metadata
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: LovenOO/distilBERT_without_preprocessing_grid_search
results: []
LovenOO/distilBERT_without_preprocessing_grid_search
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.2612
- Validation Loss: 0.4890
- Train Precision: 0.7183
- Train Recall: 0.6777
- Train F1: 0.6902
- Train Accuracy: 0.8654
- Epoch: 3
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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 5140, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_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 | Train Precision | Train Recall | Train F1 | Train Accuracy | Epoch |
|---|---|---|---|---|---|---|
| 1.1440 | 0.6108 | 0.5739 | 0.5788 | 0.5727 | 0.8367 | 0 |
| 0.5050 | 0.5447 | 0.6506 | 0.6243 | 0.6325 | 0.8489 | 1 |
| 0.3584 | 0.4823 | 0.6518 | 0.6619 | 0.6558 | 0.8620 | 2 |
| 0.2612 | 0.4890 | 0.7183 | 0.6777 | 0.6902 | 0.8654 | 3 |
Framework versions
- Transformers 4.24.0
- TensorFlow 2.13.0
- Datasets 2.14.2
- Tokenizers 0.11.0