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

Output distance: [tensor(141594.1875, device='cuda:0'), tensor(141427.3750, device='cuda:0'), tensor(141489.1719, device='cuda:0'), tensor(141771.7344, device='cuda:0'), tensor(141550.5312, device='cuda:0'), tensor(141517.1406, device='cuda:0'), tensor(141449.9688, device='cuda:0'), tensor(141454.4688, device='cuda:0'), tensor(141670.8438, device='cuda:0'), tensor(141583.8125, device='cuda:0')]

Prediction loss: [tensor(139252.0469, device='cuda:0'), tensor(140504.0156, device='cuda:0'), tensor(137753.2188, device='cuda:0'), tensor(136669.0938, device='cuda:0'), tensor(141352.7188, device='cuda:0'), tensor(137115.3438, device='cuda:0'), tensor(139489.0625, device='cuda:0'), tensor(140472.9531, device='cuda:0'), tensor(139771.5469, device='cuda:0'), tensor(141706.5000, 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(1.9146e+08, device='cuda:0'), tensor(1.9254e+08, device='cuda:0'), tensor(1.9010e+08, device='cuda:0'), tensor(1.8920e+08, device='cuda:0'), tensor(1.9177e+08, device='cuda:0'), tensor(1.9015e+08, device='cuda:0'), tensor(1.9041e+08, device='cuda:0'), tensor(1.9121e+08, device='cuda:0'), tensor(1.9092e+08, device='cuda:0'), tensor(1.9222e+08, device='cuda:0')]

Training loss: 191171856.0

Prediction time: [datetime.timedelta(microseconds=958963), datetime.timedelta(microseconds=992821), datetime.timedelta(microseconds=975891), datetime.timedelta(seconds=1, microseconds=99372), datetime.timedelta(microseconds=962946), datetime.timedelta(microseconds=975892), datetime.timedelta(microseconds=970912), datetime.timedelta(microseconds=973901), datetime.timedelta(microseconds=966929), datetime.timedelta(microseconds=969915)]

Phi time: [datetime.timedelta(seconds=1, microseconds=889022), datetime.timedelta(seconds=1, microseconds=264751), datetime.timedelta(seconds=1, microseconds=310209), datetime.timedelta(seconds=1, microseconds=281231), datetime.timedelta(seconds=1, microseconds=273015), datetime.timedelta(seconds=1, microseconds=268713), datetime.timedelta(seconds=1, microseconds=275877), datetime.timedelta(seconds=1, microseconds=291050), datetime.timedelta(seconds=1, microseconds=299098), datetime.timedelta(seconds=1, microseconds=276757)]

