###################################
2022-05-23 20:30:33.335997
Namespace(data='mri', algorithm='ALS-RS', rank='16,16,4,4', seed=0, alpha=1.0, max_num_samples=4096, max_num_steps=5, rre_gap_tol=0.0, verbose=False)
Loading MRI tensor...
Finished.
AlgorithmConfig(input_shape=(256, 256, 14, 20), rank=(16, 16, 4, 4), l2_regularization_strength=0.0, algorithm='ALS-RS', random_seed=0, epsilon=0.1, delta=0.01, downsampling_ratio=1.0, max_num_samples=4096, max_num_steps=5, rre_gap_tol=0.0, verbose=False)
step: 0
loss: 293324276331.09827 rmse: 126.43142211501021 rre: 0.8407401757347501 time: 0.33082589799999984
loss: 176658711570.93567 rmse: 98.11796864550956 rre: 0.6524621555448661 time: 0.3224392549999999
loss: 142119822074.58725 rmse: 88.00520249711211 rre: 0.5852145627665933 time: 0.28225902000000014
loss: 117120008672.2674 rmse: 79.8907626371405 rre: 0.5312553848997517 time: 0.30940323499999955
loss: 2.0757766574878993e+67 rmse: 1.0635828626035203e+30 rre: 7.07258391826308e+27 time: 3.429286858000001
Warning: The loss function increased!
rre_diff: -7.07258391826308e+27

step: 1
loss: 401692841648.19495 rmse: 147.9544613654826 rre: 0.98386348716383 time: 0.3401140419999997
loss: 272169423641.10062 rmse: 121.7869308112937 rre: 0.8098553658547105 time: 0.32274893700000007
loss: 217355650179.53955 rmse: 108.83447486947675 rre: 0.7237244823879891 time: 0.2811736259999993
loss: 145653777366.8987 rmse: 89.09265371746916 rre: 0.5924458658304337 time: 0.3127944120000006
loss: 414977361975.00006 rmse: 150.38108771775737 rre: 1.0 time: 3.413568478
Warning: The loss function increased!
rre_diff: 7.07258391826308e+27

step: 2
loss: 118994269462.4649 rmse: 80.52746774890002 rre: 0.5354893289509778 time: 0.32922002799999994
loss: 85656299214.58188 rmse: 68.3220159452304 rre: 0.45432585295207156 time: 0.32280603000000063
loss: 82286801825.62721 rmse: 66.96472823394699 rre: 0.44530019865017656 time: 0.29162672
loss: 84238929553.50226 rmse: 67.75438986588904 rre: 0.4505512687410122 time: 0.30718507099999925
Warning: The loss function increased!
loss: 6.3072643797283195e+75 rmse: 1.8539650244398427e+34 rre: 1.2328445368871485e+32 time: 3.4822364420000014
Warning: The loss function increased!
rre_diff: -1.2328445368871485e+32

step: 3
loss: 404910449331.5521 rmse: 148.54584592393698 rre: 0.9877960598525205 time: 0.3362930249999998
loss: 790516016886.3956 rmse: 207.55650824532097 rre: 1.3802035308779868 time: 0.32178380800000284
Warning: The loss function increased!
loss: 7286971863103.423 rmse: 630.1654163887326 rre: 4.190456565731577 time: 0.3254308820000027
Warning: The loss function increased!
loss: 279583218751.9052 rmse: 123.43450201205779 rre: 0.8208113392804136 time: 0.31019661700000256
loss: 414977361974.9312 rmse: 150.3810877177449 rre: 0.9999999999999171 time: 3.447286865999999
Warning: The loss function increased!
rre_diff: 1.2328445368871485e+32

step: 4
loss: 155983822677.99713 rmse: 92.19785106354475 rre: 0.6130947213028956 time: 0.3306655439999986
loss: 115662387567.40392 rmse: 79.39206451790243 rre: 0.5279391559323561 time: 0.33123365999999876
loss: 131791991797.56886 rmse: 84.74723347709254 rre: 0.5635498104399292 time: 0.28386544099999966
Warning: The loss function increased!
loss: 132868633234.92168 rmse: 85.09268995702666 rre: 0.5658470173904635 time: 0.3103349709999996
Warning: The loss function increased!
loss: 6.220475527867034e+70 rmse: 5.8222763082886605e+31 rre: 3.871681204498398e+29 time: 3.465919439999997
Warning: The loss function increased!
rre_diff: -3.871681204498398e+29

