Precision: [tensor(0.8280, device='cuda:0'), tensor(0.8284, device='cuda:0'), tensor(0.8284, device='cuda:0'), tensor(0.8281, device='cuda:0'), tensor(0.8275, device='cuda:0'), tensor(0.8279, device='cuda:0'), tensor(0.8293, device='cuda:0'), tensor(0.8270, device='cuda:0'), tensor(0.8289, device='cuda:0'), tensor(0.8288, device='cuda:0')]

Output distance: [tensor(13594.7891, device='cuda:0'), tensor(13562.9463, device='cuda:0'), tensor(13543.9424, device='cuda:0'), tensor(13586.5664, device='cuda:0'), tensor(13633.1348, device='cuda:0'), tensor(13601.1279, device='cuda:0'), tensor(13495.2520, device='cuda:0'), tensor(13633.9189, device='cuda:0'), tensor(13519.8652, device='cuda:0'), tensor(13551.9082, device='cuda:0')]

Prediction loss: [tensor(10827.0430, device='cuda:0'), tensor(10617.1992, device='cuda:0'), tensor(10676.3721, device='cuda:0'), tensor(10750.1035, device='cuda:0'), tensor(10497.0859, device='cuda:0'), tensor(10771.1328, device='cuda:0'), tensor(10644.5713, device='cuda:0'), tensor(10723.7402, device='cuda:0'), tensor(10541.5537, device='cuda:0'), tensor(10787.3301, 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': 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': 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')}]

Compressed training loss: [tensor(1.9381e+08, device='cuda:0'), tensor(1.9059e+08, device='cuda:0'), tensor(1.9136e+08, device='cuda:0'), tensor(1.9259e+08, device='cuda:0'), tensor(1.8859e+08, device='cuda:0'), tensor(1.9302e+08, device='cuda:0'), tensor(1.9049e+08, device='cuda:0'), tensor(1.9231e+08, device='cuda:0'), tensor(1.8964e+08, device='cuda:0'), tensor(1.9318e+08, device='cuda:0')]

Training loss: 191515248.0

Prediction time: [datetime.timedelta(microseconds=958994), datetime.timedelta(microseconds=886269), datetime.timedelta(microseconds=880288), datetime.timedelta(microseconds=883283), datetime.timedelta(microseconds=972907), datetime.timedelta(microseconds=884281), datetime.timedelta(microseconds=854406), datetime.timedelta(microseconds=851418), datetime.timedelta(microseconds=851419), datetime.timedelta(microseconds=969920)]

Phi time: [datetime.timedelta(seconds=1, microseconds=591512), datetime.timedelta(seconds=1, microseconds=12743), datetime.timedelta(microseconds=967955), datetime.timedelta(microseconds=965478), datetime.timedelta(microseconds=957705), datetime.timedelta(microseconds=980876), datetime.timedelta(microseconds=994999), datetime.timedelta(microseconds=964501), datetime.timedelta(microseconds=964020), datetime.timedelta(microseconds=961086)]

