Test

Fix incorrect annotations for Omni-MATH and WildBench for empty outputs #7929

Sign in to view logs

Set up job

1s

Run actions/checkout@v4

1s

Set up Python 3.12

14s

Run python3 -m pip install --upgrade build

6s

Run python3 -m build

7s

Run python3 -m pip install dist/crfm_helm-*.whl

6m 58s

Run helm-run --run-entries simple1:model=simple/model1 --max-eval-instances 10 --suite test

5s

Run helm-summarize --suite test

5s

Run helm-server --help

0s

Post Set up Python 3.12

0s

Post Run actions/checkout@v4

0s

Complete job

0s