Precision: [tensor(0.4531, device='cuda:0'), tensor(0.4497, device='cuda:0'), tensor(0.4505, device='cuda:0'), tensor(0.4569, device='cuda:0'), tensor(0.4540, device='cuda:0'), tensor(0.4630, device='cuda:0'), tensor(0.4553, device='cuda:0'), tensor(0.4522, device='cuda:0'), tensor(0.4599, device='cuda:0'), tensor(0.4485, device='cuda:0')]
Output distance: [tensor(19.2644, device='cuda:0'), tensor(19.2807, device='cuda:0'), tensor(19.2777, device='cuda:0'), tensor(19.2441, device='cuda:0'), tensor(19.2600, device='cuda:0'), tensor(19.2133, device='cuda:0'), tensor(19.2523, device='cuda:0'), tensor(19.2681, device='cuda:0'), tensor(19.2294, device='cuda:0'), tensor(19.2879, device='cuda:0')]
Prediction loss: [tensor(104.1889, device='cuda:0'), tensor(103.8668, device='cuda:0'), tensor(103.8151, device='cuda:0'), tensor(104.5409, device='cuda:0'), tensor(104.3981, device='cuda:0'), tensor(104.2875, device='cuda:0'), tensor(104.5567, device='cuda:0'), tensor(104.2227, device='cuda:0'), tensor(104.6389, device='cuda:0'), tensor(104.4946, device='cuda:0')]
Others: [{'iter_num': 9, 'num_positive': tensor(16845, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(16801, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(16851, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(16795, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(16854, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(16799, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(16783, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(16786, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(16832, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(16849, 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=899603), datetime.timedelta(seconds=2, microseconds=766482), datetime.timedelta(seconds=2, microseconds=902105), datetime.timedelta(seconds=2, microseconds=799415), datetime.timedelta(seconds=2, microseconds=899710), datetime.timedelta(seconds=2, microseconds=899793), datetime.timedelta(seconds=2, microseconds=883081), datetime.timedelta(seconds=2, microseconds=900367), datetime.timedelta(seconds=2, microseconds=902457), datetime.timedelta(seconds=2, microseconds=917828)]
Phi time: [datetime.timedelta(seconds=99, microseconds=449280), datetime.timedelta(seconds=99, microseconds=453741), datetime.timedelta(seconds=99, microseconds=536509), datetime.timedelta(seconds=99, microseconds=506119), datetime.timedelta(seconds=99, microseconds=499382), datetime.timedelta(seconds=99, microseconds=349519), datetime.timedelta(seconds=99, microseconds=382770), datetime.timedelta(seconds=99, microseconds=533614), datetime.timedelta(seconds=99, microseconds=585791), datetime.timedelta(seconds=99, microseconds=434888)]
