metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_keras_callback
model-index:
- name: saffin/vit_food101
results: []
saffin/vit_food101
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: 0.2467
- Validation Loss: 0.3126
- Train Accuracy: 0.91
- Epoch: 7
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': 32000, '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 |
---|---|---|---|
2.7797 | 1.5957 | 0.847 | 0 |
1.2120 | 0.8643 | 0.865 | 1 |
0.7002 | 0.5026 | 0.914 | 2 |
0.4838 | 0.3933 | 0.913 | 3 |
0.3949 | 0.3889 | 0.898 | 4 |
0.3269 | 0.3129 | 0.91 | 5 |
0.2794 | 0.3278 | 0.909 | 6 |
0.2467 | 0.3126 | 0.91 | 7 |
Framework versions
- Transformers 4.31.0
- TensorFlow 2.8.0
- Datasets 2.18.0
- Tokenizers 0.13.3