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: 0.78
          - name: Precision
            type: precision
            value: 0.781535758027584
          - name: Recall
            type: recall
            value: 0.78

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: 0.4819
Accuracy: 0.78
Precision: 0.7815
Recall: 0.78
F1 Score: 0.7807

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: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1 Score
No log	1.0	4	0.5936	0.7292	0.8028	0.7292	0.6191
No log	2.0	8	0.5702	0.7208	0.6468	0.7208	0.6283
No log	3.0	12	0.5834	0.7125	0.6933	0.7125	0.7000
No log	4.0	16	0.5471	0.7375	0.7034	0.7375	0.6846
No log	5.0	20	0.5487	0.725	0.6938	0.725	0.6982
No log	6.0	24	0.5253	0.7458	0.7182	0.7458	0.7116
No log	7.0	28	0.5556	0.7417	0.7393	0.7417	0.7404
0.5648	8.0	32	0.5183	0.7417	0.7155	0.7417	0.7165
0.5648	9.0	36	0.5159	0.7667	0.7504	0.7667	0.7522
0.5648	10.0	40	0.5137	0.7708	0.7579	0.7708	0.7609
0.5648	11.0	44	0.5014	0.7833	0.7693	0.7833	0.7643
0.5648	12.0	48	0.5157	0.75	0.7524	0.75	0.7511
0.5648	13.0	52	0.5151	0.7417	0.7441	0.7417	0.7428
0.5648	14.0	56	0.4908	0.7792	0.7653	0.7792	0.7663
0.3814	15.0	60	0.4901	0.7833	0.7723	0.7833	0.7747
0.3814	16.0	64	0.4993	0.7667	0.7689	0.7667	0.7677
0.3814	17.0	68	0.4814	0.7792	0.7642	0.7792	0.7627
0.3814	18.0	72	0.5165	0.7583	0.7796	0.7583	0.7656
0.3814	19.0	76	0.4817	0.7958	0.7915	0.7958	0.7933
0.3814	20.0	80	0.4748	0.8083	0.8036	0.8083	0.8054
0.3814	21.0	84	0.4831	0.8042	0.8033	0.8042	0.8037
0.3814	22.0	88	0.4795	0.8083	0.8013	0.8083	0.8032
0.2354	23.0	92	0.5048	0.7708	0.7790	0.7708	0.7743
0.2354	24.0	96	0.4838	0.8042	0.7974	0.8042	0.7995
0.2354	25.0	100	0.4894	0.7833	0.7833	0.7833	0.7833
0.2354	26.0	104	0.4852	0.8	0.7914	0.8	0.7933
0.2354	27.0	108	0.4882	0.8	0.7982	0.8	0.7990
0.2354	28.0	112	0.4932	0.7875	0.7929	0.7875	0.7898
0.2354	29.0	116	0.4883	0.8083	0.8036	0.8083	0.8054
0.1479	30.0	120	0.4886	0.8042	0.7974	0.8042	0.7995

Framework versions

Transformers 4.33.3
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.13.3