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: 0.0348
eval_accuracy: 0.9796
eval_runtime: 8.12
eval_samples_per_second: 6.034
eval_steps_per_second: 1.601
epoch: 187.0
step: 1683
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: 32
eval_batch_size: 4
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
