metadata

license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: hushem_conflu_deneme_fold5
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: test
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.6341463414634146

hushem_conflu_deneme_fold5

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

Loss: 1.9630
Accuracy: 0.6341

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: 0.001
train_batch_size: 32
eval_batch_size: 32
seed: 42
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
No log	1.0	6	1.4708	0.2439
1.7951	2.0	12	1.3099	0.2439
1.7951	3.0	18	1.1130	0.4146
1.2772	4.0	24	1.0471	0.7073
1.1124	5.0	30	1.2680	0.5366
1.1124	6.0	36	1.0908	0.5122
0.9481	7.0	42	1.5674	0.3902
0.9481	8.0	48	0.8947	0.6098
0.9653	9.0	54	1.1885	0.6098
0.639	10.0	60	0.9898	0.6585
0.639	11.0	66	1.7943	0.4634
0.5108	12.0	72	1.7088	0.5366
0.5108	13.0	78	1.6432	0.5610
0.1679	14.0	84	1.5598	0.5854
0.1286	15.0	90	2.1600	0.5854
0.1286	16.0	96	1.9849	0.5854
0.0501	17.0	102	1.9630	0.6341
0.0501	18.0	108	1.9630	0.6341
0.0271	19.0	114	1.9630	0.6341
0.0437	20.0	120	1.9630	0.6341

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1