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_0001_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: 0.8

hushem_5x_beit_base_adamax_0001_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: 0.9719
• Accuracy: 0.8

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
0.4817	1.0	27	0.8446	0.6889
0.1236	2.0	54	0.5416	0.8
0.0728	3.0	81	1.1383	0.7333
0.0137	4.0	108	0.8130	0.7556
0.0121	5.0	135	1.0498	0.7778
0.0052	6.0	162	1.2025	0.7333
0.0025	7.0	189	1.8500	0.6889
0.0027	8.0	216	1.2581	0.7333
0.0011	9.0	243	1.0128	0.7111
0.0002	10.0	270	1.1087	0.7111
0.0015	11.0	297	1.5799	0.6889
0.0003	12.0	324	1.1596	0.7333
0.0003	13.0	351	0.7321	0.8222
0.0002	14.0	378	0.7110	0.8444
0.0001	15.0	405	0.9712	0.8
0.0001	16.0	432	0.9021	0.8
0.0003	17.0	459	1.0755	0.7778
0.0001	18.0	486	0.9553	0.8
0.0001	19.0	513	0.7418	0.8
0.0001	20.0	540	0.8008	0.8222
0.0001	21.0	567	0.8246	0.8222
0.0002	22.0	594	1.0106	0.8
0.0006	23.0	621	1.3939	0.7111
0.0001	24.0	648	1.1381	0.7111
0.0002	25.0	675	1.0384	0.7556
0.0001	26.0	702	0.9699	0.7556
0.0001	27.0	729	0.8959	0.7778
0.0	28.0	756	0.8640	0.8
0.0	29.0	783	0.8622	0.8
0.0001	30.0	810	1.0310	0.7778
0.0001	31.0	837	1.1256	0.7778
0.0001	32.0	864	1.0777	0.7778
0.0001	33.0	891	0.9925	0.7556
0.0001	34.0	918	0.9854	0.7778
0.0	35.0	945	0.9843	0.7778
0.0	36.0	972	0.9861	0.7778
0.0	37.0	999	1.0844	0.8222
0.0	38.0	1026	1.0708	0.8222
0.0001	39.0	1053	1.0786	0.8
0.0	40.0	1080	1.0854	0.8
0.001	41.0	1107	1.0589	0.8
0.0001	42.0	1134	1.1362	0.7556
0.0028	43.0	1161	1.0635	0.8
0.0	44.0	1188	0.9767	0.8
0.0	45.0	1215	0.9696	0.8
0.0003	46.0	1242	0.9742	0.8
0.0	47.0	1269	0.9715	0.8
0.0	48.0	1296	0.9720	0.8
0.0001	49.0	1323	0.9719	0.8
0.0001	50.0	1350	0.9719	0.8

Framework versions

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