leopuv/cats_vs_dogs_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: 0.0285
• Train Accuracy: 0.9865
• Validation Loss: 0.0340
• Validation Accuracy: 0.9865
• 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': 80000, '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 Accuracy	Validation Loss	Validation Accuracy	Epoch
0.1739	0.9715	0.0787	0.9715	0
0.0744	0.984	0.0432	0.9840	1
0.0543	0.9895	0.0365	0.9895	2
0.0420	0.9885	0.0346	0.9885	3
0.0402	0.9855	0.0414	0.9855	4
0.0378	0.9885	0.0307	0.9885	5
0.0306	0.9855	0.0375	0.9855	6
0.0343	0.987	0.0402	0.9870	7
0.0283	0.9875	0.0381	0.9875	8
0.0285	0.9865	0.0340	0.9865	9

Framework versions

• Transformers 4.31.0
• TensorFlow 2.12.0
• Datasets 2.13.1
• Tokenizers 0.13.3