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: 0.4899
Accuracy: 0.8372

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
1.1798	1.0	217	1.2889	0.4186
1.0098	2.0	434	1.1067	0.6047
0.7827	3.0	651	0.9427	0.6977
0.6326	4.0	868	0.7917	0.6977
0.5443	5.0	1085	0.6647	0.7907
0.4438	6.0	1302	0.5810	0.8140
0.3761	7.0	1519	0.5185	0.8372
0.3386	8.0	1736	0.4778	0.8140
0.2796	9.0	1953	0.4431	0.8605
0.2037	10.0	2170	0.4372	0.8605
0.1624	11.0	2387	0.3943	0.8837
0.1477	12.0	2604	0.4019	0.8605
0.1485	13.0	2821	0.3856	0.8605
0.1192	14.0	3038	0.3686	0.8605
0.1115	15.0	3255	0.3722	0.8605
0.0891	16.0	3472	0.3567	0.8837
0.0776	17.0	3689	0.3631	0.8605
0.1039	18.0	3906	0.3600	0.8605
0.0608	19.0	4123	0.3514	0.8605
0.0639	20.0	4340	0.3706	0.8605
0.0555	21.0	4557	0.3773	0.8605
0.0552	22.0	4774	0.3713	0.8372
0.0457	23.0	4991	0.3749	0.8372
0.0383	24.0	5208	0.3901	0.8372
0.0332	25.0	5425	0.3933	0.8372
0.0322	26.0	5642	0.3995	0.8372
0.0278	27.0	5859	0.4012	0.8372
0.0212	28.0	6076	0.3938	0.8372
0.0224	29.0	6293	0.4080	0.8372
0.0218	30.0	6510	0.4237	0.8372
0.0278	31.0	6727	0.4231	0.8372
0.0212	32.0	6944	0.4330	0.8372
0.021	33.0	7161	0.4507	0.8372
0.0127	34.0	7378	0.4390	0.8372
0.0158	35.0	7595	0.4566	0.8372
0.0178	36.0	7812	0.4594	0.8372
0.0109	37.0	8029	0.4570	0.8372
0.0096	38.0	8246	0.4635	0.8372
0.0113	39.0	8463	0.4700	0.8372
0.0149	40.0	8680	0.4815	0.8372
0.0111	41.0	8897	0.4769	0.8372
0.0075	42.0	9114	0.4756	0.8372
0.0093	43.0	9331	0.4800	0.8372
0.009	44.0	9548	0.4851	0.8372
0.0065	45.0	9765	0.4808	0.8372
0.011	46.0	9982	0.4835	0.8372
0.0064	47.0	10199	0.4871	0.8372
0.0093	48.0	10416	0.4902	0.8372
0.0136	49.0	10633	0.4899	0.8372
0.0058	50.0	10850	0.4899	0.8372

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_001_fold3

hushem_40x_deit_tiny_sgd_001_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
hushem_40x_deit_tiny_sgd_001_fold3