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: 0.5240

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	0.9844
No log	2.0	76	0.8261
No log	3.0	114	0.6908
No log	4.0	152	0.6297
No log	5.0	190	0.5770
No log	6.0	228	0.5463
No log	7.0	266	0.5250
No log	8.0	304	0.5263
No log	9.0	342	0.5306
No log	10.0	380	0.5240

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.0
• Tokenizers 0.19.1