Precision: [tensor(0.5690, device='cuda:0'), tensor(0.5484, device='cuda:0'), tensor(0.5526, device='cuda:0'), tensor(0.5429, device='cuda:0'), tensor(0.5613, device='cuda:0'), tensor(0.5458, device='cuda:0'), tensor(0.5593, device='cuda:0'), tensor(0.5569, device='cuda:0'), tensor(0.5456, device='cuda:0'), tensor(0.5571, device='cuda:0')]
Output distance: [tensor(18.9033, device='cuda:0'), tensor(18.9409, device='cuda:0'), tensor(18.9329, device='cuda:0'), tensor(18.9506, device='cuda:0'), tensor(18.9179, device='cuda:0'), tensor(18.9451, device='cuda:0'), tensor(18.9214, device='cuda:0'), tensor(18.9252, device='cuda:0'), tensor(18.9459, device='cuda:0'), tensor(18.9252, device='cuda:0')]
Prediction loss: [tensor(109.3731, device='cuda:0'), tensor(108.1304, device='cuda:0'), tensor(109.2005, device='cuda:0'), tensor(108.6618, device='cuda:0'), tensor(108.6397, device='cuda:0'), tensor(108.8929, device='cuda:0'), tensor(108.9849, device='cuda:0'), tensor(109.2326, device='cuda:0'), tensor(108.0291, device='cuda:0'), tensor(109.4137, device='cuda:0')]
Others: [{'iter_num': 5, 'num_positive': tensor(5854, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(5777, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(5812, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(5775, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(5795, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(5799, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(5798, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(5821, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(5764, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(5809, 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=717420), datetime.timedelta(seconds=10, microseconds=787477), datetime.timedelta(seconds=10, microseconds=784572), datetime.timedelta(seconds=10, microseconds=660150), datetime.timedelta(seconds=10, microseconds=615645), datetime.timedelta(seconds=10, microseconds=701550), datetime.timedelta(seconds=10, microseconds=727621), datetime.timedelta(seconds=10, microseconds=738889), datetime.timedelta(seconds=11, microseconds=405625), datetime.timedelta(seconds=12, microseconds=482060)]
Phi time: [datetime.timedelta(seconds=98, microseconds=916362), datetime.timedelta(seconds=99, microseconds=152744), datetime.timedelta(seconds=99, microseconds=298890), datetime.timedelta(seconds=99, microseconds=151012), datetime.timedelta(seconds=99, microseconds=84017), datetime.timedelta(seconds=99, microseconds=143086), datetime.timedelta(seconds=98, microseconds=949903), datetime.timedelta(seconds=98, microseconds=994286), datetime.timedelta(seconds=103, microseconds=661751), datetime.timedelta(seconds=115, microseconds=537957)]
