Precision: [tensor(0.9995, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9992, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9995, device='cuda:0')]

Output distance: [tensor(22771.0137, device='cuda:0'), tensor(22774.0879, device='cuda:0'), tensor(22774.3809, device='cuda:0'), tensor(22930.7949, device='cuda:0'), tensor(22861.7949, device='cuda:0'), tensor(22785.5898, device='cuda:0'), tensor(22777.1523, device='cuda:0'), tensor(22803.3574, device='cuda:0'), tensor(22881.6816, device='cuda:0'), tensor(22752.0957, device='cuda:0')]

Prediction loss: [tensor(22701.0449, device='cuda:0'), tensor(22427.2109, device='cuda:0'), tensor(22830.7871, device='cuda:0'), tensor(23075.8203, device='cuda:0'), tensor(22815.8828, device='cuda:0'), tensor(22679.8555, device='cuda:0'), tensor(22778.1816, device='cuda:0'), tensor(23595.6055, device='cuda:0'), tensor(22489.2422, device='cuda:0'), tensor(23751.0215, device='cuda:0')]

Others: [{'iter_num': 9, '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': 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': 9, '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': 9, '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': 9, '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')}]

Compressed training loss: [tensor(8843800., device='cuda:0'), tensor(8789536., device='cuda:0'), tensor(8955109., device='cuda:0'), tensor(8955099., device='cuda:0'), tensor(8840714., device='cuda:0'), tensor(8881136., device='cuda:0'), tensor(8901096., device='cuda:0'), tensor(8993136., device='cuda:0'), tensor(8734982., device='cuda:0'), tensor(9100423., device='cuda:0')]

Training loss: 8862336.0

Prediction time: [datetime.timedelta(microseconds=962916), datetime.timedelta(microseconds=988806), datetime.timedelta(microseconds=973874), datetime.timedelta(seconds=1, microseconds=115271), datetime.timedelta(microseconds=979844), datetime.timedelta(microseconds=989802), datetime.timedelta(microseconds=985816), datetime.timedelta(microseconds=980839), datetime.timedelta(microseconds=973869), datetime.timedelta(microseconds=974869)]

Phi time: [datetime.timedelta(seconds=1, microseconds=889074), datetime.timedelta(seconds=1, microseconds=282036), datetime.timedelta(seconds=1, microseconds=282298), datetime.timedelta(seconds=1, microseconds=307316), datetime.timedelta(seconds=1, microseconds=283625), datetime.timedelta(seconds=1, microseconds=314422), datetime.timedelta(seconds=1, microseconds=301481), datetime.timedelta(seconds=1, microseconds=301666), datetime.timedelta(seconds=1, microseconds=304215), datetime.timedelta(seconds=1, microseconds=286528)]

