hushem_5x_deit_tiny_sgd_00001_fold1

hkivancoral/hushem_5x_deit_tiny_sgd_00001_fold1

hushem_5x_deit_tiny_sgd_00001_fold1 is a image classification model from hkivancoral. Use it when you need a label for an image. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

32% of all-time downloads

All-time downloads

Public

Parameters

5.5M

1.1 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors22.1 MB · 100%

At a glance

Task: Image Classification
Library: transformers
License: apache-2.0
Model type: vit
Access: Public
Created: Nov 19, 2023
Updated: Nov 19, 2023
SHA: 177b8c10

Base models

facebook/deit-tiny-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

hushem_5x_deit_tiny_sgd_00001_fold1

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: 1.6463
Accuracy: 0.2889

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: 1e-05
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
1.5609	1.0	27	1.6799	0.2667
1.5496	2.0	54	1.6782	0.2667
1.5787	3.0	81	1.6767	0.2667
1.5647	4.0	108	1.6752	0.2667
1.5195	5.0	135	1.6738	0.2667
1.5668	6.0	162	1.6723	0.2667
1.5392	7.0	189	1.6709	0.2667
1.5582	8.0	216	1.6695	0.2667
1.5313	9.0	243	1.6682	0.2667
1.5128	10.0	270	1.6669	0.2667
1.5483	11.0	297	1.6658	0.2667
1.4916	12.0	324	1.6646	0.2667
1.5319	13.0	351	1.6635	0.2667
1.5642	14.0	378	1.6625	0.2667
1.5157	15.0	405	1.6614	0.2667
1.5547	16.0	432	1.6604	0.2667
1.561	17.0	459	1.6595	0.2667
1.5198	18.0	486	1.6585	0.2667
1.5162	19.0	513	1.6577	0.2667
1.501	20.0	540	1.6568	0.2667
1.536	21.0	567	1.6560	0.2667
1.5261	22.0	594	1.6552	0.2667
1.5076	23.0	621	1.6545	0.2667
1.5241	24.0	648	1.6538	0.2667
1.519	25.0	675	1.6531	0.2667
1.5215	26.0	702	1.6525	0.2667
1.4834	27.0	729	1.6518	0.2667
1.52	28.0	756	1.6513	0.2667
1.5201	29.0	783	1.6507	0.2667
1.5274	30.0	810	1.6502	0.2667
1.5272	31.0	837	1.6498	0.2667
1.5239	32.0	864	1.6493	0.2667
1.4813	33.0	891	1.6489	0.2667
1.5127	34.0	918	1.6485	0.2889
1.5315	35.0	945	1.6482	0.2889
1.4986	36.0	972	1.6479	0.2889
1.5458	37.0	999	1.6476	0.2889
1.5577	38.0	1026	1.6473	0.2889
1.5374	39.0	1053	1.6471	0.2889
1.4671	40.0	1080	1.6469	0.2889
1.5237	41.0	1107	1.6467	0.2889
1.4934	42.0	1134	1.6466	0.2889
1.5479	43.0	1161	1.6465	0.2889
1.5299	44.0	1188	1.6464	0.2889
1.5139	45.0	1215	1.6463	0.2889
1.4949	46.0	1242	1.6463	0.2889
1.5114	47.0	1269	1.6463	0.2889
1.5095	48.0	1296	1.6463	0.2889
1.514	49.0	1323	1.6463	0.2889
1.4915	50.0	1350	1.6463	0.2889

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0

Task: Image Classification
Library: transformers
Type: vit
License: apache-2.0
Created: Nov 19, 2023
Updated: Nov 19, 2023