ViT_face

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

• Loss: 0.2726

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: 2e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	38	0.8665
No log	2.0	76	0.6146
No log	3.0	114	0.4444
No log	4.0	152	0.3421
No log	5.0	190	0.3062
No log	6.0	228	0.3003
No log	7.0	266	0.2770
No log	8.0	304	0.2762
No log	9.0	342	0.2700
No log	10.0	380	0.2726

Framework versions

• Transformers 4.42.4
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1