swin-tiny-patch4-window7-224

This model is a fine-tuned version of jagriti/swin-tiny-patch4-window7-224 on the cifar10 dataset. It achieves the following results on the evaluation set:

• Loss: 0.0907
• Accuracy: 0.9694

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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4991	1.0	351	0.1543	0.947
0.346	2.0	703	0.1023	0.964
0.3329	2.99	1053	0.0907	0.9694

Framework versions

• Transformers 4.29.2
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3