---
license: apache-2.0
base_model: makhataei/qa-persian-albert-fa-zwnj-base-v2
tags:
- generated_from_trainer
datasets:
- pquad
model-index:
- name: qa-persian-albert-fa-zwnj-base-v2
  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-albert-fa-zwnj-base-v2

This model is a fine-tuned version of [makhataei/qa-persian-albert-fa-zwnj-base-v2](https://huggingface.co/makhataei/qa-persian-albert-fa-zwnj-base-v2) on the pquad dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4440

## 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: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5

### Training results

| Training Loss | Epoch | Step  | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 1.5731        | 0.12  | 500   | 1.6899          |
| 1.4759        | 0.25  | 1000  | 1.4951          |
| 1.3844        | 0.38  | 1500  | 1.5161          |
| 1.3116        | 0.5   | 2000  | 1.3618          |
| 1.3055        | 0.62  | 2500  | 1.3795          |
| 1.2364        | 0.75  | 3000  | 1.3386          |
| 1.2189        | 0.88  | 3500  | 1.3131          |
| 1.1737        | 1.0   | 4000  | 1.2202          |
| 1.0047        | 1.12  | 4500  | 1.2268          |
| 0.9573        | 1.25  | 5000  | 1.3119          |
| 0.978         | 1.38  | 5500  | 1.1918          |
| 0.9655        | 1.5   | 6000  | 1.1896          |
| 0.9505        | 1.62  | 6500  | 1.1730          |
| 0.9379        | 1.75  | 7000  | 1.1215          |
| 0.9237        | 1.88  | 7500  | 1.0691          |
| 0.8911        | 2.0   | 8000  | 1.0819          |
| 0.6874        | 2.12  | 8500  | 1.1670          |
| 0.6919        | 2.25  | 9000  | 1.1506          |
| 0.7118        | 2.38  | 9500  | 1.1352          |
| 0.7062        | 2.5   | 10000 | 1.1762          |
| 0.7077        | 2.62  | 10500 | 1.1072          |
| 0.7055        | 2.75  | 11000 | 1.0788          |
| 0.6869        | 2.88  | 11500 | 1.0863          |
| 0.6707        | 3.0   | 12000 | 1.0167          |
| 0.4597        | 3.12  | 12500 | 1.2769          |
| 0.4652        | 3.25  | 13000 | 1.1891          |
| 0.4673        | 3.38  | 13500 | 1.1466          |
| 0.4644        | 3.5   | 14000 | 1.1818          |
| 0.4701        | 3.62  | 14500 | 1.1939          |
| 0.4765        | 3.75  | 15000 | 1.1518          |
| 0.4537        | 3.88  | 15500 | 1.1528          |
| 0.4164        | 4.0   | 16000 | 1.2239          |
| 0.2465        | 4.12  | 16500 | 1.4501          |
| 0.2495        | 4.25  | 17000 | 1.3717          |
| 0.263         | 4.38  | 17500 | 1.4030          |
| 0.2423        | 4.5   | 18000 | 1.4249          |
| 0.2297        | 4.62  | 18500 | 1.4387          |
| 0.227         | 4.75  | 19000 | 1.4600          |
| 0.239         | 4.88  | 19500 | 1.4452          |
| 0.2307        | 5.0   | 20000 | 1.4440          |


### Framework versions

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