Precision: [tensor(0.9995, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9992, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9995, device='cuda:0')]

Output distance: [tensor(143888.0156, device='cuda:0'), tensor(141897.4844, device='cuda:0'), tensor(140286.7031, device='cuda:0'), tensor(141647., device='cuda:0'), tensor(142966.5312, device='cuda:0'), tensor(143123.1250, device='cuda:0'), tensor(140443.3438, device='cuda:0'), tensor(146203.6719, device='cuda:0'), tensor(148507.0312, device='cuda:0'), tensor(144685.8281, device='cuda:0')]

Prediction loss: [tensor(145809.4688, device='cuda:0'), tensor(141542., device='cuda:0'), tensor(134542.7031, device='cuda:0'), tensor(138927.1406, device='cuda:0'), tensor(141006.2031, device='cuda:0'), tensor(142311.3906, device='cuda:0'), tensor(136349.8906, device='cuda:0'), tensor(146699.6406, device='cuda:0'), tensor(150244.8125, device='cuda:0'), tensor(144075.5469, device='cuda:0')]

Others: [{'iter_num': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 21, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 23, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 23, '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': 29, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 27, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}]

Compressed training loss: [tensor(1.9335e+08, device='cuda:0'), tensor(1.9501e+08, device='cuda:0'), tensor(1.9033e+08, device='cuda:0'), tensor(1.9301e+08, device='cuda:0'), tensor(1.9246e+08, device='cuda:0'), tensor(1.9440e+08, device='cuda:0'), tensor(1.9078e+08, device='cuda:0'), tensor(1.9381e+08, device='cuda:0'), tensor(1.9441e+08, device='cuda:0'), tensor(1.9134e+08, device='cuda:0')]

Training loss: 192913600.0

Prediction time: [datetime.timedelta(seconds=1, microseconds=669918), datetime.timedelta(seconds=1, microseconds=265633), datetime.timedelta(microseconds=615390), datetime.timedelta(seconds=1, microseconds=699791), datetime.timedelta(seconds=1, microseconds=361226), datetime.timedelta(seconds=1, microseconds=377159), datetime.timedelta(microseconds=801601), datetime.timedelta(seconds=1, microseconds=643030), datetime.timedelta(seconds=1, microseconds=679876), datetime.timedelta(seconds=1, microseconds=578307)]

Phi time: [datetime.timedelta(seconds=1, microseconds=388594), datetime.timedelta(microseconds=891713), datetime.timedelta(microseconds=853328), datetime.timedelta(microseconds=876027), datetime.timedelta(microseconds=859808), datetime.timedelta(microseconds=854877), datetime.timedelta(microseconds=854868), datetime.timedelta(microseconds=852439), datetime.timedelta(microseconds=855202), datetime.timedelta(microseconds=858398)]

