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_fold1
    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: 0.8222222222222222

hushem_5x_beit_base_rms_00001_fold1

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: 0.5839
Accuracy: 0.8222

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
0.5474	1.0	27	0.5910	0.8444
0.0818	2.0	54	0.5720	0.7778
0.0238	3.0	81	0.8576	0.7111
0.0074	4.0	108	0.5321	0.8667
0.0032	5.0	135	0.4605	0.8667
0.0017	6.0	162	0.6849	0.7778
0.0024	7.0	189	0.4973	0.8667
0.0008	8.0	216	0.4640	0.8667
0.0044	9.0	243	0.6817	0.8222
0.0005	10.0	270	0.5671	0.8222
0.0004	11.0	297	0.5195	0.8444
0.0002	12.0	324	0.7506	0.8222
0.0007	13.0	351	0.4960	0.8667
0.0004	14.0	378	0.4879	0.8667
0.0002	15.0	405	0.2878	0.8889
0.0004	16.0	432	0.5723	0.7778
0.0038	17.0	459	0.8796	0.8
0.0011	18.0	486	0.4544	0.8444
0.001	19.0	513	0.2346	0.8889
0.0001	20.0	540	0.6421	0.8444
0.0001	21.0	567	0.5172	0.8667
0.0012	22.0	594	0.4729	0.8222
0.0001	23.0	621	0.4318	0.8222
0.0001	24.0	648	0.4087	0.8222
0.0004	25.0	675	0.4267	0.8889
0.0001	26.0	702	0.4250	0.8667
0.0001	27.0	729	0.3081	0.8889
0.0001	28.0	756	0.4008	0.8222
0.0	29.0	783	0.3766	0.8444
0.0001	30.0	810	0.3622	0.9111
0.0	31.0	837	0.4006	0.8222
0.0001	32.0	864	0.4743	0.8444
0.0001	33.0	891	0.3292	0.8889
0.0001	34.0	918	1.1554	0.7556
0.0002	35.0	945	0.6888	0.8
0.0003	36.0	972	0.4504	0.8667
0.0001	37.0	999	0.4287	0.8667
0.0	38.0	1026	0.4528	0.8667
0.0001	39.0	1053	0.4353	0.8667
0.0	40.0	1080	0.4656	0.8444
0.0044	41.0	1107	0.4571	0.8222
0.0	42.0	1134	0.4813	0.8222
0.0004	43.0	1161	0.5618	0.8444
0.0	44.0	1188	0.5635	0.8444
0.0	45.0	1215	0.5635	0.8444
0.0061	46.0	1242	0.5733	0.8444
0.0	47.0	1269	0.5697	0.8444
0.0001	48.0	1296	0.5838	0.8222
0.0001	49.0	1323	0.5839	0.8222
0.0	50.0	1350	0.5839	0.8222

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0