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_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: 0.7166666666666667

smids_10x_deit_small_rms_001_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: 0.6302
Accuracy: 0.7167

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
1.1023	1.0	750	1.0958	0.34
0.9402	2.0	1500	0.9088	0.5033
0.9044	3.0	2250	0.8761	0.5383
0.8247	4.0	3000	0.8349	0.5233
0.7854	5.0	3750	0.8127	0.5633
0.7771	6.0	4500	0.8860	0.5383
0.773	7.0	5250	0.8230	0.575
0.8024	8.0	6000	0.7956	0.5883
0.8797	9.0	6750	0.8015	0.6183
0.7815	10.0	7500	0.7866	0.6083
0.7914	11.0	8250	0.7547	0.6267
0.7411	12.0	9000	0.7615	0.59
0.7343	13.0	9750	0.7214	0.6617
0.7764	14.0	10500	0.7295	0.6717
0.7555	15.0	11250	0.7012	0.6617
0.7373	16.0	12000	0.7948	0.6217
0.6985	17.0	12750	0.7396	0.6267
0.7821	18.0	13500	0.7384	0.66
0.7914	19.0	14250	0.7821	0.635
0.7863	20.0	15000	0.7254	0.655
0.6932	21.0	15750	0.7242	0.6633
0.6744	22.0	16500	0.7009	0.6817
0.6983	23.0	17250	0.6866	0.7133
0.6779	24.0	18000	0.6963	0.6983
0.6937	25.0	18750	0.6942	0.6817
0.6943	26.0	19500	0.6864	0.695
0.6231	27.0	20250	0.7126	0.665
0.6418	28.0	21000	0.6620	0.6983
0.72	29.0	21750	0.6656	0.7017
0.7042	30.0	22500	0.6697	0.6867
0.754	31.0	23250	0.6511	0.7033
0.6987	32.0	24000	0.6765	0.69
0.7166	33.0	24750	0.6802	0.7083
0.6725	34.0	25500	0.6763	0.7033
0.6612	35.0	26250	0.6382	0.7083
0.6967	36.0	27000	0.6445	0.705
0.6491	37.0	27750	0.6443	0.7133
0.7274	38.0	28500	0.6314	0.7333
0.6904	39.0	29250	0.6429	0.7267
0.6516	40.0	30000	0.6385	0.7167
0.6647	41.0	30750	0.6386	0.7
0.666	42.0	31500	0.6656	0.695
0.6901	43.0	32250	0.6568	0.715
0.6021	44.0	33000	0.6375	0.7117
0.6467	45.0	33750	0.6267	0.7117
0.6249	46.0	34500	0.6374	0.71
0.6161	47.0	35250	0.6354	0.71
0.6534	48.0	36000	0.6396	0.715
0.6031	49.0	36750	0.6326	0.7117
0.6145	50.0	37500	0.6302	0.7167

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2