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_001_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: 0.8066666666666666

smids_1x_beit_base_adamax_001_fold3

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: 1.6207
• Accuracy: 0.8067

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
0.961	1.0	75	0.9579	0.5083
0.8519	2.0	150	0.8223	0.555
0.8429	3.0	225	0.8258	0.5417
0.8689	4.0	300	1.1933	0.5183
0.7212	5.0	375	0.6887	0.7133
0.649	6.0	450	0.7128	0.6567
0.6409	7.0	525	0.6763	0.71
0.5869	8.0	600	0.5948	0.7383
0.5565	9.0	675	0.6418	0.695
0.5839	10.0	750	0.6087	0.7267
0.5293	11.0	825	0.5977	0.7267
0.4762	12.0	900	0.5491	0.7783
0.4499	13.0	975	0.5838	0.7517
0.4302	14.0	1050	0.5473	0.77
0.4099	15.0	1125	0.5508	0.755
0.3178	16.0	1200	0.5699	0.78
0.341	17.0	1275	0.6033	0.7933
0.2555	18.0	1350	0.6573	0.7767
0.3366	19.0	1425	0.5611	0.7933
0.1724	20.0	1500	0.7339	0.7933
0.2297	21.0	1575	0.8132	0.78
0.2293	22.0	1650	0.7112	0.7833
0.1656	23.0	1725	0.8681	0.7767
0.1488	24.0	1800	0.9454	0.79
0.1667	25.0	1875	0.9934	0.7767
0.0534	26.0	1950	0.9484	0.7767
0.1635	27.0	2025	1.0833	0.77
0.0554	28.0	2100	1.1552	0.8017
0.0938	29.0	2175	1.0865	0.7917
0.1141	30.0	2250	1.3605	0.7883
0.0561	31.0	2325	1.2003	0.8033
0.064	32.0	2400	1.3257	0.7933
0.0695	33.0	2475	1.6036	0.7883
0.0143	34.0	2550	1.5166	0.7717
0.0099	35.0	2625	1.5177	0.7833
0.046	36.0	2700	1.6809	0.7983
0.0535	37.0	2775	1.6548	0.7783
0.0142	38.0	2850	1.9052	0.7867
0.0043	39.0	2925	1.8855	0.785
0.0169	40.0	3000	1.8422	0.7983
0.0085	41.0	3075	1.6803	0.8033
0.0125	42.0	3150	1.4852	0.8033
0.0037	43.0	3225	1.5490	0.7883
0.0153	44.0	3300	1.3985	0.81
0.0066	45.0	3375	1.5369	0.8083
0.0076	46.0	3450	1.5177	0.7983
0.0089	47.0	3525	1.6039	0.7883
0.0027	48.0	3600	1.6013	0.8067
0.0003	49.0	3675	1.6182	0.8067
0.0026	50.0	3750	1.6207	0.8067

Framework versions

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