Bump alibabacloud-credentials from 0.3.6 to 1.0.2 #101
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: e2e_sft | |
| on: | |
| # Trigger the workflow on push or pull request, | |
| # but only for the main branch | |
| push: | |
| pull_request: | |
| branches: | |
| - main | |
| - v0.* | |
| paths: | |
| - "**/*.py" | |
| # Entrypoints | |
| - ".github/workflows/e2e_sft.yml" | |
| - "examples/data_preprocess/gsm8k.py" | |
| - "tests/e2e/sft" | |
| - "verl/trainer/fsdp_sft_trainer.py" | |
| - "verl/trainer/config/sft_trainer.yaml" | |
| - "!examples" | |
| - "!verl/trainer/main_*.py" | |
| # Recipes | |
| - "!recipe" | |
| # Megatron | |
| - "!verl/workers/**/megatron_*.py" | |
| # 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_sft: | |
| runs-on: [L20x8] | |
| timeout-minutes: 20 # 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: "0" # This is more stable | |
| container: | |
| image: whatcanyousee/verl:ngc-th2.6.0-cu124-vllm0.8.2-mcore0.11.0-te2.0 | |
| 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 peft | |
| pip3 install -e .[test,gpu] | |
| - name: Prepare gsm8k dataset | |
| run: | | |
| ray stop --force | |
| python3 examples/data_preprocess/gsm8k.py | |
| - name: Running GSM8K E2E training tests on 8 L20 GPUs with rmpad using function rm | |
| run: | | |
| ray stop --force | |
| bash tests/e2e/sft/run_sft.sh | |
| - name: Running GSM8K E2E training tests on 8 L20 GPUs w/o rmpad using function rm | |
| run: | | |
| ray stop --force | |
| RM_PAD=False bash tests/e2e/sft/run_sft.sh | |
| - name: Running GSM8K E2E training tests on 8 L20 GPUs with sequence parallism | |
| run: | | |
| ray stop --force | |
| SP_SIZE=2 bash tests/e2e/sft/run_sft.sh | |
| - name: Check loss difference between sequence parallel vs. default implementation | |
| run: | | |
| ray stop --force | |
| ENTRYPOINT="tests/e2e/sft/test_sp_loss_match.py" SP_SIZE=2 bash tests/e2e/sft/run_sft.sh | |
| - name: Running GSM8K E2E training tests on 8 L20 GPUs with sequence parallism and liger | |
| run: | | |
| ray stop --force | |
| SP_SIZE=2 LIGER=True bash tests/e2e/sft/run_sft.sh | |
| - name: Running GSM8K E2E training tests with LoRA | |
| run: | | |
| ray stop --force | |
| LORA_RANK=32 bash tests/e2e/sft/run_sft.sh | |
| # TODO: multiturn |