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

Loss: 1.6903
Accuracy: 0.2222

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
1.5766	1.0	27	1.7230	0.2222
1.5482	2.0	54	1.7214	0.2222
1.545	3.0	81	1.7199	0.2222
1.5461	4.0	108	1.7185	0.2222
1.5083	5.0	135	1.7171	0.2222
1.533	6.0	162	1.7157	0.2222
1.5321	7.0	189	1.7144	0.2222
1.5594	8.0	216	1.7131	0.2222
1.5064	9.0	243	1.7118	0.2222
1.4954	10.0	270	1.7106	0.2222
1.5489	11.0	297	1.7094	0.2222
1.5003	12.0	324	1.7083	0.2222
1.5049	13.0	351	1.7073	0.2222
1.5566	14.0	378	1.7062	0.2222
1.4974	15.0	405	1.7052	0.2222
1.4964	16.0	432	1.7043	0.2222
1.5261	17.0	459	1.7033	0.2222
1.4775	18.0	486	1.7024	0.2222
1.5065	19.0	513	1.7015	0.2222
1.4755	20.0	540	1.7007	0.2222
1.5258	21.0	567	1.6999	0.2222
1.5082	22.0	594	1.6991	0.2222
1.4959	23.0	621	1.6984	0.2222
1.4864	24.0	648	1.6977	0.2222
1.5154	25.0	675	1.6970	0.2222
1.4838	26.0	702	1.6964	0.2222
1.4873	27.0	729	1.6958	0.2222
1.5062	28.0	756	1.6952	0.2222
1.4886	29.0	783	1.6947	0.2222
1.497	30.0	810	1.6942	0.2222
1.498	31.0	837	1.6937	0.2222
1.4952	32.0	864	1.6933	0.2222
1.492	33.0	891	1.6929	0.2222
1.4832	34.0	918	1.6925	0.2222
1.5095	35.0	945	1.6922	0.2222
1.5164	36.0	972	1.6919	0.2222
1.5027	37.0	999	1.6916	0.2222
1.5132	38.0	1026	1.6913	0.2222
1.5138	39.0	1053	1.6911	0.2222
1.4995	40.0	1080	1.6909	0.2222
1.4924	41.0	1107	1.6908	0.2222
1.4936	42.0	1134	1.6906	0.2222
1.5293	43.0	1161	1.6905	0.2222
1.5068	44.0	1188	1.6904	0.2222
1.5134	45.0	1215	1.6904	0.2222
1.4849	46.0	1242	1.6903	0.2222
1.5093	47.0	1269	1.6903	0.2222
1.4852	48.0	1296	1.6903	0.2222
1.5207	49.0	1323	1.6903	0.2222
1.4563	50.0	1350	1.6903	0.2222

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0

hkivancoral/hushem_5x_deit_tiny_sgd_00001_fold2

hushem_5x_deit_tiny_sgd_00001_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
hushem_5x_deit_tiny_sgd_00001_fold2