hushem_1x_deit_tiny_sgd_00001_fold2

hkivancoral/hushem_1x_deit_tiny_sgd_00001_fold2

hushem_1x_deit_tiny_sgd_00001_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

12% of all-time downloads

All-time downloads

Public

Parameters

5.5M

664 MB 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 13, 2023
Updated: Nov 17, 2023
SHA: 1462a57f

Base models

facebook/deit-tiny-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

hushem_1x_deit_tiny_sgd_00001_fold2

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: 1.7073
Accuracy: 0.2222

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
No log	1.0	6	1.7237	0.2222
1.719	2.0	12	1.7228	0.2222
1.719	3.0	18	1.7220	0.2222
1.7128	4.0	24	1.7212	0.2222
1.7405	5.0	30	1.7204	0.2222
1.7405	6.0	36	1.7197	0.2222
1.6943	7.0	42	1.7190	0.2222
1.6943	8.0	48	1.7183	0.2222
1.6759	9.0	54	1.7176	0.2222
1.7158	10.0	60	1.7169	0.2222
1.7158	11.0	66	1.7162	0.2222
1.7024	12.0	72	1.7156	0.2222
1.7024	13.0	78	1.7150	0.2222
1.7744	14.0	84	1.7144	0.2222
1.7251	15.0	90	1.7139	0.2222
1.7251	16.0	96	1.7134	0.2222
1.6942	17.0	102	1.7129	0.2222
1.6942	18.0	108	1.7124	0.2222
1.7154	19.0	114	1.7120	0.2222
1.6829	20.0	120	1.7115	0.2222
1.6829	21.0	126	1.7111	0.2222
1.6559	22.0	132	1.7107	0.2222
1.6559	23.0	138	1.7104	0.2222
1.7194	24.0	144	1.7100	0.2222
1.6925	25.0	150	1.7097	0.2222
1.6925	26.0	156	1.7094	0.2222
1.6919	27.0	162	1.7091	0.2222
1.6919	28.0	168	1.7089	0.2222
1.6948	29.0	174	1.7086	0.2222
1.7059	30.0	180	1.7084	0.2222
1.7059	31.0	186	1.7082	0.2222
1.7337	32.0	192	1.7080	0.2222
1.7337	33.0	198	1.7079	0.2222
1.6587	34.0	204	1.7077	0.2222
1.7172	35.0	210	1.7076	0.2222
1.7172	36.0	216	1.7075	0.2222
1.7051	37.0	222	1.7075	0.2222
1.7051	38.0	228	1.7074	0.2222
1.6141	39.0	234	1.7074	0.2222
1.6784	40.0	240	1.7073	0.2222
1.6784	41.0	246	1.7073	0.2222
1.6991	42.0	252	1.7073	0.2222
1.6991	43.0	258	1.7073	0.2222
1.7247	44.0	264	1.7073	0.2222
1.6773	45.0	270	1.7073	0.2222
1.6773	46.0	276	1.7073	0.2222
1.6939	47.0	282	1.7073	0.2222
1.6939	48.0	288	1.7073	0.2222
1.6622	49.0	294	1.7073	0.2222
1.7192	50.0	300	1.7073	0.2222

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 13, 2023
Updated: Nov 17, 2023