Precision: [tensor(0.8556, device='cuda:0'), tensor(0.8539, device='cuda:0'), tensor(0.8532, device='cuda:0'), tensor(0.8551, device='cuda:0'), tensor(0.8539, device='cuda:0'), tensor(0.8531, device='cuda:0'), tensor(0.8545, device='cuda:0'), tensor(0.8558, device='cuda:0'), tensor(0.8542, device='cuda:0'), tensor(0.8551, device='cuda:0')]

Output distance: [tensor(562.5187, device='cuda:0'), tensor(576.0775, device='cuda:0'), tensor(559.4014, device='cuda:0'), tensor(579.2205, device='cuda:0'), tensor(573.1243, device='cuda:0'), tensor(560.8616, device='cuda:0'), tensor(565.6470, device='cuda:0'), tensor(544.0953, device='cuda:0'), tensor(556.0590, device='cuda:0'), tensor(571.7530, device='cuda:0')]

Prediction loss: [tensor(604.7496, device='cuda:0'), tensor(630.7139, device='cuda:0'), tensor(594.6125, device='cuda:0'), tensor(616.1110, device='cuda:0'), tensor(619.3371, device='cuda:0'), tensor(608.5646, device='cuda:0'), tensor(618.6949, device='cuda:0'), tensor(583.8485, device='cuda:0'), tensor(596.5887, device='cuda:0'), tensor(620.2328, device='cuda:0')]

Others: [{'iter_num': 30, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}]

Compressed training loss: [tensor(8782034., device='cuda:0'), tensor(9009250., device='cuda:0'), tensor(8762790., device='cuda:0'), tensor(8799638., device='cuda:0'), tensor(8948614., device='cuda:0'), tensor(8929559., device='cuda:0'), tensor(8974078., device='cuda:0'), tensor(8608774., device='cuda:0'), tensor(8754563., device='cuda:0'), tensor(8931588., device='cuda:0')]

Training loss: 8877893.0

Prediction time: [datetime.timedelta(seconds=2, microseconds=42339), datetime.timedelta(seconds=2, microseconds=63250), datetime.timedelta(seconds=2, microseconds=59266), datetime.timedelta(seconds=2, microseconds=70221), datetime.timedelta(seconds=2, microseconds=58271), datetime.timedelta(seconds=2, microseconds=47315), datetime.timedelta(seconds=2, microseconds=62245), datetime.timedelta(microseconds=953954), datetime.timedelta(seconds=2, microseconds=63249), datetime.timedelta(seconds=2, microseconds=63250)]

Phi time: [datetime.timedelta(seconds=1, microseconds=591940), datetime.timedelta(seconds=1, microseconds=7571), datetime.timedelta(microseconds=968897), datetime.timedelta(microseconds=962142), datetime.timedelta(microseconds=961790), datetime.timedelta(microseconds=974528), datetime.timedelta(microseconds=969772), datetime.timedelta(microseconds=972077), datetime.timedelta(microseconds=971133), datetime.timedelta(microseconds=970970)]

