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: 1.0622
Accuracy: 0.4483

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
1.1145	1.0	375	1.1057	0.3517
1.1046	2.0	750	1.1036	0.365
1.1155	3.0	1125	1.1017	0.3617
1.0962	4.0	1500	1.0998	0.3733
1.1039	5.0	1875	1.0980	0.375
1.1203	6.0	2250	1.0963	0.3833
1.072	7.0	2625	1.0946	0.3833
1.0855	8.0	3000	1.0930	0.3883
1.0787	9.0	3375	1.0914	0.395
1.1082	10.0	3750	1.0899	0.3933
1.0738	11.0	4125	1.0885	0.4033
1.0788	12.0	4500	1.0870	0.4067
1.0872	13.0	4875	1.0857	0.415
1.0927	14.0	5250	1.0844	0.4133
1.0769	15.0	5625	1.0831	0.4167
1.085	16.0	6000	1.0819	0.4217
1.0634	17.0	6375	1.0806	0.42
1.0703	18.0	6750	1.0795	0.42
1.0536	19.0	7125	1.0783	0.4233
1.0852	20.0	7500	1.0773	0.4267
1.076	21.0	7875	1.0762	0.43
1.0765	22.0	8250	1.0752	0.4333
1.0647	23.0	8625	1.0743	0.435
1.061	24.0	9000	1.0734	0.4367
1.0648	25.0	9375	1.0725	0.445
1.0459	26.0	9750	1.0716	0.4417
1.0405	27.0	10125	1.0708	0.4417
1.062	28.0	10500	1.0700	0.4433
1.0508	29.0	10875	1.0693	0.445
1.06	30.0	11250	1.0686	0.445
1.062	31.0	11625	1.0679	0.4433
1.0622	32.0	12000	1.0673	0.4417
1.056	33.0	12375	1.0667	0.44
1.0406	34.0	12750	1.0662	0.4417
1.0456	35.0	13125	1.0657	0.4433
1.0409	36.0	13500	1.0652	0.4483
1.0536	37.0	13875	1.0648	0.4483
1.0481	38.0	14250	1.0643	0.445
1.0612	39.0	14625	1.0640	0.445
1.0364	40.0	15000	1.0637	0.45
1.0455	41.0	15375	1.0634	0.45
1.0602	42.0	15750	1.0631	0.45
1.0611	43.0	16125	1.0629	0.45
1.0352	44.0	16500	1.0627	0.45
1.0491	45.0	16875	1.0625	0.45
1.0436	46.0	17250	1.0624	0.45
1.0657	47.0	17625	1.0623	0.45
1.0594	48.0	18000	1.0622	0.4483
1.0541	49.0	18375	1.0622	0.4483
1.0444	50.0	18750	1.0622	0.4483

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_fold3

smids_5x_deit_base_sgd_00001_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_5x_deit_base_sgd_00001_fold3