---
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
datasets:
- wmt16
metrics:
- bleu
model-index:
- name: bart-base-finetuned-en-to-ro-clean
  results:
  - task:
      name: Sequence-to-sequence Language Modeling
      type: text2text-generation
    dataset:
      name: wmt16
      type: wmt16
      config: ro-en
      split: validation
      args: ro-en
    metrics:
    - name: Bleu
      type: bleu
      value: 1.8841
---

<!-- 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. -->

# bart-base-finetuned-en-to-ro-clean

This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the wmt16 dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3502
- Bleu: 1.8841
- Gen Len: 19.7764

## 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: 1
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Bleu   | Gen Len |
|:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|
| 0.646         | 1.0   | 38145 | 1.3502          | 1.8841 | 19.7764 |


### Framework versions

- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0