Conversation
cbalioglu
added a commit
that referenced
this pull request
Mar 4, 2025
jacklanchantin
pushed a commit
that referenced
this pull request
Mar 21, 2025
uralik
pushed a commit
that referenced
this pull request
Apr 3, 2025
* Add Skywork Reward Model * reorder * working checkpoint with skywork * unify VllmReward class * cleanup wrap text * actually not quite working. needs dp gather and scatter * add gather scatter for vllm rm * working checkpoint * working checkpoint * updates * Instantiate metric recorders on rank 0 only (#1072) * fix gather bug * cleanup * comment * add grpo (runnable, but not increasing rewards yet * log outputs * cleannup * rename * merge * fixes * testing online dpo after merge * bug fix * fixing merge errors * fix bugs * merged with online_training * update grpo * cleanup * fix grpo bug * cleanup * cleanup * isort/black * move vllm generate_rewards to its own function * refactor how reward models use prompt_batch * remove breakpoint * working chkpt * remove irrelevant skywork stuff --------- Co-authored-by: jacklanchantin user <jacklanchantin@submit-2.fair-aws-h100-1.hpcaas> Co-authored-by: Can Balioglu <cbalioglu@users.noreply.github.com>
This file contains hidden or 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR ensures that
MetricRecorderinstances are constructed only on rank 0. Some recorders such asWandbRecorderhas the side effect of setting up their environment during construction which causes redundant/duplicate artifacts to be generated. The actual metric records are not affected though since we always write them on rank 0.