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: 3.8348
Accuracy: 0.3333

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
1.8114	1.0	27	1.4619	0.2444
1.4983	2.0	54	1.4843	0.2444
1.4403	3.0	81	1.4156	0.2667
1.4435	4.0	108	1.5095	0.2667
1.2795	5.0	135	1.3446	0.3778
1.2205	6.0	162	1.1283	0.4222
1.2341	7.0	189	1.3172	0.4
1.155	8.0	216	1.3274	0.4222
1.0235	9.0	243	1.2899	0.3778
0.9879	10.0	270	1.2041	0.4444
1.0325	11.0	297	1.5730	0.3778
0.8868	12.0	324	1.2430	0.4
0.8741	13.0	351	1.6314	0.3778
0.8285	14.0	378	1.0662	0.4444
0.8157	15.0	405	1.2999	0.4
0.7186	16.0	432	1.5919	0.3778
0.7002	17.0	459	1.4465	0.3778
0.8279	18.0	486	1.8180	0.3556
0.6829	19.0	513	1.3642	0.4
0.667	20.0	540	1.9605	0.3556
0.5824	21.0	567	1.2514	0.4222
0.631	22.0	594	2.5624	0.3556
0.6153	23.0	621	1.7882	0.3778
0.5567	24.0	648	1.6537	0.3778
0.6329	25.0	675	1.9454	0.3556
0.6303	26.0	702	2.1679	0.3778
0.5312	27.0	729	1.9261	0.3778
0.4661	28.0	756	2.5489	0.3556
0.585	29.0	783	2.5635	0.3556
0.533	30.0	810	2.2939	0.3778
0.4346	31.0	837	2.1685	0.4
0.5403	32.0	864	2.2296	0.3778
0.4604	33.0	891	2.2806	0.3778
0.4901	34.0	918	2.7290	0.3556
0.378	35.0	945	2.3646	0.3556
0.3541	36.0	972	2.8569	0.3556
0.2793	37.0	999	2.5674	0.3778
0.3096	38.0	1026	3.0307	0.3778
0.1909	39.0	1053	2.9692	0.3778
0.2273	40.0	1080	2.9606	0.3778
0.1997	41.0	1107	2.9181	0.3111
0.1349	42.0	1134	3.0989	0.3333
0.1046	43.0	1161	3.2836	0.3778
0.0711	44.0	1188	3.7502	0.3556
0.0691	45.0	1215	3.7360	0.3333
0.037	46.0	1242	3.9008	0.3556
0.0363	47.0	1269	3.8159	0.3556
0.0263	48.0	1296	3.8260	0.3333
0.0176	49.0	1323	3.8348	0.3333
0.0375	50.0	1350	3.8348	0.3333

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0

hkivancoral/hushem_5x_deit_tiny_rms_001_fold1

hushem_5x_deit_tiny_rms_001_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
hushem_5x_deit_tiny_rms_001_fold1