Precision: [tensor(0.9982, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9997, device='cuda:0'), tensor(0.9992, device='cuda:0'), tensor(0.9992, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9983, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9985, device='cuda:0')]

Output distance: [tensor(171692.8281, device='cuda:0'), tensor(155648.2031, device='cuda:0'), tensor(145414.5938, device='cuda:0'), tensor(183731.9844, device='cuda:0'), tensor(159208.9531, device='cuda:0'), tensor(154486.2656, device='cuda:0'), tensor(201533.5625, device='cuda:0'), tensor(151591.9375, device='cuda:0'), tensor(147398.1250, device='cuda:0'), tensor(174036.2656, device='cuda:0')]

Prediction loss: [tensor(177963.7344, device='cuda:0'), tensor(140675.3750, device='cuda:0'), tensor(146620.0469, device='cuda:0'), tensor(147035.7656, device='cuda:0'), tensor(152230.8438, device='cuda:0'), tensor(157368.2656, device='cuda:0'), tensor(223591.7188, device='cuda:0'), tensor(144811.2812, device='cuda:0'), tensor(129920.1172, device='cuda:0'), tensor(170619.3438, 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(1.8876e+08, device='cuda:0'), tensor(1.9258e+08, device='cuda:0'), tensor(1.9470e+08, device='cuda:0'), tensor(1.8559e+08, device='cuda:0'), tensor(1.9646e+08, device='cuda:0'), tensor(1.9948e+08, device='cuda:0'), tensor(1.9329e+08, device='cuda:0'), tensor(1.9177e+08, device='cuda:0'), tensor(1.7673e+08, device='cuda:0'), tensor(1.8867e+08, device='cuda:0')]

Training loss: 190803008.0

Prediction time: [datetime.timedelta(microseconds=14107), datetime.timedelta(microseconds=11927), datetime.timedelta(microseconds=15576), datetime.timedelta(microseconds=11183), datetime.timedelta(microseconds=16185), datetime.timedelta(microseconds=2202), datetime.timedelta(microseconds=16857), datetime.timedelta(microseconds=15625), datetime.timedelta(microseconds=17145), datetime.timedelta(microseconds=16616)]

Phi time: [datetime.timedelta(seconds=1, microseconds=70135), datetime.timedelta(microseconds=552118), datetime.timedelta(microseconds=544243), datetime.timedelta(microseconds=550037), datetime.timedelta(microseconds=545765), datetime.timedelta(microseconds=546833), datetime.timedelta(microseconds=548750), datetime.timedelta(microseconds=536579), datetime.timedelta(microseconds=548800), datetime.timedelta(microseconds=548117)]

