Special test with strict convergence condition

Precision: [tensor(0.5498, device='cuda:0'), tensor(0.5519, device='cuda:0'), tensor(0.5474, device='cuda:0'), tensor(0.5507, device='cuda:0'), tensor(0.5498, device='cuda:0'), tensor(0.5487, device='cuda:0'), tensor(0.5543, device='cuda:0'), tensor(0.5533, device='cuda:0'), tensor(0.5489, device='cuda:0'), tensor(0.5497, device='cuda:0')]

Output distance: [tensor(5.0071, device='cuda:0'), tensor(4.9950, device='cuda:0'), tensor(5.0218, device='cuda:0'), tensor(5.0018, device='cuda:0'), tensor(5.0071, device='cuda:0'), tensor(5.0139, device='cuda:0'), tensor(4.9803, device='cuda:0'), tensor(4.9861, device='cuda:0'), tensor(5.0129, device='cuda:0'), tensor(5.0081, device='cuda:0')]

Prediction loss: [tensor(19999834., device='cuda:0'), tensor(18532092., device='cuda:0'), tensor(18162334., device='cuda:0'), tensor(19032372., device='cuda:0'), tensor(18753160., device='cuda:0'), tensor(18000796., device='cuda:0'), tensor(19423962., device='cuda:0'), tensor(19211692., device='cuda:0'), tensor(19093528., device='cuda:0'), tensor(19231664., device='cuda:0')]

Others: [{'iter_num': 7, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 7, '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': 9, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}]

Compressed training loss: [tensor(40673.3906, device='cuda:0'), tensor(40793.9570, device='cuda:0'), tensor(40999.0078, device='cuda:0'), tensor(40933.7812, device='cuda:0'), tensor(40796.3008, device='cuda:0'), tensor(41087.3984, device='cuda:0'), tensor(40869.6250, device='cuda:0'), tensor(41048.4609, device='cuda:0'), tensor(40942.5898, device='cuda:0'), tensor(40780.6562, device='cuda:0')]

Training loss: 0

Prediction time: [datetime.timedelta(seconds=8, microseconds=876354), datetime.timedelta(seconds=8, microseconds=678195), datetime.timedelta(seconds=8, microseconds=738938), datetime.timedelta(seconds=8, microseconds=750887), datetime.timedelta(seconds=11, microseconds=44161), datetime.timedelta(seconds=10, microseconds=992381), datetime.timedelta(seconds=11, microseconds=72043), datetime.timedelta(seconds=8, microseconds=910211), datetime.timedelta(seconds=8, microseconds=623427), datetime.timedelta(seconds=8, microseconds=755867)]

Phi time: [datetime.timedelta(microseconds=360471), datetime.timedelta(microseconds=385366), datetime.timedelta(microseconds=357484), datetime.timedelta(microseconds=366446), datetime.timedelta(microseconds=317653), datetime.timedelta(microseconds=389349), datetime.timedelta(microseconds=375407), datetime.timedelta(microseconds=400303), datetime.timedelta(microseconds=417231), datetime.timedelta(microseconds=347526)]

