Vit Model Juan Bula

🚀 vit-model-juan-bula

This model is a fine - tuned version of google/vit-base-patch16-224-in21k on the beans dataset, achieving high accuracy in image classification tasks.

🚀 Quick Start

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

• Loss: 0.0077
• Accuracy: 1.0

📄 License

This model is licensed under the Apache 2.0 license.

🔍 Features

• High Accuracy: Achieves an accuracy of 1.0 on the beans dataset.
• Fine - Tuned: Based on the pre - trained google/vit-base-patch16-224-in21k model.

📚 Documentation

Model Index

• Name: vit-model-juan-bula
• Results:
  • Task:
    • Name: Image Classification
    • Type: image - classification
  • Dataset:
    • Name: beans
    • Type: beans
    • Config: default
    • Split: train
    • Args: default
  • Metrics:
    • Name: Accuracy
    • Type: accuracy
    • Value: 1.0

Widget

• Healthy Example: Healthy Image
• Bean Rust Example: Bean Rust Image

Tags

• generated_from_trainer

Metrics

• accuracy

Datasets

• beans

🔧 Technical Details

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 4.25.1
• Pytorch 1.13.0+cpu
• Datasets 2.7.1
• Tokenizers 0.13.2