Precision: [tensor(0.9993, device='cuda:0'), tensor(0.9997, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9997, device='cuda:0'), tensor(0.9992, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9998, device='cuda:0'), tensor(0.9992, device='cuda:0'), tensor(0.9995, device='cuda:0')]

Output distance: [tensor(136960.9844, device='cuda:0'), tensor(137130.0312, device='cuda:0'), tensor(136923.3125, device='cuda:0'), tensor(136891.2031, device='cuda:0'), tensor(136889.6875, device='cuda:0'), tensor(137138.1562, device='cuda:0'), tensor(136928.1406, device='cuda:0'), tensor(137382.1094, device='cuda:0'), tensor(137047.5781, device='cuda:0'), tensor(137394.4375, device='cuda:0')]

Prediction loss: [tensor(131342.5469, device='cuda:0'), tensor(134426.1094, device='cuda:0'), tensor(134357., device='cuda:0'), tensor(132411.9844, device='cuda:0'), tensor(131021.5859, device='cuda:0'), tensor(136174.2812, device='cuda:0'), tensor(135479.8438, device='cuda:0'), tensor(134428.5000, device='cuda:0'), tensor(137461.7500, device='cuda:0'), tensor(136461.8594, 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': 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(1.9101e+08, device='cuda:0'), tensor(1.9377e+08, device='cuda:0'), tensor(1.9154e+08, device='cuda:0'), tensor(1.8989e+08, device='cuda:0'), tensor(1.9018e+08, device='cuda:0'), tensor(1.9287e+08, device='cuda:0'), tensor(1.9209e+08, device='cuda:0'), tensor(1.9253e+08, device='cuda:0'), tensor(1.9413e+08, device='cuda:0'), tensor(1.9322e+08, device='cuda:0')]

Training loss: 191943440.0

Prediction time: [datetime.timedelta(microseconds=775732), datetime.timedelta(microseconds=700052), datetime.timedelta(microseconds=708019), datetime.timedelta(microseconds=795651), datetime.timedelta(microseconds=695067), datetime.timedelta(microseconds=712003), datetime.timedelta(microseconds=697065), datetime.timedelta(microseconds=712998), datetime.timedelta(microseconds=698061), datetime.timedelta(microseconds=700053)]

Phi time: [datetime.timedelta(seconds=1, microseconds=546927), datetime.timedelta(microseconds=977348), datetime.timedelta(microseconds=941820), datetime.timedelta(microseconds=944091), datetime.timedelta(microseconds=942061), datetime.timedelta(microseconds=941839), datetime.timedelta(microseconds=935230), datetime.timedelta(microseconds=935914), datetime.timedelta(microseconds=936329), datetime.timedelta(microseconds=934270)]

