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 to incrementally fine-tune AST model with the new data? #136

Open
jmren168 opened this issue Aug 8, 2024 · 0 comments
Open

How to incrementally fine-tune AST model with the new data? #136

jmren168 opened this issue Aug 8, 2024 · 0 comments

Comments

@jmren168
Copy link

jmren168 commented Aug 8, 2024

Hi @YuanGongND,

Thanks for the awesome work.
We have to incrementally fine-tine AST model because our collected data are changed over time, or we have a new class of data.

In our case, we fine-tune the AST model with a 3-class dataset, and then fine-tune the resulting AST model with a 4-class dataset, or with the collected 3-class data which are changed over time.
Here, the first 3 classes of the 4-class dataset are the same as the 3-class dataset.

Is it possible to incrementally fine-tune AST model even if we have a 4-class dataset ?

Many thanks.

@jmren168 jmren168 changed the title How to fine-tune twice on the data collected continuously over time? How to fine-tune AST model twice on the data collected continuously over time? Aug 8, 2024
@jmren168 jmren168 changed the title How to fine-tune AST model twice on the data collected continuously over time? How to incrementally fine-tune AST model with the new data? Aug 8, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant