hkivancoral's picture
End of training
2b2a968
metadata
license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_5x_deit_small_rms_00001_fold3
    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: 0.8966666666666666

smids_5x_deit_small_rms_00001_fold3

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

  • Loss: 1.0303
  • Accuracy: 0.8967

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: 1e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 50

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.2375 1.0 375 0.2542 0.9083
0.1409 2.0 750 0.2770 0.91
0.0609 3.0 1125 0.3094 0.8983
0.0237 4.0 1500 0.3996 0.8983
0.0338 5.0 1875 0.5715 0.8883
0.0534 6.0 2250 0.6112 0.8933
0.0052 7.0 2625 0.6878 0.8933
0.0006 8.0 3000 0.6908 0.9
0.0283 9.0 3375 0.6671 0.8983
0.0065 10.0 3750 0.7326 0.9067
0.0065 11.0 4125 0.6436 0.915
0.0 12.0 4500 0.7498 0.9
0.0016 13.0 4875 0.8235 0.8933
0.0003 14.0 5250 0.8655 0.895
0.0082 15.0 5625 0.7486 0.9067
0.0001 16.0 6000 0.8142 0.9017
0.0001 17.0 6375 0.7387 0.8917
0.0001 18.0 6750 0.8424 0.9067
0.0 19.0 7125 0.7973 0.9017
0.0378 20.0 7500 0.7948 0.8967
0.0 21.0 7875 0.8629 0.8917
0.0 22.0 8250 0.7939 0.9017
0.0063 23.0 8625 0.8369 0.89
0.0 24.0 9000 0.8848 0.9
0.0 25.0 9375 0.8284 0.91
0.0 26.0 9750 0.9412 0.9
0.0 27.0 10125 0.8363 0.905
0.0 28.0 10500 0.9351 0.8917
0.0 29.0 10875 0.8734 0.9033
0.0037 30.0 11250 0.9770 0.9067
0.0 31.0 11625 0.8887 0.905
0.0 32.0 12000 0.9455 0.9
0.0 33.0 12375 0.9432 0.9033
0.0 34.0 12750 0.9703 0.8983
0.0 35.0 13125 0.9495 0.9067
0.0 36.0 13500 0.9886 0.8983
0.0 37.0 13875 0.9999 0.9
0.0 38.0 14250 1.0388 0.8983
0.0 39.0 14625 1.0645 0.8917
0.0038 40.0 15000 0.9923 0.9017
0.0 41.0 15375 1.0132 0.8983
0.0 42.0 15750 1.0058 0.9017
0.0 43.0 16125 1.0185 0.8983
0.0 44.0 16500 1.0211 0.8967
0.0 45.0 16875 1.0174 0.8967
0.0 46.0 17250 1.0256 0.8967
0.0 47.0 17625 1.0251 0.8967
0.0 48.0 18000 1.0297 0.8967
0.0 49.0 18375 1.0318 0.8967
0.0 50.0 18750 1.0303 0.8967

Framework versions

  • Transformers 4.32.1
  • Pytorch 2.1.0+cu121
  • Datasets 2.12.0
  • Tokenizers 0.13.2