---
language: [en]
license: apache-2.0
library_name: transformers
pipeline_tag: text-classification
datasets: [financial_phrase_bank]
base_model: ProsusAI/finbert
tags:
- sentiment-analysis
- finance
- text-classification
model-index:
- name: Financial Sentiment BERT (FinBERT fine-tune)
  results:
  - task:
      type: text-classification
      name: Sentiment Analysis
    dataset:
      name: Financial PhraseBank
      type: financial_phrase_bank
      split: test
    metrics:
    - type: accuracy
      value: 0.81
    - type: f1
      name: macro F1
      value: 0.79
---
# Financial Sentiment BERT (FinBERT fine-tune)

Sentence-level classifier for **English financial news**.

| Item | Value |
|------|-------|
| **Base model** | `ProsusAI/finbert` |
| **Dataset** | Financial PhraseBank |
| **Labels** | positive (0) · negative (1) · neutral (2) |
| **Epochs** | 3 (early-stopped) |
| **Best val acc** | 0.8356 |
| **Test acc** | 0.81 |
| **Hardware** | CPU-only training |

## Usage

```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tok   = AutoTokenizer.from_pretrained("Kroalist/financial-sentiment-bert")
model = AutoModelForSequenceClassification.from_pretrained("Kroalist/financial-sentiment-bert")
```

_Last updated: 2025-04-23_