metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_keras_callback
model-index:
- name: duuke/food_classifier
results: []
duuke/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: 0.4973
- Validation Loss: 0.3968
- Train Accuracy: 0.908
- 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': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 16000, '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, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|---|---|---|---|
| 2.7644 | 1.6595 | 0.807 | 0 |
| 1.2028 | 0.7923 | 0.89 | 1 |
| 0.7072 | 0.5094 | 0.912 | 2 |
| 0.4973 | 0.3968 | 0.908 | 3 |
Framework versions
- Transformers 4.44.2
- TensorFlow 2.17.0
- Datasets 3.0.0
- Tokenizers 0.19.1