-
Notifications
You must be signed in to change notification settings - Fork 1k
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 Reward Model training #1246
Merged
Merged
Commits on Jun 21, 2024
-
Configuration menu - View commit details
-
Copy full SHA for a950f8b - Browse repository at this point
Copy the full SHA a950f8bView commit details -
Configuration menu - View commit details
-
Copy full SHA for e360e24 - Browse repository at this point
Copy the full SHA e360e24View commit details -
- add different packing impl (Unpacked, packing until overflow)
- fix labels to also have valid/test implementations - fix label masking in _get_batch to also include anything from get_ltor_masks_and_position_ids
Configuration menu - View commit details
-
Copy full SHA for 9ee4a8f - Browse repository at this point
Copy the full SHA 9ee4a8fView commit details -
Configuration menu - View commit details
-
Copy full SHA for 0678573 - Browse repository at this point
Copy the full SHA 0678573View commit details
Commits on Jun 24, 2024
-
Configuration menu - View commit details
-
Copy full SHA for 15e3059 - Browse repository at this point
Copy the full SHA 15e3059View commit details
Commits on Jun 25, 2024
-
- Add metrics to forward step to add DPO specific metrics that are us…
…eful (accuracy, etc) - Add reference model setup for DPO - Add pairwise dataset for positive/negative pairs - Add DPO loss
Configuration menu - View commit details
-
Copy full SHA for 2d20d86 - Browse repository at this point
Copy the full SHA 2d20d86View commit details -
Configuration menu - View commit details
-
Copy full SHA for c045006 - Browse repository at this point
Copy the full SHA c045006View commit details -
Configuration menu - View commit details
-
Copy full SHA for eed3643 - Browse repository at this point
Copy the full SHA eed3643View commit details -
Configuration menu - View commit details
-
Copy full SHA for 0392080 - Browse repository at this point
Copy the full SHA 0392080View commit details -
Configuration menu - View commit details
-
Copy full SHA for 361f459 - Browse repository at this point
Copy the full SHA 361f459View commit details
Commits on Jun 26, 2024
-
Configuration menu - View commit details
-
Copy full SHA for 7398e07 - Browse repository at this point
Copy the full SHA 7398e07View commit details -
Configuration menu - View commit details
-
Copy full SHA for 51af714 - Browse repository at this point
Copy the full SHA 51af714View commit details
Commits on Jun 28, 2024
-
Configuration menu - View commit details
-
Copy full SHA for 06c851e - Browse repository at this point
Copy the full SHA 06c851eView commit details
Commits on Sep 9, 2024
-
Configuration menu - View commit details
-
Copy full SHA for b2848c1 - Browse repository at this point
Copy the full SHA b2848c1View commit details -
Configuration menu - View commit details
-
Copy full SHA for ad80726 - Browse repository at this point
Copy the full SHA ad80726View commit details -
Configuration menu - View commit details
-
Copy full SHA for 8172162 - Browse repository at this point
Copy the full SHA 8172162View commit details -
Configuration menu - View commit details
-
Copy full SHA for ae47b7f - Browse repository at this point
Copy the full SHA ae47b7fView commit details
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.