---
license: apache-2.0
base_model: riotu-lab/ArabianGPT-03B
tags:
- generated_from_trainer
metrics:
- bleu
- rouge
model-index:
- name: res_nw_dj_03
  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_03

This model is a fine-tuned version of [riotu-lab/ArabianGPT-03B](https://huggingface.co/riotu-lab/ArabianGPT-03B) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5335
- Bleu: 0.4225
- Rouge1: 0.6608
- Rouge2: 0.4163
- Rougel: 0.6590

## 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 |
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:------:|
| 0.8829        | 1.0   | 2679  | 0.5616          | 0.4033 | 0.6239 | 0.3696 | 0.6222 |
| 0.4337        | 2.0   | 5358  | 0.5335          | 0.4225 | 0.6608 | 0.4163 | 0.6590 |
| 0.2951        | 3.0   | 8037  | 0.5473          | 0.4309 | 0.6703 | 0.4320 | 0.6688 |
| 0.2054        | 4.0   | 10716 | 0.5758          | 0.4277 | 0.6764 | 0.4400 | 0.6748 |
| 0.1557        | 5.0   | 13395 | 0.6073          | 0.4309 | 0.6728 | 0.4398 | 0.6716 |
| 0.1308        | 6.0   | 16074 | 0.6263          | 0.4315 | 0.6767 | 0.4425 | 0.6752 |
| 0.1183        | 7.0   | 18753 | 0.6491          | 0.4280 | 0.6731 | 0.4383 | 0.6715 |


### Framework versions

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