|
|
--- |
|
|
library_name: peft |
|
|
base_model: aubmindlab/bert-base-arabertv02 |
|
|
tags: |
|
|
- base_model:adapter:aubmindlab/bert-base-arabertv02 |
|
|
- lora |
|
|
- transformers |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: saudi-eou-bert-classifier |
|
|
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. --> |
|
|
|
|
|
# saudi-eou-bert-classifier |
|
|
|
|
|
This model is a fine-tuned version of [aubmindlab/bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.3407 |
|
|
- Accuracy: 0.864 |
|
|
- Auc: 0.921 |
|
|
|
|
|
## 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: 1e-05 |
|
|
- train_batch_size: 16 |
|
|
- eval_batch_size: 16 |
|
|
- seed: 42 |
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_ratio: 0.1 |
|
|
- num_epochs: 10 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Auc | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-----:| |
|
|
| 0.712 | 1.0 | 295 | 0.6541 | 0.619 | 0.685 | |
|
|
| 0.5634 | 2.0 | 590 | 0.4838 | 0.781 | 0.845 | |
|
|
| 0.4258 | 3.0 | 885 | 0.4189 | 0.819 | 0.883 | |
|
|
| 0.3619 | 4.0 | 1180 | 0.3920 | 0.837 | 0.897 | |
|
|
| 0.3366 | 5.0 | 1475 | 0.3684 | 0.853 | 0.907 | |
|
|
| 0.3309 | 6.0 | 1770 | 0.3650 | 0.854 | 0.912 | |
|
|
| 0.3191 | 7.0 | 2065 | 0.3555 | 0.856 | 0.916 | |
|
|
| 0.3028 | 8.0 | 2360 | 0.3432 | 0.864 | 0.919 | |
|
|
| 0.3018 | 9.0 | 2655 | 0.3437 | 0.859 | 0.92 | |
|
|
| 0.2987 | 10.0 | 2950 | 0.3407 | 0.864 | 0.921 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.18.0 |
|
|
- Transformers 4.57.3 |
|
|
- Pytorch 2.9.0+cu126 |
|
|
- Datasets 4.4.1 |
|
|
- Tokenizers 0.22.1 |
