mbart-ClimateChangeMeasures-en-es

This model is a fine-tuned version of facebook/mbart-large-50 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.4070
• Bleu: 13.6296
• Gen Len: 28.6364

Uses and limitations

This model has been trained to translate texts from English to Spanish, specifically focused on environmental topics and green policies. Fine-tuning was done on a relatively small dataset, which makes the results variable depending on the complexity and context of the translation.

Training and evaluation data

The dataset is the following one: ClimateChangeMeasures

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	28	3.5296	12.3925	26.1455
No log	2.0	56	3.4070	13.6296	28.6364

Framework versions

• Transformers 4.50.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1