swin-tiny-patch4-window7-224-finetuned-cifar100

This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the cifar100 dataset. It achieves the following results on the evaluation set:

• Loss: 0.5996
• Accuracy: 0.8154

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
1.5918	1.0	351	0.9104	0.7364
1.2837	2.0	703	0.6691	0.796
1.1241	2.99	1053	0.5996	0.8154

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.13.0
• Tokenizers 0.13.3