README.md

metadata

license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_1x_deit_tiny_adamax_0001_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: 0.8948247078464107

smids_1x_deit_tiny_adamax_0001_fold1

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: 0.7139
• Accuracy: 0.8948

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
0.5342	1.0	76	0.3575	0.8581
0.3487	2.0	152	0.2939	0.8898
0.1948	3.0	228	0.3052	0.8781
0.1604	4.0	304	0.3458	0.8798
0.0971	5.0	380	0.3617	0.8781
0.0708	6.0	456	0.5383	0.8664
0.0188	7.0	532	0.4843	0.8815
0.0379	8.0	608	0.6406	0.8848
0.0764	9.0	684	0.6359	0.8531
0.0087	10.0	760	0.6100	0.8798
0.0487	11.0	836	0.7711	0.8748
0.0123	12.0	912	0.6958	0.8815
0.011	13.0	988	0.7079	0.8781
0.0004	14.0	1064	0.6722	0.8898
0.0173	15.0	1140	0.7341	0.8698
0.0003	16.0	1216	0.6822	0.8932
0.0001	17.0	1292	0.6501	0.8881
0.0148	18.0	1368	0.7815	0.8631
0.0031	19.0	1444	0.7055	0.8831
0.0045	20.0	1520	0.8049	0.8831
0.0073	21.0	1596	0.7920	0.8715
0.0063	22.0	1672	0.7465	0.8715
0.0001	23.0	1748	0.8004	0.8781
0.0088	24.0	1824	0.7851	0.8748
0.0101	25.0	1900	0.7887	0.8831
0.0047	26.0	1976	0.8827	0.8614
0.0049	27.0	2052	0.7414	0.8881
0.0051	28.0	2128	0.7159	0.8915
0.0063	29.0	2204	0.6956	0.8815
0.0	30.0	2280	0.7029	0.8915
0.0047	31.0	2356	0.7051	0.8932
0.0086	32.0	2432	0.7051	0.8948
0.0	33.0	2508	0.7127	0.8865
0.0	34.0	2584	0.7124	0.8948
0.0109	35.0	2660	0.7099	0.8965
0.0034	36.0	2736	0.7067	0.8965
0.0066	37.0	2812	0.7137	0.8881
0.0	38.0	2888	0.7098	0.8915
0.0038	39.0	2964	0.7130	0.8932
0.0	40.0	3040	0.7175	0.8932
0.0028	41.0	3116	0.7128	0.8898
0.0	42.0	3192	0.7109	0.8915
0.0048	43.0	3268	0.7105	0.8915
0.0	44.0	3344	0.7293	0.8881
0.0	45.0	3420	0.7138	0.8932
0.0	46.0	3496	0.7167	0.8948
0.0	47.0	3572	0.7158	0.8948
0.0024	48.0	3648	0.7140	0.8948
0.0	49.0	3724	0.7139	0.8948
0.0	50.0	3800	0.7139	0.8948

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0