Platzi Vit Model Joaquin Romero

🚀 platzi-vit-model-Joaquin-Romero

This is a fine - tuned image classification model based on the Google ViT - Base architecture, achieving high accuracy on the beans dataset.

🚀 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 beans dataset. It achieves the following results on the evaluation set:

• Loss: 0.0613
• Accuracy: 0.9850

✨ Features

• High Accuracy: Achieves an accuracy of 0.9850 on the evaluation set.
• Fine - Tuned: Based on the pre - trained [google/vit - base - patch16 - 224 - in21k] model.

📚 Documentation

Model description

It's an Image Classification model.

Intended uses & limitations

None

Training and evaluation data

The model was trained and evaluated on the Beans dataset.

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: 4

Training results

Framework versions

• Transformers 4.27.1
• Pytorch 1.13.1+cu116
• Datasets 2.10.1
• Tokenizers 0.13.2

📄 License

This model is licensed under the Apache 2.0 license.