hushem_5x_deit_base_rms_001_fold2

hkivancoral/hushem_5x_deit_base_rms_001_fold2

hushem_5x_deit_base_rms_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

121

Public

Parameters

85.8M

16.8 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 26, 2023
Updated: Nov 26, 2023
SHA: ffdf8d93

Base models

facebook/deit-base-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

hushem_5x_deit_base_rms_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: 2.4335
Accuracy: 0.5333

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
1.7708	1.0	27	1.4022	0.2444
1.4249	2.0	54	1.3804	0.4444
1.3964	3.0	81	1.3634	0.2667
1.4087	4.0	108	1.4138	0.2444
1.5106	5.0	135	1.3226	0.3333
1.5674	6.0	162	1.3745	0.2444
1.5358	7.0	189	1.3178	0.3778
1.3201	8.0	216	1.0950	0.4
1.624	9.0	243	1.3141	0.3111
1.1174	10.0	270	1.4549	0.3778
1.1475	11.0	297	0.9651	0.5778
1.0882	12.0	324	0.9475	0.5778
1.0589	13.0	351	1.0498	0.5111
1.0658	14.0	378	0.9947	0.5333
0.9897	15.0	405	0.9894	0.5333
0.9767	16.0	432	0.9550	0.5778
0.984	17.0	459	0.9380	0.5778
1.0081	18.0	486	1.0509	0.4889
0.8973	19.0	513	0.9732	0.4444
0.8473	20.0	540	1.0049	0.4444
0.7086	21.0	567	1.0847	0.4889
0.7379	22.0	594	1.4535	0.4889
0.7312	23.0	621	1.2763	0.5333
0.6995	24.0	648	1.1444	0.3778
0.6998	25.0	675	1.1643	0.3778
0.7046	26.0	702	1.3603	0.5333
0.6675	27.0	729	1.3027	0.6222
0.6228	28.0	756	1.2068	0.4222
0.5922	29.0	783	1.6511	0.5333
0.6546	30.0	810	1.2512	0.4
0.5393	31.0	837	1.4819	0.5333
0.6185	32.0	864	1.3700	0.5111
0.6184	33.0	891	1.5080	0.5556
0.5907	34.0	918	1.4939	0.4222
0.5753	35.0	945	1.4588	0.3556
0.5557	36.0	972	1.4314	0.5111
0.4886	37.0	999	1.8012	0.5556
0.4981	38.0	1026	1.7648	0.5333
0.4253	39.0	1053	1.7892	0.5556
0.3579	40.0	1080	2.2102	0.5111
0.4246	41.0	1107	1.6607	0.5556
0.3838	42.0	1134	2.0356	0.5333
0.3957	43.0	1161	2.0405	0.5111
0.3149	44.0	1188	2.1882	0.5333
0.3434	45.0	1215	2.2887	0.5333
0.2478	46.0	1242	2.3165	0.5556
0.2362	47.0	1269	2.4365	0.5333
0.2191	48.0	1296	2.4233	0.5333
0.1896	49.0	1323	2.4335	0.5333
0.2369	50.0	1350	2.4335	0.5333

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 26, 2023
Updated: Nov 26, 2023