swin-finetuned-food101-e3

This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224 on the food101 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2714
• Accuracy: 0.9227

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: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• 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
0.5565	1.0	1183	0.3939	0.8856
0.3466	2.0	2366	0.2936	0.9156
0.1172	3.0	3549	0.2714	0.9227

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.0+cu116
• Datasets 2.7.1
• Tokenizers 0.13.2