Precision: [tensor(0.7065, device='cuda:0'), tensor(0.7081, device='cuda:0'), tensor(0.7044, device='cuda:0'), tensor(0.6997, device='cuda:0'), tensor(0.7067, device='cuda:0'), tensor(0.7062, device='cuda:0'), tensor(0.7073, device='cuda:0'), tensor(0.7070, device='cuda:0'), tensor(0.7086, device='cuda:0'), tensor(0.6991, device='cuda:0')]
Output distance: [tensor(4.8931, device='cuda:0'), tensor(4.8900, device='cuda:0'), tensor(4.8973, device='cuda:0'), tensor(4.9068, device='cuda:0'), tensor(4.8926, device='cuda:0'), tensor(4.8937, device='cuda:0'), tensor(4.8916, device='cuda:0'), tensor(4.8921, device='cuda:0'), tensor(4.8889, device='cuda:0'), tensor(4.9078, device='cuda:0')]
Prediction loss: [tensor(36.7402, device='cuda:0'), tensor(37.0425, device='cuda:0'), tensor(36.7561, device='cuda:0'), tensor(36.7107, device='cuda:0'), tensor(35.1751, device='cuda:0'), tensor(35.9148, device='cuda:0'), tensor(35.6842, device='cuda:0'), tensor(35.6760, device='cuda:0'), tensor(35.8598, device='cuda:0'), tensor(36.1431, device='cuda:0')]
Others: [{'iter_num': 30, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}]
Compressed training loss: [tensor(48992.1758, device='cuda:0'), tensor(48910.1133, device='cuda:0'), tensor(48768.1016, device='cuda:0'), tensor(49120.7305, device='cuda:0'), tensor(48900.5430, device='cuda:0'), tensor(48613.2188, device='cuda:0'), tensor(48778.1953, device='cuda:0'), tensor(48726.2383, device='cuda:0'), tensor(48909.3789, device='cuda:0'), tensor(48983.0938, device='cuda:0')]
Training loss: 0
Prediction time: [datetime.timedelta(seconds=1, microseconds=368460), datetime.timedelta(seconds=1, microseconds=49545), datetime.timedelta(seconds=1, microseconds=187960), datetime.timedelta(seconds=1, microseconds=201900), datetime.timedelta(seconds=1, microseconds=48550), datetime.timedelta(seconds=1, microseconds=179994), datetime.timedelta(seconds=1, microseconds=191942), datetime.timedelta(seconds=1, microseconds=51538), datetime.timedelta(seconds=1, microseconds=177005), datetime.timedelta(seconds=1, microseconds=182973)]
Phi time: [datetime.timedelta(seconds=7, microseconds=130080), datetime.timedelta(seconds=5, microseconds=747617), datetime.timedelta(seconds=5, microseconds=679900), datetime.timedelta(seconds=5, microseconds=659985), datetime.timedelta(seconds=5, microseconds=677908), datetime.timedelta(seconds=5, microseconds=680897), datetime.timedelta(seconds=5, microseconds=668962), datetime.timedelta(seconds=5, microseconds=675917), datetime.timedelta(seconds=5, microseconds=671937), datetime.timedelta(seconds=5, microseconds=680896)]
