README.md

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: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.49375

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: 1.4194
• Accuracy: 0.4938

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: 40

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	40	1.8274	0.325
No log	2.0	80	1.5456	0.4437
No log	3.0	120	1.4503	0.425
No log	4.0	160	1.3753	0.4688
No log	5.0	200	1.3046	0.4813
No log	6.0	240	1.2786	0.4875
No log	7.0	280	1.4095	0.4875
No log	8.0	320	1.3636	0.4688
No log	9.0	360	1.3518	0.4562
No log	10.0	400	1.4466	0.4688
No log	11.0	440	1.3533	0.5125
No log	12.0	480	1.3538	0.5125
1.002	13.0	520	1.3608	0.5188
1.002	14.0	560	1.3736	0.55
1.002	15.0	600	1.4872	0.4688
1.002	16.0	640	1.4549	0.525
1.002	17.0	680	1.4956	0.5062
1.002	18.0	720	1.5431	0.475
1.002	19.0	760	1.5045	0.5312
1.002	20.0	800	1.5330	0.525
1.002	21.0	840	1.4794	0.5375
1.002	22.0	880	1.4762	0.5375
1.002	23.0	920	1.5691	0.4813
1.002	24.0	960	1.5839	0.5
0.2831	25.0	1000	1.6461	0.4813
0.2831	26.0	1040	1.6359	0.4813
0.2831	27.0	1080	1.5603	0.525
0.2831	28.0	1120	1.5738	0.5
0.2831	29.0	1160	1.6534	0.4938
0.2831	30.0	1200	1.7387	0.4813
0.2831	31.0	1240	1.7778	0.4562
0.2831	32.0	1280	1.6399	0.525
0.2831	33.0	1320	1.6575	0.5437
0.2831	34.0	1360	1.6041	0.5062
0.2831	35.0	1400	1.8253	0.4813
0.2831	36.0	1440	1.6909	0.4875
0.2831	37.0	1480	1.6586	0.5437
0.1654	38.0	1520	1.6183	0.5125
0.1654	39.0	1560	1.6045	0.5188
0.1654	40.0	1600	1.6228	0.4938

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3