README.md

metadata

license: apache-2.0
base_model: microsoft/beit-base-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_1x_beit_base_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: 0.9031719532554258

smids_1x_beit_base_adamax_0001_fold1

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

• Loss: 0.8043
• Accuracy: 0.9032

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
0.3546	1.0	76	0.4865	0.7930
0.2399	2.0	152	0.3349	0.8731
0.136	3.0	228	0.2999	0.8831
0.1619	4.0	304	0.4346	0.8698
0.1213	5.0	380	0.4295	0.8748
0.0741	6.0	456	0.4439	0.8881
0.0995	7.0	532	0.5033	0.8815
0.0126	8.0	608	0.4887	0.8982
0.0174	9.0	684	0.6241	0.8848
0.0036	10.0	760	0.5630	0.8898
0.0047	11.0	836	0.6256	0.8898
0.025	12.0	912	0.5949	0.8982
0.0037	13.0	988	0.6192	0.8898
0.0095	14.0	1064	0.6191	0.8982
0.0074	15.0	1140	0.6693	0.8948
0.0061	16.0	1216	0.6785	0.8915
0.0003	17.0	1292	0.6825	0.8898
0.0001	18.0	1368	0.7695	0.8865
0.0107	19.0	1444	0.6909	0.8965
0.0125	20.0	1520	0.7272	0.8915
0.0016	21.0	1596	0.7585	0.8848
0.0028	22.0	1672	0.7524	0.8898
0.0017	23.0	1748	0.8165	0.8865
0.0046	24.0	1824	0.7698	0.8848
0.004	25.0	1900	0.8060	0.8915
0.003	26.0	1976	0.7525	0.8998
0.0039	27.0	2052	0.8271	0.8848
0.0001	28.0	2128	0.7809	0.8965
0.0001	29.0	2204	0.8142	0.8948
0.0	30.0	2280	0.7973	0.8881
0.0023	31.0	2356	0.7501	0.8998
0.0061	32.0	2432	0.7903	0.8932
0.0085	33.0	2508	0.7939	0.8932
0.0036	34.0	2584	0.7959	0.8982
0.0089	35.0	2660	0.7729	0.8982
0.0	36.0	2736	0.8000	0.8948
0.0038	37.0	2812	0.7757	0.8998
0.0028	38.0	2888	0.7902	0.8898
0.0024	39.0	2964	0.7785	0.9048
0.0001	40.0	3040	0.7668	0.9082
0.0052	41.0	3116	0.7725	0.9048
0.0	42.0	3192	0.7888	0.9032
0.0	43.0	3268	0.7934	0.9032
0.0	44.0	3344	0.7962	0.9032
0.0053	45.0	3420	0.8046	0.9032
0.0	46.0	3496	0.7994	0.9032
0.003	47.0	3572	0.8008	0.9032
0.0032	48.0	3648	0.8023	0.9032
0.0018	49.0	3724	0.8041	0.9032
0.0052	50.0	3800	0.8043	0.9032

Framework versions

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