Precision: [tensor(0.9987, device='cuda:0'), tensor(0.9987, device='cuda:0'), tensor(0.9988, device='cuda:0'), tensor(0.9990, device='cuda:0'), tensor(0.9987, device='cuda:0'), tensor(0.9992, device='cuda:0'), tensor(0.9988, device='cuda:0'), tensor(0.9987, device='cuda:0'), tensor(0.9992, device='cuda:0'), tensor(0.9982, device='cuda:0')]

Output distance: [tensor(24625.6602, device='cuda:0'), tensor(23274.6348, device='cuda:0'), tensor(23687.5098, device='cuda:0'), tensor(26038.7285, device='cuda:0'), tensor(23350.7363, device='cuda:0'), tensor(25241.8535, device='cuda:0'), tensor(23624.6895, device='cuda:0'), tensor(23669.9004, device='cuda:0'), tensor(25037.7988, device='cuda:0'), tensor(25525.6641, device='cuda:0')]

Prediction loss: [tensor(23552.5645, device='cuda:0'), tensor(25320.4844, device='cuda:0'), tensor(22812.0801, device='cuda:0'), tensor(21916.5527, device='cuda:0'), tensor(25381.8984, device='cuda:0'), tensor(20282.1348, device='cuda:0'), tensor(26104.5547, device='cuda:0'), tensor(23411.2070, device='cuda:0'), tensor(23815.4512, device='cuda:0'), tensor(24192.3281, device='cuda:0')]

Others: [{'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')}, {'iter_num': 17, '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': 17, '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': 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')}]

Compressed training loss: [tensor(8679060., device='cuda:0'), tensor(9392528., device='cuda:0'), tensor(8872806., device='cuda:0'), tensor(9315564., device='cuda:0'), tensor(9235796., device='cuda:0'), tensor(8580109., device='cuda:0'), tensor(9529965., device='cuda:0'), tensor(8913075., device='cuda:0'), tensor(9191362., device='cuda:0'), tensor(8677670., device='cuda:0')]

Training loss: 8873500.0

Prediction time: [datetime.timedelta(microseconds=676132), datetime.timedelta(microseconds=530750), datetime.timedelta(microseconds=601451), datetime.timedelta(microseconds=662141), datetime.timedelta(microseconds=523774), datetime.timedelta(microseconds=666173), datetime.timedelta(microseconds=522832), datetime.timedelta(microseconds=571580), datetime.timedelta(microseconds=577496), datetime.timedelta(microseconds=617381)]

Phi time: [datetime.timedelta(microseconds=701058), datetime.timedelta(microseconds=644636), datetime.timedelta(microseconds=614503), datetime.timedelta(microseconds=609952), datetime.timedelta(microseconds=584834), datetime.timedelta(microseconds=581107), datetime.timedelta(microseconds=584251), datetime.timedelta(microseconds=619297), datetime.timedelta(microseconds=623252), datetime.timedelta(microseconds=579709)]

