metadata

license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_1x_deit_tiny_adamax_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: 0.8514190317195326

smids_1x_deit_tiny_adamax_00001_fold1

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: 0.7515
Accuracy: 0.8514

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
0.6291	1.0	76	0.6157	0.7212
0.4871	2.0	152	0.4955	0.7663
0.3563	3.0	228	0.4334	0.8147
0.3532	4.0	304	0.4038	0.8264
0.2556	5.0	380	0.3826	0.8364
0.1832	6.0	456	0.3763	0.8314
0.188	7.0	532	0.3632	0.8364
0.176	8.0	608	0.3509	0.8531
0.1753	9.0	684	0.3927	0.8464
0.094	10.0	760	0.3701	0.8614
0.1113	11.0	836	0.3673	0.8598
0.0773	12.0	912	0.3708	0.8531
0.0733	13.0	988	0.3810	0.8464
0.0524	14.0	1064	0.3916	0.8648
0.0392	15.0	1140	0.4052	0.8648
0.0271	16.0	1216	0.4245	0.8614
0.0255	17.0	1292	0.4381	0.8514
0.0233	18.0	1368	0.4614	0.8698
0.0233	19.0	1444	0.4762	0.8614
0.0102	20.0	1520	0.4954	0.8664
0.0235	21.0	1596	0.5367	0.8564
0.0283	22.0	1672	0.5394	0.8681
0.0037	23.0	1748	0.5607	0.8598
0.0016	24.0	1824	0.5901	0.8564
0.0188	25.0	1900	0.5950	0.8564
0.0156	26.0	1976	0.6264	0.8531
0.0197	27.0	2052	0.6288	0.8598
0.009	28.0	2128	0.6474	0.8531
0.025	29.0	2204	0.6597	0.8564
0.0005	30.0	2280	0.6571	0.8548
0.0131	31.0	2356	0.6711	0.8531
0.0183	32.0	2432	0.6793	0.8581
0.0003	33.0	2508	0.6998	0.8514
0.0004	34.0	2584	0.6868	0.8564
0.0226	35.0	2660	0.7047	0.8564
0.0145	36.0	2736	0.7054	0.8548
0.0171	37.0	2812	0.7259	0.8464
0.0011	38.0	2888	0.7392	0.8481
0.0066	39.0	2964	0.7347	0.8481
0.0002	40.0	3040	0.7257	0.8564
0.0087	41.0	3116	0.7270	0.8548
0.0004	42.0	3192	0.7348	0.8631
0.0075	43.0	3268	0.7382	0.8564
0.0002	44.0	3344	0.7585	0.8447
0.0002	45.0	3420	0.7418	0.8531
0.0002	46.0	3496	0.7509	0.8497
0.0002	47.0	3572	0.7508	0.8514
0.0054	48.0	3648	0.7479	0.8514
0.0002	49.0	3724	0.7520	0.8514
0.0002	50.0	3800	0.7515	0.8514

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0