fine_tuned_mix40k_arabert_cleaned
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: 0.3804
- Accuracy: 0.8933
- Precision: 0.9219
- Recall: 0.8580
- F1: 0.8888
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 |
|---|---|---|---|---|---|---|---|
| 0.3113 | 1.0 | 10794 | 0.2831 | 0.8782 | 0.8802 | 0.8739 | 0.8770 |
| 0.2268 | 2.0 | 21588 | 0.2901 | 0.8861 | 0.9270 | 0.8369 | 0.8796 |
| 0.1788 | 3.0 | 32382 | 0.3294 | 0.8901 | 0.9086 | 0.8660 | 0.8868 |
| 0.1413 | 4.0 | 43176 | 0.3804 | 0.8933 | 0.9219 | 0.8580 | 0.8888 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1
- Downloads last month
- -