Precision: [tensor(0.7018, device='cuda:0'), tensor(0.7049, device='cuda:0'), tensor(0.7109, device='cuda:0'), tensor(0.7057, device='cuda:0'), tensor(0.7054, device='cuda:0'), tensor(0.7052, device='cuda:0'), tensor(0.7044, device='cuda:0'), tensor(0.7018, device='cuda:0'), tensor(0.7007, device='cuda:0'), tensor(0.7057, device='cuda:0')]
Output distance: [tensor(4.9026, device='cuda:0'), tensor(4.8963, device='cuda:0'), tensor(4.8842, device='cuda:0'), tensor(4.8947, device='cuda:0'), tensor(4.8952, device='cuda:0'), tensor(4.8958, device='cuda:0'), tensor(4.8973, device='cuda:0'), tensor(4.9026, device='cuda:0'), tensor(4.9047, device='cuda:0'), tensor(4.8947, device='cuda:0')]
Prediction loss: [tensor(36.6483, device='cuda:0'), tensor(37.3260, device='cuda:0'), tensor(35.8927, device='cuda:0'), tensor(37.2563, device='cuda:0'), tensor(34.7518, device='cuda:0'), tensor(36.9789, device='cuda:0'), tensor(38.4806, device='cuda:0'), tensor(37.6850, device='cuda:0'), tensor(35.7485, device='cuda:0'), tensor(38.0941, device='cuda:0')]
Others: [{'iter_num': 5, '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': 5, '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': 5, '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': 5, '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': 5, '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')}]
Compressed training loss: [tensor(48941.4336, device='cuda:0'), tensor(48847.3281, device='cuda:0'), tensor(48935.4180, device='cuda:0'), tensor(48702.7227, device='cuda:0'), tensor(48786.1211, device='cuda:0'), tensor(48912.2070, device='cuda:0'), tensor(48963.1367, device='cuda:0'), tensor(48952.7773, device='cuda:0'), tensor(48788.3828, device='cuda:0'), tensor(48901.0977, device='cuda:0')]
Training loss: 0
Prediction time: [datetime.timedelta(seconds=1, microseconds=51537), datetime.timedelta(seconds=1, microseconds=48545), datetime.timedelta(seconds=1, microseconds=42630), datetime.timedelta(seconds=1, microseconds=50544), datetime.timedelta(seconds=1, microseconds=64432), datetime.timedelta(seconds=1, microseconds=18682), datetime.timedelta(seconds=1, microseconds=47555), datetime.timedelta(seconds=1, microseconds=62489), datetime.timedelta(seconds=1, microseconds=48602), datetime.timedelta(seconds=1, microseconds=43520)]
Phi time: [datetime.timedelta(seconds=5, microseconds=819308), datetime.timedelta(seconds=5, microseconds=662971), datetime.timedelta(seconds=5, microseconds=657994), datetime.timedelta(seconds=5, microseconds=660988), datetime.timedelta(seconds=5, microseconds=654009), datetime.timedelta(seconds=5, microseconds=661030), datetime.timedelta(seconds=5, microseconds=684903), datetime.timedelta(seconds=5, microseconds=649031), datetime.timedelta(seconds=5, microseconds=677844), datetime.timedelta(seconds=5, microseconds=659986)]
