metadata
base_model: bert-base-chinese
tags:
- generated_from_keras_callback
model-index:
- name: AIYIYA/my_1
results: []
AIYIYA/my_1
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: 1.1600
- Validation Loss: 1.4880
- Train Accuracy: 0.7195
- 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': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 300, '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 |
|---|---|---|---|
| 3.3536 | 3.0356 | 0.2195 | 0 |
| 2.8571 | 2.6364 | 0.3902 | 1 |
| 2.4461 | 2.2839 | 0.4634 | 2 |
| 2.0491 | 2.0340 | 0.5122 | 3 |
| 1.7890 | 1.7980 | 0.6463 | 4 |
| 1.5356 | 1.6520 | 0.6951 | 5 |
| 1.3215 | 1.5640 | 0.7195 | 6 |
| 1.1600 | 1.4880 | 0.7195 | 7 |
Framework versions
- Transformers 4.31.0
- TensorFlow 2.12.0
- Datasets 2.13.1
- Tokenizers 0.13.3