---
library_name: transformers
license: mit
base_model: openai-community/gpt2
tags:
- generated_from_trainer
model-index:
- name: arabic-nano-gpt
  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. -->

# arabic-nano-gpt

This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 6.9452

## 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: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 1024
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| No log        | 1.1376 | 100  | 7.6593          |
| No log        | 2.2752 | 200  | 7.3363          |
| No log        | 3.4127 | 300  | 7.0512          |
| No log        | 4.5503 | 400  | 6.9452          |


### Framework versions

- Transformers 4.45.2
- Pytorch 2.5.0
- Datasets 3.0.1
- Tokenizers 0.20.1