vintage-lavender619's picture
Model save
45f229b verified
metadata
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: swin-tiny-patch4-window7-224-finalterm
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9326287978863936

swin-tiny-patch4-window7-224-finalterm

This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1890
  • Accuracy: 0.9326

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: 32
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 128
  • 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
1.2544 0.9684 23 0.5278 0.8692
0.3694 1.9789 47 0.2528 0.9049
0.2816 2.9895 71 0.2065 0.9234
0.2292 4.0 95 0.1986 0.9247
0.2193 4.9684 118 0.1991 0.9168
0.2286 5.9789 142 0.1913 0.9339
0.1887 6.9895 166 0.1932 0.9247
0.1905 8.0 190 0.1883 0.9287
0.1692 8.9684 213 0.1891 0.9326
0.1767 9.6842 230 0.1890 0.9326

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.2
  • Tokenizers 0.19.1