metadata
base_model: bert-base-chinese
tags:
- generated_from_keras_callback
model-index:
- name: Mattis0525/bert-base-chinese-finetuned-tcfd
results: []
Mattis0525/bert-base-chinese-finetuned-tcfd
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: 0.6446
- Train Accuracy: 0.0598
- Validation Loss: 0.6266
- Validation Accuracy: 0.0614
- Epoch: 6
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': 'AdamWeightDecay', 'learning_rate': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': -800, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|---|---|---|---|---|
| 0.9480 | 0.0555 | 0.8742 | 0.0566 | 0 |
| 0.8735 | 0.0567 | 0.7660 | 0.0589 | 1 |
| 0.7694 | 0.0574 | 0.7093 | 0.0584 | 2 |
| 0.7190 | 0.0588 | 0.6563 | 0.0604 | 3 |
| 0.6720 | 0.0592 | 0.6636 | 0.0601 | 4 |
| 0.6479 | 0.0596 | 0.6639 | 0.0602 | 5 |
| 0.6446 | 0.0598 | 0.6266 | 0.0614 | 6 |
Framework versions
- Transformers 4.41.1
- TensorFlow 2.15.0
- Datasets 2.19.1
- Tokenizers 0.19.1