metadata
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: fintuned-bert-disfluency
results: []
fintuned-bert-disfluency
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0814
- Train Sparse Categorical Accuracy: 0.9795
- Validation Loss: 0.0816
- Validation Sparse Categorical Accuracy: 0.9795
- Epoch: 2
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': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch |
|---|---|---|---|---|
| 0.1105 | 0.9694 | 0.0821 | 0.9800 | 0 |
| 0.0942 | 0.9759 | 0.0987 | 0.9765 | 1 |
| 0.0814 | 0.9795 | 0.0816 | 0.9795 | 2 |
Framework versions
- Transformers 4.21.3
- TensorFlow 2.8.2
- Datasets 2.4.0
- Tokenizers 0.12.1