mbart-neutralization

This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1563
• Bleu: 53.022
• Gen Len: 18.5417

Model description

This model has been created as part of an activity for the course "Traducción Automática", at the Máster de Procesamiento del Lenguaje y Aplicaciones de la Inteligencia Artificial a la Lingüística (Universidad de La Rioja).

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: 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	0.2031	53.022	18.5417
0.2886	2.0	880	0.1563	53.022	18.5417

Framework versions

• Transformers 4.51.2
• Pytorch 2.10.0+cu128
• Datasets 4.0.0
• Tokenizers 0.21.4