---
license: apache-2.0
base_model: riotu-lab/ArabianGPT-01B
tags:
- generated_from_trainer
metrics:
- bleu
- rouge
model-index:
- name: res_nw_yem
  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

This model is a fine-tuned version of [riotu-lab/ArabianGPT-01B](https://huggingface.co/riotu-lab/ArabianGPT-01B) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4789
- Bleu: 0.4179
- Rouge1: 0.6343
- Rouge2: 0.3810
- Rougel: 0.6307

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:------:|
| 7.4125        | 1.0   | 153  | 2.3319          | 0.0135 | 0.4043 | 0.1765 | 0.4039 |
| 1.0077        | 2.0   | 306  | 0.5519          | 0.3376 | 0.4747 | 0.1839 | 0.4733 |
| 0.483         | 3.0   | 459  | 0.4973          | 0.3582 | 0.5145 | 0.2200 | 0.5135 |
| 0.3795        | 4.0   | 612  | 0.4739          | 0.3717 | 0.5397 | 0.2524 | 0.5378 |
| 0.2901        | 5.0   | 765  | 0.4691          | 0.3795 | 0.5710 | 0.2927 | 0.5677 |
| 0.2239        | 6.0   | 918  | 0.4655          | 0.3947 | 0.5909 | 0.3232 | 0.5882 |
| 0.1763        | 7.0   | 1071 | 0.4673          | 0.4011 | 0.6047 | 0.3378 | 0.6019 |
| 0.1429        | 8.0   | 1224 | 0.4666          | 0.4085 | 0.6200 | 0.3652 | 0.6168 |
| 0.1206        | 9.0   | 1377 | 0.4765          | 0.4130 | 0.6230 | 0.3707 | 0.6208 |
| 0.1052        | 10.0  | 1530 | 0.4759          | 0.4148 | 0.6233 | 0.3762 | 0.6205 |
| 0.0955        | 11.0  | 1683 | 0.4789          | 0.4179 | 0.6343 | 0.3810 | 0.6307 |


### Framework versions

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