opus-mt-en-es-finetuned-es-to-pbb-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: 1.6535
- Bleu: 1.2729
- Gen Len: 90.5316
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 | 2.3626 | 0.171 | 109.5972 |
| No log | 2.0 | 398 | 2.0302 | 0.3065 | 95.3081 |
| 2.712 | 3.0 | 597 | 1.8861 | 0.7019 | 96.8497 |
| 2.712 | 4.0 | 796 | 1.8081 | 0.6924 | 93.4432 |
| 2.712 | 5.0 | 995 | 1.7496 | 0.9599 | 90.7563 |
| 1.942 | 6.0 | 1194 | 1.7133 | 1.0843 | 92.4646 |
| 1.942 | 7.0 | 1393 | 1.6859 | 1.1072 | 92.8725 |
| 1.7861 | 8.0 | 1592 | 1.6696 | 1.243 | 91.2184 |
| 1.7861 | 9.0 | 1791 | 1.6569 | 1.2595 | 90.1641 |
| 1.7861 | 10.0 | 1990 | 1.6535 | 1.2729 | 90.5316 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- 2