hkivancoral's picture
End of training
ea9fc1e
metadata
license: apache-2.0
base_model: microsoft/beit-base-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: hushem_1x_beit_base_adamax_001_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: 0.5348837209302325

hushem_1x_beit_base_adamax_001_fold3

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

  • Loss: 1.8097
  • Accuracy: 0.5349

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: 0.001
  • 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
No log 1.0 6 1.4381 0.2326
2.0527 2.0 12 1.4022 0.2558
2.0527 3.0 18 1.3682 0.3256
1.3782 4.0 24 1.3387 0.3953
1.2679 5.0 30 1.3721 0.3256
1.2679 6.0 36 1.7451 0.3488
1.2756 7.0 42 1.3183 0.3953
1.2756 8.0 48 1.4225 0.3023
1.173 9.0 54 1.4215 0.3953
1.1959 10.0 60 1.4072 0.3721
1.1959 11.0 66 1.4852 0.4186
1.1344 12.0 72 1.4523 0.2791
1.1344 13.0 78 1.4043 0.4651
1.0854 14.0 84 1.3638 0.3953
1.1124 15.0 90 1.4323 0.3953
1.1124 16.0 96 1.4664 0.4884
1.0108 17.0 102 1.5473 0.3721
1.0108 18.0 108 1.2300 0.4651
0.9443 19.0 114 1.2523 0.4419
0.9125 20.0 120 1.4134 0.3721
0.9125 21.0 126 1.1280 0.4884
0.8328 22.0 132 1.1054 0.4884
0.8328 23.0 138 1.6081 0.4419
0.7565 24.0 144 1.0331 0.5349
0.7135 25.0 150 1.6384 0.5116
0.7135 26.0 156 1.9524 0.4651
0.7048 27.0 162 1.1399 0.5349
0.7048 28.0 168 1.0504 0.5581
0.7074 29.0 174 1.0452 0.5581
0.7008 30.0 180 1.4757 0.5581
0.7008 31.0 186 1.0663 0.4419
0.5976 32.0 192 1.0991 0.5349
0.5976 33.0 198 1.5330 0.5814
0.5565 34.0 204 1.1511 0.5349
0.458 35.0 210 1.5836 0.5349
0.458 36.0 216 1.4225 0.5581
0.5542 37.0 222 1.4182 0.6047
0.5542 38.0 228 1.3407 0.5581
0.3706 39.0 234 1.4368 0.5581
0.3087 40.0 240 1.6899 0.5814
0.3087 41.0 246 1.8110 0.5116
0.3001 42.0 252 1.8097 0.5349
0.3001 43.0 258 1.8097 0.5349
0.3061 44.0 264 1.8097 0.5349
0.2986 45.0 270 1.8097 0.5349
0.2986 46.0 276 1.8097 0.5349
0.2791 47.0 282 1.8097 0.5349
0.2791 48.0 288 1.8097 0.5349
0.2908 49.0 294 1.8097 0.5349
0.2986 50.0 300 1.8097 0.5349

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0