<!-- 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-cbv
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: 1.3555
- Bleu: 5.8553
- Gen Len: 92.0545
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 | 193 | 2.0269 | 1.4628 | 93.9455 |
| No log | 2.0 | 386 | 1.7009 | 4.5076 | 93.0467 |
| 2.4078 | 3.0 | 579 | 1.5666 | 4.967 | 89.3217 |
| 2.4078 | 4.0 | 772 | 1.4872 | 5.194 | 92.6187 |
| 2.4078 | 5.0 | 965 | 1.4434 | 5.2623 | 93.0921 |
| 1.5878 | 6.0 | 1158 | 1.4052 | 5.5164 | 90.6628 |
| 1.5878 | 7.0 | 1351 | 1.3840 | 5.5944 | 92.4981 |
| 1.4571 | 8.0 | 1544 | 1.3652 | 5.692 | 93.1647 |
| 1.4571 | 9.0 | 1737 | 1.3580 | 5.6759 | 90.978 |
| 1.4571 | 10.0 | 1930 | 1.3555 | 5.8553 | 92.0545 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
