Precision: [tensor(0.3790, device='cuda:0'), tensor(0.3776, device='cuda:0'), tensor(0.3787, device='cuda:0'), tensor(0.3826, device='cuda:0'), tensor(0.3769, device='cuda:0'), tensor(0.3700, device='cuda:0'), tensor(0.3738, device='cuda:0'), tensor(0.3730, device='cuda:0'), tensor(0.3745, device='cuda:0'), tensor(0.3775, device='cuda:0')]
Output distance: [tensor(19.7515, device='cuda:0'), tensor(19.7600, device='cuda:0'), tensor(19.7530, device='cuda:0'), tensor(19.7300, device='cuda:0'), tensor(19.7642, device='cuda:0'), tensor(19.8053, device='cuda:0'), tensor(19.7826, device='cuda:0'), tensor(19.7872, device='cuda:0'), tensor(19.7784, device='cuda:0'), tensor(19.7606, device='cuda:0')]
Prediction loss: [tensor(105.3552, device='cuda:0'), tensor(105.2241, device='cuda:0'), tensor(105.6910, device='cuda:0'), tensor(105.3494, device='cuda:0'), tensor(105.0746, device='cuda:0'), tensor(104.5161, device='cuda:0'), tensor(104.4160, device='cuda:0'), tensor(105.0432, device='cuda:0'), tensor(105.4389, device='cuda:0'), tensor(105.7546, device='cuda:0')]
Others: [{'iter_num': 9, 'num_positive': tensor(19848, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(19848, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(19848, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(19848, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(19848, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(19848, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(19848, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(19848, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(19848, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(19848, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}]
Compressed training loss: [tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0')]
Training loss: 0
Prediction time: [datetime.timedelta(seconds=2, microseconds=916837), datetime.timedelta(seconds=2, microseconds=866646), datetime.timedelta(seconds=2, microseconds=883407), datetime.timedelta(seconds=2, microseconds=899991), datetime.timedelta(seconds=2, microseconds=900011), datetime.timedelta(seconds=2, microseconds=749825), datetime.timedelta(seconds=2, microseconds=749500), datetime.timedelta(seconds=2, microseconds=899109), datetime.timedelta(seconds=2, microseconds=756426), datetime.timedelta(seconds=2, microseconds=901219)]
Phi time: [datetime.timedelta(seconds=98, microseconds=715665), datetime.timedelta(seconds=98, microseconds=749658), datetime.timedelta(seconds=98, microseconds=815819), datetime.timedelta(seconds=98, microseconds=799479), datetime.timedelta(seconds=98, microseconds=949530), datetime.timedelta(seconds=99, microseconds=101382), datetime.timedelta(seconds=98, microseconds=700423), datetime.timedelta(seconds=98, microseconds=778990), datetime.timedelta(seconds=98, microseconds=858828), datetime.timedelta(seconds=99, microseconds=33010)]
