metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_keras_callback
model-index:
- name: Entrenal_eyes_5clasess_withOther_model
results: []
Entrenal_eyes_5clasess_withOther_model
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: 0.0845
- Train Accuracy: 0.9283
- Train Top-3-accuracy: 0.9936
- Validation Loss: 0.4386
- Validation Accuracy: 0.9313
- Validation Top-3-accuracy: 0.9940
- 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': 847, '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 |
|---|---|---|---|---|---|---|
| 0.8358 | 0.6703 | 0.9165 | 0.5139 | 0.7995 | 0.9693 | 0 |
| 0.3540 | 0.8366 | 0.9783 | 0.4737 | 0.8589 | 0.9835 | 1 |
| 0.2235 | 0.8749 | 0.9862 | 0.3874 | 0.8876 | 0.9884 | 2 |
| 0.1607 | 0.8972 | 0.9898 | 0.4559 | 0.9045 | 0.9908 | 3 |
| 0.1204 | 0.9109 | 0.9914 | 0.4410 | 0.9163 | 0.9921 | 4 |
| 0.0961 | 0.9208 | 0.9927 | 0.4393 | 0.9246 | 0.9932 | 5 |
| 0.0845 | 0.9283 | 0.9936 | 0.4386 | 0.9313 | 0.9940 | 6 |
Framework versions
- Transformers 4.44.2
- TensorFlow 2.15.1
- Datasets 3.0.0
- Tokenizers 0.19.1