Maria831Chowdhury/cat_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: 1.2533
• Validation Loss: 1.1095
• Train Accuracy: 0.5508
• 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': 3740, '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
1.5813	1.5262	0.4011	0
1.4980	1.4068	0.5027	1
1.4093	1.2781	0.4973	2
1.3448	1.2010	0.5241	3
1.2533	1.1095	0.5508	4

Framework versions

• Transformers 4.43.3
• TensorFlow 2.15.0
• Datasets 2.20.0
• Tokenizers 0.19.1