metadata

license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_3x_deit_small_rms_00001_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: 0.9081803005008348

smids_3x_deit_small_rms_00001_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: 0.8163
Accuracy: 0.9082

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
0.3764	1.0	226	0.2918	0.8831
0.2061	2.0	452	0.2699	0.8998
0.0904	3.0	678	0.3139	0.8915
0.1028	4.0	904	0.4241	0.8948
0.0553	5.0	1130	0.4370	0.9032
0.0029	6.0	1356	0.6281	0.8965
0.0117	7.0	1582	0.5524	0.9065
0.0491	8.0	1808	0.6970	0.8915
0.0376	9.0	2034	0.6152	0.9065
0.0001	10.0	2260	0.7198	0.9015
0.003	11.0	2486	0.7173	0.8898
0.0001	12.0	2712	0.6506	0.9048
0.0002	13.0	2938	0.8916	0.8831
0.0132	14.0	3164	0.7369	0.8982
0.0192	15.0	3390	0.7968	0.8982
0.0001	16.0	3616	0.7098	0.9082
0.026	17.0	3842	0.7751	0.8965
0.0001	18.0	4068	0.7904	0.9015
0.0054	19.0	4294	0.6956	0.9032
0.0	20.0	4520	0.7178	0.9032
0.0008	21.0	4746	0.7487	0.9098
0.0089	22.0	4972	0.7031	0.9115
0.0027	23.0	5198	0.7177	0.9032
0.0	24.0	5424	0.7262	0.9082
0.0	25.0	5650	0.7421	0.9082
0.0001	26.0	5876	0.7360	0.9082
0.0	27.0	6102	0.7465	0.9065
0.0	28.0	6328	0.8372	0.9048
0.0	29.0	6554	0.8930	0.8898
0.0	30.0	6780	0.7924	0.9098
0.0339	31.0	7006	0.8291	0.8998
0.0	32.0	7232	0.7573	0.9032
0.0031	33.0	7458	0.7513	0.9082
0.0	34.0	7684	0.8005	0.8998
0.0	35.0	7910	0.7724	0.9065
0.0	36.0	8136	0.7954	0.9065
0.0	37.0	8362	0.7930	0.9082
0.0	38.0	8588	0.8339	0.9048
0.0	39.0	8814	0.7697	0.9115
0.0	40.0	9040	0.7910	0.9082
0.003	41.0	9266	0.7950	0.9048
0.0027	42.0	9492	0.8033	0.9048
0.0	43.0	9718	0.7969	0.9065
0.0	44.0	9944	0.8077	0.9065
0.0	45.0	10170	0.8102	0.9098
0.0	46.0	10396	0.8111	0.9082
0.0	47.0	10622	0.8142	0.9082
0.0	48.0	10848	0.8155	0.9082
0.0	49.0	11074	0.8163	0.9082
0.0	50.0	11300	0.8163	0.9082

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2