---
license: apache-2.0
base_model: makhataei/qa-persian-distilbert-fa-zwnj-base
tags:
- generated_from_trainer
datasets:
- parsinlu_reading_comprehension
model-index:
- name: qa-persian-distilbert-fa-zwnj-base
  results: []
---

<!-- 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. -->

# qa-persian-distilbert-fa-zwnj-base

This model is a fine-tuned version of [makhataei/qa-persian-distilbert-fa-zwnj-base](https://huggingface.co/makhataei/qa-persian-distilbert-fa-zwnj-base) on the parsinlu_reading_comprehension dataset.
It achieves the following results on the evaluation set:
- Loss: 3.2461

## 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: 1e-05
- train_batch_size: 13
- eval_batch_size: 13
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.665         | 1.0   | 47   | 2.5329          |
| 1.983         | 2.0   | 94   | 2.5824          |
| 1.6365        | 3.0   | 141  | 2.6814          |
| 1.329         | 4.0   | 188  | 2.7567          |
| 1.067         | 5.0   | 235  | 2.8691          |
| 0.9063        | 6.0   | 282  | 3.0056          |
| 0.7492        | 7.0   | 329  | 3.0976          |
| 0.6718        | 8.0   | 376  | 3.1850          |
| 0.5637        | 9.0   | 423  | 3.2335          |
| 0.5525        | 10.0  | 470  | 3.2461          |


### Framework versions

- Transformers 4.35.2
- Pytorch 2.0.1+cu117
- Datasets 2.15.0
- Tokenizers 0.15.0