metadata
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: AraBERT_token_classification_AraEval24_basic_single
results: []
AraBERT_token_classification_AraEval24_basic_single
This model is a fine-tuned version of aubmindlab/bert-base-arabert on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8309
- Precision: 0.0558
- Recall: 0.0104
- F1: 0.0175
- Accuracy: 0.8720
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.5987 | 1.0 | 2830 | 0.7729 | 1.0 | 0.0002 | 0.0004 | 0.8751 |
| 0.5694 | 2.0 | 5660 | 0.7337 | 0.0 | 0.0 | 0.0 | 0.8751 |
| 0.4944 | 3.0 | 8490 | 0.7180 | 0.0 | 0.0 | 0.0 | 0.8751 |
| 0.4569 | 4.0 | 11320 | 0.7157 | 0.0683 | 0.0039 | 0.0073 | 0.8746 |
| 0.4453 | 5.0 | 14150 | 0.7393 | 0.0973 | 0.0063 | 0.0119 | 0.8745 |
| 0.3859 | 6.0 | 16980 | 0.7607 | 0.0694 | 0.0042 | 0.0080 | 0.8745 |
| 0.3847 | 7.0 | 19810 | 0.7712 | 0.0838 | 0.0074 | 0.0136 | 0.8742 |
| 0.3582 | 8.0 | 22640 | 0.7805 | 0.0462 | 0.0081 | 0.0138 | 0.8723 |
| 0.3368 | 9.0 | 25470 | 0.8114 | 0.0542 | 0.0078 | 0.0136 | 0.8727 |
| 0.3185 | 10.0 | 28300 | 0.8309 | 0.0558 | 0.0104 | 0.0175 | 0.8720 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.13.3