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_sgd_001_fold5
    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: 0.7073170731707317

hushem_5x_beit_base_sgd_001_fold5

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: 0.8979
• Accuracy: 0.7073

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
1.5363	1.0	28	1.5515	0.2439
1.4164	2.0	56	1.4971	0.3171
1.362	3.0	84	1.4523	0.3659
1.3381	4.0	112	1.3987	0.3902
1.2805	5.0	140	1.3538	0.4390
1.286	6.0	168	1.3184	0.4634
1.2664	7.0	196	1.2890	0.4634
1.1752	8.0	224	1.2605	0.4878
1.1615	9.0	252	1.2357	0.5366
1.1583	10.0	280	1.2200	0.5366
1.0622	11.0	308	1.1865	0.5854
1.0888	12.0	336	1.1579	0.5854
1.0774	13.0	364	1.1376	0.6098
1.0639	14.0	392	1.1207	0.6098
1.0329	15.0	420	1.1063	0.6098
1.0224	16.0	448	1.0819	0.6098
0.9888	17.0	476	1.0775	0.6098
0.9619	18.0	504	1.0585	0.6098
0.9636	19.0	532	1.0418	0.6098
0.932	20.0	560	1.0228	0.6098
0.9605	21.0	588	1.0275	0.6341
0.9245	22.0	616	1.0007	0.6829
0.9128	23.0	644	0.9952	0.6829
0.8833	24.0	672	0.9964	0.6585
0.8669	25.0	700	0.9755	0.6829
0.8822	26.0	728	0.9683	0.6829
0.8736	27.0	756	0.9644	0.6829
0.8195	28.0	784	0.9503	0.6829
0.815	29.0	812	0.9479	0.6829
0.8347	30.0	840	0.9483	0.6829
0.8334	31.0	868	0.9382	0.6829
0.7989	32.0	896	0.9378	0.6829
0.7878	33.0	924	0.9468	0.6829
0.8479	34.0	952	0.9186	0.7073
0.7868	35.0	980	0.9253	0.6829
0.7921	36.0	1008	0.9134	0.7073
0.7563	37.0	1036	0.9054	0.7073
0.7507	38.0	1064	0.9071	0.7073
0.8331	39.0	1092	0.8998	0.7073
0.7104	40.0	1120	0.9052	0.7073
0.773	41.0	1148	0.9044	0.7073
0.719	42.0	1176	0.9021	0.7073
0.7745	43.0	1204	0.8997	0.7073
0.781	44.0	1232	0.9016	0.7073
0.755	45.0	1260	0.9002	0.7073
0.7437	46.0	1288	0.9000	0.7073
0.7695	47.0	1316	0.8981	0.7073
0.7339	48.0	1344	0.8980	0.7073
0.7563	49.0	1372	0.8979	0.7073
0.755	50.0	1400	0.8979	0.7073

Framework versions

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