###################################
2022-05-23 20:30:09.752395
Namespace(data='mri', algorithm='ALS-RS', rank='16,16,4,4', seed=0, alpha=1.0, max_num_samples=1024, 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=1024, max_num_steps=5, rre_gap_tol=0.0, verbose=False)
step: 0
loss: 293324276331.09827 rmse: 126.43142211501021 rre: 0.8407401757347501 time: 0.32926459100000005
loss: 176658711570.93567 rmse: 98.11796864550956 rre: 0.6524621555448661 time: 0.3205366289999998
loss: 142119822074.58725 rmse: 88.00520249711211 rre: 0.5852145627665933 time: 0.28511942300000026
loss: 117120008672.2674 rmse: 79.8907626371405 rre: 0.5312553848997517 time: 0.3242228659999995
loss: 8.257484454876896e+169 rmse: 2.1213137227051353e+81 rre: 1.410625335206061e+79 time: 1.0723682749999996
Warning: The loss function increased!
rre_diff: -1.410625335206061e+79

step: 1
loss: 393296930986.44507 rmse: 146.40007451270043 rre: 0.973527168439367 time: 0.32865995100000056
loss: 224899814778.7527 rmse: 110.70712381750306 rre: 0.7361771715954313 time: 0.32044330100000007
loss: 181603369244.36865 rmse: 99.48164770339591 rre: 0.6615303108467201 time: 0.28218553899999943
loss: 147976579066.55997 rmse: 89.8002427249144 rre: 0.5971511716516901 time: 0.3265850999999991
loss: 414977361975.00006 rmse: 150.38108771775737 rre: 1.0 time: 1.0729832130000005
Warning: The loss function increased!
rre_diff: 1.410625335206061e+79

step: 2
loss: 102567067685.8062 rmse: 74.76270199239144 rre: 0.4971549489834105 time: 0.3289681719999997
loss: 78004820695.45573 rmse: 65.19912096389506 rre: 0.43355931223388927 time: 0.32070528399999887
loss: 73629025922.93942 rmse: 63.344009059248314 rre: 0.4212232403727221 time: 0.29355014200000085
loss: 73604239656.66736 rmse: 63.33334618809726 rre: 0.4211523347069041 time: 0.32725355200000017
loss: 1.2033748040493447e+165 rmse: 8.098069059551926e+78 rre: 5.385031577076222e+76 time: 1.073403837999999
Warning: The loss function increased!
rre_diff: -5.385031577076222e+76

step: 3
loss: 473289269146.2554 rmse: 160.5995588350939 rre: 1.0679505067586361 time: 0.3278359939999991
loss: 475529901208.6682 rmse: 160.97926281106754 rre: 1.0704754517616029 time: 0.3224861470000011
Warning: The loss function increased!
loss: 526231357063.3823 rmse: 169.34383108574517 rre: 1.1260979266460556 time: 0.2902707910000011
Warning: The loss function increased!
loss: 283519566493.8883 rmse: 124.30040311711561 rre: 0.8265693845120254 time: 0.3296983339999997
loss: 414950532094.8921 rmse: 150.37622628176035 rre: 0.9999676725572957 time: 1.0750402359999995
Warning: The loss function increased!
rre_diff: 5.385031577076222e+76

step: 4
loss: 123930291076.72893 rmse: 82.18068442666946 rre: 0.5464828435136087 time: 0.33198483800000034
loss: 212338976434.345 rmse: 107.57116666187002 rre: 0.7153237703916924 time: 0.325716946
Warning: The loss function increased!
loss: 739838031398.3751 rmse: 200.79335914533644 rre: 1.335230128952088 time: 0.2871694240000018
Warning: The loss function increased!
loss: 434912115250.4081 rmse: 153.95073687166092 rre: 1.0237373542649408 time: 0.328070787999998
loss: 1.1134655834432258e+154 rmse: 2.4633119738991414e+73 rre: 1.6380463868717366e+71 time: 1.076287078
Warning: The loss function increased!
rre_diff: -1.6380463868717366e+71

