Precision: [tensor(0.2837, device='cuda:0'), tensor(0.1748, device='cuda:0'), tensor(0.2334, device='cuda:0'), tensor(0.2436, device='cuda:0'), tensor(0.2271, device='cuda:0'), tensor(0.2117, device='cuda:0'), tensor(0.2022, device='cuda:0'), tensor(0.2333, device='cuda:0'), tensor(0.2400, device='cuda:0'), tensor(0.2057, device='cuda:0')]

Output distance: [tensor(1.2701e+23, device='cuda:0'), tensor(1.3299e+24, device='cuda:0'), tensor(9.4516e+22, device='cuda:0'), tensor(2.5438e+23, device='cuda:0'), tensor(1.3900e+24, device='cuda:0'), tensor(1.0244e+24, device='cuda:0'), tensor(5.4942e+24, device='cuda:0'), tensor(3.7066e+23, device='cuda:0'), tensor(1.0608e+24, device='cuda:0'), tensor(3.3688e+25, device='cuda:0')]

Prediction loss: [tensor(2.2491e+23, device='cuda:0'), tensor(2.0492e+24, device='cuda:0'), tensor(1.6577e+23, device='cuda:0'), tensor(4.4209e+23, device='cuda:0'), tensor(2.4177e+24, device='cuda:0'), tensor(1.6931e+24, device='cuda:0'), tensor(8.9914e+24, device='cuda:0'), tensor(6.2086e+23, device='cuda:0'), tensor(1.8796e+24, device='cuda:0'), tensor(5.5522e+25, device='cuda:0')]

Others: [{'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': 30, 'num_positive': tensor(17996, 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': 30, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}]

Compressed training loss: [tensor(1.9151e+08, device='cuda:0'), tensor(2.0336e+08, device='cuda:0'), tensor(1.8949e+08, device='cuda:0'), tensor(1.9370e+08, device='cuda:0'), tensor(1.9551e+08, device='cuda:0'), tensor(1.9351e+08, device='cuda:0'), tensor(1.9584e+08, device='cuda:0'), tensor(1.9812e+08, device='cuda:0'), tensor(1.9307e+08, device='cuda:0'), tensor(1.9395e+08, device='cuda:0')]

Training loss: 192915152.0

Prediction time: [datetime.timedelta(seconds=1, microseconds=340315), datetime.timedelta(seconds=1, microseconds=351269), datetime.timedelta(seconds=1, microseconds=378155), datetime.timedelta(seconds=1, microseconds=357243), datetime.timedelta(seconds=1, microseconds=361226), datetime.timedelta(seconds=1, microseconds=361229), datetime.timedelta(seconds=1, microseconds=359235), datetime.timedelta(seconds=1, microseconds=347286), datetime.timedelta(seconds=1, microseconds=392097), datetime.timedelta(seconds=1, microseconds=368200)]

Phi time: [datetime.timedelta(seconds=1, microseconds=294100), datetime.timedelta(microseconds=745292), datetime.timedelta(microseconds=674636), datetime.timedelta(microseconds=670312), datetime.timedelta(microseconds=666660), datetime.timedelta(microseconds=667438), datetime.timedelta(microseconds=670692), datetime.timedelta(microseconds=680297), datetime.timedelta(microseconds=668285), datetime.timedelta(microseconds=674260)]

