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: 0.5125

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: 1.3634
Accuracy: 0.5125

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
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.0947	1.0	10	2.0806	0.1375
2.0549	2.0	20	2.0395	0.175
1.9588	3.0	30	1.9427	0.2812
1.8014	4.0	40	1.7817	0.3438
1.6343	5.0	50	1.6330	0.4313
1.5099	6.0	60	1.5820	0.4125
1.4078	7.0	70	1.4982	0.4625
1.3281	8.0	80	1.4624	0.4813
1.253	9.0	90	1.4064	0.4813
1.1858	10.0	100	1.4197	0.4938
1.1196	11.0	110	1.3527	0.55
1.0653	12.0	120	1.3507	0.4688
1.0107	13.0	130	1.3738	0.5125
0.988	14.0	140	1.3758	0.4938
0.9433	15.0	150	1.3541	0.4813
0.9243	16.0	160	1.3265	0.5125
0.8914	17.0	170	1.3634	0.4938
0.8715	18.0	180	1.3683	0.4875
0.8679	19.0	190	1.3197	0.55
0.8479	20.0	200	1.3085	0.5188

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu117
Datasets 2.14.4
Tokenizers 0.13.3