Bencode92/tradepulse-finbert-sentiment
Description
Fine-tuned FinBERT model for financial sentiment analysis in TradePulse.
Task: Sentiment Classification
Target Column: label
Labels: ['negative', 'neutral', 'positive']
Performance
Last training: 2026-04-20 17:22
Dataset: base_reference.csv (1797 samples)
| Metric | Value |
|---|---|
| Loss | 0.0000 |
| Accuracy | 1.0000 |
| F1 Score | 1.0000 |
| F1 Macro | 1.0000 |
| Precision | 1.0000 | | Recall | 1.0000 |
Training Details
- Base Model: Bencode92/tradepulse-finbert-sentiment
- Training Mode: Incremental
- Epochs: 2
- Learning Rate: 1e-05
- Batch Size: 4
- Class Balancing: None
Usage
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
tokenizer = AutoTokenizer.from_pretrained("Bencode92/tradepulse-finbert-sentiment")
model = AutoModelForSequenceClassification.from_pretrained("Bencode92/tradepulse-finbert-sentiment")
# Example prediction
text = "Apple reported strong quarterly earnings beating expectations"
inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
outputs = model(**inputs)
predictions = outputs.logits.softmax(dim=-1)
Model Card Authors
- TradePulse ML Team
- Auto-generated on 2026-04-20 17:22:25