vit-base-patch16-224-2class_normal

This model is a fine-tuned version of google/vit-base-patch16-224 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0023
• Train Accuracy: 0.9828
• Train Top-3-accuracy: 1.0
• Validation Loss: 0.1087
• Validation Accuracy: 0.9839
• Validation Top-3-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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 170, '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	Train Accuracy	Train Top-3-accuracy	Validation Loss	Validation Accuracy	Validation Top-3-accuracy	Epoch
0.1803	0.8483	1.0	0.0796	0.9356	1.0	0
0.0129	0.9548	1.0	0.0797	0.9663	1.0	1
0.0042	0.9721	1.0	0.1078	0.9762	1.0	2
0.0026	0.9791	1.0	0.1077	0.9813	1.0	3
0.0023	0.9828	1.0	0.1087	0.9839	1.0	4

Framework versions

• Transformers 4.41.2
• TensorFlow 2.15.0
• Datasets 2.20.0
• Tokenizers 0.19.1