<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. -->
badokorach/multilingual-cased-finetuned-luganda-qa_10
This model is a fine-tuned version of badokorach/multilingual-cased-finetuned-luganda-qa_09 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0758
- Validation Loss: 0.0
- Epoch: 29
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': 2e-05, 'decay_steps': 7500, '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': 0.02}
- training_precision: mixed_float16
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 1.9301 | 0.0 | 0 |
| 1.7059 | 0.0 | 1 |
| 1.4428 | 0.0 | 2 |
| 1.2682 | 0.0 | 3 |
| 1.0610 | 0.0 | 4 |
| 0.9039 | 0.0 | 5 |
| 0.7822 | 0.0 | 6 |
| 0.6768 | 0.0 | 7 |
| 0.5872 | 0.0 | 8 |
| 0.5329 | 0.0 | 9 |
| 0.4692 | 0.0 | 10 |
| 0.4165 | 0.0 | 11 |
| 0.3618 | 0.0 | 12 |
| 0.3275 | 0.0 | 13 |
| 0.3067 | 0.0 | 14 |
| 0.2701 | 0.0 | 15 |
| 0.2405 | 0.0 | 16 |
| 0.2184 | 0.0 | 17 |
| 0.1937 | 0.0 | 18 |
| 0.1704 | 0.0 | 19 |
| 0.1675 | 0.0 | 20 |
| 0.1380 | 0.0 | 21 |
| 0.1243 | 0.0 | 22 |
| 0.1193 | 0.0 | 23 |
| 0.1062 | 0.0 | 24 |
| 0.1060 | 0.0 | 25 |
| 0.0944 | 0.0 | 26 |
| 0.0798 | 0.0 | 27 |
| 0.0843 | 0.0 | 28 |
| 0.0758 | 0.0 | 29 |
Framework versions
- Transformers 4.33.2
- TensorFlow 2.13.0
- Datasets 2.14.5
- Tokenizers 0.13.3
