---
library_name: transformers
base_model: facebook/mbart-large-50-many-to-many-mmt
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: mt-en-vi
  results: []
datasets:
- thainq107/iwslt2015-en-vi
---

<!-- 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. -->

# mt-en-vi

This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on a dataset from iwslt2015.
It achieves the following results on the evaluation set:
- Loss: 1.2564
- Bleu: 34.9585

## 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: 64
- eval_batch_size: 64
- seed: 42
- 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: 2
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Bleu    |
|:-------------:|:------:|:----:|:---------------:|:-------:|
| 1.1887        | 0.2399 | 500  | 1.2961          | 34.2118 |
| 1.1422        | 0.4798 | 1000 | 1.2807          | 34.6929 |
| 1.127         | 0.7198 | 1500 | 1.2689          | 34.7625 |
| 1.1215        | 0.9597 | 2000 | 1.2577          | 34.5726 |
| 1.031         | 1.1996 | 2500 | 1.2728          | 35.0683 |
| 1.0128        | 1.4395 | 3000 | 1.2632          | 34.8100 |
| 1.0184        | 1.6795 | 3500 | 1.2565          | 34.7721 |
| 1.0131        | 1.9194 | 4000 | 1.2564          | 34.9585 |


### Framework versions

- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 2.20.0
- Tokenizers 0.21.1