hushem_40x_deit_tiny_sgd_0001_fold4

hkivancoral/hushem_40x_deit_tiny_sgd_0001_fold4

hushem_40x_deit_tiny_sgd_0001_fold4 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

410

Public

Repo size

1.1 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin22.2 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: 1e48652d

Base models

facebook/deit-tiny-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

hushem_40x_deit_tiny_sgd_0001_fold4

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: 1.0643
Accuracy: 0.5952

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
1.4577	1.0	219	1.6228	0.1667
1.3428	2.0	438	1.5859	0.1429
1.3515	3.0	657	1.5534	0.1667
1.3164	4.0	876	1.5241	0.1905
1.262	5.0	1095	1.5001	0.1905
1.2747	6.0	1314	1.4781	0.1905
1.2005	7.0	1533	1.4587	0.1905
1.2174	8.0	1752	1.4397	0.2143
1.1711	9.0	1971	1.4197	0.2143
1.1443	10.0	2190	1.4007	0.2619
1.1123	11.0	2409	1.3821	0.2857
1.164	12.0	2628	1.3642	0.4048
1.0774	13.0	2847	1.3471	0.3810
1.1066	14.0	3066	1.3290	0.3810
1.055	15.0	3285	1.3135	0.4286
1.0496	16.0	3504	1.2984	0.4048
1.112	17.0	3723	1.2838	0.4286
1.0058	18.0	3942	1.2696	0.4286
1.0363	19.0	4161	1.2563	0.4286
1.0446	20.0	4380	1.2431	0.4286
1.0301	21.0	4599	1.2308	0.4286
1.0066	22.0	4818	1.2182	0.4524
0.9188	23.0	5037	1.2068	0.4524
0.9729	24.0	5256	1.1969	0.5238
0.9215	25.0	5475	1.1858	0.5238
0.9604	26.0	5694	1.1753	0.5476
0.9173	27.0	5913	1.1663	0.5714
0.9314	28.0	6132	1.1573	0.5714
0.8654	29.0	6351	1.1486	0.5714
0.9372	30.0	6570	1.1410	0.5714
0.9028	31.0	6789	1.1331	0.5714
0.9732	32.0	7008	1.1254	0.5714
0.9146	33.0	7227	1.1186	0.5714
0.8712	34.0	7446	1.1126	0.5714
0.8981	35.0	7665	1.1068	0.5714
0.8626	36.0	7884	1.1011	0.5714
0.884	37.0	8103	1.0956	0.5714
0.9119	38.0	8322	1.0906	0.5714
0.8378	39.0	8541	1.0862	0.5714
0.8095	40.0	8760	1.0823	0.5952
0.9067	41.0	8979	1.0785	0.5952
0.874	42.0	9198	1.0755	0.5714
0.8784	43.0	9417	1.0728	0.5714
0.8408	44.0	9636	1.0704	0.5714
0.8315	45.0	9855	1.0684	0.5714
0.8598	46.0	10074	1.0667	0.5714
0.8452	47.0	10293	1.0654	0.5952
0.863	48.0	10512	1.0647	0.5952
0.8292	49.0	10731	1.0643	0.5952
0.7869	50.0	10950	1.0643	0.5952

Framework versions

Transformers 4.32.1
Pytorch 2.1.1+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