Edit model card

hushem_1x_beit_base_rms_00001_fold4

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: 0.2419
  • Accuracy: 0.9524

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
No log 1.0 6 1.3507 0.4286
1.4746 2.0 12 1.0121 0.5238
1.4746 3.0 18 0.4084 0.9048
0.4975 4.0 24 0.8867 0.6905
0.135 5.0 30 0.3643 0.9048
0.135 6.0 36 0.2799 0.9048
0.0217 7.0 42 0.2749 0.9286
0.0217 8.0 48 0.1461 0.9524
0.0073 9.0 54 0.2904 0.9286
0.003 10.0 60 0.2142 0.9762
0.003 11.0 66 0.2416 0.9048
0.0024 12.0 72 0.2155 0.9286
0.0024 13.0 78 0.1970 0.9524
0.0018 14.0 84 0.2474 0.9286
0.002 15.0 90 0.2996 0.9048
0.002 16.0 96 0.2243 0.9524
0.0011 17.0 102 0.2323 0.9524
0.0011 18.0 108 0.2007 0.9286
0.0019 19.0 114 0.2031 0.9286
0.0015 20.0 120 0.2492 0.9286
0.0015 21.0 126 0.2398 0.9286
0.0022 22.0 132 0.2207 0.9286
0.0022 23.0 138 0.2104 0.9286
0.001 24.0 144 0.2272 0.9524
0.0009 25.0 150 0.2107 0.9286
0.0009 26.0 156 0.2183 0.9524
0.0009 27.0 162 0.2098 0.9524
0.0009 28.0 168 0.2285 0.9524
0.0007 29.0 174 0.2209 0.9524
0.0007 30.0 180 0.2991 0.9524
0.0007 31.0 186 0.2929 0.9286
0.0008 32.0 192 0.2866 0.9286
0.0008 33.0 198 0.2902 0.9524
0.0007 34.0 204 0.2876 0.9524
0.0041 35.0 210 0.2290 0.9524
0.0041 36.0 216 0.2314 0.9524
0.0005 37.0 222 0.2320 0.9524
0.0005 38.0 228 0.2342 0.9524
0.0005 39.0 234 0.2418 0.9524
0.0012 40.0 240 0.2419 0.9524
0.0012 41.0 246 0.2420 0.9524
0.0006 42.0 252 0.2419 0.9524
0.0006 43.0 258 0.2419 0.9524
0.0007 44.0 264 0.2419 0.9524
0.0041 45.0 270 0.2419 0.9524
0.0041 46.0 276 0.2419 0.9524
0.0014 47.0 282 0.2419 0.9524
0.0014 48.0 288 0.2419 0.9524
0.0023 49.0 294 0.2419 0.9524
0.0004 50.0 300 0.2419 0.9524

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0
Downloads last month
0
Safetensors
Model size
85.8M params
Tensor type
F32
·
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/hushem_1x_beit_base_rms_00001_fold4

Finetuned
(285)
this model

Evaluation results