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_rms_0001_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: 0.6744186046511628

hushem_5x_beit_base_rms_0001_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: 2.0271
• Accuracy: 0.6744

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
1.4187	1.0	28	1.4291	0.2558
1.401	2.0	56	1.4569	0.2558
1.367	3.0	84	1.2989	0.2791
1.3068	4.0	112	1.1706	0.5116
1.282	5.0	140	1.1869	0.5581
1.1177	6.0	168	0.8916	0.7442
0.8904	7.0	196	0.7798	0.7209
0.9449	8.0	224	0.6587	0.7674
0.8708	9.0	252	1.0524	0.5814
0.9352	10.0	280	0.7664	0.6744
0.8718	11.0	308	0.6191	0.7907
0.7977	12.0	336	1.1991	0.6512
0.8081	13.0	364	0.7062	0.7674
0.7399	14.0	392	0.7130	0.6744
0.8202	15.0	420	0.7484	0.6977
0.7069	16.0	448	0.6665	0.6977
0.6169	17.0	476	0.7828	0.6279
0.6766	18.0	504	0.9849	0.5814
0.6876	19.0	532	0.7015	0.7442
0.5123	20.0	560	0.9230	0.7442
0.4885	21.0	588	0.9671	0.6279
0.5212	22.0	616	1.2712	0.6744
0.5047	23.0	644	0.7902	0.6512
0.4047	24.0	672	1.3996	0.7209
0.361	25.0	700	1.1508	0.6279
0.362	26.0	728	1.0709	0.6279
0.3752	27.0	756	0.9894	0.6512
0.2958	28.0	784	1.2219	0.6279
0.3016	29.0	812	0.8154	0.6977
0.2083	30.0	840	1.2432	0.6047
0.2249	31.0	868	1.5401	0.6047
0.1443	32.0	896	1.3193	0.6279
0.1501	33.0	924	1.1707	0.6977
0.1715	34.0	952	1.1677	0.7442
0.2795	35.0	980	1.2992	0.6744
0.1174	36.0	1008	1.6643	0.6744
0.1132	37.0	1036	1.7522	0.6279
0.0738	38.0	1064	1.6182	0.6744
0.0433	39.0	1092	2.1223	0.6512
0.0483	40.0	1120	2.5522	0.5814
0.0333	41.0	1148	1.8374	0.6977
0.0107	42.0	1176	1.9629	0.6744
0.013	43.0	1204	1.6900	0.7209
0.0316	44.0	1232	2.1881	0.6512
0.0272	45.0	1260	1.8428	0.6744
0.0298	46.0	1288	1.7049	0.7674
0.0196	47.0	1316	1.9117	0.6744
0.0084	48.0	1344	2.0336	0.6744
0.0059	49.0	1372	2.0271	0.6744
0.0065	50.0	1400	2.0271	0.6744

Framework versions

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