ViV1T / viv1t_005 /output.log
bryanlimy's picture
rename folders
e148497
raw
history blame
23.3 kB
Use bfloat16 for core module.
Use parallel attention and MLP in ViViT.
Epoch 001/400
Train loss: 111647336.00 correlation: 0.0122
Validation loss: 200300080.00 correlation: 0.0267
Elapse: 537.13s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 002/400
Train loss: 97648256.00 correlation: 0.0367
Validation loss: 199289632.00 correlation: 0.0355
Elapse: 539.72s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 003/400
Train loss: 96321792.00 correlation: 0.0500
Validation loss: 198299696.00 correlation: 0.0446
Elapse: 548.37s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 004/400
Train loss: 95213544.00 correlation: 0.0617
Validation loss: 196983504.00 correlation: 0.0527
Elapse: 552.04s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 005/400
Train loss: 93915056.00 correlation: 0.0756
Validation loss: 195022704.00 correlation: 0.0660
Elapse: 551.29s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 006/400
Train loss: 92500376.00 correlation: 0.0909
Validation loss: 193045536.00 correlation: 0.0815
Elapse: 549.45s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 007/400
Train loss: 91511136.00 correlation: 0.1012
Validation loss: 191545056.00 correlation: 0.0905
Elapse: 547.11s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 008/400
Train loss: 90428944.00 correlation: 0.1113
Validation loss: 189976016.00 correlation: 0.0998
Elapse: 544.76s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 009/400
Train loss: 89301664.00 correlation: 0.1228
Validation loss: 188514336.00 correlation: 0.1074
Elapse: 541.79s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 010/400
Train loss: 88238616.00 correlation: 0.1335
Validation loss: 186730592.00 correlation: 0.1194
Elapse: 540.44s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 011/400
Train loss: 87239336.00 correlation: 0.1436
Validation loss: 185287104.00 correlation: 0.1296
Elapse: 539.71s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 012/400
Train loss: 86205256.00 correlation: 0.1540
Validation loss: 183237792.00 correlation: 0.1419
Elapse: 540.02s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 013/400
Train loss: 85068472.00 correlation: 0.1655
Validation loss: 181721296.00 correlation: 0.1515
Elapse: 539.81s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 014/400
Train loss: 84160560.00 correlation: 0.1745
Validation loss: 180469664.00 correlation: 0.1595
Elapse: 540.34s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 015/400
Train loss: 83386128.00 correlation: 0.1821
Validation loss: 179517792.00 correlation: 0.1658
Elapse: 540.81s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 016/400
Train loss: 82805200.00 correlation: 0.1877
Validation loss: 178801584.00 correlation: 0.1698
Elapse: 540.70s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 017/400
Train loss: 82275736.00 correlation: 0.1926
Validation loss: 177842080.00 correlation: 0.1761
Elapse: 540.76s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 018/400
Train loss: 81662840.00 correlation: 0.1987
Validation loss: 176971248.00 correlation: 0.1820
Elapse: 541.07s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 019/400
Train loss: 81147088.00 correlation: 0.2038
Validation loss: 176423600.00 correlation: 0.1858
Elapse: 541.20s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 020/400
Train loss: 80748784.00 correlation: 0.2079
Validation loss: 175690976.00 correlation: 0.1908
Elapse: 541.22s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 021/400
Train loss: 80313880.00 correlation: 0.2122
Validation loss: 175389216.00 correlation: 0.1929
Elapse: 540.65s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 022/400
Train loss: 79957744.00 correlation: 0.2153
Validation loss: 174862864.00 correlation: 0.1968
Elapse: 540.96s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 023/400
Train loss: 79621360.00 correlation: 0.2186
Validation loss: 174437632.00 correlation: 0.1996
Elapse: 541.11s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 024/400
Train loss: 79374368.00 correlation: 0.2211
Validation loss: 173783968.00 correlation: 0.2031
Elapse: 542.03s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 025/400
Train loss: 79085072.00 correlation: 0.2240
Validation loss: 173357520.00 correlation: 0.2059
Elapse: 541.66s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 026/400
Train loss: 78723728.00 correlation: 0.2273
Validation loss: 173125120.00 correlation: 0.2087
Elapse: 542.13s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 027/400
Train loss: 78456624.00 correlation: 0.2299
Validation loss: 172740432.00 correlation: 0.2102
Elapse: 541.72s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 028/400
Train loss: 78264240.00 correlation: 0.2316
Validation loss: 172426416.00 correlation: 0.2125
Elapse: 541.90s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 029/400
Train loss: 78095968.00 correlation: 0.2335
Validation loss: 172338688.00 correlation: 0.2139
Elapse: 542.04s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 030/400
Train loss: 77880056.00 correlation: 0.2357
Validation loss: 171972944.00 correlation: 0.2151
Elapse: 541.96s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 031/400
Train loss: 77782920.00 correlation: 0.2367
Validation loss: 171662176.00 correlation: 0.2171
Elapse: 542.59s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 032/400
Train loss: 77596272.00 correlation: 0.2382
Validation loss: 171484624.00 correlation: 0.2187
Elapse: 543.51s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 033/400
Train loss: 77378984.00 correlation: 0.2403
Validation loss: 171180896.00 correlation: 0.2208
Elapse: 542.09s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 034/400
Train loss: 77329272.00 correlation: 0.2411
Validation loss: 171382000.00 correlation: 0.2191
Elapse: 541.49s
Epoch 035/400
Train loss: 77173400.00 correlation: 0.2426
Validation loss: 170990288.00 correlation: 0.2215
Elapse: 542.22s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 036/400
Train loss: 77103352.00 correlation: 0.2430
Validation loss: 171064224.00 correlation: 0.2212
Elapse: 542.85s
Epoch 037/400
Train loss: 76961264.00 correlation: 0.2447
Validation loss: 170693952.00 correlation: 0.2239
Elapse: 542.80s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 038/400
Train loss: 76838424.00 correlation: 0.2456
Validation loss: 170481408.00 correlation: 0.2246
Elapse: 542.40s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 039/400
Train loss: 76726736.00 correlation: 0.2469
Validation loss: 170405888.00 correlation: 0.2257
Elapse: 541.86s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 040/400
Train loss: 76625736.00 correlation: 0.2481
Validation loss: 170183216.00 correlation: 0.2271
Elapse: 542.67s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 041/400
Train loss: 76633712.00 correlation: 0.2477
Validation loss: 170194400.00 correlation: 0.2270
Elapse: 542.30s
Epoch 042/400
Train loss: 76442136.00 correlation: 0.2493
Validation loss: 170452384.00 correlation: 0.2263
Elapse: 542.26s
Epoch 043/400
Train loss: 76492200.00 correlation: 0.2491
Validation loss: 170249952.00 correlation: 0.2260
Elapse: 542.10s
Epoch 044/400
Train loss: 76279480.00 correlation: 0.2510
Validation loss: 169784496.00 correlation: 0.2295
Elapse: 541.77s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 045/400
Train loss: 76193080.00 correlation: 0.2520
Validation loss: 169944928.00 correlation: 0.2278
Elapse: 542.23s
Epoch 046/400
Train loss: 76107936.00 correlation: 0.2526
Validation loss: 169860016.00 correlation: 0.2283
Elapse: 542.90s
Epoch 047/400
Train loss: 76111024.00 correlation: 0.2527
Validation loss: 169548304.00 correlation: 0.2308
Elapse: 541.89s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 048/400
Train loss: 76049672.00 correlation: 0.2534
Validation loss: 169801264.00 correlation: 0.2296
Elapse: 543.95s
Epoch 049/400
Train loss: 75997232.00 correlation: 0.2537
Validation loss: 169721248.00 correlation: 0.2301
Elapse: 543.00s
Epoch 050/400
Train loss: 75961488.00 correlation: 0.2545
Validation loss: 169722912.00 correlation: 0.2293
Elapse: 542.91s
Epoch 051/400
Train loss: 75908376.00 correlation: 0.2548
Validation loss: 169474704.00 correlation: 0.2310
Elapse: 542.56s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 052/400
Train loss: 75771856.00 correlation: 0.2561
Validation loss: 170132720.00 correlation: 0.2272
Elapse: 542.05s
Epoch 053/400
Train loss: 75913696.00 correlation: 0.2547
Validation loss: 169491888.00 correlation: 0.2309
Elapse: 542.57s
Epoch 054/400
Train loss: 75764272.00 correlation: 0.2560
Validation loss: 169266704.00 correlation: 0.2330
Elapse: 542.91s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 055/400
Train loss: 75670816.00 correlation: 0.2569
Validation loss: 169200320.00 correlation: 0.2327
Elapse: 542.21s
Epoch 056/400
Train loss: 75680240.00 correlation: 0.2570
Validation loss: 169253344.00 correlation: 0.2322
Elapse: 542.73s
Epoch 057/400
Train loss: 75623792.00 correlation: 0.2573
Validation loss: 169158704.00 correlation: 0.2336
Elapse: 544.29s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 058/400
Train loss: 75518968.00 correlation: 0.2584
Validation loss: 169124832.00 correlation: 0.2339
Elapse: 542.64s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 059/400
Train loss: 75452928.00 correlation: 0.2591
Validation loss: 169483008.00 correlation: 0.2320
Elapse: 542.34s
Epoch 060/400
Train loss: 75478992.00 correlation: 0.2590
Validation loss: 169223728.00 correlation: 0.2337
Elapse: 543.01s
Epoch 061/400
Train loss: 75414704.00 correlation: 0.2597
Validation loss: 169588672.00 correlation: 0.2307
Elapse: 542.79s
Epoch 062/400
Train loss: 75631880.00 correlation: 0.2578
Validation loss: 169325440.00 correlation: 0.2326
Elapse: 543.75s
Epoch 063/400
Train loss: 75359640.00 correlation: 0.2602
Validation loss: 169091040.00 correlation: 0.2339
Elapse: 543.16s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 064/400
Train loss: 75319080.00 correlation: 0.2605
Validation loss: 169416560.00 correlation: 0.2321
Elapse: 543.52s
Epoch 065/400
Train loss: 75306104.00 correlation: 0.2609
Validation loss: 169176224.00 correlation: 0.2331
Elapse: 542.80s
Epoch 066/400
Train loss: 75301592.00 correlation: 0.2609
Validation loss: 169371616.00 correlation: 0.2327
Elapse: 543.10s
Epoch 067/400
Train loss: 75389672.00 correlation: 0.2601
Validation loss: 169169312.00 correlation: 0.2332
Elapse: 544.11s
Epoch 068/400
Train loss: 75361008.00 correlation: 0.2604
Validation loss: 169366960.00 correlation: 0.2315
Elapse: 543.42s
Loaded checkpoint from epoch 63 (correlation: 0.2339).
Reduce learning rate of core to 1.4400e-03 (num. reduce: 1).
Reduce learning rate of readouts to 1.0800e-03 (num. reduce: 1).
Reduce learning rate of shifters to 1.0800e-03 (num. reduce: 1).
Epoch 069/400
Train loss: 73278464.00 correlation: 0.2784
Validation loss: 167482848.00 correlation: 0.2447
Elapse: 544.59s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 070/400
Train loss: 72562424.00 correlation: 0.2849
Validation loss: 167277872.00 correlation: 0.2456
Elapse: 544.90s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 071/400
Train loss: 72429480.00 correlation: 0.2862
Validation loss: 167337568.00 correlation: 0.2452
Elapse: 544.84s
Epoch 072/400
Train loss: 72339856.00 correlation: 0.2872
Validation loss: 167472656.00 correlation: 0.2442
Elapse: 544.89s
Epoch 073/400
Train loss: 72270912.00 correlation: 0.2877
Validation loss: 167356592.00 correlation: 0.2443
Elapse: 545.34s
Epoch 074/400
Train loss: 72207960.00 correlation: 0.2884
Validation loss: 167467040.00 correlation: 0.2434
Elapse: 545.38s
Epoch 075/400
Train loss: 72186752.00 correlation: 0.2885
Validation loss: 167473600.00 correlation: 0.2434
Elapse: 545.13s
Loaded checkpoint from epoch 70 (correlation: 0.2456).
Reduce learning rate of core to 4.3200e-04 (num. reduce: 1).
Reduce learning rate of readouts to 3.2400e-04 (num. reduce: 1).
Reduce learning rate of shifters to 3.2400e-04 (num. reduce: 1).
Epoch 076/400
Train loss: 71743648.00 correlation: 0.2919
Validation loss: 166945040.00 correlation: 0.2479
Elapse: 544.86s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 077/400
Train loss: 71453328.00 correlation: 0.2949
Validation loss: 166933984.00 correlation: 0.2480
Elapse: 545.20s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 078/400
Train loss: 71407184.00 correlation: 0.2951
Validation loss: 166839616.00 correlation: 0.2480
Elapse: 545.38s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 079/400
Train loss: 71308560.00 correlation: 0.2960
Validation loss: 166820688.00 correlation: 0.2484
Elapse: 545.26s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 080/400
Train loss: 71223520.00 correlation: 0.2968
Validation loss: 166801616.00 correlation: 0.2487
Elapse: 545.81s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 081/400
Train loss: 71151600.00 correlation: 0.2975
Validation loss: 166777584.00 correlation: 0.2485
Elapse: 545.15s
Epoch 082/400
Train loss: 71166128.00 correlation: 0.2973
Validation loss: 166806736.00 correlation: 0.2484
Elapse: 545.51s
Epoch 083/400
Train loss: 71003768.00 correlation: 0.2991
Validation loss: 166794000.00 correlation: 0.2487
Elapse: 545.39s
Epoch 084/400
Train loss: 71028680.00 correlation: 0.2987
Validation loss: 166740976.00 correlation: 0.2486
Elapse: 545.50s
Epoch 085/400
Train loss: 70987920.00 correlation: 0.2989
Validation loss: 166771344.00 correlation: 0.2483
Elapse: 545.38s
Loaded checkpoint from epoch 80 (correlation: 0.2487).
Reduce learning rate of core to 1.2960e-04 (num. reduce: 1).
Reduce learning rate of readouts to 9.7200e-05 (num. reduce: 1).
Reduce learning rate of shifters to 9.7200e-05 (num. reduce: 1).
Epoch 086/400
Train loss: 70886192.00 correlation: 0.2998
Validation loss: 166696544.00 correlation: 0.2492
Elapse: 545.68s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 087/400
Train loss: 70891072.00 correlation: 0.2998
Validation loss: 166700640.00 correlation: 0.2493
Elapse: 545.36s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 088/400
Train loss: 70786208.00 correlation: 0.3009
Validation loss: 166720928.00 correlation: 0.2490
Elapse: 545.75s
Epoch 089/400
Train loss: 70840864.00 correlation: 0.3002
Validation loss: 166705888.00 correlation: 0.2491
Elapse: 546.01s
Epoch 090/400
Train loss: 70781008.00 correlation: 0.3008
Validation loss: 166757248.00 correlation: 0.2489
Elapse: 545.02s
Epoch 091/400
Train loss: 70768960.00 correlation: 0.3009
Validation loss: 166698640.00 correlation: 0.2489
Elapse: 545.07s
Epoch 092/400
Train loss: 70700664.00 correlation: 0.3016
Validation loss: 166705392.00 correlation: 0.2491
Elapse: 545.85s
Loaded checkpoint from epoch 87 (correlation: 0.2493).
Reduce learning rate of core to 3.8880e-05 (num. reduce: 1).
Reduce learning rate of readouts to 2.9160e-05 (num. reduce: 1).
Reduce learning rate of shifters to 2.9160e-05 (num. reduce: 1).
Epoch 093/400
Train loss: 70743624.00 correlation: 0.3012
Validation loss: 166685456.00 correlation: 0.2494
Elapse: 545.69s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 094/400
Train loss: 70752552.00 correlation: 0.3012
Validation loss: 166676048.00 correlation: 0.2493
Elapse: 545.53s
Epoch 095/400
Train loss: 70729328.00 correlation: 0.3013
Validation loss: 166677072.00 correlation: 0.2494
Elapse: 545.12s
Epoch 096/400
Train loss: 70661304.00 correlation: 0.3018
Validation loss: 166687824.00 correlation: 0.2493
Elapse: 545.30s
Epoch 097/400
Train loss: 70768896.00 correlation: 0.3006
Validation loss: 166658272.00 correlation: 0.2492
Elapse: 545.47s
Epoch 098/400
Train loss: 70673976.00 correlation: 0.3017
Validation loss: 166648288.00 correlation: 0.2495
Elapse: 545.22s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 099/400
Train loss: 70635672.00 correlation: 0.3022
Validation loss: 166648032.00 correlation: 0.2495
Elapse: 545.17s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 100/400
Train loss: 70748008.00 correlation: 0.3010
Validation loss: 166647312.00 correlation: 0.2495
Elapse: 545.61s
Epoch 101/400
Train loss: 70682408.00 correlation: 0.3016
Validation loss: 166662208.00 correlation: 0.2494
Elapse: 545.56s
Epoch 102/400
Train loss: 70642688.00 correlation: 0.3020
Validation loss: 166662624.00 correlation: 0.2495
Elapse: 545.17s
Epoch 103/400
Train loss: 70638368.00 correlation: 0.3019
Validation loss: 166645120.00 correlation: 0.2495
Elapse: 545.25s
Epoch 104/400
Train loss: 70563872.00 correlation: 0.3027
Validation loss: 166649696.00 correlation: 0.2495
Elapse: 545.70s
Loaded checkpoint from epoch 99 (correlation: 0.2495).
Reduce learning rate of core to 1.1664e-05 (num. reduce: 1).
Reduce learning rate of readouts to 8.7480e-06 (num. reduce: 1).
Reduce learning rate of shifters to 8.7480e-06 (num. reduce: 1).
Epoch 105/400
Train loss: 70679696.00 correlation: 0.3019
Validation loss: 166646944.00 correlation: 0.2495
Elapse: 545.44s
Epoch 106/400
Train loss: 70623656.00 correlation: 0.3021
Validation loss: 166651056.00 correlation: 0.2495
Elapse: 545.46s
Epoch 107/400
Train loss: 70689912.00 correlation: 0.3013
Validation loss: 166642080.00 correlation: 0.2495
Elapse: 545.17s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 108/400
Train loss: 70636352.00 correlation: 0.3019
Validation loss: 166643376.00 correlation: 0.2495
Elapse: 545.12s
Epoch 109/400
Train loss: 70622056.00 correlation: 0.3021
Validation loss: 166645664.00 correlation: 0.2495
Elapse: 545.91s
Epoch 110/400
Train loss: 70689848.00 correlation: 0.3013
Validation loss: 166646544.00 correlation: 0.2495
Elapse: 544.95s
Epoch 111/400
Train loss: 70594792.00 correlation: 0.3025
Validation loss: 166655344.00 correlation: 0.2494
Elapse: 545.66s
Epoch 112/400
Train loss: 70636904.00 correlation: 0.3020
Validation loss: 166638224.00 correlation: 0.2495
Elapse: 544.74s
Loaded checkpoint from epoch 107 (correlation: 0.2495).
Reduce learning rate of core to 3.4992e-06 (num. reduce: 1).
Reduce learning rate of readouts to 2.6244e-06 (num. reduce: 1).
Reduce learning rate of shifters to 2.6244e-06 (num. reduce: 1).
Epoch 113/400
Train loss: 70679760.00 correlation: 0.3016
Validation loss: 166645488.00 correlation: 0.2495
Elapse: 543.62s
Epoch 114/400
Train loss: 70609840.00 correlation: 0.3026
Validation loss: 166641568.00 correlation: 0.2495
Elapse: 543.57s
Checkpoint saved to /home/storage/runs/vivit_ensemble/028/ckpt/model_state.pt.
Epoch 115/400
Train loss: 70676264.00 correlation: 0.3017
Validation loss: 166645824.00 correlation: 0.2495
Elapse: 545.22s
Epoch 116/400
Train loss: 70640760.00 correlation: 0.3023
Validation loss: 166649888.00 correlation: 0.2495
Elapse: 545.14s
Epoch 117/400
Train loss: 70651464.00 correlation: 0.3017
Validation loss: 166644896.00 correlation: 0.2495
Elapse: 545.75s
Epoch 118/400
Train loss: 70647664.00 correlation: 0.3020
Validation loss: 166642016.00 correlation: 0.2495
Elapse: 551.10s
Epoch 119/400
Train loss: 70647632.00 correlation: 0.3017
Validation loss: 166642992.00 correlation: 0.2495
Elapse: 545.02s
Loaded checkpoint from epoch 114 (correlation: 0.2495).
Reduce learning rate of core to 1.0498e-06 (num. reduce: 1).
Reduce learning rate of readouts to 7.8732e-07 (num. reduce: 1).
Reduce learning rate of shifters to 7.8732e-07 (num. reduce: 1).
Epoch 120/400
Train loss: 70673976.00 correlation: 0.3014
Validation loss: 166641376.00 correlation: 0.2495
Elapse: 544.88s
Epoch 121/400
Train loss: 70599064.00 correlation: 0.3023
Validation loss: 166642464.00 correlation: 0.2495
Elapse: 544.91s
Epoch 122/400
Train loss: 70592552.00 correlation: 0.3025
Validation loss: 166642720.00 correlation: 0.2495
Elapse: 544.80s
Epoch 123/400
Train loss: 70644184.00 correlation: 0.3019
Validation loss: 166643072.00 correlation: 0.2495
Elapse: 544.57s
Epoch 124/400
Train loss: 70629504.00 correlation: 0.3022
Validation loss: 166642208.00 correlation: 0.2495
Elapse: 545.38s
Loaded checkpoint from epoch 114 (correlation: 0.2495).
Reduce learning rate of core to 3.1493e-07 (num. reduce: 2).
Reduce learning rate of readouts to 2.3620e-07 (num. reduce: 2).
Reduce learning rate of shifters to 2.3620e-07 (num. reduce: 2).
Epoch 125/400
Train loss: 70617168.00 correlation: 0.3023
Validation loss: 166641952.00 correlation: 0.2495
Elapse: 544.97s
Epoch 126/400
Train loss: 70613328.00 correlation: 0.3026
Validation loss: 166642704.00 correlation: 0.2495
Elapse: 544.92s
Epoch 127/400
Train loss: 70681712.00 correlation: 0.3016
Validation loss: 166642848.00 correlation: 0.2495
Elapse: 544.98s
Epoch 128/400
Train loss: 70630672.00 correlation: 0.3021
Validation loss: 166642912.00 correlation: 0.2495
Elapse: 544.96s
Epoch 129/400
Train loss: 70600632.00 correlation: 0.3025
Validation loss: 166642848.00 correlation: 0.2495
Elapse: 545.27s
Model has not improved after 2 LR reductions.
Loaded checkpoint from epoch 114 (correlation: 0.2495).
ValidationA: 0.2465 B: 0.2783 C: 0.2688 D: 0.2292 E: 0.2366 F: 0.2341 G: 0.2549 H: 0.2330 I: 0.2567 J: 0.2571 average: 0.2495
Results saved to /home/storage/runs/vivit_ensemble/028.