hushem_1x_deit_base_rms_0001_fold2

hkivancoral/hushem_1x_deit_base_rms_0001_fold2

hushem_1x_deit_base_rms_0001_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

16% of all-time downloads

All-time downloads

Public

Parameters

85.8M

5.5 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 16, 2023
Updated: Nov 16, 2023
SHA: ba6bb6ca

Base models

facebook/deit-base-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

hushem_1x_deit_base_rms_0001_fold2

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: 1.8638
Accuracy: 0.6889

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	1.6610	0.2444
1.7541	2.0	12	1.4002	0.2444
1.7541	3.0	18	1.4436	0.2444
1.433	4.0	24	1.3622	0.2667
1.5527	5.0	30	1.5226	0.2444
1.5527	6.0	36	2.8318	0.2444
1.3416	7.0	42	1.1724	0.4444
1.3416	8.0	48	1.1656	0.5556
1.0916	9.0	54	1.1372	0.5111
0.9299	10.0	60	0.9556	0.6222
0.9299	11.0	66	1.2879	0.6
0.4732	12.0	72	1.7343	0.5333
0.4732	13.0	78	1.6688	0.6
0.2619	14.0	84	1.4145	0.7333
0.0705	15.0	90	1.6863	0.6889
0.0705	16.0	96	1.7254	0.6889
0.0008	17.0	102	1.7545	0.6889
0.0008	18.0	108	1.7751	0.6889
0.0006	19.0	114	1.7893	0.6889
0.0004	20.0	120	1.7996	0.6889
0.0004	21.0	126	1.8083	0.6889
0.0003	22.0	132	1.8154	0.6889
0.0003	23.0	138	1.8216	0.6889
0.0003	24.0	144	1.8277	0.6889
0.0002	25.0	150	1.8323	0.6889
0.0002	26.0	156	1.8364	0.6889
0.0002	27.0	162	1.8404	0.6889
0.0002	28.0	168	1.8425	0.6889
0.0002	29.0	174	1.8460	0.6889
0.0002	30.0	180	1.8485	0.6889
0.0002	31.0	186	1.8508	0.6889
0.0002	32.0	192	1.8533	0.6889
0.0002	33.0	198	1.8549	0.6889
0.0002	34.0	204	1.8571	0.6889
0.0002	35.0	210	1.8584	0.6889
0.0002	36.0	216	1.8598	0.6889
0.0001	37.0	222	1.8611	0.6889
0.0001	38.0	228	1.8619	0.6889
0.0001	39.0	234	1.8627	0.6889
0.0001	40.0	240	1.8634	0.6889
0.0001	41.0	246	1.8637	0.6889
0.0001	42.0	252	1.8638	0.6889
0.0001	43.0	258	1.8638	0.6889
0.0001	44.0	264	1.8638	0.6889
0.0001	45.0	270	1.8638	0.6889
0.0001	46.0	276	1.8638	0.6889
0.0001	47.0	282	1.8638	0.6889
0.0001	48.0	288	1.8638	0.6889
0.0001	49.0	294	1.8638	0.6889
0.0001	50.0	300	1.8638	0.6889

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 16, 2023
Updated: Nov 16, 2023