Add wandb logging - Githubissues

lucidrains / PaLM-rlhf-pytorch

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

MIT License

7.67k stars 668 forks source link

Open ell-hol opened 1 year ago

ell-hol commented 1 year ago

Logs train and val loss as well as generated texts by default only when wandb available

ell-hol commented 1 year ago

What it looks like: link

tcapelle commented 1 year ago

Thanks =)