<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. -->
leopuv/dog_chicken_muffin_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: 0.0326
- Train Accuracy: 0.9947
- Validation Loss: 0.0191
- Validation Accuracy: 0.9947
- 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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 22500, '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 | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|---|---|---|---|---|
| 0.4271 | 0.996 | 0.1010 | 0.9960 | 0 |
| 0.1111 | 0.9933 | 0.0613 | 0.9933 | 1 |
| 0.0774 | 0.9947 | 0.0451 | 0.9947 | 2 |
| 0.0592 | 0.9947 | 0.0354 | 0.9947 | 3 |
| 0.0457 | 0.9987 | 0.0252 | 0.9987 | 4 |
| 0.0434 | 0.992 | 0.0346 | 0.9920 | 5 |
| 0.0429 | 0.996 | 0.0270 | 0.9960 | 6 |
| 0.0397 | 0.9973 | 0.0177 | 0.9973 | 7 |
| 0.0326 | 0.9973 | 0.0161 | 0.9973 | 8 |
| 0.0326 | 0.9947 | 0.0191 | 0.9947 | 9 |
Framework versions
- Transformers 4.30.2
- TensorFlow 2.12.0
- Datasets 2.13.1
- Tokenizers 0.13.3
