metadata
license: mit
base_model: microsoft/deberta-v3-base
tags:
- generated_from_keras_callback
model-index:
- name: Tylah/test
results: []
Tylah/test
This model is a fine-tuned version of microsoft/deberta-v3-base on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.4025
- Validation Loss: 0.3167
- Train Precision: 1.0
- Train Recall: 1.0
- Train F1: 1.0
- 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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 55, '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 | Epoch |
|---|---|---|---|---|---|
| 0.7257 | 0.6381 | 0.5556 | 1.0 | 0.7143 | 0 |
| 0.5764 | 0.4544 | 0.5714 | 1.0 | 0.7273 | 1 |
| 0.4025 | 0.3167 | 1.0 | 1.0 | 1.0 | 2 |
Framework versions
- Transformers 4.31.0
- TensorFlow 2.13.0
- Datasets 2.14.4
- Tokenizers 0.13.3