<!-- 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. -->
AIYIYA/my_aa
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: 0.7596
- Validation Loss: 1.4913
- Train Accuracy: 0.6753
- Epoch: 29
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': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 280, '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 | Validation Loss | Train Accuracy | Epoch |
|---|---|---|---|
| 3.4316 | 3.2876 | 0.2078 | 0 |
| 3.0452 | 3.0083 | 0.2338 | 1 |
| 2.6954 | 2.7106 | 0.3766 | 2 |
| 2.3815 | 2.4910 | 0.4935 | 3 |
| 2.0499 | 2.3035 | 0.5584 | 4 |
| 1.8322 | 2.1419 | 0.5844 | 5 |
| 1.6292 | 1.9997 | 0.6104 | 6 |
| 1.4675 | 1.8933 | 0.6234 | 7 |
| 1.3115 | 1.8016 | 0.5974 | 8 |
| 1.2088 | 1.7273 | 0.6364 | 9 |
| 1.1053 | 1.6728 | 0.6623 | 10 |
| 1.0254 | 1.6284 | 0.6364 | 11 |
| 0.9600 | 1.6252 | 0.6494 | 12 |
| 0.9058 | 1.5662 | 0.6623 | 13 |
| 0.8675 | 1.5423 | 0.6623 | 14 |
| 0.8434 | 1.5208 | 0.6753 | 15 |
| 0.8356 | 1.5140 | 0.6753 | 16 |
| 0.8070 | 1.5024 | 0.6753 | 17 |
| 0.7749 | 1.4941 | 0.6753 | 18 |
| 0.7805 | 1.4913 | 0.6753 | 19 |
| 0.7764 | 1.4913 | 0.6753 | 20 |
| 0.7630 | 1.4913 | 0.6753 | 21 |
| 0.7806 | 1.4913 | 0.6753 | 22 |
| 0.7665 | 1.4913 | 0.6753 | 23 |
| 0.7803 | 1.4913 | 0.6753 | 24 |
| 0.7778 | 1.4913 | 0.6753 | 25 |
| 0.7781 | 1.4913 | 0.6753 | 26 |
| 0.7798 | 1.4913 | 0.6753 | 27 |
| 0.7845 | 1.4913 | 0.6753 | 28 |
| 0.7596 | 1.4913 | 0.6753 | 29 |
Framework versions
- Transformers 4.31.0
- TensorFlow 2.12.0
- Datasets 2.13.1
- Tokenizers 0.13.3
