Special test with strict convergence condition

Precision: [tensor(0.6860, device='cuda:0'), tensor(0.6794, device='cuda:0'), tensor(0.6897, device='cuda:0'), tensor(0.6941, device='cuda:0'), tensor(0.6831, device='cuda:0'), tensor(0.6865, device='cuda:0'), tensor(0.6855, device='cuda:0'), tensor(0.6892, device='cuda:0'), tensor(0.6797, device='cuda:0'), tensor(0.6905, device='cuda:0')]

Output distance: [tensor(4.9341, device='cuda:0'), tensor(4.9472, device='cuda:0'), tensor(4.9268, device='cuda:0'), tensor(4.9178, device='cuda:0'), tensor(4.9399, device='cuda:0'), tensor(4.9331, device='cuda:0'), tensor(4.9352, device='cuda:0'), tensor(4.9278, device='cuda:0'), tensor(4.9467, device='cuda:0'), tensor(4.9252, device='cuda:0')]

Prediction loss: [tensor(18703842., device='cuda:0'), tensor(19153664., device='cuda:0'), tensor(16678490., device='cuda:0'), tensor(17939296., device='cuda:0'), tensor(19616474., device='cuda:0'), tensor(18263536., device='cuda:0'), tensor(18416394., device='cuda:0'), tensor(17877352., device='cuda:0'), tensor(17213782., device='cuda:0'), tensor(18680322., device='cuda:0')]

Others: [{'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': 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': 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')}]

Compressed training loss: [tensor(40903.4258, device='cuda:0'), tensor(40898.6016, device='cuda:0'), tensor(40952.9531, device='cuda:0'), tensor(40618.2070, device='cuda:0'), tensor(40852.5547, device='cuda:0'), tensor(40973.4219, device='cuda:0'), tensor(40680.3906, device='cuda:0'), tensor(40717.0703, device='cuda:0'), tensor(40842.9766, device='cuda:0'), tensor(40729.2109, device='cuda:0')]

Training loss: 0

Prediction time: [datetime.timedelta(seconds=1, microseconds=28682), datetime.timedelta(seconds=1, microseconds=38639), datetime.timedelta(seconds=1, microseconds=34655), datetime.timedelta(seconds=1, microseconds=51584), datetime.timedelta(seconds=1, microseconds=15736), datetime.timedelta(seconds=1, microseconds=21711), datetime.timedelta(seconds=1, microseconds=52580), datetime.timedelta(seconds=1, microseconds=8765), datetime.timedelta(seconds=1, microseconds=38640), datetime.timedelta(seconds=1, microseconds=52581)]

Phi time: [datetime.timedelta(microseconds=232026), datetime.timedelta(microseconds=246964), datetime.timedelta(microseconds=252938), datetime.timedelta(microseconds=235014), datetime.timedelta(microseconds=254929), datetime.timedelta(microseconds=239993), datetime.timedelta(microseconds=238997), datetime.timedelta(microseconds=237005), datetime.timedelta(microseconds=257917), datetime.timedelta(microseconds=239992)]

