smids_5x_deit_base_adamax_00001_fold1

hkivancoral/smids_5x_deit_base_adamax_00001_fold1

smids_5x_deit_base_adamax_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

3% of all-time downloads

All-time downloads

198

Public

Repo size

17.2 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: 01f667d7

Base models

facebook/deit-base-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

smids_5x_deit_base_adamax_00001_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: 0.5548
Accuracy: 0.9115

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
0.2913	1.0	376	0.3175	0.8815
0.197	2.0	752	0.2822	0.8865
0.1857	3.0	1128	0.2733	0.8915
0.0801	4.0	1504	0.2769	0.8965
0.062	5.0	1880	0.2932	0.9048
0.0559	6.0	2256	0.3199	0.9115
0.0331	7.0	2632	0.3568	0.9098
0.0024	8.0	3008	0.4098	0.8982
0.0164	9.0	3384	0.4359	0.9065
0.0004	10.0	3760	0.4455	0.9082
0.0127	11.0	4136	0.4881	0.9082
0.0001	12.0	4512	0.4919	0.9032
0.0001	13.0	4888	0.4968	0.9115
0.0037	14.0	5264	0.5278	0.9065
0.0001	15.0	5640	0.5316	0.9115
0.0001	16.0	6016	0.5363	0.9032
0.0001	17.0	6392	0.5212	0.9149
0.0001	18.0	6768	0.5353	0.9098
0.0	19.0	7144	0.5265	0.9098
0.0147	20.0	7520	0.5277	0.9115
0.0	21.0	7896	0.5565	0.9065
0.0	22.0	8272	0.5728	0.9098
0.0	23.0	8648	0.5461	0.9115
0.0	24.0	9024	0.5300	0.9065
0.0	25.0	9400	0.5373	0.9065
0.0042	26.0	9776	0.5315	0.9082
0.0	27.0	10152	0.5779	0.9065
0.0	28.0	10528	0.5457	0.9098
0.0079	29.0	10904	0.5511	0.9098
0.003	30.0	11280	0.5454	0.9048
0.0	31.0	11656	0.5479	0.9098
0.0	32.0	12032	0.5371	0.9082
0.0	33.0	12408	0.5701	0.9065
0.0	34.0	12784	0.5431	0.9032
0.0	35.0	13160	0.5470	0.9048
0.0	36.0	13536	0.5461	0.9015
0.0	37.0	13912	0.5481	0.9115
0.0	38.0	14288	0.5522	0.9098
0.0	39.0	14664	0.5539	0.9082
0.0	40.0	15040	0.5537	0.9115
0.0	41.0	15416	0.5471	0.9048
0.0	42.0	15792	0.5483	0.9115
0.0	43.0	16168	0.5497	0.9132
0.0	44.0	16544	0.5527	0.9115
0.0	45.0	16920	0.5532	0.9115
0.0053	46.0	17296	0.5512	0.9098
0.0	47.0	17672	0.5538	0.9115
0.0	48.0	18048	0.5539	0.9098
0.0	49.0	18424	0.5540	0.9115
0.0012	50.0	18800	0.5548	0.9115

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