metadata

license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: output_dir
    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: 0.575

output_dir

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: 1.2775
Accuracy: 0.575

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: 0.0007
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: 31

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.8	2	2.0745	0.1125
No log	2.0	5	1.9646	0.1875
No log	2.8	7	1.8686	0.325
1.9551	4.0	10	1.7196	0.3937
1.9551	4.8	12	1.5011	0.4813
1.9551	6.0	15	1.3693	0.4938
1.9551	6.8	17	1.4287	0.4625
1.3855	8.0	20	1.2961	0.5188
1.3855	8.8	22	1.2534	0.5312
1.3855	10.0	25	1.2544	0.5
1.3855	10.8	27	1.2417	0.5437
0.8352	12.0	30	1.1863	0.5437
0.8352	12.8	32	1.2524	0.5437
0.8352	14.0	35	1.3570	0.5062
0.8352	14.8	37	1.3046	0.5687
0.4513	16.0	40	1.3582	0.4688
0.4513	16.8	42	1.3063	0.5625
0.4513	18.0	45	1.3494	0.5312
0.4513	18.8	47	1.2484	0.5938
0.282	20.0	50	1.3694	0.5437
0.282	20.8	52	1.4651	0.5375
0.282	22.0	55	1.3577	0.5563
0.282	22.8	57	1.2522	0.5625
0.2038	24.0	60	1.4027	0.5813
0.2038	24.8	62	1.2445	0.5938

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.13.3