DifeiT's picture
End of training
79a5c0a
metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: rsna_intracranial_hemorrhage_detection
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: test
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8585666824869482

rsna_intracranial_hemorrhage_detection

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

  • Loss: 0.4344
  • Accuracy: 0.8586

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: 16
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.6034 1.0 132 0.5659 0.8315
0.4903 2.0 265 0.4868 0.8472
0.5305 3.0 397 0.4742 0.8538
0.5424 4.0 530 0.4650 0.8552
0.4289 5.0 662 0.4508 0.8552
0.4275 6.0 795 0.4394 0.8590
0.4075 7.0 927 0.4767 0.8434
0.3649 8.0 1060 0.4462 0.8595
0.3934 9.0 1192 0.4323 0.8605
0.3436 9.96 1320 0.4344 0.8586

Framework versions

  • Transformers 4.33.2
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.5
  • Tokenizers 0.13.3