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

Add more save strategies for DPO training. #1255

Merged
merged 2 commits into from
Feb 6, 2024
Merged

Add more save strategies for DPO training. #1255

merged 2 commits into from
Feb 6, 2024

Conversation

PhilipMay
Copy link
Contributor

see #1253

@PhilipMay
Copy link
Contributor Author

Fixed: TypeError: transformers.training_args.TrainingArguments() got multiple values for keyword argument 'save_steps'

@PhilipMay
Copy link
Contributor Author

Hmm - did I break a regression test?
@filippo82

@filippo82
Copy link
Contributor

I suspect that the tests are broken for other reasons ... 😅

I had a look at your PR. I want to first check something in the validate_config method.

@winglian winglian merged commit 13eea21 into axolotl-ai-cloud:main Feb 6, 2024
5 of 7 checks passed
maximegmd pushed a commit to maximegmd/axolotl that referenced this pull request Feb 6, 2024
* Set save_strategy and save_steps in HFDPOTrainerBuilder

* fix doublicate save_steps
djsaunde pushed a commit that referenced this pull request Dec 17, 2024
* Set save_strategy and save_steps in HFDPOTrainerBuilder

* fix doublicate save_steps
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.

3 participants