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

Output distance: [tensor(23577.5547, device='cuda:0'), tensor(23734.0020, device='cuda:0'), tensor(24275.2773, device='cuda:0'), tensor(23605.4336, device='cuda:0'), tensor(24166.1543, device='cuda:0'), tensor(23607.8711, device='cuda:0'), tensor(23687.4668, device='cuda:0'), tensor(24564.5605, device='cuda:0'), tensor(25723.4238, device='cuda:0'), tensor(23844.6602, device='cuda:0')]

Prediction loss: [tensor(22978.0762, device='cuda:0'), tensor(24220.1387, device='cuda:0'), tensor(24591.6113, device='cuda:0'), tensor(23079.7754, device='cuda:0'), tensor(24448.0820, device='cuda:0'), tensor(23364.1660, device='cuda:0'), tensor(24068.4844, device='cuda:0'), tensor(24886.2070, device='cuda:0'), tensor(26258.5352, device='cuda:0'), tensor(24091.9512, device='cuda:0')]

Others: [{'iter_num': 7, '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': 27, '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': 25, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 13, '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')}, {'iter_num': 30, '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')}]

Compressed training loss: [tensor(8689738., device='cuda:0'), tensor(8957624., device='cuda:0'), tensor(8939027., device='cuda:0'), tensor(8746543., device='cuda:0'), tensor(8908508., device='cuda:0'), tensor(8836594., device='cuda:0'), tensor(8965518., device='cuda:0'), tensor(8832743., device='cuda:0'), tensor(8897342., device='cuda:0'), tensor(8924687., device='cuda:0')]

Training loss: 8852438.0

Prediction time: [datetime.timedelta(microseconds=604437), datetime.timedelta(seconds=1, microseconds=186968), datetime.timedelta(seconds=1, microseconds=533497), datetime.timedelta(microseconds=719013), datetime.timedelta(seconds=1, microseconds=433908), datetime.timedelta(microseconds=619373), datetime.timedelta(microseconds=885246), datetime.timedelta(seconds=1, microseconds=665936), datetime.timedelta(seconds=1, microseconds=667923), datetime.timedelta(seconds=1, microseconds=260654)]

Phi time: [datetime.timedelta(seconds=1, microseconds=370724), datetime.timedelta(microseconds=870544), datetime.timedelta(microseconds=851080), datetime.timedelta(microseconds=846128), datetime.timedelta(microseconds=886570), datetime.timedelta(microseconds=874028), datetime.timedelta(microseconds=844635), datetime.timedelta(microseconds=847923), datetime.timedelta(microseconds=849785), datetime.timedelta(microseconds=849347)]

