metadata

license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_1x_deit_small_rms_00001_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: 0.8848080133555927

smids_1x_deit_small_rms_00001_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: 0.7203
Accuracy: 0.8848

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
0.4024	1.0	76	0.3457	0.8598
0.2939	2.0	152	0.3056	0.8765
0.1494	3.0	228	0.3010	0.8815
0.1219	4.0	304	0.3026	0.8848
0.0709	5.0	380	0.3230	0.8881
0.0265	6.0	456	0.3473	0.8915
0.0053	7.0	532	0.4250	0.8815
0.0086	8.0	608	0.4355	0.8848
0.0119	9.0	684	0.4635	0.8865
0.0011	10.0	760	0.4824	0.8932
0.0255	11.0	836	0.5139	0.8831
0.0006	12.0	912	0.5793	0.8815
0.0183	13.0	988	0.5403	0.8848
0.0037	14.0	1064	0.5951	0.8848
0.024	15.0	1140	0.5951	0.8815
0.0002	16.0	1216	0.6061	0.8798
0.0001	17.0	1292	0.5992	0.8948
0.0157	18.0	1368	0.6206	0.8848
0.0002	19.0	1444	0.6514	0.8881
0.0058	20.0	1520	0.6656	0.8798
0.0096	21.0	1596	0.6589	0.8915
0.0045	22.0	1672	0.6509	0.8848
0.0001	23.0	1748	0.6180	0.8881
0.0001	24.0	1824	0.6676	0.8765
0.0077	25.0	1900	0.6271	0.8831
0.0032	26.0	1976	0.7135	0.8848
0.0043	27.0	2052	0.7062	0.8765
0.0034	28.0	2128	0.7064	0.8781
0.0062	29.0	2204	0.6764	0.8781
0.0001	30.0	2280	0.6847	0.8831
0.006	31.0	2356	0.6868	0.8865
0.009	32.0	2432	0.7122	0.8881
0.0	33.0	2508	0.7011	0.8865
0.0	34.0	2584	0.7102	0.8881
0.0121	35.0	2660	0.7023	0.8881
0.0034	36.0	2736	0.7188	0.8765
0.0064	37.0	2812	0.7029	0.8848
0.0001	38.0	2888	0.7098	0.8798
0.0031	39.0	2964	0.7171	0.8815
0.0	40.0	3040	0.7137	0.8815
0.0029	41.0	3116	0.7143	0.8815
0.0	42.0	3192	0.7224	0.8815
0.0048	43.0	3268	0.7157	0.8831
0.0	44.0	3344	0.7190	0.8848
0.0	45.0	3420	0.7200	0.8848
0.0	46.0	3496	0.7204	0.8848
0.0	47.0	3572	0.7209	0.8848
0.0024	48.0	3648	0.7205	0.8848
0.0	49.0	3724	0.7204	0.8848
0.0	50.0	3800	0.7203	0.8848

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0