Precision: [tensor(0.9997, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(1., device='cuda:0'), tensor(0.9998, device='cuda:0'), tensor(0.9998, device='cuda:0'), tensor(0.9997, device='cuda:0'), tensor(0.9997, device='cuda:0'), tensor(0.9998, device='cuda:0'), tensor(0.9997, device='cuda:0'), tensor(0.9998, device='cuda:0')]

Output distance: [tensor(140009.6250, device='cuda:0'), tensor(140083.3281, device='cuda:0'), tensor(139912.4531, device='cuda:0'), tensor(139713.2656, device='cuda:0'), tensor(139862.7812, device='cuda:0'), tensor(139926.7031, device='cuda:0'), tensor(139743.9062, device='cuda:0'), tensor(139766.6562, device='cuda:0'), tensor(139683.8594, device='cuda:0'), tensor(139726.3281, device='cuda:0')]

Prediction loss: [tensor(136669.2188, device='cuda:0'), tensor(132551.8125, device='cuda:0'), tensor(142706.7656, device='cuda:0'), tensor(140265.3906, device='cuda:0'), tensor(135681.8125, device='cuda:0'), tensor(138774.1719, device='cuda:0'), tensor(141444.5469, device='cuda:0'), tensor(132577.5625, device='cuda:0'), tensor(137449.1719, device='cuda:0'), tensor(136581.7812, device='cuda:0')]

Others: [{'iter_num': 11, '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': 9, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 9, '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': 9, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 9, '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': 9, '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')}]

Compressed training loss: [tensor(1.9088e+08, device='cuda:0'), tensor(1.8974e+08, device='cuda:0'), tensor(1.9520e+08, device='cuda:0'), tensor(1.9291e+08, device='cuda:0'), tensor(1.8962e+08, device='cuda:0'), tensor(1.9496e+08, device='cuda:0'), tensor(1.9502e+08, device='cuda:0'), tensor(1.8831e+08, device='cuda:0'), tensor(1.9122e+08, device='cuda:0'), tensor(1.9230e+08, device='cuda:0')]

Training loss: 192556848.0

Prediction time: [datetime.timedelta(microseconds=791665), datetime.timedelta(microseconds=815566), datetime.timedelta(microseconds=726944), datetime.timedelta(microseconds=732915), datetime.timedelta(microseconds=804613), datetime.timedelta(microseconds=703041), datetime.timedelta(microseconds=710008), datetime.timedelta(microseconds=809593), datetime.timedelta(microseconds=711008), datetime.timedelta(microseconds=815566)]

Phi time: [datetime.timedelta(seconds=1, microseconds=545073), datetime.timedelta(microseconds=972299), datetime.timedelta(microseconds=933231), datetime.timedelta(microseconds=941359), datetime.timedelta(microseconds=940038), datetime.timedelta(microseconds=933945), datetime.timedelta(microseconds=963895), datetime.timedelta(microseconds=940967), datetime.timedelta(microseconds=939610), datetime.timedelta(microseconds=981979)]

