<!-- 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. -->
uraskargi/bert-base-cased-fine-tuned-4
This model is a fine-tuned version of bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.1922
- Train Accuracy: 0.9310
- Validation Loss: 0.5247
- Validation Accuracy: 0.8303
- Train Matthews Correlation: 0.5830
- 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': '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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 9.858432402113778e-06, 'decay_steps': 665, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
Training results
Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Train Matthews Correlation | Epoch |
---|---|---|---|---|---|
0.6040 | 0.7007 | 0.5308 | 0.7191 | 0.2443 | 0 |
0.4246 | 0.8114 | 0.4163 | 0.8188 | 0.5525 | 1 |
0.2897 | 0.8848 | 0.5054 | 0.8121 | 0.5343 | 2 |
0.2224 | 0.9146 | 0.4868 | 0.8274 | 0.5754 | 3 |
0.1922 | 0.9310 | 0.5247 | 0.8303 | 0.5830 | 4 |
Framework versions
- Transformers 4.28.1
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3