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

Output distance: [tensor(38582.5547, device='cuda:0'), tensor(38859.0977, device='cuda:0'), tensor(39500.5664, device='cuda:0'), tensor(39889.0820, device='cuda:0'), tensor(38520.7422, device='cuda:0'), tensor(38506.1328, device='cuda:0'), tensor(38573.6445, device='cuda:0'), tensor(41852.8711, device='cuda:0'), tensor(38723.7695, device='cuda:0'), tensor(39470.4648, device='cuda:0')]

Prediction loss: [tensor(34884.8594, device='cuda:0'), tensor(31031.1152, device='cuda:0'), tensor(38962.2227, device='cuda:0'), tensor(37552.1758, device='cuda:0'), tensor(42827.7969, device='cuda:0'), tensor(38684.2383, device='cuda:0'), tensor(37807.2070, device='cuda:0'), tensor(38105.3555, device='cuda:0'), tensor(42117.1523, device='cuda:0'), tensor(41313.3203, 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': 9, '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': 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': 9, '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')}]

Compressed training loss: [tensor(3329178., device='cuda:0'), tensor(3064214.2500, device='cuda:0'), tensor(3621831.7500, device='cuda:0'), tensor(3492197.7500, device='cuda:0'), tensor(3906338., device='cuda:0'), tensor(3595601.5000, device='cuda:0'), tensor(3553705., device='cuda:0'), tensor(3697659., device='cuda:0'), tensor(3785641.5000, device='cuda:0'), tensor(3916655.5000, device='cuda:0')]

Training loss: 3592231.25

Prediction time: [datetime.timedelta(microseconds=558631), datetime.timedelta(microseconds=600454), datetime.timedelta(microseconds=592486), datetime.timedelta(microseconds=538713), datetime.timedelta(microseconds=487930), datetime.timedelta(microseconds=535729), datetime.timedelta(microseconds=528756), datetime.timedelta(microseconds=579542), datetime.timedelta(microseconds=490915), datetime.timedelta(microseconds=579541)]

Phi time: [datetime.timedelta(seconds=1, microseconds=89032), datetime.timedelta(microseconds=670395), datetime.timedelta(microseconds=586560), datetime.timedelta(microseconds=580669), datetime.timedelta(microseconds=583575), datetime.timedelta(microseconds=581805), datetime.timedelta(microseconds=581988), datetime.timedelta(microseconds=584648), datetime.timedelta(microseconds=579545), datetime.timedelta(microseconds=618645)]

