smids_5x_deit_tiny_sgd_001_fold3

hkivancoral/smids_5x_deit_tiny_sgd_001_fold3

smids_5x_deit_tiny_sgd_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

1% of all-time downloads

All-time downloads

604

Public

Repo size

5.5 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin86.7 MB · 100%

At a glance

Task: Image Classification
Library: transformers
License: apache-2.0
Model type: vit
Access: Public
Created: Dec 15, 2023
Updated: Dec 18, 2023
SHA: 33d694f7

Base models

facebook/deit-small-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

smids_5x_deit_tiny_sgd_001_fold3

This model is a fine-tuned version of facebook/deit-small-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.2814
Accuracy: 0.9

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
0.7088	1.0	375	0.7565	0.725
0.5465	2.0	750	0.5503	0.8
0.3877	3.0	1125	0.4580	0.8417
0.403	4.0	1500	0.4113	0.86
0.4127	5.0	1875	0.3842	0.8633
0.3531	6.0	2250	0.3637	0.8717
0.3784	7.0	2625	0.3477	0.8717
0.3315	8.0	3000	0.3357	0.88
0.281	9.0	3375	0.3284	0.8817
0.2976	10.0	3750	0.3184	0.8783
0.2299	11.0	4125	0.3116	0.8817
0.2672	12.0	4500	0.3085	0.8867
0.268	13.0	4875	0.3033	0.89
0.2659	14.0	5250	0.3003	0.89
0.2573	15.0	5625	0.2955	0.885
0.2268	16.0	6000	0.2941	0.8917
0.2876	17.0	6375	0.2932	0.895
0.2734	18.0	6750	0.2907	0.8933
0.2415	19.0	7125	0.2883	0.8933
0.2097	20.0	7500	0.2877	0.895
0.1726	21.0	7875	0.2847	0.895
0.1753	22.0	8250	0.2862	0.8983
0.2074	23.0	8625	0.2848	0.9017
0.238	24.0	9000	0.2832	0.8983
0.2264	25.0	9375	0.2826	0.9017
0.2196	26.0	9750	0.2825	0.9017
0.1923	27.0	10125	0.2817	0.9017
0.2238	28.0	10500	0.2812	0.9033
0.1599	29.0	10875	0.2828	0.9
0.1957	30.0	11250	0.2818	0.9017
0.2026	31.0	11625	0.2804	0.905
0.2064	32.0	12000	0.2838	0.9
0.2244	33.0	12375	0.2835	0.9
0.17	34.0	12750	0.2797	0.8967
0.1503	35.0	13125	0.2806	0.9033
0.1857	36.0	13500	0.2802	0.9017
0.1698	37.0	13875	0.2813	0.9017
0.1679	38.0	14250	0.2797	0.9033
0.1579	39.0	14625	0.2818	0.9017
0.1487	40.0	15000	0.2812	0.9
0.1671	41.0	15375	0.2807	0.9
0.1398	42.0	15750	0.2815	0.9017
0.1981	43.0	16125	0.2800	0.9017
0.1508	44.0	16500	0.2816	0.9017
0.17	45.0	16875	0.2807	0.9
0.1582	46.0	17250	0.2810	0.9
0.197	47.0	17625	0.2812	0.9
0.1587	48.0	18000	0.2815	0.9017
0.1477	49.0	18375	0.2815	0.9
0.1575	50.0	18750	0.2814	0.9

Framework versions

Transformers 4.32.1
Pytorch 2.1.1+cu121
Datasets 2.12.0
Tokenizers 0.13.2

Task: Image Classification
Library: transformers
Type: vit
License: apache-2.0
Created: Dec 15, 2023
Updated: Dec 18, 2023