Precision: [tensor(0.9618, device='cuda:0'), tensor(0.9610, device='cuda:0'), tensor(0.9621, device='cuda:0'), tensor(0.9616, device='cuda:0'), tensor(0.9628, device='cuda:0'), tensor(0.9611, device='cuda:0'), tensor(0.9613, device='cuda:0'), tensor(0.9613, device='cuda:0'), tensor(0.9605, device='cuda:0'), tensor(0.9617, device='cuda:0')]

Output distance: [tensor(109.4906, device='cuda:0'), tensor(121.6808, device='cuda:0'), tensor(105.9786, device='cuda:0'), tensor(106.9112, device='cuda:0'), tensor(103.8153, device='cuda:0'), tensor(112.5384, device='cuda:0'), tensor(112.8897, device='cuda:0'), tensor(110.3314, device='cuda:0'), tensor(108.9710, device='cuda:0'), tensor(103.4122, device='cuda:0')]

Prediction loss: [tensor(385.0519, device='cuda:0'), tensor(394.2079, device='cuda:0'), tensor(373.9323, device='cuda:0'), tensor(375.2667, device='cuda:0'), tensor(376.9704, device='cuda:0'), tensor(384.6809, device='cuda:0'), tensor(379.2410, device='cuda:0'), tensor(379.0772, device='cuda:0'), tensor(387.6010, device='cuda:0'), tensor(371.1924, device='cuda:0')]

Others: [{'iter_num': 9, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}]

Compressed training loss: [tensor(3618412., device='cuda:0'), tensor(3678618.2500, device='cuda:0'), tensor(3536514.7500, device='cuda:0'), tensor(3538381., device='cuda:0'), tensor(3547611.7500, device='cuda:0'), tensor(3616808.5000, device='cuda:0'), tensor(3579055.7500, device='cuda:0'), tensor(3566223.7500, device='cuda:0'), tensor(3657981.2500, device='cuda:0'), tensor(3515396.5000, device='cuda:0')]

Training loss: 3592133.5

Prediction time: [datetime.timedelta(seconds=1, microseconds=61498), datetime.timedelta(seconds=1, microseconds=67473), datetime.timedelta(seconds=1, microseconds=72451), datetime.timedelta(seconds=1, microseconds=68467), datetime.timedelta(seconds=1, microseconds=72454), datetime.timedelta(seconds=1, microseconds=83405), datetime.timedelta(seconds=1, microseconds=76436), datetime.timedelta(seconds=2, microseconds=743372), datetime.timedelta(seconds=1, microseconds=72452), datetime.timedelta(microseconds=911139)]

Phi time: [datetime.timedelta(seconds=1, microseconds=852902), datetime.timedelta(seconds=1, microseconds=273864), datetime.timedelta(seconds=1, microseconds=322972), datetime.timedelta(seconds=1, microseconds=288965), datetime.timedelta(seconds=1, microseconds=326695), datetime.timedelta(seconds=1, microseconds=306624), datetime.timedelta(seconds=1, microseconds=285204), datetime.timedelta(seconds=1, microseconds=329175), datetime.timedelta(seconds=1, microseconds=313084), datetime.timedelta(seconds=1, microseconds=310868)]

