delete unecessary files #2
This file contains hidden or 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: checkpoints | |
| on: | |
| # Trigger the workflow on push or pull request, | |
| # but only for the main branch | |
| push: | |
| branches: | |
| - main | |
| - v0.2.x | |
| paths: | |
| - "**/*.py" | |
| - .github/workflows/checkpoints.yml | |
| pull_request: | |
| branches: | |
| - main | |
| - v0.2.x | |
| paths: | |
| - "**/*.py" | |
| - "verl/trainer/config/*.yaml" | |
| - .github/workflows/checkpoints.yml | |
| - "tests/e2e/*.sh" | |
| # Cancel jobs on the same ref if a new one is triggered | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.ref }} | |
| cancel-in-progress: ${{ github.ref != 'refs/heads/main' }} | |
| # Declare permissions just read content. | |
| permissions: | |
| contents: read | |
| jobs: | |
| e2e_gsm8k_megatron: | |
| runs-on: [self-hosted, l20-0] | |
| timeout-minutes: 40 # Increase this timeout value as needed | |
| env: | |
| HTTP_PROXY: ${{ secrets.PROXY_HTTP }} | |
| HTTPS_PROXY: ${{ secrets.PROXY_HTTPS }} | |
| NO_PROXY: "localhost,127.0.0.1" | |
| HF_HUB_ENABLE_HF_TRANSFER: 1 | |
| container: | |
| image: whatcanyousee/verl:vemlp-th2.4.0-cu124-vllm0.6.3-ray2.10-te2.0-megatron0.11.0-v0.0.6 | |
| options: --gpus all --shm-size=10g | |
| steps: | |
| - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2 | |
| with: | |
| fetch-depth: 0 | |
| - name: Install the current repository | |
| run: | | |
| pip3 install hf_transfer | |
| pip3 install -e .[test] | |
| - name: Prepare gsm8k dataset | |
| run: | | |
| python3 examples/data_preprocess/gsm8k.py | |
| - name: Running Checkpoint Integration Test (Qwen Megatron) | |
| run: | | |
| ray stop --force | |
| export PYTHONPATH=$PYTHONPATH:/opt/nvidia/Megatron-LM | |
| bash tests/checkpoint/run_qwen_megatron_ckpt.sh | |
| - name: Running Checkpoint Integration Test (Deepseek Megatron) | |
| run: | | |
| ray stop --force | |
| export PYTHONPATH=$PYTHONPATH:/opt/nvidia/Megatron-LM | |
| bash tests/checkpoint/run_deepseek_megatron_ckpt.sh |