<!-- 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-pbb
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: 1.6542
- Bleu: 1.3038
- Gen Len: 91.1755
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 | 2.3635 | 0.145 | 113.25 |
| No log | 2.0 | 398 | 2.0326 | 0.3676 | 99.7058 |
| 2.7169 | 3.0 | 597 | 1.8928 | 0.573 | 98.3447 |
| 2.7169 | 4.0 | 796 | 1.8063 | 0.6535 | 91.9205 |
| 2.7169 | 5.0 | 995 | 1.7475 | 0.8058 | 92.928 |
| 1.9424 | 6.0 | 1194 | 1.7113 | 1.1078 | 92.8321 |
| 1.9424 | 7.0 | 1393 | 1.6859 | 1.3645 | 91.1288 |
| 1.7874 | 8.0 | 1592 | 1.6679 | 1.1571 | 91.4394 |
| 1.7874 | 9.0 | 1791 | 1.6568 | 1.2881 | 91.6717 |
| 1.7874 | 10.0 | 1990 | 1.6542 | 1.3038 | 91.1755 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
