smids_5x_deit_base_rms_0001_fold5

hkivancoral/smids_5x_deit_base_rms_0001_fold5

smids_5x_deit_base_rms_0001_fold5 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

272

Public

Repo size

17.5 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 18, 2023
Updated: Dec 18, 2023
SHA: 1411e638

Base models

facebook/deit-base-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

smids_5x_deit_base_rms_0001_fold5

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: 0.9290
Accuracy: 0.915

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
0.2223	1.0	375	0.3109	0.8933
0.1256	2.0	750	0.3635	0.895
0.0772	3.0	1125	0.3333	0.905
0.0469	4.0	1500	0.4780	0.8867
0.0893	5.0	1875	0.6491	0.8683
0.0141	6.0	2250	0.5373	0.8983
0.0431	7.0	2625	0.4446	0.8933
0.0189	8.0	3000	0.5065	0.9067
0.0211	9.0	3375	0.4802	0.9133
0.0346	10.0	3750	0.5071	0.9033
0.0253	11.0	4125	0.6744	0.8983
0.0144	12.0	4500	0.6389	0.89
0.0096	13.0	4875	0.6130	0.905
0.0187	14.0	5250	0.6069	0.9083
0.103	15.0	5625	0.7299	0.8867
0.0003	16.0	6000	0.6047	0.9033
0.0078	17.0	6375	0.6867	0.8917
0.0106	18.0	6750	0.6759	0.8917
0.0326	19.0	7125	0.9578	0.8633
0.0231	20.0	7500	0.7260	0.8967
0.0327	21.0	7875	0.6167	0.9
0.0188	22.0	8250	0.6583	0.905
0.0002	23.0	8625	0.6038	0.9083
0.0276	24.0	9000	0.8452	0.8983
0.0002	25.0	9375	0.6542	0.9067
0.0045	26.0	9750	0.7924	0.905
0.0011	27.0	10125	0.9081	0.9017
0.0001	28.0	10500	0.6753	0.91
0.0001	29.0	10875	0.8443	0.8933
0.0026	30.0	11250	0.8554	0.9
0.0029	31.0	11625	1.0060	0.8983
0.0001	32.0	12000	0.7158	0.905
0.0113	33.0	12375	0.8641	0.9017
0.0	34.0	12750	0.7747	0.9067
0.0	35.0	13125	0.7089	0.925
0.0	36.0	13500	0.7594	0.9133
0.0184	37.0	13875	0.7578	0.915
0.0038	38.0	14250	0.7826	0.915
0.0	39.0	14625	0.7931	0.9183
0.0	40.0	15000	0.8433	0.91
0.0	41.0	15375	0.8317	0.9133
0.0	42.0	15750	0.8659	0.9133
0.0	43.0	16125	0.8765	0.9117
0.0	44.0	16500	0.9009	0.91
0.0	45.0	16875	0.9256	0.9133
0.0	46.0	17250	0.9323	0.915
0.003	47.0	17625	0.9213	0.915
0.0	48.0	18000	0.9276	0.915
0.0	49.0	18375	0.9299	0.915
0.0021	50.0	18750	0.9290	0.915

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 18, 2023
Updated: Dec 18, 2023