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: 1.5542
Accuracy: 0.2

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: 0.0001
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
1.5719	1.0	27	1.7092	0.2222
1.5311	2.0	54	1.6949	0.2222
1.5151	3.0	81	1.6819	0.2222
1.5077	4.0	108	1.6712	0.2222
1.4707	5.0	135	1.6610	0.2222
1.4799	6.0	162	1.6507	0.2222
1.4704	7.0	189	1.6424	0.2
1.4902	8.0	216	1.6346	0.1778
1.4446	9.0	243	1.6280	0.1778
1.4231	10.0	270	1.6212	0.1778
1.4616	11.0	297	1.6153	0.1778
1.4153	12.0	324	1.6101	0.2
1.4152	13.0	351	1.6055	0.2
1.4531	14.0	378	1.6010	0.2
1.3945	15.0	405	1.5968	0.2
1.3852	16.0	432	1.5928	0.2
1.4109	17.0	459	1.5893	0.2
1.3754	18.0	486	1.5859	0.2
1.385	19.0	513	1.5829	0.2222
1.3607	20.0	540	1.5802	0.2222
1.3947	21.0	567	1.5776	0.2222
1.3764	22.0	594	1.5751	0.2222
1.382	23.0	621	1.5731	0.2222
1.3634	24.0	648	1.5711	0.2222
1.3778	25.0	675	1.5692	0.2222
1.3529	26.0	702	1.5678	0.2222
1.3485	27.0	729	1.5662	0.2222
1.3484	28.0	756	1.5647	0.2222
1.3554	29.0	783	1.5635	0.2222
1.3405	30.0	810	1.5624	0.2222
1.3634	31.0	837	1.5613	0.2222
1.3616	32.0	864	1.5602	0.2222
1.3289	33.0	891	1.5595	0.2222
1.3193	34.0	918	1.5588	0.2
1.3621	35.0	945	1.5580	0.2
1.3672	36.0	972	1.5575	0.2
1.3338	37.0	999	1.5569	0.2
1.3491	38.0	1026	1.5563	0.2
1.3543	39.0	1053	1.5559	0.2
1.3395	40.0	1080	1.5555	0.2
1.3385	41.0	1107	1.5553	0.2
1.3225	42.0	1134	1.5550	0.2
1.3557	43.0	1161	1.5547	0.2
1.3413	44.0	1188	1.5546	0.2
1.3386	45.0	1215	1.5544	0.2
1.3204	46.0	1242	1.5543	0.2
1.335	47.0	1269	1.5543	0.2
1.3373	48.0	1296	1.5542	0.2
1.3715	49.0	1323	1.5542	0.2
1.2935	50.0	1350	1.5542	0.2

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0

hkivancoral/hushem_5x_deit_tiny_sgd_0001_fold2

hushem_5x_deit_tiny_sgd_0001_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
hushem_5x_deit_tiny_sgd_0001_fold2