Precision: [tensor(0.9995, device='cuda:0'), tensor(0.9988, device='cuda:0'), tensor(0.9988, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9990, device='cuda:0'), tensor(0.9990, device='cuda:0'), tensor(0.9992, device='cuda:0'), tensor(0.9992, device='cuda:0'), tensor(0.9993, device='cuda:0')]

Output distance: [tensor(140306.7500, device='cuda:0'), tensor(140975.5469, device='cuda:0'), tensor(143483.9688, device='cuda:0'), tensor(139995.7500, device='cuda:0'), tensor(146429.3281, device='cuda:0'), tensor(141355.9375, device='cuda:0'), tensor(139873., device='cuda:0'), tensor(142017.2500, device='cuda:0'), tensor(139994.9062, device='cuda:0'), tensor(140270.8281, device='cuda:0')]

Prediction loss: [tensor(135550.3750, device='cuda:0'), tensor(142718.8125, device='cuda:0'), tensor(144310.4531, device='cuda:0'), tensor(132716.4531, device='cuda:0'), tensor(136277.5156, device='cuda:0'), tensor(143771.4062, device='cuda:0'), tensor(130941.5547, device='cuda:0'), tensor(129690.0703, device='cuda:0'), tensor(142873.4688, device='cuda:0'), tensor(141760.5156, device='cuda:0')]

Others: [{'iter_num': 9, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 13, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}]

Compressed training loss: [tensor(1.9396e+08, device='cuda:0'), tensor(1.9677e+08, device='cuda:0'), tensor(1.9541e+08, device='cuda:0'), tensor(1.9249e+08, device='cuda:0'), tensor(1.9116e+08, device='cuda:0'), tensor(1.9924e+08, device='cuda:0'), tensor(1.9007e+08, device='cuda:0'), tensor(1.8967e+08, device='cuda:0'), tensor(1.9654e+08, device='cuda:0'), tensor(1.9804e+08, device='cuda:0')]

Training loss: 192738560.0

Prediction time: [datetime.timedelta(microseconds=535727), datetime.timedelta(microseconds=616434), datetime.timedelta(microseconds=615391), datetime.timedelta(microseconds=615394), datetime.timedelta(microseconds=670162), datetime.timedelta(microseconds=557635), datetime.timedelta(microseconds=616388), datetime.timedelta(microseconds=612402), datetime.timedelta(microseconds=564605), datetime.timedelta(microseconds=559629)]

Phi time: [datetime.timedelta(seconds=1, microseconds=338719), datetime.timedelta(microseconds=803682), datetime.timedelta(microseconds=726230), datetime.timedelta(microseconds=726902), datetime.timedelta(microseconds=726478), datetime.timedelta(microseconds=732010), datetime.timedelta(microseconds=727924), datetime.timedelta(microseconds=730911), datetime.timedelta(microseconds=731748), datetime.timedelta(microseconds=732006)]

