How to train and validate on a custom QA dataset?

[DivyanshuSheth]

Hello, I read the paper and found the concept pretty interesting. I am looking to train XLM-R using X-MAML for Question-Answering on a custom dataset. It'd be great if you could let me know how to go about doing this (the dataset structure, location, and the bits of code to be modified). Thank you very much.