metadata

license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: emotion_classification
    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: 0.5625

emotion_classification

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: 1.3460
Accuracy: 0.5625

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	1.8739	0.3375
No log	2.0	80	1.5652	0.4437
No log	3.0	120	1.4717	0.425
No log	4.0	160	1.4022	0.4437
No log	5.0	200	1.3310	0.4625
No log	6.0	240	1.2914	0.5188
No log	7.0	280	1.2637	0.4938
No log	8.0	320	1.2647	0.5375
No log	9.0	360	1.2992	0.5
No log	10.0	400	1.3180	0.4625
No log	11.0	440	1.2757	0.5563
No log	12.0	480	1.3529	0.5
1.0866	13.0	520	1.2583	0.5625
1.0866	14.0	560	1.3049	0.5375
1.0866	15.0	600	1.3013	0.5312
1.0866	16.0	640	1.3309	0.5312
1.0866	17.0	680	1.3396	0.5687
1.0866	18.0	720	1.3347	0.5062
1.0866	19.0	760	1.3495	0.55
1.0866	20.0	800	1.3423	0.525

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.13.3