saffin/vit_ivi_first_test

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: 0.2158
• Train Sparse Categorical Accuracy: 1.0
• Validation Loss: 0.2144
• Validation Sparse Categorical Accuracy: 1.0
• 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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 1525, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, '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	Train Sparse Categorical Accuracy	Validation Loss	Validation Sparse Categorical Accuracy	Epoch
1.2381	0.8426	0.8788	1.0	0
0.6525	1.0	0.5058	1.0	1
0.3859	1.0	0.3354	1.0	2
0.2715	1.0	0.2602	1.0	3
0.2158	1.0	0.2144	1.0	4

Framework versions

• Transformers 4.31.0
• TensorFlow 2.8.0
• Datasets 2.18.0
• Tokenizers 0.13.3