Draft
Conversation
baptistecolle
force-pushed
the
agent-traces-v2
branch
from
f798a19 to
91e4dc1
Compare
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do?
This PR adds a pipeline to train an agent on agentic traces from smolagents
How does it work?
Step 1) We generated traces from r1 on from the open-r1/codeforces-cots dataset.
Step 2) The traces are then filtered to only keep traces that lead to solutions that pass the codeforces test-cases.
Step 3) Train a Qwen2.5-1.5B with SFT on the traces from R1.
Step 4) Evaluate the performance improvement of the base with the new traces training
The dataset of traces and the trained model are uploaded to the hub at:
(TODO: to move that to open-r1 org)
This is currently a WIP, some parts of the pipeline are not behaving correctly. This could then lead to a nice blog post.