swin-finetuned-food101

This model is a fine-tuned version of microsoft/swin-large-patch4-window7-224-in22k on the zindi dataset. It achieves the following results on the evaluation set:

• Loss: 0.5697
• Accuracy: 0.7666

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
0.7373	1.0	173	0.6503	0.7366
0.6106	2.0	347	0.5950	0.7503
0.5135	2.99	519	0.5697	0.7666

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.0
• Tokenizers 0.15.0