Precision: [tensor(0.8247, device='cuda:0'), tensor(0.8262, device='cuda:0'), tensor(0.8245, device='cuda:0'), tensor(0.8261, device='cuda:0'), tensor(0.8260, device='cuda:0'), tensor(0.8253, device='cuda:0'), tensor(0.8237, device='cuda:0'), tensor(0.8252, device='cuda:0'), tensor(0.8261, device='cuda:0'), tensor(0.8243, device='cuda:0')]

Output distance: [tensor(13694.6504, device='cuda:0'), tensor(13630.7188, device='cuda:0'), tensor(13711.9922, device='cuda:0'), tensor(13583.1514, device='cuda:0'), tensor(13623.2744, device='cuda:0'), tensor(13670.5576, device='cuda:0'), tensor(13769.2051, device='cuda:0'), tensor(13642.2305, device='cuda:0'), tensor(13604.0596, device='cuda:0'), tensor(13739.6426, device='cuda:0')]

Prediction loss: [tensor(10537.2402, device='cuda:0'), tensor(10474.2422, device='cuda:0'), tensor(10475.9043, device='cuda:0'), tensor(10418.4688, device='cuda:0'), tensor(10527.8105, device='cuda:0'), tensor(10257.2588, device='cuda:0'), tensor(10597.3926, device='cuda:0'), tensor(10588.0107, device='cuda:0'), tensor(10589.5420, device='cuda:0'), tensor(10521.3516, device='cuda:0')]

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

Compressed training loss: [tensor(1.9187e+08, device='cuda:0'), tensor(1.9068e+08, device='cuda:0'), tensor(1.9085e+08, device='cuda:0'), tensor(1.9020e+08, device='cuda:0'), tensor(1.9187e+08, device='cuda:0'), tensor(1.8691e+08, device='cuda:0'), tensor(1.9289e+08, device='cuda:0'), tensor(1.9261e+08, device='cuda:0'), tensor(1.9292e+08, device='cuda:0'), tensor(1.9218e+08, device='cuda:0')]

Training loss: 192187264.0

Prediction time: [datetime.timedelta(microseconds=772723), datetime.timedelta(microseconds=844419), datetime.timedelta(microseconds=791590), datetime.timedelta(microseconds=779694), datetime.timedelta(microseconds=786665), datetime.timedelta(microseconds=859356), datetime.timedelta(microseconds=872304), datetime.timedelta(microseconds=783677), datetime.timedelta(microseconds=777702), datetime.timedelta(microseconds=782680)]

Phi time: [datetime.timedelta(seconds=1, microseconds=423685), datetime.timedelta(microseconds=964523), datetime.timedelta(microseconds=882876), datetime.timedelta(microseconds=871039), datetime.timedelta(microseconds=863417), datetime.timedelta(microseconds=862446), datetime.timedelta(microseconds=897263), datetime.timedelta(microseconds=858827), datetime.timedelta(microseconds=867149), datetime.timedelta(microseconds=859805)]

