CoolFace
Modelpublic

ruben09/image_classification

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
2likes175downloads
Model Card

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

image_classification

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:

  • Loss: 2.0337
  • Accuracy: 0.275

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
  • trainbatchsize: 16
  • evalbatchsize: 16
  • seed: 42
  • gradientaccumulationsteps: 4
  • totaltrainbatch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lrschedulertype: linear
  • lrschedulerwarmup_ratio: 0.1
  • num_epochs: 2

Training results

Training LossEpochStepValidation LossAccuracy
2.08361.0102.05390.2062
2.02772.0202.03860.2625

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1