Precision: [tensor(0.8234, device='cuda:0'), tensor(0.8232, device='cuda:0'), tensor(0.8249, device='cuda:0'), tensor(0.8243, device='cuda:0'), tensor(0.8246, device='cuda:0'), tensor(0.8239, device='cuda:0'), tensor(0.8240, device='cuda:0'), tensor(0.8248, device='cuda:0'), tensor(0.8238, device='cuda:0'), tensor(0.8247, device='cuda:0')]

Output distance: [tensor(13732.5615, device='cuda:0'), tensor(13742.6621, device='cuda:0'), tensor(13629.0908, device='cuda:0'), tensor(13673.9531, device='cuda:0'), tensor(13667.2988, device='cuda:0'), tensor(13730.5078, device='cuda:0'), tensor(13700.8916, device='cuda:0'), tensor(13645.4092, device='cuda:0'), tensor(13740.0527, device='cuda:0'), tensor(13642.1514, device='cuda:0')]

Prediction loss: [tensor(10609.4395, device='cuda:0'), tensor(10591.3848, device='cuda:0'), tensor(10466.2939, device='cuda:0'), tensor(10666.6416, device='cuda:0'), tensor(10649.7256, device='cuda:0'), tensor(10581.4668, device='cuda:0'), tensor(10637.3135, device='cuda:0'), tensor(10628.1338, device='cuda:0'), tensor(10604.0986, device='cuda:0'), tensor(10718.3838, device='cuda:0')]

Others: [{'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': 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(1.9102e+08, device='cuda:0'), tensor(1.9076e+08, device='cuda:0'), tensor(1.8847e+08, device='cuda:0'), tensor(1.9188e+08, device='cuda:0'), tensor(1.9200e+08, device='cuda:0'), tensor(1.9101e+08, device='cuda:0'), tensor(1.9177e+08, device='cuda:0'), tensor(1.9130e+08, device='cuda:0'), tensor(1.9082e+08, device='cuda:0'), tensor(1.9327e+08, device='cuda:0')]

Training loss: 191655328.0

Prediction time: [datetime.timedelta(seconds=1, microseconds=124232), datetime.timedelta(seconds=1, microseconds=152113), datetime.timedelta(seconds=1, microseconds=301480), datetime.timedelta(seconds=1, microseconds=135188), datetime.timedelta(seconds=1, microseconds=143149), datetime.timedelta(seconds=1, microseconds=161075), datetime.timedelta(seconds=1, microseconds=147139), datetime.timedelta(seconds=1, microseconds=150123), datetime.timedelta(seconds=1, microseconds=148130), datetime.timedelta(seconds=1, microseconds=133195)]

Phi time: [datetime.timedelta(seconds=1, microseconds=927483), datetime.timedelta(seconds=1, microseconds=300677), datetime.timedelta(seconds=1, microseconds=306328), datetime.timedelta(seconds=1, microseconds=298078), datetime.timedelta(seconds=1, microseconds=303752), datetime.timedelta(seconds=1, microseconds=299985), datetime.timedelta(seconds=1, microseconds=303354), datetime.timedelta(seconds=1, microseconds=303238), datetime.timedelta(seconds=1, microseconds=304087), datetime.timedelta(seconds=1, microseconds=316058)]

