Skip to content

Conversation

Stealth-py
Copy link
Contributor

Fixes #114
This PR is open for review!

Copy link
Member

@mattdangerw mattdangerw left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks this looks good! Left a few comments.

@mattdangerw mattdangerw requested a review from haifeng-jin April 26, 2022 18:52
Copy link
Contributor

@haifeng-jin haifeng-jin left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for the PR!

@Stealth-py
Copy link
Contributor Author

Stealth-py commented Apr 26, 2022

Thank you for the reviews! I've made the appropriate changes.
Regarding this I've changed it to val_loss for now.

@Stealth-py
Copy link
Contributor Author

Thank you for the reviews! I've resolved most of them, have a few doubts in the couple unresolved conversations above.

@mattdangerw
Copy link
Member

@Stealth-py thanks! Replied above. This overall is looking great, but I think we need to resolve the "re-training" question before we land this.

@Stealth-py
Copy link
Contributor Author

Stealth-py commented May 3, 2022

@mattdangerw I've made the final changes in the last commit! I hope this is fine.

Copy link
Member

@mattdangerw mattdangerw left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This looks great! Thanks for all the work on this.

This will be a good model for hyper parameter search for fine tuning in general, which is something we will likely need to do a lot of.

@mattdangerw mattdangerw merged commit 68eb2f7 into keras-team:master May 3, 2022
@Stealth-py Stealth-py deleted the kerastuner-hyperparameter-search branch May 3, 2022 21:00
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

Successfully merging this pull request may close these issues.

Use KerasTuner to hyper-parameter search for the BERT finetuning script
4 participants