoch 705 +2023-05-26 19:42:07.648616: Current learning rate: 0.00333 +2023-05-26 19:42:46.594539: train_loss -0.9663 +2023-05-26 19:42:46.594815: val_loss -0.6137 +2023-05-26 19:42:46.594980: Pseudo dice [0.9368, 0.8629, 0.9032] +2023-05-26 19:42:46.595082: Epoch time: 38.95 s +2023-05-26 19:42:48.285494: +2023-05-26 19:42:48.285698: Epoch 706 +2023-05-26 19:42:48.285828: Current learning rate: 0.00332 +2023-05-26 19:43:25.921957: train_loss -0.9666 +2023-05-26 19:43:25.922204: val_loss -0.6137 +2023-05-26 19:43:25.922334: Pseudo dice [0.9353, 0.8625, 0.9044] +2023-05-26 19:43:25.922429: Epoch time: 37.64 s +2023-05-26 19:43:27.570783: +2023-05-26 19:43:27.571189: Epoch 707 +2023-05-26 19:43:27.571480: Current learning rate: 0.00331 +2023-05-26 19:44:05.504790: train_loss -0.9674 +2023-05-26 19:44:05.505065: val_loss -0.6107 +2023-05-26 19:44:05.505191: Pseudo dice [0.9367, 0.8627, 0.9024] +2023-05-26 19:44:05.505283: Epoch time: 37.94 s +2023-05-26 19:44:07.065807: +2023-05-26 19:44:07.066147: Epoch 708 +2023-05-26 19:44:07.066335: Current learning rate: 0.0033 +2023-05-26 19:44:44.753752: train_loss -0.9672 +2023-05-26 19:44:44.754020: val_loss -0.612 +2023-05-26 19:44:44.754136: Pseudo dice [0.9365, 0.8631, 0.899] +2023-05-26 19:44:44.754234: Epoch time: 37.69 s +2023-05-26 19:44:46.480404: +2023-05-26 19:44:46.480579: Epoch 709 +2023-05-26 19:44:46.480695: Current learning rate: 0.00329 +2023-05-26 19:45:24.309883: train_loss -0.9664 +2023-05-26 19:45:24.310117: val_loss -0.6023 +2023-05-26 19:45:24.310232: Pseudo dice [0.9349, 0.8596, 0.9009] +2023-05-26 19:45:24.310351: Epoch time: 37.83 s +2023-05-26 19:45:26.042600: +2023-05-26 19:45:26.042798: Epoch 710 +2023-05-26 19:45:26.042956: Current learning rate: 0.00328 +2023-05-26 19:46:03.637594: train_loss -0.9661 +2023-05-26 19:46:03.638125: val_loss -0.6206 +2023-05-26 19:46:03.638309: Pseudo dice [0.9367, 0.8625, 0.9039] +2023-05-26 19:46:03.638460: Epoch time: 37.6 s +2023-05-26 19:46:05.269962: +2023-05-26 19:46:05.270159: Epoch 711 +2023-05-26 19:46:05.270287: Current learning rate: 0.00327 +2023-05-26 19:46:42.988941: train_loss -0.9662 +2023-05-26 19:46:42.989212: val_loss -0.6075 +2023-05-26 19:46:42.989335: Pseudo dice [0.9373, 0.8617, 0.8994] +2023-05-26 19:46:42.989436: Epoch time: 37.72 s +2023-05-26 19:46:44.768884: +2023-05-26 19:46:44.769053: Epoch 712 +2023-05-26 19:46:44.769161: Current learning rate: 0.00326 +2023-05-26 19:47:22.770764: train_loss -0.9664 +2023-05-26 19:47:22.771137: val_loss -0.6104 +2023-05-26 19:47:22.771397: Pseudo dice [0.9369, 0.8637, 0.9018] +2023-05-26 19:47:22.771571: Epoch time: 38.0 s +2023-05-26 19:47:24.334416: +2023-05-26 19:47:24.334614: Epoch 713 +2023-05-26 19:47:24.334736: Current learning rate: 0.00325 +2023-05-26 19:48:02.200932: train_loss -0.967 +2023-05-26 19:48:02.201182: val_loss -0.6109 +2023-05-26 19:48:02.201310: Pseudo dice [0.9368, 0.8631, 0.9002] +2023-05-26 19:48:02.201416: Epoch time: 37.87 s +2023-05-26 19:48:03.821277: +2023-05-26 19:48:03.821485: Epoch 714 +2023-05-26 19:48:03.821603: Current learning rate: 0.00324 +2023-05-26 19:48:41.989399: train_loss -0.9662 +2023-05-26 19:48:41.989633: val_loss -0.6133 +2023-05-26 19:48:41.989750: Pseudo dice [0.9376, 0.8645, 0.8996] +2023-05-26 19:48:41.989854: Epoch time: 38.17 s +2023-05-26 19:48:43.674122: +2023-05-26 19:48:43.674304: Epoch 715 +2023-05-26 19:48:43.674628: Current learning rate: 0.00323 +2023-05-26 19:49:21.637982: train_loss -0.9669 +2023-05-26 19:49:21.638229: val_loss -0.6056 +2023-05-26 19:49:21.638339: Pseudo dice [0.9358, 0.861, 0.9014] +2023-05-26 19:49:21.638439: Epoch time: 37.97 s +2023-05-26 19:49:23.167619: +2023-05-26 19:49:23.167780: Epoch 716 +2023-05-26 19:49:23.167900: Current learning rate: 0.00322 +2023-05-26 19:50:01.167281: train_loss -0.9669 +2023-05-26 19:50:01.167504: val_loss -0.6151 +2023-05-26 19:50:01.167621: Pseudo dice [0.9361, 0.8617, 0.9038] +2023-05-26 19:50:01.167726: Epoch time: 38.0 s +2023-05-26 19:50:02.919233: +2023-05-26 19:50:02.919419: Epoch 717 +2023-05-26 19:50:02.919539: Current learning rate: 0.00321 +2023-05-26 19:50:40.673118: train_loss -0.9668 +2023-05-26 19:50:40.673380: val_loss -0.6148 +2023-05-26 19:50:40.673501: Pseudo dice [0.9376, 0.8634, 0.9022] +2023-05-26 19:50:40.673586: Epoch time: 37.76 s +2023-05-26 19:50:42.564104: +2023-05-26 19:50:42.564305: Epoch 718 +2023-05-26 19:50:42.564430: Current learning rate: 0.0032 +2023-05-26 19:51:20.282990: train_loss -0.967 +2023-05-26 19:51:20.283265: val_loss -0.6117 +2023-05-26 19:51:20.283402: Pseudo dice [0.9366, 0.8639, 0.9044] +2023-05-26 19:51:20.283496: Epoch time: 37.72 s +2023-05-26 19:51:22.067432: +2023-05-26 19:51:22.067663: Epoch 719 +2023-05-26 19:51:22.067794: Current learning rate: 0.00319 +2023-05-26 19:51:59.981546: train_loss -0.9664 +2023-05-26 19:51:59.981867: val_loss -0.6024 +2023-05-26 19:51:59.982021: Pseudo dice [0.9349, 0.8587, 0.9001] +2023-05-26 19:51:59.982141: Epoch time: 37.92 s +2023-05-26 19:52:01.595627: +2023-05-26 19:52:01.595837: Epoch 720 +2023-05-26 19:52:01.595982: Current learning rate: 0.00318 +2023-05-26 19:52:39.271464: train_loss -0.9671 +2023-05-26 19:52:39.271707: val_loss -0.6073 +2023-05-26 19:52:39.271831: Pseudo dice [0.9362, 0.8613, 0.901] +2023-05-26 19:52:39.271941: Epoch time: 37.68 s +2023-05-26 19:52:40.899687: +2023-05-26 19:52:40.900654: Epoch 721 +2023-05-26 19:52:40.900973: Current learning rate: 0.00317 +2023-05-26 19:53:18.784307: train_loss -0.9668 +2023-05-26 19:53:18.784583: val_loss -0.6103 +2023-05-26 19:53:18.784964: Pseudo dice [0.9372, 0.8642, 0.9015] +2023-05-26 19:53:18.785061: Epoch time: 37.89 s +2023-05-26 19:53:20.458373: +2023-05-26 19:53:20.458553: Epoch 722 +2023-05-26 19:53:20.458665: Current learning rate: 0.00316 +2023-05-26 19:53:58.506010: train_loss -0.9669 +2023-05-26 19:53:58.506672: val_loss -0.6053 +2023-05-26 19:53:58.507099: Pseudo dice [0.9355, 0.8608, 0.9003] +2023-05-26 19:53:58.507412: Epoch time: 38.05 s +2023-05-26 19:54:00.297827: +2023-05-26 19:54:00.298165: Epoch 723 +2023-05-26 19:54:00.298548: Current learning rate: 0.00315 +2023-05-26 19:54:38.208120: train_loss -0.9669 +2023-05-26 19:54:38.208343: val_loss -0.6041 +2023-05-26 19:54:38.208451: Pseudo dice [0.9365, 0.8605, 0.9004] +2023-05-26 19:54:38.208555: Epoch time: 37.91 s +2023-05-26 19:54:40.060636: +2023-05-26 19:54:40.060831: Epoch 724 +2023-05-26 19:54:40.060946: Current learning rate: 0.00314 +2023-05-26 19:55:17.985008: train_loss -0.967 +2023-05-26 19:55:17.985241: val_loss -0.6073 +2023-05-26 19:55:17.985728: Pseudo dice [0.9372, 0.8631, 0.8996] +2023-05-26 19:55:17.985829: Epoch time: 37.93 s +2023-05-26 19:55:19.803706: +2023-05-26 19:55:19.804207: Epoch 725 +2023-05-26 19:55:19.804396: Current learning rate: 0.00313 +2023-05-26 19:55:57.515051: train_loss -0.9669 +2023-05-26 19:55:57.515454: val_loss -0.6078 +2023-05-26 19:55:57.515689: Pseudo dice [0.936, 0.8623, 0.9044] +2023-05-26 19:55:57.515838: Epoch time: 37.71 s +2023-05-26 19:55:59.031317: +2023-05-26 19:55:59.031520: Epoch 726 +2023-05-26 19:55:59.031620: Current learning rate: 0.00312 +2023-05-26 19:56:36.880805: train_loss -0.9667 +2023-05-26 19:56:36.881099: val_loss -0.6124 +2023-05-26 19:56:36.881229: Pseudo dice [0.9353, 0.8608, 0.9033] +2023-05-26 19:56:36.881330: Epoch time: 37.85 s +2023-05-26 19:56:38.455256: +2023-05-26 19:56:38.455463: Epoch 727 +2023-05-26 19:56:38.455613: Current learning rate: 0.00311 +2023-05-26 19:57:16.162507: train_loss -0.9667 +2023-05-26 19:57:16.162815: val_loss -0.6169 +2023-05-26 19:57:16.162966: Pseudo dice [0.9366, 0.8633, 0.9058] +2023-05-26 19:57:16.163062: Epoch time: 37.71 s +2023-05-26 19:57:17.853554: +2023-05-26 19:57:17.853939: Epoch 728 +2023-05-26 19:57:17.854065: Current learning rate: 0.0031 +2023-05-26 19:57:56.397695: train_loss -0.9675 +2023-05-26 19:57:56.398000: val_loss -0.6067 +2023-05-26 19:57:56.398145: Pseudo dice [0.9364, 0.8616, 0.9007] +2023-05-26 19:57:56.398242: Epoch time: 38.55 s +2023-05-26 19:57:58.019904: +2023-05-26 19:57:58.020097: Epoch 729 +2023-05-26 19:57:58.020241: Current learning rate: 0.00309 +2023-05-26 19:58:35.744731: train_loss -0.9672 +2023-05-26 19:58:35.744998: val_loss -0.6093 +2023-05-26 19:58:35.745120: Pseudo dice [0.938, 0.8651, 0.9024] +2023-05-26 19:58:35.745221: Epoch time: 37.73 s +2023-05-26 19:58:37.554551: +2023-05-26 19:58:37.554758: Epoch 730 +2023-05-26 19:58:37.554906: Current learning rate: 0.00308 +2023-05-26 19:59:15.584843: train_loss -0.9671 +2023-05-26 19:59:15.585081: val_loss -0.6106 +2023-05-26 19:59:15.585194: Pseudo dice [0.937, 0.8638, 0.9038] +2023-05-26 19:59:15.585297: Epoch time: 38.03 s +2023-05-26 19:59:17.300709: +2023-05-26 19:59:17.302163: Epoch 731 +2023-05-26 19:59:17.302927: Current learning rate: 0.00307 +2023-05-26 19:59:54.802214: train_loss -0.967 +2023-05-26 19:59:54.802469: val_loss -0.6003 +2023-05-26 19:59:54.802590: Pseudo dice [0.9349, 0.8608, 0.904] +2023-05-26 19:59:54.802689: Epoch time: 37.5 s +2023-05-26 19:59:56.390471: +2023-05-26 19:59:56.390664: Epoch 732 +2023-05-26 19:59:56.390789: Current learning rate: 0.00306 +2023-05-26 20:00:33.982805: train_loss -0.9678 +2023-05-26 20:00:33.983118: val_loss -0.6022 +2023-05-26 20:00:33.983244: Pseudo dice [0.9362, 0.8621, 0.9008] +2023-05-26 20:00:33.983337: Epoch time: 37.59 s +2023-05-26 20:00:35.724294: +2023-05-26 20:00:35.724665: Epoch 733 +2023-05-26 20:00:35.724885: Current learning rate: 0.00305 +2023-05-26 20:01:13.544231: train_loss -0.9678 +2023-05-26 20:01:13.544590: val_loss -0.608 +2023-05-26 20:01:13.544746: Pseudo dice [0.9365, 0.8636, 0.899] +2023-05-26 20:01:13.544880: Epoch time: 37.82 s +2023-05-26 20:01:15.281553: +2023-05-26 20:01:15.281774: Epoch 734 +2023-05-26 20:01:15.281901: Current learning rate: 0.00304 +2023-05-26 20:01:53.262829: train_loss -0.9674 +2023-05-26 20:01:53.263117: val_loss -0.5995 +2023-05-26 20:01:53.263242: Pseudo dice [0.9343, 0.8614, 0.8998] +2023-05-26 20:01:53.263331: Epoch time: 37.98 s +2023-05-26 20:01:54.919538: +2023-05-26 20:01:54.920368: Epoch 735 +2023-05-26 20:01:54.920783: Current learning rate: 0.00303 +2023-05-26 20:02:32.718177: train_loss -0.968 +2023-05-26 20:02:32.718715: val_loss -0.6019 +2023-05-26 20:02:32.719039: Pseudo dice [0.9364, 0.8613, 0.8997] +2023-05-26 20:02:32.719125: Epoch time: 37.8 s +2023-05-26 20:02:34.414659: +2023-05-26 20:02:34.414855: Epoch 736 +2023-05-26 20:02:34.414972: Current learning rate: 0.00302 +2023-05-26 20:03:12.818330: train_loss -0.9679 +2023-05-26 20:03:12.818594: val_loss -0.6072 +2023-05-26 20:03:12.818715: Pseudo dice [0.9372, 0.864, 0.8994] +2023-05-26 20:03:12.818818: Epoch time: 38.4 s +2023-05-26 20:03:14.817346: +2023-05-26 20:03:14.817549: Epoch 737 +2023-05-26 20:03:14.817669: Current learning rate: 0.00301 +2023-05-26 20:03:52.398539: train_loss -0.9681 +2023-05-26 20:03:52.398867: val_loss -0.5928 +2023-05-26 20:03:52.399334: Pseudo dice [0.9369, 0.8606, 0.8988] +2023-05-26 20:03:52.399426: Epoch time: 37.58 s +2023-05-26 20:03:54.046646: +2023-05-26 20:03:54.047001: Epoch 738 +2023-05-26 20:03:54.047157: Current learning rate: 0.003 +2023-05-26 20:04:31.757070: train_loss -0.9685 +2023-05-26 20:04:31.757323: val_loss -0.5989 +2023-05-26 20:04:31.757447: Pseudo dice [0.9366, 0.8615, 0.899] +2023-05-26 20:04:31.757549: Epoch time: 37.71 s +2023-05-26 20:04:33.363044: +2023-05-26 20:04:33.363210: Epoch 739 +2023-05-26 20:04:33.363339: Current learning rate: 0.00299 +2023-05-26 20:05:11.196993: train_loss -0.9677 +2023-05-26 20:05:11.197248: val_loss -0.6022 +2023-05-26 20:05:11.197384: Pseudo dice [0.9368, 0.8618, 0.9011] +2023-05-26 20:05:11.197509: Epoch time: 37.84 s +2023-05-26 20:05:12.670820: +2023-05-26 20:05:12.671312: Epoch 740 +2023-05-26 20:05:12.671582: Current learning rate: 0.00297 +2023-05-26 20:05:50.529432: train_loss -0.968 +2023-05-26 20:05:50.529684: val_loss -0.6074 +2023-05-26 20:05:50.529804: Pseudo dice [0.936, 0.8605, 0.9005] +2023-05-26 20:05:50.529903: Epoch time: 37.86 s +2023-05-26 20:05:52.404448: +2023-05-26 20:05:52.404639: Epoch 741 +2023-05-26 20:05:52.404760: Current learning rate: 0.00296 +2023-05-26 20:06:30.328578: train_loss -0.9673 +2023-05-26 20:06:30.328820: val_loss -0.6083 +2023-05-26 20:06:30.328956: Pseudo dice [0.9361, 0.8608, 0.9021] +2023-05-26 20:06:30.329056: Epoch time: 37.93 s +2023-05-26 20:06:31.958467: +2023-05-26 20:06:31.958672: Epoch 742 +2023-05-26 20:06:31.958809: Current learning rate: 0.00295 +2023-05-26 20:07:10.025076: train_loss -0.9678 +2023-05-26 20:07:10.025303: val_loss -0.5978 +2023-05-26 20:07:10.025426: Pseudo dice [0.9355, 0.8612, 0.9006] +2023-05-26 20:07:10.025533: Epoch time: 38.07 s +2023-05-26 20:07:11.992987: +2023-05-26 20:07:11.993304: Epoch 743 +2023-05-26 20:07:11.993615: Current learning rate: 0.00294 +2023-05-26 20:07:50.127378: train_loss -0.968 +2023-05-26 20:07:50.127627: val_loss -0.5946 +2023-05-26 20:07:50.127762: Pseudo dice [0.9359, 0.8586, 0.903] +2023-05-26 20:07:50.127854: Epoch time: 38.14 s +2023-05-26 20:07:52.034297: +2023-05-26 20:07:52.034895: Epoch 744 +2023-05-26 20:07:52.035156: Current learning rate: 0.00293 +2023-05-26 20:08:29.713624: train_loss -0.9683 +2023-05-26 20:08:29.713874: val_loss -0.6 +2023-05-26 20:08:29.713991: Pseudo dice [0.9361, 0.8607, 0.9042] +2023-05-26 20:08:29.714095: Epoch time: 37.68 s +2023-05-26 20:08:31.439927: +2023-05-26 20:08:31.440170: Epoch 745 +2023-05-26 20:08:31.440312: Current learning rate: 0.00292 +2023-05-26 20:09:08.928533: train_loss -0.9685 +2023-05-26 20:09:08.928832: val_loss -0.6001 +2023-05-26 20:09:08.928970: Pseudo dice [0.9362, 0.8601, 0.9016] +2023-05-26 20:09:08.929075: Epoch time: 37.49 s +2023-05-26 20:09:10.536976: +2023-05-26 20:09:10.537395: Epoch 746 +2023-05-26 20:09:10.537662: Current learning rate: 0.00291 +2023-05-26 20:09:48.213917: train_loss -0.9683 +2023-05-26 20:09:48.214252: val_loss -0.6004 +2023-05-26 20:09:48.214387: Pseudo dice [0.9358, 0.8608, 0.8995] +2023-05-26 20:09:48.214492: Epoch time: 37.68 s +2023-05-26 20:09:49.777670: +2023-05-26 20:09:49.777831: Epoch 747 +2023-05-26 20:09:49.777940: Current learning rate: 0.0029 +2023-05-26 20:10:27.865107: train_loss -0.9682 +2023-05-26 20:10:27.865376: val_loss -0.608 +2023-05-26 20:10:27.865537: Pseudo dice [0.9358, 0.8612, 0.9065] +2023-05-26 20:10:27.865637: Epoch time: 38.09 s +2023-05-26 20:10:29.354352: +2023-05-26 20:10:29.354565: Epoch 748 +2023-05-26 20:10:29.354739: Current learning rate: 0.00289 +2023-05-26 20:11:07.162032: train_loss -0.9683 +2023-05-26 20:11:07.162272: val_loss -0.5992 +2023-05-26 20:11:07.162412: Pseudo dice [0.9352, 0.8609, 0.9027] +2023-05-26 20:11:07.162515: Epoch time: 37.81 s +2023-05-26 20:11:09.187272: +2023-05-26 20:11:09.187623: Epoch 749 +2023-05-26 20:11:09.187848: Current learning rate: 0.00288 +2023-05-26 20:11:47.210069: train_loss -0.9682 +2023-05-26 20:11:47.210474: val_loss -0.6049 +2023-05-26 20:11:47.210672: Pseudo dice [0.9367, 0.863, 0.9032] +2023-05-26 20:11:47.210812: Epoch time: 38.02 s +2023-05-26 20:11:50.364355: +2023-05-26 20:11:50.364581: Epoch 750 +2023-05-26 20:11:50.364716: Current learning rate: 0.00287 +2023-05-26 20:12:28.535744: train_loss -0.9681 +2023-05-26 20:12:28.536036: val_loss -0.6074 +2023-05-26 20:12:28.536185: Pseudo dice [0.9363, 0.8616, 0.9031] +2023-05-26 20:12:28.536272: Epoch time: 38.17 s +2023-05-26 20:12:30.242168: +2023-05-26 20:12:30.242357: Epoch 751 +2023-05-26 20:12:30.242471: Current learning rate: 0.00286 +2023-05-26 20:13:08.471969: train_loss -0.9686 +2023-05-26 20:13:08.472301: val_loss -0.5999 +2023-05-26 20:13:08.472454: Pseudo dice [0.9358, 0.8592, 0.8992] +2023-05-26 20:13:08.472567: Epoch time: 38.23 s +2023-05-26 20:13:10.114936: +2023-05-26 20:13:10.115306: Epoch 752 +2023-05-26 20:13:10.115429: Current learning rate: 0.00285 +2023-05-26 20:13:47.914807: train_loss -0.9686 +2023-05-26 20:13:47.915139: val_loss -0.596 +2023-05-26 20:13:47.915267: Pseudo dice [0.9361, 0.861, 0.8989] +2023-05-26 20:13:47.915357: Epoch time: 37.8 s +2023-05-26 20:13:49.638492: +2023-05-26 20:13:49.638668: Epoch 753 +2023-05-26 20:13:49.638783: Current learning rate: 0.00284 +2023-05-26 20:14:27.032696: train_loss -0.9688 +2023-05-26 20:14:27.032951: val_loss -0.5981 +2023-05-26 20:14:27.033096: Pseudo dice [0.9354, 0.8598, 0.8981] +2023-05-26 20:14:27.033197: Epoch time: 37.4 s +2023-05-26 20:14:28.741039: +2023-05-26 20:14:28.741253: Epoch 754 +2023-05-26 20:14:28.741389: Current learning rate: 0.00283 +2023-05-26 20:15:06.465809: train_loss -0.9683 +2023-05-26 20:15:06.466190: val_loss -0.5933 +2023-05-26 20:15:06.466301: Pseudo dice [0.9337, 0.8583, 0.8941] +2023-05-26 20:15:06.466391: Epoch time: 37.73 s +2023-05-26 20:15:08.448974: +2023-05-26 20:15:08.449215: Epoch 755 +2023-05-26 20:15:08.449401: Current learning rate: 0.00282 +2023-05-26 20:15:46.016266: train_loss -0.9686 +2023-05-26 20:15:46.016539: val_loss -0.6065 +2023-05-26 20:15:46.016672: Pseudo dice [0.9356, 0.8608, 0.9045] +2023-05-26 20:15:46.016764: Epoch time: 37.57 s +2023-05-26 20:15:47.621256: +2023-05-26 20:15:47.621704: Epoch 756 +2023-05-26 20:15:47.621985: Current learning rate: 0.00281 +2023-05-26 20:16:25.672271: train_loss -0.9685 +2023-05-26 20:16:25.672545: val_loss -0.606 +2023-05-26 20:16:25.672684: Pseudo dice [0.9356, 0.8627, 0.9002] +2023-05-26 20:16:25.672807: Epoch time: 38.05 s +2023-05-26 20:16:27.602132: +2023-05-26 20:16:27.602304: Epoch 757 +2023-05-26 20:16:27.602420: Current learning rate: 0.0028 +2023-05-26 20:17:05.563268: train_loss -0.9687 +2023-05-26 20:17:05.563544: val_loss -0.6025 +2023-05-26 20:17:05.563694: Pseudo dice [0.936, 0.8625, 0.9028] +2023-05-26 20:17:05.563825: Epoch time: 37.96 s +2023-05-26 20:17:07.246880: +2023-05-26 20:17:07.247067: Epoch 758 +2023-05-26 20:17:07.247184: Current learning rate: 0.00279 +2023-05-26 20:17:45.243297: train_loss -0.9688 +2023-05-26 20:17:45.243578: val_loss -0.5985 +2023-05-26 20:17:45.243799: Pseudo dice [0.9371, 0.8606, 0.9016] +2023-05-26 20:17:45.243900: Epoch time: 38.0 s +2023-05-26 20:17:46.956496: +2023-05-26 20:17:46.956665: Epoch 759 +2023-05-26 20:17:46.956782: Current learning rate: 0.00278 +2023-05-26 20:18:24.650344: train_loss -0.9688 +2023-05-26 20:18:24.650625: val_loss -0.5892 +2023-05-26 20:18:24.650745: Pseudo dice [0.9364, 0.8608, 0.8962] +2023-05-26 20:18:24.650859: Epoch time: 37.7 s +2023-05-26 20:18:26.400162: +2023-05-26 20:18:26.400644: Epoch 760 +2023-05-26 20:18:26.400853: Current learning rate: 0.00277 +2023-05-26 20:19:04.185369: train_loss -0.969 +2023-05-26 20:19:04.185612: val_loss -0.607 +2023-05-26 20:19:04.185735: Pseudo dice [0.9376, 0.8636, 0.9027] +2023-05-26 20:19:04.185851: Epoch time: 37.79 s +2023-05-26 20:19:06.223639: +2023-05-26 20:19:06.223864: Epoch 761 +2023-05-26 20:19:06.223993: Current learning rate: 0.00276 +2023-05-26 20:19:43.918316: train_loss -0.9688 +2023-05-26 20:19:43.918612: val_loss -0.5997 +2023-05-26 20:19:43.918745: Pseudo dice [0.9356, 0.8598, 0.9024] +2023-05-26 20:19:43.918851: Epoch time: 37.7 s +2023-05-26 20:19:45.508739: +2023-05-26 20:19:45.509089: Epoch 762 +2023-05-26 20:19:45.509419: Current learning rate: 0.00275 +2023-05-26 20:20:23.245921: train_loss -0.9693 +2023-05-26 20:20:23.246244: val_loss -0.5982 +2023-05-26 20:20:23.246387: Pseudo dice [0.9356, 0.8617, 0.9022] +2023-05-26 20:20:23.246489: Epoch time: 37.74 s +2023-05-26 20:20:24.859911: +2023-05-26 20:20:24.860305: Epoch 763 +2023-05-26 20:20:24.860499: Current learning rate: 0.00274 +2023-05-26 20:21:02.363265: train_loss -0.9692 +2023-05-26 20:21:02.363580: val_loss -0.5958 +2023-05-26 20:21:02.363705: Pseudo dice [0.9356, 0.8622, 0.9003] +2023-05-26 20:21:02.363792: Epoch time: 37.5 s +2023-05-26 20:21:03.994663: +2023-05-26 20:21:03.995097: Epoch 764 +2023-05-26 20:21:03.995366: Current learning rate: 0.00273 +2023-05-26 20:21:41.812697: train_loss -0.9688 +2023-05-26 20:21:41.813175: val_loss -0.591 +2023-05-26 20:21:41.813444: Pseudo dice [0.9347, 0.8591, 0.8999] +2023-05-26 20:21:41.813703: Epoch time: 37.82 s +2023-05-26 20:21:43.512617: +2023-05-26 20:21:43.513261: Epoch 765 +2023-05-26 20:21:43.513392: Current learning rate: 0.00272 +2023-05-26 20:22:21.416162: train_loss -0.9693 +2023-05-26 20:22:21.416402: val_loss -0.5947 +2023-05-26 20:22:21.416518: Pseudo dice [0.9358, 0.8612, 0.9023] +2023-05-26 20:22:21.416619: Epoch time: 37.9 s +2023-05-26 20:22:22.999560: +2023-05-26 20:22:23.000100: Epoch 766 +2023-05-26 20:22:23.000421: Current learning rate: 0.00271 +2023-05-26 20:23:00.465412: train_loss -0.9691 +2023-05-26 20:23:00.465917: val_loss -0.5876 +2023-05-26 20:23:00.466044: Pseudo dice [0.9355, 0.8592, 0.9008] +2023-05-26 20:23:00.466146: Epoch time: 37.47 s +2023-05-26 20:23:02.480714: +2023-05-26 20:23:02.480930: Epoch 767 +2023-05-26 20:23:02.481055: Current learning rate: 0.0027 +2023-05-26 20:23:40.300266: train_loss -0.9688 +2023-05-26 20:23:40.300531: val_loss -0.6016 +2023-05-26 20:23:40.300656: Pseudo dice [0.9356, 0.86, 0.905] +2023-05-26 20:23:40.300766: Epoch time: 37.82 s +2023-05-26 20:23:41.928580: +2023-05-26 20:23:41.928926: Epoch 768 +2023-05-26 20:23:41.929182: Current learning rate: 0.00268 +2023-05-26 20:24:19.662451: train_loss -0.9696 +2023-05-26 20:24:19.663172: val_loss -0.6035 +2023-05-26 20:24:19.663368: Pseudo dice [0.9378, 0.8638, 0.9023] +2023-05-26 20:24:19.663463: Epoch time: 37.74 s +2023-05-26 20:24:21.417199: +2023-05-26 20:24:21.417524: Epoch 769 +2023-05-26 20:24:21.417766: Current learning rate: 0.00267 +2023-05-26 20:24:59.129751: train_loss -0.9693 +2023-05-26 20:24:59.130181: val_loss -0.603 +2023-05-26 20:24:59.130379: Pseudo dice [0.9375, 0.8622, 0.9021] +2023-05-26 20:24:59.131336: Epoch time: 37.71 s +2023-05-26 20:25:00.859169: +2023-05-26 20:25:00.859399: Epoch 770 +2023-05-26 20:25:00.859536: Current learning rate: 0.00266 +2023-05-26 20:25:38.541120: train_loss -0.9688 +2023-05-26 20:25:38.541419: val_loss -0.5925 +2023-05-26 20:25:38.541542: Pseudo dice [0.9366, 0.86, 0.9014] +2023-05-26 20:25:38.541631: Epoch time: 37.68 s +2023-05-26 20:25:40.401516: +2023-05-26 20:25:40.401891: Epoch 771 +2023-05-26 20:25:40.402042: Current learning rate: 0.00265 +2023-05-26 20:26:18.092124: train_loss -0.9695 +2023-05-26 20:26:18.092386: val_loss -0.5903 +2023-05-26 20:26:18.092511: Pseudo dice [0.9357, 0.8604, 0.9002] +2023-05-26 20:26:18.092597: Epoch time: 37.69 s +2023-05-26 20:26:19.745968: +2023-05-26 20:26:19.746491: Epoch 772 +2023-05-26 20:26:19.746956: Current learning rate: 0.00264 +2023-05-26 20:26:57.155152: train_loss -0.9693 +2023-05-26 20:26:57.155405: val_loss -0.5987 +2023-05-26 20:26:57.155533: Pseudo dice [0.9363, 0.8631, 0.9004] +2023-05-26 20:26:57.155620: Epoch time: 37.41 s +2023-05-26 20:26:58.982729: +2023-05-26 20:26:58.982934: Epoch 773 +2023-05-26 20:26:58.983075: Current learning rate: 0.00263 +2023-05-26 20:27:36.921889: train_loss -0.9691 +2023-05-26 20:27:36.922139: val_loss -0.5968 +2023-05-26 20:27:36.922268: Pseudo dice [0.9359, 0.8624, 0.9009] +2023-05-26 20:27:36.922367: Epoch time: 37.94 s +2023-05-26 20:27:38.650326: +2023-05-26 20:27:38.650698: Epoch 774 +2023-05-26 20:27:38.650929: Current learning rate: 0.00262 +2023-05-26 20:28:16.262193: train_loss -0.9694 +2023-05-26 20:28:16.262486: val_loss -0.5893 +2023-05-26 20:28:16.262617: Pseudo dice [0.9371, 0.8605, 0.9004] +2023-05-26 20:28:16.262706: Epoch time: 37.61 s +2023-05-26 20:28:17.905232: +2023-05-26 20:28:17.905430: Epoch 775 +2023-05-26 20:28:17.905555: Current learning rate: 0.00261 +2023-05-26 20:28:55.616167: train_loss -0.9686 +2023-05-26 20:28:55.616468: val_loss -0.5994 +2023-05-26 20:28:55.616602: Pseudo dice [0.9354, 0.8616, 0.9001] +2023-05-26 20:28:55.616706: Epoch time: 37.71 s +2023-05-26 20:28:57.326956: +2023-05-26 20:28:57.327238: Epoch 776 +2023-05-26 20:28:57.327525: Current learning rate: 0.0026 +2023-05-26 20:29:35.205224: train_loss -0.9689 +2023-05-26 20:29:35.205489: val_loss -0.5947 +2023-05-26 20:29:35.205621: Pseudo dice [0.9362, 0.8636, 0.901] +2023-05-26 20:29:35.205711: Epoch time: 37.88 s +2023-05-26 20:29:36.793180: +2023-05-26 20:29:36.793531: Epoch 777 +2023-05-26 20:29:36.793747: Current learning rate: 0.00259 +2023-05-26 20:30:14.518220: train_loss -0.9691 +2023-05-26 20:30:14.518466: val_loss -0.6077 +2023-05-26 20:30:14.518582: Pseudo dice [0.9379, 0.8642, 0.9025] +2023-05-26 20:30:14.518738: Epoch time: 37.73 s +2023-05-26 20:30:16.151647: +2023-05-26 20:30:16.151836: Epoch 778 +2023-05-26 20:30:16.151958: Current learning rate: 0.00258 +2023-05-26 20:30:53.963501: train_loss -0.9699 +2023-05-26 20:30:53.963799: val_loss -0.5995 +2023-05-26 20:30:53.963941: Pseudo dice [0.9362, 0.8613, 0.9059] +2023-05-26 20:30:53.964044: Epoch time: 37.81 s +2023-05-26 20:30:55.958536: +2023-05-26 20:30:55.958820: Epoch 779 +2023-05-26 20:30:55.959021: Current learning rate: 0.00257 +2023-05-26 20:31:33.464933: train_loss -0.9698 +2023-05-26 20:31:33.465216: val_loss -0.5931 +2023-05-26 20:31:33.465523: Pseudo dice [0.937, 0.862, 0.9003] +2023-05-26 20:31:33.465679: Epoch time: 37.51 s +2023-05-26 20:31:35.089199: +2023-05-26 20:31:35.089639: Epoch 780 +2023-05-26 20:31:35.089877: Current learning rate: 0.00256 +2023-05-26 20:32:12.806149: train_loss -0.9697 +2023-05-26 20:32:12.806417: val_loss -0.599 +2023-05-26 20:32:12.806593: Pseudo dice [0.9356, 0.8619, 0.9052] +2023-05-26 20:32:12.806857: Epoch time: 37.72 s +2023-05-26 20:32:14.391684: +2023-05-26 20:32:14.391869: Epoch 781 +2023-05-26 20:32:14.391995: Current learning rate: 0.00255 +2023-05-26 20:32:52.046351: train_loss -0.9697 +2023-05-26 20:32:52.046769: val_loss -0.5963 +2023-05-26 20:32:52.046924: Pseudo dice [0.9377, 0.8636, 0.9012] +2023-05-26 20:32:52.047019: Epoch time: 37.66 s +2023-05-26 20:32:53.872850: +2023-05-26 20:32:53.873017: Epoch 782 +2023-05-26 20:32:53.873146: Current learning rate: 0.00254 +2023-05-26 20:33:31.588275: train_loss -0.9702 +2023-05-26 20:33:31.588549: val_loss -0.5894 +2023-05-26 20:33:31.588704: Pseudo dice [0.9361, 0.8596, 0.9018] +2023-05-26 20:33:31.588798: Epoch time: 37.72 s +2023-05-26 20:33:33.243780: +2023-05-26 20:33:33.244254: Epoch 783 +2023-05-26 20:33:33.244697: Current learning rate: 0.00253 +2023-05-26 20:34:10.707813: train_loss -0.97 +2023-05-26 20:34:10.708087: val_loss -0.5915 +2023-05-26 20:34:10.708231: Pseudo dice [0.9368, 0.8604, 0.9014] +2023-05-26 20:34:10.708332: Epoch time: 37.47 s +2023-05-26 20:34:12.234048: +2023-05-26 20:34:12.234396: Epoch 784 +2023-05-26 20:34:12.234595: Current learning rate: 0.00252 +2023-05-26 20:34:49.849652: train_loss -0.9697 +2023-05-26 20:34:49.849886: val_loss -0.5924 +2023-05-26 20:34:49.850008: Pseudo dice [0.9352, 0.8606, 0.9027] +2023-05-26 20:34:49.850115: Epoch time: 37.62 s +2023-05-26 20:34:51.932112: +2023-05-26 20:34:51.932332: Epoch 785 +2023-05-26 20:34:51.932452: Current learning rate: 0.00251 +2023-05-26 20:35:29.622419: train_loss -0.9693 +2023-05-26 20:35:29.622680: val_loss -0.6032 +2023-05-26 20:35:29.622814: Pseudo dice [0.9362, 0.8614, 0.9044] +2023-05-26 20:35:29.622936: Epoch time: 37.69 s +2023-05-26 20:35:31.324029: +2023-05-26 20:35:31.324363: Epoch 786 +2023-05-26 20:35:31.324581: Current learning rate: 0.0025 +2023-05-26 20:36:09.081592: train_loss -0.9694 +2023-05-26 20:36:09.081855: val_loss -0.6003 +2023-05-26 20:36:09.081988: Pseudo dice [0.9361, 0.8611, 0.9033] +2023-05-26 20:36:09.082087: Epoch time: 37.76 s +2023-05-26 20:36:10.769313: +2023-05-26 20:36:10.769817: Epoch 787 +2023-05-26 20:36:10.770103: Current learning rate: 0.00249 +2023-05-26 20:36:48.582270: train_loss -0.9696 +2023-05-26 20:36:48.582522: val_loss -0.5893 +2023-05-26 20:36:48.582641: Pseudo dice [0.9361, 0.8603, 0.9046] +2023-05-26 20:36:48.582746: Epoch time: 37.81 s +2023-05-26 20:36:50.138065: +2023-05-26 20:36:50.138256: Epoch 788 +2023-05-26 20:36:50.138366: Current learning rate: 0.00248 +2023-05-26 20:37:28.163403: train_loss -0.9701 +2023-05-26 20:37:28.163664: val_loss -0.5942 +2023-05-26 20:37:28.163769: Pseudo dice [0.9355, 0.8617, 0.9062] +2023-05-26 20:37:28.163864: Epoch time: 38.03 s +2023-05-26 20:37:29.768812: +2023-05-26 20:37:29.768975: Epoch 789 +2023-05-26 20:37:29.769085: Current learning rate: 0.00247 +2023-05-26 20:38:07.361734: train_loss -0.9701 +2023-05-26 20:38:07.362129: val_loss -0.585 +2023-05-26 20:38:07.362261: Pseudo dice [0.9351, 0.8588, 0.9036] +2023-05-26 20:38:07.362363: Epoch time: 37.59 s +2023-05-26 20:38:09.077372: +2023-05-26 20:38:09.077562: Epoch 790 +2023-05-26 20:38:09.077683: Current learning rate: 0.00245 +2023-05-26 20:38:46.864243: train_loss -0.9701 +2023-05-26 20:38:46.864609: val_loss -0.5991 +2023-05-26 20:38:46.864743: Pseudo dice [0.9363, 0.8621, 0.9024] +2023-05-26 20:38:46.864855: Epoch time: 37.79 s +2023-05-26 20:38:48.585664: +2023-05-26 20:38:48.586339: Epoch 791 +2023-05-26 20:38:48.586795: Current learning rate: 0.00244 +2023-05-26 20:39:26.317913: train_loss -0.97 +2023-05-26 20:39:26.318173: val_loss -0.6007 +2023-05-26 20:39:26.318294: Pseudo dice [0.9365, 0.8628, 0.9022] +2023-05-26 20:39:26.318396: Epoch time: 37.73 s +2023-05-26 20:39:28.260075: +2023-05-26 20:39:28.260361: Epoch 792 +2023-05-26 20:39:28.260512: Current learning rate: 0.00243 +2023-05-26 20:40:05.976295: train_loss -0.9701 +2023-05-26 20:40:05.976666: val_loss -0.5957 +2023-05-26 20:40:05.976785: Pseudo dice [0.9371, 0.8617, 0.8994] +2023-05-26 20:40:05.976878: Epoch time: 37.72 s +2023-05-26 20:40:07.847281: +2023-05-26 20:40:07.847474: Epoch 793 +2023-05-26 20:40:07.847589: Current learning rate: 0.00242 +2023-05-26 20:40:45.747462: train_loss -0.9702 +2023-05-26 20:40:45.747800: val_loss -0.5916 +2023-05-26 20:40:45.747940: Pseudo dice [0.9362, 0.8608, 0.9011] +2023-05-26 20:40:45.748040: Epoch time: 37.9 s +2023-05-26 20:40:47.378795: +2023-05-26 20:40:47.379084: Epoch 794 +2023-05-26 20:40:47.379354: Current learning rate: 0.00241 +2023-05-26 20:41:25.281529: train_loss -0.9705 +2023-05-26 20:41:25.281790: val_loss -0.5981 +2023-05-26 20:41:25.281913: Pseudo dice [0.9375, 0.8627, 0.9017] +2023-05-26 20:41:25.282013: Epoch time: 37.9 s +2023-05-26 20:41:26.957867: +2023-05-26 20:41:26.958063: Epoch 795 +2023-05-26 20:41:26.958203: Current learning rate: 0.0024 +2023-05-26 20:42:04.588706: train_loss -0.9701 +2023-05-26 20:42:04.589123: val_loss -0.5908 +2023-05-26 20:42:04.589364: Pseudo dice [0.9364, 0.8615, 0.9036] +2023-05-26 20:42:04.589563: Epoch time: 37.63 s +2023-05-26 20:42:06.090433: +2023-05-26 20:42:06.090611: Epoch 796 +2023-05-26 20:42:06.090734: Current learning rate: 0.00239 +2023-05-26 20:42:44.246198: train_loss -0.97 +2023-05-26 20:42:44.246425: val_loss -0.5909 +2023-05-26 20:42:44.246542: Pseudo dice [0.9349, 0.8603, 0.9059] +2023-05-26 20:42:44.246640: Epoch time: 38.16 s +2023-05-26 20:42:45.863799: +2023-05-26 20:42:45.864148: Epoch 797 +2023-05-26 20:42:45.864457: Current learning rate: 0.00238 +2023-05-26 20:43:23.478843: train_loss -0.97 +2023-05-26 20:43:23.479328: val_loss -0.5835 +2023-05-26 20:43:23.479815: Pseudo dice [0.9359, 0.86, 0.9023] +2023-05-26 20:43:23.480109: Epoch time: 37.62 s +2023-05-26 20:43:25.475490: +2023-05-26 20:43:25.475752: Epoch 798 +2023-05-26 20:43:25.475969: Current learning rate: 0.00237 +2023-05-26 20:44:03.373239: train_loss -0.9705 +2023-05-26 20:44:03.373574: val_loss -0.5971 +2023-05-26 20:44:03.373691: Pseudo dice [0.9366, 0.863, 0.9045] +2023-05-26 20:44:03.373770: Epoch time: 37.9 s +2023-05-26 20:44:04.975769: +2023-05-26 20:44:04.975973: Epoch 799 +2023-05-26 20:44:04.976118: Current learning rate: 0.00236 +2023-05-26 20:44:42.892370: train_loss -0.9708 +2023-05-26 20:44:42.892631: val_loss -0.5941 +2023-05-26 20:44:42.892759: Pseudo dice [0.9371, 0.8625, 0.9032] +2023-05-26 20:44:42.892844: Epoch time: 37.92 s +2023-05-26 20:44:46.228126: +2023-05-26 20:44:46.228324: Epoch 800 +2023-05-26 20:44:46.228443: Current learning rate: 0.00235 +2023-05-26 20:45:24.059268: train_loss -0.9705 +2023-05-26 20:45:24.059531: val_loss -0.5991 +2023-05-26 20:45:24.059673: Pseudo dice [0.936, 0.8612, 0.9058] +2023-05-26 20:45:24.059769: Epoch time: 37.83 s +2023-05-26 20:45:25.731006: +2023-05-26 20:45:25.731179: Epoch 801 +2023-05-26 20:45:25.731299: Current learning rate: 0.00234 +2023-05-26 20:46:03.427827: train_loss -0.9709 +2023-05-26 20:46:03.428117: val_loss -0.5824 +2023-05-26 20:46:03.428266: Pseudo dice [0.937, 0.8626, 0.9049] +2023-05-26 20:46:03.428358: Epoch time: 37.7 s +2023-05-26 20:46:05.186106: +2023-05-26 20:46:05.186296: Epoch 802 +2023-05-26 20:46:05.186423: Current learning rate: 0.00233 +2023-05-26 20:46:42.958560: train_loss -0.9704 +2023-05-26 20:46:42.958801: val_loss -0.587 +2023-05-26 20:46:42.958979: Pseudo dice [0.9367, 0.8609, 0.9009] +2023-05-26 20:46:42.959104: Epoch time: 37.77 s +2023-05-26 20:46:44.854317: +2023-05-26 20:46:44.854504: Epoch 803 +2023-05-26 20:46:44.854656: Current learning rate: 0.00232 +2023-05-26 20:47:23.825111: train_loss -0.9704 +2023-05-26 20:47:23.825545: val_loss -0.5941 +2023-05-26 20:47:23.825806: Pseudo dice [0.9353, 0.8594, 0.9036] +2023-05-26 20:47:23.826059: Epoch time: 38.97 s +2023-05-26 20:47:25.497757: +2023-05-26 20:47:25.498177: Epoch 804 +2023-05-26 20:47:25.499005: Current learning rate: 0.00231 +2023-05-26 20:48:03.374466: train_loss -0.9708 +2023-05-26 20:48:03.374712: val_loss -0.5879 +2023-05-26 20:48:03.374846: Pseudo dice [0.936, 0.8622, 0.9] +2023-05-26 20:48:03.374974: Epoch time: 37.88 s +2023-05-26 20:48:05.025091: +2023-05-26 20:48:05.025426: Epoch 805 +2023-05-26 20:48:05.025624: Current learning rate: 0.0023 +2023-05-26 20:48:42.423141: train_loss -0.9708 +2023-05-26 20:48:42.423413: val_loss -0.5994 +2023-05-26 20:48:42.423536: Pseudo dice [0.9373, 0.8615, 0.9032] +2023-05-26 20:48:42.423623: Epoch time: 37.4 s +2023-05-26 20:48:44.187189: +2023-05-26 20:48:44.187368: Epoch 806 +2023-05-26 20:48:44.187487: Current learning rate: 0.00229 +2023-05-26 20:49:22.197633: train_loss -0.9709 +2023-05-26 20:49:22.197878: val_loss -0.591 +2023-05-26 20:49:22.197996: Pseudo dice [0.9375, 0.8625, 0.9025] +2023-05-26 20:49:22.198098: Epoch time: 38.01 s +2023-05-26 20:49:23.751030: +2023-05-26 20:49:23.751364: Epoch 807 +2023-05-26 20:49:23.751487: Current learning rate: 0.00228 +2023-05-26 20:50:01.533692: train_loss -0.9713 +2023-05-26 20:50:01.533978: val_loss -0.5872 +2023-05-26 20:50:01.534104: Pseudo dice [0.9349, 0.8614, 0.9047] +2023-05-26 20:50:01.534211: Epoch time: 37.78 s +2023-05-26 20:50:03.242262: +2023-05-26 20:50:03.242978: Epoch 808 +2023-05-26 20:50:03.243358: Current learning rate: 0.00226 +2023-05-26 20:50:40.801260: train_loss -0.9712 +2023-05-26 20:50:40.801502: val_loss -0.588 +2023-05-26 20:50:40.801620: Pseudo dice [0.9352, 0.8608, 0.9035] +2023-05-26 20:50:40.801724: Epoch time: 37.56 s +2023-05-26 20:50:42.713892: +2023-05-26 20:50:42.714254: Epoch 809 +2023-05-26 20:50:42.714512: Current learning rate: 0.00225 +2023-05-26 20:51:20.988678: train_loss -0.9711 +2023-05-26 20:51:20.989053: val_loss -0.5925 +2023-05-26 20:51:20.989219: Pseudo dice [0.9378, 0.8626, 0.905] +2023-05-26 20:51:20.989350: Epoch time: 38.28 s +2023-05-26 20:51:22.721128: +2023-05-26 20:51:22.721307: Epoch 810 +2023-05-26 20:51:22.721425: Current learning rate: 0.00224 +2023-05-26 20:52:01.908961: train_loss -0.9711 +2023-05-26 20:52:01.909183: val_loss -0.5766 +2023-05-26 20:52:01.909301: Pseudo dice [0.9366, 0.8594, 0.8991] +2023-05-26 20:52:01.909409: Epoch time: 39.19 s +2023-05-26 20:52:03.449764: +2023-05-26 20:52:03.450055: Epoch 811 +2023-05-26 20:52:03.450267: Current learning rate: 0.00223 +2023-05-26 20:52:41.141337: train_loss -0.9712 +2023-05-26 20:52:41.141626: val_loss -0.5916 +2023-05-26 20:52:41.141748: Pseudo dice [0.9381, 0.8628, 0.9059] +2023-05-26 20:52:41.141839: Epoch time: 37.69 s +2023-05-26 20:52:42.954992: +2023-05-26 20:52:42.955182: Epoch 812 +2023-05-26 20:52:42.955313: Current learning rate: 0.00222 +2023-05-26 20:53:21.057245: train_loss -0.9713 +2023-05-26 20:53:21.057476: val_loss -0.598 +2023-05-26 20:53:21.057594: Pseudo dice [0.9372, 0.863, 0.9025] +2023-05-26 20:53:21.057697: Epoch time: 38.1 s +2023-05-26 20:53:22.694419: +2023-05-26 20:53:22.694609: Epoch 813 +2023-05-26 20:53:22.694745: Current learning rate: 0.00221 +2023-05-26 20:54:00.240076: train_loss -0.971 +2023-05-26 20:54:00.240391: val_loss -0.5965 +2023-05-26 20:54:00.240520: Pseudo dice [0.9367, 0.8619, 0.909] +2023-05-26 20:54:00.240620: Epoch time: 37.55 s +2023-05-26 20:54:01.906440: +2023-05-26 20:54:01.906761: Epoch 814 +2023-05-26 20:54:01.907101: Current learning rate: 0.0022 +2023-05-26 20:54:39.437077: train_loss -0.9709 +2023-05-26 20:54:39.437367: val_loss -0.5883 +2023-05-26 20:54:39.437492: Pseudo dice [0.937, 0.8621, 0.9021] +2023-05-26 20:54:39.437581: Epoch time: 37.53 s +2023-05-26 20:54:41.157313: +2023-05-26 20:54:41.157995: Epoch 815 +2023-05-26 20:54:41.158280: Current learning rate: 0.00219 +2023-05-26 20:55:18.643149: train_loss -0.9713 +2023-05-26 20:55:18.643403: val_loss -0.5853 +2023-05-26 20:55:18.643520: Pseudo dice [0.9374, 0.8631, 0.8997] +2023-05-26 20:55:18.643606: Epoch time: 37.49 s +2023-05-26 20:55:20.689418: +2023-05-26 20:55:20.689619: Epoch 816 +2023-05-26 20:55:20.689746: Current learning rate: 0.00218 +2023-05-26 20:55:58.572754: train_loss -0.9712 +2023-05-26 20:55:58.573663: val_loss -0.5982 +2023-05-26 20:55:58.573827: Pseudo dice [0.9379, 0.8621, 0.905] +2023-05-26 20:55:58.573929: Epoch time: 37.88 s +2023-05-26 20:56:00.397124: +2023-05-26 20:56:00.397441: Epoch 817 +2023-05-26 20:56:00.397563: Current learning rate: 0.00217 +2023-05-26 20:56:38.202087: train_loss -0.971 +2023-05-26 20:56:38.202365: val_loss -0.5876 +2023-05-26 20:56:38.202503: Pseudo dice [0.9364, 0.8615, 0.9032] +2023-05-26 20:56:38.202594: Epoch time: 37.81 s +2023-05-26 20:56:39.984277: +2023-05-26 20:56:39.984472: Epoch 818 +2023-05-26 20:56:39.984606: Current learning rate: 0.00216 +2023-05-26 20:57:17.489159: train_loss -0.971 +2023-05-26 20:57:17.489399: val_loss -0.5835 +2023-05-26 20:57:17.489516: Pseudo dice [0.9374, 0.8619, 0.8975] +2023-05-26 20:57:17.489614: Epoch time: 37.51 s +2023-05-26 20:57:19.140054: +2023-05-26 20:57:19.140258: Epoch 819 +2023-05-26 20:57:19.140394: Current learning rate: 0.00215 +2023-05-26 20:57:57.199272: train_loss -0.9709 +2023-05-26 20:57:57.199511: val_loss -0.5948 +2023-05-26 20:57:57.199629: Pseudo dice [0.9381, 0.8641, 0.9016] +2023-05-26 20:57:57.199738: Epoch time: 38.06 s +2023-05-26 20:57:58.751150: +2023-05-26 20:57:58.751542: Epoch 820 +2023-05-26 20:57:58.751769: Current learning rate: 0.00214 +2023-05-26 20:58:36.781654: train_loss -0.9715 +2023-05-26 20:58:36.781892: val_loss -0.5893 +2023-05-26 20:58:36.781998: Pseudo dice [0.9375, 0.8629, 0.9006] +2023-05-26 20:58:36.782100: Epoch time: 38.03 s +2023-05-26 20:58:38.545142: +2023-05-26 20:58:38.545609: Epoch 821 +2023-05-26 20:58:38.545987: Current learning rate: 0.00213 +2023-05-26 20:59:16.312503: train_loss -0.9713 +2023-05-26 20:59:16.312825: val_loss -0.5854 +2023-05-26 20:59:16.312992: Pseudo dice [0.9375, 0.863, 0.9006] +2023-05-26 20:59:16.313115: Epoch time: 37.77 s +2023-05-26 20:59:18.354866: +2023-05-26 20:59:18.355239: Epoch 822 +2023-05-26 20:59:18.355457: Current learning rate: 0.00212 +2023-05-26 20:59:56.044757: train_loss -0.9712 +2023-05-26 20:59:56.045027: val_loss -0.5908 +2023-05-26 20:59:56.045128: Pseudo dice [0.9361, 0.861, 0.9026] +2023-05-26 20:59:56.045211: Epoch time: 37.69 s +2023-05-26 20:59:57.691191: +2023-05-26 20:59:57.691604: Epoch 823 +2023-05-26 20:59:57.691770: Current learning rate: 0.0021 +2023-05-26 21:00:35.799111: train_loss -0.9718 +2023-05-26 21:00:35.799414: val_loss -0.584 +2023-05-26 21:00:35.799548: Pseudo dice [0.9371, 0.8627, 0.8993] +2023-05-26 21:00:35.799644: Epoch time: 38.11 s +2023-05-26 21:00:37.336447: +2023-05-26 21:00:37.336818: Epoch 824 +2023-05-26 21:00:37.337054: Current learning rate: 0.00209 +2023-05-26 21:01:15.195675: train_loss -0.9719 +2023-05-26 21:01:15.195943: val_loss -0.5725 +2023-05-26 21:01:15.196074: Pseudo dice [0.9363, 0.8611, 0.8968] +2023-05-26 21:01:15.196156: Epoch time: 37.86 s +2023-05-26 21:01:16.743861: +2023-05-26 21:01:16.744080: Epoch 825 +2023-05-26 21:01:16.744197: Current learning rate: 0.00208 +2023-05-26 21:01:54.774448: train_loss -0.972 +2023-05-26 21:01:54.774681: val_loss -0.5796 +2023-05-26 21:01:54.774804: Pseudo dice [0.9365, 0.8621, 0.8976] +2023-05-26 21:01:54.774918: Epoch time: 38.03 s +2023-05-26 21:01:56.153717: +2023-05-26 21:01:56.153993: Epoch 826 +2023-05-26 21:01:56.154243: Current learning rate: 0.00207 +2023-05-26 21:02:34.069828: train_loss -0.9717 +2023-05-26 21:02:34.070057: val_loss -0.5826 +2023-05-26 21:02:34.070179: Pseudo dice [0.9373, 0.8622, 0.8993] +2023-05-26 21:02:34.070283: Epoch time: 37.92 s +2023-05-26 21:02:35.597556: +2023-05-26 21:02:35.597877: Epoch 827 +2023-05-26 21:02:35.598109: Current learning rate: 0.00206 +2023-05-26 21:03:13.206044: train_loss -0.972 +2023-05-26 21:03:13.206325: val_loss -0.578 +2023-05-26 21:03:13.206484: Pseudo dice [0.9357, 0.86, 0.9012] +2023-05-26 21:03:13.206576: Epoch time: 37.61 s +2023-05-26 21:03:14.823927: +2023-05-26 21:03:14.824152: Epoch 828 +2023-05-26 21:03:14.824305: Current learning rate: 0.00205 +2023-05-26 21:03:52.559021: train_loss -0.9725 +2023-05-26 21:03:52.559314: val_loss -0.5757 +2023-05-26 21:03:52.559444: Pseudo dice [0.9363, 0.8614, 0.901] +2023-05-26 21:03:52.559538: Epoch time: 37.74 s +2023-05-26 21:03:54.399174: +2023-05-26 21:03:54.399379: Epoch 829 +2023-05-26 21:03:54.399507: Current learning rate: 0.00204 +2023-05-26 21:04:32.080002: train_loss -0.9718 +2023-05-26 21:04:32.080339: val_loss -0.5825 +2023-05-26 21:04:32.080468: Pseudo dice [0.9351, 0.8604, 0.9018] +2023-05-26 21:04:32.080568: Epoch time: 37.68 s +2023-05-26 21:04:33.668000: +2023-05-26 21:04:33.668784: Epoch 830 +2023-05-26 21:04:33.669095: Current learning rate: 0.00203 +2023-05-26 21:05:11.344930: train_loss -0.9722 +2023-05-26 21:05:11.345212: val_loss -0.5766 +2023-05-26 21:05:11.345328: Pseudo dice [0.9358, 0.8593, 0.9022] +2023-05-26 21:05:11.345423: Epoch time: 37.68 s +2023-05-26 21:05:12.924570: +2023-05-26 21:05:12.924767: Epoch 831 +2023-05-26 21:05:12.924883: Current learning rate: 0.00202 +2023-05-26 21:05:50.408730: train_loss -0.9719 +2023-05-26 21:05:50.409028: val_loss -0.5851 +2023-05-26 21:05:50.409170: Pseudo dice [0.9365, 0.862, 0.9013] +2023-05-26 21:05:50.409261: Epoch time: 37.49 s +2023-05-26 21:05:52.204246: +2023-05-26 21:05:52.204439: Epoch 832 +2023-05-26 21:05:52.204563: Current learning rate: 0.00201 +2023-05-26 21:06:30.382613: train_loss -0.9721 +2023-05-26 21:06:30.383341: val_loss -0.5779 +2023-05-26 21:06:30.383464: Pseudo dice [0.9364, 0.8603, 0.8957] +2023-05-26 21:06:30.383604: Epoch time: 38.18 s +2023-05-26 21:06:32.111564: +2023-05-26 21:06:32.111933: Epoch 833 +2023-05-26 21:06:32.112143: Current learning rate: 0.002 +2023-05-26 21:07:09.866368: train_loss -0.972 +2023-05-26 21:07:09.866596: val_loss -0.5843 +2023-05-26 21:07:09.866703: Pseudo dice [0.9365, 0.8613, 0.9044] +2023-05-26 21:07:09.866782: Epoch time: 37.76 s +2023-05-26 21:07:11.435163: +2023-05-26 21:07:11.435559: Epoch 834 +2023-05-26 21:07:11.435688: Current learning rate: 0.00199 +2023-05-26 21:07:49.115131: train_loss -0.9719 +2023-05-26 21:07:49.115373: val_loss -0.5949 +2023-05-26 21:07:49.115492: Pseudo dice [0.9366, 0.8616, 0.9067] +2023-05-26 21:07:49.115590: Epoch time: 37.68 s +2023-05-26 21:07:50.849862: +2023-05-26 21:07:50.850372: Epoch 835 +2023-05-26 21:07:50.850720: Current learning rate: 0.00198 +2023-05-26 21:08:28.633787: train_loss -0.9723 +2023-05-26 21:08:28.634086: val_loss -0.5819 +2023-05-26 21:08:28.634562: Pseudo dice [0.9375, 0.862, 0.904] +2023-05-26 21:08:28.634686: Epoch time: 37.79 s +2023-05-26 21:08:30.154551: +2023-05-26 21:08:30.154767: Epoch 836 +2023-05-26 21:08:30.154900: Current learning rate: 0.00196 +2023-05-26 21:09:07.979904: train_loss -0.9724 +2023-05-26 21:09:07.980142: val_loss -0.5823 +2023-05-26 21:09:07.980263: Pseudo dice [0.9377, 0.8623, 0.901] +2023-05-26 21:09:07.980367: Epoch time: 37.83 s +2023-05-26 21:09:09.479504: +2023-05-26 21:09:09.479668: Epoch 837 +2023-05-26 21:09:09.479783: Current learning rate: 0.00195 +2023-05-26 21:09:47.199259: train_loss -0.9718 +2023-05-26 21:09:47.199501: val_loss -0.5805 +2023-05-26 21:09:47.199633: Pseudo dice [0.9368, 0.861, 0.9025] +2023-05-26 21:09:47.199731: Epoch time: 37.72 s +2023-05-26 21:09:48.864911: +2023-05-26 21:09:48.865104: Epoch 838 +2023-05-26 21:09:48.865290: Current learning rate: 0.00194 +2023-05-26 21:10:26.553012: train_loss -0.9723 +2023-05-26 21:10:26.553261: val_loss -0.5815 +2023-05-26 21:10:26.553380: Pseudo dice [0.9363, 0.8603, 0.9048] +2023-05-26 21:10:26.553482: Epoch time: 37.69 s +2023-05-26 21:10:28.164203: +2023-05-26 21:10:28.164664: Epoch 839 +2023-05-26 21:10:28.164840: Current learning rate: 0.00193 +2023-05-26 21:11:05.830749: train_loss -0.9724 +2023-05-26 21:11:05.831026: val_loss -0.5849 +2023-05-26 21:11:05.831148: Pseudo dice [0.9376, 0.8624, 0.902] +2023-05-26 21:11:05.831233: Epoch time: 37.67 s +2023-05-26 21:11:07.347347: +2023-05-26 21:11:07.347807: Epoch 840 +2023-05-26 21:11:07.347943: Current learning rate: 0.00192 +2023-05-26 21:11:46.027786: train_loss -0.9732 +2023-05-26 21:11:46.028116: val_loss -0.5815 +2023-05-26 21:11:46.028263: Pseudo dice [0.9365, 0.8613, 0.9022] +2023-05-26 21:11:46.028370: Epoch time: 38.68 s +2023-05-26 21:11:47.758847: +2023-05-26 21:11:47.759019: Epoch 841 +2023-05-26 21:11:47.759139: Current learning rate: 0.00191 +2023-05-26 21:12:25.351457: train_loss -0.9729 +2023-05-26 21:12:25.351684: val_loss -0.5787 +2023-05-26 21:12:25.351802: Pseudo dice [0.9368, 0.8615, 0.8999] +2023-05-26 21:12:25.351906: Epoch time: 37.59 s +2023-05-26 21:12:27.120709: +2023-05-26 21:12:27.121193: Epoch 842 +2023-05-26 21:12:27.121509: Current learning rate: 0.0019 +2023-05-26 21:13:04.897022: train_loss -0.9733 +2023-05-26 21:13:04.897421: val_loss -0.5802 +2023-05-26 21:13:04.897621: Pseudo dice [0.9366, 0.8606, 0.902] +2023-05-26 21:13:04.897790: Epoch time: 37.78 s +2023-05-26 21:13:06.381875: +2023-05-26 21:13:06.382061: Epoch 843 +2023-05-26 21:13:06.382210: Current learning rate: 0.00189 +2023-05-26 21:13:44.121817: train_loss -0.973 +2023-05-26 21:13:44.122085: val_loss -0.5801 +2023-05-26 21:13:44.122216: Pseudo dice [0.9363, 0.8603, 0.9051] +2023-05-26 21:13:44.122322: Epoch time: 37.74 s +2023-05-26 21:13:45.730994: +2023-05-26 21:13:45.731461: Epoch 844 +2023-05-26 21:13:45.731779: Current learning rate: 0.00188 +2023-05-26 21:14:23.371625: train_loss -0.9728 +2023-05-26 21:14:23.371946: val_loss -0.5802 +2023-05-26 21:14:23.372077: Pseudo dice [0.9376, 0.8624, 0.9017] +2023-05-26 21:14:23.372175: Epoch time: 37.64 s +2023-05-26 21:14:24.895639: +2023-05-26 21:14:24.896002: Epoch 845 +2023-05-26 21:14:24.896231: Current learning rate: 0.00187 +2023-05-26 21:15:02.553789: train_loss -0.9723 +2023-05-26 21:15:02.554059: val_loss -0.5693 +2023-05-26 21:15:02.554196: Pseudo dice [0.936, 0.86, 0.8963] +2023-05-26 21:15:02.554302: Epoch time: 37.66 s +2023-05-26 21:15:04.258177: +2023-05-26 21:15:04.258373: Epoch 846 +2023-05-26 21:15:04.258507: Current learning rate: 0.00186 +2023-05-26 21:15:42.320908: train_loss -0.9728 +2023-05-26 21:15:42.321742: val_loss -0.578 +2023-05-26 21:15:42.321858: Pseudo dice [0.9361, 0.8613, 0.9051] +2023-05-26 21:15:42.321949: Epoch time: 38.06 s +2023-05-26 21:15:43.993414: +2023-05-26 21:15:43.993768: Epoch 847 +2023-05-26 21:15:43.993977: Current learning rate: 0.00185 +2023-05-26 21:16:21.813112: train_loss -0.9727 +2023-05-26 21:16:21.813337: val_loss -0.5819 +2023-05-26 21:16:21.813442: Pseudo dice [0.9362, 0.8615, 0.9009] +2023-05-26 21:16:21.813537: Epoch time: 37.82 s +2023-05-26 21:16:23.644909: +2023-05-26 21:16:23.645205: Epoch 848 +2023-05-26 21:16:23.645430: Current learning rate: 0.00184 +2023-05-26 21:17:01.535374: train_loss -0.9729 +2023-05-26 21:17:01.535875: val_loss -0.5772 +2023-05-26 21:17:01.536165: Pseudo dice [0.9371, 0.8613, 0.8988] +2023-05-26 21:17:01.536258: Epoch time: 37.89 s +2023-05-26 21:17:03.271880: +2023-05-26 21:17:03.272074: Epoch 849 +2023-05-26 21:17:03.272187: Current learning rate: 0.00182 +2023-05-26 21:17:41.074998: train_loss -0.973 +2023-05-26 21:17:41.075334: val_loss -0.5849 +2023-05-26 21:17:41.075505: Pseudo dice [0.936, 0.861, 0.9039] +2023-05-26 21:17:41.075641: Epoch time: 37.8 s +2023-05-26 21:17:44.229547: +2023-05-26 21:17:44.229981: Epoch 850 +2023-05-26 21:17:44.230275: Current learning rate: 0.00181 +2023-05-26 21:18:22.429807: train_loss -0.9727 +2023-05-26 21:18:22.430040: val_loss -0.5783 +2023-05-26 21:18:22.430167: Pseudo dice [0.9374, 0.8623, 0.9008] +2023-05-26 21:18:22.430273: Epoch time: 38.2 s +2023-05-26 21:18:23.976387: +2023-05-26 21:18:23.976703: Epoch 851 +2023-05-26 21:18:23.976990: Current learning rate: 0.0018 +2023-05-26 21:19:01.578488: train_loss -0.973 +2023-05-26 21:19:01.578761: val_loss -0.5766 +2023-05-26 21:19:01.578902: Pseudo dice [0.9366, 0.8614, 0.9013] +2023-05-26 21:19:01.578995: Epoch time: 37.6 s +2023-05-26 21:19:03.050334: +2023-05-26 21:19:03.050725: Epoch 852 +2023-05-26 21:19:03.050989: Current learning rate: 0.00179 +2023-05-26 21:19:40.957533: train_loss -0.9733 +2023-05-26 21:19:40.957899: val_loss -0.5755 +2023-05-26 21:19:40.958035: Pseudo dice [0.937, 0.8637, 0.8998] +2023-05-26 21:19:40.958138: Epoch time: 37.91 s +2023-05-26 21:19:42.564634: +2023-05-26 21:19:42.564825: Epoch 853 +2023-05-26 21:19:42.564940: Current learning rate: 0.00178 +2023-05-26 21:20:20.141087: train_loss -0.9733 +2023-05-26 21:20:20.141318: val_loss -0.574 +2023-05-26 21:20:20.141427: Pseudo dice [0.9349, 0.8599, 0.8992] +2023-05-26 21:20:20.141526: Epoch time: 37.58 s +2023-05-26 21:20:21.635246: +2023-05-26 21:20:21.635424: Epoch 854 +2023-05-26 21:20:21.635545: Current learning rate: 0.00177 +2023-05-26 21:20:59.502961: train_loss -0.9731 +2023-05-26 21:20:59.503207: val_loss -0.5782 +2023-05-26 21:20:59.503339: Pseudo dice [0.9353, 0.8608, 0.9006] +2023-05-26 21:20:59.503428: Epoch time: 37.87 s +2023-05-26 21:21:01.329942: +2023-05-26 21:21:01.330234: Epoch 855 +2023-05-26 21:21:01.330455: Current learning rate: 0.00176 +2023-05-26 21:21:39.006387: train_loss -0.9733 +2023-05-26 21:21:39.006657: val_loss -0.5676 +2023-05-26 21:21:39.006796: Pseudo dice [0.9367, 0.8606, 0.8959] +2023-05-26 21:21:39.006912: Epoch time: 37.68 s +2023-05-26 21:21:40.513195: +2023-05-26 21:21:40.513632: Epoch 856 +2023-05-26 21:21:40.513879: Current learning rate: 0.00175 +2023-05-26 21:22:18.181594: train_loss -0.9736 +2023-05-26 21:22:18.181877: val_loss -0.5723 +2023-05-26 21:22:18.182008: Pseudo dice [0.9369, 0.8618, 0.8986] +2023-05-26 21:22:18.182112: Epoch time: 37.67 s +2023-05-26 21:22:19.829837: +2023-05-26 21:22:19.830024: Epoch 857 +2023-05-26 21:22:19.830146: Current learning rate: 0.00174 +2023-05-26 21:22:57.528154: train_loss -0.9733 +2023-05-26 21:22:57.528380: val_loss -0.5686 +2023-05-26 21:22:57.528488: Pseudo dice [0.9351, 0.8603, 0.9006] +2023-05-26 21:22:57.528580: Epoch time: 37.7 s +2023-05-26 21:22:58.934439: +2023-05-26 21:22:58.934646: Epoch 858 +2023-05-26 21:22:58.934748: Current learning rate: 0.00173 +2023-05-26 21:23:36.521209: train_loss -0.9736 +2023-05-26 21:23:36.521496: val_loss -0.5723 +2023-05-26 21:23:36.521624: Pseudo dice [0.9357, 0.8585, 0.901] +2023-05-26 21:23:36.521715: Epoch time: 37.59 s +2023-05-26 21:23:38.149403: +2023-05-26 21:23:38.149604: Epoch 859 +2023-05-26 21:23:38.149729: Current learning rate: 0.00172 +2023-05-26 21:24:15.884351: train_loss -0.9734 +2023-05-26 21:24:15.884628: val_loss -0.5784 +2023-05-26 21:24:15.884750: Pseudo dice [0.935, 0.861, 0.9007] +2023-05-26 21:24:15.884837: Epoch time: 37.74 s +2023-05-26 21:24:17.504373: +2023-05-26 21:24:17.504829: Epoch 860 +2023-05-26 21:24:17.505069: Current learning rate: 0.0017 +2023-05-26 21:24:55.207160: train_loss -0.9734 +2023-05-26 21:24:55.207536: val_loss -0.5826 +2023-05-26 21:24:55.208018: Pseudo dice [0.9379, 0.8631, 0.902] +2023-05-26 21:24:55.208175: Epoch time: 37.7 s +2023-05-26 21:24:56.766678: +2023-05-26 21:24:56.766871: Epoch 861 +2023-05-26 21:24:56.766997: Current learning rate: 0.00169 +2023-05-26 21:25:34.863716: train_loss -0.9738 +2023-05-26 21:25:34.863980: val_loss -0.5742 +2023-05-26 21:25:34.864098: Pseudo dice [0.9348, 0.8584, 0.9005] +2023-05-26 21:25:34.864200: Epoch time: 38.1 s +2023-05-26 21:25:36.750596: +2023-05-26 21:25:36.750812: Epoch 862 +2023-05-26 21:25:36.750964: Current learning rate: 0.00168 +2023-05-26 21:26:14.580218: train_loss -0.9732 +2023-05-26 21:26:14.580549: val_loss -0.5778 +2023-05-26 21:26:14.580682: Pseudo dice [0.9364, 0.8629, 0.9003] +2023-05-26 21:26:14.580780: Epoch time: 37.83 s +2023-05-26 21:26:16.239834: +2023-05-26 21:26:16.240025: Epoch 863 +2023-05-26 21:26:16.240150: Current learning rate: 0.00167 +2023-05-26 21:26:53.850811: train_loss -0.9737 +2023-05-26 21:26:53.851221: val_loss -0.5783 +2023-05-26 21:26:53.851683: Pseudo dice [0.9369, 0.8643, 0.8996] +2023-05-26 21:26:53.851793: Epoch time: 37.61 s +2023-05-26 21:26:55.547086: +2023-05-26 21:26:55.547513: Epoch 864 +2023-05-26 21:26:55.547708: Current learning rate: 0.00166 +2023-05-26 21:27:33.207322: train_loss -0.9737 +2023-05-26 21:27:33.207680: val_loss -0.5749 +2023-05-26 21:27:33.207788: Pseudo dice [0.9369, 0.8614, 0.9003] +2023-05-26 21:27:33.207878: Epoch time: 37.66 s +2023-05-26 21:27:34.771611: +2023-05-26 21:27:34.771809: Epoch 865 +2023-05-26 21:27:34.771942: Current learning rate: 0.00165 +2023-05-26 21:28:12.362134: train_loss -0.9736 +2023-05-26 21:28:12.362366: val_loss -0.5625 +2023-05-26 21:28:12.362483: Pseudo dice [0.9364, 0.8607, 0.8975] +2023-05-26 21:28:12.362599: Epoch time: 37.59 s +2023-05-26 21:28:13.753056: +2023-05-26 21:28:13.753228: Epoch 866 +2023-05-26 21:28:13.753334: Current learning rate: 0.00164 +2023-05-26 21:28:51.268090: train_loss -0.9735 +2023-05-26 21:28:51.268355: val_loss -0.5696 +2023-05-26 21:28:51.268851: Pseudo dice [0.9357, 0.8589, 0.9023] +2023-05-26 21:28:51.268960: Epoch time: 37.52 s +2023-05-26 21:28:52.785311: +2023-05-26 21:28:52.785828: Epoch 867 +2023-05-26 21:28:52.786081: Current learning rate: 0.00163 +2023-05-26 21:29:30.453077: train_loss -0.974 +2023-05-26 21:29:30.453343: val_loss -0.5748 +2023-05-26 21:29:30.453465: Pseudo dice [0.9361, 0.8605, 0.8992] +2023-05-26 21:29:30.453571: Epoch time: 37.67 s +2023-05-26 21:29:31.991443: +2023-05-26 21:29:31.991798: Epoch 868 +2023-05-26 21:29:31.992034: Current learning rate: 0.00162 +2023-05-26 21:30:09.904832: train_loss -0.9739 +2023-05-26 21:30:09.905112: val_loss -0.57 +2023-05-26 21:30:09.905247: Pseudo dice [0.9366, 0.862, 0.9028] +2023-05-26 21:30:09.905344: Epoch time: 37.91 s +2023-05-26 21:30:12.069617: +2023-05-26 21:30:12.070061: Epoch 869 +2023-05-26 21:30:12.070383: Current learning rate: 0.00161 +2023-05-26 21:30:49.687329: train_loss -0.9739 +2023-05-26 21:30:49.687634: val_loss -0.5725 +2023-05-26 21:30:49.687766: Pseudo dice [0.9374, 0.8622, 0.9013] +2023-05-26 21:30:49.687856: Epoch time: 37.62 s +2023-05-26 21:30:51.357463: +2023-05-26 21:30:51.357635: Epoch 870 +2023-05-26 21:30:51.357750: Current learning rate: 0.00159 +2023-05-26 21:31:29.020577: train_loss -0.9737 +2023-05-26 21:31:29.020823: val_loss -0.5741 +2023-05-26 21:31:29.020943: Pseudo dice [0.936, 0.8604, 0.9047] +2023-05-26 21:31:29.021045: Epoch time: 37.66 s +2023-05-26 21:31:30.502580: +2023-05-26 21:31:30.502790: Epoch 871 +2023-05-26 21:31:30.502919: Current learning rate: 0.00158 +2023-05-26 21:32:08.140125: train_loss -0.9739 +2023-05-26 21:32:08.140375: val_loss -0.5743 +2023-05-26 21:32:08.141031: Pseudo dice [0.9369, 0.8621, 0.901] +2023-05-26 21:32:08.141181: Epoch time: 37.64 s +2023-05-26 21:32:09.695644: +2023-05-26 21:32:09.696100: Epoch 872 +2023-05-26 21:32:09.696528: Current learning rate: 0.00157 +2023-05-26 21:32:47.310699: train_loss -0.9743 +2023-05-26 21:32:47.311097: val_loss -0.5687 +2023-05-26 21:32:47.311218: Pseudo dice [0.9368, 0.8627, 0.903] +2023-05-26 21:32:47.311321: Epoch time: 37.62 s +2023-05-26 21:32:48.884483: +2023-05-26 21:32:48.884657: Epoch 873 +2023-05-26 21:32:48.884778: Current learning rate: 0.00156 +2023-05-26 21:33:26.121596: train_loss -0.9738 +2023-05-26 21:33:26.121895: val_loss -0.5716 +2023-05-26 21:33:26.122091: Pseudo dice [0.9368, 0.8615, 0.9012] +2023-05-26 21:33:26.122200: Epoch time: 37.24 s +2023-05-26 21:33:27.620484: +2023-05-26 21:33:27.620801: Epoch 874 +2023-05-26 21:33:27.620978: Current learning rate: 0.00155 +2023-05-26 21:34:05.206577: train_loss -0.9741 +2023-05-26 21:34:05.206839: val_loss -0.5725 +2023-05-26 21:34:05.207465: Pseudo dice [0.9369, 0.8624, 0.8999] +2023-05-26 21:34:05.207566: Epoch time: 37.59 s +2023-05-26 21:34:06.805789: +2023-05-26 21:34:06.805958: Epoch 875 +2023-05-26 21:34:06.806088: Current learning rate: 0.00154 +2023-05-26 21:34:44.754584: train_loss -0.9743 +2023-05-26 21:34:44.754875: val_loss -0.5668 +2023-05-26 21:34:44.755002: Pseudo dice [0.9356, 0.8594, 0.9003] +2023-05-26 21:34:44.755088: Epoch time: 37.95 s +2023-05-26 21:34:46.360025: +2023-05-26 21:34:46.360483: Epoch 876 +2023-05-26 21:34:46.360753: Current learning rate: 0.00153 +2023-05-26 21:35:24.086858: train_loss -0.9742 +2023-05-26 21:35:24.087092: val_loss -0.572 +2023-05-26 21:35:24.087210: Pseudo dice [0.936, 0.8603, 0.9004] +2023-05-26 21:35:24.087382: Epoch time: 37.73 s +2023-05-26 21:35:25.585793: +2023-05-26 21:35:25.586213: Epoch 877 +2023-05-26 21:35:25.586487: Current learning rate: 0.00152 +2023-05-26 21:36:03.273866: train_loss -0.9741 +2023-05-26 21:36:03.274132: val_loss -0.5718 +2023-05-26 21:36:03.274251: Pseudo dice [0.9368, 0.8614, 0.9025] +2023-05-26 21:36:03.274335: Epoch time: 37.69 s +2023-05-26 21:36:04.877009: +2023-05-26 21:36:04.877449: Epoch 878 +2023-05-26 21:36:04.877588: Current learning rate: 0.00151 +2023-05-26 21:36:42.519171: train_loss -0.9745 +2023-05-26 21:36:42.519459: val_loss -0.5737 +2023-05-26 21:36:42.519590: Pseudo dice [0.9369, 0.8615, 0.9052] +2023-05-26 21:36:42.519692: Epoch time: 37.64 s +2023-05-26 21:36:44.195822: +2023-05-26 21:36:44.196458: Epoch 879 +2023-05-26 21:36:44.196698: Current learning rate: 0.00149 +2023-05-26 21:37:22.252744: train_loss -0.9743 +2023-05-26 21:37:22.252989: val_loss -0.5742 +2023-05-26 21:37:22.253300: Pseudo dice [0.9376, 0.8633, 0.9002] +2023-05-26 21:37:22.253447: Epoch time: 38.06 s +2023-05-26 21:37:23.890755: +2023-05-26 21:37:23.891120: Epoch 880 +2023-05-26 21:37:23.891353: Current learning rate: 0.00148 +2023-05-26 21:38:01.587088: train_loss -0.9744 +2023-05-26 21:38:01.587397: val_loss -0.566 +2023-05-26 21:38:01.587779: Pseudo dice [0.937, 0.8612, 0.8994] +2023-05-26 21:38:01.587945: Epoch time: 37.7 s +2023-05-26 21:38:03.211651: +2023-05-26 21:38:03.211882: Epoch 881 +2023-05-26 21:38:03.212017: Current learning rate: 0.00147 +2023-05-26 21:38:40.731395: train_loss -0.9743 +2023-05-26 21:38:40.731635: val_loss -0.5688 +2023-05-26 21:38:40.731748: Pseudo dice [0.9366, 0.8609, 0.8983] +2023-05-26 21:38:40.731847: Epoch time: 37.52 s +2023-05-26 21:38:42.507961: +2023-05-26 21:38:42.508297: Epoch 882 +2023-05-26 21:38:42.508480: Current learning rate: 0.00146 +2023-05-26 21:39:20.321612: train_loss -0.9747 +2023-05-26 21:39:20.321860: val_loss -0.5628 +2023-05-26 21:39:20.321977: Pseudo dice [0.9368, 0.861, 0.8992] +2023-05-26 21:39:20.322079: Epoch time: 37.81 s +2023-05-26 21:39:21.925315: +2023-05-26 21:39:21.925878: Epoch 883 +2023-05-26 21:39:21.926479: Current learning rate: 0.00145 +2023-05-26 21:39:59.593065: train_loss -0.9747 +2023-05-26 21:39:59.593306: val_loss -0.5677 +2023-05-26 21:39:59.593424: Pseudo dice [0.9354, 0.8603, 0.9028] +2023-05-26 21:39:59.593529: Epoch time: 37.67 s +2023-05-26 21:40:01.095687: +2023-05-26 21:40:01.096353: Epoch 884 +2023-05-26 21:40:01.096737: Current learning rate: 0.00144 +2023-05-26 21:40:38.930865: train_loss -0.975 +2023-05-26 21:40:38.931152: val_loss -0.5646 +2023-05-26 21:40:38.931311: Pseudo dice [0.9358, 0.8613, 0.8974] +2023-05-26 21:40:38.931421: Epoch time: 37.84 s +2023-05-26 21:40:40.395094: +2023-05-26 21:40:40.395258: Epoch 885 +2023-05-26 21:40:40.395431: Current learning rate: 0.00143 +2023-05-26 21:41:18.081574: train_loss -0.9751 +2023-05-26 21:41:18.082032: val_loss -0.5784 +2023-05-26 21:41:18.082150: Pseudo dice [0.9375, 0.8633, 0.9029] +2023-05-26 21:41:18.082246: Epoch time: 37.69 s +2023-05-26 21:41:19.652219: +2023-05-26 21:41:19.652486: Epoch 886 +2023-05-26 21:41:19.652749: Current learning rate: 0.00142 +2023-05-26 21:41:57.205314: train_loss -0.9747 +2023-05-26 21:41:57.205673: val_loss -0.5713 +2023-05-26 21:41:57.205796: Pseudo dice [0.9369, 0.8626, 0.9036] +2023-05-26 21:41:57.205889: Epoch time: 37.55 s +2023-05-26 21:41:58.710255: +2023-05-26 21:41:58.710479: Epoch 887 +2023-05-26 21:41:58.710604: Current learning rate: 0.00141 +2023-05-26 21:42:36.484381: train_loss -0.9744 +2023-05-26 21:42:36.484669: val_loss -0.5554 +2023-05-26 21:42:36.484803: Pseudo dice [0.9357, 0.8605, 0.8951] +2023-05-26 21:42:36.484900: Epoch time: 37.78 s +2023-05-26 21:42:38.061244: +2023-05-26 21:42:38.061414: Epoch 888 +2023-05-26 21:42:38.061530: Current learning rate: 0.00139 +2023-05-26 21:43:16.193275: train_loss -0.9751 +2023-05-26 21:43:16.193564: val_loss -0.5737 +2023-05-26 21:43:16.193711: Pseudo dice [0.9374, 0.863, 0.9009] +2023-05-26 21:43:16.193810: Epoch time: 38.13 s +2023-05-26 21:43:18.325643: +2023-05-26 21:43:18.326338: Epoch 889 +2023-05-26 21:43:18.326672: Current learning rate: 0.00138 +2023-05-26 21:43:56.225186: train_loss -0.9751 +2023-05-26 21:43:56.225433: val_loss -0.5676 +2023-05-26 21:43:56.225534: Pseudo dice [0.9359, 0.8623, 0.9008] +2023-05-26 21:43:56.225626: Epoch time: 37.9 s +2023-05-26 21:43:58.023049: +2023-05-26 21:43:58.023227: Epoch 890 +2023-05-26 21:43:58.023364: Current learning rate: 0.00137 +2023-05-26 21:44:35.780295: train_loss -0.9751 +2023-05-26 21:44:35.780530: val_loss -0.572 +2023-05-26 21:44:35.780664: Pseudo dice [0.9363, 0.8618, 0.9056] +2023-05-26 21:44:35.780770: Epoch time: 37.76 s +2023-05-26 21:44:37.266995: +2023-05-26 21:44:37.267349: Epoch 891 +2023-05-26 21:44:37.267635: Current learning rate: 0.00136 +2023-05-26 21:45:15.080343: train_loss -0.975 +2023-05-26 21:45:15.080570: val_loss -0.5642 +2023-05-26 21:45:15.080681: Pseudo dice [0.9361, 0.8614, 0.9021] +2023-05-26 21:45:15.080783: Epoch time: 37.81 s +2023-05-26 21:45:16.783474: +2023-05-26 21:45:16.783641: Epoch 892 +2023-05-26 21:45:16.783759: Current learning rate: 0.00135 +2023-05-26 21:45:54.383723: train_loss -0.9751 +2023-05-26 21:45:54.384022: val_loss -0.572 +2023-05-26 21:45:54.384336: Pseudo dice [0.9372, 0.8622, 0.9042] +2023-05-26 21:45:54.384529: Epoch time: 37.6 s +2023-05-26 21:45:55.956496: +2023-05-26 21:45:55.957011: Epoch 893 +2023-05-26 21:45:55.957283: Current learning rate: 0.00134 +2023-05-26 21:46:33.676914: train_loss -0.975 +2023-05-26 21:46:33.677190: val_loss -0.5687 +2023-05-26 21:46:33.677329: Pseudo dice [0.937, 0.8625, 0.901] +2023-05-26 21:46:33.677567: Epoch time: 37.72 s +2023-05-26 21:46:35.183723: +2023-05-26 21:46:35.184063: Epoch 894 +2023-05-26 21:46:35.184268: Current learning rate: 0.00133 +2023-05-26 21:47:12.823400: train_loss -0.9755 +2023-05-26 21:47:12.823695: val_loss -0.5616 +2023-05-26 21:47:12.823824: Pseudo dice [0.9363, 0.8624, 0.8985] +2023-05-26 21:47:12.823915: Epoch time: 37.64 s +2023-05-26 21:47:14.350853: +2023-05-26 21:47:14.351199: Epoch 895 +2023-05-26 21:47:14.351456: Current learning rate: 0.00132 +2023-05-26 21:47:52.048240: train_loss -0.9755 +2023-05-26 21:47:52.048487: val_loss -0.5676 +2023-05-26 21:47:52.048610: Pseudo dice [0.9368, 0.8616, 0.9017] +2023-05-26 21:47:52.048715: Epoch time: 37.7 s +2023-05-26 21:47:53.997627: +2023-05-26 21:47:53.997862: Epoch 896 +2023-05-26 21:47:53.998002: Current learning rate: 0.0013 +2023-05-26 21:48:32.051809: train_loss -0.9755 +2023-05-26 21:48:32.052088: val_loss -0.5673 +2023-05-26 21:48:32.052226: Pseudo dice [0.9372, 0.8625, 0.9012] +2023-05-26 21:48:32.052324: Epoch time: 38.06 s +2023-05-26 21:48:33.645312: +2023-05-26 21:48:33.645533: Epoch 897 +2023-05-26 21:48:33.645672: Current learning rate: 0.00129 +2023-05-26 21:49:11.186876: train_loss -0.9756 +2023-05-26 21:49:11.187724: val_loss -0.5691 +2023-05-26 21:49:11.187883: Pseudo dice [0.9363, 0.8627, 0.9026] +2023-05-26 21:49:11.188022: Epoch time: 37.54 s +2023-05-26 21:49:12.645254: +2023-05-26 21:49:12.645436: Epoch 898 +2023-05-26 21:49:12.645543: Current learning rate: 0.00128 +2023-05-26 21:49:50.194922: train_loss -0.9754 +2023-05-26 21:49:50.195160: val_loss -0.5632 +2023-05-26 21:49:50.195282: Pseudo dice [0.9365, 0.8627, 0.9015] +2023-05-26 21:49:50.195370: Epoch time: 37.55 s +2023-05-26 21:49:51.697286: +2023-05-26 21:49:51.697622: Epoch 899 +2023-05-26 21:49:51.697831: Current learning rate: 0.00127 +2023-05-26 21:50:29.302329: train_loss -0.9756 +2023-05-26 21:50:29.302739: val_loss -0.5574 +2023-05-26 21:50:29.303008: Pseudo dice [0.9372, 0.8627, 0.8986] +2023-05-26 21:50:29.303170: Epoch time: 37.61 s +2023-05-26 21:50:32.628261: +2023-05-26 21:50:32.628431: Epoch 900 +2023-05-26 21:50:32.628560: Current learning rate: 0.00126 +2023-05-26 21:51:09.959934: train_loss -0.9756 +2023-05-26 21:51:09.960246: val_loss -0.5614 +2023-05-26 21:51:09.960375: Pseudo dice [0.9356, 0.8613, 0.9038] +2023-05-26 21:51:09.960470: Epoch time: 37.33 s +2023-05-26 21:51:11.460545: +2023-05-26 21:51:11.460977: Epoch 901 +2023-05-26 21:51:11.461426: Current learning rate: 0.00125 +2023-05-26 21:51:49.277566: train_loss -0.9755 +2023-05-26 21:51:49.278044: val_loss -0.5768 +2023-05-26 21:51:49.278301: Pseudo dice [0.9387, 0.866, 0.9042] +2023-05-26 21:51:49.278408: Epoch time: 37.82 s +2023-05-26 21:51:51.310236: +2023-05-26 21:51:51.310960: Epoch 902 +2023-05-26 21:51:51.311090: Current learning rate: 0.00124 +2023-05-26 21:52:28.976212: train_loss -0.9763 +2023-05-26 21:52:28.976487: val_loss -0.5661 +2023-05-26 21:52:28.976613: Pseudo dice [0.9377, 0.8621, 0.9011] +2023-05-26 21:52:28.976714: Epoch time: 37.67 s +2023-05-26 21:52:30.657489: +2023-05-26 21:52:30.658386: Epoch 903 +2023-05-26 21:52:30.658543: Current learning rate: 0.00122 +2023-05-26 21:53:08.370486: train_loss -0.9763 +2023-05-26 21:53:08.370768: val_loss -0.565 +2023-05-26 21:53:08.370934: Pseudo dice [0.9374, 0.8627, 0.9008] +2023-05-26 21:53:08.371037: Epoch time: 37.71 s +2023-05-26 21:53:09.964320: +2023-05-26 21:53:09.964535: Epoch 904 +2023-05-26 21:53:09.964672: Current learning rate: 0.00121 +2023-05-26 21:53:47.603301: train_loss -0.9754 +2023-05-26 21:53:47.603817: val_loss -0.5616 +2023-05-26 21:53:47.603941: Pseudo dice [0.9359, 0.8613, 0.9032] +2023-05-26 21:53:47.604035: Epoch time: 37.64 s +2023-05-26 21:53:49.184838: +2023-05-26 21:53:49.185041: Epoch 905 +2023-05-26 21:53:49.185249: Current learning rate: 0.0012 +2023-05-26 21:54:27.019969: train_loss -0.9757 +2023-05-26 21:54:27.020268: val_loss -0.5651 +2023-05-26 21:54:27.020403: Pseudo dice [0.936, 0.86, 0.901] +2023-05-26 21:54:27.020504: Epoch time: 37.84 s +2023-05-26 21:54:28.552324: +2023-05-26 21:54:28.552514: Epoch 906 +2023-05-26 21:54:28.552633: Current learning rate: 0.00119 +2023-05-26 21:55:06.469224: train_loss -0.976 +2023-05-26 21:55:06.469498: val_loss -0.5688 +2023-05-26 21:55:06.469628: Pseudo dice [0.9379, 0.8631, 0.9036] +2023-05-26 21:55:06.469718: Epoch time: 37.92 s +2023-05-26 21:55:08.099755: +2023-05-26 21:55:08.099922: Epoch 907 +2023-05-26 21:55:08.100032: Current learning rate: 0.00118 +2023-05-26 21:55:45.205705: train_loss -0.9759 +2023-05-26 21:55:45.205909: val_loss -0.5708 +2023-05-26 21:55:45.206003: Pseudo dice [0.9369, 0.8627, 0.9055] +2023-05-26 21:55:45.206087: Epoch time: 37.11 s +2023-05-26 21:55:46.627132: +2023-05-26 21:55:46.627326: Epoch 908 +2023-05-26 21:55:46.627452: Current learning rate: 0.00117 +2023-05-26 21:56:24.098915: train_loss -0.976 +2023-05-26 21:56:24.099152: val_loss -0.5627 +2023-05-26 21:56:24.099267: Pseudo dice [0.9373, 0.864, 0.9035] +2023-05-26 21:56:24.099367: Epoch time: 37.47 s +2023-05-26 21:56:25.995530: +2023-05-26 21:56:25.995719: Epoch 909 +2023-05-26 21:56:25.995834: Current learning rate: 0.00116 +2023-05-26 21:57:04.252892: train_loss -0.9764 +2023-05-26 21:57:04.253153: val_loss -0.5597 +2023-05-26 21:57:04.253295: Pseudo dice [0.9372, 0.8614, 0.9032] +2023-05-26 21:57:04.253386: Epoch time: 38.26 s +2023-05-26 21:57:05.838485: +2023-05-26 21:57:05.838868: Epoch 910 +2023-05-26 21:57:05.839123: Current learning rate: 0.00115 +2023-05-26 21:57:43.737761: train_loss -0.9764 +2023-05-26 21:57:43.738094: val_loss -0.5458 +2023-05-26 21:57:43.738247: Pseudo dice [0.9349, 0.8585, 0.9007] +2023-05-26 21:57:43.738345: Epoch time: 37.9 s +2023-05-26 21:57:45.348318: +2023-05-26 21:57:45.348513: Epoch 911 +2023-05-26 21:57:45.348622: Current learning rate: 0.00113 +2023-05-26 21:58:23.038145: train_loss -0.9765 +2023-05-26 21:58:23.038469: val_loss -0.5554 +2023-05-26 21:58:23.038629: Pseudo dice [0.9378, 0.8626, 0.9011] +2023-05-26 21:58:23.038743: Epoch time: 37.69 s +2023-05-26 21:58:24.593532: +2023-05-26 21:58:24.593718: Epoch 912 +2023-05-26 21:58:24.593834: Current learning rate: 0.00112 +2023-05-26 21:59:02.391555: train_loss -0.9767 +2023-05-26 21:59:02.391827: val_loss -0.5656 +2023-05-26 21:59:02.391961: Pseudo dice [0.9373, 0.8629, 0.902] +2023-05-26 21:59:02.392069: Epoch time: 37.8 s +2023-05-26 21:59:03.983080: +2023-05-26 21:59:03.983271: Epoch 913 +2023-05-26 21:59:03.983403: Current learning rate: 0.00111 +2023-05-26 21:59:41.623621: train_loss -0.9763 +2023-05-26 21:59:41.623863: val_loss -0.5598 +2023-05-26 21:59:41.623979: Pseudo dice [0.938, 0.8631, 0.9005] +2023-05-26 21:59:41.624082: Epoch time: 37.64 s +2023-05-26 21:59:43.172094: +2023-05-26 21:59:43.172314: Epoch 914 +2023-05-26 21:59:43.172457: Current learning rate: 0.0011 +2023-05-26 22:00:20.712282: train_loss -0.9763 +2023-05-26 22:00:20.712655: val_loss -0.5572 +2023-05-26 22:00:20.712882: Pseudo dice [0.9371, 0.8617, 0.9016] +2023-05-26 22:00:20.713067: Epoch time: 37.54 s +2023-05-26 22:00:22.337901: +2023-05-26 22:00:22.338193: Epoch 915 +2023-05-26 22:00:22.338422: Current learning rate: 0.00109 +2023-05-26 22:01:00.015709: train_loss -0.9763 +2023-05-26 22:01:00.015965: val_loss -0.549 +2023-05-26 22:01:00.016096: Pseudo dice [0.9353, 0.8592, 0.9009] +2023-05-26 22:01:00.016186: Epoch time: 37.68 s +2023-05-26 22:01:01.843374: +2023-05-26 22:01:01.843700: Epoch 916 +2023-05-26 22:01:01.843857: Current learning rate: 0.00108 +2023-05-26 22:01:40.004797: train_loss -0.9765 +2023-05-26 22:01:40.005096: val_loss -0.5552 +2023-05-26 22:01:40.005275: Pseudo dice [0.9368, 0.862, 0.8973] +2023-05-26 22:01:40.005391: Epoch time: 38.16 s +2023-05-26 22:01:41.592210: +2023-05-26 22:01:41.592553: Epoch 917 +2023-05-26 22:01:41.592793: Current learning rate: 0.00106 +2023-05-26 22:02:19.282640: train_loss -0.9764 +2023-05-26 22:02:19.282920: val_loss -0.5648 +2023-05-26 22:02:19.283060: Pseudo dice [0.9374, 0.8634, 0.9031] +2023-05-26 22:02:19.283162: Epoch time: 37.69 s +2023-05-26 22:02:20.796864: +2023-05-26 22:02:20.797067: Epoch 918 +2023-05-26 22:02:20.797178: Current learning rate: 0.00105 +2023-05-26 22:02:58.712324: train_loss -0.9767 +2023-05-26 22:02:58.713192: val_loss -0.5526 +2023-05-26 22:02:58.713575: Pseudo dice [0.9371, 0.8617, 0.8994] +2023-05-26 22:02:58.713840: Epoch time: 37.92 s +2023-05-26 22:03:00.512538: +2023-05-26 22:03:00.512739: Epoch 919 +2023-05-26 22:03:00.512857: Current learning rate: 0.00104 +2023-05-26 22:03:38.009650: train_loss -0.9767 +2023-05-26 22:03:38.009888: val_loss -0.5525 +2023-05-26 22:03:38.009997: Pseudo dice [0.9364, 0.8617, 0.8992] +2023-05-26 22:03:38.010096: Epoch time: 37.5 s +2023-05-26 22:03:39.516464: +2023-05-26 22:03:39.516963: Epoch 920 +2023-05-26 22:03:39.517109: Current learning rate: 0.00103 +2023-05-26 22:04:17.016646: train_loss -0.9767 +2023-05-26 22:04:17.016896: val_loss -0.5513 +2023-05-26 22:04:17.017010: Pseudo dice [0.9357, 0.8608, 0.9022] +2023-05-26 22:04:17.017109: Epoch time: 37.5 s +2023-05-26 22:04:18.574721: +2023-05-26 22:04:18.575017: Epoch 921 +2023-05-26 22:04:18.575169: Current learning rate: 0.00102 +2023-05-26 22:04:56.219778: train_loss -0.9767 +2023-05-26 22:04:56.220050: val_loss -0.5523 +2023-05-26 22:04:56.220182: Pseudo dice [0.9367, 0.8614, 0.9025] +2023-05-26 22:04:56.220310: Epoch time: 37.65 s +2023-05-26 22:04:57.685618: +2023-05-26 22:04:57.686005: Epoch 922 +2023-05-26 22:04:57.686390: Current learning rate: 0.00101 +2023-05-26 22:05:35.207665: train_loss -0.977 +2023-05-26 22:05:35.207909: val_loss -0.5492 +2023-05-26 22:05:35.208032: Pseudo dice [0.9362, 0.8611, 0.9008] +2023-05-26 22:05:35.208621: Epoch time: 37.52 s +2023-05-26 22:05:37.210338: +2023-05-26 22:05:37.210500: Epoch 923 +2023-05-26 22:05:37.210611: Current learning rate: 0.001 +2023-05-26 22:06:14.670069: train_loss -0.9774 +2023-05-26 22:06:14.670282: val_loss -0.5455 +2023-05-26 22:06:14.670391: Pseudo dice [0.9362, 0.8624, 0.8991] +2023-05-26 22:06:14.670479: Epoch time: 37.46 s +2023-05-26 22:06:16.145460: +2023-05-26 22:06:16.145892: Epoch 924 +2023-05-26 22:06:16.146090: Current learning rate: 0.00098 +2023-05-26 22:06:53.633732: train_loss -0.9771 +2023-05-26 22:06:53.633993: val_loss -0.5443 +2023-05-26 22:06:53.634125: Pseudo dice [0.9357, 0.8607, 0.8978] +2023-05-26 22:06:53.634239: Epoch time: 37.49 s +2023-05-26 22:06:55.125262: +2023-05-26 22:06:55.125451: Epoch 925 +2023-05-26 22:06:55.125570: Current learning rate: 0.00097 +2023-05-26 22:07:33.061250: train_loss -0.9769 +2023-05-26 22:07:33.061507: val_loss -0.5586 +2023-05-26 22:07:33.061641: Pseudo dice [0.9359, 0.8627, 0.9023] +2023-05-26 22:07:33.061755: Epoch time: 37.94 s +2023-05-26 22:07:34.734649: +2023-05-26 22:07:34.734999: Epoch 926 +2023-05-26 22:07:34.735268: Current learning rate: 0.00096 +2023-05-26 22:08:12.665070: train_loss -0.977 +2023-05-26 22:08:12.665381: val_loss -0.5514 +2023-05-26 22:08:12.665521: Pseudo dice [0.9357, 0.8602, 0.902] +2023-05-26 22:08:12.665612: Epoch time: 37.93 s +2023-05-26 22:08:14.209906: +2023-05-26 22:08:14.210239: Epoch 927 +2023-05-26 22:08:14.210454: Current learning rate: 0.00095 +2023-05-26 22:08:52.120688: train_loss -0.977 +2023-05-26 22:08:52.120981: val_loss -0.557 +2023-05-26 22:08:52.121105: Pseudo dice [0.9372, 0.8616, 0.9038] +2023-05-26 22:08:52.121192: Epoch time: 37.91 s +2023-05-26 22:08:53.567128: +2023-05-26 22:08:53.567294: Epoch 928 +2023-05-26 22:08:53.567418: Current learning rate: 0.00094 +2023-05-26 22:09:31.200666: train_loss -0.9769 +2023-05-26 22:09:31.200953: val_loss -0.5467 +2023-05-26 22:09:31.201070: Pseudo dice [0.9365, 0.8598, 0.901] +2023-05-26 22:09:31.201154: Epoch time: 37.63 s +2023-05-26 22:09:32.798954: +2023-05-26 22:09:32.799222: Epoch 929 +2023-05-26 22:09:32.799462: Current learning rate: 0.00092 +2023-05-26 22:10:10.677181: train_loss -0.9772 +2023-05-26 22:10:10.677447: val_loss -0.5456 +2023-05-26 22:10:10.677570: Pseudo dice [0.9355, 0.8605, 0.9013] +2023-05-26 22:10:10.677655: Epoch time: 37.88 s +2023-05-26 22:10:12.186281: +2023-05-26 22:10:12.186501: Epoch 930 +2023-05-26 22:10:12.186643: Current learning rate: 0.00091 +2023-05-26 22:10:49.849895: train_loss -0.9776 +2023-05-26 22:10:49.850177: val_loss -0.5529 +2023-05-26 22:10:49.850292: Pseudo dice [0.9366, 0.8624, 0.9056] +2023-05-26 22:10:49.850389: Epoch time: 37.66 s +2023-05-26 22:10:51.539354: +2023-05-26 22:10:51.540127: Epoch 931 +2023-05-26 22:10:51.540552: Current learning rate: 0.0009 +2023-05-26 22:11:29.286503: train_loss -0.9775 +2023-05-26 22:11:29.286914: val_loss -0.5504 +2023-05-26 22:11:29.287107: Pseudo dice [0.9364, 0.8609, 0.9043] +2023-05-26 22:11:29.287235: Epoch time: 37.75 s +2023-05-26 22:11:30.769152: +2023-05-26 22:11:30.769443: Epoch 932 +2023-05-26 22:11:30.769669: Current learning rate: 0.00089 +2023-05-26 22:12:08.637016: train_loss -0.9775 +2023-05-26 22:12:08.637273: val_loss -0.5401 +2023-05-26 22:12:08.637388: Pseudo dice [0.9358, 0.859, 0.9013] +2023-05-26 22:12:08.637491: Epoch time: 37.87 s +2023-05-26 22:12:10.373176: +2023-05-26 22:12:10.373429: Epoch 933 +2023-05-26 22:12:10.373622: Current learning rate: 0.00088 +2023-05-26 22:12:49.137779: train_loss -0.9775 +2023-05-26 22:12:49.138065: val_loss -0.552 +2023-05-26 22:12:49.138209: Pseudo dice [0.936, 0.8614, 0.9028] +2023-05-26 22:12:49.138316: Epoch time: 38.77 s +2023-05-26 22:12:50.724917: +2023-05-26 22:12:50.725137: Epoch 934 +2023-05-26 22:12:50.725290: Current learning rate: 0.00087 +2023-05-26 22:13:28.573127: train_loss -0.9775 +2023-05-26 22:13:28.573388: val_loss -0.5442 +2023-05-26 22:13:28.573527: Pseudo dice [0.9361, 0.8595, 0.902] +2023-05-26 22:13:28.573634: Epoch time: 37.85 s +2023-05-26 22:13:30.152320: +2023-05-26 22:13:30.152533: Epoch 935 +2023-05-26 22:13:30.152659: Current learning rate: 0.00085 +2023-05-26 22:14:07.642657: train_loss -0.9777 +2023-05-26 22:14:07.642928: val_loss -0.5451 +2023-05-26 22:14:07.643071: Pseudo dice [0.9367, 0.8614, 0.9017] +2023-05-26 22:14:07.643165: Epoch time: 37.49 s +2023-05-26 22:14:09.456946: +2023-05-26 22:14:09.457183: Epoch 936 +2023-05-26 22:14:09.457326: Current learning rate: 0.00084 +2023-05-26 22:14:47.216127: train_loss -0.9778 +2023-05-26 22:14:47.216522: val_loss -0.5428 +2023-05-26 22:14:47.216671: Pseudo dice [0.9354, 0.8599, 0.9045] +2023-05-26 22:14:47.216774: Epoch time: 37.76 s +2023-05-26 22:14:48.780642: +2023-05-26 22:14:48.781101: Epoch 937 +2023-05-26 22:14:48.781413: Current learning rate: 0.00083 +2023-05-26 22:15:26.474030: train_loss -0.9776 +2023-05-26 22:15:26.474341: val_loss -0.5397 +2023-05-26 22:15:26.474468: Pseudo dice [0.9368, 0.8617, 0.898] +2023-05-26 22:15:26.474560: Epoch time: 37.69 s +2023-05-26 22:15:27.999900: +2023-05-26 22:15:28.000148: Epoch 938 +2023-05-26 22:15:28.000528: Current learning rate: 0.00082 +2023-05-26 22:16:05.696438: train_loss -0.9774 +2023-05-26 22:16:05.697442: val_loss -0.5521 +2023-05-26 22:16:05.697574: Pseudo dice [0.9381, 0.863, 0.9037] +2023-05-26 22:16:05.697672: Epoch time: 37.7 s +2023-05-26 22:16:07.393776: +2023-05-26 22:16:07.394212: Epoch 939 +2023-05-26 22:16:07.394521: Current learning rate: 0.00081 +2023-05-26 22:16:46.233967: train_loss -0.9775 +2023-05-26 22:16:46.234251: val_loss -0.5505 +2023-05-26 22:16:46.234372: Pseudo dice [0.9363, 0.8616, 0.9038] +2023-05-26 22:16:46.234457: Epoch time: 38.84 s +2023-05-26 22:16:47.814003: +2023-05-26 22:16:47.814277: Epoch 940 +2023-05-26 22:16:47.814466: Current learning rate: 0.00079 +2023-05-26 22:17:25.550392: train_loss -0.9777 +2023-05-26 22:17:25.550795: val_loss -0.5472 +2023-05-26 22:17:25.551058: Pseudo dice [0.9382, 0.8631, 0.8982] +2023-05-26 22:17:25.551178: Epoch time: 37.74 s +2023-05-26 22:17:27.091772: +2023-05-26 22:17:27.092348: Epoch 941 +2023-05-26 22:17:27.092501: Current learning rate: 0.00078 +2023-05-26 22:18:04.617596: train_loss -0.9778 +2023-05-26 22:18:04.617868: val_loss -0.5406 +2023-05-26 22:18:04.618010: Pseudo dice [0.937, 0.8616, 0.901] +2023-05-26 22:18:04.618120: Epoch time: 37.53 s +2023-05-26 22:18:06.189039: +2023-05-26 22:18:06.189605: Epoch 942 +2023-05-26 22:18:06.190000: Current learning rate: 0.00077 +2023-05-26 22:18:44.042529: train_loss -0.9779 +2023-05-26 22:18:44.042862: val_loss -0.5429 +2023-05-26 22:18:44.042987: Pseudo dice [0.9359, 0.8602, 0.9003] +2023-05-26 22:18:44.043085: Epoch time: 37.85 s +2023-05-26 22:18:45.934111: +2023-05-26 22:18:45.934335: Epoch 943 +2023-05-26 22:18:45.934484: Current learning rate: 0.00076 +2023-05-26 22:19:23.706832: train_loss -0.9783 +2023-05-26 22:19:23.707119: val_loss -0.5472 +2023-05-26 22:19:23.707260: Pseudo dice [0.9359, 0.8623, 0.9032] +2023-05-26 22:19:23.707365: Epoch time: 37.77 s +2023-05-26 22:19:25.241798: +2023-05-26 22:19:25.242182: Epoch 944 +2023-05-26 22:19:25.242358: Current learning rate: 0.00075 +2023-05-26 22:20:02.738137: train_loss -0.9781 +2023-05-26 22:20:02.738402: val_loss -0.5332 +2023-05-26 22:20:02.738538: Pseudo dice [0.9357, 0.8618, 0.899] +2023-05-26 22:20:02.738652: Epoch time: 37.5 s +2023-05-26 22:20:04.230370: +2023-05-26 22:20:04.230553: Epoch 945 +2023-05-26 22:20:04.230666: Current learning rate: 0.00074 +2023-05-26 22:20:42.137218: train_loss -0.978 +2023-05-26 22:20:42.137460: val_loss -0.5402 +2023-05-26 22:20:42.137575: Pseudo dice [0.9368, 0.8624, 0.8985] +2023-05-26 22:20:42.137676: Epoch time: 37.91 s +2023-05-26 22:20:43.758778: +2023-05-26 22:20:43.759032: Epoch 946 +2023-05-26 22:20:43.759231: Current learning rate: 0.00072 +2023-05-26 22:21:22.124983: train_loss -0.9782 +2023-05-26 22:21:22.125300: val_loss -0.5387 +2023-05-26 22:21:22.125430: Pseudo dice [0.9373, 0.8618, 0.9028] +2023-05-26 22:21:22.125530: Epoch time: 38.37 s +2023-05-26 22:21:23.732714: +2023-05-26 22:21:23.733050: Epoch 947 +2023-05-26 22:21:23.733189: Current learning rate: 0.00071 +2023-05-26 22:22:03.583220: train_loss -0.9785 +2023-05-26 22:22:03.583615: val_loss -0.5308 +2023-05-26 22:22:03.583725: Pseudo dice [0.9359, 0.8592, 0.9011] +2023-05-26 22:22:03.583821: Epoch time: 39.85 s +2023-05-26 22:22:05.259850: +2023-05-26 22:22:05.260183: Epoch 948 +2023-05-26 22:22:05.260322: Current learning rate: 0.0007 +2023-05-26 22:22:43.331212: train_loss -0.9784 +2023-05-26 22:22:43.331486: val_loss -0.5461 +2023-05-26 22:22:43.331607: Pseudo dice [0.9367, 0.8611, 0.9039] +2023-05-26 22:22:43.331694: Epoch time: 38.07 s +2023-05-26 22:22:44.852070: +2023-05-26 22:22:44.852363: Epoch 949 +2023-05-26 22:22:44.852612: Current learning rate: 0.00069 +2023-05-26 22:23:22.456437: train_loss -0.9783 +2023-05-26 22:23:22.456693: val_loss -0.5429 +2023-05-26 22:23:22.456814: Pseudo dice [0.9353, 0.8613, 0.9002] +2023-05-26 22:23:22.456917: Epoch time: 37.61 s +2023-05-26 22:23:25.783867: +2023-05-26 22:23:25.784324: Epoch 950 +2023-05-26 22:23:25.784461: Current learning rate: 0.00067 +2023-05-26 22:24:03.527716: train_loss -0.9784 +2023-05-26 22:24:03.528119: val_loss -0.5401 +2023-05-26 22:24:03.528271: Pseudo dice [0.937, 0.8614, 0.9022] +2023-05-26 22:24:03.528364: Epoch time: 37.75 s +2023-05-26 22:24:04.995654: +2023-05-26 22:24:04.995854: Epoch 951 +2023-05-26 22:24:04.996041: Current learning rate: 0.00066 +2023-05-26 22:24:42.721853: train_loss -0.9777 +2023-05-26 22:24:42.722154: val_loss -0.5409 +2023-05-26 22:24:42.722285: Pseudo dice [0.9374, 0.8624, 0.9004] +2023-05-26 22:24:42.722378: Epoch time: 37.73 s +2023-05-26 22:24:44.326837: +2023-05-26 22:24:44.327120: Epoch 952 +2023-05-26 22:24:44.327418: Current learning rate: 0.00065 +2023-05-26 22:25:22.133933: train_loss -0.9784 +2023-05-26 22:25:22.134199: val_loss -0.542 +2023-05-26 22:25:22.134344: Pseudo dice [0.9371, 0.862, 0.9027] +2023-05-26 22:25:22.134457: Epoch time: 37.81 s +2023-05-26 22:25:23.695668: +2023-05-26 22:25:23.695974: Epoch 953 +2023-05-26 22:25:23.696104: Current learning rate: 0.00064 +2023-05-26 22:26:01.099601: train_loss -0.9784 +2023-05-26 22:26:01.099895: val_loss -0.5347 +2023-05-26 22:26:01.100028: Pseudo dice [0.9364, 0.8603, 0.9002] +2023-05-26 22:26:01.100117: Epoch time: 37.41 s +2023-05-26 22:26:02.698217: +2023-05-26 22:26:02.698452: Epoch 954 +2023-05-26 22:26:02.698597: Current learning rate: 0.00063 +2023-05-26 22:26:40.308602: train_loss -0.9784 +2023-05-26 22:26:40.309014: val_loss -0.5383 +2023-05-26 22:26:40.309129: Pseudo dice [0.9364, 0.8616, 0.9026] +2023-05-26 22:26:40.309225: Epoch time: 37.61 s +2023-05-26 22:26:41.982512: +2023-05-26 22:26:41.982882: Epoch 955 +2023-05-26 22:26:41.983126: Current learning rate: 0.00061 +2023-05-26 22:27:19.696887: train_loss -0.9785 +2023-05-26 22:27:19.697250: val_loss -0.5395 +2023-05-26 22:27:19.697380: Pseudo dice [0.9364, 0.861, 0.9048] +2023-05-26 22:27:19.697483: Epoch time: 37.72 s +2023-05-26 22:27:21.560183: +2023-05-26 22:27:21.561015: Epoch 956 +2023-05-26 22:27:21.561366: Current learning rate: 0.0006 +2023-05-26 22:27:59.100336: train_loss -0.9787 +2023-05-26 22:27:59.100560: val_loss -0.5415 +2023-05-26 22:27:59.100678: Pseudo dice [0.9367, 0.8618, 0.9025] +2023-05-26 22:27:59.100794: Epoch time: 37.54 s +2023-05-26 22:28:00.695973: +2023-05-26 22:28:00.696418: Epoch 957 +2023-05-26 22:28:00.696714: Current learning rate: 0.00059 +2023-05-26 22:28:38.399210: train_loss -0.9784 +2023-05-26 22:28:38.399509: val_loss -0.5447 +2023-05-26 22:28:38.399673: Pseudo dice [0.9364, 0.8612, 0.9048] +2023-05-26 22:28:38.399868: Epoch time: 37.7 s +2023-05-26 22:28:39.997370: +2023-05-26 22:28:39.997725: Epoch 958 +2023-05-26 22:28:39.998055: Current learning rate: 0.00058 +2023-05-26 22:29:17.524729: train_loss -0.9786 +2023-05-26 22:29:17.525130: val_loss -0.5363 +2023-05-26 22:29:17.525268: Pseudo dice [0.9345, 0.8597, 0.9054] +2023-05-26 22:29:17.525378: Epoch time: 37.53 s +2023-05-26 22:29:19.140704: +2023-05-26 22:29:19.140902: Epoch 959 +2023-05-26 22:29:19.141087: Current learning rate: 0.00056 +2023-05-26 22:29:56.893450: train_loss -0.9788 +2023-05-26 22:29:56.893724: val_loss -0.5368 +2023-05-26 22:29:56.893849: Pseudo dice [0.9366, 0.8614, 0.9038] +2023-05-26 22:29:56.893952: Epoch time: 37.75 s +2023-05-26 22:29:58.530926: +2023-05-26 22:29:58.531615: Epoch 960 +2023-05-26 22:29:58.531985: Current learning rate: 0.00055 +2023-05-26 22:30:36.144665: train_loss -0.9789 +2023-05-26 22:30:36.144890: val_loss -0.5356 +2023-05-26 22:30:36.145009: Pseudo dice [0.9365, 0.8628, 0.9038] +2023-05-26 22:30:36.145118: Epoch time: 37.62 s +2023-05-26 22:30:37.627939: +2023-05-26 22:30:37.628124: Epoch 961 +2023-05-26 22:30:37.628261: Current learning rate: 0.00054 +2023-05-26 22:31:15.680583: train_loss -0.9788 +2023-05-26 22:31:15.681073: val_loss -0.5289 +2023-05-26 22:31:15.681299: Pseudo dice [0.9365, 0.8596, 0.9017] +2023-05-26 22:31:15.681453: Epoch time: 38.05 s +2023-05-26 22:31:17.243228: +2023-05-26 22:31:17.243591: Epoch 962 +2023-05-26 22:31:17.243799: Current learning rate: 0.00053 +2023-05-26 22:31:54.752668: train_loss -0.9789 +2023-05-26 22:31:54.752937: val_loss -0.5352 +2023-05-26 22:31:54.753064: Pseudo dice [0.9371, 0.8614, 0.9035] +2023-05-26 22:31:54.753156: Epoch time: 37.51 s +2023-05-26 22:31:56.759164: +2023-05-26 22:31:56.759419: Epoch 963 +2023-05-26 22:31:56.759799: Current learning rate: 0.00051 +2023-05-26 22:32:34.275756: train_loss -0.9788 +2023-05-26 22:32:34.276021: val_loss -0.5333 +2023-05-26 22:32:34.276160: Pseudo dice [0.9366, 0.8604, 0.9034] +2023-05-26 22:32:34.276269: Epoch time: 37.52 s +2023-05-26 22:32:35.869948: +2023-05-26 22:32:35.870177: Epoch 964 +2023-05-26 22:32:35.870304: Current learning rate: 0.0005 +2023-05-26 22:33:13.581835: train_loss -0.9791 +2023-05-26 22:33:13.582354: val_loss -0.5368 +2023-05-26 22:33:13.582458: Pseudo dice [0.937, 0.8626, 0.9019] +2023-05-26 22:33:13.582572: Epoch time: 37.71 s +2023-05-26 22:33:15.121077: +2023-05-26 22:33:15.121408: Epoch 965 +2023-05-26 22:33:15.121537: Current learning rate: 0.00049 +2023-05-26 22:33:52.791583: train_loss -0.979 +2023-05-26 22:33:52.791819: val_loss -0.5365 +2023-05-26 22:33:52.791945: Pseudo dice [0.9362, 0.8626, 0.9046] +2023-05-26 22:33:52.792062: Epoch time: 37.67 s +2023-05-26 22:33:54.475778: +2023-05-26 22:33:54.476077: Epoch 966 +2023-05-26 22:33:54.476286: Current learning rate: 0.00048 +2023-05-26 22:34:31.825251: train_loss -0.9791 +2023-05-26 22:34:31.825559: val_loss -0.5348 +2023-05-26 22:34:31.825690: Pseudo dice [0.9372, 0.8613, 0.9034] +2023-05-26 22:34:31.825794: Epoch time: 37.35 s +2023-05-26 22:34:33.296320: +2023-05-26 22:34:33.296620: Epoch 967 +2023-05-26 22:34:33.296807: Current learning rate: 0.00046 +2023-05-26 22:35:10.856316: train_loss -0.9793 +2023-05-26 22:35:10.856606: val_loss -0.5209 +2023-05-26 22:35:10.856744: Pseudo dice [0.9361, 0.8614, 0.8983] +2023-05-26 22:35:10.856839: Epoch time: 37.56 s +2023-05-26 22:35:12.437233: +2023-05-26 22:35:12.437664: Epoch 968 +2023-05-26 22:35:12.437952: Current learning rate: 0.00045 +2023-05-26 22:35:49.947227: train_loss -0.9792 +2023-05-26 22:35:49.947480: val_loss -0.524 +2023-05-26 22:35:49.947600: Pseudo dice [0.9357, 0.86, 0.9017] +2023-05-26 22:35:49.947702: Epoch time: 37.51 s +2023-05-26 22:35:51.438471: +2023-05-26 22:35:51.438893: Epoch 969 +2023-05-26 22:35:51.439233: Current learning rate: 0.00044 +2023-05-26 22:36:29.179887: train_loss -0.9796 +2023-05-26 22:36:29.180252: val_loss -0.5265 +2023-05-26 22:36:29.180377: Pseudo dice [0.9363, 0.8617, 0.9022] +2023-05-26 22:36:29.180485: Epoch time: 37.74 s +2023-05-26 22:36:31.227459: +2023-05-26 22:36:31.227790: Epoch 970 +2023-05-26 22:36:31.227944: Current learning rate: 0.00043 +2023-05-26 22:37:09.354574: train_loss -0.9792 +2023-05-26 22:37:09.354870: val_loss -0.5286 +2023-05-26 22:37:09.355028: Pseudo dice [0.936, 0.8615, 0.9019] +2023-05-26 22:37:09.355142: Epoch time: 38.13 s +2023-05-26 22:37:10.911035: +2023-05-26 22:37:10.911229: Epoch 971 +2023-05-26 22:37:10.911339: Current learning rate: 0.00041 +2023-05-26 22:37:48.200584: train_loss -0.9795 +2023-05-26 22:37:48.200903: val_loss -0.5319 +2023-05-26 22:37:48.201019: Pseudo dice [0.9361, 0.8612, 0.9039] +2023-05-26 22:37:48.201107: Epoch time: 37.29 s +2023-05-26 22:37:49.785609: +2023-05-26 22:37:49.785879: Epoch 972 +2023-05-26 22:37:49.786027: Current learning rate: 0.0004 +2023-05-26 22:38:27.289316: train_loss -0.9794 +2023-05-26 22:38:27.290111: val_loss -0.5278 +2023-05-26 22:38:27.290298: Pseudo dice [0.9359, 0.8599, 0.9003] +2023-05-26 22:38:27.290395: Epoch time: 37.51 s +2023-05-26 22:38:28.817244: +2023-05-26 22:38:28.817438: Epoch 973 +2023-05-26 22:38:28.817553: Current learning rate: 0.00039 +2023-05-26 22:39:06.050019: train_loss -0.9794 +2023-05-26 22:39:06.050264: val_loss -0.5245 +2023-05-26 22:39:06.050378: Pseudo dice [0.9354, 0.861, 0.9002] +2023-05-26 22:39:06.050487: Epoch time: 37.23 s +2023-05-26 22:39:07.477796: +2023-05-26 22:39:07.477949: Epoch 974 +2023-05-26 22:39:07.478066: Current learning rate: 0.00037 +2023-05-26 22:39:44.797845: train_loss -0.9797 +2023-05-26 22:39:44.798096: val_loss -0.5274 +2023-05-26 22:39:44.798228: Pseudo dice [0.9378, 0.8619, 0.9017] +2023-05-26 22:39:44.798323: Epoch time: 37.32 s +2023-05-26 22:39:46.337412: +2023-05-26 22:39:46.337644: Epoch 975 +2023-05-26 22:39:46.337790: Current learning rate: 0.00036 +2023-05-26 22:40:23.713314: train_loss -0.9798 +2023-05-26 22:40:23.713645: val_loss -0.5252 +2023-05-26 22:40:23.713777: Pseudo dice [0.9358, 0.8612, 0.9043] +2023-05-26 22:40:23.713876: Epoch time: 37.38 s +2023-05-26 22:40:25.659711: +2023-05-26 22:40:25.660557: Epoch 976 +2023-05-26 22:40:25.661375: Current learning rate: 0.00035 +2023-05-26 22:41:03.247034: train_loss -0.9798 +2023-05-26 22:41:03.247271: val_loss -0.5184 +2023-05-26 22:41:03.247399: Pseudo dice [0.9368, 0.8606, 0.9016] +2023-05-26 22:41:03.247487: Epoch time: 37.59 s +2023-05-26 22:41:04.917438: +2023-05-26 22:41:04.917634: Epoch 977 +2023-05-26 22:41:04.917759: Current learning rate: 0.00034 +2023-05-26 22:41:42.671714: train_loss -0.9797 +2023-05-26 22:41:42.671949: val_loss -0.5252 +2023-05-26 22:41:42.672070: Pseudo dice [0.9346, 0.8609, 0.9038] +2023-05-26 22:41:42.672176: Epoch time: 37.76 s +2023-05-26 22:41:44.176769: +2023-05-26 22:41:44.177098: Epoch 978 +2023-05-26 22:41:44.177383: Current learning rate: 0.00032 +2023-05-26 22:42:21.746386: train_loss -0.9796 +2023-05-26 22:42:21.746884: val_loss -0.5243 +2023-05-26 22:42:21.747032: Pseudo dice [0.9369, 0.8619, 0.9023] +2023-05-26 22:42:21.747138: Epoch time: 37.57 s +2023-05-26 22:42:23.400738: +2023-05-26 22:42:23.401297: Epoch 979 +2023-05-26 22:42:23.401489: Current learning rate: 0.00031 +2023-05-26 22:43:01.116048: train_loss -0.9797 +2023-05-26 22:43:01.116783: val_loss -0.5297 +2023-05-26 22:43:01.116929: Pseudo dice [0.9362, 0.8627, 0.9014] +2023-05-26 22:43:01.117047: Epoch time: 37.72 s +2023-05-26 22:43:02.943552: +2023-05-26 22:43:02.943748: Epoch 980 +2023-05-26 22:43:02.943868: Current learning rate: 0.0003 +2023-05-26 22:43:40.378908: train_loss -0.98 +2023-05-26 22:43:40.379527: val_loss -0.5245 +2023-05-26 22:43:40.379643: Pseudo dice [0.9366, 0.8605, 0.9024] +2023-05-26 22:43:40.379736: Epoch time: 37.44 s +2023-05-26 22:43:41.965738: +2023-05-26 22:43:41.965992: Epoch 981 +2023-05-26 22:43:41.966282: Current learning rate: 0.00028 +2023-05-26 22:44:19.457389: train_loss -0.9795 +2023-05-26 22:44:19.457748: val_loss -0.5277 +2023-05-26 22:44:19.457870: Pseudo dice [0.9374, 0.8628, 0.9022] +2023-05-26 22:44:19.457986: Epoch time: 37.49 s +2023-05-26 22:44:21.081304: +2023-05-26 22:44:21.081522: Epoch 982 +2023-05-26 22:44:21.081664: Current learning rate: 0.00027 +2023-05-26 22:44:58.381430: train_loss -0.9798 +2023-05-26 22:44:58.381745: val_loss -0.5139 +2023-05-26 22:44:58.381876: Pseudo dice [0.9361, 0.861, 0.9008] +2023-05-26 22:44:58.381974: Epoch time: 37.3 s +2023-05-26 22:45:00.348480: +2023-05-26 22:45:00.348710: Epoch 983 +2023-05-26 22:45:00.348844: Current learning rate: 0.00026 +2023-05-26 22:45:37.830529: train_loss -0.9803 +2023-05-26 22:45:37.830881: val_loss -0.52 +2023-05-26 22:45:37.830997: Pseudo dice [0.9357, 0.861, 0.9035] +2023-05-26 22:45:37.831091: Epoch time: 37.48 s +2023-05-26 22:45:39.448494: +2023-05-26 22:45:39.448988: Epoch 984 +2023-05-26 22:45:39.449151: Current learning rate: 0.00024 +2023-05-26 22:46:17.137004: train_loss -0.9803 +2023-05-26 22:46:17.137235: val_loss -0.5235 +2023-05-26 22:46:17.137353: Pseudo dice [0.9363, 0.8627, 0.8995] +2023-05-26 22:46:17.137455: Epoch time: 37.69 s +2023-05-26 22:46:18.839438: +2023-05-26 22:46:18.839610: Epoch 985 +2023-05-26 22:46:18.839721: Current learning rate: 0.00023 +2023-05-26 22:46:56.514623: train_loss -0.98 +2023-05-26 22:46:56.515033: val_loss -0.5206 +2023-05-26 22:46:56.515192: Pseudo dice [0.935, 0.8601, 0.9031] +2023-05-26 22:46:56.515321: Epoch time: 37.68 s +2023-05-26 22:46:58.231560: +2023-05-26 22:46:58.231782: Epoch 986 +2023-05-26 22:46:58.231915: Current learning rate: 0.00021 +2023-05-26 22:47:35.962657: train_loss -0.9801 +2023-05-26 22:47:35.962950: val_loss -0.5233 +2023-05-26 22:47:35.963101: Pseudo dice [0.937, 0.8633, 0.8993] +2023-05-26 22:47:35.963192: Epoch time: 37.73 s +2023-05-26 22:47:37.432921: +2023-05-26 22:47:37.433112: Epoch 987 +2023-05-26 22:47:37.433217: Current learning rate: 0.0002 +2023-05-26 22:48:14.884813: train_loss -0.9798 +2023-05-26 22:48:14.885046: val_loss -0.5166 +2023-05-26 22:48:14.885152: Pseudo dice [0.9362, 0.8622, 0.9012] +2023-05-26 22:48:14.885260: Epoch time: 37.45 s +2023-05-26 22:48:16.471842: +2023-05-26 22:48:16.472271: Epoch 988 +2023-05-26 22:48:16.472476: Current learning rate: 0.00019 +2023-05-26 22:48:54.149915: train_loss -0.9804 +2023-05-26 22:48:54.150187: val_loss -0.5178 +2023-05-26 22:48:54.150321: Pseudo dice [0.9354, 0.8622, 0.9013] +2023-05-26 22:48:54.150430: Epoch time: 37.68 s +2023-05-26 22:48:55.834522: +2023-05-26 22:48:55.834702: Epoch 989 +2023-05-26 22:48:55.834868: Current learning rate: 0.00017 +2023-05-26 22:49:33.905260: train_loss -0.9801 +2023-05-26 22:49:33.905552: val_loss -0.5134 +2023-05-26 22:49:33.905685: Pseudo dice [0.936, 0.8599, 0.9002] +2023-05-26 22:49:33.905773: Epoch time: 38.07 s +2023-05-26 22:49:35.479964: +2023-05-26 22:49:35.480251: Epoch 990 +2023-05-26 22:49:35.480376: Current learning rate: 0.00016 +2023-05-26 22:50:12.957534: train_loss -0.98 +2023-05-26 22:50:12.957882: val_loss -0.5155 +2023-05-26 22:50:12.958027: Pseudo dice [0.9354, 0.8613, 0.901] +2023-05-26 22:50:12.958138: Epoch time: 37.48 s +2023-05-26 22:50:14.516900: +2023-05-26 22:50:14.517120: Epoch 991 +2023-05-26 22:50:14.517248: Current learning rate: 0.00014 +2023-05-26 22:50:52.090196: train_loss -0.9806 +2023-05-26 22:50:52.090529: val_loss -0.5181 +2023-05-26 22:50:52.090662: Pseudo dice [0.9371, 0.8635, 0.9013] +2023-05-26 22:50:52.090788: Epoch time: 37.57 s +2023-05-26 22:50:53.689135: +2023-05-26 22:50:53.689358: Epoch 992 +2023-05-26 22:50:53.689517: Current learning rate: 0.00013 +2023-05-26 22:51:31.110816: train_loss -0.9803 +2023-05-26 22:51:31.111187: val_loss -0.5129 +2023-05-26 22:51:31.111300: Pseudo dice [0.9361, 0.8606, 0.9014] +2023-05-26 22:51:31.111414: Epoch time: 37.42 s +2023-05-26 22:51:32.736408: +2023-05-26 22:51:32.736612: Epoch 993 +2023-05-26 22:51:32.736747: Current learning rate: 0.00011 +2023-05-26 22:52:11.059226: train_loss -0.9804 +2023-05-26 22:52:11.059531: val_loss -0.5282 +2023-05-26 22:52:11.059671: Pseudo dice [0.9367, 0.8635, 0.9051] +2023-05-26 22:52:11.059764: Epoch time: 38.32 s +2023-05-26 22:52:12.811562: +2023-05-26 22:52:12.811767: Epoch 994 +2023-05-26 22:52:12.811899: Current learning rate: 0.0001 +2023-05-26 22:52:50.491314: train_loss -0.9803 +2023-05-26 22:52:50.491610: val_loss -0.5179 +2023-05-26 22:52:50.491740: Pseudo dice [0.9374, 0.8629, 0.9014] +2023-05-26 22:52:50.491844: Epoch time: 37.68 s +2023-05-26 22:52:52.072569: +2023-05-26 22:52:52.072757: Epoch 995 +2023-05-26 22:52:52.072872: Current learning rate: 8e-05 +2023-05-26 22:53:29.610943: train_loss -0.9799 +2023-05-26 22:53:29.611370: val_loss -0.5163 +2023-05-26 22:53:29.611504: Pseudo dice [0.9368, 0.862, 0.9012] +2023-05-26 22:53:29.611616: Epoch time: 37.54 s +2023-05-26 22:53:31.572171: +2023-05-26 22:53:31.572389: Epoch 996 +2023-05-26 22:53:31.572528: Current learning rate: 7e-05 +2023-05-26 22:54:09.327835: train_loss -0.9805 +2023-05-26 22:54:09.328195: val_loss -0.5086 +2023-05-26 22:54:09.328326: Pseudo dice [0.9361, 0.861, 0.8983] +2023-05-26 22:54:09.328420: Epoch time: 37.76 s +2023-05-26 22:54:11.043402: +2023-05-26 22:54:11.043769: Epoch 997 +2023-05-26 22:54:11.044002: Current learning rate: 5e-05 +2023-05-26 22:54:48.506341: train_loss -0.9809 +2023-05-26 22:54:48.506608: val_loss -0.5226 +2023-05-26 22:54:48.506996: Pseudo dice [0.9364, 0.8637, 0.9047] +2023-05-26 22:54:48.507113: Epoch time: 37.46 s +2023-05-26 22:54:50.164500: +2023-05-26 22:54:50.164921: Epoch 998 +2023-05-26 22:54:50.165185: Current learning rate: 4e-05 +2023-05-26 22:55:27.801005: train_loss -0.9805 +2023-05-26 22:55:27.801308: val_loss -0.5082 +2023-05-26 22:55:27.801431: Pseudo dice [0.9349, 0.8598, 0.9001] +2023-05-26 22:55:27.801530: Epoch time: 37.64 s +2023-05-26 22:55:29.365603: +2023-05-26 22:55:29.365983: Epoch 999 +2023-05-26 22:55:29.366192: Current learning rate: 2e-05 +2023-05-26 22:56:07.163135: train_loss -0.9804 +2023-05-26 22:56:07.163399: val_loss -0.5102 +2023-05-26 22:56:07.163620: Pseudo dice [0.936, 0.8608, 0.8996] +2023-05-26 22:56:07.163750: Epoch time: 37.8 s +2023-05-26 22:56:09.263301: Training done. +2023-05-26 22:56:09.450068: Using splits from existing split file: /home/gillesv/data/nnUNet_preprocessed/Dataset001_CAMUS/splits_final.json +2023-05-26 22:56:09.452906: The split file contains 10 splits. +2023-05-26 22:56:09.453018: Desired fold for training: 0 +2023-05-26 22:56:09.453067: This split has 1600 training and 200 validation cases. +2023-05-26 22:56:09.459805: predicting patient0042_2CH_ED +2023-05-26 22:56:09.949258: predicting patient0042_2CH_ES +2023-05-26 22:56:10.024433: predicting patient0042_4CH_ED +2023-05-26 22:56:10.090669: predicting patient0042_4CH_ES +2023-05-26 22:56:10.200020: predicting patient0048_2CH_ED +2023-05-26 22:56:10.264668: predicting patient0048_2CH_ES +2023-05-26 22:56:10.351642: predicting patient0048_4CH_ED +2023-05-26 22:56:10.470475: predicting patient0048_4CH_ES +2023-05-26 22:56:10.649189: predicting patient0049_2CH_ED +2023-05-26 22:56:10.718285: predicting patient0049_2CH_ES +2023-05-26 22:56:10.817730: predicting patient0049_4CH_ED +2023-05-26 22:56:10.860901: predicting patient0049_4CH_ES +2023-05-26 22:56:10.903797: predicting patient0054_2CH_ED +2023-05-26 22:56:10.947811: predicting patient0054_2CH_ES +2023-05-26 22:56:10.990765: predicting patient0054_4CH_ED +2023-05-26 22:56:11.033812: predicting patient0054_4CH_ES +2023-05-26 22:56:11.089137: predicting patient0057_2CH_ED +2023-05-26 22:56:11.144473: predicting patient0057_2CH_ES +2023-05-26 22:56:11.195019: predicting patient0057_4CH_ED +2023-05-26 22:56:11.245965: predicting patient0057_4CH_ES +2023-05-26 22:56:11.287913: predicting patient0059_2CH_ED +2023-05-26 22:56:11.332702: predicting patient0059_2CH_ES +2023-05-26 22:56:11.375138: predicting patient0059_4CH_ED +2023-05-26 22:56:11.414954: predicting patient0059_4CH_ES +2023-05-26 22:56:13.786569: predicting patient0062_2CH_ED +2023-05-26 22:56:13.830294: predicting patient0062_2CH_ES +2023-05-26 22:56:13.893410: predicting patient0062_4CH_ED +2023-05-26 22:56:13.943949: predicting patient0062_4CH_ES +2023-05-26 22:56:13.997785: predicting patient0063_2CH_ED +2023-05-26 22:56:14.044252: predicting patient0063_2CH_ES +2023-05-26 22:56:14.133454: predicting patient0063_4CH_ED +2023-05-26 22:56:14.196332: predicting patient0063_4CH_ES +2023-05-26 22:56:14.244729: predicting patient0065_2CH_ED +2023-05-26 22:56:14.333092: predicting patient0065_2CH_ES +2023-05-26 22:56:14.472183: predicting patient0065_4CH_ED +2023-05-26 22:56:14.524113: predicting patient0065_4CH_ES +2023-05-26 22:56:14.614764: predicting patient0066_2CH_ED +2023-05-26 22:56:14.675079: predicting patient0066_2CH_ES +2023-05-26 22:56:14.724513: predicting patient0066_4CH_ED +2023-05-26 22:56:14.781509: predicting patient0066_4CH_ES +2023-05-26 22:56:14.835077: predicting patient0067_2CH_ED +2023-05-26 22:56:14.893574: predicting patient0067_2CH_ES +2023-05-26 22:56:14.948985: predicting patient0067_4CH_ED +2023-05-26 22:56:15.002844: predicting patient0067_4CH_ES +2023-05-26 22:56:15.060464: predicting patient0068_2CH_ED +2023-05-26 22:56:15.111943: predicting patient0068_2CH_ES +2023-05-26 22:56:15.162844: predicting patient0068_4CH_ED +2023-05-26 22:56:15.219279: predicting patient0068_4CH_ES +2023-05-26 22:56:15.265690: predicting patient0069_2CH_ED +2023-05-26 22:56:15.311893: predicting patient0069_2CH_ES +2023-05-26 22:56:15.370303: predicting patient0069_4CH_ED +2023-05-26 22:56:15.417991: predicting patient0069_4CH_ES +2023-05-26 22:56:15.475401: predicting patient0070_2CH_ED +2023-05-26 22:56:15.538911: predicting patient0070_2CH_ES +2023-05-26 22:56:15.592948: predicting patient0070_4CH_ED +2023-05-26 22:56:15.647478: predicting patient0070_4CH_ES +2023-05-26 22:56:15.709936: predicting patient0071_2CH_ED +2023-05-26 22:56:15.768013: predicting patient0071_2CH_ES +2023-05-26 22:56:15.815012: predicting patient0071_4CH_ED +2023-05-26 22:56:15.866128: predicting patient0071_4CH_ES +2023-05-26 22:56:15.915483: predicting patient0072_2CH_ED +2023-05-26 22:56:15.973198: predicting patient0072_2CH_ES +2023-05-26 22:56:16.018595: predicting patient0072_4CH_ED +2023-05-26 22:56:16.067361: predicting patient0072_4CH_ES +2023-05-26 22:56:16.128522: predicting patient0073_2CH_ED +2023-05-26 22:56:16.207627: predicting patient0073_2CH_ES +2023-05-26 22:56:16.268264: predicting patient0073_4CH_ED +2023-05-26 22:56:16.327515: predicting patient0073_4CH_ES +2023-05-26 22:56:16.377396: predicting patient0074_2CH_ED +2023-05-26 22:56:16.438339: predicting patient0074_2CH_ES +2023-05-26 22:56:16.498270: predicting patient0074_4CH_ED +2023-05-26 22:56:16.551779: predicting patient0074_4CH_ES +2023-05-26 22:56:16.605713: predicting patient0075_2CH_ED +2023-05-26 22:56:16.662421: predicting patient0075_2CH_ES +2023-05-26 22:56:16.719102: predicting patient0075_4CH_ED +2023-05-26 22:56:16.779974: predicting patient0075_4CH_ES +2023-05-26 22:56:16.834059: predicting patient0076_2CH_ED +2023-05-26 22:56:16.887486: predicting patient0076_2CH_ES +2023-05-26 22:56:16.936707: predicting patient0076_4CH_ED +2023-05-26 22:56:16.980574: predicting patient0076_4CH_ES +2023-05-26 22:56:17.028943: predicting patient0077_2CH_ED +2023-05-26 22:56:17.077051: predicting patient0077_2CH_ES +2023-05-26 22:56:17.126214: predicting patient0077_4CH_ED +2023-05-26 22:56:17.171347: predicting patient0077_4CH_ES +2023-05-26 22:56:17.216481: predicting patient0078_2CH_ED +2023-05-26 22:56:17.266534: predicting patient0078_2CH_ES +2023-05-26 22:56:17.319378: predicting patient0078_4CH_ED +2023-05-26 22:56:17.373986: predicting patient0078_4CH_ES +2023-05-26 22:56:17.427493: predicting patient0079_2CH_ED +2023-05-26 22:56:17.477907: predicting patient0079_2CH_ES +2023-05-26 22:56:17.525821: predicting patient0079_4CH_ED +2023-05-26 22:56:17.572205: predicting patient0079_4CH_ES +2023-05-26 22:56:17.619348: predicting patient0080_2CH_ED +2023-05-26 22:56:17.677996: predicting patient0080_2CH_ES +2023-05-26 22:56:17.732581: predicting patient0080_4CH_ED +2023-05-26 22:56:17.790096: predicting patient0080_4CH_ES +2023-05-26 22:56:17.845574: predicting patient0082_2CH_ED +2023-05-26 22:56:17.897224: predicting patient0082_2CH_ES +2023-05-26 22:56:17.952248: predicting patient0082_4CH_ED +2023-05-26 22:56:18.007598: predicting patient0082_4CH_ES +2023-05-26 22:56:18.062313: predicting patient0083_2CH_ED +2023-05-26 22:56:18.127164: predicting patient0083_2CH_ES +2023-05-26 22:56:18.197338: predicting patient0083_4CH_ED +2023-05-26 22:56:18.249450: predicting patient0083_4CH_ES +2023-05-26 22:56:18.301141: predicting patient0084_2CH_ED +2023-05-26 22:56:18.352313: predicting patient0084_2CH_ES +2023-05-26 22:56:18.403734: predicting patient0084_4CH_ED +2023-05-26 22:56:18.450249: predicting patient0084_4CH_ES +2023-05-26 22:56:18.503754: predicting patient0085_2CH_ED +2023-05-26 22:56:18.556653: predicting patient0085_2CH_ES +2023-05-26 22:56:18.613852: predicting patient0085_4CH_ED +2023-05-26 22:56:18.661160: predicting patient0085_4CH_ES +2023-05-26 22:56:18.709196: predicting patient0086_2CH_ED +2023-05-26 22:56:18.761987: predicting patient0086_2CH_ES +2023-05-26 22:56:18.811365: predicting patient0086_4CH_ED +2023-05-26 22:56:18.870475: predicting patient0086_4CH_ES +2023-05-26 22:56:18.936091: predicting patient0087_2CH_ED +2023-05-26 22:56:18.994071: predicting patient0087_2CH_ES +2023-05-26 22:56:19.049586: predicting patient0087_4CH_ED +2023-05-26 22:56:19.105896: predicting patient0087_4CH_ES +2023-05-26 22:56:19.162902: predicting patient0088_2CH_ED +2023-05-26 22:56:19.212650: predicting patient0088_2CH_ES +2023-05-26 22:56:19.266080: predicting patient0088_4CH_ED +2023-05-26 22:56:19.314217: predicting patient0088_4CH_ES +2023-05-26 22:56:19.363109: predicting patient0090_2CH_ED +2023-05-26 22:56:19.413690: predicting patient0090_2CH_ES +2023-05-26 22:56:19.468793: predicting patient0090_4CH_ED +2023-05-26 22:56:19.521316: predicting patient0090_4CH_ES +2023-05-26 22:56:19.573447: predicting patient0093_2CH_ED +2023-05-26 22:56:19.620886: predicting patient0093_2CH_ES +2023-05-26 22:56:19.669901: predicting patient0093_4CH_ED +2023-05-26 22:56:19.726448: predicting patient0093_4CH_ES +2023-05-26 22:56:19.779789: predicting patient0095_2CH_ED +2023-05-26 22:56:19.831160: predicting patient0095_2CH_ES +2023-05-26 22:56:19.885538: predicting patient0095_4CH_ED +2023-05-26 22:56:19.942431: predicting patient0095_4CH_ES +2023-05-26 22:56:19.999847: predicting patient0096_2CH_ED +2023-05-26 22:56:20.053983: predicting patient0096_2CH_ES +2023-05-26 22:56:20.101291: predicting patient0096_4CH_ED +2023-05-26 22:56:20.157037: predicting patient0096_4CH_ES +2023-05-26 22:56:20.206796: predicting patient0100_2CH_ED +2023-05-26 22:56:20.257626: predicting patient0100_2CH_ES +2023-05-26 22:56:20.304824: predicting patient0100_4CH_ED +2023-05-26 22:56:20.369817: predicting patient0100_4CH_ES +2023-05-26 22:56:20.428681: predicting patient0101_2CH_ED +2023-05-26 22:56:20.492585: predicting patient0101_2CH_ES +2023-05-26 22:56:20.542207: predicting patient0101_4CH_ED +2023-05-26 22:56:20.593549: predicting patient0101_4CH_ES +2023-05-26 22:56:20.642219: predicting patient0102_2CH_ED +2023-05-26 22:56:20.693687: predicting patient0102_2CH_ES +2023-05-26 22:56:20.744931: predicting patient0102_4CH_ED +2023-05-26 22:56:20.803828: predicting patient0102_4CH_ES +2023-05-26 22:56:20.853910: predicting patient0103_2CH_ED +2023-05-26 22:56:20.909772: predicting patient0103_2CH_ES +2023-05-26 22:56:20.959005: predicting patient0103_4CH_ED +2023-05-26 22:56:21.013418: predicting patient0103_4CH_ES +2023-05-26 22:56:21.068190: predicting patient0104_2CH_ED +2023-05-26 22:56:21.116667: predicting patient0104_2CH_ES +2023-05-26 22:56:21.162218: predicting patient0104_4CH_ED +2023-05-26 22:56:21.208207: predicting patient0104_4CH_ES +2023-05-26 22:56:21.263339: predicting patient0106_2CH_ED +2023-05-26 22:56:21.316423: predicting patient0106_2CH_ES +2023-05-26 22:56:21.368868: predicting patient0106_4CH_ED +2023-05-26 22:56:21.423833: predicting patient0106_4CH_ES +2023-05-26 22:56:21.477717: predicting patient0111_2CH_ED +2023-05-26 22:56:21.542916: predicting patient0111_2CH_ES +2023-05-26 22:56:21.603235: predicting patient0111_4CH_ED +2023-05-26 22:56:21.651800: predicting patient0111_4CH_ES +2023-05-26 22:56:21.704663: predicting patient0112_2CH_ED +2023-05-26 22:56:21.754779: predicting patient0112_2CH_ES +2023-05-26 22:56:21.807117: predicting patient0112_4CH_ED +2023-05-26 22:56:21.858459: predicting patient0112_4CH_ES +2023-05-26 22:56:21.905879: predicting patient0114_2CH_ED +2023-05-26 22:56:21.974185: predicting patient0114_2CH_ES +2023-05-26 22:56:22.033320: predicting patient0114_4CH_ED +2023-05-26 22:56:22.093039: predicting patient0114_4CH_ES +2023-05-26 22:56:22.143386: predicting patient0119_2CH_ED +2023-05-26 22:56:22.202612: predicting patient0119_2CH_ES +2023-05-26 22:56:22.248549: predicting patient0119_4CH_ED +2023-05-26 22:56:22.293561: predicting patient0119_4CH_ES +2023-05-26 22:56:22.343378: predicting patient0183_2CH_ED +2023-05-26 22:56:22.387903: predicting patient0183_2CH_ES +2023-05-26 22:56:22.441393: predicting patient0183_4CH_ED +2023-05-26 22:56:22.492548: predicting patient0183_4CH_ES +2023-05-26 22:56:22.545588: predicting patient0195_2CH_ED +2023-05-26 22:56:22.599603: predicting patient0195_2CH_ES +2023-05-26 22:56:22.658839: predicting patient0195_4CH_ED +2023-05-26 22:56:22.712937: predicting patient0195_4CH_ES +2023-05-26 22:56:22.773364: predicting patient0196_2CH_ED +2023-05-26 22:56:22.828190: predicting patient0196_2CH_ES +2023-05-26 22:56:22.871588: predicting patient0196_4CH_ED +2023-05-26 22:56:22.916371: predicting patient0196_4CH_ES +2023-05-26 22:56:22.973483: predicting patient0430_2CH_ED +2023-05-26 22:56:23.026343: predicting patient0430_2CH_ES +2023-05-26 22:56:23.089133: predicting patient0430_4CH_ED +2023-05-26 22:56:23.148191: predicting patient0430_4CH_ES +2023-05-26 22:56:23.197594: predicting patient0431_2CH_ED +2023-05-26 22:56:23.255746: predicting patient0431_2CH_ES +2023-05-26 22:56:23.316657: predicting patient0431_4CH_ED +2023-05-26 22:56:23.369301: predicting patient0431_4CH_ES +2023-05-26 22:56:26.782543: Validation complete +2023-05-26 22:56:26.782715: Mean Validation Dice: 0.8926558000503587