|
--- |
|
library_name: transformers |
|
license: mit |
|
base_model: facebook/mbart-large-50 |
|
tags: |
|
- simplification |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: mbart-neutralization |
|
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. --> |
|
|
|
# mbart-neutralization |
|
|
|
This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on the dataset [Spanish Gender Neutralization |
|
dataset](https://huggingface.co/datasets/hackathon-pln-es/neutral-es). |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0117 |
|
- Bleu: 96.8831 |
|
- Gen Len: 22.9479 |
|
|
|
## Model description |
|
|
|
This model intends to translate sentences from current Spanish to neutralised Spanish. |
|
|
|
## Intended uses & limitations |
|
|
|
This model has been created as an in-class exercice, so the coverage of it can be very limited. |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 5.6e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- 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 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:| |
|
| No log | 1.0 | 440 | 0.0212 | 97.3896 | 18.7604 | |
|
| 0.2286 | 2.0 | 880 | 0.0117 | 96.8831 | 22.9479 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.49.0 |
|
- Pytorch 2.5.1+cu124 |
|
- Datasets 3.3.2 |
|
- Tokenizers 0.21.0 |
|
|
