smids_5x_deit_base_rms_001_fold1

hkivancoral/smids_5x_deit_base_rms_001_fold1

smids_5x_deit_base_rms_001_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

341

Public

Repo size

17.2 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin343 MB · 100%

At a glance

Task: Image Classification
Library: transformers
License: apache-2.0
Model type: vit
Access: Public
Created: Dec 17, 2023
Updated: Dec 17, 2023
SHA: 5ff93367

Base models

facebook/deit-base-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

smids_5x_deit_base_rms_001_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: 0.6839
Accuracy: 0.7863

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
1.1051	1.0	376	1.0840	0.3356
0.8654	2.0	752	0.8754	0.4841
0.7982	3.0	1128	0.7992	0.5843
0.8215	4.0	1504	0.8640	0.5509
0.8937	5.0	1880	0.7446	0.6678
0.7292	6.0	2256	0.7760	0.6361
0.6914	7.0	2632	0.7052	0.6694
0.6499	8.0	3008	0.7542	0.6511
0.6981	9.0	3384	0.6919	0.6912
0.6852	10.0	3760	0.6488	0.6995
0.5929	11.0	4136	0.6360	0.7162
0.6018	12.0	4512	0.6410	0.7212
0.578	13.0	4888	0.6824	0.7078
0.5646	14.0	5264	0.6123	0.7546
0.5813	15.0	5640	0.6611	0.7479
0.5334	16.0	6016	0.6911	0.7012
0.4401	17.0	6392	0.6234	0.7362
0.5629	18.0	6768	0.5782	0.7412
0.5062	19.0	7144	0.6504	0.7329
0.444	20.0	7520	0.5828	0.7696
0.4995	21.0	7896	0.5919	0.7446
0.4251	22.0	8272	0.6276	0.7629
0.4812	23.0	8648	0.6155	0.7462
0.4775	24.0	9024	0.6984	0.7179
0.4597	25.0	9400	0.6577	0.7295
0.4394	26.0	9776	0.5934	0.7429
0.4129	27.0	10152	0.6066	0.7563
0.4098	28.0	10528	0.5792	0.7579
0.4483	29.0	10904	0.5708	0.7613
0.3862	30.0	11280	0.5970	0.7679
0.4253	31.0	11656	0.6053	0.7546
0.4815	32.0	12032	0.5808	0.7479
0.3892	33.0	12408	0.5698	0.7613
0.35	34.0	12784	0.5670	0.7563
0.3952	35.0	13160	0.5921	0.7696
0.4191	36.0	13536	0.5999	0.7863
0.3174	37.0	13912	0.5845	0.7679
0.3864	38.0	14288	0.6529	0.7496
0.4036	39.0	14664	0.6327	0.7679
0.4274	40.0	15040	0.5923	0.7646
0.357	41.0	15416	0.6017	0.7863
0.348	42.0	15792	0.6309	0.7763
0.2967	43.0	16168	0.6418	0.7679
0.3292	44.0	16544	0.6405	0.7780
0.3428	45.0	16920	0.6600	0.7813
0.3127	46.0	17296	0.6429	0.7780
0.2979	47.0	17672	0.6618	0.7813
0.3209	48.0	18048	0.6803	0.7796
0.2866	49.0	18424	0.6856	0.7880
0.2611	50.0	18800	0.6839	0.7863

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2

Task: Image Classification
Library: transformers
Type: vit
License: apache-2.0
Created: Dec 17, 2023
Updated: Dec 17, 2023