metadata
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: cards-swin-tiny-patch4-window7-224-finetuned-v1
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: 0.4106853980417199
cards-swin-tiny-patch4-window7-224-finetuned-v1
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: 1.3763
- Accuracy: 0.4107
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 |
|---|---|---|---|---|
| 1.6417 | 1.0 | 734 | 1.6075 | 0.3000 |
| 1.577 | 2.0 | 1468 | 1.5511 | 0.3355 |
| 1.5699 | 3.0 | 2202 | 1.4887 | 0.3567 |
| 1.5361 | 4.0 | 2936 | 1.4659 | 0.3686 |
| 1.525 | 5.0 | 3670 | 1.4169 | 0.3920 |
| 1.4744 | 6.0 | 4404 | 1.4029 | 0.3957 |
| 1.4846 | 7.0 | 5138 | 1.3962 | 0.4029 |
| 1.4729 | 8.0 | 5872 | 1.3932 | 0.4026 |
| 1.4416 | 9.0 | 6606 | 1.3821 | 0.4088 |
| 1.4255 | 10.0 | 7340 | 1.3763 | 0.4107 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.0.1+cu117
- Datasets 2.17.0
- Tokenizers 0.15.2