Special test with strict convergence condition

Precision: [tensor(0.6897, device='cuda:0'), tensor(0.6899, device='cuda:0'), tensor(0.6886, device='cuda:0'), tensor(0.6970, device='cuda:0'), tensor(0.6871, device='cuda:0'), tensor(0.6905, device='cuda:0'), tensor(0.6957, device='cuda:0'), tensor(0.6865, device='cuda:0'), tensor(0.6857, device='cuda:0'), tensor(0.6944, device='cuda:0')]

Output distance: [tensor(4.9268, device='cuda:0'), tensor(4.9262, device='cuda:0'), tensor(4.9289, device='cuda:0'), tensor(4.9121, device='cuda:0'), tensor(4.9320, device='cuda:0'), tensor(4.9252, device='cuda:0'), tensor(4.9147, device='cuda:0'), tensor(4.9331, device='cuda:0'), tensor(4.9346, device='cuda:0'), tensor(4.9173, device='cuda:0')]

Prediction loss: [tensor(19918100., device='cuda:0'), tensor(17349838., device='cuda:0'), tensor(18266592., device='cuda:0'), tensor(18232562., device='cuda:0'), tensor(19138586., device='cuda:0'), tensor(18261710., device='cuda:0'), tensor(18255182., device='cuda:0'), tensor(16894338., device='cuda:0'), tensor(18905398., device='cuda:0'), tensor(17737698., device='cuda:0')]

Others: [{'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': 7, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 11, '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': 11, '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': 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')}]

Compressed training loss: [tensor(40754.1133, device='cuda:0'), tensor(40838.5703, device='cuda:0'), tensor(40926.8359, device='cuda:0'), tensor(40962.4453, device='cuda:0'), tensor(40789.9570, device='cuda:0'), tensor(40893.1328, device='cuda:0'), tensor(40637.1484, device='cuda:0'), tensor(40941.0312, device='cuda:0'), tensor(40809.6172, device='cuda:0'), tensor(40847.5469, device='cuda:0')]

Training loss: 0

Prediction time: [datetime.timedelta(seconds=1, microseconds=177007), datetime.timedelta(seconds=1, microseconds=132199), datetime.timedelta(seconds=1, microseconds=68468), datetime.timedelta(seconds=1, microseconds=6731), datetime.timedelta(seconds=1, microseconds=62494), datetime.timedelta(seconds=1, microseconds=36603), datetime.timedelta(seconds=1, microseconds=55523), datetime.timedelta(seconds=1, microseconds=29633), datetime.timedelta(seconds=1, microseconds=18680), datetime.timedelta(seconds=1, microseconds=33616)]

Phi time: [datetime.timedelta(microseconds=480961), datetime.timedelta(microseconds=278817), datetime.timedelta(microseconds=275830), datetime.timedelta(microseconds=249939), datetime.timedelta(microseconds=236994), datetime.timedelta(microseconds=250936), datetime.timedelta(microseconds=235004), datetime.timedelta(microseconds=234007), datetime.timedelta(microseconds=256912), datetime.timedelta(microseconds=252928)]

