feat: add capability to set min/max eps separately as proposed in the…#95
Merged
parthchadha merged 3 commits intomainfrom Mar 31, 2025
Merged
feat: add capability to set min/max eps separately as proposed in the…#95parthchadha merged 3 commits intomainfrom
parthchadha merged 3 commits intomainfrom
Conversation
… DAPO paper Signed-off-by: Parth Chadha <pchadha@nvidia.com>
parthchadha
force-pushed
the
pchadha/dapo-eps
branch
from
96b14e7 to
2f905f7
Compare
SahilJain314
approved these changes
Mar 31, 2025
Contributor
SahilJain314
left a comment
SahilJain314
left a comment
There was a problem hiding this comment.
Modified a bit of documentation on the loss, but otherwise LGTM
Signed-off-by: Parth Chadha <pchadha@nvidia.com>
parthchadha
force-pushed
the
pchadha/dapo-eps
branch
from
2b6ffd9 to
077762b
Compare
yfw
pushed a commit
that referenced
this pull request
Apr 2, 2025
#95) Signed-off-by: Parth Chadha <pchadha@nvidia.com> Co-authored-by: Sahil Jain <48468750+SahilJain314@users.noreply.github.com> Signed-off-by: Yi-Fu Wu <yifu.wu@gmail.com>
KiddoZhu
pushed a commit
that referenced
this pull request
May 6, 2025
#95) Signed-off-by: Parth Chadha <pchadha@nvidia.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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
… DAPO paper
What does this PR do ?
Allows users to set min/max clipping threshold as proposed in the DAPO paper.
Issues
List issues that this PR closes (syntax):
Usage
# Add a code snippet demonstrating how to use thisBefore your PR is "Ready for review"
Pre checks:
Additional Information