Special test with strict convergence condition

Precision: [tensor(0.7322, device='cuda:0'), tensor(0.7295, device='cuda:0'), tensor(0.7348, device='cuda:0'), tensor(0.7298, device='cuda:0'), tensor(0.7300, device='cuda:0'), tensor(0.7350, device='cuda:0'), tensor(0.7429, device='cuda:0'), tensor(0.7349, device='cuda:0'), tensor(0.7417, device='cuda:0'), tensor(0.7303, device='cuda:0')]

Output distance: [tensor(5.0147, device='cuda:0'), tensor(5.0147, device='cuda:0'), tensor(5.0100, device='cuda:0'), tensor(5.0186, device='cuda:0'), tensor(5.0158, device='cuda:0'), tensor(5.0105, device='cuda:0'), tensor(5.0026, device='cuda:0'), tensor(5.0097, device='cuda:0'), tensor(5.0016, device='cuda:0'), tensor(5.0173, device='cuda:0')]

Prediction loss: [tensor(17180756., device='cuda:0'), tensor(19248894., device='cuda:0'), tensor(18088638., device='cuda:0'), tensor(18029556., device='cuda:0'), tensor(18011956., device='cuda:0'), tensor(18985866., device='cuda:0'), tensor(19699692., device='cuda:0'), tensor(17828026., device='cuda:0'), tensor(18938094., device='cuda:0'), tensor(18022922., device='cuda:0')]

Others: [{'iter_num': 9, 'num_positive': tensor(2390, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(2418, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(2402, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(2383, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(2404, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(2396, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(2380, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(2403, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(2400, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(2388, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}]

Compressed training loss: [tensor(40900.5078, device='cuda:0'), tensor(40857.7617, device='cuda:0'), tensor(40863.3477, device='cuda:0'), tensor(40765.4180, device='cuda:0'), tensor(40877.7227, device='cuda:0'), tensor(40685.2227, device='cuda:0'), tensor(40783.8984, device='cuda:0'), tensor(40831.8438, device='cuda:0'), tensor(40725.6602, device='cuda:0'), tensor(40846.6836, device='cuda:0')]

Training loss: 0

Prediction time: [datetime.timedelta(seconds=1, microseconds=28682), datetime.timedelta(seconds=1, microseconds=36648), datetime.timedelta(seconds=1, microseconds=14739), datetime.timedelta(seconds=1, microseconds=3787), datetime.timedelta(seconds=1, microseconds=11753), datetime.timedelta(seconds=1, microseconds=27685), datetime.timedelta(seconds=1, microseconds=24697), datetime.timedelta(microseconds=988848), datetime.timedelta(seconds=1, microseconds=33660), datetime.timedelta(seconds=1, microseconds=31668)]

Phi time: [datetime.timedelta(microseconds=236009), datetime.timedelta(microseconds=262896), datetime.timedelta(microseconds=252939), datetime.timedelta(microseconds=256920), datetime.timedelta(microseconds=238997), datetime.timedelta(microseconds=234018), datetime.timedelta(microseconds=257917), datetime.timedelta(microseconds=250948), datetime.timedelta(microseconds=235014), datetime.timedelta(microseconds=256923)]

