krm/my_exercice_mrpc
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: 0.6942
- Train Accuracy: 0.6200
- Validation Loss: 0.6486
- Validation Accuracy: 0.6838
- Epoch: 2
Model description
Ce modèle n'est pas à utiliser. Il s'agit d'un petit essai.
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': 0.001, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|---|---|---|---|---|
| 0.6860 | 0.6314 | 0.7727 | 0.6838 | 0 |
| 0.6862 | 0.6347 | 0.6326 | 0.6838 | 1 |
| 0.6942 | 0.6200 | 0.6486 | 0.6838 | 2 |
Framework versions
- Transformers 4.22.2
- TensorFlow 2.8.2
- Datasets 2.5.1
- Tokenizers 0.12.1