swiftformer-xs-DMAE / README.md
Augusto777's picture
End of training
2beece7 verified
|
raw
history blame
3.96 kB
metadata
base_model: MBZUAI/swiftformer-xs
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: swiftformer-xs-DMAE
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: validation
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.10869565217391304

swiftformer-xs-DMAE

This model is a fine-tuned version of MBZUAI/swiftformer-xs on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 113.8883
  • Accuracy: 0.1087

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: 2.5e-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
  • num_epochs: 40

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 0.86 3 113.8883 0.1087
No log 2.0 7 113.8868 0.1087
114.1606 2.86 10 113.8851 0.1087
114.1606 4.0 14 113.8846 0.1087
114.1606 4.86 17 113.8832 0.1087
113.5172 6.0 21 113.8808 0.1087
113.5172 6.86 24 113.8795 0.1087
113.5172 8.0 28 113.8794 0.1087
111.7557 8.86 31 113.8766 0.1087
111.7557 10.0 35 113.8747 0.1087
111.7557 10.86 38 113.8735 0.1087
115.9434 12.0 42 113.8712 0.1087
115.9434 12.86 45 113.8699 0.1087
115.9434 14.0 49 113.8671 0.1087
112.3427 14.86 52 113.8607 0.1087
112.3427 16.0 56 113.8567 0.1087
112.3427 16.86 59 113.8570 0.1087
113.2123 18.0 63 113.8532 0.1087
113.2123 18.86 66 113.8511 0.1087
114.0835 20.0 70 113.8500 0.1087
114.0835 20.86 73 113.8469 0.1087
114.0835 22.0 77 113.8450 0.1087
114.5528 22.86 80 113.8422 0.1087
114.5528 24.0 84 113.8341 0.1087
114.5528 24.86 87 113.8315 0.1087
114.5432 26.0 91 113.8268 0.1087
114.5432 26.86 94 113.8247 0.1087
114.5432 28.0 98 113.8250 0.1087
112.7825 28.86 101 113.8207 0.1087
112.7825 30.0 105 113.8155 0.1087
112.7825 30.86 108 113.8183 0.1087
114.2965 32.0 112 113.8187 0.1087
114.2965 32.86 115 113.8187 0.1087
114.2965 34.0 119 113.8124 0.1087
114.0925 34.29 120 113.8146 0.1087

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.1.2+cu118
  • Datasets 2.16.1
  • Tokenizers 0.15.0