Precision: [tensor(0.9998, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9990, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9990, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9990, device='cuda:0')]

Output distance: [tensor(150041.2188, device='cuda:0'), tensor(152037.8594, device='cuda:0'), tensor(146430.9375, device='cuda:0'), tensor(145962.7969, device='cuda:0'), tensor(147739.8438, device='cuda:0'), tensor(145516.8438, device='cuda:0'), tensor(152202.5781, device='cuda:0'), tensor(147956.5156, device='cuda:0'), tensor(146682.3281, device='cuda:0'), tensor(145608.6562, device='cuda:0')]

Prediction loss: [tensor(137212.9219, device='cuda:0'), tensor(135051.0625, device='cuda:0'), tensor(137707.2344, device='cuda:0'), tensor(135168.4375, device='cuda:0'), tensor(136202.9375, device='cuda:0'), tensor(126140.4609, device='cuda:0'), tensor(141301.6250, device='cuda:0'), tensor(144942.0469, device='cuda:0'), tensor(146494.6875, device='cuda:0'), tensor(156944.3125, device='cuda:0')]

Others: [{'iter_num': 13, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 13, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 13, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 13, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 13, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 15, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 13, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 13, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}]

Compressed training loss: [tensor(1.8868e+08, device='cuda:0'), tensor(1.9068e+08, device='cuda:0'), tensor(1.8362e+08, device='cuda:0'), tensor(1.8787e+08, device='cuda:0'), tensor(1.9122e+08, device='cuda:0'), tensor(1.8183e+08, device='cuda:0'), tensor(1.9136e+08, device='cuda:0'), tensor(1.9317e+08, device='cuda:0'), tensor(1.9891e+08, device='cuda:0'), tensor(2.0020e+08, device='cuda:0')]

Training loss: 190751888.0

Prediction time: [datetime.timedelta(microseconds=499988), datetime.timedelta(microseconds=550598), datetime.timedelta(microseconds=527101), datetime.timedelta(microseconds=499018), datetime.timedelta(microseconds=534908), datetime.timedelta(microseconds=540757), datetime.timedelta(microseconds=585850), datetime.timedelta(microseconds=529787), datetime.timedelta(microseconds=491894), datetime.timedelta(microseconds=538311)]

Phi time: [datetime.timedelta(seconds=1, microseconds=69016), datetime.timedelta(microseconds=613969), datetime.timedelta(microseconds=557097), datetime.timedelta(microseconds=548949), datetime.timedelta(microseconds=560864), datetime.timedelta(microseconds=580239), datetime.timedelta(microseconds=546776), datetime.timedelta(microseconds=556929), datetime.timedelta(microseconds=558876), datetime.timedelta(microseconds=558270)]

