Special test with strict convergence condition

Precision: [tensor(0.5519, device='cuda:0'), tensor(0.5506, device='cuda:0'), tensor(0.5518, device='cuda:0'), tensor(0.5501, device='cuda:0'), tensor(0.5498, device='cuda:0'), tensor(0.5510, device='cuda:0'), tensor(0.5502, device='cuda:0'), tensor(0.5582, device='cuda:0'), tensor(0.5505, device='cuda:0'), tensor(0.5519, device='cuda:0')]

Output distance: [tensor(4.9945, device='cuda:0'), tensor(5.0024, device='cuda:0'), tensor(4.9955, device='cuda:0'), tensor(5.0055, device='cuda:0'), tensor(5.0076, device='cuda:0'), tensor(5.0003, device='cuda:0'), tensor(5.0050, device='cuda:0'), tensor(4.9567, device='cuda:0'), tensor(5.0034, device='cuda:0'), tensor(4.9945, device='cuda:0')]

Prediction loss: [tensor(18481204., device='cuda:0'), tensor(19168098., device='cuda:0'), tensor(18908606., device='cuda:0'), tensor(18142582., device='cuda:0'), tensor(18593922., device='cuda:0'), tensor(17154014., device='cuda:0'), tensor(18469150., device='cuda:0'), tensor(17817282., device='cuda:0'), tensor(17968342., device='cuda:0'), tensor(18722434., device='cuda:0')]

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

Compressed training loss: [tensor(40668.0820, device='cuda:0'), tensor(41021.9805, device='cuda:0'), tensor(40792.1289, device='cuda:0'), tensor(40819.3555, device='cuda:0'), tensor(40850.5977, device='cuda:0'), tensor(40810.9492, device='cuda:0'), tensor(40806.6094, device='cuda:0'), tensor(40870.7852, device='cuda:0'), tensor(40916.5742, device='cuda:0'), tensor(40867.1484, device='cuda:0')]

Training loss: 0

Prediction time: [datetime.timedelta(seconds=11, microseconds=14287), datetime.timedelta(seconds=8, microseconds=704086), datetime.timedelta(seconds=11, microseconds=96937), datetime.timedelta(seconds=11, microseconds=157679), datetime.timedelta(seconds=8, microseconds=727984), datetime.timedelta(seconds=8, microseconds=800677), datetime.timedelta(seconds=11, microseconds=56110), datetime.timedelta(seconds=8, microseconds=907224), datetime.timedelta(seconds=13, microseconds=416102), datetime.timedelta(seconds=8, microseconds=671225)]

Phi time: [datetime.timedelta(microseconds=367442), datetime.timedelta(microseconds=343543), datetime.timedelta(microseconds=366445), datetime.timedelta(microseconds=363458), datetime.timedelta(microseconds=363458), datetime.timedelta(microseconds=331593), datetime.timedelta(microseconds=297738), datetime.timedelta(microseconds=310682), datetime.timedelta(microseconds=332589), datetime.timedelta(microseconds=364454)]

