hkivancoral's picture
End of training
89f1481
metadata
license: apache-2.0
base_model: microsoft/beit-base-patch16-224-pt22k-ft22k
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: hushem_40x_beit_base_f3
    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: 0.8837209302325582

hushem_40x_beit_base_f3

This model is a fine-tuned version of microsoft/beit-base-patch16-224-pt22k-ft22k on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 0.9422
  • Accuracy: 0.8837

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
0.0594 1.0 108 0.4441 0.8372
0.0595 2.0 217 0.8725 0.8605
0.0173 3.0 325 0.5866 0.9070
0.0084 4.0 434 0.6360 0.8605
0.0005 5.0 542 0.6191 0.8837
0.0008 6.0 651 0.6635 0.9070
0.0008 7.0 759 0.8772 0.8837
0.0001 8.0 868 0.8012 0.9070
0.0 9.0 976 0.9139 0.8837
0.0001 9.95 1080 0.9422 0.8837

Framework versions

  • Transformers 4.35.0
  • Pytorch 2.1.0+cu118
  • Datasets 2.14.6
  • Tokenizers 0.14.1