hushem_5x_deit_base_adamax_001_fold2

hkivancoral/hushem_5x_deit_base_adamax_001_fold2

hushem_5x_deit_base_adamax_001_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

4% of all-time downloads

All-time downloads

117

Public

Parameters

85.8M

16.5 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: 8edfc2cd

Base models

facebook/deit-base-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

hushem_5x_deit_base_adamax_001_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: 5.7416
Accuracy: 0.4889

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: 0.001
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
1.4053	1.0	27	1.3685	0.3111
1.3925	2.0	54	3.6868	0.2889
1.2318	3.0	81	1.5265	0.3333
1.1218	4.0	108	1.3720	0.3778
0.9389	5.0	135	1.3538	0.4444
0.8792	6.0	162	1.1885	0.4444
0.8387	7.0	189	1.3407	0.4889
0.7915	8.0	216	1.2361	0.4222
0.79	9.0	243	1.2485	0.4667
0.7076	10.0	270	1.6183	0.5333
0.6051	11.0	297	1.7700	0.4889
0.5603	12.0	324	1.7918	0.3556
0.6144	13.0	351	2.1767	0.5556
0.5279	14.0	378	1.6851	0.3778
0.3562	15.0	405	2.1689	0.4444
0.3897	16.0	432	2.2755	0.4667
0.4523	17.0	459	2.3235	0.4222
0.5055	18.0	486	2.6282	0.5556
0.2707	19.0	513	2.3398	0.5333
0.4827	20.0	540	2.5025	0.5111
0.2449	21.0	567	2.2455	0.4667
0.3199	22.0	594	3.8583	0.5333
0.2715	23.0	621	2.9016	0.5556
0.2241	24.0	648	2.9266	0.4444
0.1264	25.0	675	3.0321	0.4222
0.1028	26.0	702	3.8439	0.5778
0.2082	27.0	729	3.7749	0.5333
0.2344	28.0	756	3.4616	0.5333
0.0842	29.0	783	3.5970	0.5111
0.0483	30.0	810	4.3955	0.5111
0.1454	31.0	837	3.9120	0.5556
0.0972	32.0	864	3.9463	0.4889
0.014	33.0	891	4.4955	0.4889
0.0007	34.0	918	5.1958	0.5111
0.0273	35.0	945	5.0022	0.4889
0.0071	36.0	972	4.9340	0.5333
0.0003	37.0	999	5.2310	0.4889
0.0004	38.0	1026	5.5820	0.4889
0.0001	39.0	1053	5.6491	0.4889
0.0001	40.0	1080	5.6867	0.4889
0.0001	41.0	1107	5.7009	0.4889
0.0001	42.0	1134	5.7115	0.4889
0.0	43.0	1161	5.7213	0.4889
0.0001	44.0	1188	5.7289	0.4889
0.0001	45.0	1215	5.7342	0.4889
0.0	46.0	1242	5.7384	0.4889
0.0	47.0	1269	5.7406	0.4889
0.0	48.0	1296	5.7416	0.4889
0.0001	49.0	1323	5.7416	0.4889
0.0	50.0	1350	5.7416	0.4889

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