metadata
language: en
license: apache-2.0
tags:
- text-classification
- news
- bert
- modernbert
- transformers
- supervised
datasets:
- heegyu/news-category-dataset
metrics:
- accuracy
- f1
model-index:
- name: ModernBERT News Classifier
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: HuffPost News Category
type: heegyu/news-category-dataset
metrics:
- name: Accuracy
type: accuracy
value: 0.72
- name: Macro F1
type: f1
value: 0.63
base_model:
- answerdotai/ModernBERT-large
ModernBERT — News Classifier
Fine-tuned ModernBERT for classifying news text into multiple categories.
- Base model: answerdotai/ModernBERT-large
- Task: Text classification
- Dataset: HuffPost News Category
- Input: headline + short description
- Output: predicted category (top-k supported)
Usage
from transformers import pipeline
classifier = pipeline(
"text-classification",
model="kurcontko/modernbert-news-classifier",
top_k=3
)
print(classifier("Apple unveils new AI models on latest iPhone"))
Evaluation
| Metric | Score |
|---|---|
| Accuracy | 0.72 |
| Macro F1 | 0.63 |
Evaluated on the validation split of the HuffPost News Category dataset.
Training
Max sequence length: 512
Batch size: 32
Epochs: 3
Early stopping enabled
Input was constructed as headline + short_description.