metadata

license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_5x_deit_tiny_adamax_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: 0.9016666666666666

smids_5x_deit_tiny_adamax_00001_fold3

This model is a fine-tuned version of facebook/deit-tiny-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.8603
Accuracy: 0.9017

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
0.3577	1.0	375	0.3812	0.845
0.2949	2.0	750	0.2946	0.89
0.1716	3.0	1125	0.2716	0.8933
0.1812	4.0	1500	0.2588	0.9117
0.1483	5.0	1875	0.2753	0.8983
0.1406	6.0	2250	0.2966	0.9017
0.1265	7.0	2625	0.3030	0.9
0.1011	8.0	3000	0.3279	0.9017
0.0557	9.0	3375	0.3594	0.9017
0.0231	10.0	3750	0.3998	0.91
0.0281	11.0	4125	0.4583	0.89
0.0358	12.0	4500	0.4967	0.8967
0.0189	13.0	4875	0.5490	0.9017
0.0022	14.0	5250	0.5821	0.8967
0.0008	15.0	5625	0.6304	0.9017
0.0004	16.0	6000	0.6440	0.9017
0.0002	17.0	6375	0.6611	0.9017
0.0001	18.0	6750	0.6624	0.905
0.0008	19.0	7125	0.7059	0.9067
0.0001	20.0	7500	0.6928	0.9067
0.0001	21.0	7875	0.7172	0.905
0.0	22.0	8250	0.7360	0.905
0.0192	23.0	8625	0.7528	0.905
0.0	24.0	9000	0.7580	0.9
0.0	25.0	9375	0.7737	0.9017
0.0	26.0	9750	0.7755	0.9017
0.0	27.0	10125	0.7892	0.9
0.0	28.0	10500	0.7918	0.905
0.0	29.0	10875	0.8126	0.9017
0.0178	30.0	11250	0.8092	0.8967
0.0	31.0	11625	0.8243	0.9033
0.0	32.0	12000	0.8257	0.9017
0.0	33.0	12375	0.8314	0.9017
0.0	34.0	12750	0.8261	0.9033
0.0	35.0	13125	0.8406	0.9033
0.0	36.0	13500	0.8423	0.9033
0.0	37.0	13875	0.8427	0.905
0.0	38.0	14250	0.8439	0.9017
0.0	39.0	14625	0.8460	0.9033
0.0006	40.0	15000	0.8531	0.905
0.0	41.0	15375	0.8498	0.9033
0.0	42.0	15750	0.8562	0.9017
0.0	43.0	16125	0.8549	0.9033
0.0	44.0	16500	0.8565	0.905
0.0	45.0	16875	0.8586	0.905
0.0	46.0	17250	0.8582	0.9017
0.0	47.0	17625	0.8601	0.9017
0.0	48.0	18000	0.8602	0.9017
0.0	49.0	18375	0.8603	0.9017
0.0	50.0	18750	0.8603	0.9017

Framework versions

Transformers 4.32.1
Pytorch 2.1.1+cu121
Datasets 2.12.0
Tokenizers 0.13.2