shbA/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: 0.6730
• Train Accuracy: 0.675
• Validation Loss: 0.6380
• Validation Accuracy: 0.8000
• Epoch: 5

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': 1600, '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': 0.05}
• training_precision: float32

Training results

Train Loss	Train Accuracy	Validation Loss	Validation Accuracy	Epoch
0.8438	0.625	0.6171	0.8000	0
0.9123	0.625	0.8710	0.6000	1
0.7847	0.7	0.5295	1.0	2
0.8369	0.625	0.5829	1.0	3
0.7734	0.675	1.0318	0.4000	4
0.6730	0.675	0.6380	0.8000	5

Framework versions

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