---

license: mit language: en datasets:

• rotten_tomatoes metrics:
• accuracy pipeline_tag: text-classification tags:
• sentiment-analysis
• distilbert

---

DistilBERT Fine-tuned on Rotten Tomatoes

Model Description

This model is a fine-tuned version of distilbert-base-uncased for binary sentiment classification (positive/negative movie reviews).

Training Data

• Dataset: Rotten Tomatoes movie reviews
• Train samples: 8,530
• Test samples: 1,066

Training Procedure

• Base model: distilbert-base-uncased
• Epochs: 3
• Batch size: 16
• Learning rate: 2e-5
• Max sequence length: 128

Evaluation Results

• Accuracy: ~85% on test set

Usage

from transformers import pipeline

classifier = pipeline("sentiment-analysis", model="Nav772/distilbert-rotten-tomatoes-sentiment")
result = classifier("This movie was great!")
print(result)

Limitations

• Trained only on movie reviews; may not generalize to other domains
• English language only
• Binary classification only (no neutral category)