Precision: [tensor(0.9995, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9998, device='cuda:0'), tensor(0.9998, device='cuda:0'), tensor(0.9997, device='cuda:0'), tensor(0.9997, device='cuda:0'), tensor(1., device='cuda:0'), tensor(0.9998, device='cuda:0')]

Output distance: [tensor(145332.3750, device='cuda:0'), tensor(145722.0625, device='cuda:0'), tensor(144014.7344, device='cuda:0'), tensor(146072.9375, device='cuda:0'), tensor(153344.9844, device='cuda:0'), tensor(151042.4844, device='cuda:0'), tensor(155206.4219, device='cuda:0'), tensor(144211.2031, device='cuda:0'), tensor(147096.3906, device='cuda:0'), tensor(143567.2344, device='cuda:0')]

Prediction loss: [tensor(142773.0469, device='cuda:0'), tensor(141550.5469, device='cuda:0'), tensor(144291.1719, device='cuda:0'), tensor(140995.3750, device='cuda:0'), tensor(131545.9844, device='cuda:0'), tensor(137331.9531, device='cuda:0'), tensor(161475.8281, device='cuda:0'), tensor(136430.4688, device='cuda:0'), tensor(142766.8438, device='cuda:0'), tensor(146134.4375, device='cuda:0')]

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

Compressed training loss: [tensor(1.9147e+08, device='cuda:0'), tensor(1.9335e+08, device='cuda:0'), tensor(1.9028e+08, device='cuda:0'), tensor(1.9540e+08, device='cuda:0'), tensor(1.8874e+08, device='cuda:0'), tensor(1.8429e+08, device='cuda:0'), tensor(1.9779e+08, device='cuda:0'), tensor(1.8696e+08, device='cuda:0'), tensor(1.9512e+08, device='cuda:0'), tensor(1.9848e+08, device='cuda:0')]

Training loss: 191565824.0

Prediction time: [datetime.timedelta(microseconds=37840), datetime.timedelta(microseconds=37839), datetime.timedelta(microseconds=42818), datetime.timedelta(microseconds=35848), datetime.timedelta(microseconds=41827), datetime.timedelta(microseconds=38835), datetime.timedelta(microseconds=38837), datetime.timedelta(microseconds=38838), datetime.timedelta(microseconds=41825), datetime.timedelta(microseconds=38835)]

Phi time: [datetime.timedelta(seconds=1, microseconds=334144), datetime.timedelta(microseconds=732041), datetime.timedelta(microseconds=721172), datetime.timedelta(microseconds=728293), datetime.timedelta(microseconds=728408), datetime.timedelta(microseconds=727054), datetime.timedelta(microseconds=734992), datetime.timedelta(microseconds=730768), datetime.timedelta(microseconds=724576), datetime.timedelta(microseconds=729940)]

