hkivancoral's picture
End of training
3ccadc8
metadata
license: apache-2.0
base_model: microsoft/beit-large-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_10x_beit_large_sgd_00001_fold1
    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: 0.6360601001669449

smids_10x_beit_large_sgd_00001_fold1

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

  • Loss: 0.8308
  • Accuracy: 0.6361

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
1.1798 1.0 751 1.2530 0.3139
1.1588 2.0 1502 1.2210 0.3272
1.0286 3.0 2253 1.1929 0.3272
1.0699 4.0 3004 1.1680 0.3372
1.0532 5.0 3755 1.1455 0.3539
1.0168 6.0 4506 1.1249 0.3589
1.0334 7.0 5257 1.1059 0.3840
1.006 8.0 6008 1.0879 0.3923
0.9781 9.0 6759 1.0713 0.4073
0.9206 10.0 7510 1.0557 0.4324
0.9599 11.0 8261 1.0410 0.4457
0.8538 12.0 9012 1.0272 0.4591
0.8992 13.0 9763 1.0143 0.4725
0.9105 14.0 10514 1.0019 0.4925
0.8886 15.0 11265 0.9904 0.5058
0.8635 16.0 12016 0.9792 0.5209
0.9091 17.0 12767 0.9687 0.5292
0.8236 18.0 13518 0.9588 0.5342
0.8559 19.0 14269 0.9493 0.5426
0.7879 20.0 15020 0.9403 0.5509
0.765 21.0 15771 0.9320 0.5543
0.8223 22.0 16522 0.9238 0.5593
0.782 23.0 17273 0.9162 0.5659
0.875 24.0 18024 0.9090 0.5726
0.8022 25.0 18775 0.9023 0.5793
0.8471 26.0 19526 0.8959 0.5860
0.7822 27.0 20277 0.8898 0.5977
0.789 28.0 21028 0.8841 0.6010
0.8149 29.0 21779 0.8788 0.6027
0.7987 30.0 22530 0.8738 0.6077
0.7188 31.0 23281 0.8692 0.6160
0.802 32.0 24032 0.8649 0.6194
0.8114 33.0 24783 0.8608 0.6194
0.7414 34.0 25534 0.8570 0.6210
0.766 35.0 26285 0.8536 0.6210
0.7537 36.0 27036 0.8504 0.6260
0.7794 37.0 27787 0.8475 0.6277
0.7455 38.0 28538 0.8448 0.6311
0.7702 39.0 29289 0.8424 0.6311
0.75 40.0 30040 0.8403 0.6311
0.7442 41.0 30791 0.8384 0.6344
0.6885 42.0 31542 0.8367 0.6344
0.7317 43.0 32293 0.8353 0.6344
0.7377 44.0 33044 0.8340 0.6344
0.7327 45.0 33795 0.8330 0.6344
0.752 46.0 34546 0.8322 0.6361
0.7091 47.0 35297 0.8315 0.6361
0.7684 48.0 36048 0.8311 0.6361
0.7425 49.0 36799 0.8309 0.6361
0.7641 50.0 37550 0.8308 0.6361

Framework versions

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