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: 1.3600
Accuracy: 0.2683

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
1.4054	1.0	220	1.3726	0.2683
1.4058	2.0	440	1.3720	0.2683
1.4165	3.0	660	1.3713	0.2683
1.3927	4.0	880	1.3707	0.2683
1.4116	5.0	1100	1.3701	0.2683
1.3812	6.0	1320	1.3696	0.2683
1.4048	7.0	1540	1.3690	0.2683
1.3591	8.0	1760	1.3685	0.2683
1.4052	9.0	1980	1.3680	0.2683
1.3882	10.0	2200	1.3676	0.2683
1.3863	11.0	2420	1.3671	0.2683
1.3965	12.0	2640	1.3667	0.2683
1.4035	13.0	2860	1.3663	0.2683
1.3813	14.0	3080	1.3659	0.2683
1.3758	15.0	3300	1.3655	0.2683
1.3822	16.0	3520	1.3651	0.2683
1.3951	17.0	3740	1.3648	0.2683
1.3934	18.0	3960	1.3645	0.2683
1.3858	19.0	4180	1.3642	0.2683
1.3848	20.0	4400	1.3639	0.2683
1.379	21.0	4620	1.3636	0.2683
1.3756	22.0	4840	1.3633	0.2683
1.3759	23.0	5060	1.3630	0.2683
1.3873	24.0	5280	1.3628	0.2683
1.3701	25.0	5500	1.3626	0.2683
1.3779	26.0	5720	1.3623	0.2683
1.3916	27.0	5940	1.3621	0.2683
1.3605	28.0	6160	1.3619	0.2927
1.3832	29.0	6380	1.3617	0.2927
1.3641	30.0	6600	1.3616	0.2927
1.3806	31.0	6820	1.3614	0.2927
1.3762	32.0	7040	1.3612	0.2927
1.3671	33.0	7260	1.3611	0.2683
1.3772	34.0	7480	1.3610	0.2683
1.3577	35.0	7700	1.3608	0.2683
1.3486	36.0	7920	1.3607	0.2683
1.3611	37.0	8140	1.3606	0.2683
1.355	38.0	8360	1.3605	0.2683
1.3682	39.0	8580	1.3604	0.2683
1.3669	40.0	8800	1.3603	0.2683
1.3585	41.0	9020	1.3603	0.2683
1.3549	42.0	9240	1.3602	0.2683
1.3669	43.0	9460	1.3602	0.2683
1.353	44.0	9680	1.3601	0.2683
1.3499	45.0	9900	1.3601	0.2683
1.3573	46.0	10120	1.3600	0.2683
1.384	47.0	10340	1.3600	0.2683
1.367	48.0	10560	1.3600	0.2683
1.3753	49.0	10780	1.3600	0.2683
1.3687	50.0	11000	1.3600	0.2683

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2

hkivancoral/hushem_40x_deit_base_sgd_00001_fold5

hushem_40x_deit_base_sgd_00001_fold5

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
hushem_40x_deit_base_sgd_00001_fold5