FIRE sampling added. #58
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Hi, Sorry for the delay as I find it extremely challenging to update the code with the latest version of the verl as many things have changed and I am not able to access the original test environment again. I have updated the code logic following the suggestion from @eric-haibin-lin above, and also merge the latest commits. Please take another round of review and let me know if there is any further suggestions. Thanks! |
|
|
|
Hi, Thanks for the info. Again, I am not so familiar with the CI system, so I am wondering is the current status ready to go after my last commit? Or is there anything I still need work on as the only failing check I see seems to be caused by random shutdown from the server. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Add FIRE sampling from paper Flaming-hot Initiation with Regular Execution Sampling for Large Language Models (https://arxiv.org/abs/2410.21236) to the PPO trainer loop as an additional option to turn on.