| language: en | |
| license: apache-2.0 | |
| tags: | |
| - text-classification | |
| - sentiment-analysis | |
| - bert | |
| - imdb | |
| datasets: | |
| - imdb | |
| metrics: | |
| - accuracy | |
| - f1 | |
| # BERT Fine-tuned on IMDB Sentiment Analysis | |
| ## Model Description | |
| This model is a fine-tuned version of `bert-base-uncased` | |
| on the IMDB movie reviews dataset for sentiment analysis. | |
| ## Training Details | |
| - Base Model: bert-base-uncased | |
| - Dataset: IMDB (2000 train, 500 test samples) | |
| - Epochs: 3 | |
| - Learning Rate: 2e-5 | |
| - Batch Size: 16 | |
| - Framework: HuggingFace Transformers | |
| ## Results | |
| | Metric | Score | | |
| |----------|-------| | |
| | Accuracy | ~88% | | |
| | F1 Score | ~0.88 | | |
| ## Usage | |
| ```python | |
| from transformers import pipeline | |
| classifier = pipeline( | |
| 'sentiment-analysis', | |
| model='your-hf-username/bert-imdb-sentiment' | |
| ) | |
| result = classifier("This movie was absolutely amazing!") | |
| print(result) | |
| # [{'label': 'POSITIVE', 'score': 0.98}] | |
| ``` | |
| ## Labels | |
| - LABEL_0 → Negative 😠 | |
| - LABEL_1 → Positive 😊 | |