csiztom/vit-base-patch16-224-in21k-street-view

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: 3.3425
• Train Accuracy: 0.3008
• Train Top-3-accuracy: 0.5072
• Validation Loss: 3.8645
• Validation Accuracy: 0.1618
• Validation Top-3-accuracy: 0.2830
• Epoch: 3

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': 6e-05, 'decay_steps': 5250, '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
4.6754	0.0403	0.0977	4.4868	0.0723	0.1510	0
4.2813	0.1050	0.2225	4.2261	0.0996	0.2077	1
3.8606	0.1848	0.3483	4.0354	0.1300	0.2513	2
3.3425	0.3008	0.5072	3.8645	0.1618	0.2830	3

Framework versions

• Transformers 4.34.1
• TensorFlow 2.14.0
• Datasets 2.14.6
• Tokenizers 0.14.1