metadata
library_name: transformers
license: apache-2.0
base_model: CAMeL-Lab/bert-base-arabic-camelbert-mix-ner
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: pii_ar_detector
results: []
pii_ar_detector
This model is a fine-tuned version of CAMeL-Lab/bert-base-arabic-camelbert-mix-ner on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0931
- Precision: 0.9476
- Recall: 0.9620
- F1: 0.9547
- Accuracy: 0.9870
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: 16
- eval_batch_size: 16
- seed: 42
- 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: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0886 | 1.0 | 12425 | 0.0917 | 0.8918 | 0.9041 | 0.8979 | 0.9652 |
| 0.0624 | 2.0 | 24850 | 0.0775 | 0.9037 | 0.9343 | 0.9187 | 0.9747 |
| 0.0422 | 3.0 | 37275 | 0.0634 | 0.9205 | 0.9461 | 0.9331 | 0.9823 |
| 0.0274 | 4.0 | 49700 | 0.0682 | 0.9316 | 0.9521 | 0.9418 | 0.9840 |
| 0.0195 | 5.0 | 62125 | 0.0702 | 0.9365 | 0.9567 | 0.9465 | 0.9853 |
| 0.0135 | 6.0 | 74550 | 0.0737 | 0.9394 | 0.9583 | 0.9487 | 0.9857 |
| 0.0084 | 7.0 | 86975 | 0.0801 | 0.9444 | 0.9595 | 0.9519 | 0.9864 |
| 0.0069 | 8.0 | 99400 | 0.0857 | 0.9449 | 0.9624 | 0.9536 | 0.9870 |
| 0.0043 | 9.0 | 111825 | 0.0887 | 0.9488 | 0.9608 | 0.9548 | 0.9869 |
| 0.003 | 10.0 | 124250 | 0.0931 | 0.9476 | 0.9620 | 0.9547 | 0.9870 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1