metadata
library_name: transformers
license: cc-by-sa-4.0
base_model: klue/bert-base
tags:
- generated_from_keras_callback
model-index:
- name: bert-base-nsmc
results: []
bert-base-nsmc
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: 0.0298
- Train Accuracy: 1.0
- Validation Loss: 0.2335
- Validation Accuracy: 1.0
- Epoch: 4
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': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 5e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 4.5, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 0.5, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.1}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|---|---|---|---|---|
| 0.5729 | 1.0 | 0.5564 | 1.0 | 0 |
| 0.4097 | 1.0 | 0.3896 | 1.0 | 1 |
| 0.1165 | 1.0 | 0.2967 | 1.0 | 2 |
| 0.0442 | 1.0 | 0.2517 | 1.0 | 3 |
| 0.0298 | 1.0 | 0.2335 | 1.0 | 4 |
Framework versions
- Transformers 4.48.3
- TensorFlow 2.18.0
- Tokenizers 0.21.0