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: 1.3702
Accuracy: 0.2889

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
1.5833	1.0	215	1.4002	0.1778
1.5381	2.0	430	1.3990	0.2
1.505	3.0	645	1.3978	0.2222
1.446	4.0	860	1.3967	0.2444
1.4742	5.0	1075	1.3956	0.2222
1.3991	6.0	1290	1.3945	0.2222
1.4142	7.0	1505	1.3933	0.2222
1.4895	8.0	1720	1.3923	0.2222
1.4297	9.0	1935	1.3912	0.2222
1.4803	10.0	2150	1.3901	0.2222
1.4253	11.0	2365	1.3890	0.2222
1.4151	12.0	2580	1.3880	0.2222
1.3649	13.0	2795	1.3870	0.2222
1.4058	14.0	3010	1.3860	0.2444
1.3858	15.0	3225	1.3850	0.2444
1.3985	16.0	3440	1.3841	0.2444
1.4078	17.0	3655	1.3832	0.2444
1.3916	18.0	3870	1.3823	0.2444
1.4138	19.0	4085	1.3814	0.2444
1.3697	20.0	4300	1.3807	0.2444
1.3976	21.0	4515	1.3799	0.2444
1.45	22.0	4730	1.3791	0.2444
1.3757	23.0	4945	1.3784	0.2444
1.4088	24.0	5160	1.3777	0.2667
1.3948	25.0	5375	1.3771	0.2667
1.3916	26.0	5590	1.3764	0.2667
1.3383	27.0	5805	1.3759	0.2667
1.3507	28.0	6020	1.3753	0.2889
1.3823	29.0	6235	1.3748	0.2889
1.3489	30.0	6450	1.3743	0.2889
1.3905	31.0	6665	1.3738	0.2889
1.3646	32.0	6880	1.3734	0.2889
1.394	33.0	7095	1.3730	0.2889
1.3256	34.0	7310	1.3726	0.2889
1.342	35.0	7525	1.3723	0.2889
1.3277	36.0	7740	1.3720	0.2889
1.3815	37.0	7955	1.3717	0.2889
1.3516	38.0	8170	1.3714	0.2889
1.3573	39.0	8385	1.3712	0.2889
1.3764	40.0	8600	1.3710	0.2889
1.3508	41.0	8815	1.3708	0.2889
1.4032	42.0	9030	1.3707	0.2889
1.3548	43.0	9245	1.3705	0.2889
1.3623	44.0	9460	1.3704	0.2889
1.3744	45.0	9675	1.3704	0.2889
1.3298	46.0	9890	1.3703	0.2889
1.352	47.0	10105	1.3703	0.2889
1.363	48.0	10320	1.3702	0.2889
1.3844	49.0	10535	1.3702	0.2889
1.3587	50.0	10750	1.3702	0.2889

Framework versions

Transformers 4.32.1
Pytorch 2.1.1+cu121
Datasets 2.12.0
Tokenizers 0.13.2

hkivancoral/hushem_40x_deit_tiny_sgd_00001_fold1

hushem_40x_deit_tiny_sgd_00001_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
hushem_40x_deit_tiny_sgd_00001_fold1