metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_keras_callback
model-index:
- name: cc-01-bert-finetuned
results: []
cc-01-bert-finetuned
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0058
- Validation Loss: 0.5378
- Train Recall: 0.8693
- 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', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1770, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Train Recall | Epoch |
|---|---|---|---|
| 0.4422 | 0.4857 | 0.9477 | 0 |
| 0.2513 | 0.3470 | 0.8497 | 1 |
| 0.1331 | 0.4266 | 0.7974 | 2 |
| 0.0640 | 0.4452 | 0.8824 | 3 |
| 0.0339 | 0.5141 | 0.8366 | 4 |
| 0.0225 | 0.5295 | 0.8431 | 5 |
| 0.0090 | 0.5200 | 0.8889 | 6 |
| 0.0058 | 0.5378 | 0.8693 | 7 |
Framework versions
- Transformers 4.31.0
- TensorFlow 2.13.0
- Datasets 2.14.4
- Tokenizers 0.13.3