Hugging Face's logo

Mickaelass
/
vit-base-beans

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
vit-base-beans / README.md
Mickaelass's picture
Mickaelass
End of training
c65ce43 verified
preview code
|
raw
history blame contribute delete
1.47 kB
metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
datasets:
  - imagefolder
model-index:
  - name: vit-base-beans
    results: []

vit-base-beans

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

  • eval_loss: 0.0080
  • eval_accuracy: 0.9975
  • eval_runtime: 135.4458
  • eval_samples_per_second: 147.823
  • eval_steps_per_second: 18.48
  • epoch: 0.7191
  • step: 1800

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: 32
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 2
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.47.1
  • Pytorch 2.5.1+cu121
  • Datasets 3.2.0
  • Tokenizers 0.21.0