metadata
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: shbA/food_classifier
results: []
shbA/food_classifier
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.8652
- Train Accuracy: 0.75
- Validation Loss: 0.7771
- Validation Accuracy: 0.75
- 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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 1600, '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, 'weight_decay_rate': 0.05}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|---|---|---|---|---|
| 0.9228 | 0.7 | 0.9388 | 0.7000 | 0 |
| 0.9711 | 0.775 | 0.8639 | 0.7750 | 1 |
| 0.8841 | 0.825 | 0.8585 | 0.8250 | 2 |
| 0.8757 | 0.65 | 0.8448 | 0.6500 | 3 |
| 0.8802 | 0.75 | 0.7883 | 0.75 | 4 |
| 0.8652 | 0.75 | 0.7771 | 0.75 | 5 |
Framework versions
- Transformers 4.29.1
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3