metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - recall
model-index:
  - name: vca
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: test
          args: default
        metrics:
          - name: Recall
            type: recall
            value: 0.7866666666666666

vca

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: 0.2021
Recall: 0.7867

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: 64
eval_batch_size: 64
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 256
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine_with_restarts
lr_scheduler_warmup_ratio: 0.1
num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Recall
No log	1.0	9	0.4676	0.0
No log	2.0	18	0.2918	0.0
No log	3.0	27	0.2191	0.0
No log	4.0	36	0.1971	0.1733
No log	5.0	45	0.1695	0.4133
No log	6.0	54	0.1693	0.52
No log	7.0	63	0.1597	0.5867
No log	8.0	72	0.1863	0.7733
No log	9.0	81	0.1591	0.72
No log	10.0	90	0.1543	0.72
No log	11.0	99	0.1559	0.6933
No log	12.0	108	0.1658	0.7333
No log	13.0	117	0.1691	0.6533
No log	14.0	126	0.1779	0.68
No log	15.0	135	0.1635	0.8133
No log	16.0	144	0.1765	0.6933
No log	17.0	153	0.1679	0.7333
No log	18.0	162	0.1694	0.7467
No log	19.0	171	0.1770	0.8133
No log	20.0	180	0.1692	0.7867
No log	21.0	189	0.2021	0.7867

Framework versions

Transformers 4.31.0.dev0
Pytorch 1.13.1+cu117
Datasets 2.11.0
Tokenizers 0.13.3