vit-base-patch16-224-7class224

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: 0.0078
• Train Accuracy: 0.9540
• Train Top-3-accuracy: 0.9960
• Validation Loss: 0.1065
• Validation Accuracy: 0.9569
• Validation Top-3-accuracy: 0.9963
• 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': 630, '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
0.6954	0.6170	0.9295	0.3090	0.7653	0.9734	0
0.1603	0.8272	0.9819	0.1722	0.8640	0.9865	1
0.0448	0.8890	0.9892	0.1220	0.9071	0.9912	2
0.0201	0.9192	0.9924	0.1171	0.9289	0.9934	3
0.0132	0.9359	0.9942	0.1132	0.9416	0.9948	4
0.0089	0.9466	0.9952	0.1095	0.9506	0.9957	5
0.0078	0.9540	0.9960	0.1065	0.9569	0.9963	6

Framework versions

• Transformers 4.41.2
• TensorFlow 2.15.0
• Datasets 2.20.0
• Tokenizers 0.19.1