|
--- |
|
language: en |
|
license: mit |
|
datasets: imdb |
|
tags: |
|
- sentiment-analysis |
|
- transformers |
|
- huggingface |
|
--- |
|
|
|
# 🎬 IMDb Sentiment Classifier |
|
This is a fine-tuned **DistilBERT model** for analyzing sentiment in IMDb movie reviews. |
|
|
|
## 📌 Dataset |
|
- **Source:** IMDb dataset from Hugging Face Datasets |
|
- **Task:** Binary classification (Positive / Negative) |
|
|
|
## 📌 Training Details |
|
- **Model:** `distilbert-base-uncased` |
|
- **Learning rate:** `2e-5` |
|
- **Batch size:** `4` |
|
- **Epochs:** `1` |
|
- **Loss function:** CrossEntropyLoss |
|
|
|
## 📌 Evaluation Results |
|
| Metric | Score | |
|
|------------|--------| |
|
| Accuracy | 92.5% | |
|
| F1-score | 92.6% | |
|
| Precision | 92.9% | |
|
| Recall | 92.3% | |
|
|
|
## 📌 How to Use |
|
```python |
|
from transformers import pipeline |
|
|
|
classifier = pipeline("text-classification", model="Camilla9000/imdb-sentiment-classifier") |
|
print(classifier("This movie was amazing!")) |
|
|
