Precision: [tensor(0.9998, device='cuda:0'), tensor(0.9992, device='cuda:0'), tensor(0.9997, device='cuda:0'), tensor(0.9997, device='cuda:0'), tensor(0.9998, device='cuda:0'), tensor(0.9997, device='cuda:0'), tensor(0.9997, device='cuda:0'), tensor(0.9997, device='cuda:0'), tensor(0.9998, device='cuda:0'), tensor(0.9993, device='cuda:0')]

Output distance: [tensor(31914.1816, device='cuda:0'), tensor(24472.0684, device='cuda:0'), tensor(24771.5332, device='cuda:0'), tensor(25978.2910, device='cuda:0'), tensor(23613.5938, device='cuda:0'), tensor(23997.1855, device='cuda:0'), tensor(24501.2363, device='cuda:0'), tensor(31887.6133, device='cuda:0'), tensor(26580.7188, device='cuda:0'), tensor(35219.1992, device='cuda:0')]

Prediction loss: [tensor(33912.1992, device='cuda:0'), tensor(23294.3887, device='cuda:0'), tensor(23105.2402, device='cuda:0'), tensor(26414.9004, device='cuda:0'), tensor(24177.9258, device='cuda:0'), tensor(22979.8750, device='cuda:0'), tensor(24489.7656, device='cuda:0'), tensor(34785.4180, device='cuda:0'), tensor(28068.6484, device='cuda:0'), tensor(40568.9531, device='cuda:0')]

Others: [{'iter_num': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, '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': 21, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}]

Compressed training loss: [tensor(8865503., device='cuda:0'), tensor(8741439., device='cuda:0'), tensor(8466810., device='cuda:0'), tensor(8704923., device='cuda:0'), tensor(8945663., device='cuda:0'), tensor(8779048., device='cuda:0'), tensor(9039679., device='cuda:0'), tensor(8977619., device='cuda:0'), tensor(9013454., device='cuda:0'), tensor(9529405., device='cuda:0')]

Training loss: 8860352.0

Prediction time: [datetime.timedelta(seconds=1, microseconds=380197), datetime.timedelta(seconds=1, microseconds=416050), datetime.timedelta(seconds=1, microseconds=415055), datetime.timedelta(seconds=1, microseconds=432980), datetime.timedelta(microseconds=709024), datetime.timedelta(seconds=1, microseconds=93407), datetime.timedelta(seconds=1, microseconds=394124), datetime.timedelta(seconds=1, microseconds=409023), datetime.timedelta(seconds=1, microseconds=413010), datetime.timedelta(seconds=1, microseconds=412014)]

Phi time: [datetime.timedelta(seconds=1, microseconds=318144), datetime.timedelta(microseconds=793372), datetime.timedelta(microseconds=725021), datetime.timedelta(microseconds=727217), datetime.timedelta(microseconds=725425), datetime.timedelta(microseconds=731651), datetime.timedelta(microseconds=727316), datetime.timedelta(microseconds=728807), datetime.timedelta(microseconds=723187), datetime.timedelta(microseconds=722656)]

