metadata
library_name: transformers
license: mit
base_model: facebook/mbart-large-50
tags:
- simplification
- generated_from_trainer
metrics:
- bleu
model-index:
- name: mbart-neutralization
results: []
mbart-neutralization
This model is a fine-tuned version of facebook/mbart-large-50 on an the dataset Spanish Gender Neutralization dataset. 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