metadata
license: mit
tags:
- generated_from_keras_callback
model-index:
- name: maxime7770/model
results: []
maxime7770/model
This model is a fine-tuned version of camembert-base on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.3854
- Validation Loss: 0.5874
- Epoch: 15
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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 650, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 1.6014 | 1.6111 | 0 |
| 1.5695 | 1.5934 | 1 |
| 1.5128 | 1.5183 | 2 |
| 1.4323 | 1.3869 | 3 |
| 1.3073 | 1.2395 | 4 |
| 1.1639 | 1.1111 | 5 |
| 1.0148 | 1.0003 | 6 |
| 0.8949 | 0.9099 | 7 |
| 0.7910 | 0.8363 | 8 |
| 0.6968 | 0.7782 | 9 |
| 0.6153 | 0.7293 | 10 |
| 0.5506 | 0.6909 | 11 |
| 0.5102 | 0.6588 | 12 |
| 0.4615 | 0.6300 | 13 |
| 0.4204 | 0.6072 | 14 |
| 0.3854 | 0.5874 | 15 |
Framework versions
- Transformers 4.18.0
- TensorFlow 2.8.0
- Datasets 2.1.0
- Tokenizers 0.12.1