|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: opus-mt-en-mul-finetuned-lfn-to-en |
|
results: [] |
|
language: |
|
- en |
|
- lfn |
|
pipeline_tag: translation |
|
--- |
|
|
|
# opus-mt-en-mul-finetuned-lfn-to-en |
|
|
|
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-mul](https://huggingface.co/Helsinki-NLP/opus-mt-en-mul) on the Tatoeba English-Elefen sentence pair dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6208 |
|
- Bleu: 62.9717 |
|
- Gen Len: 11.5165 |
|
|
|
## Model description |
|
|
|
Elefen (or Lingua Franca Nova, abbreviated to "LFN") is a simple language designed for international communication. |
|
Its vocabulary is based on Catalan, Spanish, French, Italian and Portuguese. The grammar is very reduced, similar to Romance creoles. |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 2e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.3 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.10.1 |
|
- Tokenizers 0.13.2 |
