Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
language: en
|
| 4 |
+
tags:
|
| 5 |
+
- sentiment-analysis
|
| 6 |
+
- text-classification
|
| 7 |
+
- distilbert
|
| 8 |
+
- imdb
|
| 9 |
+
datasets:
|
| 10 |
+
- imdb
|
| 11 |
+
metrics:
|
| 12 |
+
- accuracy
|
| 13 |
+
- f1
|
| 14 |
+
- precision
|
| 15 |
+
- recall
|
| 16 |
+
---
|
| 17 |
+
|
| 18 |
+
# IMDB Sentiment Analysis Model
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of `distilbert-base-uncased` on the IMDB dataset for sentiment analysis.
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
The model was trained on the IMDB movie reviews dataset to classify movie reviews as either positive (1) or negative (0).
|
| 25 |
+
|
| 26 |
+
## Training procedure
|
| 27 |
+
|
| 28 |
+
- Model: DistilBERT (distilbert-base-uncased)
|
| 29 |
+
- Training Data: IMDB Dataset (40,000 training samples)
|
| 30 |
+
- Validation Data: 5,000 samples
|
| 31 |
+
- Test Data: 5,000 samples
|
| 32 |
+
- Epochs: 2
|
| 33 |
+
- Batch Size: 32
|
| 34 |
+
- Learning Rate: 2e-5
|
| 35 |
+
- Max Sequence Length: 256 tokens
|
| 36 |
+
|
| 37 |
+
## Usage
|