Precision: [tensor(0.4319, device='cuda:0'), tensor(0.4279, device='cuda:0'), tensor(0.4325, device='cuda:0'), tensor(0.4322, device='cuda:0'), tensor(0.4358, device='cuda:0'), tensor(0.4199, device='cuda:0'), tensor(0.4358, device='cuda:0'), tensor(0.4326, device='cuda:0'), tensor(0.4362, device='cuda:0'), tensor(0.4362, device='cuda:0')]
Output distance: [tensor(19.4338, device='cuda:0'), tensor(19.4583, device='cuda:0'), tensor(19.4305, device='cuda:0'), tensor(19.4323, device='cuda:0'), tensor(19.4105, device='cuda:0'), tensor(19.5060, device='cuda:0'), tensor(19.4108, device='cuda:0'), tensor(19.4296, device='cuda:0'), tensor(19.4081, device='cuda:0'), tensor(19.4084, device='cuda:0')]
Prediction loss: [tensor(104.9070, device='cuda:0'), tensor(104.1363, device='cuda:0'), tensor(105.4208, device='cuda:0'), tensor(105.2330, device='cuda:0'), tensor(104.2910, device='cuda:0'), tensor(104.9432, device='cuda:0'), tensor(105.1338, device='cuda:0'), tensor(104.4089, device='cuda:0'), tensor(104.3028, device='cuda:0'), tensor(104.8334, device='cuda:0')]
Others: [{'iter_num': 30, 'num_positive': tensor(19848, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(19848, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(19848, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(19848, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(19848, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(19848, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(19848, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(19848, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(19848, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(19848, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}]
Compressed training loss: [tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0')]
Training loss: 0
Prediction time: [datetime.timedelta(seconds=4, microseconds=328036), datetime.timedelta(seconds=4, microseconds=328197), datetime.timedelta(seconds=4, microseconds=338728), datetime.timedelta(seconds=4, microseconds=333309), datetime.timedelta(seconds=4, microseconds=317383), datetime.timedelta(seconds=4, microseconds=306680), datetime.timedelta(seconds=4, microseconds=343828), datetime.timedelta(seconds=4, microseconds=314506), datetime.timedelta(seconds=4, microseconds=310189), datetime.timedelta(seconds=4, microseconds=317106)]
Phi time: [datetime.timedelta(seconds=97, microseconds=593435), datetime.timedelta(seconds=97, microseconds=549398), datetime.timedelta(seconds=97, microseconds=501388), datetime.timedelta(seconds=97, microseconds=327638), datetime.timedelta(seconds=97, microseconds=588419), datetime.timedelta(seconds=97, microseconds=409879), datetime.timedelta(seconds=97, microseconds=438263), datetime.timedelta(seconds=97, microseconds=485541), datetime.timedelta(seconds=97, microseconds=533274), datetime.timedelta(seconds=97, microseconds=363788)]
