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: 1.4477
Accuracy: 0.5062

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	40	1.9208	0.2687
No log	2.0	80	1.6469	0.3688
1.7432	3.0	120	1.5591	0.45
1.7432	4.0	160	1.4880	0.4313
0.9778	5.0	200	1.4477	0.5062
0.9778	6.0	240	1.4999	0.45
0.9778	7.0	280	1.4733	0.475
0.442	8.0	320	1.4793	0.4625
0.442	9.0	360	1.5115	0.4625
0.2429	10.0	400	1.5220	0.4625

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.13.3

stevanojs/emotion_classification

emotion_classification

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

stevanojs/
emotion_classification