---
license: apache-2.0
base_model: riotu-lab/ArabianGPT-1.5B
tags:
- generated_from_trainer
metrics:
- bleu
- rouge
model-index:
- name: res_nw_dj_1.5b
  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. -->

# res_nw_dj_1.5b

This model is a fine-tuned version of [riotu-lab/ArabianGPT-1.5B](https://huggingface.co/riotu-lab/ArabianGPT-1.5B) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6726
- Bleu: 0.3710
- Rouge1: 0.5676
- Rouge2: 0.3031
- Rougel: 0.5652

## 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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 20.0

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Bleu   | Rouge1 | Rouge2 | Rougel |
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:------:|
| 1.4014        | 1.0   | 2679  | 0.7688          | 0.3339 | 0.4842 | 0.2115 | 0.4815 |
| 0.706         | 2.0   | 5358  | 0.7103          | 0.3526 | 0.5204 | 0.2487 | 0.5180 |
| 0.6195        | 3.0   | 8037  | 0.6853          | 0.3635 | 0.5434 | 0.2748 | 0.5411 |
| 0.5498        | 4.0   | 10716 | 0.6749          | 0.3675 | 0.5583 | 0.2898 | 0.5558 |
| 0.4884        | 5.0   | 13395 | 0.6726          | 0.3710 | 0.5676 | 0.3031 | 0.5652 |
| 0.4327        | 6.0   | 16074 | 0.6755          | 0.3767 | 0.5737 | 0.3128 | 0.5714 |
| 0.3816        | 7.0   | 18753 | 0.6852          | 0.3766 | 0.5767 | 0.3159 | 0.5746 |
| 0.3353        | 8.0   | 21432 | 0.6988          | 0.3721 | 0.5774 | 0.3198 | 0.5754 |
| 0.2942        | 9.0   | 24111 | 0.7148          | 0.3768 | 0.5785 | 0.3207 | 0.5763 |
| 0.2579        | 10.0  | 26790 | 0.7326          | 0.3760 | 0.5807 | 0.3234 | 0.5784 |


### Framework versions

- Transformers 4.45.0.dev0
- Pytorch 2.3.1+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1