Precision: [tensor(0.3953, device='cuda:0'), tensor(0.3943, device='cuda:0'), tensor(0.3934, device='cuda:0'), tensor(0.3934, device='cuda:0'), tensor(0.3908, device='cuda:0'), tensor(0.3947, device='cuda:0'), tensor(0.3955, device='cuda:0'), tensor(0.3935, device='cuda:0'), tensor(0.3920, device='cuda:0'), tensor(0.3961, device='cuda:0')]

Output distance: [tensor(20.0723, device='cuda:0'), tensor(20.0825, device='cuda:0'), tensor(20.0913, device='cuda:0'), tensor(20.0910, device='cuda:0'), tensor(20.1170, device='cuda:0'), tensor(20.0780, device='cuda:0'), tensor(20.0707, device='cuda:0'), tensor(20.0901, device='cuda:0'), tensor(20.1049, device='cuda:0'), tensor(20.0647, device='cuda:0')]

Prediction loss: [tensor(103.0026, device='cuda:0'), tensor(102.4917, device='cuda:0'), tensor(102.1462, device='cuda:0'), tensor(101.9743, device='cuda:0'), tensor(101.8281, device='cuda:0'), tensor(102.8524, device='cuda:0'), tensor(102.0946, device='cuda:0'), tensor(102.4320, device='cuda:0'), tensor(102.2156, device='cuda:0'), tensor(102.4106, device='cuda:0')]

Others: [{'iter_num': 60, 'num_positive': tensor(33080, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 60, 'num_positive': tensor(33080, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 60, 'num_positive': tensor(33080, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 60, 'num_positive': tensor(33080, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 60, 'num_positive': tensor(33080, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 60, 'num_positive': tensor(33080, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 60, 'num_positive': tensor(33080, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 60, 'num_positive': tensor(33080, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 60, 'num_positive': tensor(33080, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 60, 'num_positive': tensor(33080, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}]

Compressed training loss: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0]

Training loss: 0

Prediction time: [datetime.timedelta(seconds=10, microseconds=851972), datetime.timedelta(seconds=10, microseconds=835045), datetime.timedelta(seconds=10, microseconds=874877), datetime.timedelta(seconds=10, microseconds=849983), datetime.timedelta(seconds=10, microseconds=876867), datetime.timedelta(seconds=10, microseconds=844009), datetime.timedelta(seconds=10, microseconds=874878), datetime.timedelta(seconds=10, microseconds=862928), datetime.timedelta(seconds=10, microseconds=870896), datetime.timedelta(seconds=10, microseconds=899772)]

Phi time: [datetime.timedelta(seconds=6, microseconds=772939), datetime.timedelta(seconds=6, microseconds=878015), datetime.timedelta(seconds=6, microseconds=860331), datetime.timedelta(seconds=6, microseconds=866061), datetime.timedelta(seconds=6, microseconds=896477), datetime.timedelta(seconds=6, microseconds=853699), datetime.timedelta(seconds=6, microseconds=858165), datetime.timedelta(seconds=6, microseconds=873584), datetime.timedelta(seconds=6, microseconds=851929), datetime.timedelta(seconds=6, microseconds=854721)]

