Special test with strict convergence condition

Precision: [tensor(0.2837, device='cuda:0'), tensor(0.2854, device='cuda:0'), tensor(0.2835, device='cuda:0'), tensor(0.2852, device='cuda:0'), tensor(0.2878, device='cuda:0'), tensor(0.2882, device='cuda:0'), tensor(0.2832, device='cuda:0'), tensor(0.2878, device='cuda:0'), tensor(0.2919, device='cuda:0'), tensor(0.2872, device='cuda:0')]

Output distance: [tensor(6.6038, device='cuda:0'), tensor(6.5939, device='cuda:0'), tensor(6.6054, device='cuda:0'), tensor(6.5949, device='cuda:0'), tensor(6.5792, device='cuda:0'), tensor(6.5771, device='cuda:0'), tensor(6.6070, device='cuda:0'), tensor(6.5792, device='cuda:0'), tensor(6.5550, device='cuda:0'), tensor(6.5828, device='cuda:0')]

Prediction loss: [tensor(19766494., device='cuda:0'), tensor(18900038., device='cuda:0'), tensor(18502720., device='cuda:0'), tensor(19089972., device='cuda:0'), tensor(17600226., device='cuda:0'), tensor(17666466., device='cuda:0'), tensor(18701166., device='cuda:0'), tensor(20035178., device='cuda:0'), tensor(18161686., device='cuda:0'), tensor(18886278., device='cuda:0')]

Others: [{'iter_num': 5, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}]

Compressed training loss: [tensor(40738.3320, device='cuda:0'), tensor(40858.2734, device='cuda:0'), tensor(40816.6367, device='cuda:0'), tensor(40916.8320, device='cuda:0'), tensor(40922.4023, device='cuda:0'), tensor(41065.8281, device='cuda:0'), tensor(40936.6523, device='cuda:0'), tensor(40690.3672, device='cuda:0'), tensor(40833.3906, device='cuda:0'), tensor(40652.7461, device='cuda:0')]

Training loss: 0

Prediction time: [datetime.timedelta(seconds=6, microseconds=270406), datetime.timedelta(seconds=6, microseconds=162862), datetime.timedelta(seconds=6, microseconds=210660), datetime.timedelta(seconds=6, microseconds=145935), datetime.timedelta(seconds=6, microseconds=246509), datetime.timedelta(seconds=6, microseconds=254474), datetime.timedelta(seconds=6, microseconds=292313), datetime.timedelta(seconds=6, microseconds=235554), datetime.timedelta(seconds=6, microseconds=359031), datetime.timedelta(seconds=6, microseconds=205681)]

Phi time: [datetime.timedelta(microseconds=240978), datetime.timedelta(microseconds=373417), datetime.timedelta(microseconds=365450), datetime.timedelta(microseconds=331594), datetime.timedelta(microseconds=375407), datetime.timedelta(microseconds=437146), datetime.timedelta(microseconds=340556), datetime.timedelta(microseconds=398311), datetime.timedelta(microseconds=334581), datetime.timedelta(microseconds=365450)]

