hushem_1x_deit_rms_lr0001_fold3

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

  • Loss: 2.7920
  • Accuracy: 0.4651

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
No log 1.0 6 1.3959 0.2558
2.0191 2.0 12 1.4540 0.2791
2.0191 3.0 18 1.5040 0.3721
1.4688 4.0 24 1.3687 0.3256
1.3397 5.0 30 1.3082 0.4186
1.3397 6.0 36 1.3917 0.3256
1.1986 7.0 42 1.4209 0.3256
1.1986 8.0 48 1.4510 0.3721
1.0698 9.0 54 1.4225 0.3023
0.8214 10.0 60 1.5289 0.4186
0.8214 11.0 66 1.4884 0.4419
0.5823 12.0 72 2.0101 0.3256
0.5823 13.0 78 1.6036 0.5349
0.4001 14.0 84 1.6332 0.4186
0.2362 15.0 90 2.0095 0.4884
0.2362 16.0 96 1.8563 0.5581
0.1078 17.0 102 2.1555 0.5116
0.1078 18.0 108 2.0019 0.5581
0.0769 19.0 114 2.3852 0.4884
0.0351 20.0 120 2.4880 0.5349
0.0351 21.0 126 2.5950 0.4884
0.001 22.0 132 2.5992 0.4884
0.001 23.0 138 2.6117 0.4884
0.0006 24.0 144 2.6223 0.4884
0.0005 25.0 150 2.6443 0.4884
0.0005 26.0 156 2.6672 0.4884
0.0004 27.0 162 2.6883 0.4884
0.0004 28.0 168 2.6994 0.4884
0.0003 29.0 174 2.7093 0.4884
0.0003 30.0 180 2.7225 0.4884
0.0003 31.0 186 2.7350 0.4884
0.0003 32.0 192 2.7468 0.4651
0.0003 33.0 198 2.7564 0.4651
0.0003 34.0 204 2.7644 0.4651
0.0002 35.0 210 2.7717 0.4651
0.0002 36.0 216 2.7756 0.4651
0.0002 37.0 222 2.7805 0.4651
0.0002 38.0 228 2.7848 0.4651
0.0002 39.0 234 2.7876 0.4651
0.0002 40.0 240 2.7903 0.4651
0.0002 41.0 246 2.7917 0.4651
0.0002 42.0 252 2.7920 0.4651
0.0002 43.0 258 2.7920 0.4651
0.0002 44.0 264 2.7920 0.4651
0.0002 45.0 270 2.7920 0.4651
0.0002 46.0 276 2.7920 0.4651
0.0002 47.0 282 2.7920 0.4651
0.0002 48.0 288 2.7920 0.4651
0.0002 49.0 294 2.7920 0.4651
0.0002 50.0 300 2.7920 0.4651

Framework versions

  • Transformers 4.35.0
  • Pytorch 2.1.0+cu118
  • Datasets 2.14.6
  • Tokenizers 0.14.1
Downloads last month
29
Safetensors
Model size
5.53M 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_deit_tiny_rms_lr0001_fold3

Finetuned
(363)
this model

Evaluation results