ALM-AHME's picture
update model card README.md
4917a5c
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: >-
      beit-large-patch16-224-finetuned-Lesion-Classification-HAM10000-AH-60-20-20
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: Augmented-Final
          split: train
          args: Augmented-Final
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9907502569373073

beit-large-patch16-224-finetuned-Lesion-Classification-HAM10000-AH-60-20-20

This model is a fine-tuned version of microsoft/beit-large-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0434
  • Accuracy: 0.9908

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-06
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.9
  • num_epochs: 12

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.9688 1.0 122 1.8425 0.2775
1.4822 2.0 244 1.3833 0.5457
1.1239 3.0 366 0.9321 0.6680
0.8686 4.0 488 0.6691 0.7698
0.5234 5.0 610 0.4872 0.8335
0.5246 6.0 732 0.3586 0.8736
0.3691 7.0 854 0.3134 0.8993
0.4708 8.0 976 0.2069 0.9394
0.1694 9.0 1098 0.1832 0.9414
0.2749 10.0 1220 0.1198 0.9640
0.1777 11.0 1342 0.0845 0.9733
0.1529 12.0 1464 0.0434 0.9908

Framework versions

  • Transformers 4.30.2
  • Pytorch 2.0.1+cu118
  • Datasets 2.13.1
  • Tokenizers 0.13.3