metadata
license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: deit-tiny-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: 0.8127853881278538
deit-tiny-patch16-224-finetuned-piid
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: 0.5154
- Accuracy: 0.8128
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 |
---|---|---|---|---|
1.2298 | 0.98 | 20 | 1.1138 | 0.4703 |
0.7642 | 2.0 | 41 | 0.9123 | 0.5982 |
0.6167 | 2.98 | 61 | 0.6736 | 0.6849 |
0.5628 | 4.0 | 82 | 0.6615 | 0.7032 |
0.5616 | 4.98 | 102 | 0.5985 | 0.7352 |
0.4742 | 6.0 | 123 | 0.4981 | 0.7854 |
0.3434 | 6.98 | 143 | 0.5729 | 0.7489 |
0.3691 | 8.0 | 164 | 0.5779 | 0.7397 |
0.3375 | 8.98 | 184 | 0.5417 | 0.7580 |
0.3192 | 10.0 | 205 | 0.5554 | 0.7534 |
0.2795 | 10.98 | 225 | 0.5656 | 0.7763 |
0.242 | 12.0 | 246 | 0.5319 | 0.7991 |
0.2557 | 12.98 | 266 | 0.5154 | 0.8128 |
0.2465 | 14.0 | 287 | 0.5763 | 0.7991 |
0.221 | 14.98 | 307 | 0.5683 | 0.8037 |
0.2058 | 16.0 | 328 | 0.5852 | 0.8128 |
0.1809 | 16.98 | 348 | 0.6282 | 0.8082 |
0.1638 | 18.0 | 369 | 0.6289 | 0.7945 |
0.155 | 18.98 | 389 | 0.6134 | 0.8037 |
0.2094 | 19.51 | 400 | 0.6114 | 0.8082 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3