|
|
--- |
|
|
language: ar |
|
|
license: mit |
|
|
base_model: UBC-NLP/MARBERT |
|
|
tags: |
|
|
- sentiment-analysis |
|
|
- arabic |
|
|
- bert |
|
|
pipeline_tag: text-classification |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# arabic-sentiment-analysis-model |
|
|
|
|
|
This model is a fine-tuned version of [UBC-NLP/MARBERT](https://huggingface.co/UBC-NLP/MARBERT) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0339 |
|
|
|
|
|
## Model description |
|
|
|
|
|
This model is fine-tuned for Arabic Sentiment Analysis. It can classify Arabic text into different emotional categories (Positive/Negative). |
|
|
|
|
|
- **Developed by:** Hager Abbas |
|
|
- **Language:** Arabic |
|
|
- **Model Type:** Text Classification |
|
|
- **Fine-tuned from:** [اسم الموديل الأصلي اللي استخدمناه، غالباً bert-base-arabic] |
|
|
|
|
|
## Intended uses & limitations |
|
|
|
|
|
This model is intended for analyzing social media posts, customer reviews, and general Arabic text to determine sentiment. |
|
|
## How to use |
|
|
```python |
|
|
from transformers import pipeline |
|
|
classifier = pipeline("sentiment-analysis", model="HagerAbbas/اسم-الموديل-بتاعك") |
|
|
classifier("أنا سعيد جداً بهذا الإنجاز") |
|
|
|
|
|
## Training and evaluation data |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Training procedure |
|
|
|
|
|
### Training hyperparameters |
|
|
|
|
|
The following hyperparameters were used during training: |
|
|
- learning_rate: 2e-05 |
|
|
- train_batch_size: 16 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 3 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 0.168 | 1.0 | 113 | 0.2174 | |
|
|
| 0.1619 | 2.0 | 226 | 0.0477 | |
|
|
| 0.014 | 3.0 | 339 | 0.0339 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.57.3 |
|
|
- Pytorch 2.9.0+cu126 |
|
|
- Datasets 4.4.2 |
|
|
- Tokenizers 0.22.1 |
|
|
|
