traduccion-es-en-model
This model is a fine-tuned version of Helsinki-NLP/opus-mt-es-en on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6483
- Bleu: 61.7249
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu |
|---|---|---|---|---|
| No log | 1.0 | 4 | 7.7900 | 60.6214 |
| No log | 2.0 | 8 | 2.8613 | 63.4722 |
| 5.8699 | 3.0 | 12 | 2.1328 | 61.3300 |
| 5.8699 | 4.0 | 16 | 1.9463 | 64.3845 |
| 2.0286 | 5.0 | 20 | 1.8477 | 61.7249 |
| 2.0286 | 6.0 | 24 | 1.7668 | 61.7249 |
| 2.0286 | 7.0 | 28 | 1.7085 | 61.7249 |
| 1.3097 | 8.0 | 32 | 1.6737 | 61.7249 |
| 1.3097 | 9.0 | 36 | 1.6539 | 61.7249 |
| 1.1073 | 10.0 | 40 | 1.6483 | 61.7249 |
Framework versions
- Transformers 5.3.0
- Pytorch 2.10.0+cu128
- Datasets 4.6.1
- Tokenizers 0.22.2
- Downloads last month
- 27
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for marneyra/traduccion-es-en-model
Base model
Helsinki-NLP/opus-mt-es-en