Precision: [tensor(0.9997, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9992, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9990, device='cuda:0'), tensor(0.9997, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9992, device='cuda:0'), tensor(0.9992, device='cuda:0'), tensor(0.9997, device='cuda:0')]

Output distance: [tensor(140126.8906, device='cuda:0'), tensor(142768.3750, device='cuda:0'), tensor(139835.5469, device='cuda:0'), tensor(143753.7969, device='cuda:0'), tensor(141206.3750, device='cuda:0'), tensor(140846.9531, device='cuda:0'), tensor(144056.4219, device='cuda:0'), tensor(143536.9531, device='cuda:0'), tensor(139622.7031, device='cuda:0'), tensor(140152.1875, device='cuda:0')]

Prediction loss: [tensor(140672.0156, device='cuda:0'), tensor(136057.5312, device='cuda:0'), tensor(146319.5938, device='cuda:0'), tensor(125874.1641, device='cuda:0'), tensor(130298.7188, device='cuda:0'), tensor(124080.7031, device='cuda:0'), tensor(119436.6172, device='cuda:0'), tensor(133411.5000, device='cuda:0'), tensor(133808., device='cuda:0'), tensor(133969.1875, device='cuda:0')]

Others: [{'iter_num': 11, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 13, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 15, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 15, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 13, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 13, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}]

Compressed training loss: [tensor(1.9920e+08, device='cuda:0'), tensor(1.9518e+08, device='cuda:0'), tensor(2.0061e+08, device='cuda:0'), tensor(1.8447e+08, device='cuda:0'), tensor(1.9076e+08, device='cuda:0'), tensor(1.9121e+08, device='cuda:0'), tensor(1.8509e+08, device='cuda:0'), tensor(1.8706e+08, device='cuda:0'), tensor(1.9211e+08, device='cuda:0'), tensor(1.9849e+08, device='cuda:0')]

Training loss: 191436416.0

Prediction time: [datetime.timedelta(microseconds=531743), datetime.timedelta(microseconds=599458), datetime.timedelta(microseconds=514819), datetime.timedelta(microseconds=653230), datetime.timedelta(microseconds=556638), datetime.timedelta(microseconds=552656), datetime.timedelta(microseconds=650242), datetime.timedelta(microseconds=600453), datetime.timedelta(microseconds=599458), datetime.timedelta(microseconds=551661)]

Phi time: [datetime.timedelta(seconds=1, microseconds=276587), datetime.timedelta(microseconds=740108), datetime.timedelta(microseconds=658190), datetime.timedelta(microseconds=664183), datetime.timedelta(microseconds=664186), datetime.timedelta(microseconds=659204), datetime.timedelta(microseconds=653107), datetime.timedelta(microseconds=657020), datetime.timedelta(microseconds=659470), datetime.timedelta(microseconds=657783)]

