F-eB-e/food_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: 0.3625
• Validation Loss: 0.3347
• Train Accuracy: 0.918
• 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': 20000, '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
2.7562	1.5563	0.873	0
1.1775	0.7872	0.892	1
0.6780	0.4881	0.914	2
0.4781	0.3626	0.925	3
0.3625	0.3347	0.918	4

Framework versions

• Transformers 4.45.0.dev0
• TensorFlow 2.17.0
• Datasets 2.20.0
• Tokenizers 0.19.1