hushem_5x_deit_base_rms_001_fold3

hkivancoral/hushem_5x_deit_base_rms_001_fold3

hushem_5x_deit_base_rms_001_fold3 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

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: c1c5aec6

Base models

facebook/deit-base-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

hushem_5x_deit_base_rms_001_fold3

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: 4.1290
Accuracy: 0.5349

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
2.2595	1.0	28	2.7858	0.2558
1.4501	2.0	56	1.7856	0.2558
1.3782	3.0	84	1.3873	0.3721
1.2094	4.0	112	1.1943	0.3953
1.0231	5.0	140	1.6338	0.3023
1.0191	6.0	168	1.7056	0.2558
1.0547	7.0	196	1.1755	0.4884
1.0296	8.0	224	1.0491	0.5349
1.0202	9.0	252	2.3436	0.2791
1.0203	10.0	280	1.0971	0.4419
0.9795	11.0	308	1.0790	0.5581
0.955	12.0	336	1.4547	0.6047
0.9606	13.0	364	0.9445	0.6512
0.9236	14.0	392	1.2878	0.3721
0.9401	15.0	420	0.9664	0.4651
0.8825	16.0	448	0.9455	0.6512
0.8605	17.0	476	0.9844	0.6977
0.8738	18.0	504	1.1677	0.4651
0.8294	19.0	532	1.0462	0.6744
0.689	20.0	560	1.1927	0.6047
0.7976	21.0	588	1.0142	0.7209
0.741	22.0	616	0.7957	0.7907
0.7475	23.0	644	0.7104	0.7209
0.6791	24.0	672	1.7534	0.5349
0.6457	25.0	700	0.9601	0.6512
0.7254	26.0	728	1.1256	0.6279
0.6589	27.0	756	1.4604	0.5349
0.6888	28.0	784	0.8802	0.7209
0.6341	29.0	812	0.9513	0.7442
0.5815	30.0	840	1.2459	0.6047
0.5918	31.0	868	1.5991	0.5116
0.5623	32.0	896	1.5099	0.6279
0.5389	33.0	924	1.3552	0.6744
0.5523	34.0	952	1.5820	0.6279
0.5205	35.0	980	2.2601	0.4651
0.4888	36.0	1008	1.7684	0.5349
0.4363	37.0	1036	2.2769	0.5581
0.3724	38.0	1064	2.5879	0.5581
0.3349	39.0	1092	2.2241	0.5581
0.5052	40.0	1120	2.8178	0.4651
0.3018	41.0	1148	2.5305	0.5814
0.2857	42.0	1176	2.9348	0.5581
0.1485	43.0	1204	3.1875	0.5581
0.1386	44.0	1232	3.2594	0.6279
0.1242	45.0	1260	3.4524	0.5814
0.0734	46.0	1288	3.6284	0.5814
0.0218	47.0	1316	4.0538	0.5349
0.0226	48.0	1344	4.1281	0.5349
0.01	49.0	1372	4.1290	0.5349
0.0091	50.0	1400	4.1290	0.5349

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