opus-mt-en-es-finetuned-es-to-maq-v0.1

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: 1.9026
• Bleu: 6.2542
• Gen Len: 85.8168

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

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	194	2.4894	2.7357	106.7282
No log	2.0	388	2.2333	4.5116	90.6795
2.6136	3.0	582	2.1176	4.7062	91.1743
2.6136	4.0	776	2.0314	5.3422	89.0635
2.6136	5.0	970	1.9925	5.5413	90.2363
1.9444	6.0	1164	1.9523	6.1301	84.5288
1.9444	7.0	1358	1.9292	5.8244	88.6617
1.8038	8.0	1552	1.9137	6.2976	88.0
1.8038	9.0	1746	1.9062	6.2889	85.0679
1.8038	10.0	1940	1.9026	6.2542	85.8168

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3