Skip to content

Conversation

@hiyouga
Copy link
Owner

@hiyouga hiyouga commented Jul 14, 2025

Also fix the loss balance across gradient accumulation and fix the ulysses patch

https://unsloth.ai/blog/gradient

@hiyouga hiyouga force-pushed the yaowei/dynbsz branch 2 times, most recently from c8a469c to 0a8824e Compare July 14, 2025 10:36
@hiyouga hiyouga merged commit f4264e7 into main Jul 14, 2025
1 check passed
@hiyouga hiyouga deleted the yaowei/dynbsz branch July 14, 2025 10:41
hiyouga added a commit that referenced this pull request Oct 4, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants