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: 1.3898
Accuracy: 0.3111

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
1.4168	1.0	215	1.4077	0.2444
1.3843	2.0	430	1.4068	0.2444
1.4045	3.0	645	1.4059	0.2444
1.3944	4.0	860	1.4051	0.2444
1.3979	5.0	1075	1.4043	0.2444
1.4212	6.0	1290	1.4036	0.2667
1.4197	7.0	1505	1.4029	0.2667
1.369	8.0	1720	1.4022	0.2667
1.3853	9.0	1935	1.4015	0.2667
1.4053	10.0	2150	1.4008	0.2667
1.3723	11.0	2365	1.4002	0.2667
1.3571	12.0	2580	1.3996	0.2667
1.3936	13.0	2795	1.3990	0.2667
1.3779	14.0	3010	1.3985	0.2667
1.3861	15.0	3225	1.3979	0.2667
1.4005	16.0	3440	1.3974	0.2889
1.3769	17.0	3655	1.3969	0.2889
1.3909	18.0	3870	1.3964	0.2889
1.3834	19.0	4085	1.3960	0.2889
1.3642	20.0	4300	1.3956	0.2889
1.3863	21.0	4515	1.3951	0.2889
1.3863	22.0	4730	1.3947	0.2889
1.3703	23.0	4945	1.3944	0.2889
1.3733	24.0	5160	1.3940	0.2889
1.3751	25.0	5375	1.3937	0.3111
1.3799	26.0	5590	1.3933	0.3111
1.3637	27.0	5805	1.3930	0.3111
1.3658	28.0	6020	1.3927	0.3111
1.3837	29.0	6235	1.3924	0.3111
1.3573	30.0	6450	1.3922	0.3111
1.3483	31.0	6665	1.3919	0.3111
1.3737	32.0	6880	1.3917	0.3111
1.3567	33.0	7095	1.3915	0.3111
1.3764	34.0	7310	1.3913	0.3111
1.3646	35.0	7525	1.3911	0.3111
1.3557	36.0	7740	1.3909	0.3111
1.3829	37.0	7955	1.3907	0.3111
1.3713	38.0	8170	1.3906	0.3111
1.3468	39.0	8385	1.3905	0.3111
1.3527	40.0	8600	1.3903	0.3111
1.3629	41.0	8815	1.3902	0.3111
1.3464	42.0	9030	1.3901	0.3111
1.3709	43.0	9245	1.3901	0.3111
1.3524	44.0	9460	1.3900	0.3111
1.3532	45.0	9675	1.3899	0.3111
1.3657	46.0	9890	1.3899	0.3111
1.3891	47.0	10105	1.3899	0.3111
1.3666	48.0	10320	1.3898	0.3111
1.3713	49.0	10535	1.3898	0.3111
1.3614	50.0	10750	1.3898	0.3111

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_fold2

hushem_40x_deit_base_sgd_00001_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
hushem_40x_deit_base_sgd_00001_fold2