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

Output distance: [tensor(23588.3867, device='cuda:0'), tensor(22768.7871, device='cuda:0'), tensor(22894.6426, device='cuda:0'), tensor(22906.6191, device='cuda:0'), tensor(23000., device='cuda:0'), tensor(23042.3457, device='cuda:0'), tensor(23055.4023, device='cuda:0'), tensor(23359.7383, device='cuda:0'), tensor(23145.0020, device='cuda:0'), tensor(23704.3145, device='cuda:0')]

Prediction loss: [tensor(23570.1094, device='cuda:0'), tensor(22215.0898, device='cuda:0'), tensor(23224.1777, device='cuda:0'), tensor(23675.6309, device='cuda:0'), tensor(23214.0430, device='cuda:0'), tensor(22972.0098, device='cuda:0'), tensor(23026.6895, device='cuda:0'), tensor(22831.6855, device='cuda:0'), tensor(22917.3438, device='cuda:0'), tensor(24125.2109, device='cuda:0')]

Others: [{'iter_num': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 15, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 17, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 19, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 21, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 21, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 25, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 23, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}]

Compressed training loss: [tensor(8870878., device='cuda:0'), tensor(8631144., device='cuda:0'), tensor(8894649., device='cuda:0'), tensor(8906611., device='cuda:0'), tensor(8785153., device='cuda:0'), tensor(8784719., device='cuda:0'), tensor(8769742., device='cuda:0'), tensor(8717165., device='cuda:0'), tensor(8716566., device='cuda:0'), tensor(8910224., device='cuda:0')]

Training loss: 8808121.0

Prediction time: [datetime.timedelta(seconds=2, microseconds=637812), datetime.timedelta(microseconds=730900), datetime.timedelta(seconds=1, microseconds=494660), datetime.timedelta(seconds=1, microseconds=652992), datetime.timedelta(seconds=1, microseconds=807336), datetime.timedelta(seconds=1, microseconds=969647), datetime.timedelta(seconds=1, microseconds=977615), datetime.timedelta(seconds=2, microseconds=274354), datetime.timedelta(seconds=2, microseconds=129967), datetime.timedelta(seconds=2, microseconds=659718)]

Phi time: [datetime.timedelta(seconds=1, microseconds=900514), datetime.timedelta(seconds=1, microseconds=279008), datetime.timedelta(seconds=1, microseconds=281246), datetime.timedelta(seconds=1, microseconds=293210), datetime.timedelta(seconds=1, microseconds=290189), datetime.timedelta(seconds=1, microseconds=287676), datetime.timedelta(seconds=1, microseconds=288995), datetime.timedelta(seconds=1, microseconds=294206), datetime.timedelta(seconds=1, microseconds=286252), datetime.timedelta(seconds=1, microseconds=284909)]

