vit-base-patch16-224-in21k-4class

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: 0.1673
• Train Accuracy: 0.9240
• Train Top-3-accuracy: 0.9960
• Validation Loss: 0.2804
• Validation Accuracy: 0.9284
• 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': 231, '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
1.1244	0.5585	0.9362	0.8773	0.7081	0.9753	0
0.6801	0.7656	0.9822	0.5789	0.8040	0.9871	1
0.4108	0.8329	0.9897	0.4105	0.8548	0.9915	2
0.2717	0.8725	0.9927	0.3397	0.8855	0.9937	3
0.2123	0.8967	0.9944	0.3307	0.9055	0.9948	4
0.1822	0.9126	0.9953	0.2927	0.9187	0.9957	5
0.1673	0.9240	0.9960	0.2804	0.9284	0.9963	6

Framework versions

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