README.md

metadata

library_name: transformers
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: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.46875

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: 1.4789
• Accuracy: 0.4688

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: 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: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	20	1.9690	0.2812
No log	2.0	40	1.7928	0.4
No log	3.0	60	1.6533	0.4313
No log	4.0	80	1.5701	0.45
No log	5.0	100	1.5244	0.45
No log	6.0	120	1.4789	0.4688
No log	7.0	140	1.4781	0.4688
No log	8.0	160	1.4793	0.4375
No log	9.0	180	1.4670	0.4375
No log	10.0	200	1.5136	0.45
No log	11.0	220	1.5041	0.45
No log	12.0	240	1.5178	0.4437
No log	13.0	260	1.5302	0.4437
No log	14.0	280	1.5348	0.45
No log	15.0	300	1.5386	0.45

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1