opus-mt-es-en-finetuned_model-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: 1.9803
• Bleu: 13.8765
• Gen Len: 45.316

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: 16
• eval_batch_size: 16
• 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
2.5745	1.0	4674	2.3717	10.1245	46.0135
2.2901	2.0	9348	2.1461	12.2345	45.3126
2.1356	3.0	14022	2.0491	13.1754	45.496
2.0507	4.0	18696	1.9967	13.689	45.3156
2.0222	5.0	23370	1.9803	13.8765	45.316

Framework versions

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