CML-EC2-Runner #33
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: CML-EC2-Runner | |
| on: | |
| workflow_dispatch: | |
| jobs: | |
| launch-runner: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v3 | |
| - uses: iterative/setup-cml@v1 | |
| - name: Deploy runner on AWS EC2 | |
| env: | |
| REPO_TOKEN: ${{ secrets.PERSONAL_ACCESS_TOKEN }} | |
| AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }} | |
| AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }} | |
| run: | | |
| cml runner launch \ | |
| --cloud=aws \ | |
| --name=session-08 \ | |
| --cloud-region=ap-south-1 \ | |
| --cloud-type=g4dn.xlarge \ | |
| --cloud-hdd-size=64 \ | |
| --cloud-spot \ | |
| --single \ | |
| --labels=cml-gpu \ | |
| --idle-timeout=100 | |
| train-and-report: | |
| runs-on: [self-hosted, cml-gpu] | |
| needs: launch-runner | |
| timeout-minutes: 20 | |
| # runs-on: ubuntu-latest | |
| steps: | |
| - name: Verify EC2 Instance | |
| run: | | |
| echo "Checking instance information..." | |
| # Check if we're on EC2 | |
| TOKEN=$(curl -X PUT "http://169.254.169.254/latest/api/token" -H "X-aws-ec2-metadata-token-ttl-seconds: 21600") | |
| curl -H "X-aws-ec2-metadata-token: $TOKEN" http://169.254.169.254/latest/meta-data/instance-type | |
| echo "Checking system resources..." | |
| lscpu | |
| free -h | |
| df -h | |
| nvidia-smi # This will show GPU if available | |
| echo "Checking environment..." | |
| env | grep AWS || true | |
| hostname | |
| whoami | |
| pwd | |
| - uses: actions/checkout@v4 | |
| with: | |
| fetch-depth: 1 | |
| - name: Authenticate with AWS ECR | |
| uses: aws-actions/configure-aws-credentials@v4 | |
| with: | |
| aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }} | |
| aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }} | |
| aws-region: ${{ secrets.AWS_REGION }} | |
| - name: Nvidia check | |
| run: | | |
| nvidia-smi | |
| - name: Install Docker | |
| run: | | |
| curl -fsSL https://get.docker.com -o get-docker.sh | |
| sh get-docker.sh | |
| - name: Login to Amazon ECR | |
| id: login-ecr | |
| uses: aws-actions/amazon-ecr-login@v2 | |
| - name: Pull Docker image from ECR | |
| run: | | |
| docker pull ${{secrets.AWS_ECR_LOGIN_URI}}/${{ secrets.ECR_REPOSITORY_NAME }}:latest | |
| ls -a | |
| - name: Run DVC commands in container | |
| run: | | |
| docker run --rm --gpus=all \ | |
| -e AWS_ACCESS_KEY_ID=${{ secrets.AWS_ACCESS_KEY_ID }} \ | |
| -e AWS_SECRET_ACCESS_KEY=${{ secrets.AWS_SECRET_ACCESS_KEY }} \ | |
| -e AWS_DEFAULT_REGION=${{ secrets.AWS_REGION }} \ | |
| ${{ secrets.AWS_ECR_LOGIN_URI }}/${{ secrets.ECR_REPOSITORY_NAME }}:latest \ | |
| /bin/bash -c " | |
| dvc pull -r myremote && \ | |
| mkdir model_storage && \ | |
| dvc repro -f | |
| " | |
| # # Wait a moment to ensure the container has started | |
| # sleep 5 | |
| # # Print logs from the container | |
| # docker logs $CONTAINER_ID | |
| # # Stop the container after retrieving logs | |
| # docker stop $CONTAINER_ID | |
| - name: Clean previous images and containers | |
| run: | | |
| docker system prune -f | |