---
library_name: transformers
license: apache-2.0
base_model: Z-Jafari/bert-base-multilingual-cased-finetuned-PersianQuAD-3epochs
tags:
- generated_from_trainer
model-index:
- name: bert-base-multilingual-cased-finetuned-PersianQuAD_DeepseekQA_QA_Ch-3epochs
  results: []
datasets:
- Z-Jafari/PersianQuAD
- Z-Jafari/PersianQuAD_DeepseekQA_QA_Ch
language:
- fa
metrics:
- f1
- exact_match
pipeline_tag: question-answering
---

<!-- 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. -->

# bert-base-multilingual-cased-finetuned-PersianQuAD_DeepseekQA_QA_Ch-3epochs

This model is a fine-tuned version of [Z-Jafari/bert-base-multilingual-cased-finetuned-PersianQuAD-3epochs](https://huggingface.co/Z-Jafari/bert-base-multilingual-cased-finetuned-PersianQuAD-3epochs) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1974
- {'exact_match': 79.0, 'f1': 81.76440836940834}

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 0.4442        | 1.0   | 2166 | 0.9220          |
| 0.2865        | 2.0   | 4332 | 1.0993          |
| 0.1559        | 3.0   | 6498 | 1.1974          |


### Framework versions

- Transformers 4.57.3
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1