Precision: [tensor(1., device='cuda:0'), tensor(1., device='cuda:0'), tensor(0.9998, device='cuda:0'), tensor(1., device='cuda:0'), tensor(0.9998, device='cuda:0'), tensor(1., device='cuda:0'), tensor(1., device='cuda:0'), tensor(1., device='cuda:0'), tensor(0.9998, device='cuda:0'), tensor(0.9998, device='cuda:0')]

Output distance: [tensor(39238.2305, device='cuda:0'), tensor(38041.4922, device='cuda:0'), tensor(39078.8359, device='cuda:0'), tensor(49127.0703, device='cuda:0'), tensor(42973.0039, device='cuda:0'), tensor(38949.1758, device='cuda:0'), tensor(38415.5117, device='cuda:0'), tensor(44698.1602, device='cuda:0'), tensor(38736.8555, device='cuda:0'), tensor(40922.7695, device='cuda:0')]

Prediction loss: [tensor(39024.3672, device='cuda:0'), tensor(34916.1211, device='cuda:0'), tensor(39832.0781, device='cuda:0'), tensor(50637.2266, device='cuda:0'), tensor(42421.3008, device='cuda:0'), tensor(36904.6289, device='cuda:0'), tensor(36760.3047, device='cuda:0'), tensor(46407.7422, device='cuda:0'), tensor(37923.5312, device='cuda:0'), tensor(42472.9531, device='cuda:0')]

Others: [{'iter_num': 29, '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': 27, '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': 23, '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': 30, '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': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}]

Compressed training loss: [tensor(3600395.5000, device='cuda:0'), tensor(3363541.7500, device='cuda:0'), tensor(3686777.7500, device='cuda:0'), tensor(3646519.5000, device='cuda:0'), tensor(3476553.7500, device='cuda:0'), tensor(3253369.5000, device='cuda:0'), tensor(3464448.7500, device='cuda:0'), tensor(3671478., device='cuda:0'), tensor(3536890.5000, device='cuda:0'), tensor(3680003.7500, device='cuda:0')]

Training loss: 3598350.0

Prediction time: [datetime.timedelta(seconds=1, microseconds=356245), datetime.timedelta(microseconds=597466), datetime.timedelta(seconds=1, microseconds=318408), datetime.timedelta(seconds=1, microseconds=425953), datetime.timedelta(seconds=1, microseconds=417985), datetime.timedelta(seconds=1, microseconds=168044), datetime.timedelta(microseconds=875287), datetime.timedelta(seconds=1, microseconds=415995), datetime.timedelta(microseconds=566597), datetime.timedelta(seconds=1, microseconds=413008)]

Phi time: [datetime.timedelta(seconds=1, microseconds=316055), datetime.timedelta(microseconds=811084), datetime.timedelta(microseconds=730364), datetime.timedelta(microseconds=725921), datetime.timedelta(microseconds=732894), datetime.timedelta(microseconds=730710), datetime.timedelta(microseconds=726917), datetime.timedelta(microseconds=732890), datetime.timedelta(microseconds=722010), datetime.timedelta(microseconds=723172)]

