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: 1.2807
Accuracy: 0.525

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
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	40	1.8038	0.3875
No log	2.0	80	1.5444	0.4125
No log	3.0	120	1.4651	0.4188
No log	4.0	160	1.3985	0.4562
No log	5.0	200	1.2891	0.525
No log	6.0	240	1.2928	0.5
No log	7.0	280	1.3412	0.5
No log	8.0	320	1.3548	0.475
No log	9.0	360	1.2867	0.5312
No log	10.0	400	1.3636	0.475
No log	11.0	440	1.3431	0.5188
No log	12.0	480	1.2872	0.5312
1.0092	13.0	520	1.3491	0.525
1.0092	14.0	560	1.2864	0.5437
1.0092	15.0	600	1.3278	0.5312
1.0092	16.0	640	1.3772	0.5062
1.0092	17.0	680	1.4458	0.5
1.0092	18.0	720	1.3208	0.525
1.0092	19.0	760	1.4037	0.5
1.0092	20.0	800	1.2810	0.5375

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu121
Datasets 2.17.0
Tokenizers 0.15.1

felitrisnanto/ViT-emotion-classification

ViT-emotion-classification

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

felitrisnanto/
ViT-emotion-classification