parallelize evaluation in rl-training #60
Merged
Conversation
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
kennyyu
approved these changes
Oct 31, 2025
tinker_cookbook/rl/train.py
Outdated
|
|
||
| # Create tasks for all evaluators | ||
| tasks = [ | ||
| run_single_evaluation(evaluator, cfg, i_batch, sampling_client) for evaluator in evaluators |
Contributor
There was a problem hiding this comment.
nit: can we use asyncio.create_task(..., name=f"evals_task_{ev_name}") to give these coroutines a name? This makes it easier to identify these workloads in traces!
Contributor
Author
There was a problem hiding this comment.
good catch! just addressed.
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Outdated suggestions cannot be applied.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.
Parallelize different evaluators during a RL training loop.