<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
EnhancedModel
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: 0.0455
- Accuracy: 0.98
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: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2872 | 0.05 | 50 | 0.1340 | 0.94 |
| 0.1292 | 0.11 | 100 | 0.1201 | 0.96 |
| 0.1141 | 0.16 | 150 | 0.0616 | 0.98 |
| 0.1242 | 0.21 | 200 | 0.0554 | 0.98 |
| 0.1148 | 0.27 | 250 | 0.1123 | 0.98 |
| 0.0798 | 0.32 | 300 | 0.0946 | 0.98 |
| 0.1207 | 0.37 | 350 | 0.1145 | 0.98 |
| 0.0655 | 0.43 | 400 | 0.0778 | 0.98 |
| 0.084 | 0.48 | 450 | 0.0472 | 0.99 |
| 0.0783 | 0.53 | 500 | 0.0603 | 0.97 |
| 0.1034 | 0.58 | 550 | 0.0806 | 0.98 |
| 0.0556 | 0.64 | 600 | 0.0598 | 0.99 |
| 0.0702 | 0.69 | 650 | 0.0638 | 0.99 |
| 0.0665 | 0.74 | 700 | 0.0971 | 0.98 |
| 0.0481 | 0.8 | 750 | 0.0956 | 0.98 |
| 0.0474 | 0.85 | 800 | 0.0444 | 0.99 |
| 0.0661 | 0.9 | 850 | 0.0550 | 0.99 |
| 0.0522 | 0.96 | 900 | 0.0397 | 0.99 |
| 0.0857 | 1.01 | 950 | 0.0484 | 0.99 |
| 0.027 | 1.06 | 1000 | 0.0655 | 0.99 |
| 0.0224 | 1.12 | 1050 | 0.0548 | 0.99 |
| 0.0177 | 1.17 | 1100 | 0.0573 | 0.99 |
| 0.0278 | 1.22 | 1150 | 0.0400 | 0.99 |
| 0.0376 | 1.28 | 1200 | 0.0499 | 0.99 |
| 0.0412 | 1.33 | 1250 | 0.0455 | 0.98 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
