hkivancoral's picture
End of training
8680b94
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_0001_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: 0.8714524207011686

smids_10x_beit_large_sgd_0001_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: 0.3289
  • Accuracy: 0.8715

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: 0.0001
  • 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
0.9122 1.0 751 1.0277 0.4591
0.7509 2.0 1502 0.8635 0.6194
0.6317 3.0 2253 0.7448 0.7012
0.5452 4.0 3004 0.6612 0.7446
0.5954 5.0 3755 0.5972 0.7830
0.5075 6.0 4506 0.5495 0.7930
0.5045 7.0 5257 0.5158 0.8130
0.4666 8.0 6008 0.4891 0.8147
0.4159 9.0 6759 0.4686 0.8247
0.4231 10.0 7510 0.4504 0.8280
0.4497 11.0 8261 0.4359 0.8364
0.3539 12.0 9012 0.4229 0.8381
0.3554 13.0 9763 0.4122 0.8414
0.3441 14.0 10514 0.4038 0.8414
0.3331 15.0 11265 0.3962 0.8431
0.3376 16.0 12016 0.3885 0.8431
0.374 17.0 12767 0.3827 0.8431
0.3157 18.0 13518 0.3768 0.8464
0.3563 19.0 14269 0.3725 0.8514
0.3183 20.0 15020 0.3682 0.8548
0.2569 21.0 15771 0.3646 0.8598
0.312 22.0 16522 0.3608 0.8581
0.3262 23.0 17273 0.3576 0.8598
0.3722 24.0 18024 0.3550 0.8598
0.3339 25.0 18775 0.3524 0.8598
0.3725 26.0 19526 0.3497 0.8631
0.35 27.0 20277 0.3474 0.8664
0.3858 28.0 21028 0.3456 0.8648
0.3212 29.0 21779 0.3439 0.8664
0.3222 30.0 22530 0.3422 0.8681
0.2584 31.0 23281 0.3410 0.8664
0.3877 32.0 24032 0.3393 0.8698
0.3116 33.0 24783 0.3380 0.8698
0.3141 34.0 25534 0.3366 0.8715
0.3279 35.0 26285 0.3358 0.8681
0.2798 36.0 27036 0.3348 0.8715
0.3928 37.0 27787 0.3341 0.8715
0.3 38.0 28538 0.3331 0.8715
0.2471 39.0 29289 0.3324 0.8715
0.3456 40.0 30040 0.3317 0.8715
0.3078 41.0 30791 0.3311 0.8715
0.24 42.0 31542 0.3306 0.8715
0.289 43.0 32293 0.3302 0.8715
0.2977 44.0 33044 0.3297 0.8715
0.2559 45.0 33795 0.3294 0.8715
0.3508 46.0 34546 0.3292 0.8715
0.26 47.0 35297 0.3291 0.8715
0.3325 48.0 36048 0.3290 0.8715
0.2898 49.0 36799 0.3289 0.8715
0.2912 50.0 37550 0.3289 0.8715

Framework versions

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