初始化项目，由ModelHub XC社区提供模型
Model: dmaheshwar22/qwen-1.5b-coder-grpo-scratch-step200 Source: Original Platform
This commit is contained in:
ModelHub XC
165
README.md
Normal file
165
README.md
Normal file
@@ -0,0 +1,165 @@
|
||||
---
|
||||
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.
|
||||
Reference in New Issue
Block a user