Edit model card

vit-base-beans

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:

  • Accuracy: 0.9850
  • Loss: 0.0711

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: 2e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 1337
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5.0

Training results

Training Loss Epoch Step Accuracy Validation Loss
0.3303 1.0 130 0.9624 0.2543
0.1519 2.0 260 0.9850 0.1059
0.1879 3.0 390 0.9850 0.0908
0.1189 4.0 520 0.9850 0.0714
0.1095 5.0 650 0.9850 0.0711

Framework versions

  • Transformers 4.21.1
  • Pytorch 1.12.1+cu102
  • Datasets 2.4.0
  • Tokenizers 0.12.1
Downloads last month
6
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train liangy2/vit-base-beans

Evaluation results