Precision: [tensor(0.8497, device='cuda:0'), tensor(0.8526, device='cuda:0'), tensor(0.8499, device='cuda:0'), tensor(0.8522, device='cuda:0'), tensor(0.8506, device='cuda:0'), tensor(0.8517, device='cuda:0'), tensor(0.8504, device='cuda:0'), tensor(0.8572, device='cuda:0'), tensor(0.8527, device='cuda:0'), tensor(0.8524, device='cuda:0')]

Output distance: [tensor(570.0951, device='cuda:0'), tensor(557.7813, device='cuda:0'), tensor(563.4771, device='cuda:0'), tensor(556.8271, device='cuda:0'), tensor(561.7596, device='cuda:0'), tensor(558.9039, device='cuda:0'), tensor(558.5563, device='cuda:0'), tensor(531.9787, device='cuda:0'), tensor(561.5734, device='cuda:0'), tensor(553.6320, device='cuda:0')]

Prediction loss: [tensor(585.5040, device='cuda:0'), tensor(576.6513, device='cuda:0'), tensor(592.0041, device='cuda:0'), tensor(617.3014, device='cuda:0'), tensor(600.9537, device='cuda:0'), tensor(608.9803, device='cuda:0'), tensor(628.2320, device='cuda:0'), tensor(577.3621, device='cuda:0'), tensor(586.9291, device='cuda:0'), tensor(591.2885, device='cuda:0')]

Others: [{'iter_num': 15, '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': 15, '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': 19, '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': 15, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 17, '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': 13, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}]

Compressed training loss: [tensor(8888572., device='cuda:0'), tensor(8787151., device='cuda:0'), tensor(8949142., device='cuda:0'), tensor(9349850., device='cuda:0'), tensor(9081788., device='cuda:0'), tensor(9227987., device='cuda:0'), tensor(9412793., device='cuda:0'), tensor(8698065., device='cuda:0'), tensor(8948996., device='cuda:0'), tensor(8961237., device='cuda:0')]

Training loss: 8891091.0

Prediction time: [datetime.timedelta(microseconds=792638), datetime.timedelta(microseconds=809567), datetime.timedelta(microseconds=820520), datetime.timedelta(microseconds=778697), datetime.timedelta(microseconds=962915), datetime.timedelta(microseconds=811558), datetime.timedelta(microseconds=828486), datetime.timedelta(microseconds=870311), datetime.timedelta(microseconds=828486), datetime.timedelta(microseconds=745837)]

Phi time: [datetime.timedelta(seconds=1, microseconds=353519), datetime.timedelta(microseconds=812626), datetime.timedelta(microseconds=738621), datetime.timedelta(microseconds=743956), datetime.timedelta(microseconds=742413), datetime.timedelta(microseconds=744882), datetime.timedelta(microseconds=744443), datetime.timedelta(microseconds=736915), datetime.timedelta(microseconds=744170), datetime.timedelta(microseconds=743528)]

