metadata

license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_5x_deit_tiny_adamax_00001_fold5
    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: 0.8883333333333333

smids_5x_deit_tiny_adamax_00001_fold5

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: 0.8310
Accuracy: 0.8883

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
0.3076	1.0	375	0.3691	0.8367
0.2287	2.0	750	0.2879	0.8783
0.189	3.0	1125	0.2852	0.885
0.1751	4.0	1500	0.2883	0.8867
0.0982	5.0	1875	0.3260	0.8833
0.0575	6.0	2250	0.3348	0.875
0.0552	7.0	2625	0.3820	0.8883
0.0223	8.0	3000	0.4434	0.89
0.0296	9.0	3375	0.4885	0.8883
0.005	10.0	3750	0.5225	0.8917
0.0192	11.0	4125	0.5900	0.8883
0.006	12.0	4500	0.6146	0.885
0.0003	13.0	4875	0.6354	0.8867
0.0012	14.0	5250	0.6738	0.8867
0.0003	15.0	5625	0.7057	0.8767
0.0001	16.0	6000	0.6776	0.8967
0.0001	17.0	6375	0.7281	0.885
0.0151	18.0	6750	0.7671	0.88
0.0	19.0	7125	0.7446	0.885
0.0	20.0	7500	0.7595	0.885
0.0	21.0	7875	0.7847	0.8833
0.0104	22.0	8250	0.8045	0.8867
0.0001	23.0	8625	0.8013	0.885
0.0	24.0	9000	0.8150	0.8833
0.0	25.0	9375	0.8170	0.885
0.0	26.0	9750	0.8095	0.8883
0.0	27.0	10125	0.8047	0.8867
0.0	28.0	10500	0.8115	0.8867
0.0	29.0	10875	0.8193	0.8867
0.0071	30.0	11250	0.8281	0.8883
0.0	31.0	11625	0.8141	0.89
0.0	32.0	12000	0.8187	0.89
0.0	33.0	12375	0.8183	0.8883
0.0	34.0	12750	0.8223	0.885
0.0	35.0	13125	0.8200	0.8867
0.0	36.0	13500	0.8256	0.8883
0.0	37.0	13875	0.8249	0.8883
0.0017	38.0	14250	0.8193	0.8883
0.0	39.0	14625	0.8227	0.885
0.0	40.0	15000	0.8247	0.89
0.0	41.0	15375	0.8288	0.885
0.0	42.0	15750	0.8238	0.8917
0.0	43.0	16125	0.8250	0.8883
0.0	44.0	16500	0.8262	0.8917
0.0	45.0	16875	0.8283	0.8917
0.0	46.0	17250	0.8299	0.8867
0.0027	47.0	17625	0.8304	0.8867
0.0	48.0	18000	0.8306	0.8867
0.0	49.0	18375	0.8310	0.8867
0.004	50.0	18750	0.8310	0.8883

Framework versions

Transformers 4.32.1
Pytorch 2.1.1+cu121
Datasets 2.12.0
Tokenizers 0.13.2