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

Output distance: [tensor(23206.3418, device='cuda:0'), tensor(23168.1543, device='cuda:0'), tensor(23048.2031, device='cuda:0'), tensor(23040.1406, device='cuda:0'), tensor(23030.0586, device='cuda:0'), tensor(23008.1973, device='cuda:0'), tensor(23124.1895, device='cuda:0'), tensor(23030.9785, device='cuda:0'), tensor(23092.0430, device='cuda:0'), tensor(23038.8848, device='cuda:0')]

Prediction loss: [tensor(22999.8262, device='cuda:0'), tensor(24046.4746, device='cuda:0'), tensor(22422.7090, device='cuda:0'), tensor(22713.8105, device='cuda:0'), tensor(22694.3086, device='cuda:0'), tensor(22348.2656, device='cuda:0'), tensor(24001.7324, device='cuda:0'), tensor(21871.0098, device='cuda:0'), tensor(21364.2500, device='cuda:0'), tensor(23685.4336, device='cuda:0')]

Others: [{'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')}, {'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')}, {'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': 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')}]

Compressed training loss: [tensor(8791503., device='cuda:0'), tensor(9074346., device='cuda:0'), tensor(8643534., device='cuda:0'), tensor(8861914., device='cuda:0'), tensor(8839644., device='cuda:0'), tensor(8725618., device='cuda:0'), tensor(9092095., device='cuda:0'), tensor(8602808., device='cuda:0'), tensor(8435630., device='cuda:0'), tensor(8903085., device='cuda:0')]

Training loss: 8856726.0

Prediction time: [datetime.timedelta(microseconds=581534), datetime.timedelta(microseconds=629331), datetime.timedelta(microseconds=657220), datetime.timedelta(microseconds=615391), datetime.timedelta(microseconds=607425), datetime.timedelta(microseconds=673144), datetime.timedelta(microseconds=593483), datetime.timedelta(microseconds=652224), datetime.timedelta(microseconds=658209), datetime.timedelta(microseconds=590495)]

Phi time: [datetime.timedelta(seconds=1, microseconds=378295), datetime.timedelta(microseconds=859063), datetime.timedelta(microseconds=781317), datetime.timedelta(microseconds=776365), datetime.timedelta(microseconds=783177), datetime.timedelta(microseconds=786028), datetime.timedelta(microseconds=789792), datetime.timedelta(microseconds=775917), datetime.timedelta(microseconds=784522), datetime.timedelta(microseconds=783757)]

