qwen-1.5b-coder-grpo-scratch-step200/README.md

---
license: apache-2.0
base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
language:
  - en
library_name: transformers
pipeline_tag: text-generation
tags:
  - code
  - python
  - reinforcement-learning
  - grpo
  - rlvr
  - verifiable-rewards
datasets:
  - evalplus/mbppplus
  - evalplus/humanevalplus
---

# Qwen-2.5-Coder-1.5B — GRPO from base, 200 steps

GRPO-trained variant of `Qwen/Qwen2.5-Coder-1.5B-Instruct`, optimized with
**verifiable rewards from sandboxed test execution** — same family of
techniques behind DeepSeek-R1 and Kimi-K1.5, scaled down to a 1.5B model
that fits on a single 24 GB GPU.

> **Honest framing:** this is a **pipeline-validation run**, not the
> headline checkpoint. Trained from base (no SFT warm-start), 200 steps,
> single A100. Pass@1 on HumanEval+ is essentially tied with the SFT
> baseline — see [Results](#results) for numbers. The headline run
> (SFT-warmstarted, 500+ steps) is forthcoming as a separate model.

## Training setup

| | |
|---|---|
| Base model | `Qwen/Qwen2.5-Coder-1.5B-Instruct` |
| RL algorithm | GRPO (group-relative policy optimization) |
| RL framework | [verl](https://github.com/volcengine/verl) v0.7.0 |
| Rollout engine | vLLM |
| Group size (samples per prompt) | 8 |
| Train batch | 32 prompts × 8 rollouts = 256 candidates per step |
| Learning rate | 1e-6 |
| KL coefficient (loss-side) | 0.04, low-variance KL |
| KL coefficient (reward-side) | 0.001 |
| Temperature (rollout) | 1.0 |
| Total steps | 200 |
| Hardware | 1× A100 80 GB (FSDP with CPU offload) |
| Warm-start | None — trained from base instruct model |
| Training data | 319 MBPP-train prompts (MBPP+ contamination removed) |

### Reward function

Each rollout is scored by a composite reward executed in a sandboxed
Docker container running pytest:

- **Test-pass rate** (primary signal) — fraction of hidden tests passing
- **Lint reward** — `ruff` clean code bonus
- **Length penalty** — anti-verbosity
- **Compile-error penalty** — hard penalty for non-runnable code

All numeric rewards are bounded in `[0, ~1.1]` to keep GRPO group-relative
advantages well-scaled.

## Results

Greedy decoding, n=5 samples, temperature=0.2, evaluated with
[evalplus](https://github.com/evalplus/evalplus):

| Setup | HumanEval+ pass@1 | HumanEval+ pass@5 |
|---|---|---|
| Qwen-2.5-Coder-1.5B base | 0.627 | — |
| + SFT (3 epochs LoRA on rejection-sampled MBPP) | 0.638 | — |
| **+ GRPO from base, 200 steps (this model)** | **0.6415** | **0.6890** |
| + SFT + Coordinator retry (max 3 rounds) | 0.677 | — |
| Best-of-8 @ T=0.7 (oracle ceiling) | 0.783 | — |

**Reading the numbers honestly:**

- +1.4 pts over base, +0.4 pts over SFT — the SFT delta is within noise
  (no paired bootstrap significance at p<0.05 on 164 problems).
- Pass@5 = 0.689 implies the policy *can* solve ~69% of HumanEval+; the
  4.7-pt gap to pass@1 says it picks the wrong sample at temp=0.2 about
  5% of the time. There's headroom — this is not a converged policy.
- Most likely cause of the modest lift: trained from base instead of
  SFT-warmstarted, and stopped at step 200. The
  [WEEK4_GUIDE](https://github.com/Devesh-Maheshwari/verifiable-rl-coder/blob/main/docs/WEEK4_GUIDE.md)
  projection of 0.68–0.75 assumes both SFT warm-start and 500–1000 steps.

## Intended use

- **Research and education** — concrete reference for end-to-end GRPO with
  verifiable rewards on a small open coder. Reward function, sandbox, and
  training config are all open-source in the
  [companion repo](https://github.com/Devesh-Maheshwari/verifiable-rl-coder).
- **NOT for production inference** — at 0.64 pass@1 it is no stronger than
  the SFT baseline; use the headline run (forthcoming) for that.

## How to use

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "dmaheshwar22/qwen-1.5b-coder-grpo-scratch-step200"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, dtype="bfloat16", device_map="auto")

prompt = "Write a Python function `is_prime(n: int) -> bool` that returns True iff n is prime."
messages = [{"role": "user", "content": prompt}]
inputs = tok.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(model.device)
out = model.generate(inputs, max_new_tokens=256, temperature=0.2, do_sample=True)
print(tok.decode(out[0][inputs.shape[1]:], skip_special_tokens=True))
```

Or with vLLM for batched evaluation:

```python
from vllm import LLM, SamplingParams
llm = LLM(model="dmaheshwar22/qwen-1.5b-coder-grpo-scratch-step200",
          gpu_memory_utilization=0.5, dtype="bfloat16")
out = llm.generate(["def is_prime(n):"],
                   SamplingParams(max_tokens=256, temperature=0.2))
print(out[0].outputs[0].text)
```

## Limitations

- **Coding-only.** Trained on MBPP-style Python tasks; do not expect
  general-purpose chat or reasoning quality outside coding.
- **Output format.** Despite the in-training markdown-fence stripping fix,
  the policy occasionally still wraps code in ```` ``` ````. Strip fences
  in any downstream evaluator.
- **Sandbox required for reward replay.** Reproducing the training reward
  signal requires running pytest in a Docker container with the project's
  resource limits — see the companion repo's `sandbox/runner.py`.
- **Not safety-tuned.** Inherits all behaviors of the base instruct model.

## Reproduction

Full training config, reward function, and sandbox runner are in the
companion repo:

- Repo: <https://github.com/Devesh-Maheshwari/verifiable-rl-coder>
- Training config: `configs/grpo_qwen1_5b.yaml`
- Reward fn: `src/verifiable_rl_coder/training/grpo_reward.py`
- Sandbox: `src/verifiable_rl_coder/sandbox/runner.py`
- CHTC submit scripts: `chtc/train_grpo.{sub,sh}`, `chtc/submit_train_grpo.sh`

## Citation

```bibtex
@misc{verifiable-rl-coder-2026,
  author       = {Maheshwari, Devesh},
  title        = {Verifiable-RL Coder: GRPO-trained Qwen-2.5-Coder with sandboxed verifiable rewards},
  year         = {2026},
  howpublished = {\url{https://github.com/Devesh-Maheshwari/verifiable-rl-coder}}
}
```

## Acknowledgments

- [Qwen team](https://huggingface.co/Qwen) for the strong open-weights coder base.
- [verl](https://github.com/volcengine/verl) for the production-grade GRPO trainer.
- [evalplus](https://github.com/evalplus/evalplus) for the hardened HumanEval+/MBPP+ benchmarks.
- Trained on UW-Madison Center for High Throughput Computing (CHTC) resources.