Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

How many samples were used to train Flan-T5? #92

Open
rohan-mehta opened this issue Aug 7, 2023 · 0 comments
Open

How many samples were used to train Flan-T5? #92

rohan-mehta opened this issue Aug 7, 2023 · 0 comments

Comments

@rohan-mehta
Copy link

Hey all, possibly silly question. I see that the huggingface collection has many millions of samples, and the google blog post suggests that the collection has 15M samples: https://ai.googleblog.com/2023/02/the-flan-collection-advancing-open.html

On the other hand mixtures.py suggests that ~350K samples is the default maximum: https://github.com/google-research/FLAN/blob/main/flan/v2/mixtures.py#L27

How many samples were actually used to fine tune T5 and produce Flan-T5?

Thanks!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Development

No branches or pull requests

1 participant