| --- |
| tags: |
| - generated_from_trainer |
| metrics: |
| - precision |
| - recall |
| - f1 |
| - accuracy |
| model-index: |
| - name: AraBERT_token_classification_Araieval24_binary |
| results: [] |
| --- |
| |
| <!-- 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. --> |
|
|
| # AraBERT_token_classification_Araieval24_binary |
|
|
| This model is a fine-tuned version of [aubmindlab/bert-base-arabertv2](https://huggingface.co/aubmindlab/bert-base-arabertv2) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 1.0062 |
| - Precision: 0.1851 |
| - Recall: 0.2340 |
| - F1: 0.2067 |
| - Accuracy: 0.7436 |
|
|
| ## 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 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: linear |
| - num_epochs: 10 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
| |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
| | 0.5408 | 1.0 | 776 | 0.5362 | 0.1292 | 0.1665 | 0.1455 | 0.7566 | |
| | 0.4664 | 2.0 | 1552 | 0.5402 | 0.1399 | 0.2139 | 0.1692 | 0.7462 | |
| | 0.3855 | 3.0 | 2328 | 0.5915 | 0.1632 | 0.1935 | 0.1771 | 0.7552 | |
| | 0.2911 | 4.0 | 3104 | 0.6717 | 0.1712 | 0.1953 | 0.1825 | 0.7457 | |
| | 0.2334 | 5.0 | 3880 | 0.7420 | 0.1826 | 0.2066 | 0.1939 | 0.7473 | |
| | 0.18 | 6.0 | 4656 | 0.8034 | 0.1835 | 0.2278 | 0.2033 | 0.7447 | |
| | 0.1611 | 7.0 | 5432 | 0.8849 | 0.1949 | 0.2275 | 0.2099 | 0.7515 | |
| | 0.1323 | 8.0 | 6208 | 0.9530 | 0.1870 | 0.2337 | 0.2078 | 0.7449 | |
| | 0.1133 | 9.0 | 6984 | 1.0043 | 0.1909 | 0.2348 | 0.2106 | 0.7434 | |
| | 0.1007 | 10.0 | 7760 | 1.0062 | 0.1851 | 0.2340 | 0.2067 | 0.7436 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.30.2 |
| - Pytorch 2.3.1+cu121 |
| - Datasets 2.20.0 |
| - Tokenizers 0.13.3 |
|
|
