Special test with strict convergence condition

Precision: [tensor(0.5533, device='cuda:0'), tensor(0.5565, device='cuda:0'), tensor(0.5544, device='cuda:0'), tensor(0.5537, device='cuda:0'), tensor(0.5537, device='cuda:0'), tensor(0.5554, device='cuda:0'), tensor(0.5519, device='cuda:0'), tensor(0.5523, device='cuda:0'), tensor(0.5563, device='cuda:0'), tensor(0.5529, device='cuda:0')]

Output distance: [tensor(4.9866, device='cuda:0'), tensor(4.9672, device='cuda:0'), tensor(4.9798, device='cuda:0'), tensor(4.9840, device='cuda:0'), tensor(4.9840, device='cuda:0'), tensor(4.9735, device='cuda:0'), tensor(4.9945, device='cuda:0'), tensor(4.9924, device='cuda:0'), tensor(4.9682, device='cuda:0'), tensor(4.9887, device='cuda:0')]

Prediction loss: [tensor(20230966., device='cuda:0'), tensor(18886854., device='cuda:0'), tensor(17966816., device='cuda:0'), tensor(19036268., device='cuda:0'), tensor(19762348., device='cuda:0'), tensor(19091290., device='cuda:0'), tensor(18557408., device='cuda:0'), tensor(18919264., device='cuda:0'), tensor(18388178., device='cuda:0'), tensor(18435854., device='cuda:0')]

Others: [{'iter_num': 9, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}]

Compressed training loss: [tensor(40894.2266, device='cuda:0'), tensor(40773., device='cuda:0'), tensor(40843.9023, device='cuda:0'), tensor(40873.5430, device='cuda:0'), tensor(40787.8945, device='cuda:0'), tensor(40908.7852, device='cuda:0'), tensor(40955.1094, device='cuda:0'), tensor(40668.2578, device='cuda:0'), tensor(40663.6562, device='cuda:0'), tensor(40809.1055, device='cuda:0')]

Training loss: 0

Prediction time: [datetime.timedelta(seconds=1, microseconds=78427), datetime.timedelta(seconds=1, microseconds=104317), datetime.timedelta(seconds=1, microseconds=88385), datetime.timedelta(seconds=1, microseconds=104316), datetime.timedelta(seconds=1, microseconds=129211), datetime.timedelta(seconds=1, microseconds=104316), datetime.timedelta(seconds=1, microseconds=101329), datetime.timedelta(seconds=1, microseconds=99337), datetime.timedelta(seconds=1, microseconds=80417), datetime.timedelta(seconds=1, microseconds=113279)]

Phi time: [datetime.timedelta(microseconds=236994), datetime.timedelta(microseconds=249939), datetime.timedelta(microseconds=253924), datetime.timedelta(microseconds=256911), datetime.timedelta(microseconds=236996), datetime.timedelta(microseconds=258903), datetime.timedelta(microseconds=252928), datetime.timedelta(microseconds=255915), datetime.timedelta(microseconds=253924), datetime.timedelta(microseconds=235999)]

