###################################
2022-05-23 20:25:50.327157
Namespace(data='mri', algorithm='ALS-RS', rank='8,4,4,1', 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=(8, 4, 4, 1), 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: 324912849692.4593 rmse: 133.0651912886661 rre: 0.8848532306031022 time: 0.27347117799999987
loss: 248488828264.31516 rmse: 116.36823656689651 rre: 0.7738222826616479 time: 0.26532030900000025
loss: 220595682073.49335 rmse: 109.64264975784072 rre: 0.7290986614196024 time: 0.1813691559999997
loss: 131993704434.64587 rmse: 84.81206310649094 rre: 0.5639809127173651 time: 0.25410809999999984
loss: 106445349192.00826 rmse: 76.16305652079174 rre: 0.5064669878152385 time: 0.28110844199999985
rre_diff: 0.48032988499091456

step: 1
loss: 96786440971.24341 rmse: 72.6253568196376 rre: 0.4829420901379863 time: 0.27404265000000017
loss: 92363165729.00974 rmse: 70.94640993141253 rre: 0.47177747553314847 time: 0.26753809900000025
loss: 90439723371.77765 rmse: 70.20380183541157 rre: 0.46683930074487506 time: 0.17517253300000046
loss: 90439489419.37695 rmse: 70.20371103262057 rre: 0.4668386969269856 time: 0.25520908399999964
loss: 90620889531.55775 rmse: 70.27408173964673 rre: 0.46730664610925404 time: 0.28088747199999986
Warning: The loss function increased!
rre_diff: 0.039160341705984425

step: 2
loss: 88617360707.3609 rmse: 69.49289825764048 rre: 0.4621119537854931 time: 0.2734464379999997
loss: 87357957724.34929 rmse: 68.99732525474754 rre: 0.4588165061303794 time: 0.26712414700000053
loss: 86947977671.89081 rmse: 68.83522900755578 rre: 0.4577386029867607 time: 0.1768991059999987
loss: 86947972412.80165 rmse: 68.83522692579021 rre: 0.45773858914349363 time: 0.24748598699999924
loss: 88337877594.25734 rmse: 69.38322770875327 rre: 0.4613826696012142 time: 0.2817840010000001
Warning: The loss function increased!
rre_diff: 0.00592397650803983

step: 3
loss: 86486891009.04967 rmse: 68.65246917259934 rre: 0.45652329168844474 time: 0.27457572399999997
loss: 86031084820.49263 rmse: 68.4713228839517 rre: 0.45531871010576835 time: 0.2662847639999999
loss: 85771092958.34949 rmse: 68.36778207166249 rre: 0.45463018727446974 time: 0.17578653900000063
loss: 85771089887.1803 rmse: 68.36778084765439 rre: 0.4546301791350944 time: 0.2508170449999998
loss: 87282403979.3615 rmse: 68.96748175742442 rre: 0.4586180536668679 time: 0.28314640099999977
Warning: The loss function increased!
rre_diff: 0.002764615934346293

step: 4
loss: 85958195141.49619 rmse: 68.44231063607256 rre: 0.45512578526183073 time: 0.2744365930000008
loss: 85519132783.60686 rmse: 68.26729001173533 rre: 0.45396193795234896 time: 0.2662314479999992
loss: 85317028016.39081 rmse: 68.18657529008996 rre: 0.4534252034276138 time: 0.1749421739999999
loss: 85317021613.3939 rmse: 68.18657273140708 rre: 0.45342518641295504 time: 0.24653648900000036
loss: 87552516340.32509 rmse: 69.0741159585667 rre: 0.45932714682984865 time: 0.2807594860000009
Warning: The loss function increased!
rre_diff: -0.000709093162980734

