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: 1.3470
Accuracy: 0.3556

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: 0.001
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	1.4885	0.2
1.5055	2.0	12	1.4667	0.2667
1.5055	3.0	18	1.4496	0.2444
1.4394	4.0	24	1.4374	0.2444
1.4154	5.0	30	1.4269	0.2444
1.4154	6.0	36	1.4185	0.2667
1.3643	7.0	42	1.4107	0.3333
1.3643	8.0	48	1.4053	0.3556
1.3559	9.0	54	1.4001	0.3556
1.3227	10.0	60	1.3952	0.3556
1.3227	11.0	66	1.3910	0.3556
1.3197	12.0	72	1.3872	0.3556
1.3197	13.0	78	1.3837	0.3556
1.2846	14.0	84	1.3804	0.3556
1.2901	15.0	90	1.3773	0.3556
1.2901	16.0	96	1.3743	0.3333
1.2643	17.0	102	1.3716	0.3333
1.2643	18.0	108	1.3691	0.3333
1.2844	19.0	114	1.3667	0.3333
1.2293	20.0	120	1.3643	0.3333
1.2293	21.0	126	1.3623	0.3333
1.2404	22.0	132	1.3607	0.3333
1.2404	23.0	138	1.3587	0.3333
1.2359	24.0	144	1.3573	0.3333
1.2062	25.0	150	1.3561	0.3333
1.2062	26.0	156	1.3548	0.3333
1.2199	27.0	162	1.3536	0.3333
1.2199	28.0	168	1.3527	0.3333
1.2151	29.0	174	1.3520	0.3556
1.2005	30.0	180	1.3511	0.3556
1.2005	31.0	186	1.3504	0.3556
1.1928	32.0	192	1.3498	0.3556
1.1928	33.0	198	1.3492	0.3556
1.1891	34.0	204	1.3487	0.3556
1.1974	35.0	210	1.3482	0.3556
1.1974	36.0	216	1.3478	0.3556
1.1657	37.0	222	1.3476	0.3556
1.1657	38.0	228	1.3474	0.3556
1.1722	39.0	234	1.3472	0.3556
1.2031	40.0	240	1.3471	0.3556
1.2031	41.0	246	1.3470	0.3556
1.1899	42.0	252	1.3470	0.3556
1.1899	43.0	258	1.3470	0.3556
1.1761	44.0	264	1.3470	0.3556
1.1715	45.0	270	1.3470	0.3556
1.1715	46.0	276	1.3470	0.3556
1.1816	47.0	282	1.3470	0.3556
1.1816	48.0	288	1.3470	0.3556
1.1504	49.0	294	1.3470	0.3556
1.1896	50.0	300	1.3470	0.3556

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_001_fold2

hushem_1x_deit_small_sgd_001_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
hushem_1x_deit_small_sgd_001_fold2