<!-- 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-mim
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: 1.3342
- Bleu: 5.6597
- Gen Len: 92.9975
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 | 2.0821 | 0.911 | 104.3748 |
| No log | 2.0 | 398 | 1.6654 | 3.059 | 91.1862 |
| 2.5881 | 3.0 | 597 | 1.5316 | 3.6794 | 92.7799 |
| 2.5881 | 4.0 | 796 | 1.4603 | 4.4586 | 92.8792 |
| 2.5881 | 5.0 | 995 | 1.4168 | 4.8055 | 92.9459 |
| 1.5569 | 6.0 | 1194 | 1.3818 | 5.1205 | 94.6893 |
| 1.5569 | 7.0 | 1393 | 1.3618 | 5.5735 | 92.873 |
| 1.4302 | 8.0 | 1592 | 1.3459 | 5.6645 | 93.3283 |
| 1.4302 | 9.0 | 1791 | 1.3355 | 5.6963 | 93.2189 |
| 1.4302 | 10.0 | 1990 | 1.3342 | 5.6597 | 92.9975 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
