jtatman/vit-base-patch16-224-in21k-euroSat

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: 0.0217
• Train Accuracy: 0.9835
• Train Top-3-accuracy: 0.9977
• Validation Loss: 0.0529
• Validation Accuracy: 0.9850
• Validation Top-3-accuracy: 0.9979
• 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': 3590, '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
0.4701	0.8661	0.9502	0.1578	0.9489	0.9895	0
0.0997	0.9615	0.9929	0.0886	0.9689	0.9948	1
0.0519	0.9735	0.9958	0.0642	0.9771	0.9966	2
0.0308	0.9797	0.9971	0.0549	0.9818	0.9974	3
0.0217	0.9835	0.9977	0.0529	0.9850	0.9979	4

Framework versions

• Transformers 4.41.1
• TensorFlow 2.15.0
• Datasets 2.19.1
• Tokenizers 0.19.1