metadata

license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_10x_deit_small_sgd_001_fold1
    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: 0.9015025041736227

smids_10x_deit_small_sgd_001_fold1

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

Loss: 0.2862
Accuracy: 0.9015

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: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.5539	1.0	751	0.5690	0.7763
0.3867	2.0	1502	0.4456	0.8314
0.3236	3.0	2253	0.3927	0.8497
0.259	4.0	3004	0.3726	0.8514
0.3099	5.0	3755	0.3487	0.8598
0.2986	6.0	4506	0.3416	0.8715
0.2728	7.0	5257	0.3260	0.8731
0.2249	8.0	6008	0.3188	0.8781
0.2673	9.0	6759	0.3155	0.8848
0.2491	10.0	7510	0.3089	0.8848
0.2349	11.0	8261	0.3099	0.8881
0.2513	12.0	9012	0.3016	0.8898
0.2098	13.0	9763	0.3061	0.8898
0.1606	14.0	10514	0.3022	0.8881
0.1914	15.0	11265	0.2955	0.8881
0.2039	16.0	12016	0.2953	0.8898
0.2821	17.0	12767	0.2940	0.8965
0.1703	18.0	13518	0.2962	0.8915
0.2178	19.0	14269	0.2905	0.8965
0.1883	20.0	15020	0.2902	0.8998
0.13	21.0	15771	0.2893	0.8948
0.1613	22.0	16522	0.2875	0.8982
0.1627	23.0	17273	0.2879	0.8948
0.2201	24.0	18024	0.2853	0.8998
0.2067	25.0	18775	0.2893	0.8965
0.1982	26.0	19526	0.2860	0.8982
0.1922	27.0	20277	0.2854	0.8998
0.2065	28.0	21028	0.2873	0.8948
0.1663	29.0	21779	0.2836	0.9032
0.1637	30.0	22530	0.2824	0.9032
0.1216	31.0	23281	0.2840	0.8998
0.2073	32.0	24032	0.2863	0.9065
0.1694	33.0	24783	0.2888	0.8965
0.1525	34.0	25534	0.2882	0.8982
0.1562	35.0	26285	0.2864	0.9032
0.1612	36.0	27036	0.2821	0.9032
0.2418	37.0	27787	0.2832	0.9015
0.138	38.0	28538	0.2859	0.9032
0.0832	39.0	29289	0.2853	0.8998
0.1792	40.0	30040	0.2866	0.9015
0.1296	41.0	30791	0.2848	0.9032
0.1436	42.0	31542	0.2863	0.9032
0.1676	43.0	32293	0.2864	0.9015
0.129	44.0	33044	0.2863	0.9015
0.1268	45.0	33795	0.2864	0.9015
0.182	46.0	34546	0.2870	0.8998
0.0802	47.0	35297	0.2872	0.9015
0.1369	48.0	36048	0.2866	0.9015
0.1294	49.0	36799	0.2861	0.9015
0.1488	50.0	37550	0.2862	0.9015

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2