Precision: [tensor(0.5549, device='cuda:0'), tensor(0.5487, device='cuda:0'), tensor(0.5444, device='cuda:0'), tensor(0.5331, device='cuda:0'), tensor(0.5410, device='cuda:0'), tensor(0.5446, device='cuda:0'), tensor(0.5624, device='cuda:0'), tensor(0.5541, device='cuda:0'), tensor(0.5476, device='cuda:0'), tensor(0.5585, device='cuda:0')]
Output distance: [tensor(18.9157, device='cuda:0'), tensor(18.9281, device='cuda:0'), tensor(18.9365, device='cuda:0'), tensor(18.9592, device='cuda:0'), tensor(18.9435, device='cuda:0'), tensor(18.9362, device='cuda:0'), tensor(18.9005, device='cuda:0'), tensor(18.9172, device='cuda:0'), tensor(18.9302, device='cuda:0'), tensor(18.9084, device='cuda:0')]
Prediction loss: [tensor(108.5891, device='cuda:0'), tensor(108.2945, device='cuda:0'), tensor(109.3786, device='cuda:0'), tensor(108.0880, device='cuda:0'), tensor(109.0051, device='cuda:0'), tensor(107.7117, device='cuda:0'), tensor(109.8347, device='cuda:0'), tensor(109.1885, device='cuda:0'), tensor(108.5745, device='cuda:0'), tensor(109.4736, device='cuda:0')]
Others: [{'iter_num': 5, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}]
Compressed training loss: [tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0')]
Training loss: 0
Prediction time: [datetime.timedelta(seconds=10, microseconds=265171), datetime.timedelta(seconds=10, microseconds=462810), datetime.timedelta(seconds=10, microseconds=443635), datetime.timedelta(seconds=10, microseconds=213744), datetime.timedelta(seconds=10, microseconds=359398), datetime.timedelta(seconds=10, microseconds=332015), datetime.timedelta(seconds=10, microseconds=349225), datetime.timedelta(seconds=10, microseconds=370992), datetime.timedelta(seconds=10, microseconds=341815), datetime.timedelta(seconds=10, microseconds=374852)]
Phi time: [datetime.timedelta(seconds=97, microseconds=578116), datetime.timedelta(seconds=97, microseconds=595177), datetime.timedelta(seconds=97, microseconds=622249), datetime.timedelta(seconds=97, microseconds=329556), datetime.timedelta(seconds=97, microseconds=645465), datetime.timedelta(seconds=97, microseconds=530670), datetime.timedelta(seconds=97, microseconds=475829), datetime.timedelta(seconds=97, microseconds=447653), datetime.timedelta(seconds=97, microseconds=438707), datetime.timedelta(seconds=97, microseconds=651235)]
