Precision: [tensor(0.9608, device='cuda:0'), tensor(0.9642, device='cuda:0'), tensor(0.9600, device='cuda:0'), tensor(0.9607, device='cuda:0'), tensor(0.9622, device='cuda:0'), tensor(0.9578, device='cuda:0'), tensor(0.9594, device='cuda:0'), tensor(0.9613, device='cuda:0'), tensor(0.9588, device='cuda:0'), tensor(0.9566, device='cuda:0')]

Output distance: [tensor(106.8445, device='cuda:0'), tensor(92.1413, device='cuda:0'), tensor(107.9380, device='cuda:0'), tensor(105.8497, device='cuda:0'), tensor(96.9288, device='cuda:0'), tensor(108.4528, device='cuda:0'), tensor(109.0050, device='cuda:0'), tensor(100.7572, device='cuda:0'), tensor(109.3785, device='cuda:0'), tensor(117.2894, device='cuda:0')]

Prediction loss: [tensor(396.8763, device='cuda:0'), tensor(363.5497, device='cuda:0'), tensor(378.9667, device='cuda:0'), tensor(367.3156, device='cuda:0'), tensor(383.4862, device='cuda:0'), tensor(376.9015, device='cuda:0'), tensor(356.4762, device='cuda:0'), tensor(371.1397, device='cuda:0'), tensor(383.1385, device='cuda:0'), tensor(373.4490, device='cuda:0')]

Others: [{'iter_num': 11, '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': 13, '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': 13, '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': 13, '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': 13, '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')}]

Compressed training loss: [tensor(3767540.7500, device='cuda:0'), tensor(3430500., device='cuda:0'), tensor(3613621.5000, device='cuda:0'), tensor(3464921.7500, device='cuda:0'), tensor(3629615.7500, device='cuda:0'), tensor(3580167., device='cuda:0'), tensor(3383926., device='cuda:0'), tensor(3525914.7500, device='cuda:0'), tensor(3650108.2500, device='cuda:0'), tensor(3545527.2500, device='cuda:0')]

Training loss: 3597498.0

Prediction time: [datetime.timedelta(microseconds=761768), datetime.timedelta(microseconds=869317), datetime.timedelta(microseconds=868330), datetime.timedelta(microseconds=885245), datetime.timedelta(microseconds=849398), datetime.timedelta(microseconds=780689), datetime.timedelta(microseconds=848401), datetime.timedelta(microseconds=865330), datetime.timedelta(microseconds=933050), datetime.timedelta(microseconds=875289)]

Phi time: [datetime.timedelta(seconds=1, microseconds=480690), datetime.timedelta(microseconds=946141), datetime.timedelta(microseconds=869477), datetime.timedelta(microseconds=866515), datetime.timedelta(microseconds=868119), datetime.timedelta(microseconds=889411), datetime.timedelta(microseconds=867683), datetime.timedelta(microseconds=874147), datetime.timedelta(microseconds=883589), datetime.timedelta(microseconds=870886)]

