metadata
license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: deit-small-patch16-224-finetuned-piid
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: val
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.7671232876712328
deit-small-patch16-224-finetuned-piid
This model is a fine-tuned version of facebook/deit-small-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.6409
- Accuracy: 0.7671
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.2316 | 0.98 | 20 | 1.0505 | 0.5251 |
| 0.7423 | 2.0 | 41 | 0.7781 | 0.6347 |
| 0.6286 | 2.98 | 61 | 0.7165 | 0.6712 |
| 0.5196 | 4.0 | 82 | 0.6297 | 0.7260 |
| 0.4871 | 4.98 | 102 | 0.6319 | 0.7352 |
| 0.3666 | 6.0 | 123 | 0.5845 | 0.7443 |
| 0.2804 | 6.98 | 143 | 0.6830 | 0.7260 |
| 0.2812 | 8.0 | 164 | 0.5775 | 0.7580 |
| 0.2244 | 8.98 | 184 | 0.6285 | 0.7397 |
| 0.233 | 10.0 | 205 | 0.5887 | 0.7671 |
| 0.2368 | 10.98 | 225 | 0.6399 | 0.7671 |
| 0.1849 | 12.0 | 246 | 0.6024 | 0.7626 |
| 0.1877 | 12.98 | 266 | 0.5884 | 0.7763 |
| 0.1686 | 14.0 | 287 | 0.6725 | 0.7900 |
| 0.1769 | 14.98 | 307 | 0.5996 | 0.7671 |
| 0.1267 | 16.0 | 328 | 0.6102 | 0.7626 |
| 0.0933 | 16.98 | 348 | 0.6367 | 0.7854 |
| 0.1247 | 18.0 | 369 | 0.6364 | 0.7626 |
| 0.0837 | 18.98 | 389 | 0.6379 | 0.7671 |
| 0.1476 | 19.51 | 400 | 0.6409 | 0.7671 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1