Hyperparameters for training

#2
by VukDju - opened

Hello,
First of all I would like to thank you for your work, the RQUGE framework seems very interesting to me. I am writing this to ask you about the hyperparameters that you used for fine-tuning RoBERTa model over MOCHA dataset for the span scorer module of RQUGE.

I am trying to make adjustments to enable RQUGE work for Slovenian language, and it would mean very much too me to know this information.

Thank you.

Kind regards,
Vuk Đuranović

Sign up or log in to comment