bert-fa-base-uncased-finetuned-nestedRewrite_QA
This model is a fine-tuned version of HooshvareLab/bert-fa-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4838
- {'exact_match': 72.3, 'f1': 75.96127432485267}
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: 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
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7103 | 1.0 | 2018 | 1.0847 |
| 0.3990 | 2.0 | 4036 | 1.2622 |
| 0.2382 | 3.0 | 6054 | 1.4838 |
Framework versions
- Transformers 5.16.1
- Pytorch 2.11.0+cu128
- Datasets 4.8.5
- Tokenizers 0.23.1