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_sgd_0001_fold4
    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: 0.7783333333333333

smids_3x_deit_small_sgd_0001_fold4

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: 0.5687
Accuracy: 0.7783

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: 0.0001
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
1.0247	1.0	225	1.0422	0.45
1.0237	2.0	450	1.0174	0.4883
0.9838	3.0	675	0.9928	0.52
0.9769	4.0	900	0.9683	0.555
0.9529	5.0	1125	0.9446	0.5867
0.9169	6.0	1350	0.9209	0.6017
0.9264	7.0	1575	0.8980	0.6083
0.9011	8.0	1800	0.8753	0.6267
0.8821	9.0	2025	0.8542	0.63
0.8381	10.0	2250	0.8337	0.66
0.8339	11.0	2475	0.8147	0.6683
0.8391	12.0	2700	0.7963	0.6833
0.8165	13.0	2925	0.7789	0.6933
0.736	14.0	3150	0.7623	0.7083
0.7819	15.0	3375	0.7468	0.725
0.7441	16.0	3600	0.7323	0.72
0.7169	17.0	3825	0.7189	0.7333
0.7451	18.0	4050	0.7062	0.7383
0.7048	19.0	4275	0.6943	0.74
0.6589	20.0	4500	0.6832	0.745
0.6884	21.0	4725	0.6730	0.7433
0.7041	22.0	4950	0.6635	0.745
0.6833	23.0	5175	0.6547	0.75
0.6669	24.0	5400	0.6465	0.7533
0.6608	25.0	5625	0.6391	0.7517
0.6311	26.0	5850	0.6322	0.7567
0.6676	27.0	6075	0.6258	0.7583
0.6172	28.0	6300	0.6199	0.7617
0.6339	29.0	6525	0.6146	0.765
0.6134	30.0	6750	0.6096	0.7717
0.6169	31.0	6975	0.6051	0.775
0.5976	32.0	7200	0.6008	0.7767
0.601	33.0	7425	0.5969	0.7767
0.6016	34.0	7650	0.5933	0.78
0.5916	35.0	7875	0.5900	0.78
0.6147	36.0	8100	0.5870	0.78
0.5896	37.0	8325	0.5843	0.78
0.5987	38.0	8550	0.5818	0.78
0.5562	39.0	8775	0.5795	0.78
0.6128	40.0	9000	0.5775	0.7817
0.5635	41.0	9225	0.5757	0.78
0.6047	42.0	9450	0.5742	0.78
0.5584	43.0	9675	0.5728	0.78
0.628	44.0	9900	0.5716	0.78
0.5798	45.0	10125	0.5707	0.7783
0.583	46.0	10350	0.5699	0.7783
0.5729	47.0	10575	0.5694	0.7783
0.5825	48.0	10800	0.5690	0.7783
0.6044	49.0	11025	0.5688	0.7783
0.5946	50.0	11250	0.5687	0.7783

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2