HarshaSingamshetty1/roof_classifier

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: 1.6380
• Validation Loss: 2.1987
• Train Accuracy: 0.4375
• Epoch: 14

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': 1770, '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	Validation Loss	Train Accuracy	Epoch
2.9764	2.9730	0.05	0
2.8746	2.9232	0.125	1
2.7792	2.8802	0.1375	2
2.6648	2.8491	0.225	3
2.5573	2.7563	0.1625	4
2.4614	2.7155	0.2875	5
2.3453	2.7005	0.2	6
2.2737	2.6443	0.2875	7
2.1555	2.5396	0.3625	8
2.0694	2.4244	0.425	9
2.0112	2.3738	0.4875	10
1.8867	2.3843	0.4125	11
1.8217	2.2878	0.45	12
1.7253	2.2642	0.475	13
1.6380	2.1987	0.4375	14

Framework versions

• Transformers 4.35.2
• TensorFlow 2.14.0
• Datasets 2.15.0
• Tokenizers 0.15.0