Skip to content

[mcore] moonlight (small model with deepseekv3 arch) (#1284) #11

[mcore] moonlight (small model with deepseekv3 arch) (#1284)

[mcore] moonlight (small model with deepseekv3 arch) (#1284) #11

Workflow file for this run

name: e2e_sppo
on:
# Trigger the workflow on push or pull request,
# but only for the main branch
push:
branches:
- main
- v0.*
pull_request:
branches:
- main
- v0.*
paths:
- "**/*.py"
# Other entrypoints
- "!examples/**"
- "!tests/**"
- "!verl/trainer/main_*.py"
- "!verl/trainer/fsdp_sft_trainer.py"
# Other recipes
- "!recipe/**"
# Megatron
- "!verl/workers/**/megatron_*.py"
# Home
- "recipe/sppo"
# Entrypoints
- ".github/workflows/e2e_sppo.yml"
- "examples/data_preprocess/gsm8k.py"
- "tests/e2e/run_sppo.sh"
# Declare permissions just read content.
permissions:
contents: read
jobs:
e2e_sppo:
runs-on: [L20x8]
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-mirror.com"
HF_ENDPOINT: "https://hf-mirror.com"
HF_HUB_ENABLE_HF_TRANSFER: "0" # This is more stable
container:
image: ocss884/verl-sglang:ngc-th2.6.0-cu126-sglang0.4.5.post3
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 -e .[test,gpu,sglang] --no-deps
- name: Prepare MATH dataset
run: |
python3 examples/data_preprocess/math_dataset.py --local_dir ./data/math
- name: Prepare Model checkpoint
run: |
huggingface-cli download Qwen/Qwen2.5-0.5B-Instruct --local-dir ./models/Qwen2.5-0.5B-Instruct
- name: Running the E2E test with the SPPO algorithm
run: |
ray stop --force
bash tests/e2e/run_sppo.sh