Special test with strict convergence condition

Precision: [tensor(0.5524, device='cuda:0'), tensor(0.5557, device='cuda:0'), tensor(0.5570, device='cuda:0'), tensor(0.5542, device='cuda:0'), tensor(0.5584, device='cuda:0'), tensor(0.5572, device='cuda:0'), tensor(0.5554, device='cuda:0'), tensor(0.5545, device='cuda:0'), tensor(0.5555, device='cuda:0'), tensor(0.5538, device='cuda:0')]

Output distance: [tensor(4.9919, device='cuda:0'), tensor(4.9719, device='cuda:0'), tensor(4.9640, device='cuda:0'), tensor(4.9808, device='cuda:0'), tensor(4.9556, device='cuda:0'), tensor(4.9630, device='cuda:0'), tensor(4.9735, device='cuda:0'), tensor(4.9793, device='cuda:0'), tensor(4.9730, device='cuda:0'), tensor(4.9835, device='cuda:0')]

Prediction loss: [tensor(18516310., device='cuda:0'), tensor(18354876., device='cuda:0'), tensor(19443226., device='cuda:0'), tensor(19593220., device='cuda:0'), tensor(18791068., device='cuda:0'), tensor(17623058., device='cuda:0'), tensor(19013162., device='cuda:0'), tensor(17838648., device='cuda:0'), tensor(18871022., device='cuda:0'), tensor(18152382., device='cuda:0')]

Others: [{'iter_num': 11, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 11, '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': 11, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 11, '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(40743.9180, device='cuda:0'), tensor(40821.0547, device='cuda:0'), tensor(40730.5781, device='cuda:0'), tensor(40739.9141, device='cuda:0'), tensor(40842.7656, device='cuda:0'), tensor(40754.5273, device='cuda:0'), tensor(40817.7930, device='cuda:0'), tensor(40873.2070, device='cuda:0'), tensor(40897.9102, device='cuda:0'), tensor(40870.2852, device='cuda:0')]

Training loss: 0

Prediction time: [datetime.timedelta(seconds=1, microseconds=108300), datetime.timedelta(seconds=1, microseconds=123236), datetime.timedelta(seconds=1, microseconds=97345), datetime.timedelta(seconds=1, microseconds=100333), datetime.timedelta(seconds=1, microseconds=83404), datetime.timedelta(seconds=1, microseconds=105312), datetime.timedelta(seconds=1, microseconds=116265), datetime.timedelta(seconds=1, microseconds=98342), datetime.timedelta(seconds=1, microseconds=94359), datetime.timedelta(seconds=1, microseconds=102325)]

Phi time: [datetime.timedelta(microseconds=238987), datetime.timedelta(microseconds=248945), datetime.timedelta(microseconds=252928), datetime.timedelta(microseconds=234009), datetime.timedelta(microseconds=258902), datetime.timedelta(microseconds=254919), datetime.timedelta(microseconds=253923), datetime.timedelta(microseconds=235999), datetime.timedelta(microseconds=235999), datetime.timedelta(microseconds=257907)]

