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

Loss: 1.0653
Accuracy: 0.475

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
1.1101	1.0	375	1.1105	0.3333
1.1112	2.0	750	1.1084	0.3483
1.1096	3.0	1125	1.1064	0.3533
1.1002	4.0	1500	1.1045	0.3633
1.1197	5.0	1875	1.1027	0.3667
1.0859	6.0	2250	1.1009	0.3733
1.0856	7.0	2625	1.0992	0.3833
1.0857	8.0	3000	1.0975	0.3883
1.0995	9.0	3375	1.0959	0.3933
1.1123	10.0	3750	1.0943	0.4
1.0849	11.0	4125	1.0928	0.405
1.0866	12.0	4500	1.0914	0.4067
1.08	13.0	4875	1.0899	0.42
1.0796	14.0	5250	1.0886	0.4217
1.082	15.0	5625	1.0872	0.425
1.0851	16.0	6000	1.0859	0.4283
1.0643	17.0	6375	1.0847	0.4283
1.0676	18.0	6750	1.0834	0.4283
1.0655	19.0	7125	1.0823	0.43
1.0761	20.0	7500	1.0811	0.4283
1.069	21.0	7875	1.0800	0.4333
1.0634	22.0	8250	1.0790	0.435
1.0576	23.0	8625	1.0780	0.4383
1.0581	24.0	9000	1.0770	0.4367
1.0635	25.0	9375	1.0761	0.44
1.0553	26.0	9750	1.0752	0.4417
1.0268	27.0	10125	1.0743	0.4433
1.0755	28.0	10500	1.0735	0.4483
1.0483	29.0	10875	1.0727	0.455
1.0533	30.0	11250	1.0720	0.455
1.0638	31.0	11625	1.0713	0.455
1.0617	32.0	12000	1.0707	0.4567
1.0624	33.0	12375	1.0700	0.46
1.052	34.0	12750	1.0695	0.4667
1.0462	35.0	13125	1.0689	0.4683
1.0582	36.0	13500	1.0684	0.4683
1.0432	37.0	13875	1.0680	0.4683
1.0468	38.0	14250	1.0675	0.47
1.0664	39.0	14625	1.0671	0.4717
1.0442	40.0	15000	1.0668	0.47
1.0443	41.0	15375	1.0665	0.4717
1.0372	42.0	15750	1.0662	0.4717
1.0389	43.0	16125	1.0660	0.4717
1.044	44.0	16500	1.0658	0.4717
1.0519	45.0	16875	1.0656	0.4717
1.0549	46.0	17250	1.0655	0.475
1.0727	47.0	17625	1.0654	0.475
1.0653	48.0	18000	1.0653	0.475
1.0698	49.0	18375	1.0653	0.475
1.0509	50.0	18750	1.0653	0.475

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2

hkivancoral/smids_5x_deit_base_sgd_00001_fold4

smids_5x_deit_base_sgd_00001_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_5x_deit_base_sgd_00001_fold4