Edit model card

hushem_1x_beit_base_rms_001_fold5

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: 1.0249
  • Accuracy: 0.5610

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 4.0765 0.2683
4.3424 2.0 12 1.4584 0.2439
4.3424 3.0 18 1.4177 0.2439
1.6981 4.0 24 1.4396 0.2439
1.439 5.0 30 1.4302 0.2439
1.439 6.0 36 1.4113 0.2683
1.4514 7.0 42 1.4298 0.2439
1.4514 8.0 48 1.4142 0.2683
1.4037 9.0 54 1.3909 0.2683
1.4226 10.0 60 1.3819 0.2683
1.4226 11.0 66 1.3922 0.2683
1.3954 12.0 72 1.3475 0.2195
1.3954 13.0 78 1.3669 0.2439
1.4193 14.0 84 1.3582 0.2683
1.3817 15.0 90 1.3869 0.2439
1.3817 16.0 96 1.6362 0.2439
1.3794 17.0 102 1.4473 0.2439
1.3794 18.0 108 1.3118 0.4146
1.3773 19.0 114 1.3101 0.3415
1.3081 20.0 120 1.4119 0.2439
1.3081 21.0 126 1.2040 0.4634
1.2767 22.0 132 2.0544 0.2439
1.2767 23.0 138 1.2316 0.3415
1.3145 24.0 144 1.3728 0.2683
1.2519 25.0 150 1.3114 0.2927
1.2519 26.0 156 1.1523 0.5122
1.2177 27.0 162 1.1097 0.4634
1.2177 28.0 168 1.2516 0.3902
1.1299 29.0 174 1.1372 0.4390
1.1588 30.0 180 1.1704 0.4146
1.1588 31.0 186 1.0311 0.5610
1.1686 32.0 192 1.0730 0.4634
1.1686 33.0 198 1.0832 0.4634
1.038 34.0 204 1.1414 0.4878
1.0117 35.0 210 0.9564 0.6585
1.0117 36.0 216 1.1782 0.4146
1.0097 37.0 222 1.0629 0.5122
1.0097 38.0 228 1.0278 0.4634
0.9459 39.0 234 1.0014 0.5610
0.8786 40.0 240 0.9935 0.5854
0.8786 41.0 246 1.0190 0.5610
0.8792 42.0 252 1.0249 0.5610
0.8792 43.0 258 1.0249 0.5610
0.7834 44.0 264 1.0249 0.5610
0.8444 45.0 270 1.0249 0.5610
0.8444 46.0 276 1.0249 0.5610
0.8306 47.0 282 1.0249 0.5610
0.8306 48.0 288 1.0249 0.5610
0.8546 49.0 294 1.0249 0.5610
0.8485 50.0 300 1.0249 0.5610

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0
Downloads last month
1
Safetensors
Model size
85.8M params
Tensor type
F32
·
Inference API
Drag image file here or click to browse from your device
This model can be loaded on Inference API (serverless).

Finetuned from

Evaluation results