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: 0.2038

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	0.8817
No log	2.0	76	0.6110
No log	3.0	114	0.4243
No log	4.0	152	0.3180
No log	5.0	190	0.2811
No log	6.0	228	0.2286
No log	7.0	266	0.2133
No log	8.0	304	0.2082
No log	9.0	342	0.2050
No log	10.0	380	0.2038

Framework versions

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