Special test with strict convergence condition

Precision: [tensor(0.5514, device='cuda:0'), tensor(0.5495, device='cuda:0'), tensor(0.5512, device='cuda:0'), tensor(0.5543, device='cuda:0'), tensor(0.5506, device='cuda:0'), tensor(0.5490, device='cuda:0'), tensor(0.5478, device='cuda:0'), tensor(0.5497, device='cuda:0'), tensor(0.5530, device='cuda:0'), tensor(0.5494, device='cuda:0')]

Output distance: [tensor(4.9976, device='cuda:0'), tensor(5.0092, device='cuda:0'), tensor(4.9992, device='cuda:0'), tensor(4.9803, device='cuda:0'), tensor(5.0024, device='cuda:0'), tensor(5.0123, device='cuda:0'), tensor(5.0192, device='cuda:0'), tensor(5.0081, device='cuda:0'), tensor(4.9882, device='cuda:0'), tensor(5.0097, device='cuda:0')]

Prediction loss: [tensor(18981878., device='cuda:0'), tensor(17610314., device='cuda:0'), tensor(16514801., device='cuda:0'), tensor(16102829., device='cuda:0'), tensor(19696594., device='cuda:0'), tensor(17784476., device='cuda:0'), tensor(19777190., device='cuda:0'), tensor(18218418., device='cuda:0'), tensor(18215352., device='cuda:0'), tensor(19693548., device='cuda:0')]

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

Compressed training loss: [tensor(40855.3125, device='cuda:0'), tensor(40812.3086, device='cuda:0'), tensor(40690.9727, device='cuda:0'), tensor(40799.0078, device='cuda:0'), tensor(40902.6016, device='cuda:0'), tensor(40903.6172, device='cuda:0'), tensor(40992.9531, device='cuda:0'), tensor(40956.5352, device='cuda:0'), tensor(40596.8125, device='cuda:0'), tensor(40706.2227, device='cuda:0')]

Training loss: 0

Prediction time: [datetime.timedelta(seconds=1, microseconds=90376), datetime.timedelta(seconds=1, microseconds=111287), datetime.timedelta(seconds=1, microseconds=75438), datetime.timedelta(seconds=1, microseconds=89380), datetime.timedelta(seconds=1, microseconds=100333), datetime.timedelta(seconds=1, microseconds=106307), datetime.timedelta(seconds=1, microseconds=61498), datetime.timedelta(seconds=1, microseconds=67473), datetime.timedelta(seconds=1, microseconds=101330), datetime.timedelta(seconds=1, microseconds=57516)]

Phi time: [datetime.timedelta(microseconds=231020), datetime.timedelta(microseconds=252927), datetime.timedelta(microseconds=256912), datetime.timedelta(microseconds=230024), datetime.timedelta(microseconds=236000), datetime.timedelta(microseconds=232017), datetime.timedelta(microseconds=255914), datetime.timedelta(microseconds=231019), datetime.timedelta(microseconds=256910), datetime.timedelta(microseconds=250936)]

