face_poofing_detection

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.6273
• Accuracy: 0.9871

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
6.3243	0.9846	48	5.6154	0.8919
4.4794	1.9897	97	4.3516	0.9202
3.8293	2.9949	146	3.6687	0.9730
3.2121	4.0	195	3.1092	0.9820
2.733	4.9846	243	2.6919	0.9743
2.3114	5.9897	292	2.2633	0.9923
1.9962	6.9949	341	1.9594	0.9923
1.7789	8.0	390	1.7641	0.9897
1.6642	8.9846	438	1.6506	0.9910
1.6005	9.8462	480	1.6273	0.9871

Framework versions

• Transformers 4.44.2
• Pytorch 2.5.0+cu121
• Datasets 3.1.0
• Tokenizers 0.19.1