metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_keras_callback
model-index:
- name: AIUser245/food_classifier
results: []
AIUser245/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: 0.3703
- Validation Loss: 0.3299
- Train Accuracy: 0.924
- Epoch: 4
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': 20000, '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': 0.01}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|---|---|---|---|
| 2.7963 | 1.5950 | 0.861 | 0 |
| 1.2101 | 0.8091 | 0.886 | 1 |
| 0.6770 | 0.4879 | 0.922 | 2 |
| 0.5020 | 0.3645 | 0.927 | 3 |
| 0.3703 | 0.3299 | 0.924 | 4 |
Framework versions
- Transformers 4.32.1
- TensorFlow 2.12.0
- Datasets 2.14.4
- Tokenizers 0.13.3