smids_5x_deit_base_sgd_0001_fold3

hkivancoral/smids_5x_deit_base_sgd_0001_fold3

smids_5x_deit_base_sgd_0001_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

1% of all-time downloads

All-time downloads

218

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: 83f8bb92

Base models

facebook/deit-base-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

smids_5x_deit_base_sgd_0001_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: 0.5127
Accuracy: 0.8183

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
1.086	1.0	375	1.0870	0.4083
1.0544	2.0	750	1.0666	0.4433
1.0309	3.0	1125	1.0448	0.48
0.9851	4.0	1500	1.0206	0.5333
0.9784	5.0	1875	0.9932	0.575
0.9454	6.0	2250	0.9632	0.6017
0.9054	7.0	2625	0.9323	0.6317
0.8859	8.0	3000	0.9017	0.6617
0.8212	9.0	3375	0.8722	0.675
0.846	10.0	3750	0.8441	0.69
0.7793	11.0	4125	0.8178	0.6967
0.7556	12.0	4500	0.7933	0.72
0.753	13.0	4875	0.7705	0.7333
0.7537	14.0	5250	0.7493	0.7433
0.7009	15.0	5625	0.7292	0.7517
0.6573	16.0	6000	0.7106	0.7517
0.6888	17.0	6375	0.6931	0.7583
0.6952	18.0	6750	0.6769	0.765
0.6154	19.0	7125	0.6622	0.7733
0.6418	20.0	7500	0.6487	0.7833
0.5745	21.0	7875	0.6362	0.7883
0.5966	22.0	8250	0.6248	0.7933
0.6053	23.0	8625	0.6144	0.7983
0.6111	24.0	9000	0.6047	0.8
0.5758	25.0	9375	0.5959	0.805
0.5916	26.0	9750	0.5876	0.8067
0.5804	27.0	10125	0.5800	0.81
0.5956	28.0	10500	0.5730	0.81
0.5266	29.0	10875	0.5666	0.81
0.5435	30.0	11250	0.5607	0.8117
0.566	31.0	11625	0.5553	0.8133
0.5691	32.0	12000	0.5503	0.8133
0.6036	33.0	12375	0.5456	0.815
0.5178	34.0	12750	0.5415	0.8133
0.4823	35.0	13125	0.5375	0.8167
0.4738	36.0	13500	0.5340	0.8183
0.5126	37.0	13875	0.5307	0.8183
0.4971	38.0	14250	0.5278	0.8183
0.5124	39.0	14625	0.5252	0.82
0.4766	40.0	15000	0.5229	0.82
0.4547	41.0	15375	0.5208	0.82
0.5009	42.0	15750	0.5190	0.82
0.5345	43.0	16125	0.5174	0.82
0.5032	44.0	16500	0.5161	0.8183
0.4932	45.0	16875	0.5150	0.8183
0.5003	46.0	17250	0.5141	0.8183
0.5538	47.0	17625	0.5134	0.8183
0.5053	48.0	18000	0.5130	0.8183
0.5053	49.0	18375	0.5128	0.8183
0.4871	50.0	18750	0.5127	0.8183

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