Hugging Face's logo

SSM10
/
vit_models

Image Classification
Safetensors
vit
Generated from Trainer
Model card Files Community
vit_models / README.md
ssilvera10's picture
ssilvera10
Update README.md
3fe6a20 verified
preview code
|
raw
history blame
1.77 kB
metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - image-classification
  - generated_from_trainer
metrics:
  - accuracy
widget:
  - src: >-
      https://huggingface.co/SSM10/vit_models/blob/main/healthy_66daaf31-4e54-476e-85e5-42d062377763.jpeg
    example_title: Healthy
  - src: >-
      https://huggingface.co/SSM10/vit_models/blob/main/bean_rust_f1500068-80a0-41b1-b57c-2a601fb95e66.jpeg
    example_title: Bean Rust
model-index:
  - name: vit_models
    results: []
datasets:
  - AI-Lab-Makerere/beans
pipeline_tag: image-classification

vit_models

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: 0.0299
  • Accuracy: 0.9774

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
0.1297 3.8462 500 0.0299 0.9774

Framework versions

  • Transformers 4.43.3
  • Pytorch 2.3.1
  • Datasets 2.20.0
  • Tokenizers 0.19.1