IGustavsen/mbart-50-finetuned-english-german-wikilingua_epoch-1
This model is a fine-tuned version of facebook/mbart-large-50 on the WikiLingua dataset. It achieves the following results on the evaluation set:
- Train Loss: 2.7358
- Validation Loss: 2.3730
- Epoch: 0
Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 2.7358 | 2.3730 | 0 |
Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3