mbart-traduccion

This model is a fine-tuned version of facebook/mbart-large-50 on Iker/InstructTranslation-EN-ES-Raw. It achieves the following results on the evaluation set:

• Loss: 0.5543
• Bleu: 64.2175
• Gen Len: 82.8185

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: 5.6e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	146	0.6936	62.2127	79.6096
No log	2.0	292	0.5543	64.2175	82.8185

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2