vit-base-patch16-224-finetuned-wildcats

This model is a fine-tuned version of google/vit-base-patch16-224 on the wildcat image dataset.

Model description

Demo is hosted at https://huggingface.co/spaces/rsadaphule/wildcats

Intended uses & limitations

Classify wildcats

Training and evaluation data

Model has been trained on wildcat images

Training procedure

Fine tune Vision Transformer on wildcat images

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

accuracy : 97%

Framework versions

• Transformers 4.24.0
• Pytorch 2.1.0+cu121
• Datasets 2.7.1
• Tokenizers 0.13.3