metadata

license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
  - precision
  - recall
model-index:
  - name: vit-base-patch16-224
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: validation
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.7066666666666667
          - name: Precision
            type: precision
            value: 0.5034113712374582
          - name: Recall
            type: recall
            value: 0.7066666666666667

vit-base-patch16-224

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

Loss: 0.5891
Accuracy: 0.7067
Precision: 0.5034
Recall: 0.7067
F1 Score: 0.5880

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: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1 Score
No log	1.0	4	0.5970	0.725	0.5256	0.725	0.6094
No log	2.0	8	0.5990	0.7292	0.8028	0.7292	0.6191
No log	3.0	12	0.5648	0.725	0.5256	0.725	0.6094
0.6217	4.0	16	0.6035	0.7042	0.6625	0.7042	0.6709
0.6217	5.0	20	0.5560	0.7333	0.8050	0.7333	0.6286
0.6217	6.0	24	0.5656	0.7167	0.6184	0.7167	0.6194
0.6217	7.0	28	0.5552	0.7292	0.8028	0.7292	0.6191
0.5729	8.0	32	0.5532	0.7292	0.7126	0.7292	0.6263
0.5729	9.0	36	0.5634	0.7292	0.6863	0.7292	0.6453
0.5729	10.0	40	0.5589	0.7333	0.7009	0.7333	0.6536
0.5729	11.0	44	0.5676	0.7292	0.6848	0.7292	0.6612
0.5599	12.0	48	0.5655	0.7333	0.6952	0.7333	0.6688
0.5599	13.0	52	0.5692	0.7333	0.6954	0.7333	0.6816
0.5599	14.0	56	0.5746	0.725	0.6864	0.725	0.6863
0.5382	15.0	60	0.5752	0.7208	0.6832	0.7208	0.6864

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.13.3