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: 0.6202
- 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 |
|---|---|---|---|---|
| 1.1537 | 0.98 | 20 | 1.0005 | 0.5479 |
| 0.7025 | 2.0 | 41 | 0.8481 | 0.5936 |
| 0.6581 | 2.98 | 61 | 0.6351 | 0.7215 |
| 0.5019 | 4.0 | 82 | 0.6696 | 0.7215 |
| 0.4708 | 4.98 | 102 | 0.5861 | 0.7534 |
| 0.3647 | 6.0 | 123 | 0.5584 | 0.7763 |
| 0.2973 | 6.98 | 143 | 0.5784 | 0.7671 |
| 0.2827 | 8.0 | 164 | 0.5851 | 0.7671 |
| 0.237 | 8.98 | 184 | 0.6791 | 0.7626 |
| 0.2505 | 10.0 | 205 | 0.5550 | 0.7626 |
| 0.2018 | 10.98 | 225 | 0.5446 | 0.7626 |
| 0.1841 | 12.0 | 246 | 0.5497 | 0.7443 |
| 0.1692 | 12.98 | 266 | 0.5917 | 0.7717 |
| 0.1624 | 14.0 | 287 | 0.5254 | 0.7763 |
| 0.1518 | 14.98 | 307 | 0.5296 | 0.7808 |
| 0.1275 | 16.0 | 328 | 0.5858 | 0.7626 |
| 0.1107 | 16.98 | 348 | 0.5919 | 0.7763 |
| 0.1192 | 18.0 | 369 | 0.6027 | 0.7717 |
| 0.0842 | 18.98 | 389 | 0.6435 | 0.7717 |
| 0.1472 | 19.51 | 400 | 0.6202 | 0.7671 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3