metadata

license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - image-classification
  - generated_from_trainer
metrics:
  - accuracy
widget:
  - src: healthy.jpeg
    example_title: Healthy
  - src: bean_rust.jpeg
    example_title: Bean Rust
model-index:
  - name: vit_model
    results: []
datasets:
  - AI-Lab-Makerere/beans
language:
  - en
pipeline_tag: image-classification

vit_model

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: 0.0388
Accuracy: 0.9925

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: 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

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.1321	3.8462	500	0.0388	0.9925

Framework versions

Transformers 4.40.0
Pytorch 2.2.1+cu121
Datasets 2.19.0
Tokenizers 0.19.1