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

Loss: 1.4227
Accuracy: 0.2619

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: 0.0001
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
No log	1.0	6	1.4804	0.2619
1.5213	2.0	12	1.4770	0.2857
1.5213	3.0	18	1.4737	0.2857
1.5439	4.0	24	1.4702	0.2857
1.5226	5.0	30	1.4673	0.2857
1.5226	6.0	36	1.4646	0.2857
1.52	7.0	42	1.4618	0.2857
1.52	8.0	48	1.4591	0.2857
1.5076	9.0	54	1.4566	0.2857
1.5003	10.0	60	1.4541	0.2857
1.5003	11.0	66	1.4520	0.2857
1.4856	12.0	72	1.4497	0.2857
1.4856	13.0	78	1.4476	0.2857
1.5104	14.0	84	1.4457	0.2857
1.4726	15.0	90	1.4438	0.2857
1.4726	16.0	96	1.4420	0.2857
1.4844	17.0	102	1.4403	0.2857
1.4844	18.0	108	1.4387	0.2619
1.4456	19.0	114	1.4373	0.2619
1.5242	20.0	120	1.4359	0.2619
1.5242	21.0	126	1.4347	0.2619
1.4484	22.0	132	1.4335	0.2619
1.4484	23.0	138	1.4324	0.2619
1.4722	24.0	144	1.4314	0.2619
1.4802	25.0	150	1.4303	0.2619
1.4802	26.0	156	1.4294	0.2619
1.4658	27.0	162	1.4284	0.2619
1.4658	28.0	168	1.4276	0.2619
1.4705	29.0	174	1.4269	0.2619
1.4629	30.0	180	1.4263	0.2619
1.4629	31.0	186	1.4256	0.2619
1.4786	32.0	192	1.4251	0.2619
1.4786	33.0	198	1.4246	0.2619
1.4444	34.0	204	1.4242	0.2619
1.435	35.0	210	1.4238	0.2619
1.435	36.0	216	1.4235	0.2619
1.4653	37.0	222	1.4232	0.2619
1.4653	38.0	228	1.4230	0.2619
1.4482	39.0	234	1.4228	0.2619
1.4598	40.0	240	1.4227	0.2619
1.4598	41.0	246	1.4227	0.2619
1.4528	42.0	252	1.4227	0.2619
1.4528	43.0	258	1.4227	0.2619
1.4661	44.0	264	1.4227	0.2619
1.4575	45.0	270	1.4227	0.2619
1.4575	46.0	276	1.4227	0.2619
1.4719	47.0	282	1.4227	0.2619
1.4719	48.0	288	1.4227	0.2619
1.4602	49.0	294	1.4227	0.2619
1.465	50.0	300	1.4227	0.2619

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1

hkivancoral/hushem_1x_deit_small_sgd_0001_fold4

hushem_1x_deit_small_sgd_0001_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
hushem_1x_deit_small_sgd_0001_fold4