| --- |
| library_name: transformers |
| license: apache-2.0 |
| base_model: microsoft/swin-tiny-patch4-window7-224 |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| model-index: |
| - name: swin-tiny-patch4-window7-224-cifar100 |
| results: [] |
| --- |
| |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| should probably proofread and complete it, then remove this comment. --> |
|
|
| # swin-tiny-patch4-window7-224-cifar100 |
|
|
| This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.4724 |
| - Accuracy: 0.8783 |
|
|
| ## 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: 128 |
| - eval_batch_size: 64 |
| - seed: 42 |
| - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| - lr_scheduler_type: cosine |
| - lr_scheduler_warmup_steps: 0.1 |
| - num_epochs: 10 |
| - mixed_precision_training: Native AMP |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | |
| |:-------------:|:------:|:----:|:---------------:|:--------:| |
| | 0.7531 | 1.2788 | 500 | 0.7326 | 0.7825 | |
| | 0.4348 | 2.5575 | 1000 | 0.5393 | 0.8389 | |
| | 0.3005 | 3.8363 | 1500 | 0.4975 | 0.8536 | |
| | 0.1651 | 5.1151 | 2000 | 0.4906 | 0.8664 | |
| | 0.0960 | 6.3939 | 2500 | 0.4844 | 0.8701 | |
| | 0.0716 | 7.6726 | 3000 | 0.4771 | 0.8767 | |
| | 0.0538 | 8.9514 | 3500 | 0.4724 | 0.8783 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 5.3.0 |
| - Pytorch 2.6.0+cu124 |
| - Datasets 4.8.3 |
| - Tokenizers 0.22.2 |
| |
