bigscience-workshop/t-zero

Instructions for fine-tuning a trained t-zero

louis030195 opened this issue · 2 comments

louis030195 commented

First, thanks for the great work!

Does it make sense to request instructions for fine-tuning a trained t-zero? That would be really great. If it is outside the scope of this repo, feel free to close this issue.

If yes, I would suggest providing the computing power required, thanks!

VictorSanh commented

hi @louis030195!
I think you will find this PR #3 interesting. it supports single task fine-tuning (including the few-shot case).

If yes, I would suggest providing the computing power required, thanks!

If you mean, documenting how much resources (in number of GPUs for instance) are needed to fine-tune on a dataset of size XXX, yes we should do that!

  • 🚀1
VictorSanh commented

pr #3 is merged