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: 0.53125

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: 1.3583
• Accuracy: 0.5312

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: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	40	1.3917	0.5
No log	2.0	80	1.3327	0.525
No log	3.0	120	1.2901	0.5062
No log	4.0	160	1.3720	0.45
No log	5.0	200	1.4239	0.4688
No log	6.0	240	1.3587	0.5125
No log	7.0	280	1.3874	0.5
No log	8.0	320	1.3341	0.5312
No log	9.0	360	1.2295	0.6
No log	10.0	400	1.3267	0.5563
No log	11.0	440	1.3808	0.5375
No log	12.0	480	1.3547	0.55
0.6621	13.0	520	1.5197	0.5125
0.6621	14.0	560	1.5709	0.525
0.6621	15.0	600	1.4058	0.5875
0.6621	16.0	640	1.4561	0.5375
0.6621	17.0	680	1.6183	0.525
0.6621	18.0	720	1.6036	0.525
0.6621	19.0	760	1.5561	0.5375
0.6621	20.0	800	1.6527	0.5
0.6621	21.0	840	1.7574	0.5188
0.6621	22.0	880	1.8418	0.475
0.6621	23.0	920	1.5058	0.5625
0.6621	24.0	960	1.8427	0.4938
0.2166	25.0	1000	1.7561	0.4938
0.2166	26.0	1040	1.7327	0.525
0.2166	27.0	1080	1.8137	0.5125
0.2166	28.0	1120	1.8352	0.4938
0.2166	29.0	1160	1.7171	0.55
0.2166	30.0	1200	2.0487	0.4688
0.2166	31.0	1240	1.8911	0.4688
0.2166	32.0	1280	1.5932	0.5563
0.2166	33.0	1320	1.7250	0.5062
0.2166	34.0	1360	1.9414	0.5125
0.2166	35.0	1400	1.9959	0.4688
0.2166	36.0	1440	1.9066	0.4938
0.2166	37.0	1480	1.8892	0.5312
0.1291	38.0	1520	1.8439	0.5375
0.1291	39.0	1560	2.0001	0.525
0.1291	40.0	1600	1.9060	0.5
0.1291	41.0	1640	1.9419	0.5375
0.1291	42.0	1680	1.7496	0.5563
0.1291	43.0	1720	1.9750	0.5188
0.1291	44.0	1760	2.0106	0.5188
0.1291	45.0	1800	1.9180	0.55
0.1291	46.0	1840	1.9644	0.525
0.1291	47.0	1880	1.8182	0.5687
0.1291	48.0	1920	1.9591	0.5312
0.1291	49.0	1960	1.8103	0.5687
0.0866	50.0	2000	2.0038	0.5125

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.0
• Tokenizers 0.15.2