---
license: apache-2.0
base_model: riotu-lab/ArabianGPT-03B
tags:
- generated_from_trainer
metrics:
- bleu
- rouge
model-index:
- name: res_nw_yem_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_yem_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: 0.3767
- Bleu: 0.4279
- Rouge1: 0.6599
- Rouge2: 0.3971
- Rougel: 0.6585

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:------:|
| 4.4383        | 1.0   | 153  | 0.7436          | 0.0155 | 0.4698 | 0.1921 | 0.4693 |
| 0.4733        | 2.0   | 306  | 0.3933          | 0.3967 | 0.5938 | 0.3154 | 0.5909 |
| 0.2714        | 3.0   | 459  | 0.3767          | 0.4279 | 0.6599 | 0.3971 | 0.6585 |
| 0.1837        | 4.0   | 612  | 0.3863          | 0.4380 | 0.6762 | 0.4184 | 0.6726 |
| 0.129         | 5.0   | 765  | 0.3835          | 0.4536 | 0.6994 | 0.4576 | 0.6968 |
| 0.0999        | 6.0   | 918  | 0.3938          | 0.4493 | 0.6979 | 0.4541 | 0.6936 |
| 0.0844        | 7.0   | 1071 | 0.3971          | 0.4623 | 0.7107 | 0.4766 | 0.7069 |
| 0.0741        | 8.0   | 1224 | 0.3947          | 0.4715 | 0.7229 | 0.4895 | 0.7189 |


### Framework versions

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