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

Output distance: [tensor(140171.7500, device='cuda:0'), tensor(140098.5938, device='cuda:0'), tensor(140209.1562, device='cuda:0'), tensor(140109.2188, device='cuda:0'), tensor(140371.5156, device='cuda:0'), tensor(141470.5625, device='cuda:0'), tensor(140283.2500, device='cuda:0'), tensor(140100.4219, device='cuda:0'), tensor(141399.7500, device='cuda:0'), tensor(140327.3438, device='cuda:0')]

Prediction loss: [tensor(141815.3750, device='cuda:0'), tensor(138797.3750, device='cuda:0'), tensor(138738.3906, device='cuda:0'), tensor(137008.1250, device='cuda:0'), tensor(138088.9531, device='cuda:0'), tensor(134081.0469, device='cuda:0'), tensor(139892.2969, device='cuda:0'), tensor(130990.9609, device='cuda:0'), tensor(134858.3594, device='cuda:0'), tensor(138524.6562, device='cuda:0')]

Others: [{'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': 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': 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')}]

Compressed training loss: [tensor(1.9775e+08, device='cuda:0'), tensor(1.9387e+08, device='cuda:0'), tensor(1.9312e+08, device='cuda:0'), tensor(1.9333e+08, device='cuda:0'), tensor(1.9432e+08, device='cuda:0'), tensor(1.9119e+08, device='cuda:0'), tensor(1.9340e+08, device='cuda:0'), tensor(1.8937e+08, device='cuda:0'), tensor(1.9102e+08, device='cuda:0'), tensor(1.9293e+08, device='cuda:0')]

Training loss: 192692688.0

Prediction time: [datetime.timedelta(microseconds=658204), datetime.timedelta(microseconds=698043), datetime.timedelta(microseconds=676131), datetime.timedelta(microseconds=678102), datetime.timedelta(microseconds=747828), datetime.timedelta(microseconds=742848), datetime.timedelta(microseconds=682108), datetime.timedelta(microseconds=749816), datetime.timedelta(microseconds=751812), datetime.timedelta(microseconds=687097)]

Phi time: [datetime.timedelta(seconds=1, microseconds=467471), datetime.timedelta(microseconds=910090), datetime.timedelta(microseconds=857120), datetime.timedelta(microseconds=856732), datetime.timedelta(microseconds=857547), datetime.timedelta(microseconds=854341), datetime.timedelta(microseconds=879555), datetime.timedelta(microseconds=855762), datetime.timedelta(microseconds=859001), datetime.timedelta(microseconds=859223)]

