Epl1/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: 0.3725
• Validation Loss: 0.3553
• Train Accuracy: 0.911
• 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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 20000, '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
2.8116	1.7125	0.778	0
1.2501	0.8766	0.851	1
0.7145	0.5461	0.888	2
0.5083	0.4211	0.904	3
0.3725	0.3553	0.911	4

Framework versions

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