smids_5x_beit_base_rms_0001_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: 1.3488
  • Accuracy: 0.855

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
0.5467 1.0 375 0.5969 0.7483
0.4112 2.0 750 0.6522 0.7967
0.3586 3.0 1125 0.4558 0.83
0.3318 4.0 1500 0.3669 0.8567
0.318 5.0 1875 0.4227 0.8267
0.2611 6.0 2250 0.4142 0.8467
0.2866 7.0 2625 0.4534 0.83
0.2297 8.0 3000 0.4296 0.8517
0.1623 9.0 3375 0.5359 0.835
0.1313 10.0 3750 0.5677 0.8433
0.1856 11.0 4125 0.5198 0.8667
0.087 12.0 4500 0.6463 0.8417
0.0974 13.0 4875 0.5874 0.8417
0.0478 14.0 5250 0.7058 0.84
0.0326 15.0 5625 0.7427 0.8283
0.0198 16.0 6000 0.8945 0.84
0.0746 17.0 6375 0.8489 0.8333
0.1024 18.0 6750 0.7564 0.8383
0.0499 19.0 7125 0.8028 0.8483
0.0808 20.0 7500 1.0400 0.8267
0.0495 21.0 7875 1.0596 0.83
0.0441 22.0 8250 0.9512 0.85
0.0385 23.0 8625 0.8380 0.8483
0.0162 24.0 9000 1.0671 0.8517
0.0061 25.0 9375 0.8747 0.86
0.0284 26.0 9750 1.0398 0.815
0.0446 27.0 10125 0.9748 0.845
0.0208 28.0 10500 1.0700 0.8517
0.0357 29.0 10875 1.0579 0.845
0.0301 30.0 11250 0.9043 0.8583
0.0099 31.0 11625 0.9420 0.8533
0.0327 32.0 12000 1.0192 0.8467
0.0502 33.0 12375 0.8952 0.8517
0.0352 34.0 12750 0.9041 0.8667
0.0188 35.0 13125 1.2059 0.8433
0.0229 36.0 13500 1.2761 0.84
0.0123 37.0 13875 1.1077 0.8583
0.0002 38.0 14250 1.1468 0.85
0.0009 39.0 14625 1.1590 0.8617
0.0211 40.0 15000 1.3901 0.8683
0.001 41.0 15375 1.2933 0.8533
0.0077 42.0 15750 1.1576 0.8583
0.0369 43.0 16125 1.3070 0.8433
0.0132 44.0 16500 1.0120 0.8633
0.0003 45.0 16875 1.2641 0.8633
0.0001 46.0 17250 1.2268 0.8633
0.0004 47.0 17625 1.1854 0.8583
0.0001 48.0 18000 1.3326 0.865
0.0187 49.0 18375 1.3505 0.8567
0.0011 50.0 18750 1.3488 0.855

Framework versions

  • Transformers 4.32.1
  • Pytorch 2.1.0+cu121
  • Datasets 2.12.0
  • Tokenizers 0.13.2
Downloads last month
7
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for hkivancoral/smids_5x_beit_base_rms_0001_fold3

Finetuned
(292)
this model

Evaluation results