metadata

license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_1x_deit_small_rms_0001_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: 0.6811352253756261

smids_1x_deit_small_rms_0001_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: 0.7301
Accuracy: 0.6811

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
1.1511	1.0	76	1.0039	0.4290
0.9396	2.0	152	0.9980	0.4658
0.9392	3.0	228	1.1592	0.3239
0.9832	4.0	304	1.0157	0.4791
0.9342	5.0	380	0.9184	0.4725
0.951	6.0	456	0.9262	0.4958
1.1061	7.0	532	1.1999	0.3406
0.8983	8.0	608	1.5626	0.4207
0.8399	9.0	684	0.8862	0.5242
0.7906	10.0	760	2.9194	0.3255
0.9054	11.0	836	0.8409	0.5476
0.8842	12.0	912	0.8563	0.5409
0.8173	13.0	988	0.9009	0.4958
0.8653	14.0	1064	0.8617	0.5476
0.7859	15.0	1140	0.8470	0.5109
0.7904	16.0	1216	0.8290	0.6027
0.8076	17.0	1292	1.0668	0.5326
0.7582	18.0	1368	0.8092	0.5776
0.8375	19.0	1444	0.8034	0.5927
0.817	20.0	1520	0.8094	0.5593
0.7636	21.0	1596	0.8786	0.6060
0.7574	22.0	1672	0.7805	0.6093
0.7196	23.0	1748	0.8013	0.6227
0.746	24.0	1824	0.9940	0.5492
0.698	25.0	1900	0.7894	0.6227
0.7416	26.0	1976	0.7704	0.6177
0.7441	27.0	2052	0.7868	0.6110
0.7488	28.0	2128	0.7854	0.6294
0.6844	29.0	2204	0.7483	0.6394
0.7046	30.0	2280	0.7522	0.6144
0.7612	31.0	2356	0.7237	0.6811
0.7095	32.0	2432	0.7781	0.6060
0.7219	33.0	2508	0.7248	0.6477
0.7697	34.0	2584	0.7404	0.6394
0.7924	35.0	2660	0.7779	0.6077
0.6939	36.0	2736	0.7018	0.6628
0.7175	37.0	2812	0.7115	0.6711
0.663	38.0	2888	0.7095	0.6594
0.7209	39.0	2964	0.7131	0.6761
0.6707	40.0	3040	0.7148	0.6745
0.6033	41.0	3116	0.7278	0.6761
0.6657	42.0	3192	0.7175	0.6745
0.5768	43.0	3268	0.7542	0.6611
0.608	44.0	3344	0.7272	0.6811
0.5917	45.0	3420	0.7194	0.6795
0.6179	46.0	3496	0.7229	0.6828
0.5513	47.0	3572	0.7301	0.6861
0.5669	48.0	3648	0.7286	0.6845
0.4852	49.0	3724	0.7286	0.6811
0.6153	50.0	3800	0.7301	0.6811

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0