vit-base-patch16-224-EyesNewfourclassTryAfterYolo

This model is a fine-tuned version of google/vit-base-patch16-224 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0091
• Train Accuracy: 0.9437
• Train Top-3-accuracy: 1.0
• Validation Loss: 0.2316
• Validation Accuracy: 0.9437
• Validation Top-3-accuracy: 0.9946
• Epoch: 4

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': 465, '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
0.5159	0.9276	0.9757	0.2680	0.9276	0.9973	0
0.0910	0.9383	0.9993	0.2330	0.9383	0.9973	1
0.0277	0.9383	1.0	0.2437	0.9383	0.9946	2
0.0122	0.9437	1.0	0.2309	0.9437	0.9973	3
0.0091	0.9437	1.0	0.2316	0.9437	0.9946	4

Framework versions

• Transformers 4.42.4
• TensorFlow 2.17.0
• Datasets 2.20.0
• Tokenizers 0.19.1