Add OSFT implementation through mini-trainer #1
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
Maxusmusti
reviewed
Aug 22, 2025
Contributor
Maxusmusti
left a comment
Maxusmusti
left a comment
There was a problem hiding this comment.
Looks good, just a couple of questions/comments
Maxusmusti
reviewed
Aug 22, 2025
src/training_hub/algorithms/osft.py
Outdated
| 'checkpoint_at_epoch': bool, | ||
| 'save_final_checkpoint': bool, | ||
| 'training_mode': str, | ||
| 'max_epochs': int, |
Contributor
There was a problem hiding this comment.
should this just be epochs?
Collaborator
Author
There was a problem hiding this comment.
Yes, thank you for catching this
RobotSail
force-pushed
the
add-osft
branch
5 times, most recently
from
a3dbb85 to
2c7f53b
Compare
RobotSail
pushed a commit
that referenced
this pull request
Oct 14, 2025
adds hierarchical priority, handles edge cases, surface warnings and …
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Outdated suggestions cannot be applied.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.
This PR adds Orthogonal Subspace Fine-Tuning (OSFT) into the training hub.
This is mostly done but still needs the final components:
pyproject.tomlshould have themini-trainerdependency pointing to a valid pypi release