metadata

license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: image_classification
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: en-US
          split: train
          args: en-US
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.60625

image_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: 1.1918
Accuracy: 0.6062

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: 0.0003
train_batch_size: 32
eval_batch_size: 32
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	20	1.6651	0.3187
No log	2.0	40	1.3900	0.475
No log	3.0	60	1.2950	0.4875
No log	4.0	80	1.2170	0.5813
No log	5.0	100	1.1709	0.5687
No log	6.0	120	1.2711	0.525
No log	7.0	140	1.1324	0.575
No log	8.0	160	1.2349	0.5437
No log	9.0	180	1.3844	0.5312
No log	10.0	200	1.2460	0.55
No log	11.0	220	1.2182	0.6125
No log	12.0	240	1.3365	0.5563
No log	13.0	260	1.2137	0.6125
No log	14.0	280	1.3335	0.575
No log	15.0	300	1.1078	0.625
No log	16.0	320	1.2962	0.6
No log	17.0	340	1.2558	0.6125
No log	18.0	360	1.3949	0.55
No log	19.0	380	1.3807	0.5687
No log	20.0	400	1.2734	0.6

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.13.3