fine-tuned-arabert-ned-latest
This model is a fine-tuned version of aubmindlab/bert-base-arabertv02 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1399
- Accuracy: 0.9741
- Precision: 0.9789
- Recall: 0.9818
- F1: 0.9803
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.1337 | 1.0 | 56232 | 0.1134 | 0.9716 | 0.9761 | 0.9809 | 0.9785 |
| 0.1031 | 2.0 | 112464 | 0.1135 | 0.9742 | 0.9765 | 0.9846 | 0.9805 |
| 0.0916 | 3.0 | 168696 | 0.1060 | 0.9745 | 0.9791 | 0.9822 | 0.9807 |
| 0.0812 | 4.0 | 224928 | 0.1138 | 0.9733 | 0.9787 | 0.9808 | 0.9798 |
| 0.076 | 5.0 | 281160 | 0.1277 | 0.9745 | 0.9782 | 0.9832 | 0.9807 |
| 0.0676 | 6.0 | 337392 | 0.1399 | 0.9741 | 0.9789 | 0.9818 | 0.9803 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1
- Downloads last month
- -