Special test with strict convergence condition

Precision: [tensor(0.6839, device='cuda:0'), tensor(0.6831, device='cuda:0'), tensor(0.6857, device='cuda:0'), tensor(0.6886, device='cuda:0'), tensor(0.6847, device='cuda:0'), tensor(0.6860, device='cuda:0'), tensor(0.6847, device='cuda:0'), tensor(0.6889, device='cuda:0'), tensor(0.6844, device='cuda:0'), tensor(0.6847, device='cuda:0')]

Output distance: [tensor(4.9383, device='cuda:0'), tensor(4.9399, device='cuda:0'), tensor(4.9346, device='cuda:0'), tensor(4.9289, device='cuda:0'), tensor(4.9367, device='cuda:0'), tensor(4.9341, device='cuda:0'), tensor(4.9367, device='cuda:0'), tensor(4.9283, device='cuda:0'), tensor(4.9373, device='cuda:0'), tensor(4.9367, device='cuda:0')]

Prediction loss: [tensor(18057354., device='cuda:0'), tensor(18708800., device='cuda:0'), tensor(17002332., device='cuda:0'), tensor(20441576., device='cuda:0'), tensor(18665212., device='cuda:0'), tensor(17768198., device='cuda:0'), tensor(18080508., device='cuda:0'), tensor(19562788., device='cuda:0'), tensor(18790616., device='cuda:0'), tensor(18489420., 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': 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': 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(40889.7461, device='cuda:0'), tensor(40896.5898, device='cuda:0'), tensor(40770.8242, device='cuda:0'), tensor(40871.1641, device='cuda:0'), tensor(40979.2305, device='cuda:0'), tensor(40794.3203, device='cuda:0'), tensor(40852.1523, device='cuda:0'), tensor(40929.1758, device='cuda:0'), tensor(40864.1250, device='cuda:0'), tensor(40870.8711, device='cuda:0')]

Training loss: 0

Prediction time: [datetime.timedelta(seconds=6, microseconds=461872), datetime.timedelta(seconds=6, microseconds=295568), datetime.timedelta(seconds=4, microseconds=89830), datetime.timedelta(seconds=6, microseconds=296566), datetime.timedelta(seconds=6, microseconds=302541), datetime.timedelta(seconds=6, microseconds=377228), datetime.timedelta(seconds=6, microseconds=267687), datetime.timedelta(seconds=6, microseconds=230840), datetime.timedelta(seconds=6, microseconds=389175), datetime.timedelta(seconds=6, microseconds=356315)]

Phi time: [datetime.timedelta(microseconds=346545), datetime.timedelta(microseconds=402312), datetime.timedelta(microseconds=372436), datetime.timedelta(microseconds=359490), datetime.timedelta(microseconds=397332), datetime.timedelta(microseconds=425214), datetime.timedelta(microseconds=379407), datetime.timedelta(microseconds=428202), datetime.timedelta(microseconds=350531), datetime.timedelta(microseconds=335591)]

