metadata
base_model: Davlan/bert-base-multilingual-cased-finetuned-luganda
tags:
- generated_from_keras_callback
model-index:
- name: badokorach/bert-berta-base
results: []
badokorach/bert-berta-base
This model is a fine-tuned version of Davlan/bert-base-multilingual-cased-finetuned-luganda on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.6578
- Validation Loss: 0.0
- 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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 4e-05, 'decay_steps': 1120, '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': 0.03}
- training_precision: mixed_float16
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 2.4199 | 0.0 | 0 |
| 1.8885 | 0.0 | 1 |
| 1.7700 | 0.0 | 2 |
| 1.5049 | 0.0 | 3 |
| 1.0805 | 0.0 | 4 |
| 0.6578 | 0.0 | 5 |
Framework versions
- Transformers 4.33.0
- TensorFlow 2.12.0
- Datasets 2.14.4
- Tokenizers 0.13.3