Edit model card

hushem_1x_deit_base_sgd_001_fold1

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

  • Loss: 1.4169
  • Accuracy: 0.2222

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 1.5144 0.1333
1.4099 2.0 12 1.5058 0.1333
1.4099 3.0 18 1.4975 0.1333
1.3953 4.0 24 1.4914 0.1333
1.3839 5.0 30 1.4843 0.1556
1.3839 6.0 36 1.4779 0.1778
1.3707 7.0 42 1.4724 0.1778
1.3707 8.0 48 1.4679 0.1778
1.3722 9.0 54 1.4633 0.1778
1.3434 10.0 60 1.4589 0.1778
1.3434 11.0 66 1.4552 0.2
1.3467 12.0 72 1.4521 0.2
1.3467 13.0 78 1.4488 0.2
1.3313 14.0 84 1.4460 0.2
1.33 15.0 90 1.4434 0.2
1.33 16.0 96 1.4413 0.2
1.325 17.0 102 1.4392 0.2
1.325 18.0 108 1.4371 0.2
1.3231 19.0 114 1.4349 0.2222
1.3131 20.0 120 1.4330 0.2222
1.3131 21.0 126 1.4314 0.2444
1.3095 22.0 132 1.4300 0.2444
1.3095 23.0 138 1.4284 0.2444
1.3181 24.0 144 1.4271 0.2444
1.2959 25.0 150 1.4260 0.2222
1.2959 26.0 156 1.4247 0.2222
1.2924 27.0 162 1.4239 0.2222
1.2924 28.0 168 1.4230 0.2222
1.2867 29.0 174 1.4221 0.2222
1.2887 30.0 180 1.4212 0.2222
1.2887 31.0 186 1.4204 0.2222
1.2851 32.0 192 1.4198 0.2222
1.2851 33.0 198 1.4193 0.2222
1.2896 34.0 204 1.4187 0.2222
1.2742 35.0 210 1.4183 0.2222
1.2742 36.0 216 1.4179 0.2222
1.2726 37.0 222 1.4176 0.2222
1.2726 38.0 228 1.4173 0.2222
1.2881 39.0 234 1.4171 0.2222
1.2721 40.0 240 1.4170 0.2222
1.2721 41.0 246 1.4169 0.2222
1.2788 42.0 252 1.4169 0.2222
1.2788 43.0 258 1.4169 0.2222
1.2737 44.0 264 1.4169 0.2222
1.2763 45.0 270 1.4169 0.2222
1.2763 46.0 276 1.4169 0.2222
1.2804 47.0 282 1.4169 0.2222
1.2804 48.0 288 1.4169 0.2222
1.2603 49.0 294 1.4169 0.2222
1.275 50.0 300 1.4169 0.2222

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu118
  • Datasets 2.14.7
  • 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_deit_base_sgd_001_fold1

Finetuned
(261)
this model

Evaluation results