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: 1.5045
Accuracy: 0.2889

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
No log	1.0	6	1.5103	0.2889
1.5406	2.0	12	1.5100	0.2889
1.5406	3.0	18	1.5097	0.2889
1.5187	4.0	24	1.5094	0.2889
1.5371	5.0	30	1.5091	0.2889
1.5371	6.0	36	1.5089	0.2889
1.517	7.0	42	1.5086	0.2889
1.517	8.0	48	1.5084	0.2889
1.5407	9.0	54	1.5081	0.2889
1.5157	10.0	60	1.5079	0.2889
1.5157	11.0	66	1.5077	0.2889
1.5121	12.0	72	1.5074	0.2889
1.5121	13.0	78	1.5072	0.2889
1.538	14.0	84	1.5070	0.2889
1.5262	15.0	90	1.5068	0.2889
1.5262	16.0	96	1.5066	0.2889
1.5233	17.0	102	1.5064	0.2889
1.5233	18.0	108	1.5063	0.2889
1.5376	19.0	114	1.5061	0.2889
1.5005	20.0	120	1.5060	0.2889
1.5005	21.0	126	1.5058	0.2889
1.5271	22.0	132	1.5057	0.2889
1.5271	23.0	138	1.5056	0.2889
1.5205	24.0	144	1.5055	0.2889
1.5085	25.0	150	1.5054	0.2889
1.5085	26.0	156	1.5053	0.2889
1.5221	27.0	162	1.5052	0.2889
1.5221	28.0	168	1.5051	0.2889
1.5344	29.0	174	1.5050	0.2889
1.5325	30.0	180	1.5049	0.2889
1.5325	31.0	186	1.5048	0.2889
1.5365	32.0	192	1.5048	0.2889
1.5365	33.0	198	1.5047	0.2889
1.5421	34.0	204	1.5046	0.2889
1.5276	35.0	210	1.5046	0.2889
1.5276	36.0	216	1.5046	0.2889
1.5101	37.0	222	1.5045	0.2889
1.5101	38.0	228	1.5045	0.2889
1.5025	39.0	234	1.5045	0.2889
1.5405	40.0	240	1.5045	0.2889
1.5405	41.0	246	1.5045	0.2889
1.5373	42.0	252	1.5045	0.2889
1.5373	43.0	258	1.5045	0.2889
1.5465	44.0	264	1.5045	0.2889
1.4924	45.0	270	1.5045	0.2889
1.4924	46.0	276	1.5045	0.2889
1.521	47.0	282	1.5045	0.2889
1.521	48.0	288	1.5045	0.2889
1.494	49.0	294	1.5045	0.2889
1.5268	50.0	300	1.5045	0.2889

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_00001_fold1

hushem_1x_deit_small_sgd_00001_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
hushem_1x_deit_small_sgd_00001_fold1