Precision: [tensor(0.3313, device='cuda:0'), tensor(0.3381, device='cuda:0'), tensor(0.3360, device='cuda:0'), tensor(0.3292, device='cuda:0'), tensor(0.3342, device='cuda:0'), tensor(0.3368, device='cuda:0'), tensor(0.3337, device='cuda:0'), tensor(0.3389, device='cuda:0'), tensor(0.3329, device='cuda:0'), tensor(0.3324, device='cuda:0')]
Output distance: [tensor(5.6435, device='cuda:0'), tensor(5.6298, device='cuda:0'), tensor(5.6340, device='cuda:0'), tensor(5.6477, device='cuda:0'), tensor(5.6377, device='cuda:0'), tensor(5.6325, device='cuda:0'), tensor(5.6388, device='cuda:0'), tensor(5.6282, device='cuda:0'), tensor(5.6403, device='cuda:0'), tensor(5.6414, device='cuda:0')]
Prediction loss: [tensor(36.8923, device='cuda:0'), tensor(35.8364, device='cuda:0'), tensor(36.7900, device='cuda:0'), tensor(36.1927, device='cuda:0'), tensor(36.7413, device='cuda:0'), tensor(35.7625, device='cuda:0'), tensor(36.9251, device='cuda:0'), tensor(35.4660, device='cuda:0'), tensor(37.3860, device='cuda:0'), tensor(36.1879, 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': 3, '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': 3, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 3, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 3, '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(48885.3008, device='cuda:0'), tensor(48889., device='cuda:0'), tensor(48861.9180, device='cuda:0'), tensor(48803.5508, device='cuda:0'), tensor(48888.3828, device='cuda:0'), tensor(48915.2578, device='cuda:0'), tensor(48739.9414, device='cuda:0'), tensor(48820.9570, device='cuda:0'), tensor(48825.3203, device='cuda:0'), tensor(48943.3672, device='cuda:0')]
Training loss: 0
Prediction time: [datetime.timedelta(seconds=6, microseconds=43357), datetime.timedelta(seconds=6, microseconds=72239), datetime.timedelta(seconds=6, microseconds=57300), datetime.timedelta(seconds=3, microseconds=946257), datetime.timedelta(seconds=6, microseconds=35400), datetime.timedelta(seconds=6, microseconds=50381), datetime.timedelta(seconds=3, microseconds=924348), datetime.timedelta(seconds=4, microseconds=43846), datetime.timedelta(seconds=3, microseconds=923405), datetime.timedelta(seconds=6, microseconds=16416)]
Phi time: [datetime.timedelta(seconds=5, microseconds=676916), datetime.timedelta(seconds=5, microseconds=828267), datetime.timedelta(seconds=5, microseconds=852153), datetime.timedelta(seconds=5, microseconds=870092), datetime.timedelta(seconds=5, microseconds=796403), datetime.timedelta(seconds=5, microseconds=893991), datetime.timedelta(seconds=5, microseconds=875070), datetime.timedelta(seconds=5, microseconds=809350), datetime.timedelta(seconds=5, microseconds=855154), datetime.timedelta(seconds=5, microseconds=810344)]
