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

Output distance: [tensor(23053.0176, device='cuda:0'), tensor(23091.7598, device='cuda:0'), tensor(23187.2695, device='cuda:0'), tensor(23051.8555, device='cuda:0'), tensor(23084.7070, device='cuda:0'), tensor(23193.1113, device='cuda:0'), tensor(23064.6406, device='cuda:0'), tensor(23056.3145, device='cuda:0'), tensor(22999.0859, device='cuda:0'), tensor(23029.7461, device='cuda:0')]

Prediction loss: [tensor(22803.4902, device='cuda:0'), tensor(22800.4297, device='cuda:0'), tensor(22928.4180, device='cuda:0'), tensor(22724.5488, device='cuda:0'), tensor(23902.6875, device='cuda:0'), tensor(21607.3965, device='cuda:0'), tensor(22195.8184, device='cuda:0'), tensor(23067.9492, device='cuda:0'), tensor(23173.7598, device='cuda:0'), tensor(22202.6406, device='cuda:0')]

Others: [{'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': 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': 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')}]

Compressed training loss: [tensor(8853050., device='cuda:0'), tensor(8910700., device='cuda:0'), tensor(8930563., device='cuda:0'), tensor(9024472., device='cuda:0'), tensor(9020156., device='cuda:0'), tensor(8779901., device='cuda:0'), tensor(8789867., device='cuda:0'), tensor(8846560., device='cuda:0'), tensor(8912302., device='cuda:0'), tensor(8690097., device='cuda:0')]

Training loss: 8891346.0

Prediction time: [datetime.timedelta(microseconds=712975), datetime.timedelta(microseconds=655224), datetime.timedelta(microseconds=734884), datetime.timedelta(microseconds=635305), datetime.timedelta(microseconds=658208), datetime.timedelta(microseconds=649247), datetime.timedelta(microseconds=732890), datetime.timedelta(microseconds=663185), datetime.timedelta(microseconds=655220), datetime.timedelta(microseconds=653233)]

Phi time: [datetime.timedelta(seconds=1, microseconds=462432), datetime.timedelta(microseconds=911482), datetime.timedelta(microseconds=860652), datetime.timedelta(microseconds=860178), datetime.timedelta(microseconds=866328), datetime.timedelta(microseconds=861358), datetime.timedelta(microseconds=890412), datetime.timedelta(microseconds=861846), datetime.timedelta(microseconds=865123), datetime.timedelta(microseconds=863502)]

