opus-mt-es-en-GEC-spanish-merged-exp
This model is a fine-tuned version of Helsinki-NLP/opus-mt-es-en on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1056
- Gleu: 0.7289
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: 0.0013223040248761528
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.09857017609527079
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Gleu |
|---|---|---|---|---|
| 1.9924 | 1.0 | 2216 | 0.3180 | 0.4943 |
| 0.9720 | 2.0 | 4432 | 0.1849 | 0.6301 |
| 0.5051 | 3.0 | 6648 | 0.1318 | 0.6911 |
| 0.2586 | 4.0 | 8864 | 0.1056 | 0.7289 |
Framework versions
- Transformers 5.5.1
- Pytorch 2.11.0+cu128
- Datasets 4.8.5
- Tokenizers 0.22.2