metadata
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: swin-tiny-patch4-window7-224-finetuned-fraud-detection
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9591584158415841
swin-tiny-patch4-window7-224-finetuned-fraud-detection
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1294
- Accuracy: 0.9592
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.1859 | 1.0 | 57 | 0.2052 | 0.9394 |
0.14 | 2.0 | 114 | 0.1544 | 0.9505 |
0.1296 | 3.0 | 171 | 0.1620 | 0.9530 |
0.1208 | 4.0 | 228 | 0.1573 | 0.9493 |
0.0889 | 5.0 | 285 | 0.1294 | 0.9592 |
0.0846 | 6.0 | 342 | 0.1400 | 0.9517 |
0.0775 | 7.0 | 399 | 0.1222 | 0.9567 |
0.0774 | 8.0 | 456 | 0.1564 | 0.9418 |
0.0577 | 9.0 | 513 | 0.1274 | 0.9579 |
0.0722 | 10.0 | 570 | 0.1332 | 0.9579 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.1