Precision: [tensor(0.9987, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9983, device='cuda:0'), tensor(0.9987, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9978, device='cuda:0'), tensor(0.9995, device='cuda:0')]

Output distance: [tensor(148190.3750, device='cuda:0'), tensor(155707.6562, device='cuda:0'), tensor(156939.4375, device='cuda:0'), tensor(150929.8906, device='cuda:0'), tensor(153737.5312, device='cuda:0'), tensor(166550.3594, device='cuda:0'), tensor(154633., device='cuda:0'), tensor(144600.8281, device='cuda:0'), tensor(151122.7656, device='cuda:0'), tensor(143919.8750, device='cuda:0')]

Prediction loss: [tensor(148436.1094, device='cuda:0'), tensor(156726.5156, device='cuda:0'), tensor(140008.4062, device='cuda:0'), tensor(127293.9297, device='cuda:0'), tensor(132343.9844, device='cuda:0'), tensor(142332.9375, device='cuda:0'), tensor(154165.4688, device='cuda:0'), tensor(132005.2188, device='cuda:0'), tensor(126337.1719, device='cuda:0'), tensor(139256.4531, 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(1.9676e+08, device='cuda:0'), tensor(1.9347e+08, device='cuda:0'), tensor(1.9022e+08, device='cuda:0'), tensor(1.8297e+08, device='cuda:0'), tensor(1.8601e+08, device='cuda:0'), tensor(1.8624e+08, device='cuda:0'), tensor(1.9155e+08, device='cuda:0'), tensor(1.8541e+08, device='cuda:0'), tensor(1.8185e+08, device='cuda:0'), tensor(1.8980e+08, device='cuda:0')]

Training loss: 190781184.0

Prediction time: [datetime.timedelta(microseconds=19962), datetime.timedelta(microseconds=23900), datetime.timedelta(microseconds=20915), datetime.timedelta(microseconds=22903), datetime.timedelta(microseconds=21954), datetime.timedelta(microseconds=20913), datetime.timedelta(microseconds=23899), datetime.timedelta(microseconds=22903), datetime.timedelta(microseconds=22907), datetime.timedelta(microseconds=23898)]

Phi time: [datetime.timedelta(seconds=1, microseconds=272793), datetime.timedelta(microseconds=657026), datetime.timedelta(microseconds=657060), datetime.timedelta(microseconds=654623), datetime.timedelta(microseconds=656858), datetime.timedelta(microseconds=651032), datetime.timedelta(microseconds=654974), datetime.timedelta(microseconds=654738), datetime.timedelta(microseconds=655433), datetime.timedelta(microseconds=654385)]

