{
 "schema_version": 1,
 "generated": "2026-10-20",
 "id": "daoyuanli2816-mini-verl--first-local-ppo-grpo-run",
 "repo": "DaoyuanLi2816/mini-verl",
 "repo_url": "https://github.com/DaoyuanLi2816/mini-verl",
 "repo_slug": "daoyuanli2816-mini-verl",
 "title": "Run a first PPO experiment on one GPU",
 "page_title": "How to run a first PPO experiment on one GPU with Mini Verl",
 "summary": "Install miniVERL, sample prompts and train a Qwen3-0.6B PPO run with a length reward.",
 "who": "An ML engineer with one NVIDIA GPU who wants a working reinforcement learning run before adapting it to their own task.",
 "problem": "Setting up verl-style reinforcement learning usually assumes a multi-GPU cluster, so a single-GPU user has no simple starting point.",
 "outcome": "A local PPO run that writes reward logs to rewards.jsonl and saves a resumable run under the chosen run ID.",
 "steps": [
  "Install the matching CUDA-enabled PyTorch build from the PyTorch installer, then run `python -m pip install \"miniverl[train,hydra]\"`.",
  "Create a small prompt set with `miniverl data sample --reward-profile target-length --rows 8 --out data/rl-prompts.parquet`.",
  "Check the configuration without training using `miniverl run --example hydra-ppo --bind reward.provider=target_length --dry-run`.",
  "Start the run with `miniverl run --example hydra-ppo --bind reward.provider=target_length --run-id local-ppo`.",
  "Open rewards.jsonl in the run output to read the reward for each rollout."
 ],
 "agent_prompt": "Work in the miniverl repo (DaoyuanLi2816/mini-verl) on this machine. Install it, sample 8 prompts into data/rl-prompts.parquet, run the hydra-ppo example with run ID <run-id>, and report the path to rewards.jsonl. Verify that the dry run passes before the full run starts.",
 "agents": [
  "any"
 ],
 "difficulty": "Intermediate",
 "time": "1 hour",
 "basis": "readme",
 "caveat": "The README gives the workflow for a Qwen3-0.6B example on one NVIDIA GPU, and the CUDA PyTorch build must be chosen separately from the miniverl install.",
 "category": "Research",
 "tags": [
  "Research"
 ],
 "lang": "python",
 "requirements": [
  "A single NVIDIA GPU with a CUDA-enabled PyTorch build installed from the PyTorch installer",
  "Python with pip available",
  "Enough GPU memory for the chosen model (see the single-GPU guide and hardware planning docs)"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": true,
 "score": 1.0,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/daoyuanli2816-mini-verl/first-local-ppo-grpo-run/",
 "md": "https://dedupedai.com/use-cases/daoyuanli2816-mini-verl/first-local-ppo-grpo-run/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/daoyuanli2816-mini-verl--first-local-ppo-grpo-run.json",
 "api_version": "v1"
}