Special test with strict convergence condition

Precision: [tensor(0.6270, device='cuda:0'), tensor(0.6299, device='cuda:0'), tensor(0.6252, device='cuda:0'), tensor(0.6263, device='cuda:0'), tensor(0.6316, device='cuda:0'), tensor(0.6252, device='cuda:0'), tensor(0.6231, device='cuda:0'), tensor(0.6215, device='cuda:0'), tensor(0.6255, device='cuda:0'), tensor(0.6253, device='cuda:0')]

Output distance: [tensor(4.9606, device='cuda:0'), tensor(4.9564, device='cuda:0'), tensor(4.9625, device='cuda:0'), tensor(4.9604, device='cuda:0'), tensor(4.9504, device='cuda:0'), tensor(4.9638, device='cuda:0'), tensor(4.9711, device='cuda:0'), tensor(4.9748, device='cuda:0'), tensor(4.9659, device='cuda:0'), tensor(4.9659, device='cuda:0')]

Prediction loss: [tensor(18477168., device='cuda:0'), tensor(19346640., device='cuda:0'), tensor(19007132., device='cuda:0'), tensor(19344216., device='cuda:0'), tensor(19279696., device='cuda:0'), tensor(17393072., device='cuda:0'), tensor(18556976., device='cuda:0'), tensor(19101904., device='cuda:0'), tensor(19928084., device='cuda:0'), tensor(17607668., device='cuda:0')]

Others: [{'iter_num': 11, 'num_positive': tensor(5182, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(5128, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(5227, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(5215, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(5147, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(5208, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(5184, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(5194, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(5162, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(5172, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}]

Compressed training loss: [tensor(40884.0781, device='cuda:0'), tensor(40819.5781, device='cuda:0'), tensor(40732.1484, device='cuda:0'), tensor(40845.1289, device='cuda:0'), tensor(40745.0898, device='cuda:0'), tensor(40858.9766, device='cuda:0'), tensor(40752.8945, device='cuda:0'), tensor(40818.2109, device='cuda:0'), tensor(40753.1133, device='cuda:0'), tensor(40652.4805, device='cuda:0')]

Training loss: 0

Prediction time: [datetime.timedelta(seconds=1, microseconds=68469), datetime.timedelta(seconds=1, microseconds=51540), datetime.timedelta(seconds=1, microseconds=59506), datetime.timedelta(seconds=1, microseconds=71455), datetime.timedelta(seconds=1, microseconds=47556), datetime.timedelta(seconds=1, microseconds=90375), datetime.timedelta(seconds=1, microseconds=85397), datetime.timedelta(seconds=1, microseconds=81413), datetime.timedelta(seconds=1, microseconds=69464), datetime.timedelta(seconds=1, microseconds=78426)]

Phi time: [datetime.timedelta(microseconds=235003), datetime.timedelta(microseconds=241974), datetime.timedelta(microseconds=237990), datetime.timedelta(microseconds=252928), datetime.timedelta(microseconds=251933), datetime.timedelta(microseconds=239982), datetime.timedelta(microseconds=233011), datetime.timedelta(microseconds=237991), datetime.timedelta(microseconds=237991), datetime.timedelta(microseconds=236000)]

