Dataset Model2

🚀 dataset_model2

This model is a fine - tuned version of [google/vit - base - patch16 - 224 - in21k](https://huggingface.co/google/vit - base - patch16 - 224 - in21k) on the imagefolder dataset, aiming to solve image classification tasks and provide high - accuracy classification results.

🚀 Quick Start

This model is a fine - tuned version of [google/vit - base - patch16 - 224 - in21k](https://huggingface.co/google/vit - base - patch16 - 224 - in21k) on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.5350
• Accuracy: 0.8798

✨ Features

• Fine - Tuned Model: Based on the pre - trained [google/vit - base - patch16 - 224 - in21k](https://huggingface.co/google/vit - base - patch16 - 224 - in21k), fine - tuned on the imagefolder dataset.
• Good Performance: Achieves an accuracy of 0.8798 on the evaluation set.

📚 Documentation

Model Information

Training Procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0001
• 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: 20

Training results

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.0+cu117
• Datasets 2.7.1
• Tokenizers 0.13.2

📄 License

This project is licensed under the Apache - 2.0 license.