A request for finetune code about MiniCheck-FT5

[lifelsl]

I tried to follow the approach of MiniCheck-FT5 in the paper a few days ago, but unfortunately, it did not achieve the same good effect🤣. I also understand that this is because my finetune code was not written very well. It is not a simple text classification task. If it's convenient for you, could you please send me the finetune code of the MiniCheck-FT5.

[Liyan06]

Hi,

You can double check the "Appendix G Training Details" in the paper to make sure you train the model the same way as we did.

For fine-tuning:

• You can take a look here for fine-tuning the T5 model.
• For fine-tuning RoBERTa and DeBERTa models, we used the training script from here.