smids_5x_deit_base_sgd_001_fold1

hkivancoral/smids_5x_deit_base_sgd_001_fold1

smids_5x_deit_base_sgd_001_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

3% of all-time downloads

All-time downloads

321

Public

Repo size

17.5 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 17, 2023
Updated: Dec 17, 2023
SHA: 2d273e37

Base models

facebook/deit-base-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

smids_5x_deit_base_sgd_001_fold1

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: 0.2661
Accuracy: 0.8932

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
0.7985	1.0	376	0.8182	0.6978
0.594	2.0	752	0.5849	0.7746
0.4653	3.0	1128	0.4811	0.8197
0.4509	4.0	1504	0.4265	0.8264
0.406	5.0	1880	0.3929	0.8447
0.3758	6.0	2256	0.3696	0.8581
0.3147	7.0	2632	0.3531	0.8698
0.3421	8.0	3008	0.3417	0.8664
0.3606	9.0	3384	0.3307	0.8798
0.2866	10.0	3760	0.3222	0.8865
0.2912	11.0	4136	0.3153	0.8798
0.2629	12.0	4512	0.3094	0.8865
0.2464	13.0	4888	0.3048	0.8848
0.2413	14.0	5264	0.3005	0.8881
0.3125	15.0	5640	0.2955	0.8932
0.226	16.0	6016	0.2931	0.8865
0.2346	17.0	6392	0.2899	0.8915
0.2997	18.0	6768	0.2867	0.8881
0.2564	19.0	7144	0.2849	0.8898
0.1951	20.0	7520	0.2838	0.8898
0.2828	21.0	7896	0.2817	0.8898
0.2327	22.0	8272	0.2806	0.8898
0.2604	23.0	8648	0.2786	0.8865
0.2065	24.0	9024	0.2780	0.8881
0.2338	25.0	9400	0.2766	0.8881
0.2197	26.0	9776	0.2745	0.8898
0.1797	27.0	10152	0.2743	0.8898
0.199	28.0	10528	0.2732	0.8915
0.2002	29.0	10904	0.2724	0.8898
0.1586	30.0	11280	0.2714	0.8932
0.1861	31.0	11656	0.2710	0.8932
0.2539	32.0	12032	0.2706	0.8948
0.1906	33.0	12408	0.2700	0.8948
0.1642	34.0	12784	0.2697	0.8915
0.1856	35.0	13160	0.2694	0.8915
0.2084	36.0	13536	0.2691	0.8932
0.1812	37.0	13912	0.2681	0.8948
0.2073	38.0	14288	0.2680	0.8948
0.1854	39.0	14664	0.2677	0.8915
0.1953	40.0	15040	0.2671	0.8932
0.1912	41.0	15416	0.2672	0.8948
0.1646	42.0	15792	0.2669	0.8932
0.1689	43.0	16168	0.2666	0.8932
0.1894	44.0	16544	0.2664	0.8932
0.173	45.0	16920	0.2663	0.8932
0.2186	46.0	17296	0.2661	0.8932
0.1671	47.0	17672	0.2661	0.8932
0.1916	48.0	18048	0.2661	0.8932
0.1583	49.0	18424	0.2661	0.8932
0.137	50.0	18800	0.2661	0.8932

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 17, 2023
Updated: Dec 17, 2023