Precision: [tensor(0.4317, device='cuda:0'), tensor(0.4376, device='cuda:0'), tensor(0.4304, device='cuda:0'), tensor(0.4305, device='cuda:0'), tensor(0.4349, device='cuda:0'), tensor(0.4282, device='cuda:0'), tensor(0.4355, device='cuda:0'), tensor(0.4307, device='cuda:0'), tensor(0.4384, device='cuda:0'), tensor(0.4315, device='cuda:0')]
Output distance: [tensor(19.4350, device='cuda:0'), tensor(19.3996, device='cuda:0'), tensor(19.4429, device='cuda:0'), tensor(19.4426, device='cuda:0'), tensor(19.4163, device='cuda:0'), tensor(19.4565, device='cuda:0'), tensor(19.4126, device='cuda:0'), tensor(19.4411, device='cuda:0'), tensor(19.3948, device='cuda:0'), tensor(19.4365, device='cuda:0')]
Prediction loss: [tensor(104.1839, device='cuda:0'), tensor(104.3214, device='cuda:0'), tensor(104.5809, device='cuda:0'), tensor(104.5923, device='cuda:0'), tensor(104.0535, device='cuda:0'), tensor(104.4720, device='cuda:0'), tensor(104.5881, device='cuda:0'), tensor(104.9832, device='cuda:0'), tensor(104.5233, device='cuda:0'), tensor(104.9876, device='cuda:0')]
Others: [{'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': 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': 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': 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')}]
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=13, microseconds=803861), datetime.timedelta(seconds=13, microseconds=715418), datetime.timedelta(seconds=13, microseconds=720379), datetime.timedelta(seconds=17, microseconds=124915), datetime.timedelta(seconds=14, microseconds=15561), datetime.timedelta(seconds=13, microseconds=898361), datetime.timedelta(seconds=17, microseconds=74385), datetime.timedelta(seconds=13, microseconds=801306), datetime.timedelta(seconds=13, microseconds=734201), datetime.timedelta(seconds=13, microseconds=703039)]
Phi time: [datetime.timedelta(seconds=97, microseconds=710279), datetime.timedelta(seconds=97, microseconds=851887), datetime.timedelta(seconds=97, microseconds=280809), datetime.timedelta(seconds=97, microseconds=354368), datetime.timedelta(seconds=97, microseconds=551031), datetime.timedelta(seconds=97, microseconds=473203), datetime.timedelta(seconds=97, microseconds=580883), datetime.timedelta(seconds=97, microseconds=627822), datetime.timedelta(seconds=97, microseconds=484758), datetime.timedelta(seconds=97, microseconds=437810)]
