metadata
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-finetuned-cifar10
results: []
swin-tiny-patch4-window7-224-finetuned-cifar10
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0760
- Accuracy: 0.9758
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- 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 |
|---|---|---|---|---|
| 0.314 | 1.0 | 176 | 0.1211 | 0.9612 |
| 0.2992 | 2.0 | 352 | 0.1186 | 0.9622 |
| 0.3544 | 3.0 | 528 | 0.0989 | 0.968 |
| 0.3068 | 4.0 | 704 | 0.0872 | 0.9724 |
| 0.3421 | 5.0 | 880 | 0.0858 | 0.972 |
| 0.2915 | 6.0 | 1056 | 0.0824 | 0.9724 |
| 0.3051 | 7.0 | 1232 | 0.0822 | 0.974 |
| 0.2849 | 8.0 | 1408 | 0.0770 | 0.975 |
| 0.2661 | 9.0 | 1584 | 0.0773 | 0.9756 |
| 0.2504 | 10.0 | 1760 | 0.0760 | 0.9758 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2
- Datasets 2.16.1
- Tokenizers 0.15.0