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: 1.5092
Accuracy: 0.2857

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	1.6866	0.2857
1.7029	2.0	12	1.6755	0.2857
1.7029	3.0	18	1.6648	0.2857
1.6819	4.0	24	1.6543	0.2857
1.7084	5.0	30	1.6452	0.2857
1.7084	6.0	36	1.6365	0.2857
1.661	7.0	42	1.6277	0.2857
1.661	8.0	48	1.6195	0.2857
1.6506	9.0	54	1.6113	0.2857
1.6321	10.0	60	1.6035	0.2857
1.6321	11.0	66	1.5969	0.2857
1.605	12.0	72	1.5900	0.2857
1.605	13.0	78	1.5837	0.2857
1.6205	14.0	84	1.5775	0.2857
1.6128	15.0	90	1.5717	0.2857
1.6128	16.0	96	1.5663	0.2857
1.5818	17.0	102	1.5613	0.2857
1.5818	18.0	108	1.5566	0.2857
1.6012	19.0	114	1.5522	0.2857
1.6068	20.0	120	1.5482	0.2857
1.6068	21.0	126	1.5443	0.2857
1.5674	22.0	132	1.5409	0.2857
1.5674	23.0	138	1.5376	0.2857
1.565	24.0	144	1.5344	0.2857
1.5842	25.0	150	1.5314	0.2857
1.5842	26.0	156	1.5286	0.2857
1.5593	27.0	162	1.5260	0.2857
1.5593	28.0	168	1.5236	0.2857
1.5824	29.0	174	1.5216	0.2857
1.537	30.0	180	1.5196	0.2857
1.537	31.0	186	1.5181	0.2857
1.5437	32.0	192	1.5165	0.2857
1.5437	33.0	198	1.5150	0.2857
1.5369	34.0	204	1.5137	0.2857
1.5371	35.0	210	1.5125	0.2857
1.5371	36.0	216	1.5116	0.2857
1.5229	37.0	222	1.5109	0.2857
1.5229	38.0	228	1.5102	0.2857
1.5623	39.0	234	1.5097	0.2857
1.5343	40.0	240	1.5094	0.2857
1.5343	41.0	246	1.5093	0.2857
1.5211	42.0	252	1.5092	0.2857
1.5211	43.0	258	1.5092	0.2857
1.5618	44.0	264	1.5092	0.2857
1.5309	45.0	270	1.5092	0.2857
1.5309	46.0	276	1.5092	0.2857
1.5362	47.0	282	1.5092	0.2857
1.5362	48.0	288	1.5092	0.2857
1.5728	49.0	294	1.5092	0.2857
1.5244	50.0	300	1.5092	0.2857

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1

hkivancoral/hushem_1x_deit_tiny_sgd_0001_fold4

hushem_1x_deit_tiny_sgd_0001_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
hushem_1x_deit_tiny_sgd_0001_fold4