metadata
library_name: transformers
license: apache-2.0
base_model: HooshvareLab/bert-fa-base-uncased
tags:
- generated_from_trainer
model-index:
- name: bert-fa-base-uncased-finetuned-DS_Q_N_C_QA-topAug0.95
results: []
datasets:
- Z-Jafari/PersianQuAD
- Z-Jafari/DS_Q_N_C_QA
bert-fa-base-uncased-finetuned-DS_Q_N_C_QA-topAug0.95
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: 1.2418
- {'exact_match': 76.9, 'f1': 80.90408674324868}
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 |
|---|---|---|---|
| 0.7683 | 1.0 | 1911 | 0.9822 |
| 0.4363 | 2.0 | 3822 | 1.0873 |
| 0.2444 | 3.0 | 5733 | 1.2418 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1