metadata
library_name: transformers
base_model: aubmindlab/bert-base-arabertv2
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: arabert-hate-speech
results: []
arabert-hate-speech
This model is a fine-tuned version of aubmindlab/bert-base-arabertv2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5588
- Accuracy: 0.9451
- Precision: 0.9464
- Recall: 0.9451
- F1: 0.9450
Model description
More information needed
Intended uses & limitations
More information needed
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: 32
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 500
- num_epochs: 20
- mixed_precision_training: Native AMP
- label_smoothing_factor: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 1.6993 | 1.0 | 100 | 1.5844 | 0.3845 | 0.3695 | 0.3845 | 0.3545 |
| 1.2593 | 2.0 | 200 | 1.0278 | 0.7662 | 0.7766 | 0.7662 | 0.7634 |
| 0.8076 | 3.0 | 300 | 0.6558 | 0.9056 | 0.9076 | 0.9056 | 0.9059 |
| 0.6413 | 4.0 | 400 | 0.5866 | 0.9282 | 0.9310 | 0.9282 | 0.9280 |
| 0.5734 | 5.0 | 500 | 0.5556 | 0.9451 | 0.9457 | 0.9451 | 0.9450 |
| 0.5203 | 6.0 | 600 | 0.5825 | 0.9338 | 0.9389 | 0.9338 | 0.9344 |
| 0.4843 | 7.0 | 700 | 0.5588 | 0.9451 | 0.9464 | 0.9451 | 0.9450 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1