Special test with strict convergence condition

Precision: [tensor(0.6941, device='cuda:0'), tensor(0.6831, device='cuda:0'), tensor(0.6844, device='cuda:0'), tensor(0.6831, device='cuda:0'), tensor(0.6884, device='cuda:0'), tensor(0.6847, device='cuda:0'), tensor(0.6892, device='cuda:0'), tensor(0.6886, device='cuda:0'), tensor(0.6886, device='cuda:0'), tensor(0.6894, device='cuda:0')]

Output distance: [tensor(4.9178, device='cuda:0'), tensor(4.9399, device='cuda:0'), tensor(4.9373, device='cuda:0'), tensor(4.9399, device='cuda:0'), tensor(4.9294, device='cuda:0'), tensor(4.9367, device='cuda:0'), tensor(4.9278, device='cuda:0'), tensor(4.9289, device='cuda:0'), tensor(4.9289, device='cuda:0'), tensor(4.9273, device='cuda:0')]

Prediction loss: [tensor(17837590., device='cuda:0'), tensor(20277280., device='cuda:0'), tensor(18753452., device='cuda:0'), tensor(17850898., device='cuda:0'), tensor(18527458., device='cuda:0'), tensor(18164142., device='cuda:0'), tensor(19611658., device='cuda:0'), tensor(19255266., device='cuda:0'), tensor(18238590., device='cuda:0'), tensor(18119754., device='cuda:0')]

Others: [{'iter_num': 9, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}]

Compressed training loss: [tensor(40619.8125, device='cuda:0'), tensor(40666.2891, device='cuda:0'), tensor(40915.6992, device='cuda:0'), tensor(40908.3320, device='cuda:0'), tensor(40796.0898, device='cuda:0'), tensor(40867.5078, device='cuda:0'), tensor(40753.8047, device='cuda:0'), tensor(40794.5312, device='cuda:0'), tensor(40913.4375, device='cuda:0'), tensor(40896.9453, device='cuda:0')]

Training loss: 0

Prediction time: [datetime.timedelta(seconds=1, microseconds=44615), datetime.timedelta(seconds=1, microseconds=51584), datetime.timedelta(seconds=1, microseconds=46607), datetime.timedelta(seconds=1, microseconds=32666), datetime.timedelta(seconds=1, microseconds=31668), datetime.timedelta(seconds=1, microseconds=30674), datetime.timedelta(seconds=1, microseconds=62539), datetime.timedelta(seconds=1, microseconds=31668), datetime.timedelta(seconds=1, microseconds=45610), datetime.timedelta(seconds=1, microseconds=20714)]

Phi time: [datetime.timedelta(microseconds=239991), datetime.timedelta(microseconds=250946), datetime.timedelta(microseconds=252938), datetime.timedelta(microseconds=257917), datetime.timedelta(microseconds=238002), datetime.timedelta(microseconds=243975), datetime.timedelta(microseconds=234018), datetime.timedelta(microseconds=263892), datetime.timedelta(microseconds=257917), datetime.timedelta(microseconds=253935)]

