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

Output distance: [tensor(30074.2793, device='cuda:0'), tensor(25027.7461, device='cuda:0'), tensor(25619.8926, device='cuda:0'), tensor(24208.2988, device='cuda:0'), tensor(24040.4922, device='cuda:0'), tensor(24422.5898, device='cuda:0'), tensor(23539.5918, device='cuda:0'), tensor(23822.9219, device='cuda:0'), tensor(24517.6289, device='cuda:0'), tensor(23882.5273, device='cuda:0')]

Prediction loss: [tensor(32248.3711, device='cuda:0'), tensor(25098.4375, device='cuda:0'), tensor(26739.8926, device='cuda:0'), tensor(23962.8340, device='cuda:0'), tensor(23852.1836, device='cuda:0'), tensor(24128.7285, device='cuda:0'), tensor(21909.2305, device='cuda:0'), tensor(23916.5898, device='cuda:0'), tensor(23816.4805, device='cuda:0'), tensor(23923.5820, device='cuda:0')]

Others: [{'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': 25, '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': 27, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 23, '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(9042937., device='cuda:0'), tensor(8943471., device='cuda:0'), tensor(9015055., device='cuda:0'), tensor(8916001., device='cuda:0'), tensor(8828034., device='cuda:0'), tensor(8733272., device='cuda:0'), tensor(8537630., device='cuda:0'), tensor(8903434., device='cuda:0'), tensor(8723244., device='cuda:0'), tensor(8888568., device='cuda:0')]

Training loss: 8869705.0

Prediction time: [datetime.timedelta(seconds=1, microseconds=493663), datetime.timedelta(seconds=1, microseconds=527521), datetime.timedelta(seconds=1, microseconds=518558), datetime.timedelta(seconds=1, microseconds=315422), datetime.timedelta(seconds=1, microseconds=524534), datetime.timedelta(seconds=1, microseconds=407033), datetime.timedelta(microseconds=586511), datetime.timedelta(seconds=1, microseconds=235758), datetime.timedelta(seconds=1, microseconds=496654), datetime.timedelta(seconds=1, microseconds=520552)]

Phi time: [datetime.timedelta(seconds=1, microseconds=384144), datetime.timedelta(microseconds=832897), datetime.timedelta(microseconds=780317), datetime.timedelta(microseconds=781943), datetime.timedelta(microseconds=785653), datetime.timedelta(microseconds=778697), datetime.timedelta(microseconds=780010), datetime.timedelta(microseconds=783034), datetime.timedelta(microseconds=804988), datetime.timedelta(microseconds=783017)]

