Precision: [tensor(0.9623, device='cuda:0'), tensor(0.9614, device='cuda:0'), tensor(0.9603, device='cuda:0'), tensor(0.9622, device='cuda:0'), tensor(0.9611, device='cuda:0'), tensor(0.9614, device='cuda:0'), tensor(0.9620, device='cuda:0'), tensor(0.9616, device='cuda:0'), tensor(0.9613, device='cuda:0'), tensor(0.9614, device='cuda:0')]

Output distance: [tensor(109.5360, device='cuda:0'), tensor(105.8360, device='cuda:0'), tensor(118.9873, device='cuda:0'), tensor(109.2937, device='cuda:0'), tensor(118.4917, device='cuda:0'), tensor(113.2677, device='cuda:0'), tensor(108.1707, device='cuda:0'), tensor(106.2773, device='cuda:0'), tensor(108.0501, device='cuda:0'), tensor(116.2691, device='cuda:0')]

Prediction loss: [tensor(379.1297, device='cuda:0'), tensor(374.8411, device='cuda:0'), tensor(395.2869, device='cuda:0'), tensor(377.3274, device='cuda:0'), tensor(398.3005, device='cuda:0'), tensor(377.3463, device='cuda:0'), tensor(376.9723, device='cuda:0'), tensor(369.3322, device='cuda:0'), tensor(371.2651, device='cuda:0'), tensor(384.6794, device='cuda:0')]

Others: [{'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')}, {'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': 9, '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': 13, '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(3588749.2500, device='cuda:0'), tensor(3560305.5000, device='cuda:0'), tensor(3719552.5000, device='cuda:0'), tensor(3559298.2500, device='cuda:0'), tensor(3728028., device='cuda:0'), tensor(3564418.7500, device='cuda:0'), tensor(3568091.2500, device='cuda:0'), tensor(3509020.2500, device='cuda:0'), tensor(3533226., device='cuda:0'), tensor(3633977., device='cuda:0')]

Training loss: 3601148.25

Prediction time: [datetime.timedelta(seconds=1, microseconds=992548), datetime.timedelta(microseconds=961922), datetime.timedelta(seconds=2, microseconds=13451), datetime.timedelta(seconds=2, microseconds=7486), datetime.timedelta(seconds=2, microseconds=24417), datetime.timedelta(seconds=2, microseconds=7486), datetime.timedelta(microseconds=824507), datetime.timedelta(seconds=2, microseconds=10473), datetime.timedelta(seconds=1, microseconds=52535), datetime.timedelta(seconds=1, microseconds=999519)]

Phi time: [datetime.timedelta(seconds=1, microseconds=518639), datetime.timedelta(microseconds=983201), datetime.timedelta(microseconds=988286), datetime.timedelta(microseconds=958719), datetime.timedelta(microseconds=955955), datetime.timedelta(microseconds=951252), datetime.timedelta(microseconds=950609), datetime.timedelta(microseconds=941575), datetime.timedelta(microseconds=951262), datetime.timedelta(microseconds=955353)]

