README.md

metadata

license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - image-classification
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: vit_epochs5_batch32_lr5e-05_size224_tiles3_seed2_q1
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: Dogs_vs_Cats
          type: imagefolder
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9842666666666666

vit_epochs5_batch32_lr5e-05_size224_tiles3_seed2_q1

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

• Loss: 0.0674
• Accuracy: 0.9843

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
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.0313	1.0	469	0.1323	0.9677
0.0003	2.0	938	0.0674	0.9843
0.0001	3.0	1407	0.0740	0.9853
0.0001	4.0	1876	0.0715	0.9867
0.0001	5.0	2345	0.0720	0.9864

Framework versions

• Transformers 4.41.1
• Pytorch 2.2.2
• Datasets 2.18.0
• Tokenizers 0.19.1