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: 0.0332
Accuracy: 1.0

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
0.7295	1.0	28	0.4220	0.8095
0.0888	2.0	56	0.1615	0.9286
0.0158	3.0	84	0.0867	0.9524
0.0047	4.0	112	0.1052	0.9524
0.001	5.0	140	0.1157	0.9524
0.0007	6.0	168	0.0506	0.9762
0.0004	7.0	196	0.0523	0.9762
0.0003	8.0	224	0.0521	1.0
0.0003	9.0	252	0.0486	1.0
0.0002	10.0	280	0.0478	1.0
0.0002	11.0	308	0.0461	1.0
0.0002	12.0	336	0.0436	1.0
0.0002	13.0	364	0.0422	1.0
0.0002	14.0	392	0.0427	1.0
0.0002	15.0	420	0.0410	1.0
0.0001	16.0	448	0.0408	1.0
0.0001	17.0	476	0.0398	1.0
0.0001	18.0	504	0.0389	1.0
0.0001	19.0	532	0.0389	1.0
0.0001	20.0	560	0.0386	1.0
0.0001	21.0	588	0.0377	1.0
0.0001	22.0	616	0.0375	1.0
0.0001	23.0	644	0.0368	1.0
0.0001	24.0	672	0.0368	1.0
0.0001	25.0	700	0.0364	1.0
0.0001	26.0	728	0.0360	1.0
0.0001	27.0	756	0.0354	1.0
0.0001	28.0	784	0.0352	1.0
0.0001	29.0	812	0.0345	1.0
0.0001	30.0	840	0.0346	1.0
0.0001	31.0	868	0.0344	1.0
0.0001	32.0	896	0.0342	1.0
0.0001	33.0	924	0.0343	1.0
0.0001	34.0	952	0.0340	1.0
0.0001	35.0	980	0.0336	1.0
0.0001	36.0	1008	0.0333	1.0
0.0001	37.0	1036	0.0331	1.0
0.0001	38.0	1064	0.0333	1.0
0.0001	39.0	1092	0.0331	1.0
0.0001	40.0	1120	0.0332	1.0
0.0001	41.0	1148	0.0332	1.0
0.0001	42.0	1176	0.0331	1.0
0.0001	43.0	1204	0.0330	1.0
0.0001	44.0	1232	0.0331	1.0
0.0001	45.0	1260	0.0330	1.0
0.0001	46.0	1288	0.0331	1.0
0.0001	47.0	1316	0.0332	1.0
0.0001	48.0	1344	0.0332	1.0
0.0001	49.0	1372	0.0332	1.0
0.0001	50.0	1400	0.0332	1.0

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0

hkivancoral/hushem_5x_deit_base_adamax_0001_fold4

hushem_5x_deit_base_adamax_0001_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
hushem_5x_deit_base_adamax_0001_fold4