metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: BERThard
results: []
license: mit
datasets:
- hard
language:
- ar
pipeline_tag: text-classification
inference: false
BERThard
This model is a fine-tuned version of aubmindlab/bert-base-arabertv2 on the Hotel Arabic Reviews Dataset (HARD) dataset. It achieves the following results on the evaluation set:
- Loss: 0.4141
- Accuracy: 0.8311
Model description
@misc{alshahrani2024arabic,
title={{Arabic Synonym BERT-based Adversarial Examples for Text Classification}},
author={Norah Alshahrani and Saied Alshahrani and Esma Wali and Jeanna Matthews},
year={2024},
eprint={2402.03477},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
Training procedure
We have trained this model using the PaperSpace GPU-Cloud service. We used a machine with 8 CPUs, 45GB RAM, and A6000 GPU with 48GB RAM.
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4488 | 1.0 | 5946 | 0.4104 | 0.8232 |
| 0.3866 | 2.0 | 11892 | 0.4047 | 0.8288 |
| 0.3462 | 3.0 | 17838 | 0.4141 | 0.8311 |
Framework versions
- Transformers 4.28.1
- Pytorch 1.12.1+cu116
- Datasets 2.4.0
- Tokenizers 0.12.1