---
tags:
- fine-tuned
- qwen3
- humaneval
- codeforces
- lora
- sft
base_model: Qwen/Qwen3-0.6B
datasets:
- open-r1/codeforces-cots
---

# Qwen3-0.6B Fine-tuned on Codeforces-CoTS (Python)

Reproduction of [Ben Burtenshaw's HuggingFace fine-tuning challenge](https://x.com/ben_burtenshaw/status/1999502002251006449) (Claude Code vs Codex). Fine-tuned using SFT on the **solutions_py** subset of `open-r1/codeforces-cots`.

## Results on HumanEval

| Model | Score | Problems Passed |
|-------|-------|-----------------|
| Base (Qwen3-0.6B) | 40.24% | 66/164 |
| **Fine-tuned** | **40.85%** | **67/164** |
| **Improvement** | **+0.61%** | **+1 problem** |

### Variance Across Runs

Same script, same hardware, 3 parallel runs:

| Run | Score | Result |
|-----|-------|--------|
| 1 | 40.85% | Win (+1) |
| 2 | 40.24% | Tie |
| 3 | 39.63% | Loss (-1) |

Fine-tuning has randomness. Multiple attempts are expected.

## Key Insight

The default `codeforces-cots` dataset is ~90% C++. Training on it for a Python benchmark (HumanEval) hurt performance in early attempts. Using the `solutions_py` subset doubled the baseline from ~18% to 40%.

**Domain alignment > data quantity.**

## Training Details

- **Dataset**: `open-r1/codeforces-cots` (`solutions_py` subset) - 500 examples
- **Method**: LoRA (r=8, alpha=16, dropout=0.05)
- **Steps**: 150
- **Learning Rate**: 5e-6
- **Batch Size**: 2 (gradient accumulation: 4)
- **Hardware**: a10g-small (~$0.75/hr)
- **Runtime**: ~1 hour

## Reproduction

1. Get a HuggingFace Pro account
2. Set `HF_TOKEN` as a secret
3. Run:

```bash
hf jobs uv run \
  --flavor a10g-small \
  --timeout 14400 \
  --secrets HF_TOKEN \
  "https://huggingface.co/passagereptile455/training-scripts/resolve/main/train_humaneval_clean.py"
```

Script: [passagereptile455/training-scripts](https://huggingface.co/passagereptile455/training-scripts)

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("passagereptile455/qwen3-humaneval-sft")
tokenizer = AutoTokenizer.from_pretrained("passagereptile455/qwen3-humaneval-sft")

messages = [{"role": "user", "content": "Write a Python function to check if a number is prime"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

## Debugging Notes

What broke along the way (5 attempts total):
- TRL API changed: `processing_class` not `tokenizer`
- Auth changed: `HfApi(token=)` not `login()`
- Upload: Need to pass `token=` to `push_to_hub()` explicitly

Most time was spent on infrastructure debugging, not ML.

## Acknowledgments

Based on [Ben Burtenshaw's challenge](https://x.com/ben_burtenshaw/status/1999502002251006449) comparing Claude Code vs Codex for fine-tuning tasks.