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_00001_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: 0.9047619047619048

hushem_5x_beit_base_rms_00001_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: 0.4242
• Accuracy: 0.9048

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: 1e-05
• 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
0.7963	1.0	28	0.5873	0.8095
0.1378	2.0	56	0.2600	0.9048
0.0372	3.0	84	0.1249	0.9286
0.0142	4.0	112	0.1881	0.9048
0.0031	5.0	140	0.2720	0.9524
0.0011	6.0	168	0.2309	0.9286
0.0018	7.0	196	0.3809	0.9048
0.0008	8.0	224	0.3332	0.9048
0.0014	9.0	252	0.3365	0.8810
0.0123	10.0	280	0.2089	0.9286
0.0005	11.0	308	0.1962	0.9286
0.0038	12.0	336	0.2845	0.9048
0.0078	13.0	364	0.2498	0.9048
0.001	14.0	392	0.0353	1.0
0.0002	15.0	420	0.1604	0.9286
0.0003	16.0	448	0.6770	0.8810
0.0002	17.0	476	0.3566	0.9048
0.0001	18.0	504	0.1974	0.8810
0.0004	19.0	532	0.0247	1.0
0.0001	20.0	560	0.0905	0.9286
0.0001	21.0	588	0.1806	0.9286
0.0011	22.0	616	0.2156	0.9524
0.0007	23.0	644	0.4203	0.9286
0.0002	24.0	672	0.2731	0.9286
0.0054	25.0	700	0.2589	0.8810
0.0001	26.0	728	0.2893	0.9048
0.0	27.0	756	0.3737	0.8810
0.0002	28.0	784	0.3310	0.9048
0.0001	29.0	812	0.2394	0.9048
0.0	30.0	840	0.2320	0.9048
0.0001	31.0	868	0.2751	0.9048
0.0012	32.0	896	0.2756	0.9048
0.0	33.0	924	0.1983	0.9048
0.0001	34.0	952	0.1565	0.9048
0.0	35.0	980	0.1912	0.9048
0.0001	36.0	1008	0.2103	0.9048
0.0	37.0	1036	0.1693	0.9048
0.0	38.0	1064	0.1895	0.9048
0.0	39.0	1092	0.2300	0.9048
0.0018	40.0	1120	0.7391	0.9048
0.0	41.0	1148	0.6660	0.9048
0.0	42.0	1176	0.5981	0.9048
0.0001	43.0	1204	0.6379	0.9048
0.0001	44.0	1232	0.5736	0.9048
0.0002	45.0	1260	0.4940	0.9048
0.0001	46.0	1288	0.4348	0.9048
0.0001	47.0	1316	0.4551	0.9048
0.0	48.0	1344	0.4241	0.9048
0.0026	49.0	1372	0.4242	0.9048
0.0	50.0	1400	0.4242	0.9048

Framework versions

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