metadata
library_name: transformers
base_model: asafaya/bert-base-arabic
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Sfaya-BBA
results: []
Sfaya-BBA
This model is a fine-tuned version of asafaya/bert-base-arabic on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4582
- Accuracy: 0.8677
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: 0.0005
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 60
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.089 | 0.2041 | 100 | 0.5876 | 0.7882 |
| 0.5172 | 0.4082 | 200 | 0.4480 | 0.8525 |
| 0.5454 | 0.6122 | 300 | 0.4582 | 0.8677 |
| 0.5396 | 0.8163 | 400 | 0.5377 | 0.8307 |
| 0.932 | 1.0204 | 500 | 1.7065 | 0.4448 |
| 1.7739 | 1.2245 | 600 | 1.6662 | 0.4375 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3