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

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

• Loss: 1.6048
• Bleu: 4.3691
• Gen Len: 90.628

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: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	197	2.2612	1.6643	112.3057
No log	2.0	394	1.9432	2.2102	95.5885
2.5492	3.0	591	1.8172	2.8502	95.6293
2.5492	4.0	788	1.7422	3.156	92.9006
2.5492	5.0	985	1.6962	3.2496	91.9032
1.8541	6.0	1182	1.6573	3.6696	91.0064
1.8541	7.0	1379	1.6345	3.8424	90.5987
1.7136	8.0	1576	1.6158	4.0247	91.6229
1.7136	9.0	1773	1.6077	4.2614	89.265
1.7136	10.0	1970	1.6048	4.3691	90.628

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.0+cu118
• Datasets 2.11.0
• Tokenizers 0.13.3