Special test with strict convergence condition

Precision: [tensor(0.5537, device='cuda:0'), tensor(0.5525, device='cuda:0'), tensor(0.5526, device='cuda:0'), tensor(0.5489, device='cuda:0'), tensor(0.5474, device='cuda:0'), tensor(0.5515, device='cuda:0'), tensor(0.5547, device='cuda:0'), tensor(0.5517, device='cuda:0'), tensor(0.5519, device='cuda:0'), tensor(0.5499, device='cuda:0')]

Output distance: [tensor(4.9840, device='cuda:0'), tensor(4.9913, device='cuda:0'), tensor(4.9908, device='cuda:0'), tensor(5.0129, device='cuda:0'), tensor(5.0218, device='cuda:0'), tensor(4.9971, device='cuda:0'), tensor(4.9777, device='cuda:0'), tensor(4.9961, device='cuda:0'), tensor(4.9945, device='cuda:0'), tensor(5.0066, device='cuda:0')]

Prediction loss: [tensor(19112220., device='cuda:0'), tensor(19180758., device='cuda:0'), tensor(19587708., device='cuda:0'), tensor(17322930., device='cuda:0'), tensor(19417664., device='cuda:0'), tensor(18274190., device='cuda:0'), tensor(19103886., device='cuda:0'), tensor(19362392., device='cuda:0'), tensor(19345182., device='cuda:0'), tensor(20747214., device='cuda:0')]

Others: [{'iter_num': 7, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}]

Compressed training loss: [tensor(40777.8867, device='cuda:0'), tensor(40878.3672, device='cuda:0'), tensor(41131.3086, device='cuda:0'), tensor(40700.0625, device='cuda:0'), tensor(40772.2031, device='cuda:0'), tensor(40801.3047, device='cuda:0'), tensor(40661.8086, device='cuda:0'), tensor(40867.0156, device='cuda:0'), tensor(40841.0078, device='cuda:0'), tensor(40786.9570, device='cuda:0')]

Training loss: 0

Prediction time: [datetime.timedelta(seconds=1, microseconds=102326), datetime.timedelta(seconds=1, microseconds=94358), datetime.timedelta(seconds=1, microseconds=99338), datetime.timedelta(seconds=1, microseconds=87388), datetime.timedelta(seconds=1, microseconds=90379), datetime.timedelta(seconds=1, microseconds=62493), datetime.timedelta(seconds=1, microseconds=103321), datetime.timedelta(seconds=1, microseconds=100333), datetime.timedelta(seconds=1, microseconds=92366), datetime.timedelta(seconds=1, microseconds=86392)]

Phi time: [datetime.timedelta(microseconds=372420), datetime.timedelta(microseconds=260894), datetime.timedelta(microseconds=235998), datetime.timedelta(microseconds=246953), datetime.timedelta(microseconds=245953), datetime.timedelta(microseconds=251932), datetime.timedelta(microseconds=230025), datetime.timedelta(microseconds=232016), datetime.timedelta(microseconds=232016), datetime.timedelta(microseconds=234008)]

