How to fine tune on DocVQA

#1
by hal9003 - opened

Is there a tutorial or tips for fine tuning on QA task?

https://github.com/NielsRogge/Transformers-Tutorials/blob/master/UDOP/Fine_tune_UDOP_on_a_custom_dataset_(toy_RVL_CDIP_dataset).ipynb

I think you just need to update "target_sequence" with your question and answer. You can try with that.

Indeed, and you could set the labels of the question tokens to -100 to make sure the model only learns to complete the question. Refer to my Donut example notebook.

Thanks!

ImportError: cannot import name 'UdopForConditionalGeneration' from 'transformers'
I am getting this error while importing it from transformers

Sign up or log in to comment