Skip to content

[LLM] Rewrite GSM8K reward function to follow standard GRPO conventions #15531

[LLM] Rewrite GSM8K reward function to follow standard GRPO conventions

[LLM] Rewrite GSM8K reward function to follow standard GRPO conventions #15531

Triggered via pull request March 5, 2026 11:01
Status Failure
Total duration 14m 25s
Artifacts

docs.yml

on: pull_request
Matrix: build-docs
upload  /  job
upload / job
Fit to window
Zoom out
Zoom in

Annotations

1 error and 3 warnings
build-docs (3.12, 12.8) / linux-job
Process completed with exit code 1.
build-docs (3.12, 12.8) / linux-job
No files were found with the provided path: /home/ec2-user/actions-runner/_work/_temp/artifacts/. No artifacts will be uploaded.
build-docs (3.12, 12.8) / linux-job
Back off 27.615 seconds before retry.
build-docs (3.12, 12.8) / linux-job
Failed to download action 'https://api.github.com/repos/actions/upload-artifact/tarball/ea165f8d65b6e75b540449e92b4886f43607fa02'. Error: Response status code does not indicate success: 502 (Bad Gateway). C24C:27EA4C:13B019E:551A5D6:69A963AA