question-detection-ar-20260119
This model is a fine-tuned version of distilbert/distilbert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2406
- Accuracy: 0.9647
- F1: 0.9647
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- 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
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.2947 | 1.0 | 184 | 0.2573 | 0.9185 | 0.9184 |
| 0.1694 | 2.0 | 368 | 0.2380 | 0.9484 | 0.9484 |
| 0.078 | 3.0 | 552 | 0.2595 | 0.9538 | 0.9538 |
| 0.0007 | 4.0 | 736 | 0.3014 | 0.9484 | 0.9483 |
| 0.0002 | 5.0 | 920 | 0.2406 | 0.9647 | 0.9647 |
| 0.0002 | 6.0 | 1104 | 0.2538 | 0.9647 | 0.9647 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.2
- Downloads last month
- 4