hushem_40x_beit_large_adamax_001_fold4

This model is a fine-tuned version of microsoft/beit-large-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.0452
• Accuracy: 0.9762

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
0.4622	1.0	219	0.6192	0.7143
0.1812	2.0	438	0.3334	0.8810
0.1061	3.0	657	0.3100	0.8810
0.061	4.0	876	0.3909	0.9048
0.07	5.0	1095	0.5029	0.8095
0.0116	6.0	1314	0.1841	0.9286
0.0286	7.0	1533	0.1625	0.9524
0.0589	8.0	1752	0.3628	0.9286
0.0111	9.0	1971	0.1004	0.9762
0.0199	10.0	2190	0.2149	0.9524
0.0026	11.0	2409	0.2299	0.9524
0.003	12.0	2628	0.0798	0.9524
0.0002	13.0	2847	0.3767	0.9524
0.0	14.0	3066	0.3423	0.9524
0.0	15.0	3285	0.3097	0.9524
0.0	16.0	3504	0.3620	0.9524
0.0	17.0	3723	0.3599	0.9524
0.0109	18.0	3942	1.0112	0.8810
0.0058	19.0	4161	0.3536	0.9286
0.0	20.0	4380	0.1749	0.9524
0.0	21.0	4599	0.1549	0.9762
0.0	22.0	4818	0.1579	0.9762
0.0001	23.0	5037	0.2020	0.9762
0.0	24.0	5256	0.1981	0.9524
0.0	25.0	5475	0.2004	0.9524
0.0	26.0	5694	0.2385	0.9524
0.0	27.0	5913	0.2312	0.9762
0.0	28.0	6132	0.2326	0.9524
0.0	29.0	6351	0.2329	0.9762
0.0	30.0	6570	0.2354	0.9762
0.0	31.0	6789	0.2406	0.9762
0.0	32.0	7008	0.1614	0.9524
0.0	33.0	7227	0.7242	0.8810
0.0	34.0	7446	0.6237	0.9048
0.0	35.0	7665	0.2046	0.9762
0.0	36.0	7884	0.3311	0.9524
0.0	37.0	8103	0.0102	1.0
0.0	38.0	8322	0.0205	0.9762
0.0	39.0	8541	0.4064	0.9286
0.0	40.0	8760	0.2152	0.9524
0.0	41.0	8979	0.0320	0.9762
0.0	42.0	9198	0.0414	0.9762
0.0	43.0	9417	0.0410	0.9762
0.0	44.0	9636	0.0475	0.9762
0.0	45.0	9855	0.0475	0.9762
0.0	46.0	10074	0.0463	0.9762
0.0	47.0	10293	0.0463	0.9762
0.0	48.0	10512	0.0476	0.9762
0.0	49.0	10731	0.0481	0.9762
0.0	50.0	10950	0.0452	0.9762

Framework versions

• Transformers 4.32.1
• Pytorch 2.1.0+cu121
• Datasets 2.12.0
• Tokenizers 0.13.2