Precision: [tensor(0.6406, device='cuda:0'), tensor(0.6422, device='cuda:0'), tensor(0.6464, device='cuda:0'), tensor(0.6311, device='cuda:0'), tensor(0.6388, device='cuda:0'), tensor(0.6388, device='cuda:0'), tensor(0.6416, device='cuda:0'), tensor(0.6456, device='cuda:0'), tensor(0.6380, device='cuda:0'), tensor(0.6440, device='cuda:0')]

Output distance: [tensor(5.0249, device='cuda:0'), tensor(5.0218, device='cuda:0'), tensor(5.0134, device='cuda:0'), tensor(5.0438, device='cuda:0'), tensor(5.0286, device='cuda:0'), tensor(5.0286, device='cuda:0'), tensor(5.0228, device='cuda:0'), tensor(5.0150, device='cuda:0'), tensor(5.0302, device='cuda:0'), tensor(5.0181, device='cuda:0')]

Prediction loss: [tensor(19579296., device='cuda:0'), tensor(16899260., device='cuda:0'), tensor(18022338., device='cuda:0'), tensor(17537256., device='cuda:0'), tensor(15853924., device='cuda:0'), tensor(18000216., device='cuda:0'), tensor(18792856., device='cuda:0'), tensor(16754772., device='cuda:0'), tensor(18241302., device='cuda:0'), tensor(18774324., device='cuda:0')]

Others: [{'iter_num': 7, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}]

Compressed training loss: [tensor(40616.5430, device='cuda:0'), tensor(41175.1680, device='cuda:0'), tensor(40624.6133, device='cuda:0'), tensor(40648.4180, device='cuda:0'), tensor(40795.1562, device='cuda:0'), tensor(40859.2578, device='cuda:0'), tensor(40832.9844, device='cuda:0'), tensor(40598.7344, device='cuda:0'), tensor(40795.2578, device='cuda:0'), tensor(40823.6172, device='cuda:0')]

Training loss: 0

Prediction time: [datetime.timedelta(seconds=1, microseconds=20312), datetime.timedelta(seconds=1, microseconds=18028), datetime.timedelta(microseconds=973068), datetime.timedelta(seconds=1, microseconds=2799), datetime.timedelta(microseconds=972268), datetime.timedelta(microseconds=992711), datetime.timedelta(microseconds=984861), datetime.timedelta(microseconds=970315), datetime.timedelta(microseconds=999103), datetime.timedelta(microseconds=988602)]

Phi time: [datetime.timedelta(microseconds=164514), datetime.timedelta(microseconds=189161), datetime.timedelta(microseconds=195312), datetime.timedelta(microseconds=189280), datetime.timedelta(microseconds=194278), datetime.timedelta(microseconds=179946), datetime.timedelta(microseconds=171228), datetime.timedelta(microseconds=179699), datetime.timedelta(microseconds=195834), datetime.timedelta(microseconds=193677)]

