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_adamax_00001_fold3
    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: 0.9033333333333333

smids_1x_deit_small_adamax_00001_fold3

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: 0.6007
Accuracy: 0.9033

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
0.5827	1.0	75	0.5406	0.805
0.4124	2.0	150	0.3981	0.855
0.3474	3.0	225	0.3546	0.8683
0.2752	4.0	300	0.3424	0.8733
0.1916	5.0	375	0.3180	0.8767
0.1614	6.0	450	0.3047	0.8933
0.176	7.0	525	0.3087	0.8967
0.0932	8.0	600	0.3077	0.905
0.1095	9.0	675	0.3172	0.8983
0.0598	10.0	750	0.3393	0.8933
0.0561	11.0	825	0.3389	0.8983
0.0304	12.0	900	0.3510	0.9017
0.0312	13.0	975	0.3659	0.8967
0.0138	14.0	1050	0.3876	0.9033
0.0066	15.0	1125	0.4169	0.895
0.0031	16.0	1200	0.4314	0.8933
0.0025	17.0	1275	0.4363	0.9017
0.0143	18.0	1350	0.4488	0.9017
0.0193	19.0	1425	0.4765	0.9017
0.0077	20.0	1500	0.5000	0.9017
0.001	21.0	1575	0.4881	0.8967
0.0006	22.0	1650	0.5102	0.8967
0.0114	23.0	1725	0.5087	0.9017
0.0005	24.0	1800	0.5357	0.9017
0.0004	25.0	1875	0.5221	0.9017
0.0091	26.0	1950	0.5331	0.8983
0.0004	27.0	2025	0.5349	0.8983
0.0004	28.0	2100	0.5415	0.9017
0.0003	29.0	2175	0.5413	0.9017
0.0003	30.0	2250	0.5492	0.9
0.0003	31.0	2325	0.5599	0.9017
0.0003	32.0	2400	0.5614	0.9
0.0002	33.0	2475	0.5598	0.9
0.0063	34.0	2550	0.5669	0.9033
0.0068	35.0	2625	0.5658	0.905
0.0129	36.0	2700	0.5827	0.9017
0.002	37.0	2775	0.5827	0.9017
0.0002	38.0	2850	0.5886	0.905
0.0002	39.0	2925	0.5846	0.8983
0.0002	40.0	3000	0.5897	0.905
0.0002	41.0	3075	0.5926	0.905
0.0007	42.0	3150	0.5977	0.9017
0.0036	43.0	3225	0.5932	0.905
0.0002	44.0	3300	0.5979	0.9017
0.01	45.0	3375	0.6035	0.9033
0.0096	46.0	3450	0.6006	0.9033
0.0033	47.0	3525	0.6008	0.905
0.0001	48.0	3600	0.5996	0.9033
0.0001	49.0	3675	0.6014	0.9033
0.003	50.0	3750	0.6007	0.9033

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0