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_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: 0.7716666666666666

smids_3x_deit_small_sgd_0001_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: 0.6009
Accuracy: 0.7717

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
1.0412	1.0	225	1.0610	0.4117
1.0073	2.0	450	1.0359	0.4517
0.9921	3.0	675	1.0120	0.4917
0.9585	4.0	900	0.9890	0.515
0.951	5.0	1125	0.9674	0.5517
0.9167	6.0	1350	0.9465	0.5667
0.9008	7.0	1575	0.9258	0.58
0.9034	8.0	1800	0.9058	0.605
0.8748	9.0	2025	0.8869	0.6283
0.8544	10.0	2250	0.8687	0.64
0.8432	11.0	2475	0.8520	0.65
0.8244	12.0	2700	0.8358	0.66
0.8203	13.0	2925	0.8201	0.665
0.7835	14.0	3150	0.8053	0.6733
0.7537	15.0	3375	0.7910	0.68
0.7828	16.0	3600	0.7779	0.6983
0.7529	17.0	3825	0.7656	0.7067
0.7496	18.0	4050	0.7534	0.7167
0.6935	19.0	4275	0.7418	0.7283
0.7161	20.0	4500	0.7310	0.7283
0.6651	21.0	4725	0.7207	0.7283
0.7137	22.0	4950	0.7112	0.7333
0.6691	23.0	5175	0.7018	0.7367
0.6667	24.0	5400	0.6932	0.7383
0.6381	25.0	5625	0.6850	0.735
0.636	26.0	5850	0.6772	0.74
0.6231	27.0	6075	0.6700	0.7467
0.6306	28.0	6300	0.6632	0.7517
0.6547	29.0	6525	0.6569	0.7583
0.5884	30.0	6750	0.6510	0.7583
0.5952	31.0	6975	0.6455	0.7583
0.6201	32.0	7200	0.6404	0.7633
0.6515	33.0	7425	0.6357	0.765
0.6177	34.0	7650	0.6313	0.765
0.5987	35.0	7875	0.6273	0.765
0.6037	36.0	8100	0.6236	0.7633
0.571	37.0	8325	0.6202	0.765
0.5948	38.0	8550	0.6172	0.7667
0.6088	39.0	8775	0.6144	0.765
0.5862	40.0	9000	0.6119	0.77
0.5659	41.0	9225	0.6097	0.7733
0.6112	42.0	9450	0.6077	0.7733
0.5562	43.0	9675	0.6060	0.775
0.6002	44.0	9900	0.6046	0.7733
0.6408	45.0	10125	0.6034	0.7717
0.6068	46.0	10350	0.6024	0.7717
0.5514	47.0	10575	0.6017	0.7717
0.6016	48.0	10800	0.6013	0.7717
0.6117	49.0	11025	0.6010	0.7717
0.5649	50.0	11250	0.6009	0.7717

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2