EyesNewSixClassTry-unKnown2

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: 0.1042
• Train Accuracy: 0.9647
• Train Top-3-accuracy: 0.9995
• Validation Loss: 0.1846
• Validation Accuracy: 0.9647
• Validation Top-3-accuracy: 1.0
• 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': 1e-05, 'decay_steps': 695, '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
1.1744	0.8622	0.8843	0.6698	0.8622	0.9788	0
0.4377	0.9399	0.9883	0.3257	0.9399	0.9965	1
0.2127	0.9505	0.9959	0.2377	0.9505	0.9965	2
0.1349	0.9647	0.9991	0.1957	0.9647	1.0	3
0.1042	0.9647	0.9995	0.1846	0.9647	1.0	4

Framework versions

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