image_classification

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the food101 dataset. It achieves the following results on the evaluation set:

• Loss: 1.5938
• Accuracy: 0.911

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:

• learning_rate: 5e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.7307	0.99	62	2.5306	0.833
1.8698	2.0	125	1.7637	0.903
1.5629	2.98	186	1.5856	0.915

Framework versions

• Transformers 4.33.1
• Pytorch 1.13.1+cu117
• Datasets 2.14.5
• Tokenizers 0.13.3