README.md

metadata

library_name: transformers
license: apache-2.0
base_model: google/vit-large-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: vit_4090_downsample_normal_da
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: test
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.35706727135298566
          - name: Precision
            type: precision
            value: 0.426496961448031
          - name: Recall
            type: recall
            value: 0.35706727135298566
          - name: F1
            type: f1
            value: 0.30112832284646396

vit_4090_downsample_normal_da

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

• Loss: 6.3528
• Accuracy: 0.3571
• Precision: 0.4265
• Recall: 0.3571
• F1: 0.3011

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: 0.0001
• train_batch_size: 24
• eval_batch_size: 4
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.1307	1.0	1834	4.1849	0.3710	0.4442	0.3710	0.3346
0.0388	2.0	3668	4.7670	0.3805	0.4413	0.3805	0.3444
0.0277	3.0	5502	4.5994	0.4204	0.4645	0.4204	0.3922
0.0174	4.0	7336	4.7754	0.3619	0.4226	0.3619	0.3361
0.0113	5.0	9170	5.1718	0.3586	0.4126	0.3586	0.3005
0.0092	6.0	11004	4.9205	0.3800	0.4535	0.3800	0.3450
0.005	7.0	12838	5.8665	0.3701	0.3679	0.3701	0.2726
0.0033	8.0	14672	5.8658	0.3382	0.4145	0.3382	0.3009
0.001	9.0	16506	6.1933	0.3495	0.3938	0.3495	0.2864
0.0001	10.0	18340	6.3528	0.3571	0.4265	0.3571	0.3011

Framework versions

• Transformers 4.49.0
• Pytorch 2.5.1
• Datasets 3.2.0
• Tokenizers 0.21.1