cifar100-vit-base-patch16-224-in21k

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the cifar100 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2945
  • Accuracy: 0.926

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: 10.0

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.3866 1.0 5313 1.0968 0.8747
0.6479 2.0 10626 0.4377 0.9004
0.6092 3.0 15939 0.3439 0.9081
0.4173 4.0 21252 0.3205 0.9169
0.4665 5.0 26565 0.3039 0.9175
0.3944 6.0 31878 0.3082 0.9201
0.303 7.0 37191 0.3011 0.9241
0.6128 8.0 42504 0.2983 0.9261
0.3794 9.0 47817 0.2945 0.926
0.3274 10.0 53130 0.3032 0.9269

Framework versions

  • Transformers 4.38.0
  • Pytorch 2.1.2+cu118
  • Datasets 2.19.1
  • Tokenizers 0.15.2
Downloads last month
2,081
Safetensors
Model size
85.9M params
Tensor type
F32
·
Inference Examples
Unable to determine this model's library. Check the docs .

Model tree for pkr7098/cifar100-vit-base-patch16-224-in21k

Finetuned
(1769)
this model