metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_keras_callback
model-index:
- name: aditnnda/felidae_klasifikasi
results: []
aditnnda/felidae_klasifikasi
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: 0.9213
- Train Accuracy: 0.7869
- Validation Loss: 0.8231
- Validation Accuracy: 0.7869
- Epoch: 9
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': 1820, '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 | Validation Loss | Validation Accuracy | Epoch |
|---|---|---|---|---|
| 1.6070 | 0.3770 | 1.5670 | 0.3770 | 0 |
| 1.5299 | 0.6557 | 1.4816 | 0.6557 | 1 |
| 1.4347 | 0.6066 | 1.3838 | 0.6066 | 2 |
| 1.3535 | 0.6885 | 1.2822 | 0.6885 | 3 |
| 1.2562 | 0.6885 | 1.1766 | 0.6885 | 4 |
| 1.1829 | 0.7705 | 1.0732 | 0.7705 | 5 |
| 1.1037 | 0.8033 | 0.9889 | 0.8033 | 6 |
| 1.0444 | 0.8525 | 0.9204 | 0.8525 | 7 |
| 0.9640 | 0.8197 | 0.8722 | 0.8197 | 8 |
| 0.9213 | 0.7869 | 0.8231 | 0.7869 | 9 |
Framework versions
- Transformers 4.35.1
- TensorFlow 2.14.0
- Datasets 2.14.6
- Tokenizers 0.14.1