hushem_1x_deit_base_adamax_0001_fold1

hkivancoral/hushem_1x_deit_base_adamax_0001_fold1

hushem_1x_deit_base_adamax_0001_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

2% of all-time downloads

All-time downloads

453

Public

Parameters

85.8M

7.9 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors343 MB · 100%

At a glance

Task: Image Classification
Library: transformers
License: apache-2.0
Model type: vit
Access: Public
Created: Nov 15, 2023
Updated: Nov 15, 2023
SHA: 6593ca51

Base models

facebook/deit-base-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

hushem_1x_deit_base_adamax_0001_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: 1.0735
Accuracy: 0.7556

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	1.2850	0.3333
1.0598	2.0	12	0.9334	0.6889
1.0598	3.0	18	0.8053	0.7333
0.3175	4.0	24	0.8711	0.6444
0.0445	5.0	30	0.8608	0.7556
0.0445	6.0	36	0.7787	0.7778
0.0064	7.0	42	0.8229	0.7111
0.0064	8.0	48	0.9560	0.6667
0.0019	9.0	54	1.0123	0.7111
0.001	10.0	60	1.0574	0.7111
0.001	11.0	66	1.0683	0.7111
0.0007	12.0	72	1.0663	0.7111
0.0007	13.0	78	1.0586	0.7111
0.0005	14.0	84	1.0513	0.7333
0.0005	15.0	90	1.0471	0.7333
0.0005	16.0	96	1.0473	0.7333
0.0004	17.0	102	1.0477	0.7333
0.0004	18.0	108	1.0472	0.7333
0.0004	19.0	114	1.0473	0.7333
0.0004	20.0	120	1.0490	0.7556
0.0004	21.0	126	1.0517	0.7556
0.0004	22.0	132	1.0538	0.7556
0.0004	23.0	138	1.0557	0.7556
0.0003	24.0	144	1.0576	0.7556
0.0003	25.0	150	1.0597	0.7556
0.0003	26.0	156	1.0622	0.7556
0.0003	27.0	162	1.0623	0.7556
0.0003	28.0	168	1.0636	0.7556
0.0003	29.0	174	1.0651	0.7556
0.0003	30.0	180	1.0659	0.7556
0.0003	31.0	186	1.0671	0.7556
0.0003	32.0	192	1.0678	0.7556
0.0003	33.0	198	1.0692	0.7556
0.0003	34.0	204	1.0702	0.7556
0.0003	35.0	210	1.0706	0.7556
0.0003	36.0	216	1.0707	0.7556
0.0003	37.0	222	1.0711	0.7556
0.0003	38.0	228	1.0722	0.7556
0.0003	39.0	234	1.0729	0.7556
0.0003	40.0	240	1.0733	0.7556
0.0003	41.0	246	1.0735	0.7556
0.0003	42.0	252	1.0735	0.7556
0.0003	43.0	258	1.0735	0.7556
0.0003	44.0	264	1.0735	0.7556
0.0003	45.0	270	1.0735	0.7556
0.0003	46.0	276	1.0735	0.7556
0.0003	47.0	282	1.0735	0.7556
0.0003	48.0	288	1.0735	0.7556
0.0003	49.0	294	1.0735	0.7556
0.0003	50.0	300	1.0735	0.7556

Framework versions

Transformers 4.35.1
Pytorch 2.1.0+cu118
Datasets 2.14.7
Tokenizers 0.14.1

Task: Image Classification
Library: transformers
Type: vit
License: apache-2.0
Created: Nov 15, 2023
Updated: Nov 15, 2023