Special test with strict convergence condition

Precision: [tensor(0.6886, device='cuda:0'), tensor(0.6931, device='cuda:0'), tensor(0.6871, device='cuda:0'), tensor(0.6892, device='cuda:0'), tensor(0.6876, device='cuda:0'), tensor(0.6873, device='cuda:0'), tensor(0.6920, device='cuda:0'), tensor(0.6823, device='cuda:0'), tensor(0.6805, device='cuda:0'), tensor(0.6884, device='cuda:0')]

Output distance: [tensor(4.9289, device='cuda:0'), tensor(4.9199, device='cuda:0'), tensor(4.9320, device='cuda:0'), tensor(4.9278, device='cuda:0'), tensor(4.9310, device='cuda:0'), tensor(4.9315, device='cuda:0'), tensor(4.9220, device='cuda:0'), tensor(4.9415, device='cuda:0'), tensor(4.9451, device='cuda:0'), tensor(4.9294, device='cuda:0')]

Prediction loss: [tensor(19739768., device='cuda:0'), tensor(17883716., device='cuda:0'), tensor(18300368., device='cuda:0'), tensor(19005432., device='cuda:0'), tensor(19330522., device='cuda:0'), tensor(18191520., device='cuda:0'), tensor(18705134., device='cuda:0'), tensor(18168964., device='cuda:0'), tensor(17586380., device='cuda:0'), tensor(18231158., 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(40824.3633, device='cuda:0'), tensor(40746.0508, device='cuda:0'), tensor(40684.1367, device='cuda:0'), tensor(40767.4570, device='cuda:0'), tensor(40718.3750, device='cuda:0'), tensor(40823.7109, device='cuda:0'), tensor(40927.1484, device='cuda:0'), tensor(40826.0547, device='cuda:0'), tensor(40817.2656, device='cuda:0'), tensor(40954.6172, device='cuda:0')]

Training loss: 0

Prediction time: [datetime.timedelta(seconds=1, microseconds=52581), datetime.timedelta(seconds=1, microseconds=24697), datetime.timedelta(seconds=1, microseconds=13744), datetime.timedelta(seconds=1, microseconds=29677), datetime.timedelta(seconds=1, microseconds=24697), datetime.timedelta(seconds=1, microseconds=18723), datetime.timedelta(microseconds=994824), datetime.timedelta(seconds=1, microseconds=21711), datetime.timedelta(seconds=1, microseconds=20715), datetime.timedelta(seconds=1, microseconds=23701)]

Phi time: [datetime.timedelta(microseconds=231030), datetime.timedelta(microseconds=254931), datetime.timedelta(microseconds=233022), datetime.timedelta(microseconds=238001), datetime.timedelta(microseconds=233023), datetime.timedelta(microseconds=255925), datetime.timedelta(microseconds=254929), datetime.timedelta(microseconds=238001), datetime.timedelta(microseconds=237005), datetime.timedelta(microseconds=252939)]

