metadata

license: apache-2.0
base_model: facebook/deit-base-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_3x_deit_base_sgd_00001_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: 0.39

smids_3x_deit_base_sgd_00001_fold5

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

Loss: 1.0839
Accuracy: 0.39

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: 1e-05
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: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.1036	1.0	225	1.1105	0.345
1.1373	2.0	450	1.1092	0.3483
1.1157	3.0	675	1.1081	0.345
1.0955	4.0	900	1.1069	0.345
1.1099	5.0	1125	1.1058	0.3467
1.1089	6.0	1350	1.1047	0.345
1.1067	7.0	1575	1.1037	0.35
1.0974	8.0	1800	1.1027	0.3483
1.103	9.0	2025	1.1017	0.3483
1.0886	10.0	2250	1.1008	0.35
1.1042	11.0	2475	1.0999	0.3467
1.0817	12.0	2700	1.0990	0.3483
1.0974	13.0	2925	1.0981	0.35
1.0843	14.0	3150	1.0973	0.3533
1.0853	15.0	3375	1.0965	0.3567
1.0875	16.0	3600	1.0957	0.355
1.101	17.0	3825	1.0950	0.3517
1.0772	18.0	4050	1.0943	0.3533
1.0926	19.0	4275	1.0936	0.355
1.1029	20.0	4500	1.0929	0.3567
1.0868	21.0	4725	1.0923	0.3567
1.0978	22.0	4950	1.0917	0.3617
1.0872	23.0	5175	1.0911	0.3633
1.0922	24.0	5400	1.0905	0.3717
1.0864	25.0	5625	1.0900	0.3717
1.0678	26.0	5850	1.0895	0.3733
1.0684	27.0	6075	1.0890	0.3767
1.0793	28.0	6300	1.0885	0.3767
1.0972	29.0	6525	1.0881	0.38
1.0711	30.0	6750	1.0877	0.38
1.0882	31.0	6975	1.0873	0.3783
1.0634	32.0	7200	1.0869	0.38
1.0851	33.0	7425	1.0865	0.3783
1.0775	34.0	7650	1.0862	0.38
1.0604	35.0	7875	1.0859	0.3783
1.0657	36.0	8100	1.0856	0.38
1.0791	37.0	8325	1.0854	0.3817
1.0734	38.0	8550	1.0851	0.3817
1.0719	39.0	8775	1.0849	0.3867
1.0762	40.0	9000	1.0847	0.3883
1.074	41.0	9225	1.0846	0.3883
1.0744	42.0	9450	1.0844	0.3883
1.0769	43.0	9675	1.0843	0.3883
1.079	44.0	9900	1.0842	0.3883
1.0661	45.0	10125	1.0841	0.3883
1.0565	46.0	10350	1.0840	0.3883
1.071	47.0	10575	1.0840	0.3883
1.0641	48.0	10800	1.0839	0.39
1.0708	49.0	11025	1.0839	0.39
1.0689	50.0	11250	1.0839	0.39

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2