###################################
2022-05-23 20:27:59.527379
Namespace(data='mri', algorithm='ALS-RS', rank='8,8,4,4', 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=(8, 8, 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: 291963897710.7579 rmse: 126.13789972307775 rre: 0.8387883186469536 time: 0.3643562819999999
loss: 183829586573.04907 rmse: 100.0895471380635 rre: 0.6655727037027188 time: 0.34022658100000003
loss: 148492165331.18906 rmse: 89.95654959523692 rre: 0.598190576757044 time: 0.2619147150000001
loss: 125200817677.30743 rmse: 82.60086620504299 rre: 0.5492769566880136 time: 0.2926972940000008
loss: 3.4822391059345043e+56 rmse: 4.3562251016973723e+24 rre: 2.896790525862767e+22 time: 0.48061038299999925
Warning: The loss function increased!
rre_diff: -2.896790525862767e+22

step: 1
loss: 409643023613.20795 rmse: 149.41142249600892 rre: 0.993551947013654 time: 0.34782990499999933
loss: 359135454834.1371 rmse: 139.8975664827036 rre: 0.9302869702955617 time: 0.34215225500000024
loss: 287358464623.0668 rmse: 125.13909685122455 rre: 0.8321465069204166 time: 0.26977365499999983
loss: 176916581913.81238 rmse: 98.18955438118816 rre: 0.6529381843910794 time: 0.27032292499999944
loss: 414977361975.00006 rmse: 150.38108771775737 rre: 1.0 time: 0.4771504679999996
Warning: The loss function increased!
rre_diff: 2.896790525862767e+22

step: 2
loss: 126215607277.22675 rmse: 82.93494283039273 rre: 0.5514984901961151 time: 0.34267118600000046
loss: 107509646481.9013 rmse: 76.5428688908397 rre: 0.5089926536141242 time: 0.338040243
loss: 99903046988.42294 rmse: 73.78539152495304 rre: 0.4906560568536191 time: 0.25685930699999915
loss: 99869734170.27731 rmse: 73.77308857552447 rre: 0.4905742450406093 time: 0.2742406309999996
loss: 5.172685913903689e+76 rmse: 5.3093220998145405e+34 rre: 3.5305783329479154e+32 time: 0.47208606000000053
Warning: The loss function increased!
rre_diff: -3.5305783329479154e+32

step: 3
loss: 391285963933.1225 rmse: 146.02531564732803 rre: 0.9710351072961749 time: 0.35532470200000077
loss: 325991108776.42395 rmse: 133.2858041560898 rre: 0.8863202559503169 time: 0.3457588600000001
loss: 262981614637.10373 rmse: 119.7136611291297 rre: 0.7960685944353202 time: 0.2745592119999998
loss: 172015557801.42502 rmse: 96.81995647224028 rre: 0.6438306700770561 time: 0.26858052499999907
loss: 414977361975.00006 rmse: 150.38108771775737 rre: 1.0 time: 0.47316249800000065
Warning: The loss function increased!
rre_diff: 3.5305783329479154e+32

step: 4
loss: 155681314599.79245 rmse: 92.108405472863 rre: 0.6124999284865965 time: 0.34084779099999807
loss: 108682830290.37709 rmse: 76.95936734306036 rre: 0.5117622735080989 time: 0.3405984989999986
loss: 102646396216.5986 rmse: 74.79160829299721 rre: 0.49734716930209855 time: 0.25517104799999757
loss: 102816737666.00366 rmse: 74.85364081564074 rre: 0.4977596714563586 time: 0.26798633800000005
Warning: The loss function increased!
loss: 1.97798306258221e+88 rmse: 3.2831619298398737e+40 rre: 2.183227944195931e+38 time: 0.4717932280000028
Warning: The loss function increased!
rre_diff: -2.183227944195931e+38

