opus-ph-ph
This model is a fine-tuned version of Helsinki-NLP/opus-mt-tc-bible-big-mul-mul on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.7528
- Bleu Global: 28.4879
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: 16
- 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 Global |
|---|---|---|---|---|
| 0.6364 | 1.0 | 1268 | 1.9412 | 25.9524 |
| 0.1826 | 2.0 | 2536 | 2.2076 | 25.5630 |
| 0.1035 | 3.0 | 3804 | 2.3956 | 28.8255 |
| 0.06 | 4.0 | 5072 | 2.5487 | 28.1852 |
| 0.0436 | 5.0 | 6340 | 2.6189 | 28.7365 |
| 0.0298 | 6.0 | 7608 | 2.7528 | 28.4879 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.0
- Downloads last month
- 19
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for rbcurzon/opus-ph-ph
Base model
Helsinki-NLP/opus-mt-tc-bible-big-mul-mul