Skip to content

[loss_scale] support last_round_with_ignore_empty_think for rag #4623

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Jun 17, 2025

Conversation

sosofun
Copy link
Contributor

@sosofun sosofun commented Jun 17, 2025

extend loss_scale to support last_round_with_ignore_empty_think for rag trainning

PR type

  • Bug Fix
  • New Feature
  • Document Updates
  • More Models or Datasets Support

PR information

Write the detail information belongs to this PR.

Experiment results

Paste your experiment result here(if needed).

extend loss_scale to support last_round_with_ignore_empty_think for rag trainning
@Jintao-Huang
Copy link
Collaborator

please run:

pip install pre-commit
pre-commit run --all-files

@Jintao-Huang Jintao-Huang changed the title support last_round_with_ignore_empty_think for rag [loss_scale] support last_round_with_ignore_empty_think for rag Jun 17, 2025
remove blank line contains whitespace for pre-commit
@Jintao-Huang Jintao-Huang merged commit 336520a into modelscope:main Jun 17, 2025
2 checks passed
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