README.md

metadata

license: apache-2.0
base_model: akahana/vit-base-cats-vs-dogs
tags:
  - generated_from_trainer
datasets:
  - cats_vs_dogs
metrics:
  - accuracy
model-index:
  - name: cat_or_dogs
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: cats_vs_dogs
          type: cats_vs_dogs
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9820589491670226

cat_or_dogs

This model is a fine-tuned version of akahana/vit-base-cats-vs-dogs on the cats_vs_dogs dataset. It achieves the following results on the evaluation set:

• Loss: 0.0561
• Accuracy: 0.9821

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: 1e-06
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine_with_restarts
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.0389	1.0	1171	0.0638	0.9793
0.0682	2.0	2342	0.0510	0.9812
0.0623	3.0	3513	0.0561	0.9821

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.1
• Tokenizers 0.15.2