Traindiff test GH workflow fixes #7
Workflow file for this run
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: Containerized training differences tests between Jax and PyTorch | |
| on: | |
| pull_request: | |
| branches: | |
| - 'main' | |
| jobs: | |
| build_and_push_docker_image: | |
| runs-on: self-hosted | |
| steps: | |
| - uses: actions/checkout@v2 | |
| - name: Build and push docker image | |
| run: | | |
| GIT_BRANCH=${{ github.head_ref || github.ref_name }} | |
| FRAMEWORK=both | |
| IMAGE_NAME="algoperf_${GIT_BRANCH}" | |
| cd $HOME/algorithmic-efficiency/docker | |
| docker build --no-cache -t $IMAGE_NAME . --build-arg framework=$FRAMEWORK --build-arg branch=$GIT_BRANCH | |
| BUILD_RETURN=$? | |
| if [[ ${BUILD_RETURN} != 0 ]]; then exit ${BUILD_RETURN}; fi | |
| docker tag $IMAGE_NAME us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/$IMAGE_NAME | |
| docker push us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/$IMAGE_NAME | |
| traindiffs_tests: | |
| runs-on: self-hosted | |
| needs: build_and_push_docker_image | |
| steps: | |
| - uses: actions/checkout@v2 | |
| - name: Run containerized traindiffs test | |
| run: | | |
| docker pull us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_${{ github.head_ref || github.ref_name }} | |
| docker run -v $HOME/data/:/data/ -v $HOME/experiment_runs/:/experiment_runs -v $HOME/experiment_runs/logs:/logs --gpus all --ipc=host us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_${{ github.head_ref || github.ref_name }} --traindiffs_test true |