You can deploy this model and start earning money today!

mluger/
vitFaceExpressionBalancedAugmentationFer2013Plus

transformers

tensorboard

safetensors

generated_from_trainer

imagefolder

google/vit-base-patch16-224-in21k

Views

No views yet

vitFaceExpressionBalancedAugmentationFer2013Plus

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

Loss: 0.5194
Accuracy: 0.8405

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: 3e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.2073	1.0	666	0.6685	0.7808
0.8278	2.0	1332	0.5579	0.8131
0.7247	3.0	1998	0.5157	0.8252
0.4977	4.0	2664	0.5088	0.8300
0.405	5.0	3330	0.5071	0.8384
0.3964	6.0	3996	0.5110	0.8394
0.2824	7.0	4662	0.5183	0.8421
0.3041	8.0	5328	0.5194	0.8405

Framework versions

Transformers 4.51.3
Pytorch 2.6.0+cu124
Datasets 3.5.1
Tokenizers 0.21.1

mluger/vitFaceExpressionBalancedAugmentationFer2013Plus

vitFaceExpressionBalancedAugmentationFer2013Plus

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

mluger/
vitFaceExpressionBalancedAugmentationFer2013Plus