Precision: [tensor(0.6913, device='cuda:0'), tensor(0.7025, device='cuda:0'), tensor(0.6905, device='cuda:0'), tensor(0.6944, device='cuda:0'), tensor(0.6960, device='cuda:0'), tensor(0.6997, device='cuda:0'), tensor(0.6981, device='cuda:0'), tensor(0.6931, device='cuda:0'), tensor(0.6928, device='cuda:0'), tensor(0.6983, device='cuda:0')]

Output distance: [tensor(4.9236, device='cuda:0'), tensor(4.9010, device='cuda:0'), tensor(4.9252, device='cuda:0'), tensor(4.9173, device='cuda:0'), tensor(4.9142, device='cuda:0'), tensor(4.9068, device='cuda:0'), tensor(4.9099, device='cuda:0'), tensor(4.9199, device='cuda:0'), tensor(4.9205, device='cuda:0'), tensor(4.9094, device='cuda:0')]

Prediction loss: [tensor(18184020., device='cuda:0'), tensor(17682894., device='cuda:0'), tensor(18132256., device='cuda:0'), tensor(18070488., device='cuda:0'), tensor(18330146., device='cuda:0'), tensor(18702874., device='cuda:0'), tensor(19245246., device='cuda:0'), tensor(18146318., device='cuda:0'), tensor(19089300., device='cuda:0'), tensor(18496896., device='cuda:0')]

Others: [{'iter_num': 3, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 3, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 3, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}]

Compressed training loss: [tensor(40837.5000, device='cuda:0'), tensor(40749.1523, device='cuda:0'), tensor(40885.6094, device='cuda:0'), tensor(40810.3633, device='cuda:0'), tensor(40713.9297, device='cuda:0'), tensor(40807.5586, device='cuda:0'), tensor(40831.8203, device='cuda:0'), tensor(40894.2695, device='cuda:0'), tensor(40791.2852, device='cuda:0'), tensor(40879.5430, device='cuda:0')]

Training loss: 0

Prediction time: [datetime.timedelta(microseconds=991003), datetime.timedelta(microseconds=994115), datetime.timedelta(seconds=1, microseconds=14987), datetime.timedelta(seconds=1, microseconds=2067), datetime.timedelta(seconds=1, microseconds=18479), datetime.timedelta(seconds=1, microseconds=7276), datetime.timedelta(microseconds=999000), datetime.timedelta(seconds=1, microseconds=16791), datetime.timedelta(seconds=1, microseconds=9), datetime.timedelta(seconds=1, microseconds=1009)]

Phi time: [datetime.timedelta(microseconds=292841), datetime.timedelta(microseconds=298844), datetime.timedelta(microseconds=286875), datetime.timedelta(microseconds=297759), datetime.timedelta(microseconds=300021), datetime.timedelta(microseconds=300960), datetime.timedelta(microseconds=301008), datetime.timedelta(microseconds=293235), datetime.timedelta(microseconds=306496), datetime.timedelta(microseconds=299038)]

