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

Output distance: [tensor(23692.3125, device='cuda:0'), tensor(23777.3945, device='cuda:0'), tensor(23835.8789, device='cuda:0'), tensor(23739.0430, device='cuda:0'), tensor(23827.2852, device='cuda:0'), tensor(23682.7656, device='cuda:0'), tensor(23881.1777, device='cuda:0'), tensor(23782.3633, device='cuda:0'), tensor(23685.1660, device='cuda:0'), tensor(23673.9082, device='cuda:0')]

Prediction loss: [tensor(23775.4434, device='cuda:0'), tensor(23750.9980, device='cuda:0'), tensor(23071.9883, device='cuda:0'), tensor(24377.1699, device='cuda:0'), tensor(23980.5020, device='cuda:0'), tensor(23517.1152, device='cuda:0'), tensor(23113.9883, device='cuda:0'), tensor(23781.8281, device='cuda:0'), tensor(24768.7656, device='cuda:0'), tensor(24081.1621, 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': 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': 9, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}]

Compressed training loss: [tensor(8883316., device='cuda:0'), tensor(8863517., device='cuda:0'), tensor(8657729., device='cuda:0'), tensor(9030514., device='cuda:0'), tensor(8850253., device='cuda:0'), tensor(8830115., device='cuda:0'), tensor(8728547., device='cuda:0'), tensor(8774919., device='cuda:0'), tensor(9141811., device='cuda:0'), tensor(8891711., device='cuda:0')]

Training loss: 8857305.0

Prediction time: [datetime.timedelta(microseconds=617379), datetime.timedelta(microseconds=632321), datetime.timedelta(microseconds=707049), datetime.timedelta(microseconds=631322), datetime.timedelta(microseconds=636323), datetime.timedelta(microseconds=628332), datetime.timedelta(microseconds=723929), datetime.timedelta(microseconds=623354), datetime.timedelta(microseconds=636246), datetime.timedelta(microseconds=634260)]

Phi time: [datetime.timedelta(seconds=1, microseconds=380103), datetime.timedelta(microseconds=886817), datetime.timedelta(microseconds=867179), datetime.timedelta(microseconds=850423), datetime.timedelta(microseconds=853860), datetime.timedelta(microseconds=851103), datetime.timedelta(microseconds=854110), datetime.timedelta(microseconds=853762), datetime.timedelta(microseconds=854104), datetime.timedelta(microseconds=852808)]

