Precision: [tensor(0.8577, device='cuda:0'), tensor(0.8579, device='cuda:0'), tensor(0.8556, device='cuda:0'), tensor(0.8568, device='cuda:0'), tensor(0.8578, device='cuda:0'), tensor(0.8567, device='cuda:0'), tensor(0.8588, device='cuda:0'), tensor(0.8568, device='cuda:0'), tensor(0.8562, device='cuda:0'), tensor(0.8583, device='cuda:0')]

Output distance: [tensor(534.6006, device='cuda:0'), tensor(534.6752, device='cuda:0'), tensor(546.4864, device='cuda:0'), tensor(539.9979, device='cuda:0'), tensor(535.9352, device='cuda:0'), tensor(540.5450, device='cuda:0'), tensor(524.0054, device='cuda:0'), tensor(541.5192, device='cuda:0'), tensor(542.7327, device='cuda:0'), tensor(531.9908, device='cuda:0')]

Prediction loss: [tensor(606.2883, device='cuda:0'), tensor(607.8014, device='cuda:0'), tensor(608.2779, device='cuda:0'), tensor(608.6317, device='cuda:0'), tensor(606.5045, device='cuda:0'), tensor(609.3127, device='cuda:0'), tensor(611.9325, device='cuda:0'), tensor(619.3907, device='cuda:0'), tensor(602.4385, device='cuda:0'), tensor(611.2447, device='cuda:0')]

Others: [{'iter_num': 13, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 13, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 15, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}]

Compressed training loss: [tensor(8912958., device='cuda:0'), tensor(8895448., device='cuda:0'), tensor(8890092., device='cuda:0'), tensor(8906328., device='cuda:0'), tensor(8919451., device='cuda:0'), tensor(8910356., device='cuda:0'), tensor(8947289., device='cuda:0'), tensor(9051763., device='cuda:0'), tensor(8800547., device='cuda:0'), tensor(8940445., device='cuda:0')]

Training loss: 8888734.0

Prediction time: [datetime.timedelta(microseconds=952959), datetime.timedelta(microseconds=856369), datetime.timedelta(microseconds=851389), datetime.timedelta(microseconds=963913), datetime.timedelta(microseconds=882259), datetime.timedelta(microseconds=866326), datetime.timedelta(seconds=1, microseconds=52537), datetime.timedelta(microseconds=883254), datetime.timedelta(microseconds=883253), datetime.timedelta(microseconds=868319)]

Phi time: [datetime.timedelta(seconds=1, microseconds=613829), datetime.timedelta(seconds=1, microseconds=7345), datetime.timedelta(microseconds=964491), datetime.timedelta(microseconds=967995), datetime.timedelta(microseconds=964810), datetime.timedelta(microseconds=997861), datetime.timedelta(microseconds=979217), datetime.timedelta(microseconds=966317), datetime.timedelta(microseconds=963327), datetime.timedelta(microseconds=963390)]

