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(0.9995, device='cuda:0'), tensor(0.9990, device='cuda:0'), tensor(0.9992, device='cuda:0'), tensor(0.9992, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9995, device='cuda:0')]

Output distance: [tensor(141209.6250, device='cuda:0'), tensor(141699.8438, device='cuda:0'), tensor(140244.9688, device='cuda:0'), tensor(140735.3281, device='cuda:0'), tensor(140027.3438, device='cuda:0'), tensor(141693.5938, device='cuda:0'), tensor(143186.0312, device='cuda:0'), tensor(140547.4375, device='cuda:0'), tensor(140736.9688, device='cuda:0'), tensor(141284.9375, device='cuda:0')]

Prediction loss: [tensor(139855.8750, device='cuda:0'), tensor(137109.7969, device='cuda:0'), tensor(137960.2812, device='cuda:0'), tensor(143795.1094, device='cuda:0'), tensor(146135.5000, device='cuda:0'), tensor(142605.7188, device='cuda:0'), tensor(139452.8281, device='cuda:0'), tensor(140832.5625, device='cuda:0'), tensor(141280.1875, device='cuda:0'), tensor(140183.6250, 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': 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': 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': 9, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}]

Compressed training loss: [tensor(1.9417e+08, device='cuda:0'), tensor(1.9408e+08, device='cuda:0'), tensor(1.9430e+08, device='cuda:0'), tensor(1.9481e+08, device='cuda:0'), tensor(1.9599e+08, device='cuda:0'), tensor(1.9200e+08, device='cuda:0'), tensor(1.9311e+08, device='cuda:0'), tensor(1.9568e+08, device='cuda:0'), tensor(1.9509e+08, device='cuda:0'), tensor(1.9362e+08, device='cuda:0')]

Training loss: 191664768.0

Prediction time: [datetime.timedelta(microseconds=536725), datetime.timedelta(microseconds=568589), datetime.timedelta(microseconds=517806), datetime.timedelta(microseconds=513821), datetime.timedelta(microseconds=499879), datetime.timedelta(microseconds=576554), datetime.timedelta(microseconds=565601), datetime.timedelta(microseconds=507845), datetime.timedelta(microseconds=507846), datetime.timedelta(microseconds=521787)]

Phi time: [datetime.timedelta(seconds=1, microseconds=178095), datetime.timedelta(microseconds=717262), datetime.timedelta(microseconds=653228), datetime.timedelta(microseconds=646691), datetime.timedelta(microseconds=646531), datetime.timedelta(microseconds=647808), datetime.timedelta(microseconds=644623), datetime.timedelta(microseconds=649957), datetime.timedelta(microseconds=647659), datetime.timedelta(microseconds=648861)]

