metadata
license: apache-2.0
tags:
- image-classification
- tensorflow
- vision
- generated_from_keras_callback
model-index:
- name: amyeroberts/vit-base-beans
results: []
amyeroberts/vit-base-beans
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the beans dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.1538
- Train Accuracy: 0.9774
- Validation Loss: 0.1126
- Validation Accuracy: 0.9774
- 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', 'global_clipnorm': 1.0, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 5170, '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}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|---|---|---|---|---|
| 0.6342 | 0.9925 | 0.2390 | 0.9925 | 0 |
| 0.2234 | 0.9774 | 0.1293 | 0.9774 | 1 |
| 0.1538 | 0.9774 | 0.1126 | 0.9774 | 2 |
Framework versions
- Transformers 4.24.0.dev0
- TensorFlow 2.10.0
- Datasets 2.6.2.dev0
- Tokenizers 0.12.1