Laputa

关于中文编码问题 bert应该都是能正常显示中文的，这个应该怎么解决 INFO:tensorflow:Writing example 0 of 3272863 -- 2 |   | INFO:tensorflow:*** Example *** 3 |   | INFO:tensorflow:guid: train-0 4 |   | INFO:tensorflow:tokens: [CLS] \u6211 \u7684 \u4e16 \u754c \u963f \u9633...

用户自定义词典不生效

3

rt

看着乱乱的...

The parameters of loss are always similarity during training

3

I have 3 losses, such as """ tensor([0.9926, 0.9926, 0.9927], requires_grad=True) tensor([0.9908, 0.9908, 0.9909], requires_grad=True) tensor([0.9873, 0.9873, 0.9873], requires_grad=True) """