Edit model card

vit-tiny-patch16-224-winkawaks

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

  • Loss: 0.3542
  • Accuracy: 0.8429

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: 5e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.5345 1.0 202 0.4689 0.7771
0.4936 2.0 404 0.5022 0.7485
0.4911 3.0 606 0.3887 0.8279
0.4191 4.0 808 0.4121 0.8098
0.4408 5.0 1010 0.3897 0.8255
0.4134 6.0 1212 0.3714 0.8332
0.4117 7.0 1414 0.3685 0.8377
0.3991 8.0 1616 0.3602 0.8412
0.3936 9.0 1818 0.3542 0.8429
0.3422 10.0 2020 0.3540 0.8398

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
5
Safetensors
Model size
5.52M params
Tensor type
F32
·
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.

Model tree for jalaneunos/vit-tiny-patch16-224-winkawaks

Finetuned
(13)
this model

Evaluation results