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_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: 0.8966666666666666

smids_3x_deit_small_rms_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: 0.9862
Accuracy: 0.8967

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
0.2966	1.0	225	0.2690	0.9033
0.1769	2.0	450	0.2748	0.8983
0.056	3.0	675	0.2735	0.9083
0.044	4.0	900	0.3836	0.8983
0.0464	5.0	1125	0.4418	0.9033
0.0264	6.0	1350	0.5404	0.9
0.0095	7.0	1575	0.6147	0.9033
0.0323	8.0	1800	0.7069	0.895
0.0188	9.0	2025	0.6561	0.8917
0.0451	10.0	2250	0.7550	0.8883
0.0417	11.0	2475	0.7782	0.885
0.0052	12.0	2700	0.7305	0.8983
0.0	13.0	2925	0.7512	0.895
0.0288	14.0	3150	0.7604	0.905
0.0005	15.0	3375	0.9139	0.8833
0.0005	16.0	3600	0.8987	0.895
0.0052	17.0	3825	0.8858	0.8867
0.0001	18.0	4050	0.8522	0.9067
0.0	19.0	4275	0.8054	0.8983
0.0188	20.0	4500	0.9106	0.8833
0.0011	21.0	4725	0.9098	0.9
0.0058	22.0	4950	0.8872	0.895
0.0	23.0	5175	0.8360	0.9017
0.0049	24.0	5400	0.8800	0.9017
0.0051	25.0	5625	0.8690	0.8967
0.0025	26.0	5850	0.8437	0.9067
0.0	27.0	6075	0.8956	0.8983
0.0186	28.0	6300	0.8603	0.895
0.0039	29.0	6525	0.8775	0.9
0.0038	30.0	6750	0.8713	0.91
0.0039	31.0	6975	0.8607	0.9033
0.0	32.0	7200	0.9394	0.895
0.0	33.0	7425	0.9694	0.8917
0.0	34.0	7650	0.9863	0.8917
0.0	35.0	7875	0.9386	0.8983
0.0	36.0	8100	0.9806	0.8867
0.0	37.0	8325	0.9851	0.89
0.0	38.0	8550	0.9929	0.89
0.0	39.0	8775	0.9484	0.9067
0.0	40.0	9000	0.9905	0.8933
0.0	41.0	9225	0.9966	0.8917
0.0	42.0	9450	0.9879	0.8933
0.0	43.0	9675	0.9809	0.8967
0.0	44.0	9900	0.9763	0.9017
0.0	45.0	10125	0.9905	0.8967
0.0	46.0	10350	0.9941	0.8967
0.0024	47.0	10575	0.9905	0.8967
0.0	48.0	10800	0.9890	0.8967
0.0	49.0	11025	0.9879	0.8967
0.0	50.0	11250	0.9862	0.8967

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2