Deexit/custom_ViT

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: 0.9353
• Validation Loss: 1.0343
• Train Accuracy: 0.8667
• Epoch: 9

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': 1680, '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	Validation Loss	Train Accuracy	Epoch
2.2697	2.1984	0.4667	0
2.1245	2.0728	0.6	1
1.9780	1.9057	0.8	2
1.8135	1.7702	0.8667	3
1.6516	1.6121	0.8667	4
1.4854	1.4733	0.8667	5
1.3306	1.3294	0.8667	6
1.1829	1.2269	0.8333	7
1.0596	1.1176	0.8667	8
0.9353	1.0343	0.8667	9

Framework versions

• Transformers 4.31.0
• TensorFlow 2.12.0
• Datasets 2.14.4
• Tokenizers 0.13.3