How to set the Pad Token for meta-llama/Llama-3 Models

[Chahnwoo]

Hello @nbroad,
I had been left incredibly confused because so many people seemed to set pad_token=eos_token, despite the reality you’ve mentioned here:

@nbroad

If you aren’t using flash attention 2, you should be careful about the padding tokens because some data collators will mask out padding tokens from the loss

Thank you for the clarification.