add two benchmark datasets aime-2024 and math-odyssey #173
This file contains 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
| name: Unit tests | |
| on: | |
| pull_request: | |
| branches: [ "main" ] | |
| # Allows you to run this workflow manually from the Actions tab | |
| workflow_dispatch: | |
| permissions: | |
| contents: read | |
| jobs: | |
| unit-tests: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v3 | |
| - name: Set up Python 3.10 | |
| uses: actions/setup-python@v3 | |
| with: | |
| python-version: "3.10" | |
| - name: Install dependencies | |
| run: | | |
| python -m pip install --upgrade pip | |
| pip install . | |
| pip install pytest pytest-cov pytest-timeout | |
| - name: Run all tests | |
| run: | | |
| ./nemo_skills/code_execution/local_sandbox/start_local_sandbox.sh & | |
| sleep 120 | |
| export NEMO_SKILLS_CONFIG=cluster_configs/local.yaml | |
| export NEMO_SKILLS_SANDBOX_HOST="$(docker inspect -f '{{range.NetworkSettings.Networks}}{{.IPAddress}}{{end}}' `docker ps -a | grep local-sandbox | awk '{print $1}'`)" | |
| echo $NEMO_SKILLS_SANDBOX_HOST | |
| set -o pipefail # this will make sure next line returns non-0 exit code if tests fail | |
| python -m pytest tests/ --junitxml=pytest.xml --cov-report=term-missing:skip-covered --cov=nemo_skills --cov=pipeline --durations=30 -rs -vvv | tee pytest-coverage.txt | |
| - name: Check help message | |
| run: | | |
| NEMO_SKILLS_CONFIG=cluster_configs/slurm.yaml python tests/check_help.py --all | |
| cluster-tests: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v3 | |
| # we want to be more conservative with python version here as some clusters might have older installed | |
| - name: Set up Python 3.8 | |
| uses: actions/setup-python@v3 | |
| with: | |
| python-version: "3.8" | |
| - name: Install dependencies | |
| run: | | |
| python -m pip install --upgrade pip | |
| # testing cluster environment where no other packages should be required | |
| pip install --user pyyaml evalplus pytest pytest-cov pytest-timeout | |
| - name: Run help | |
| run: | | |
| NEMO_SKILLS_CONFIG=cluster_configs/slurm.yaml python tests/check_help.py | |
| - name: Check datasets preparation | |
| run: | | |
| NEMO_SKILLS_CONFIG=cluster_configs/slurm.yaml pytest tests/test_datasets.py |