NUM_GPUS=1
MASTER_ADDR=ip-10-0-135-126
MASTER_PORT=18935
WORLD_SIZE=1
PID of this process = 2164521
------ ARGS ------- 
 Namespace(model_suffix='beta', hcp_flat_path='/weka/proj-medarc/shared/HCP-Flat', batch_size=256, wandb_log=True, num_epochs=50, lr_scheduler_type='cycle', save_ckpt=False, seed=42, max_lr=1e-05, target='age', num_workers=15, weight_decay=1e-05)
Input dimension: 737280
total_steps 21750
wandb_config:
 {'model_name': 'HCPflat_raw_age', 'batch_size': 256, 'weight_decay': 1e-05, 'num_epochs': 50, 'seed': 42, 'lr_scheduler_type': 'cycle', 'save_ckpt': False, 'max_lr': 1e-05, 'target': 'age', 'num_workers': 15}
wandb_id: HCPflat_raw_beta_age_31e54b73-122f-4c96-8d20-21ee38d0705b
Step [100/435] - Training Loss: 0.6079 - Training MSE: 0.5940
Step [200/435] - Training Loss: 0.5179 - Training MSE: 0.5895
Step [300/435] - Training Loss: 0.5806 - Training MSE: 0.5846
Step [400/435] - Training Loss: 0.4953 - Training MSE: 0.5817
Epoch [1/50] - Training Loss: 0.5784, Training MSE: 0.5813 - Validation Loss: 0.5355, Validation MSE: 0.5417
Step [100/435] - Training Loss: 0.4042 - Training MSE: 0.5476
Step [200/435] - Training Loss: 0.5508 - Training MSE: 0.5488
Step [300/435] - Training Loss: 0.4799 - Training MSE: 0.5478
Step [400/435] - Training Loss: 0.5536 - Training MSE: 0.5496
Epoch [2/50] - Training Loss: 0.4875, Training MSE: 0.5496 - Validation Loss: 0.5427, Validation MSE: 0.5495
Step [100/435] - Training Loss: 0.3078 - Training MSE: 0.5391
Step [200/435] - Training Loss: 0.3315 - Training MSE: 0.5413
Step [300/435] - Training Loss: 0.3964 - Training MSE: 0.5442
Step [400/435] - Training Loss: 0.3456 - Training MSE: 0.5453
Epoch [3/50] - Training Loss: 0.3329, Training MSE: 0.5454 - Validation Loss: 0.5490, Validation MSE: 0.5614
Step [100/435] - Training Loss: 0.2159 - Training MSE: 0.5618
Step [200/435] - Training Loss: 0.2387 - Training MSE: 0.5638
Step [300/435] - Training Loss: 0.2004 - Training MSE: 0.5652
Step [400/435] - Training Loss: 0.2158 - Training MSE: 0.5671
Epoch [4/50] - Training Loss: 0.2364, Training MSE: 0.5674 - Validation Loss: 0.5676, Validation MSE: 0.5808
Step [100/435] - Training Loss: 0.1533 - Training MSE: 0.5899
Step [200/435] - Training Loss: 0.1590 - Training MSE: 0.5937
Step [300/435] - Training Loss: 0.1987 - Training MSE: 0.5943
Step [400/435] - Training Loss: 0.2009 - Training MSE: 0.5958
Epoch [5/50] - Training Loss: 0.1795, Training MSE: 0.5955 - Validation Loss: 0.6034, Validation MSE: 0.6168
Step [100/435] - Training Loss: 0.1450 - Training MSE: 0.6214
Step [200/435] - Training Loss: 0.1467 - Training MSE: 0.6192
Step [300/435] - Training Loss: 0.1742 - Training MSE: 0.6189
Step [400/435] - Training Loss: 0.1820 - Training MSE: 0.6200
Epoch [6/50] - Training Loss: 0.1412, Training MSE: 0.6204 - Validation Loss: 0.6164, Validation MSE: 0.6309
Step [100/435] - Training Loss: 0.0961 - Training MSE: 0.6445
Step [200/435] - Training Loss: 0.1143 - Training MSE: 0.6474
Step [300/435] - Training Loss: 0.1104 - Training MSE: 0.6465
Step [400/435] - Training Loss: 0.1170 - Training MSE: 0.6448
Epoch [7/50] - Training Loss: 0.1132, Training MSE: 0.6442 - Validation Loss: 0.6420, Validation MSE: 0.6572
Step [100/435] - Training Loss: 0.0859 - Training MSE: 0.6744
Step [200/435] - Training Loss: 0.0967 - Training MSE: 0.6682
Step [300/435] - Training Loss: 0.0962 - Training MSE: 0.6668
Step [400/435] - Training Loss: 0.1131 - Training MSE: 0.6671
Epoch [8/50] - Training Loss: 0.0912, Training MSE: 0.6655 - Validation Loss: 0.6658, Validation MSE: 0.6790
Step [100/435] - Training Loss: 0.0650 - Training MSE: 0.6852
Step [200/435] - Training Loss: 0.0806 - Training MSE: 0.6835
Step [300/435] - Training Loss: 0.0789 - Training MSE: 0.6826
Step [400/435] - Training Loss: 0.0915 - Training MSE: 0.6824
Epoch [9/50] - Training Loss: 0.0739, Training MSE: 0.6820 - Validation Loss: 0.6844, Validation MSE: 0.7001
Step [100/435] - Training Loss: 0.0604 - Training MSE: 0.6952
Step [200/435] - Training Loss: 0.0608 - Training MSE: 0.6973
Step [300/435] - Training Loss: 0.0601 - Training MSE: 0.6990
Step [400/435] - Training Loss: 0.0888 - Training MSE: 0.6998
Epoch [10/50] - Training Loss: 0.0602, Training MSE: 0.6998 - Validation Loss: 0.7134, Validation MSE: 0.7278
Step [100/435] - Training Loss: 0.0403 - Training MSE: 0.7351
Step [200/435] - Training Loss: 0.0519 - Training MSE: 0.7232
Step [300/435] - Training Loss: 0.0490 - Training MSE: 0.7203
Step [400/435] - Training Loss: 0.0611 - Training MSE: 0.7156
Epoch [11/50] - Training Loss: 0.0492, Training MSE: 0.7141 - Validation Loss: 0.7246, Validation MSE: 0.7388
Step [100/435] - Training Loss: 0.0310 - Training MSE: 0.7381
Step [200/435] - Training Loss: 0.0368 - Training MSE: 0.7302
Step [300/435] - Training Loss: 0.0446 - Training MSE: 0.7282
Step [400/435] - Training Loss: 0.0474 - Training MSE: 0.7276
Epoch [12/50] - Training Loss: 0.0400, Training MSE: 0.7267 - Validation Loss: 0.7409, Validation MSE: 0.7569
Step [100/435] - Training Loss: 0.0315 - Training MSE: 0.7505
Step [200/435] - Training Loss: 0.0310 - Training MSE: 0.7421
Step [300/435] - Training Loss: 0.0356 - Training MSE: 0.7409
Step [400/435] - Training Loss: 0.0428 - Training MSE: 0.7382
Epoch [13/50] - Training Loss: 0.0324, Training MSE: 0.7377 - Validation Loss: 0.7593, Validation MSE: 0.7739
Step [100/435] - Training Loss: 0.0229 - Training MSE: 0.7523
Step [200/435] - Training Loss: 0.0279 - Training MSE: 0.7534
Step [300/435] - Training Loss: 0.0317 - Training MSE: 0.7516
Step [400/435] - Training Loss: 0.0314 - Training MSE: 0.7493
Epoch [14/50] - Training Loss: 0.0268, Training MSE: 0.7477 - Validation Loss: 0.7724, Validation MSE: 0.7878
Step [100/435] - Training Loss: 0.0163 - Training MSE: 0.7665
Step [200/435] - Training Loss: 0.0220 - Training MSE: 0.7628
Step [300/435] - Training Loss: 0.0242 - Training MSE: 0.7608
Step [400/435] - Training Loss: 0.0288 - Training MSE: 0.7579
Epoch [15/50] - Training Loss: 0.0215, Training MSE: 0.7572 - Validation Loss: 0.7895, Validation MSE: 0.8040
Step [100/435] - Training Loss: 0.0134 - Training MSE: 0.7748
Step [200/435] - Training Loss: 0.0160 - Training MSE: 0.7727
Step [300/435] - Training Loss: 0.0197 - Training MSE: 0.7660
Step [400/435] - Training Loss: 0.0230 - Training MSE: 0.7650
Epoch [16/50] - Training Loss: 0.0180, Training MSE: 0.7649 - Validation Loss: 0.8056, Validation MSE: 0.8198
Step [100/435] - Training Loss: 0.0127 - Training MSE: 0.7814
Step [200/435] - Training Loss: 0.0157 - Training MSE: 0.7747
Step [300/435] - Training Loss: 0.0165 - Training MSE: 0.7720
Step [400/435] - Training Loss: 0.0159 - Training MSE: 0.7728
Epoch [17/50] - Training Loss: 0.0145, Training MSE: 0.7717 - Validation Loss: 0.8114, Validation MSE: 0.8293
Step [100/435] - Training Loss: 0.0095 - Training MSE: 0.7832
Step [200/435] - Training Loss: 0.0129 - Training MSE: 0.7875
Step [300/435] - Training Loss: 0.0104 - Training MSE: 0.7807
Step [400/435] - Training Loss: 0.0119 - Training MSE: 0.7786
Epoch [18/50] - Training Loss: 0.0119, Training MSE: 0.7773 - Validation Loss: 0.8136, Validation MSE: 0.8289
Step [100/435] - Training Loss: 0.0080 - Training MSE: 0.7895
Step [200/435] - Training Loss: 0.0097 - Training MSE: 0.7878
Step [300/435] - Training Loss: 0.0100 - Training MSE: 0.7860
Step [400/435] - Training Loss: 0.0121 - Training MSE: 0.7824
Epoch [19/50] - Training Loss: 0.0100, Training MSE: 0.7826 - Validation Loss: 0.8201, Validation MSE: 0.8367
Step [100/435] - Training Loss: 0.0101 - Training MSE: 0.7886
Step [200/435] - Training Loss: 0.0097 - Training MSE: 0.7900
Step [300/435] - Training Loss: 0.0096 - Training MSE: 0.7883
Step [400/435] - Training Loss: 0.0120 - Training MSE: 0.7878
Epoch [20/50] - Training Loss: 0.0084, Training MSE: 0.7878 - Validation Loss: 0.8246, Validation MSE: 0.8405
Step [100/435] - Training Loss: 0.0061 - Training MSE: 0.7964
Step [200/435] - Training Loss: 0.0061 - Training MSE: 0.7913
Step [300/435] - Training Loss: 0.0081 - Training MSE: 0.7896
Step [400/435] - Training Loss: 0.0067 - Training MSE: 0.7924
Epoch [21/50] - Training Loss: 0.0071, Training MSE: 0.7912 - Validation Loss: 0.8344, Validation MSE: 0.8493
Step [100/435] - Training Loss: 0.0067 - Training MSE: 0.8002
Step [200/435] - Training Loss: 0.0071 - Training MSE: 0.8009
Step [300/435] - Training Loss: 0.0070 - Training MSE: 0.7963
Step [400/435] - Training Loss: 0.0053 - Training MSE: 0.7946
Epoch [22/50] - Training Loss: 0.0060, Training MSE: 0.7941 - Validation Loss: 0.8400, Validation MSE: 0.8555
Step [100/435] - Training Loss: 0.0046 - Training MSE: 0.7930
Step [200/435] - Training Loss: 0.0054 - Training MSE: 0.7987
Step [300/435] - Training Loss: 0.0048 - Training MSE: 0.7986
Step [400/435] - Training Loss: 0.0058 - Training MSE: 0.7976
Epoch [23/50] - Training Loss: 0.0051, Training MSE: 0.7968 - Validation Loss: 0.8398, Validation MSE: 0.8552
Step [100/435] - Training Loss: 0.0046 - Training MSE: 0.8091
Step [200/435] - Training Loss: 0.0044 - Training MSE: 0.8047
Step [300/435] - Training Loss: 0.0041 - Training MSE: 0.7978
Step [400/435] - Training Loss: 0.0041 - Training MSE: 0.7975
Epoch [24/50] - Training Loss: 0.0046, Training MSE: 0.7982 - Validation Loss: 0.8454, Validation MSE: 0.8614
Step [100/435] - Training Loss: 0.0043 - Training MSE: 0.8051
Step [200/435] - Training Loss: 0.0041 - Training MSE: 0.8029
Step [300/435] - Training Loss: 0.0036 - Training MSE: 0.8008
Step [400/435] - Training Loss: 0.0034 - Training MSE: 0.8006
Epoch [25/50] - Training Loss: 0.0040, Training MSE: 0.8000 - Validation Loss: 0.8471, Validation MSE: 0.8635
Step [100/435] - Training Loss: 0.0035 - Training MSE: 0.7997
Step [200/435] - Training Loss: 0.0028 - Training MSE: 0.8036
Step [300/435] - Training Loss: 0.0036 - Training MSE: 0.8002
Step [400/435] - Training Loss: 0.0042 - Training MSE: 0.8029
Epoch [26/50] - Training Loss: 0.0037, Training MSE: 0.8015 - Validation Loss: 0.8479, Validation MSE: 0.8643
Step [100/435] - Training Loss: 0.0035 - Training MSE: 0.8106
Step [200/435] - Training Loss: 0.0054 - Training MSE: 0.8063
Step [300/435] - Training Loss: 0.0046 - Training MSE: 0.8047
Step [400/435] - Training Loss: 0.0040 - Training MSE: 0.8028
Epoch [27/50] - Training Loss: 0.0043, Training MSE: 0.8031 - Validation Loss: 0.8483, Validation MSE: 0.8642
Step [100/435] - Training Loss: 0.0028 - Training MSE: 0.8015
Step [200/435] - Training Loss: 0.0040 - Training MSE: 0.8030
Step [300/435] - Training Loss: 0.0036 - Training MSE: 0.8030
Step [400/435] - Training Loss: 0.0079 - Training MSE: 0.8025
Epoch [28/50] - Training Loss: 0.0037, Training MSE: 0.8037 - Validation Loss: 0.8482, Validation MSE: 0.8644
Step [100/435] - Training Loss: 0.0133 - Training MSE: 0.8092
Step [200/435] - Training Loss: 0.0036 - Training MSE: 0.8067
Step [300/435] - Training Loss: 0.0033 - Training MSE: 0.8063
Step [400/435] - Training Loss: 0.0020 - Training MSE: 0.8067
Epoch [29/50] - Training Loss: 0.0044, Training MSE: 0.8054 - Validation Loss: 0.8503, Validation MSE: 0.8654
Step [100/435] - Training Loss: 0.0021 - Training MSE: 0.8117
Step [200/435] - Training Loss: 0.0121 - Training MSE: 0.8105
Step [300/435] - Training Loss: 0.0028 - Training MSE: 0.8060
Step [400/435] - Training Loss: 0.0025 - Training MSE: 0.8052
Epoch [30/50] - Training Loss: 0.0038, Training MSE: 0.8053 - Validation Loss: 0.8541, Validation MSE: 0.8688
Step [100/435] - Training Loss: 0.0014 - Training MSE: 0.7938
Step [200/435] - Training Loss: 0.0031 - Training MSE: 0.8074
Step [300/435] - Training Loss: 0.0015 - Training MSE: 0.8058
Step [400/435] - Training Loss: 0.0017 - Training MSE: 0.8041
Epoch [31/50] - Training Loss: 0.0025, Training MSE: 0.8045 - Validation Loss: 0.8527, Validation MSE: 0.8680
Step [100/435] - Training Loss: 0.0031 - Training MSE: 0.8159
Step [200/435] - Training Loss: 0.0014 - Training MSE: 0.8139
Step [300/435] - Training Loss: 0.0012 - Training MSE: 0.8103
Step [400/435] - Training Loss: 0.0011 - Training MSE: 0.8056
Epoch [32/50] - Training Loss: 0.0019, Training MSE: 0.8038 - Validation Loss: 0.8513, Validation MSE: 0.8665
Step [100/435] - Training Loss: 0.0102 - Training MSE: 0.8013
Step [200/435] - Training Loss: 0.0009 - Training MSE: 0.8001
Step [300/435] - Training Loss: 0.0006 - Training MSE: 0.8021
Step [400/435] - Training Loss: 0.0008 - Training MSE: 0.8021
Epoch [33/50] - Training Loss: 0.0008, Training MSE: 0.8031 - Validation Loss: 0.8515, Validation MSE: 0.8670
Step [100/435] - Training Loss: 0.0004 - Training MSE: 0.7997
Step [200/435] - Training Loss: 0.0004 - Training MSE: 0.8031
Step [300/435] - Training Loss: 0.0004 - Training MSE: 0.8047
Step [400/435] - Training Loss: 0.0005 - Training MSE: 0.8031
Epoch [34/50] - Training Loss: 0.0004, Training MSE: 0.8029 - Validation Loss: 0.8521, Validation MSE: 0.8676
Step [100/435] - Training Loss: 0.0002 - Training MSE: 0.7941
Step [200/435] - Training Loss: 0.0005 - Training MSE: 0.7996
Step [300/435] - Training Loss: 0.0003 - Training MSE: 0.8016
Step [400/435] - Training Loss: 0.0003 - Training MSE: 0.8022
Epoch [35/50] - Training Loss: 0.0003, Training MSE: 0.8028 - Validation Loss: 0.8521, Validation MSE: 0.8676
Step [100/435] - Training Loss: 0.0006 - Training MSE: 0.8030
Step [200/435] - Training Loss: 0.0002 - Training MSE: 0.8033
Step [300/435] - Training Loss: 0.0002 - Training MSE: 0.8046
Step [400/435] - Training Loss: 0.0002 - Training MSE: 0.8030
Epoch [36/50] - Training Loss: 0.0002, Training MSE: 0.8028 - Validation Loss: 0.8526, Validation MSE: 0.8683
Step [100/435] - Training Loss: 0.0001 - Training MSE: 0.8003
Step [200/435] - Training Loss: 0.0002 - Training MSE: 0.8045
Step [300/435] - Training Loss: 0.0002 - Training MSE: 0.8042
Step [400/435] - Training Loss: 0.0002 - Training MSE: 0.8047
Epoch [37/50] - Training Loss: 0.0002, Training MSE: 0.8033 - Validation Loss: 0.8518, Validation MSE: 0.8675
Step [100/435] - Training Loss: 0.0001 - Training MSE: 0.8073
Step [200/435] - Training Loss: 0.0002 - Training MSE: 0.8066
Step [300/435] - Training Loss: 0.0001 - Training MSE: 0.8049
Step [400/435] - Training Loss: 0.0001 - Training MSE: 0.8029
Epoch [38/50] - Training Loss: 0.0002, Training MSE: 0.8030 - Validation Loss: 0.8526, Validation MSE: 0.8680
Step [100/435] - Training Loss: 0.0001 - Training MSE: 0.8039
Step [200/435] - Training Loss: 0.0002 - Training MSE: 0.7996
Step [300/435] - Training Loss: 0.0001 - Training MSE: 0.8031
Step [400/435] - Training Loss: 0.0001 - Training MSE: 0.8036
Epoch [39/50] - Training Loss: 0.0001, Training MSE: 0.8035 - Validation Loss: 0.8525, Validation MSE: 0.8681
Step [100/435] - Training Loss: 0.0001 - Training MSE: 0.8010
Step [200/435] - Training Loss: 0.0001 - Training MSE: 0.8027
Step [300/435] - Training Loss: 0.0002 - Training MSE: 0.8015
Step [400/435] - Training Loss: 0.0001 - Training MSE: 0.8031
Epoch [40/50] - Training Loss: 0.0001, Training MSE: 0.8036 - Validation Loss: 0.8533, Validation MSE: 0.8687
Step [100/435] - Training Loss: 0.0001 - Training MSE: 0.8101
Step [200/435] - Training Loss: 0.0001 - Training MSE: 0.8026
Step [300/435] - Training Loss: 0.0001 - Training MSE: 0.8033
Step [400/435] - Training Loss: 0.0001 - Training MSE: 0.8038
Epoch [41/50] - Training Loss: 0.0001, Training MSE: 0.8033 - Validation Loss: 0.8533, Validation MSE: 0.8688
Step [100/435] - Training Loss: 0.0001 - Training MSE: 0.8005
Step [200/435] - Training Loss: 0.0001 - Training MSE: 0.8006
Step [300/435] - Training Loss: 0.0000 - Training MSE: 0.8055
Step [400/435] - Training Loss: 0.0000 - Training MSE: 0.8031
Epoch [42/50] - Training Loss: 0.0001, Training MSE: 0.8035 - Validation Loss: 0.8533, Validation MSE: 0.8689
Step [100/435] - Training Loss: 0.0000 - Training MSE: 0.7973
Step [200/435] - Training Loss: 0.0000 - Training MSE: 0.8005
Step [300/435] - Training Loss: 0.0000 - Training MSE: 0.8027
Step [400/435] - Training Loss: 0.0000 - Training MSE: 0.8034
Epoch [43/50] - Training Loss: 0.0000, Training MSE: 0.8033 - Validation Loss: 0.8532, Validation MSE: 0.8688
Step [100/435] - Training Loss: 0.0000 - Training MSE: 0.7967
Step [200/435] - Training Loss: 0.0000 - Training MSE: 0.7960
Step [300/435] - Training Loss: 0.0000 - Training MSE: 0.7976
Step [400/435] - Training Loss: 0.0000 - Training MSE: 0.8024
Epoch [44/50] - Training Loss: 0.0000, Training MSE: 0.8032 - Validation Loss: 0.8533, Validation MSE: 0.8688
Step [100/435] - Training Loss: 0.0000 - Training MSE: 0.8043
Step [200/435] - Training Loss: 0.0000 - Training MSE: 0.8054
Step [300/435] - Training Loss: 0.0000 - Training MSE: 0.8052
Step [400/435] - Training Loss: 0.0000 - Training MSE: 0.8047
Epoch [45/50] - Training Loss: 0.0000, Training MSE: 0.8037 - Validation Loss: 0.8533, Validation MSE: 0.8689
Step [100/435] - Training Loss: 0.0000 - Training MSE: 0.8019
Step [200/435] - Training Loss: 0.0000 - Training MSE: 0.8023
Step [300/435] - Training Loss: 0.0000 - Training MSE: 0.8026
Step [400/435] - Training Loss: 0.0000 - Training MSE: 0.8041
Epoch [46/50] - Training Loss: 0.0000, Training MSE: 0.8032 - Validation Loss: 0.8533, Validation MSE: 0.8689
Step [100/435] - Training Loss: 0.0000 - Training MSE: 0.7993
Step [200/435] - Training Loss: 0.0000 - Training MSE: 0.8029
Step [300/435] - Training Loss: 0.0000 - Training MSE: 0.8066
Step [400/435] - Training Loss: 0.0000 - Training MSE: 0.8051
Epoch [47/50] - Training Loss: 0.0000, Training MSE: 0.8036 - Validation Loss: 0.8533, Validation MSE: 0.8689
Step [100/435] - Training Loss: 0.0000 - Training MSE: 0.7992
Step [200/435] - Training Loss: 0.0000 - Training MSE: 0.8020
Step [300/435] - Training Loss: 0.0000 - Training MSE: 0.8030
Step [400/435] - Training Loss: 0.0000 - Training MSE: 0.8036
Epoch [48/50] - Training Loss: 0.0000, Training MSE: 0.8032 - Validation Loss: 0.8533, Validation MSE: 0.8689
Step [100/435] - Training Loss: 0.0000 - Training MSE: 0.7972
Step [200/435] - Training Loss: 0.0000 - Training MSE: 0.7993
Step [300/435] - Training Loss: 0.0000 - Training MSE: 0.8023
Step [400/435] - Training Loss: 0.0000 - Training MSE: 0.8016
Epoch [49/50] - Training Loss: 0.0000, Training MSE: 0.8035 - Validation Loss: 0.8533, Validation MSE: 0.8689
Step [100/435] - Training Loss: 0.0000 - Training MSE: 0.8021
Step [200/435] - Training Loss: 0.0000 - Training MSE: 0.8040
Step [300/435] - Training Loss: 0.0000 - Training MSE: 0.8023
Step [400/435] - Training Loss: 0.0000 - Training MSE: 0.8036
Epoch [50/50] - Training Loss: 0.0000, Training MSE: 0.8037 - Validation Loss: 0.8533, Validation MSE: 0.8689
wandb: 🚀 View run HCPflat_raw_beta_age at: https://stability.wandb.io/ckadirt/fMRI-foundation-model/runs/HCPflat_raw_beta_age_31e54b73-122f-4c96-8d20-21ee38d0705b
wandb: Find logs at: wandb/run-20241127_021238-HCPflat_raw_beta_age_31e54b73-122f-4c96-8d20-21ee38d0705b/logs