CynthiaCR/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: 0.5354
• Validation Loss: 1.3575
• Train Accuracy: 0.5062
• 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': 6400, '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
2.0502	2.0061	0.2375	0
1.8368	1.7539	0.3187	1
1.6074	1.6316	0.3875	2
1.4768	1.5368	0.4437	3
1.3390	1.4388	0.4813	4
1.1889	1.3995	0.4562	5
1.0397	1.3773	0.4688	6
0.8703	1.4785	0.4625	7
0.6962	1.3854	0.4938	8
0.5354	1.3575	0.5062	9

Framework versions

• Transformers 4.29.1
• TensorFlow 2.12.0
• Datasets 2.12.0
• Tokenizers 0.13.3