hushem_1x_deit_tiny_sgd_lr0001_fold4

hkivancoral/hushem_1x_deit_tiny_sgd_lr0001_fold4

hushem_1x_deit_tiny_sgd_lr0001_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

10% 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 10, 2023
Updated: Nov 10, 2023
SHA: 5ad952be

Base models

facebook/deit-tiny-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

hushem_1x_deit_tiny_sgd_lr0001_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: 1.4980
Accuracy: 0.1667

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
No log	1.0	6	1.5601	0.1905
1.6045	2.0	12	1.5566	0.1905
1.6045	3.0	18	1.5532	0.1905
1.6142	4.0	24	1.5500	0.1905
1.6266	5.0	30	1.5471	0.1905
1.6266	6.0	36	1.5442	0.1905
1.6101	7.0	42	1.5414	0.1905
1.6101	8.0	48	1.5385	0.1905
1.6089	9.0	54	1.5358	0.1905
1.5908	10.0	60	1.5333	0.1905
1.5908	11.0	66	1.5308	0.1905
1.5657	12.0	72	1.5284	0.1905
1.5657	13.0	78	1.5261	0.1905
1.6049	14.0	84	1.5240	0.1905
1.5586	15.0	90	1.5222	0.1905
1.5586	16.0	96	1.5201	0.1905
1.5639	17.0	102	1.5182	0.1905
1.5639	18.0	108	1.5166	0.1905
1.5536	19.0	114	1.5151	0.1905
1.5821	20.0	120	1.5136	0.1905
1.5821	21.0	126	1.5122	0.1905
1.5341	22.0	132	1.5109	0.1905
1.5341	23.0	138	1.5096	0.1905
1.6078	24.0	144	1.5084	0.1905
1.5121	25.0	150	1.5073	0.1905
1.5121	26.0	156	1.5061	0.1905
1.5521	27.0	162	1.5050	0.1905
1.5521	28.0	168	1.5041	0.1905
1.5505	29.0	174	1.5033	0.1905
1.5712	30.0	180	1.5025	0.1905
1.5712	31.0	186	1.5017	0.1905
1.5865	32.0	192	1.5010	0.1905
1.5865	33.0	198	1.5005	0.1905
1.4766	34.0	204	1.4999	0.1905
1.5501	35.0	210	1.4994	0.1905
1.5501	36.0	216	1.4990	0.1905
1.5465	37.0	222	1.4987	0.1667
1.5465	38.0	228	1.4984	0.1667
1.5254	39.0	234	1.4982	0.1667
1.575	40.0	240	1.4980	0.1667
1.575	41.0	246	1.4980	0.1667
1.5455	42.0	252	1.4980	0.1667
1.5455	43.0	258	1.4980	0.1667
1.5648	44.0	264	1.4980	0.1667
1.5279	45.0	270	1.4980	0.1667
1.5279	46.0	276	1.4980	0.1667
1.5492	47.0	282	1.4980	0.1667
1.5492	48.0	288	1.4980	0.1667
1.5479	49.0	294	1.4980	0.1667
1.5321	50.0	300	1.4980	0.1667

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1

Task: Image Classification
Library: transformers
Type: vit
License: apache-2.0
Created: Nov 10, 2023
Updated: Nov 10, 2023