vit-base-patch16-224-franciscoflores-classification

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:

• Loss: 0.0071
• accuracy : 0.9988

Model description

Transfer learning from a pre-trained image classification model determines which images are of a dog and which ones are of food

Intended uses & limitations

More information needed

Training and evaluation data

This model was trained using the "sasha/dog-food"

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0002
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
0.0618	1.9	500	0.0146
0.0062	3.8	1000	0.0071

Framework versions

• Transformers 4.33.1
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3