Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,36 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: en
|
| 3 |
+
tags:
|
| 4 |
+
- sentiment-analysis
|
| 5 |
+
- distilbert
|
| 6 |
+
- transformers
|
| 7 |
+
license: mit
|
| 8 |
+
license_file: LICENSE
|
| 9 |
+
datasets:
|
| 10 |
+
- imdb
|
| 11 |
+
metrics:
|
| 12 |
+
- accuracy
|
| 13 |
+
- f1
|
| 14 |
+
- precision
|
| 15 |
+
- recall
|
| 16 |
+
model_type: distilbert
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
+
# Fine-tuned DistilBERT for Sentiment Analysis
|
| 20 |
+
|
| 21 |
+
**Model Description**: A fine-tuned DistilBERT model for sentiment analysis on the IMDB dataset, capable of classifying movie reviews as positive or negative.
|
| 22 |
+
|
| 23 |
+
## Model Details
|
| 24 |
+
- **Model Type**: Transformer-based model (DistilBERT)
|
| 25 |
+
- **Number of Labels**: 2 (Positive and Negative)
|
| 26 |
+
- **Training Dataset**: IMDB Reviews
|
| 27 |
+
|
| 28 |
+
## Training
|
| 29 |
+
- **Training Data Size**: 20,000 samples for training and 5,000 samples for evaluation.
|
| 30 |
+
- **Training Procedure**: The model was fine-tuned for 3 epochs with a batch size of 16.
|
| 31 |
+
- **Evaluation Metrics**: Accuracy, Precision, Recall, F1-score.
|
| 32 |
+
|
| 33 |
+
## Usage
|
| 34 |
+
### Installation
|
| 35 |
+
```bash
|
| 36 |
+
pip install transformers
|