Nahuatl_Espanol_v1
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6778
- Bleu: 29.2544
- Gen Len: 42.705
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: 0.0005
- 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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 2.1277 | 300 | 0.7834 | 26.6199 | 41.9314 |
| 0.3038 | 4.2553 | 600 | 0.6428 | 27.5908 | 42.4358 |
| 0.3038 | 6.3830 | 900 | 0.6778 | 29.2544 | 42.705 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.0
- Datasets 2.19.2
- Tokenizers 0.19.1