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: hushem_5x_beit_base_adamax_0001_fold4
    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: 0.9523809523809523

hushem_5x_beit_base_adamax_0001_fold4

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: 0.2108
• Accuracy: 0.9524

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
0.5267	1.0	28	0.2719	0.9524
0.1179	2.0	56	0.1300	0.9762
0.0416	3.0	84	0.1526	0.9524
0.0289	4.0	112	0.2224	0.9762
0.0045	5.0	140	0.2573	0.9286
0.0019	6.0	168	0.1214	0.9524
0.0019	7.0	196	0.0241	0.9762
0.005	8.0	224	0.0079	1.0
0.0006	9.0	252	0.1770	0.9762
0.0008	10.0	280	0.0288	0.9762
0.0001	11.0	308	0.1121	0.9762
0.0003	12.0	336	0.0948	0.9762
0.0002	13.0	364	0.1371	0.9762
0.0014	14.0	392	0.0039	1.0
0.0003	15.0	420	0.0665	0.9762
0.0002	16.0	448	0.1660	0.9762
0.003	17.0	476	0.0467	0.9762
0.005	18.0	504	0.2825	0.9286
0.0001	19.0	532	0.1710	0.9286
0.0001	20.0	560	0.1283	0.9524
0.0001	21.0	588	0.1190	0.9524
0.0003	22.0	616	0.0164	1.0
0.0002	23.0	644	0.1235	0.9762
0.0001	24.0	672	0.1896	0.9762
0.0001	25.0	700	0.2082	0.9762
0.0001	26.0	728	0.0141	1.0
0.0	27.0	756	0.0694	0.9762
0.0001	28.0	784	0.1668	0.9762
0.0	29.0	812	0.1843	0.9762
0.0001	30.0	840	0.1640	0.9762
0.0	31.0	868	0.1522	0.9762
0.0001	32.0	896	0.1655	0.9762
0.0	33.0	924	0.1990	0.9762
0.0001	34.0	952	0.2441	0.9524
0.0002	35.0	980	0.1896	0.9762
0.0001	36.0	1008	0.1613	0.9762
0.0	37.0	1036	0.1651	0.9762
0.0	38.0	1064	0.1775	0.9762
0.0002	39.0	1092	0.2044	0.9762
0.0006	40.0	1120	0.1473	0.9762
0.0	41.0	1148	0.1688	0.9524
0.0	42.0	1176	0.2053	0.9524
0.0	43.0	1204	0.2132	0.9524
0.0002	44.0	1232	0.2078	0.9524
0.0002	45.0	1260	0.1978	0.9524
0.0006	46.0	1288	0.2109	0.9524
0.0001	47.0	1316	0.2092	0.9524
0.0001	48.0	1344	0.2108	0.9524
0.0	49.0	1372	0.2108	0.9524
0.0	50.0	1400	0.2108	0.9524

Framework versions

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