hushem_40x_deit_base_sgd_001_fold2

hkivancoral/hushem_40x_deit_base_sgd_001_fold2

hushem_40x_deit_base_sgd_001_fold2 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

1% of all-time downloads

All-time downloads

205

Public

Repo size

11 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin343 MB · 100%

At a glance

Task: Image Classification
Library: transformers
License: apache-2.0
Model type: vit
Access: Public
Created: Dec 24, 2023
Updated: Dec 24, 2023
SHA: ba117af6

Base models

facebook/deit-base-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

hushem_40x_deit_base_sgd_001_fold2

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

Loss: 0.9714
Accuracy: 0.7111

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
1.2707	1.0	215	1.3448	0.3333
1.0768	2.0	430	1.2879	0.3333
0.9642	3.0	645	1.2312	0.3556
0.8173	4.0	860	1.1793	0.4222
0.7029	5.0	1075	1.1361	0.4889
0.6404	6.0	1290	1.1006	0.5111
0.5591	7.0	1505	1.0646	0.5778
0.4274	8.0	1720	1.0467	0.5778
0.3944	9.0	1935	1.0267	0.6444
0.3254	10.0	2150	1.0079	0.6222
0.2604	11.0	2365	0.9958	0.6222
0.2631	12.0	2580	0.9759	0.6222
0.2337	13.0	2795	0.9617	0.6
0.1789	14.0	3010	0.9588	0.6222
0.1879	15.0	3225	0.9460	0.6222
0.1684	16.0	3440	0.9372	0.6222
0.1577	17.0	3655	0.9384	0.6444
0.14	18.0	3870	0.9410	0.6444
0.1197	19.0	4085	0.9384	0.6444
0.1254	20.0	4300	0.9412	0.6444
0.1072	21.0	4515	0.9296	0.6444
0.0973	22.0	4730	0.9322	0.6444
0.0821	23.0	4945	0.9340	0.6444
0.0927	24.0	5160	0.9345	0.6667
0.0715	25.0	5375	0.9358	0.6667
0.0724	26.0	5590	0.9414	0.6889
0.0815	27.0	5805	0.9356	0.6667
0.0671	28.0	6020	0.9387	0.6889
0.053	29.0	6235	0.9438	0.6889
0.0671	30.0	6450	0.9381	0.7111
0.0428	31.0	6665	0.9431	0.7111
0.041	32.0	6880	0.9407	0.7111
0.0371	33.0	7095	0.9476	0.7111
0.0372	34.0	7310	0.9501	0.7111
0.0416	35.0	7525	0.9484	0.7111
0.0375	36.0	7740	0.9551	0.7111
0.0443	37.0	7955	0.9530	0.7111
0.031	38.0	8170	0.9549	0.7111
0.0359	39.0	8385	0.9537	0.7111
0.0327	40.0	8600	0.9553	0.7111
0.0313	41.0	8815	0.9602	0.7111
0.0312	42.0	9030	0.9634	0.7111
0.0302	43.0	9245	0.9659	0.7111
0.0284	44.0	9460	0.9687	0.7111
0.0286	45.0	9675	0.9696	0.7111
0.0307	46.0	9890	0.9699	0.7111
0.0251	47.0	10105	0.9708	0.7111
0.0291	48.0	10320	0.9714	0.7111
0.0372	49.0	10535	0.9713	0.7111
0.0296	50.0	10750	0.9714	0.7111

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2

Task: Image Classification
Library: transformers
Type: vit
License: apache-2.0
Created: Dec 24, 2023
Updated: Dec 24, 2023