---
base_model: Dhahlan2000/Simple_Translation-model-for-GPT-v2
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: Simple_Translation-model-for-GPT-v3
  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. -->

# Simple_Translation-model-for-GPT-v3

This model is a fine-tuned version of [Dhahlan2000/Simple_Translation-model-for-GPT-v2](https://huggingface.co/Dhahlan2000/Simple_Translation-model-for-GPT-v2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4882
- Bleu: 30.5908
- Gen Len: 15.3476

## 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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
| 0.7494        | 1.0   | 4571 | 0.5369          | 28.6585 | 15.3298 |
| 0.6735        | 2.0   | 9142 | 0.4882          | 30.5908 | 15.3476 |


### Framework versions

- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1