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: 3.0511
Accuracy: 0.7778

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: 0.001
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
0.091	1.0	215	1.8850	0.7111
0.0695	2.0	430	1.9470	0.6444
0.0617	3.0	645	1.5137	0.7556
0.0146	4.0	860	1.8770	0.7333
0.0437	5.0	1075	2.0442	0.7333
0.0116	6.0	1290	1.4759	0.8
0.0035	7.0	1505	2.8704	0.6444
0.0344	8.0	1720	2.7808	0.6444
0.0121	9.0	1935	2.7705	0.6889
0.0003	10.0	2150	2.2137	0.7556
0.0626	11.0	2365	2.2191	0.7111
0.0001	12.0	2580	2.1839	0.7111
0.0106	13.0	2795	2.7238	0.6444
0.0001	14.0	3010	3.0158	0.6444
0.0001	15.0	3225	2.3783	0.7556
0.0	16.0	3440	2.3314	0.7556
0.0	17.0	3655	2.3547	0.7556
0.0	18.0	3870	2.3759	0.7556
0.0	19.0	4085	2.3984	0.7556
0.0	20.0	4300	2.4203	0.7556
0.0	21.0	4515	2.4425	0.7556
0.0	22.0	4730	2.4655	0.7556
0.0	23.0	4945	2.4901	0.7556
0.0	24.0	5160	2.5187	0.7556
0.0	25.0	5375	2.5510	0.7556
0.0	26.0	5590	2.5849	0.7556
0.0	27.0	5805	2.6187	0.7556
0.0	28.0	6020	2.6506	0.7556
0.0	29.0	6235	2.6816	0.7556
0.0	30.0	6450	2.7120	0.7556
0.0	31.0	6665	2.7426	0.7778
0.0	32.0	6880	2.7738	0.7778
0.0	33.0	7095	2.8047	0.7778
0.0	34.0	7310	2.8362	0.7778
0.0	35.0	7525	2.8656	0.7778
0.0	36.0	7740	2.8925	0.7778
0.0	37.0	7955	2.9162	0.7778
0.0	38.0	8170	2.9371	0.7778
0.0	39.0	8385	2.9556	0.7778
0.0	40.0	8600	2.9717	0.7778
0.0	41.0	8815	2.9862	0.7778
0.0	42.0	9030	2.9991	0.7778
0.0	43.0	9245	3.0106	0.7778
0.0	44.0	9460	3.0207	0.7778
0.0	45.0	9675	3.0295	0.7778
0.0	46.0	9890	3.0369	0.7778
0.0	47.0	10105	3.0430	0.7778
0.0	48.0	10320	3.0475	0.7778
0.0	49.0	10535	3.0503	0.7778
0.0	50.0	10750	3.0511	0.7778

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2

hkivancoral/hushem_40x_deit_base_adamax_001_fold2

hushem_40x_deit_base_adamax_001_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
hushem_40x_deit_base_adamax_001_fold2