metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_keras_callback
model-index:
- name: tobijen/bert_left_headings
results: []
tobijen/bert_left_headings
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: 2.9281
- Validation Loss: 6.3114
- Epoch: 5
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': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 4.2355 | 6.1111 | 0 |
| 3.8648 | 6.1665 | 1 |
| 3.6034 | 6.1879 | 2 |
| 3.3677 | 6.2372 | 3 |
| 3.1317 | 6.2744 | 4 |
| 2.9281 | 6.3114 | 5 |
Framework versions
- Transformers 4.31.0
- TensorFlow 2.12.0
- Datasets 2.13.1
- Tokenizers 0.13.3