<!-- 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-ngu
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: 1.8826
- Bleu: 5.6695
- Gen Len: 78.319
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 | 2.6657 | 1.353 | 116.2686 |
| No log | 2.0 | 398 | 2.3408 | 1.6397 | 99.3127 |
| 2.97 | 3.0 | 597 | 2.1759 | 2.3741 | 100.1248 |
| 2.97 | 4.0 | 796 | 2.0744 | 3.4996 | 88.343 |
| 2.97 | 5.0 | 995 | 2.0044 | 4.3822 | 81.2623 |
| 2.209 | 6.0 | 1194 | 1.9554 | 4.9553 | 80.5813 |
| 2.209 | 7.0 | 1393 | 1.9217 | 5.3635 | 81.3291 |
| 2.0188 | 8.0 | 1592 | 1.8985 | 5.542 | 81.1929 |
| 2.0188 | 9.0 | 1791 | 1.8875 | 5.579 | 78.744 |
| 2.0188 | 10.0 | 1990 | 1.8826 | 5.6695 | 78.319 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
