Prahas10/roof-classification

This model is a fine-tuned version of google/vit-base-patch32-384 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0374
• Validation Loss: 0.0935
• Train Accuracy: 0.9818
• Epoch: 8

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': 4380, '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': 0.0001}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Accuracy	Epoch
1.9894	1.4451	0.6364	0
0.6770	0.6352	0.8727	1
0.2797	0.6216	0.8455	2
0.1648	0.2777	0.9	3
0.1120	0.2635	0.9182	4
0.1131	0.3882	0.8364	5
0.1013	0.6015	0.8273	6
0.0444	0.1688	0.9727	7
0.0374	0.0935	0.9818	8

Framework versions

• Transformers 4.38.2
• TensorFlow 2.15.0
• Datasets 2.16.1
• Tokenizers 0.15.2