yudiwbs/marian-finetuned-kde4-en-to-id
Penjelasan: https://yudiwbs.wordpress.com/2023/09/01/fine-tune-model-machine-translation-inggris-indonesia-en-id/
This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-id on KDE dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.5779
- Validation Loss: 0.6892
- Epoch: 2
Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 1245, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: mixed_float16
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 1.0329 | 0.7683 | 0 |
| 0.7086 | 0.7042 | 1 |
| 0.5779 | 0.6892 | 2 |
Framework versions
- Transformers 4.32.1
- TensorFlow 2.12.0
- Datasets 2.14.4
- Tokenizers 0.13.3