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

Loss: 1.4953
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: 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	1.5027	0.3095
1.6067	2.0	12	1.5024	0.2857
1.6067	3.0	18	1.5020	0.2857
1.5707	4.0	24	1.5016	0.2857
1.5808	5.0	30	1.5013	0.2857
1.5808	6.0	36	1.5009	0.2857
1.5893	7.0	42	1.5006	0.2857
1.5893	8.0	48	1.5003	0.2857
1.5944	9.0	54	1.5000	0.2857
1.5821	10.0	60	1.4997	0.2857
1.5821	11.0	66	1.4994	0.2857
1.5703	12.0	72	1.4991	0.2857
1.5703	13.0	78	1.4988	0.2857
1.5654	14.0	84	1.4986	0.2857
1.5848	15.0	90	1.4983	0.2857
1.5848	16.0	96	1.4981	0.2857
1.606	17.0	102	1.4978	0.2857
1.606	18.0	108	1.4976	0.2857
1.6306	19.0	114	1.4974	0.2857
1.5966	20.0	120	1.4972	0.2857
1.5966	21.0	126	1.4970	0.2857
1.5946	22.0	132	1.4969	0.2857
1.5946	23.0	138	1.4967	0.2857
1.5656	24.0	144	1.4966	0.2857
1.5572	25.0	150	1.4964	0.2857
1.5572	26.0	156	1.4963	0.2857
1.5856	27.0	162	1.4961	0.2857
1.5856	28.0	168	1.4960	0.2857
1.612	29.0	174	1.4959	0.2857
1.581	30.0	180	1.4958	0.2857
1.581	31.0	186	1.4957	0.2857
1.566	32.0	192	1.4956	0.2857
1.566	33.0	198	1.4956	0.2857
1.5925	34.0	204	1.4955	0.2857
1.5991	35.0	210	1.4954	0.2857
1.5991	36.0	216	1.4954	0.2857
1.5811	37.0	222	1.4954	0.2857
1.5811	38.0	228	1.4953	0.2857
1.5945	39.0	234	1.4953	0.2857
1.5831	40.0	240	1.4953	0.2857
1.5831	41.0	246	1.4953	0.2857
1.5802	42.0	252	1.4953	0.2857
1.5802	43.0	258	1.4953	0.2857
1.6388	44.0	264	1.4953	0.2857
1.5513	45.0	270	1.4953	0.2857
1.5513	46.0	276	1.4953	0.2857
1.5675	47.0	282	1.4953	0.2857
1.5675	48.0	288	1.4953	0.2857
1.6043	49.0	294	1.4953	0.2857
1.6042	50.0	300	1.4953	0.2857

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0

hkivancoral/hushem_1x_beit_base_sgd_00001_fold4

hushem_1x_beit_base_sgd_00001_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
hushem_1x_beit_base_sgd_00001_fold4