finetuned-arabert-textclassification
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: 0.1374
- Accuracy: 0.9596
- Precision: 0.9863
- Recall: 0.9513
- F1: 0.9685
Model description
More information needed
Intended uses & limitations
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 |
|---|---|---|---|---|---|---|---|
| 0.125 | 1.0 | 69088 | 0.0901 | 0.9720 | 0.9805 | 0.9765 | 0.9785 |
| 0.1001 | 2.0 | 138176 | 0.1109 | 0.9741 | 0.9770 | 0.9834 | 0.9802 |
| 0.0962 | 3.0 | 207264 | 0.0995 | 0.9740 | 0.9739 | 0.9867 | 0.9802 |
| 0.0979 | 4.0 | 276352 | 0.1374 | 0.9596 | 0.9863 | 0.9513 | 0.9685 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.2.0
- Tokenizers 0.12.1
- Downloads last month
- 3