kruti-15/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: 0.0223
• Train Accuracy: 0.9964
• Train Top-3-accuracy: 1.0
• Train Apcer: 0.5004
• Train Bpcer: 0.4996
• Validation Loss: 0.0220
• Validation Accuracy: 0.9968
• Validation Top-3-accuracy: 1.0
• Validation Apcer: 0.4993
• Validation Bpcer: 0.5007
• 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': 135, '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': 0.09}
• training_precision: float32

Training results

Train Loss	Train Accuracy	Train Top-3-accuracy	Train Apcer	Train Bpcer	Validation Loss	Validation Accuracy	Validation Top-3-accuracy	Validation Apcer	Validation Bpcer	Epoch
0.2475	0.9291	1.0	0.5039	0.4961	0.0704	0.9830	1.0	0.5016	0.4984	0
0.0475	0.9886	1.0	0.4971	0.5029	0.0333	0.9917	1.0	0.4972	0.5028	1
0.0289	0.9934	1.0	0.5014	0.4986	0.0255	0.9946	1.0	0.5003	0.4997	2
0.0240	0.9953	1.0	0.5004	0.4996	0.0228	0.9959	1.0	0.4990	0.5010	3
0.0223	0.9964	1.0	0.5004	0.4996	0.0220	0.9968	1.0	0.4993	0.5007	4

Framework versions

• Transformers 4.39.3
• TensorFlow 2.15.0
• Datasets 2.18.0
• Tokenizers 0.15.2