---
library_name: transformers
license: cc-by-nc-4.0
base_model: kinleyrabgay/nllb-200-600M-dzo-eng
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: nllb-200-600M-dzo-eng
  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. -->

# nllb-200-600M-dzo-eng

This model is a fine-tuned version of [facebook/nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M) on [kinleyrabgay/dz_to_en](https://huggingface.co/datasets/kinleyrabgay/dz_to_en) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0774
- Bleu: 59.5127

## 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: 3e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Bleu    |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.0765        | 1.0   | 1250 | 0.0746          | 58.0373 |
| 0.0576        | 2.0   | 2500 | 0.0728          | 58.5746 |
| 0.0465        | 3.0   | 3750 | 0.0735          | 59.3099 |
| 0.0381        | 4.0   | 5000 | 0.0758          | 59.2493 |
| 0.033         | 5.0   | 6250 | 0.0774          | 59.5127 |


### Framework versions

- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1

## Usage
```python
from transformers import pipeline

translator = pipeline(
    "translation",
    model="kinleyrabgay/nllb-200-600M-dzo-eng",
    src_lang="dzo_Tibt",
    tgt_lang="eng_Latn"
)

dz_text = "ག་ནི་བ་ ཡིད་ཕྲོག"
translation = translator(dz_text)
print(translation[0]['translation_text'])
```