Precision: [tensor(0.9993, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9997, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9998, device='cuda:0'), tensor(0.9985, device='cuda:0'), tensor(0.9997, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9983, device='cuda:0')]

Output distance: [tensor(143828.3438, device='cuda:0'), tensor(142422.9375, device='cuda:0'), tensor(140205.3750, device='cuda:0'), tensor(143604.6094, device='cuda:0'), tensor(148022.3750, device='cuda:0'), tensor(140645.8281, device='cuda:0'), tensor(146468.9531, device='cuda:0'), tensor(141916.8906, device='cuda:0'), tensor(141934.4375, device='cuda:0'), tensor(153989.4844, device='cuda:0')]

Prediction loss: [tensor(140053.5625, device='cuda:0'), tensor(130212.4453, device='cuda:0'), tensor(129864.6719, device='cuda:0'), tensor(146238.3125, device='cuda:0'), tensor(136985.7500, device='cuda:0'), tensor(150579.7812, device='cuda:0'), tensor(126623.8047, device='cuda:0'), tensor(130572.2891, device='cuda:0'), tensor(143273.4844, device='cuda:0'), tensor(147470.4688, device='cuda:0')]

Others: [{'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': 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': 15, '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': 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': 11, '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')}]

Compressed training loss: [tensor(1.9618e+08, device='cuda:0'), tensor(1.8831e+08, device='cuda:0'), tensor(1.9295e+08, device='cuda:0'), tensor(1.9542e+08, device='cuda:0'), tensor(1.9959e+08, device='cuda:0'), tensor(1.9638e+08, device='cuda:0'), tensor(1.8390e+08, device='cuda:0'), tensor(1.9000e+08, device='cuda:0'), tensor(1.9439e+08, device='cuda:0'), tensor(2.0145e+08, device='cuda:0')]

Training loss: 191514144.0

Prediction time: [datetime.timedelta(microseconds=546681), datetime.timedelta(microseconds=635306), datetime.timedelta(microseconds=591492), datetime.timedelta(microseconds=593481), datetime.timedelta(microseconds=682109), datetime.timedelta(microseconds=523779), datetime.timedelta(microseconds=630327), datetime.timedelta(microseconds=578546), datetime.timedelta(microseconds=583525), datetime.timedelta(microseconds=682108)]

Phi time: [datetime.timedelta(seconds=1, microseconds=274351), datetime.timedelta(microseconds=737448), datetime.timedelta(microseconds=653219), datetime.timedelta(microseconds=656683), datetime.timedelta(microseconds=657758), datetime.timedelta(microseconds=654567), datetime.timedelta(microseconds=658436), datetime.timedelta(microseconds=654770), datetime.timedelta(microseconds=661017), datetime.timedelta(microseconds=658533)]

