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_00001_fold2
    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: 0.7777777777777778

hushem_5x_beit_base_adamax_00001_fold2

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: 1.0731
• Accuracy: 0.7778

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
1.133	1.0	27	1.1782	0.4444
0.7374	2.0	54	0.9657	0.6889
0.4404	3.0	81	0.7664	0.7556
0.2921	4.0	108	0.7034	0.7778
0.1574	5.0	135	0.7044	0.7778
0.0983	6.0	162	0.6550	0.8222
0.0636	7.0	189	0.6911	0.7778
0.0455	8.0	216	0.6445	0.8
0.0369	9.0	243	0.7441	0.8
0.0208	10.0	270	0.7266	0.8222
0.0164	11.0	297	0.7445	0.8
0.0128	12.0	324	0.7928	0.7556
0.0152	13.0	351	0.8051	0.8
0.0093	14.0	378	0.8366	0.8
0.005	15.0	405	0.8967	0.7778
0.0081	16.0	432	0.8765	0.7556
0.0143	17.0	459	0.8233	0.8
0.0086	18.0	486	0.8818	0.7778
0.0082	19.0	513	0.9209	0.7778
0.0106	20.0	540	0.9710	0.7778
0.0048	21.0	567	0.8635	0.8
0.0078	22.0	594	1.0340	0.7778
0.0037	23.0	621	1.0458	0.7778
0.0038	24.0	648	1.0554	0.7778
0.0027	25.0	675	0.9290	0.8
0.0037	26.0	702	0.9379	0.7778
0.006	27.0	729	0.9412	0.8
0.001	28.0	756	0.9493	0.8
0.0018	29.0	783	1.0041	0.8
0.0014	30.0	810	1.0318	0.8
0.0008	31.0	837	1.0197	0.8
0.0016	32.0	864	1.0685	0.7556
0.005	33.0	891	1.0574	0.7556
0.0013	34.0	918	1.0948	0.7556
0.0027	35.0	945	1.0699	0.7556
0.0008	36.0	972	1.0485	0.8
0.0014	37.0	999	1.0539	0.7778
0.0009	38.0	1026	1.0508	0.7778
0.0013	39.0	1053	1.0236	0.7778
0.0008	40.0	1080	1.0556	0.8
0.0014	41.0	1107	1.0682	0.8
0.0011	42.0	1134	1.0760	0.8
0.0041	43.0	1161	1.0831	0.8
0.0007	44.0	1188	1.0675	0.7778
0.0039	45.0	1215	1.0667	0.7778
0.0013	46.0	1242	1.0695	0.7778
0.0014	47.0	1269	1.0717	0.7778
0.0015	48.0	1296	1.0731	0.7778
0.002	49.0	1323	1.0731	0.7778
0.0013	50.0	1350	1.0731	0.7778

Framework versions

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