Precision: [tensor(0.9067, device='cuda:0'), tensor(0.9132, device='cuda:0'), tensor(0.9489, device='cuda:0'), tensor(0.9152, device='cuda:0'), tensor(0.9428, device='cuda:0'), tensor(0.9532, device='cuda:0'), tensor(0.9542, device='cuda:0'), tensor(0.9402, device='cuda:0'), tensor(0.8653, device='cuda:0'), tensor(0.9293, device='cuda:0')]

Output distance: [tensor(2.4909e+08, device='cuda:0'), tensor(11240894., device='cuda:0'), tensor(49596.7852, device='cuda:0'), tensor(1.9435e+08, device='cuda:0'), tensor(7698900., device='cuda:0'), tensor(2714.2773, device='cuda:0'), tensor(22092.9453, device='cuda:0'), tensor(4531045., device='cuda:0'), tensor(4.0172e+08, device='cuda:0'), tensor(15952960., device='cuda:0')]

Prediction loss: [tensor(3.2401e+08, device='cuda:0'), tensor(14246745., device='cuda:0'), tensor(65919.7891, device='cuda:0'), tensor(2.6455e+08, device='cuda:0'), tensor(10163102., device='cuda:0'), tensor(3730.2727, device='cuda:0'), tensor(31196.0879, device='cuda:0'), tensor(5780799.5000, device='cuda:0'), tensor(4.8543e+08, device='cuda:0'), tensor(19137302., device='cuda:0')]

Others: [{'iter_num': 30, 'num_positive': tensor(17983, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(17986, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(17989, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(17982, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(17997, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(17999, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(17996, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(17986, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(17996, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}]

Compressed training loss: [tensor(3655952.7500, device='cuda:0'), tensor(3797932., device='cuda:0'), tensor(3446365.7500, device='cuda:0'), tensor(3778770.5000, device='cuda:0'), tensor(3485517.2500, device='cuda:0'), tensor(3237018., device='cuda:0'), tensor(3419134.5000, device='cuda:0'), tensor(3600375.5000, device='cuda:0'), tensor(4088248., device='cuda:0'), tensor(3807894.5000, device='cuda:0')]

Training loss: 3583194.25

Prediction time: [datetime.timedelta(seconds=1, microseconds=530508), datetime.timedelta(seconds=1, microseconds=577308), datetime.timedelta(seconds=1, microseconds=565361), datetime.timedelta(seconds=1, microseconds=555403), datetime.timedelta(seconds=1, microseconds=553411), datetime.timedelta(seconds=1, microseconds=547435), datetime.timedelta(seconds=1, microseconds=560383), datetime.timedelta(seconds=1, microseconds=558391), datetime.timedelta(seconds=1, microseconds=565361), datetime.timedelta(seconds=1, microseconds=557396)]

Phi time: [datetime.timedelta(seconds=1, microseconds=323454), datetime.timedelta(microseconds=814722), datetime.timedelta(microseconds=742810), datetime.timedelta(microseconds=738805), datetime.timedelta(microseconds=740856), datetime.timedelta(microseconds=742060), datetime.timedelta(microseconds=738115), datetime.timedelta(microseconds=745000), datetime.timedelta(microseconds=742732), datetime.timedelta(microseconds=736177)]

