metadata
license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_5x_deit_tiny_sgd_0001_fold1
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.26666666666666666
hushem_5x_deit_tiny_sgd_0001_fold1
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: 1.5185
- Accuracy: 0.2667
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 |
|---|---|---|---|---|
| 1.5559 | 1.0 | 27 | 1.6659 | 0.2667 |
| 1.5307 | 2.0 | 54 | 1.6510 | 0.2667 |
| 1.5463 | 3.0 | 81 | 1.6380 | 0.2889 |
| 1.5241 | 4.0 | 108 | 1.6272 | 0.2889 |
| 1.4794 | 5.0 | 135 | 1.6169 | 0.2889 |
| 1.5071 | 6.0 | 162 | 1.6070 | 0.2889 |
| 1.4768 | 7.0 | 189 | 1.5986 | 0.2889 |
| 1.4869 | 8.0 | 216 | 1.5910 | 0.2889 |
| 1.4651 | 9.0 | 243 | 1.5844 | 0.3111 |
| 1.4396 | 10.0 | 270 | 1.5781 | 0.3111 |
| 1.4572 | 11.0 | 297 | 1.5728 | 0.3111 |
| 1.4029 | 12.0 | 324 | 1.5680 | 0.3111 |
| 1.4355 | 13.0 | 351 | 1.5638 | 0.3111 |
| 1.4582 | 14.0 | 378 | 1.5597 | 0.2889 |
| 1.4073 | 15.0 | 405 | 1.5561 | 0.2889 |
| 1.4381 | 16.0 | 432 | 1.5526 | 0.2889 |
| 1.4333 | 17.0 | 459 | 1.5495 | 0.2889 |
| 1.3978 | 18.0 | 486 | 1.5468 | 0.2889 |
| 1.3884 | 19.0 | 513 | 1.5441 | 0.2889 |
| 1.3796 | 20.0 | 540 | 1.5418 | 0.2889 |
| 1.4025 | 21.0 | 567 | 1.5397 | 0.2889 |
| 1.3822 | 22.0 | 594 | 1.5376 | 0.2889 |
| 1.3868 | 23.0 | 621 | 1.5359 | 0.2889 |
| 1.3907 | 24.0 | 648 | 1.5343 | 0.2889 |
| 1.38 | 25.0 | 675 | 1.5327 | 0.2667 |
| 1.3755 | 26.0 | 702 | 1.5313 | 0.2667 |
| 1.3485 | 27.0 | 729 | 1.5299 | 0.2667 |
| 1.3648 | 28.0 | 756 | 1.5287 | 0.2667 |
| 1.3797 | 29.0 | 783 | 1.5276 | 0.2667 |
| 1.3716 | 30.0 | 810 | 1.5265 | 0.2667 |
| 1.389 | 31.0 | 837 | 1.5256 | 0.2667 |
| 1.3813 | 32.0 | 864 | 1.5247 | 0.2667 |
| 1.3289 | 33.0 | 891 | 1.5240 | 0.2667 |
| 1.3517 | 34.0 | 918 | 1.5232 | 0.2667 |
| 1.3834 | 35.0 | 945 | 1.5225 | 0.2667 |
| 1.3458 | 36.0 | 972 | 1.5218 | 0.2667 |
| 1.3745 | 37.0 | 999 | 1.5212 | 0.2667 |
| 1.3761 | 38.0 | 1026 | 1.5207 | 0.2667 |
| 1.3726 | 39.0 | 1053 | 1.5203 | 0.2667 |
| 1.3125 | 40.0 | 1080 | 1.5199 | 0.2667 |
| 1.3599 | 41.0 | 1107 | 1.5196 | 0.2667 |
| 1.3277 | 42.0 | 1134 | 1.5193 | 0.2667 |
| 1.3748 | 43.0 | 1161 | 1.5191 | 0.2667 |
| 1.3689 | 44.0 | 1188 | 1.5188 | 0.2667 |
| 1.3379 | 45.0 | 1215 | 1.5187 | 0.2667 |
| 1.3358 | 46.0 | 1242 | 1.5186 | 0.2667 |
| 1.3497 | 47.0 | 1269 | 1.5185 | 0.2667 |
| 1.3482 | 48.0 | 1296 | 1.5185 | 0.2667 |
| 1.3616 | 49.0 | 1323 | 1.5185 | 0.2667 |
| 1.3216 | 50.0 | 1350 | 1.5185 | 0.2667 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0