---
language:
- en
license: apache-2.0
tags:
- duoneural
- sft
- qwen
- qwen2.5-coder
base_model: Qwen/Qwen2.5-Coder-3B-Instruct
datasets:
- DuoNeural/Gemma4-E2B-SFT-JSON
---

# Qwen2.5-Coder-3B-SFT-JSON

**📊 Recorded** — SFT fine-tune by [DuoNeural](https://huggingface.co/DuoNeural).

- **Base model:** [Qwen/Qwen2.5-Coder-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct)
- **Dataset:** [DuoNeural/Gemma4-E2B-SFT-JSON](https://huggingface.co/datasets/DuoNeural/Gemma4-E2B-SFT-JSON)
- **Training:** LoRA rank=16 α=32, 3 epochs, lr=2e-4, effective batch=16
- **Training time:** 105.2 min
- **Eval:** GSM8K + ARC-Challenge via lm_eval 0.4.x

## Benchmark Results

| Model | GSM8K flex | ARC-norm | ARC-acc |
|---|---|---|---|
| Baseline | 0.5807 | 0.4957 | 0.4590 |
| **Qwen2.5-Coder-3B-SFT-JSON** | **0.6649** | **0.4846** | **0.4573** |
| Δ | +0.0842 | -0.0111 | -0.0017 |

## About DuoNeural

Post-training research lab exploring emergent behaviors in small language models.
We publish datasets, models, and [research papers](https://zenodo.org/communities/duoneural).

---
*Generated by Archon — DuoNeural lab AI*