feat: Use openmathinstruct2 training in grpo math example#18
Merged
parthchadha merged 11 commits intomainfrom Mar 21, 2025
Merged
feat: Use openmathinstruct2 training in grpo math example#18parthchadha merged 11 commits intomainfrom
parthchadha merged 11 commits intomainfrom
Conversation
parthchadha
requested review from
SahilJain314 and
terrykong
and removed request for
SahilJain314
terrykong
reviewed
Mar 21, 2025
terrykong
reviewed
Mar 21, 2025
parthchadha
force-pushed
the
pchadha/openmathinstruct2
branch
from
e3a2e9a to
c4f14b9
Compare
parthchadha
force-pushed
the
pchadha/openmathinstruct2
branch
from
c4f14b9 to
dc02972
Compare
SahilJain314
previously approved these changes
Mar 21, 2025
terrykong
reviewed
Mar 21, 2025
Signed-off-by: Parth Chadha <pchadha@nvidia.com>
Signed-off-by: Parth Chadha <pchadha@nvidia.com>
- flatten hyperparams for tb no longer errors for lists (was an issue for schedulers) - the submission script now overlaps the head on the first worker (no longer needs extra node just for head) - fixes the CI to handle weird permissions issues - added sphinx build and doctest to CI - added functional tests to CI - nuked an old example - added docs for functional tests - --no-container-mount-home - fix a unit tests that expected cuda to skip - allow running unit tests on slurm head node with no gpu - add a hermetic script to run functional tests Signed-off-by: Terry Kong <terryk@nvidia.com> Signed-off-by: Parth Chadha <pchadha@nvidia.com>
Signed-off-by: Sahil Jain <sahilj@nvidia.com> Co-authored-by: Terry Kong <terrycurtiskong@gmail.com> Signed-off-by: Parth Chadha <pchadha@nvidia.com>
Signed-off-by: Terry Kong <terryk@nvidia.com> Signed-off-by: Parth Chadha <pchadha@nvidia.com>
Signed-off-by: Terry Kong <terryk@nvidia.com> Signed-off-by: Parth Chadha <pchadha@nvidia.com>
Signed-off-by: Terry Kong <terryk@nvidia.com> Signed-off-by: Parth Chadha <pchadha@nvidia.com>
…es (#20) Signed-off-by: Parth Chadha <pchadha@nvidia.com>
Signed-off-by: Parth Chadha <pchadha@nvidia.com>
parthchadha
force-pushed
the
pchadha/openmathinstruct2
branch
from
dc02972 to
2d0f943
Compare
github-actions
bot
added
documentation
…uct2 Signed-off-by: Parth Chadha <pchadha@nvidia.com>
parthchadha
force-pushed
the
pchadha/openmathinstruct2
branch
from
f33dd76 to
e40d315
Compare
terrykong
approved these changes
Mar 21, 2025
KiddoZhu
pushed a commit
that referenced
this pull request
May 6, 2025
Signed-off-by: Parth Chadha <pchadha@nvidia.com> Signed-off-by: Terry Kong <terryk@nvidia.com> Signed-off-by: Sahil Jain <sahilj@nvidia.com> Co-authored-by: Terry Kong <terrycurtiskong@gmail.com> Co-authored-by: Sahil Jain <48468750+SahilJain314@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
3 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 ?
Add a one line overview of what this PR aims to accomplish.
Changelog
Usage
# Add a code snippet demonstrating how to use thisBefore your PR is "Ready for review"
Pre checks:
Checklist when contributing
Additional Information