hadith-finetuned-ner6
This model is a fine-tuned version of CAMeL-Lab/bert-base-arabic-camelbert-msa-ner on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0961
- Precision: 0.9482
- Recall: 0.9817
- F1: 0.9647
- Accuracy: 0.9734
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.318 | 1.0 | 468 | 0.3680 | 0.7983 | 0.8545 | 0.8255 | 0.8769 |
| 0.2445 | 2.0 | 937 | 0.2620 | 0.8390 | 0.9344 | 0.8841 | 0.9155 |
| 0.1219 | 3.0 | 1405 | 0.1794 | 0.8865 | 0.9530 | 0.9186 | 0.9416 |
| 0.1508 | 4.0 | 1874 | 0.1496 | 0.8988 | 0.9721 | 0.9340 | 0.9511 |
| 0.0934 | 5.0 | 2342 | 0.1216 | 0.9273 | 0.9764 | 0.9512 | 0.9638 |
| 0.1072 | 6.0 | 2811 | 0.1087 | 0.9382 | 0.9797 | 0.9585 | 0.9691 |
| 0.0769 | 7.0 | 3279 | 0.1028 | 0.9417 | 0.9829 | 0.9619 | 0.9712 |
| 0.0453 | 7.99 | 3744 | 0.0961 | 0.9482 | 0.9817 | 0.9647 | 0.9734 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.14.1
- Downloads last month
- 7
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for AhmedTaha012/hadith-finetuned-ner6
Base model
CAMeL-Lab/bert-base-arabic-camelbert-msa-ner