pokemon_classifier / README.md
stbnlen's picture
update model card README.md
1b5344f
|
raw
history blame
1.89 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - pokemon-classification
metrics:
  - accuracy
model-index:
  - name: pokemon_classifier
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: pokemon-classification
          type: pokemon-classification
          config: full
          split: validation
          args: full
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.09496402877697842

pokemon_classifier

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

  • Loss: 8.0010
  • Accuracy: 0.0950

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: 0.0002
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 4

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.3716 0.82 500 7.1987 0.0655
0.1136 1.64 1000 7.6050 0.0777
0.0434 2.46 1500 8.0010 0.0820
0.0163 3.28 2000 8.0010 0.0950

Framework versions

  • Transformers 4.30.2
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3