smids_5x_beit_base_sgd_001_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: 0.2771
• Accuracy: 0.8915

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
0.7737	1.0	376	1.0623	0.3957
0.6499	2.0	752	0.5904	0.7679
0.5039	3.0	1128	0.4948	0.8114
0.4425	4.0	1504	0.4355	0.8314
0.4117	5.0	1880	0.4034	0.8381
0.3506	6.0	2256	0.3735	0.8497
0.3184	7.0	2632	0.3579	0.8614
0.3583	8.0	3008	0.3422	0.8664
0.3344	9.0	3384	0.3340	0.8765
0.3048	10.0	3760	0.3243	0.8731
0.3275	11.0	4136	0.3128	0.8815
0.2663	12.0	4512	0.3111	0.8765
0.2691	13.0	4888	0.3046	0.8815
0.2761	14.0	5264	0.3135	0.8715
0.3203	15.0	5640	0.2998	0.8831
0.2245	16.0	6016	0.2963	0.8881
0.2282	17.0	6392	0.2992	0.8881
0.3086	18.0	6768	0.2841	0.8881
0.2882	19.0	7144	0.2985	0.8831
0.2358	20.0	7520	0.2906	0.8898
0.25	21.0	7896	0.2925	0.8848
0.2381	22.0	8272	0.2832	0.8915
0.2558	23.0	8648	0.2829	0.8898
0.2316	24.0	9024	0.2855	0.8865
0.2594	25.0	9400	0.2808	0.8915
0.2312	26.0	9776	0.2815	0.8915
0.1664	27.0	10152	0.2829	0.8865
0.2051	28.0	10528	0.2875	0.8815
0.229	29.0	10904	0.2816	0.8881
0.1761	30.0	11280	0.2816	0.8915
0.2039	31.0	11656	0.2802	0.8965
0.2453	32.0	12032	0.2762	0.8965
0.186	33.0	12408	0.2762	0.8965
0.1739	34.0	12784	0.2763	0.8948
0.1942	35.0	13160	0.2781	0.8898
0.2172	36.0	13536	0.2768	0.8898
0.1982	37.0	13912	0.2760	0.8965
0.2031	38.0	14288	0.2780	0.8881
0.2045	39.0	14664	0.2746	0.8948
0.1936	40.0	15040	0.2754	0.8998
0.2051	41.0	15416	0.2792	0.8948
0.2059	42.0	15792	0.2787	0.8932
0.2037	43.0	16168	0.2780	0.8932
0.2183	44.0	16544	0.2796	0.8898
0.1934	45.0	16920	0.2779	0.8965
0.2385	46.0	17296	0.2770	0.8915
0.1872	47.0	17672	0.2768	0.8948
0.1967	48.0	18048	0.2773	0.8898
0.1829	49.0	18424	0.2770	0.8932
0.1506	50.0	18800	0.2771	0.8915

Framework versions

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