Precision: [tensor(0.4991, device='cuda:0'), tensor(0.4944, device='cuda:0'), tensor(0.4844, device='cuda:0'), tensor(0.4915, device='cuda:0'), tensor(0.4967, device='cuda:0'), tensor(0.4943, device='cuda:0'), tensor(0.4788, device='cuda:0'), tensor(0.4731, device='cuda:0'), tensor(0.4905, device='cuda:0'), tensor(0.5024, device='cuda:0')]
Output distance: [tensor(19.0272, device='cuda:0'), tensor(19.0366, device='cuda:0'), tensor(19.0565, device='cuda:0'), tensor(19.0423, device='cuda:0'), tensor(19.0320, device='cuda:0'), tensor(19.0369, device='cuda:0'), tensor(19.0677, device='cuda:0'), tensor(19.0792, device='cuda:0'), tensor(19.0444, device='cuda:0'), tensor(19.0206, device='cuda:0')]
Prediction loss: [tensor(108.5304, device='cuda:0'), tensor(109.3523, device='cuda:0'), tensor(108.8918, device='cuda:0'), tensor(108.3649, device='cuda:0'), tensor(109.5235, device='cuda:0'), tensor(109.2075, device='cuda:0'), tensor(109.0974, device='cuda:0'), tensor(108.2891, device='cuda:0'), tensor(107.9067, device='cuda:0'), tensor(109.3742, device='cuda:0')]
Others: [{'iter_num': 5, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(6616, 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=10, microseconds=294265), datetime.timedelta(seconds=10, microseconds=293335), datetime.timedelta(seconds=10, microseconds=171394), datetime.timedelta(seconds=10, microseconds=173699), datetime.timedelta(seconds=10, microseconds=289265), datetime.timedelta(seconds=10, microseconds=318911), datetime.timedelta(seconds=10, microseconds=302813), datetime.timedelta(seconds=10, microseconds=247393), datetime.timedelta(seconds=10, microseconds=205946), datetime.timedelta(seconds=10, microseconds=281092)]
Phi time: [datetime.timedelta(seconds=97, microseconds=312516), datetime.timedelta(seconds=97, microseconds=454127), datetime.timedelta(seconds=97, microseconds=344741), datetime.timedelta(seconds=99, microseconds=385041), datetime.timedelta(seconds=97, microseconds=504926), datetime.timedelta(seconds=97, microseconds=384663), datetime.timedelta(seconds=97, microseconds=375869), datetime.timedelta(seconds=97, microseconds=402411), datetime.timedelta(seconds=97, microseconds=488123), datetime.timedelta(seconds=97, microseconds=481179)]
