<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
opus-mt-en-es-finetuned-es-to-kbh
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: 1.8301
- Bleu: 4.1693
- Gen Len: 84.6051
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 | 198 | 2.5750 | 1.16 | 121.8152 |
| No log | 2.0 | 396 | 2.2444 | 1.7294 | 97.6532 |
| 2.9216 | 3.0 | 594 | 2.0938 | 2.4491 | 91.4253 |
| 2.9216 | 4.0 | 792 | 2.0059 | 2.766 | 86.719 |
| 2.9216 | 5.0 | 990 | 1.9410 | 3.406 | 84.8456 |
| 2.1149 | 6.0 | 1188 | 1.8986 | 3.5985 | 85.9671 |
| 2.1149 | 7.0 | 1386 | 1.8642 | 3.8399 | 83.9595 |
| 1.9446 | 8.0 | 1584 | 1.8456 | 3.9151 | 83.8101 |
| 1.9446 | 9.0 | 1782 | 1.8330 | 4.1315 | 84.1797 |
| 1.9446 | 10.0 | 1980 | 1.8301 | 4.1693 | 84.6051 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
