Why not create an example of using PPO to train a summarization model?

[Bo396543018]

Thank you for your excellent work. I have a question. I saw that you provided the script for training the RM model from the OpenAI paper 'Learning to Summarize from Human Feedback'. Why haven't you further trained PPO on that dataset.

[lvwerra]

Lack of time and people - feel free to try it!