This model is a fine-tuned version of facebook/deit-small-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.9274
Accuracy: 0.8781

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
0.7007	1.0	76	0.6595	0.7362
0.4949	2.0	152	0.4467	0.8247
0.3674	3.0	228	0.5673	0.7896
0.3934	4.0	304	0.3697	0.8598
0.2797	5.0	380	0.3646	0.8681
0.1743	6.0	456	0.5610	0.8314
0.205	7.0	532	0.4358	0.8514
0.1774	8.0	608	0.5386	0.8297
0.2157	9.0	684	0.6881	0.7863
0.1067	10.0	760	0.4110	0.8798
0.1404	11.0	836	0.5543	0.8514
0.0545	12.0	912	0.6338	0.8464
0.0886	13.0	988	0.5900	0.8531
0.0855	14.0	1064	0.6471	0.8447
0.0787	15.0	1140	0.5610	0.8648
0.0216	16.0	1216	0.7846	0.8664
0.0158	17.0	1292	0.9724	0.8614
0.0343	18.0	1368	0.8631	0.8481
0.0043	19.0	1444	0.7197	0.8765
0.0087	20.0	1520	0.6941	0.8748
0.0139	21.0	1596	0.8416	0.8514
0.005	22.0	1672	0.7895	0.8681
0.0003	23.0	1748	0.7713	0.8731
0.0251	24.0	1824	0.7771	0.8781
0.0091	25.0	1900	0.8505	0.8848
0.0036	26.0	1976	0.8475	0.8798
0.0054	27.0	2052	0.8606	0.8765
0.0027	28.0	2128	0.8615	0.8848
0.0048	29.0	2204	0.8705	0.8831
0.0	30.0	2280	0.8694	0.8798
0.0044	31.0	2356	0.8749	0.8815
0.0079	32.0	2432	0.8740	0.8815
0.0	33.0	2508	0.8806	0.8848
0.0	34.0	2584	0.8808	0.8815
0.0095	35.0	2660	0.8885	0.8831
0.0037	36.0	2736	0.8930	0.8798
0.0061	37.0	2812	0.9018	0.8831
0.0	38.0	2888	0.9039	0.8781
0.0029	39.0	2964	0.9042	0.8831
0.0	40.0	3040	0.9042	0.8781
0.0026	41.0	3116	0.9094	0.8831
0.0	42.0	3192	0.9098	0.8831
0.0045	43.0	3268	0.9154	0.8831
0.0	44.0	3344	0.9138	0.8781
0.0	45.0	3420	0.9190	0.8815
0.0	46.0	3496	0.9203	0.8798
0.0	47.0	3572	0.9235	0.8781
0.0026	48.0	3648	0.9263	0.8815
0.0	49.0	3724	0.9273	0.8781
0.0	50.0	3800	0.9274	0.8781

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0

hkivancoral/smids_1x_deit_small_adamax_001_fold1

smids_1x_deit_small_adamax_001_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_1x_deit_small_adamax_001_fold1