Deexit/swin-tiny-patch4-window7-224-finetuned-eurosat

This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 1.9176
• Validation Loss: 3.2903
• Validation Accuracy: 0.0
• Epoch: 13

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': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: float32

Training results

Train Loss	Validation Loss	Validation Accuracy	Epoch
2.7734	2.7408	0.0	0
2.4056	2.7463	0.0	1
2.1880	2.7762	0.0	2
2.0477	2.8285	0.0	3
2.1556	2.8884	0.0	4
2.0269	2.9569	0.0	5
1.7258	3.0337	0.0	6
2.3555	3.1071	0.0	7
1.8657	3.1494	0.0	8
1.8121	3.1848	0.0	9
1.9192	3.2109	0.0	10
1.9925	3.2335	0.0	11
2.0157	3.2654	0.0	12
1.9176	3.2903	0.0	13

Framework versions

• Transformers 4.31.0
• TensorFlow 2.13.0
• Datasets 2.14.3
• Tokenizers 0.13.3