Merge pull request #790 from Niccolo-Ajroldi/pass_train_state #795
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 Regression Tests for Workload Variants | ||
| on: | ||
| pull_request: | ||
| branches: | ||
| - 'main' | ||
| jobs: | ||
| build_and_push_jax_docker_image: | ||
| runs-on: self-hosted | ||
| steps: | ||
| - uses: actions/checkout@v2 | ||
| - name: Build and push docker images | ||
| run: | | ||
| GIT_BRANCH=${{ github.head_ref || github.ref_name }} | ||
| FRAMEWORK=jax | ||
| IMAGE_NAME="algoperf_${FRAMEWORK}_${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/$IMAGE_NAME | ||
| build_and_push_pytorch_docker_image: | ||
| runs-on: self-hosted | ||
| steps: | ||
| - uses: actions/checkout@v2 | ||
| - name: Build and push docker images | ||
| run: | | ||
| GIT_BRANCH=${{ github.head_ref || github.ref_name }} | ||
| FRAMEWORK=pytorch | ||
| IMAGE_NAME="algoperf_${FRAMEWORK}_${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/$IMAGE_NAME | ||
| criteo_layernorm_jax: | ||
| runs-on: self-hosted | ||
| needs: build_and_push_jax_docker_image | ||
| steps: | ||
| - uses: actions/checkout@v2 | ||
| - name: Run containerized workload | ||
| run: | | ||
| docker pull us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_jax_${{ github.head_ref || github.ref_name }} | ||
| docker run -v $HOME/data/:/data/ -v $HOME/experiment_runs/:/experiment_runs -v $HOME/experiment_runs/logs:/logs --gpus all --ipc=host us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_jax_${{ github.head_ref || github.ref_name }} -d criteo1tb -f jax -s reference_algorithms/paper_baselines/adamw/jax/submission.py -w criteo1tb_layernorm -t reference_algorithms/paper_baselines/adamw/tuning_search_space.json -e tests/regression_tests/adamw -m 10 -c False -o True -r false | ||
| criteo_resnet_jax: | ||
| runs-on: self-hosted | ||
| needs: build_and_push_jax_docker_image | ||
| steps: | ||
| - uses: actions/checkout@v2 | ||
| - name: Run containerized workload | ||
| run: | | ||
| docker pull us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_jax_${{ github.head_ref || github.ref_name }} | ||
| docker run -v $HOME/data/:/data/ -v $HOME/experiment_runs/:/experiment_runs -v $HOME/experiment_runs/logs:/logs --gpus all --ipc=host us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_jax_${{ github.head_ref || github.ref_name }} -d criteo1tb -f jax -s reference_algorithms/paper_baselines/adamw/jax/submission.py -w criteo1tb_resnet -t reference_algorithms/paper_baselines/adamw/tuning_search_space.json -e tests/regression_tests/adamw -m 10 -c False -o True -r false | ||
| criteo_layernorm_pytorch: | ||
| runs-on: self-hosted | ||
| needs: build_and_push_pytorch_docker_image | ||
| steps: | ||
| - uses: actions/checkout@v2 | ||
| - name: Run containerized workload | ||
| run: | | ||
| docker pull us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_pytorch_${{ github.head_ref || github.ref_name }} | ||
| docker run -v $HOME/data/:/data/ -v $HOME/experiment_runs/:/experiment_runs -v $HOME/experiment_runs/logs:/logs --gpus all --ipc=host us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_pytorch_${{ github.head_ref || github.ref_name }} -d criteo1tb -f pytorch -s reference_algorithms/paper_baselines/adamw/pytorch/submission.py -w criteo1tb_layernorm -t reference_algorithms/paper_baselines/adamw/tuning_search_space.json -e tests/regression_tests/adamw -m 10 -c False -o True -r false | ||
| criteo_resnet_pytorch: | ||
| runs-on: self-hosted | ||
| needs: build_and_push_pytorch_docker_image | ||
| steps: | ||
| - uses: actions/checkout@v2 | ||
| - name: Run containerized workload | ||
| run: | | ||
| docker pull us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_pytorch_${{ github.head_ref || github.ref_name }} | ||
| docker run -v $HOME/data/:/data/ -v $HOME/experiment_runs/:/experiment_runs -v $HOME/experiment_runs/logs:/logs --gpus all --ipc=host us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_pytorch_${{ github.head_ref || github.ref_name }} -d criteo1tb -f pytorch -s reference_algorithms/paper_baselines/adamw/pytorch/submission.py -w criteo1tb_resnet -t reference_algorithms/paper_baselines/adamw/tuning_search_space.json -e tests/regression_tests/adamw -m 10 -c False -o True -r false | ||
| criteo_resnet_pytorch: | ||
| runs-on: self-hosted | ||
| needs: build_and_push_pytorch_docker_image | ||
| steps: | ||
| - uses: actions/checkout@v2 | ||
| - name: Run containerized workload | ||
| run: | | ||
| docker pull us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_pytorch_${{ github.head_ref || github.ref_name }} | ||
| docker run -v $HOME/data/:/data/ -v $HOME/experiment_runs/:/experiment_runs -v $HOME/experiment_runs/logs:/logs --gpus all --ipc=host us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_pytorch_${{ github.head_ref || github.ref_name }} -d criteo1tb -f pytorch -s reference_algorithms/paper_baselines/adamw/pytorch/submission.py -w criteo1tb_embed_init -t reference_algorithms/paper_baselines/adamw/tuning_search_space.json -e tests/regression_tests/adamw -m 10 -c False -o True -r false | ||
