---
library_name: transformers
license: apache-2.0
base_model:
- Qwen/Qwen3-8B
tags:
- finance
- reasoning
- chain-of-thought
- financial-analysis
model-index:
- name: ODA-Fin-SFT-8B
  results: []
datasets:
- OpenDataArena/ODA-Fin-SFT-318k
language:
- en
- zh
metrics:
- accuracy
- f1
pipeline_tag: question-answering
---



<div align="center">
  <h1>Unlocking Data Value in Finance: A Study on Distillation
and Difficulty-Aware Training</h1>

</div>

<div align="center">
  
[![Paper](https://img.shields.io/badge/arXiv-Paper-red)](https://arxiv.org/abs/2603.07223)
[![Collections](https://img.shields.io/badge/🤗-Collections-yellow)](https://huggingface.co/collections/OpenDataArena/oda-finance)

</div>

<figure align="center">
  <img src="imgs/model_compare.png" width="100%" alt="Model Performance Comparison">
  <figcaption><em>Average score across Financial benchmarks. ODA-Fin-RL/SFT-8B demonstrates strong performance relative to thinking models with significantly more parameters.</em></figcaption>
</figure>

---

This repository provides **ODA-Fin-SFT-8B**, a financial language model trained on high-quality Chain-of-Thought data. For the reinforcement learning version, see [ODA-Fin-RL-8B](https://huggingface.co/OpenDataArena/ODA-Fin-RL-8B).

## 📖 Overview

**ODA-Fin-SFT-8B** is an 8B-parameter financial language model built on Qwen3-8B, fine-tuned on the **ODA-Fin-SFT-318K** dataset—a meticulously curated corpus of 318K samples with high-quality Chain-of-Thought (CoT) reasoning traces distilled from **Qwen3-235B-A22B-Thinking**. This model establishes a robust foundation for financial reasoning, demonstrating state-of-the-art performance across diverse financial tasks.

### 🎯 Key Highlights

- **Base Model**: Qwen3-8B
- **Training Data**: ODA-Fin-SFT-318K (318K samples with verified CoT)
- **Training Method**: Supervised Fine-Tuning with full-parameter updates
- **Avg Performance**: 72.1% across 9 financial benchmarks
- **Key Strengths**: 
  - Balanced performance across general financial understanding, sentiment analysis, and numerical reasoning
  - Serves as optimal initialization for subsequent RL training

---

## 🧠 Model Training

### Training Configuration

```yaml
Base Model: Qwen/Qwen3-8B
Training Framework: Full-parameter fine-tuning
Hardware: 16×NVIDIA A100 (80GB)
Sequence Length: 16,384 tokens
Batch Size: 1 per device
Gradient Accumulation: 16 steps
Learning Rate: 1.0e-5 (cosine schedule)
Warmup Ratio: 0.1
Epochs: 3
Training Data: ODA-Fin-SFT-318K
```


---

## 📊 Model Performance


Models trained on ODA-Fin-SFT-318K demonstrate superior performance across 9 financial benchmarks:

<figure align="center">
  <img src="imgs/main_results_table.png" width="100%" alt="p">
  <figcaption><em>Main Results. 'FinIQ', 'HL' and 'CFQA' refer to FinanceIQ, Headlines, and ConvFinQA benchmarks.</em></figcaption>
</figure>

---


## 📊 Benchmark Details

### General Financial Understanding

- **FinEval** (Chinese): Financial domain knowledge across banking, insurance, securities (Acc/zh)
- **Finova**: Agent-level financial reasoning and compliance verification (Acc/zh)
- **FinanceIQ**: Professional certifications (CPA, CFA) expertise assessment (Acc/zh)

### Sentiment Analysis

- **FOMC**: Hawkish vs. Dovish monetary policy stance classification (Weighted-F1/en)
- **FPB**: Financial PhraseBank sentiment classification (Weighted-F1/en)
- **Headlines**: Financial news headline sentiment interpretation (Weighted-F1/en)

### Numerical Reasoning

- **FinQA**: Complex numerical reasoning over financial reports (Acc/en)
- **TaTQA**: Hybrid tabular-textual arithmetic operations (Acc/en)
- **ConvFinQA**: Multi-turn conversational numerical analysis (Acc/en)

---

## 📚 Citation

```bibtex
@misc{cao2026unlockingdatavaluefinance,
      title={Unlocking Data Value in Finance: A Study on Distillation and Difficulty-Aware Training}, 
      author={Chuxue Cao and Honglin Lin and Zhanping Zhong and Xin Gao and Mengzhang Cai and Conghui He and Sirui Han and Lijun Wu},
      year={2026},
      eprint={2603.07223},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2603.07223}, 
}
```

---

## 📄 License

This model is released under the [Apache 2.0 License](https://opensource.org/licenses/Apache-2.0). The training data (ODA-Fin-SFT-318K) aggregates from 25+ open-source repositories, each with their own licenses.

---

## 🤝 Acknowledgments

We thank the creators of DianJin-R1-Data, Agentar-DeepFinance-100K, financial_phrasebank, Finance-Instruct-500k, and others. We also thank the Qwen team for the powerful Qwen3 series models.

---

## 🔗 Related Resources

- **SFT Dataset**: [ODA-Fin-SFT-318K](https://huggingface.co/datasets/OpenDataArena/ODA-Fin-SFT-318k)
- **RL Dataset**: [ODA-Fin-RL-12K](https://huggingface.co/datasets/OpenDataArena/ODA-Fin-RL-12K)
<!-- - **RL Model**: [ODA-Fin-SFT-8B](https://huggingface.co/OpenDataArena/ODA-Fin-SFT-8B) -->
- **RL Model**: [ODA-Fin-RL-8B](https://huggingface.co/OpenDataArena/ODA-Fin-RL-8B)

<!-- - **Paper**: [arXiv:2512.XXXXX](https://arxiv.org/abs/2512.XXXXX) -->