<!-- 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-maq-v2
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: 1.7424
- Bleu: 7.2893
- Gen Len: 88.7368
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
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 199 | 2.3492 | 2.8829 | 112.5101 |
| No log | 2.0 | 398 | 2.0881 | 4.6067 | 91.5164 |
| 2.6444 | 3.0 | 597 | 1.9612 | 5.3841 | 93.9332 |
| 2.6444 | 4.0 | 796 | 1.8841 | 5.7548 | 90.3476 |
| 2.6444 | 5.0 | 995 | 1.8330 | 6.1233 | 87.9055 |
| 1.9708 | 6.0 | 1194 | 1.7965 | 6.7074 | 91.0063 |
| 1.9708 | 7.0 | 1393 | 1.7734 | 6.9091 | 89.267 |
| 1.8266 | 8.0 | 1592 | 1.7564 | 7.0616 | 88.6272 |
| 1.8266 | 9.0 | 1791 | 1.7456 | 7.1479 | 89.2531 |
| 1.8266 | 10.0 | 1990 | 1.7424 | 7.2893 | 88.7368 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
