Special test with strict convergence condition

Precision: [tensor(0.5552, device='cuda:0'), tensor(0.5556, device='cuda:0'), tensor(0.5547, device='cuda:0'), tensor(0.5526, device='cuda:0'), tensor(0.5551, device='cuda:0'), tensor(0.5575, device='cuda:0'), tensor(0.5543, device='cuda:0'), tensor(0.5516, device='cuda:0'), tensor(0.5551, device='cuda:0'), tensor(0.5533, device='cuda:0')]

Output distance: [tensor(4.9751, device='cuda:0'), tensor(4.9724, device='cuda:0'), tensor(4.9777, device='cuda:0'), tensor(4.9903, device='cuda:0'), tensor(4.9756, device='cuda:0'), tensor(4.9609, device='cuda:0'), tensor(4.9803, device='cuda:0'), tensor(4.9966, device='cuda:0'), tensor(4.9756, device='cuda:0'), tensor(4.9861, device='cuda:0')]

Prediction loss: [tensor(18589960., device='cuda:0'), tensor(19667146., device='cuda:0'), tensor(18215108., device='cuda:0'), tensor(18286096., device='cuda:0'), tensor(17789492., device='cuda:0'), tensor(19212160., device='cuda:0'), tensor(19752374., device='cuda:0'), tensor(17906030., device='cuda:0'), tensor(18181672., device='cuda:0'), tensor(19383450., device='cuda:0')]

Others: [{'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': 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': 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')}]

Compressed training loss: [tensor(40792.8008, device='cuda:0'), tensor(40872.5859, device='cuda:0'), tensor(40747.0547, device='cuda:0'), tensor(40829.7305, device='cuda:0'), tensor(40947.9414, device='cuda:0'), tensor(40843.8828, device='cuda:0'), tensor(40794.6133, device='cuda:0'), tensor(40943.3867, device='cuda:0'), tensor(40819.5234, device='cuda:0'), tensor(40856.4531, device='cuda:0')]

Training loss: 0

Prediction time: [datetime.timedelta(seconds=1, microseconds=120249), datetime.timedelta(seconds=1, microseconds=82409), datetime.timedelta(seconds=1, microseconds=100333), datetime.timedelta(seconds=1, microseconds=85397), datetime.timedelta(seconds=1, microseconds=74441), datetime.timedelta(seconds=1, microseconds=57515), datetime.timedelta(seconds=1, microseconds=91371), datetime.timedelta(seconds=1, microseconds=70396), datetime.timedelta(seconds=1, microseconds=82409), datetime.timedelta(seconds=1, microseconds=106308)]

Phi time: [datetime.timedelta(microseconds=239982), datetime.timedelta(microseconds=239982), datetime.timedelta(microseconds=242970), datetime.timedelta(microseconds=252926), datetime.timedelta(microseconds=239982), datetime.timedelta(microseconds=237991), datetime.timedelta(microseconds=235999), datetime.timedelta(microseconds=238054), datetime.timedelta(microseconds=235999), datetime.timedelta(microseconds=257906)]

