making PR triggered CPU test for changes to megatron (#1195)

* making PR triggered CPU test for changes to megatron

* Update NeoXArgs docs automatically

* pre-commit

* Update NeoXArgs docs automatically

---------

Co-authored-by: github-actions <[email protected]>
Co-authored-by: Quentin Anthony <[email protected]>

.github/workflows/cpu_ci_on_pr.yml

@@ -0,0 +1,69 @@
+name: "Pull Request CPU Tests"
+
+on:
+ pull_request:
+ paths: # job only triggers when the PR changes files under megatron directory
+ - "megatron/**"
+
+jobs:
+ run-tests:
+ runs-on: [ 'test', 'self-hosted' ]
+ steps:
+ - name: Checkout Repo
+ uses: actions/checkout@v4
+
+ - name: Install Python
+ uses: actions/setup-python@v4
+ with:
+ python-version: "3.8"
+ cache: "pip"
+ cache-dependency-path: "**/requirements*.txt"
+
+ - name: Upgrade Pip
+ run: python -m pip install --upgrade pip
+
+ - name: Set up Docker repository # this should possibly be done by the worker before the job starts in the interest of execution time?
+ run: |
+ # Add Docker's official GPG key:
+ sudo apt-get update -y
+ sudo apt-get install ca-certificates curl -y
+ sudo install -m 0755 -d /etc/apt/keyrings
+ sudo curl -fsSL https://download.docker.com/linux/ubuntu/gpg -o /etc/apt/keyrings/docker.asc
+ sudo chmod a+r /etc/apt/keyrings/docker.asc
+
+ # Add the repository to Apt sources:
+ echo \
+ "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/ubuntu \
+ $(. /etc/os-release && echo "$VERSION_CODENAME") stable" | \
+ sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
+ sudo apt-get update
+ - name: Docker installation # this should possibly be done by the worker before the job starts in the interest of execution time?
+ run: |
+ sudo apt-get install docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin -y
+ sudo docker run hello-world
+ - name: Prepare data
+ run: |
+ python prepare_data.py -d ./data
+ - name: Remove previous container
+ run: |
+ if docker ps -a | grep -q "$CONTAINER"; then
+ echo "Container already exists, deleting it..."
+ docker rm -f $CONTAINER
+ fi
+ - name: Create container
+ run: |
+ export NEOX_DATA_PATH='./data/enwik8'
+ export NEOX_CHECKPOINT_PATH='/mnt/sda/checkpoints' #todo: where do I get this?
+ docker compose run -d --build --name $CONTAINER gpt-neox tail -f /dev/null
+ - name: Install test requirements
+ run: |
+ docker exec $CONTAINER pip install -r /workspace/requirements-dev.txt
+ - name: Execute CPU tests 1
+ run: |
+ docker exec $CONTAINER sh -c "cd gpt-neox && pytest tests -m cpu"
+ - name: Execute CPU tests 2
+ run: |
+ docker exec $CONTAINER sh -c "cd gpt-neox && PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python pytest tests -m cpu"
+ - name: Generate report
+ run: |
+ docker exec $CONTAINER python -m http.server --directory htmlcov 8000

configs/neox_arguments.md

@@ -111,7 +111,7 @@ Logging Arguments
 
 - **git_hash**: str
 
- Default = f70c54d
+ Default = 11a5537
 
  current git hash of repository