metadata

license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
  - image-classification
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: Vit-Base-30VN
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: vuongnhathien/30VNFoods
          type: imagefolder
          config: default
          split: validation
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8920634920634921

Vit-Base-30VN

This model is a fine-tuned version of google/vit-base-patch16-224 on the vuongnhathien/30VNFoods dataset. It achieves the following results on the evaluation set:

Loss: 0.5335
Accuracy: 0.8921

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: 64
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
0.6059	1.0	275	0.5290	0.8425
0.284	2.0	550	0.5239	0.8569
0.1336	3.0	825	0.6038	0.8469
0.0807	4.0	1100	0.5934	0.8628
0.0357	5.0	1375	0.6220	0.8588
0.0206	6.0	1650	0.5674	0.8803
0.0105	7.0	1925	0.5276	0.8907
0.005	8.0	2200	0.5096	0.8922
0.0018	9.0	2475	0.5064	0.8926
0.0035	10.0	2750	0.5055	0.8974

Framework versions

Transformers 4.39.3
Pytorch 2.1.2
Datasets 2.18.0
Tokenizers 0.15.2