metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_keras_callback
model-index:
- name: traynothein_resize_foreclasss
results: []
traynothein_resize_foreclasss
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: 0.0744
- Train Accuracy: 0.9404
- Train Top-3-accuracy: 0.9991
- Validation Loss: 0.2720
- Validation Accuracy: 0.9431
- Validation Top-3-accuracy: 0.9991
- Epoch: 6
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': 658, '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 | Train Accuracy | Train Top-3-accuracy | Validation Loss | Validation Accuracy | Validation Top-3-accuracy | Epoch |
|---|---|---|---|---|---|---|
| 0.6708 | 0.7378 | 0.9752 | 0.4218 | 0.8246 | 0.9933 | 0 |
| 0.3109 | 0.8569 | 0.9956 | 0.3083 | 0.8754 | 0.9968 | 1 |
| 0.2024 | 0.8899 | 0.9975 | 0.2776 | 0.9011 | 0.9979 | 2 |
| 0.1370 | 0.9104 | 0.9982 | 0.2734 | 0.9170 | 0.9985 | 3 |
| 0.0996 | 0.9237 | 0.9986 | 0.2775 | 0.9288 | 0.9988 | 4 |
| 0.0814 | 0.9334 | 0.9989 | 0.2695 | 0.9372 | 0.9990 | 5 |
| 0.0744 | 0.9404 | 0.9991 | 0.2720 | 0.9431 | 0.9991 | 6 |
Framework versions
- Transformers 4.44.2
- TensorFlow 2.15.1
- Datasets 3.0.0
- Tokenizers 0.19.1