metadata

license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_10x_deit_small_rms_001_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: 0.8063439065108514

smids_10x_deit_small_rms_001_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: 1.5007
Accuracy: 0.8063

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
0.7661	1.0	751	0.8852	0.6060
0.6485	2.0	1502	0.7308	0.6578
0.696	3.0	2253	0.7036	0.6594
0.6301	4.0	3004	0.7247	0.6761
0.6536	5.0	3755	0.6760	0.6828
0.6653	6.0	4506	0.6159	0.7095
0.5636	7.0	5257	0.5571	0.7579
0.5506	8.0	6008	0.6121	0.7329
0.5582	9.0	6759	0.5862	0.7546
0.5548	10.0	7510	0.5892	0.7329
0.5549	11.0	8261	0.5848	0.7412
0.5362	12.0	9012	0.6200	0.7396
0.4966	13.0	9763	0.5530	0.7713
0.4818	14.0	10514	0.5786	0.7529
0.4746	15.0	11265	0.6115	0.7229
0.4852	16.0	12016	0.6019	0.7362
0.4634	17.0	12767	0.5783	0.7613
0.453	18.0	13518	0.5821	0.7462
0.4908	19.0	14269	0.5445	0.7629
0.4881	20.0	15020	0.5377	0.7763
0.4025	21.0	15771	0.5423	0.7813
0.4591	22.0	16522	0.5168	0.7813
0.3695	23.0	17273	0.5306	0.7730
0.4288	24.0	18024	0.5369	0.7997
0.4022	25.0	18775	0.5176	0.7896
0.3916	26.0	19526	0.5681	0.7830
0.4188	27.0	20277	0.5488	0.7830
0.4088	28.0	21028	0.5430	0.7947
0.3236	29.0	21779	0.5528	0.7947
0.3272	30.0	22530	0.5104	0.8164
0.305	31.0	23281	0.5401	0.8080
0.3925	32.0	24032	0.5133	0.8013
0.3211	33.0	24783	0.5292	0.7980
0.2648	34.0	25534	0.6583	0.7846
0.2286	35.0	26285	0.6241	0.7896
0.2863	36.0	27036	0.6657	0.7947
0.2968	37.0	27787	0.5922	0.8214
0.2233	38.0	28538	0.6706	0.7880
0.1424	39.0	29289	0.6769	0.8097
0.2253	40.0	30040	0.7552	0.7963
0.1253	41.0	30791	0.7804	0.8164
0.16	42.0	31542	0.8311	0.7980
0.1962	43.0	32293	0.8198	0.8047
0.0759	44.0	33044	0.9444	0.7997
0.1175	45.0	33795	0.9448	0.8080
0.1291	46.0	34546	1.0860	0.8080
0.0879	47.0	35297	1.2492	0.7980
0.0404	48.0	36048	1.3416	0.8047
0.0466	49.0	36799	1.4861	0.8030
0.0362	50.0	37550	1.5007	0.8063

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2