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: 0.0162
• Validation Loss: 0.2163
• Train Accuracy: 0.8916
• Epoch: 24

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': 4825, '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
2.5019	2.0795	0.3735	0
1.7660	1.7259	0.4458	1
1.0922	1.0990	0.7590	2
0.6402	0.8232	0.8193	3
0.4725	0.6107	0.8675	4
0.2674	0.4986	0.9157	5
0.1794	0.5000	0.9157	6
0.2579	0.7721	0.7349	7
0.1269	0.3304	0.8675	8
0.0970	0.2980	0.8795	9
0.1181	0.4988	0.8193	10
0.1241	0.2899	0.8795	11
0.2311	0.4113	0.8795	12
0.0753	0.2964	0.9157	13
0.0637	0.4096	0.8675	14
0.0540	0.3032	0.9036	15
0.0334	0.2694	0.9277	16
0.0212	0.1793	0.9639	17
0.0241	0.3772	0.8554	18
0.0471	0.5727	0.8675	19
0.0652	0.3167	0.8916	20
0.0281	0.2690	0.9036	21
0.0478	0.2169	0.9277	22
0.0193	0.2091	0.9880	23
0.0162	0.2163	0.8916	24

Framework versions

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