opus-mt-es-en-finetuned-en-to-es

This model is a fine-tuned version of Helsinki-NLP/opus-mt-es-en on the opus_books dataset. It achieves the following results on the evaluation set:

• Loss: 2.0963
• Bleu: 12.6368
• Gen Len: 45.2439

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: 2e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
2.7993	1.0	2337	2.5049	9.0673	46.0969
2.434	2.0	4674	2.2687	10.9353	45.3797
2.2723	3.0	7011	2.1639	11.9589	45.3567
2.1979	4.0	9348	2.1117	12.4972	45.4107
2.1644	5.0	11685	2.0963	12.6368	45.2439

Framework versions

• Transformers 4.33.1
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3