metadata
license: cc-by-sa-4.0
base_model: klue/bert-base
tags:
- generated_from_keras_callback
model-index:
- name: category2
results: []
category2
This model is a fine-tuned version of klue/bert-base on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.1245
- Train Accuracy: 1.0
- Validation Loss: 0.3052
- Validation Accuracy: 0.9512
- Epoch: 7
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': 'Adam', 'learning_rate': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|---|---|---|---|---|
| 3.5655 | 0.1598 | 3.1279 | 0.4390 | 0 |
| 2.4666 | 0.6926 | 2.0870 | 0.7073 | 1 |
| 1.4274 | 0.9126 | 1.2408 | 0.8780 | 2 |
| 0.7632 | 0.9740 | 0.8015 | 0.8902 | 3 |
| 0.4298 | 0.9891 | 0.5613 | 0.9146 | 4 |
| 0.2529 | 1.0 | 0.4192 | 0.9268 | 5 |
| 0.1709 | 1.0 | 0.3459 | 0.9512 | 6 |
| 0.1245 | 1.0 | 0.3052 | 0.9512 | 7 |
Framework versions
- Transformers 4.31.0
- TensorFlow 2.12.0
- Tokenizers 0.13.3