metadata

license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: visual_emotion_classification_vit_base_finetunned
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.5125

visual_emotion_classification_vit_base_finetunned

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: 1.3576
Accuracy: 0.5125

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: 2.5e-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: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	40	1.9700	0.2625
2.0074	2.0	80	1.7194	0.3688
1.726	3.0	120	1.5775	0.3875
1.5202	4.0	160	1.4900	0.4875
1.3857	5.0	200	1.4261	0.4938
1.3857	6.0	240	1.4090	0.5
1.2831	7.0	280	1.3510	0.475
1.2007	8.0	320	1.3788	0.475
1.1256	9.0	360	1.3183	0.5
1.0345	10.0	400	1.2937	0.4813
1.0345	11.0	440	1.2384	0.5437
0.9438	12.0	480	1.2100	0.525
0.872	13.0	520	1.2450	0.525
0.8193	14.0	560	1.2264	0.5312
0.763	15.0	600	1.2296	0.5125
0.763	16.0	640	1.2539	0.5188
0.7166	17.0	680	1.2253	0.5563
0.6328	18.0	720	1.2723	0.5312
0.5917	19.0	760	1.2870	0.4875
0.5841	20.0	800	1.3011	0.5375
0.5841	21.0	840	1.2071	0.575
0.559	22.0	880	1.2555	0.575
0.5109	23.0	920	1.3140	0.5
0.5036	24.0	960	1.2593	0.5
0.4787	25.0	1000	1.2573	0.5813
0.4787	26.0	1040	1.2163	0.55
0.4583	27.0	1080	1.2349	0.5563
0.4766	28.0	1120	1.3349	0.5188
0.4709	29.0	1160	1.3284	0.5312
0.4442	30.0	1200	1.2684	0.5625

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu121
Datasets 2.17.0
Tokenizers 0.15.1