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

Output distance: [tensor(140824.5781, device='cuda:0'), tensor(140559.3750, device='cuda:0'), tensor(140582.6250, device='cuda:0'), tensor(140156.0156, device='cuda:0'), tensor(140178.2188, device='cuda:0'), tensor(141667.3906, device='cuda:0'), tensor(140160.8750, device='cuda:0'), tensor(140122.2656, device='cuda:0'), tensor(140221.1875, device='cuda:0'), tensor(142030.5156, device='cuda:0')]

Prediction loss: [tensor(140225.1250, device='cuda:0'), tensor(135648.4688, device='cuda:0'), tensor(137018.6094, device='cuda:0'), tensor(137703.5938, device='cuda:0'), tensor(135563.1094, device='cuda:0'), tensor(135780.2500, device='cuda:0'), tensor(136268.6250, device='cuda:0'), tensor(138094.7812, device='cuda:0'), tensor(137871.2031, device='cuda:0'), tensor(135520.9688, 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(1.9424e+08, device='cuda:0'), tensor(1.9205e+08, device='cuda:0'), tensor(1.9345e+08, device='cuda:0'), tensor(1.9286e+08, device='cuda:0'), tensor(1.8971e+08, device='cuda:0'), tensor(1.9145e+08, device='cuda:0'), tensor(1.9148e+08, device='cuda:0'), tensor(1.9335e+08, device='cuda:0'), tensor(1.9181e+08, device='cuda:0'), tensor(1.9170e+08, device='cuda:0')]

Training loss: 192480400.0

Prediction time: [datetime.timedelta(microseconds=115513), datetime.timedelta(microseconds=121489), datetime.timedelta(microseconds=118503), datetime.timedelta(microseconds=118503), datetime.timedelta(microseconds=118499), datetime.timedelta(microseconds=117506), datetime.timedelta(microseconds=118502), datetime.timedelta(microseconds=120494), datetime.timedelta(microseconds=117505), datetime.timedelta(microseconds=118501)]

Phi time: [datetime.timedelta(seconds=1, microseconds=860213), datetime.timedelta(seconds=1, microseconds=267461), datetime.timedelta(seconds=1, microseconds=249121), datetime.timedelta(seconds=1, microseconds=299227), datetime.timedelta(seconds=1, microseconds=287219), datetime.timedelta(seconds=1, microseconds=284769), datetime.timedelta(seconds=1, microseconds=316794), datetime.timedelta(seconds=1, microseconds=289528), datetime.timedelta(seconds=1, microseconds=292676), datetime.timedelta(seconds=1, microseconds=326223)]

