Precision: [tensor(0.3582, device='cuda:0'), tensor(0.3628, device='cuda:0'), tensor(0.3621, device='cuda:0'), tensor(0.3630, device='cuda:0'), tensor(0.3628, device='cuda:0'), tensor(0.3648, device='cuda:0'), tensor(0.3597, device='cuda:0'), tensor(0.3616, device='cuda:0'), tensor(0.3629, device='cuda:0'), tensor(0.3594, device='cuda:0')]
Output distance: [tensor(20.4438, device='cuda:0'), tensor(20.3975, device='cuda:0'), tensor(20.4045, device='cuda:0'), tensor(20.3954, device='cuda:0'), tensor(20.3969, device='cuda:0'), tensor(20.3773, device='cuda:0'), tensor(20.4281, device='cuda:0'), tensor(20.4093, device='cuda:0'), tensor(20.3966, device='cuda:0'), tensor(20.4317, device='cuda:0')]
Prediction loss: [tensor(101.5980, device='cuda:0'), tensor(102.5001, device='cuda:0'), tensor(101.1810, device='cuda:0'), tensor(101.1644, device='cuda:0'), tensor(102.3716, device='cuda:0'), tensor(101.4901, device='cuda:0'), tensor(101.3093, device='cuda:0'), tensor(101.1037, device='cuda:0'), tensor(101.7230, device='cuda:0'), tensor(102.0262, device='cuda:0')]
Others: [{'iter_num': 30, 'num_positive': tensor(33080, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(33080, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(33080, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(33080, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(33080, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(33080, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(33080, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(33080, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(33080, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(33080, 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=4, microseconds=584607), datetime.timedelta(seconds=4, microseconds=601243), datetime.timedelta(seconds=4, microseconds=599747), datetime.timedelta(seconds=4, microseconds=600022), datetime.timedelta(seconds=4, microseconds=616869), datetime.timedelta(seconds=4, microseconds=633602), datetime.timedelta(seconds=4, microseconds=592021), datetime.timedelta(seconds=4, microseconds=600025), datetime.timedelta(seconds=4, microseconds=616855), datetime.timedelta(seconds=4, microseconds=594466)]
Phi time: [datetime.timedelta(seconds=98, microseconds=917150), datetime.timedelta(seconds=98, microseconds=649213), datetime.timedelta(seconds=98, microseconds=732833), datetime.timedelta(seconds=98, microseconds=849694), datetime.timedelta(seconds=98, microseconds=965977), datetime.timedelta(seconds=99, microseconds=101301), datetime.timedelta(seconds=98, microseconds=901892), datetime.timedelta(seconds=98, microseconds=802176), datetime.timedelta(seconds=99, microseconds=183023), datetime.timedelta(seconds=98, microseconds=889546)]
