Continue pretraining on my dataset

Thanks for your incredible models,
I want to fine tune the model using mlm on my dataset. Can i use the regular fine tuning using transformers package or i must use the current repo pretraining method?

The issue names no files or tests. Start by comparing the repository's current pretraining method with regular MLM fine-tuning through the Transformers package, then document which workflow applies to a user's dataset and what prerequisites or limitations determine that choice.

Written by the indexing model from the issue text.