Precision: [tensor(0.6931, device='cuda:0'), tensor(0.6949, device='cuda:0'), tensor(0.6976, device='cuda:0'), tensor(0.7070, device='cuda:0'), tensor(0.6960, device='cuda:0'), tensor(0.6920, device='cuda:0'), tensor(0.6952, device='cuda:0'), tensor(0.6936, device='cuda:0'), tensor(0.6936, device='cuda:0'), tensor(0.7012, device='cuda:0')]

Output distance: [tensor(4.9199, device='cuda:0'), tensor(4.9163, device='cuda:0'), tensor(4.9110, device='cuda:0'), tensor(4.8921, device='cuda:0'), tensor(4.9142, device='cuda:0'), tensor(4.9220, device='cuda:0'), tensor(4.9157, device='cuda:0'), tensor(4.9189, device='cuda:0'), tensor(4.9189, device='cuda:0'), tensor(4.9036, device='cuda:0')]

Prediction loss: [tensor(19829596., device='cuda:0'), tensor(19143376., device='cuda:0'), tensor(18208126., device='cuda:0'), tensor(18628164., device='cuda:0'), tensor(18720120., device='cuda:0'), tensor(18336884., device='cuda:0'), tensor(18303928., device='cuda:0'), tensor(17240554., device='cuda:0'), tensor(18432172., device='cuda:0'), tensor(18287732., device='cuda:0')]

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

Compressed training loss: [tensor(40876.6250, device='cuda:0'), tensor(40688.6133, device='cuda:0'), tensor(40813.6172, device='cuda:0'), tensor(40771.8477, device='cuda:0'), tensor(40854.6758, device='cuda:0'), tensor(40749.3867, device='cuda:0'), tensor(40872.5000, device='cuda:0'), tensor(40940.2500, device='cuda:0'), tensor(40784.9297, device='cuda:0'), tensor(40712.1875, device='cuda:0')]

Training loss: 0

Prediction time: [datetime.timedelta(seconds=1, microseconds=23222), datetime.timedelta(seconds=1, microseconds=47012), datetime.timedelta(seconds=1, microseconds=34379), datetime.timedelta(seconds=1, microseconds=27742), datetime.timedelta(seconds=1, microseconds=40792), datetime.timedelta(seconds=1, microseconds=22828), datetime.timedelta(seconds=1, microseconds=38990), datetime.timedelta(seconds=1, microseconds=33666), datetime.timedelta(seconds=1, microseconds=10602), datetime.timedelta(seconds=1, microseconds=38801)]

Phi time: [datetime.timedelta(microseconds=303656), datetime.timedelta(microseconds=300035), datetime.timedelta(microseconds=303116), datetime.timedelta(microseconds=321319), datetime.timedelta(microseconds=300019), datetime.timedelta(microseconds=308775), datetime.timedelta(microseconds=292288), datetime.timedelta(microseconds=307139), datetime.timedelta(microseconds=292809), datetime.timedelta(microseconds=299988)]

