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

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: 0.6499
- Bleu: 0.2518
- Rouge1: 0.5702
- Rouge2: 0.3118
- Rougel: 0.5677

## 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: 3.0

### Training results

| Training Loss | Epoch | Step | Validation Loss | Bleu   | Rouge1 | Rouge2 | Rougel |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:------:|
| 1.2513        | 1.0   | 2703 | 0.7112          | 0.2201 | 0.5172 | 0.2533 | 0.5148 |
| 0.6462        | 2.0   | 5406 | 0.6569          | 0.2451 | 0.5579 | 0.2974 | 0.5553 |
| 0.5673        | 3.0   | 8109 | 0.6499          | 0.2518 | 0.5702 | 0.3118 | 0.5677 |


### Framework versions

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