<!-- 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. -->
Hzmin9/my_awesome_model
This model is a fine-tuned version of bert-base-chinese on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.1928
- Train Accuracy: 0.6725
- Validation Loss: 1.3273
- Validation Accuracy: 0.6725
- Epoch: 9
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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 2250, '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}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|---|---|---|---|---|
| 2.0541 | 0.595 | 1.5183 | 0.5950 | 0 |
| 1.3021 | 0.6125 | 1.2977 | 0.6125 | 1 |
| 0.9285 | 0.6625 | 1.2059 | 0.6625 | 2 |
| 0.7071 | 0.6625 | 1.1796 | 0.6625 | 3 |
| 0.5354 | 0.6525 | 1.2179 | 0.6525 | 4 |
| 0.4165 | 0.6825 | 1.1801 | 0.6825 | 5 |
| 0.3302 | 0.6675 | 1.3224 | 0.6675 | 6 |
| 0.2655 | 0.6725 | 1.3056 | 0.6725 | 7 |
| 0.2195 | 0.6675 | 1.3366 | 0.6675 | 8 |
| 0.1928 | 0.6725 | 1.3273 | 0.6725 | 9 |
Framework versions
- Transformers 4.33.0
- TensorFlow 2.13.0
- Datasets 2.14.4
- Tokenizers 0.13.3
