Precision: [tensor(0.9998, device='cuda:0'), tensor(1., device='cuda:0'), tensor(0.9997, device='cuda:0'), tensor(0.9998, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9998, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9922, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(1., device='cuda:0')]

Output distance: [tensor(142184.0625, device='cuda:0'), tensor(142578.6406, device='cuda:0'), tensor(143325.0938, device='cuda:0'), tensor(142183.4688, device='cuda:0'), tensor(146720.6094, device='cuda:0'), tensor(142525.2344, device='cuda:0'), tensor(144219.5156, device='cuda:0'), tensor(159772.0156, device='cuda:0'), tensor(143803.8438, device='cuda:0'), tensor(149655.1562, device='cuda:0')]

Prediction loss: [tensor(129432.2031, device='cuda:0'), tensor(130295.1797, device='cuda:0'), tensor(139215.5000, device='cuda:0'), tensor(133456.5938, device='cuda:0'), tensor(148444.7812, device='cuda:0'), tensor(136168.2188, device='cuda:0'), tensor(137430.8906, device='cuda:0'), tensor(157327.9062, device='cuda:0'), tensor(134033.3594, device='cuda:0'), tensor(143212.9375, device='cuda:0')]

Others: [{'iter_num': 15, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 17, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 29, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}]

Compressed training loss: [tensor(1.8461e+08, device='cuda:0'), tensor(1.8988e+08, device='cuda:0'), tensor(1.9532e+08, device='cuda:0'), tensor(1.8818e+08, device='cuda:0'), tensor(1.9435e+08, device='cuda:0'), tensor(1.9006e+08, device='cuda:0'), tensor(1.8918e+08, device='cuda:0'), tensor(1.9735e+08, device='cuda:0'), tensor(1.8838e+08, device='cuda:0'), tensor(1.8945e+08, device='cuda:0')]

Training loss: 191267040.0

Prediction time: [datetime.timedelta(microseconds=837447), datetime.timedelta(seconds=1, microseconds=422965), datetime.timedelta(seconds=1, microseconds=416991), datetime.timedelta(microseconds=946039), datetime.timedelta(seconds=1, microseconds=384133), datetime.timedelta(seconds=1, microseconds=426948), datetime.timedelta(seconds=1, microseconds=420976), datetime.timedelta(seconds=1, microseconds=416991), datetime.timedelta(seconds=1, microseconds=425952), datetime.timedelta(seconds=1, microseconds=435912)]

Phi time: [datetime.timedelta(seconds=1, microseconds=332920), datetime.timedelta(microseconds=801057), datetime.timedelta(microseconds=734158), datetime.timedelta(microseconds=730387), datetime.timedelta(microseconds=731517), datetime.timedelta(microseconds=728828), datetime.timedelta(microseconds=729509), datetime.timedelta(microseconds=738655), datetime.timedelta(microseconds=724901), datetime.timedelta(microseconds=733466)]

