metadata
license: apache-2.0
base_model: Helsinki-NLP/opus-mt-ha-en
tags:
- generated_from_keras_callback
model-index:
- name: Baghdad99/saad-opus-ha-to-en
results: []
Baghdad99/saad-opus-ha-to-en
This model is a fine-tuned version of Helsinki-NLP/opus-mt-ha-en on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.8407
- Validation Loss: 1.1336
- Epoch: 5
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:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 30610, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_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 |
|---|---|---|
| 1.2289 | 1.1080 | 0 |
| 1.0949 | 1.1099 | 1 |
| 1.0078 | 1.1135 | 2 |
| 0.9412 | 1.1249 | 3 |
| 0.8863 | 1.1283 | 4 |
| 0.8407 | 1.1336 | 5 |
Framework versions
- Transformers 4.35.0
- TensorFlow 2.14.0
- Datasets 2.14.6
- Tokenizers 0.14.1