<!-- 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-hch
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: 2.0178
- Bleu: 1.9905
- Gen Len: 81.1723
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 | 199 | 2.7890 | 0.3652 | 102.7094 |
| No log | 2.0 | 398 | 2.4674 | 0.972 | 87.7774 |
| 3.082 | 3.0 | 597 | 2.3066 | 0.9605 | 96.1358 |
| 3.082 | 4.0 | 796 | 2.2094 | 1.1101 | 85.0277 |
| 3.082 | 5.0 | 995 | 2.1428 | 1.5563 | 83.2981 |
| 2.3793 | 6.0 | 1194 | 2.0939 | 1.6876 | 85.3434 |
| 2.3793 | 7.0 | 1393 | 2.0595 | 1.5749 | 84.0843 |
| 2.1974 | 8.0 | 1592 | 2.0350 | 1.8507 | 81.7006 |
| 2.1974 | 9.0 | 1791 | 2.0226 | 2.0672 | 81.5421 |
| 2.1974 | 10.0 | 1990 | 2.0178 | 1.9905 | 81.1723 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
