Special test with strict convergence condition

Precision: [tensor(0.6316, device='cuda:0'), tensor(0.6260, device='cuda:0'), tensor(0.6327, device='cuda:0'), tensor(0.6250, device='cuda:0'), tensor(0.6285, device='cuda:0'), tensor(0.6287, device='cuda:0'), tensor(0.6288, device='cuda:0'), tensor(0.6324, device='cuda:0'), tensor(0.6299, device='cuda:0'), tensor(0.6321, device='cuda:0')]

Output distance: [tensor(4.9160, device='cuda:0'), tensor(4.9331, device='cuda:0'), tensor(4.9131, device='cuda:0'), tensor(4.9352, device='cuda:0'), tensor(4.9252, device='cuda:0'), tensor(4.9212, device='cuda:0'), tensor(4.9215, device='cuda:0'), tensor(4.9152, device='cuda:0'), tensor(4.9212, device='cuda:0'), tensor(4.9139, device='cuda:0')]

Prediction loss: [tensor(17946100., device='cuda:0'), tensor(18914216., device='cuda:0'), tensor(20176818., device='cuda:0'), tensor(19368342., device='cuda:0'), tensor(19478340., device='cuda:0'), tensor(17800462., device='cuda:0'), tensor(17469452., device='cuda:0'), tensor(17491626., device='cuda:0'), tensor(17596824., device='cuda:0'), tensor(17587906., device='cuda:0')]

Others: [{'iter_num': 11, 'num_positive': tensor(5644, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(5639, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(5641, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(5653, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(5645, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(5694, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(5687, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(5623, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(5644, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(5656, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}]

Compressed training loss: [tensor(40927.2227, device='cuda:0'), tensor(40956.1094, device='cuda:0'), tensor(40888.4297, device='cuda:0'), tensor(40970.5703, device='cuda:0'), tensor(40808.2148, device='cuda:0'), tensor(40946.5117, device='cuda:0'), tensor(40915.3633, device='cuda:0'), tensor(40727.8281, device='cuda:0'), tensor(40912.3750, device='cuda:0'), tensor(40959.3281, device='cuda:0')]

Training loss: 0

Prediction time: [datetime.timedelta(seconds=1, microseconds=127220), datetime.timedelta(seconds=1, microseconds=63490), datetime.timedelta(seconds=1, microseconds=59506), datetime.timedelta(seconds=1, microseconds=72452), datetime.timedelta(seconds=1, microseconds=76434), datetime.timedelta(seconds=1, microseconds=84401), datetime.timedelta(seconds=1, microseconds=82409), datetime.timedelta(seconds=1, microseconds=77431), datetime.timedelta(seconds=1, microseconds=75439), datetime.timedelta(seconds=1, microseconds=57515)]

Phi time: [datetime.timedelta(microseconds=238986), datetime.timedelta(microseconds=257906), datetime.timedelta(microseconds=235999), datetime.timedelta(microseconds=239982), datetime.timedelta(microseconds=252928), datetime.timedelta(microseconds=235999), datetime.timedelta(microseconds=255915), datetime.timedelta(microseconds=258902), datetime.timedelta(microseconds=235004), datetime.timedelta(microseconds=238987)]

