swin-base-patch4-window7-224-in22k-MM_Classification_base_web_images

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

• Loss: 0.3017
• Accuracy: 0.8838

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: 7

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.517	0.9927	68	0.4430	0.8157
0.4211	2.0	137	0.3800	0.8457
0.3532	2.9927	205	0.3563	0.8616
0.3365	4.0	274	0.3333	0.8700
0.2976	4.9927	342	0.3017	0.8838
0.2611	6.0	411	0.3119	0.8810
0.255	6.9489	476	0.3085	0.8820

Framework versions

• Transformers 4.44.0
• Pytorch 1.13.1+cu117
• Datasets 2.20.0
• Tokenizers 0.19.1