smids_10x_deit_tiny_sgd_001_fold5

hkivancoral/smids_10x_deit_tiny_sgd_001_fold5

smids_10x_deit_tiny_sgd_001_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

1% of all-time downloads

All-time downloads

511

Public

Repo size

1.1 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin22.2 MB · 100%

At a glance

Task: Image Classification
Library: transformers
License: apache-2.0
Model type: vit
Access: Public
Created: Dec 22, 2023
Updated: Dec 22, 2023
SHA: 691a2c85

Base models

facebook/deit-tiny-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

smids_10x_deit_tiny_sgd_001_fold5

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

Loss: 0.2805
Accuracy: 0.88

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
0.5873	1.0	750	0.5427	0.8017
0.4134	2.0	1500	0.4078	0.8383
0.4003	3.0	2250	0.3567	0.8583
0.322	4.0	3000	0.3309	0.8733
0.3592	5.0	3750	0.3090	0.8767
0.2384	6.0	4500	0.3021	0.8717
0.2287	7.0	5250	0.2872	0.8833
0.2763	8.0	6000	0.2770	0.8883
0.301	9.0	6750	0.2801	0.89
0.2498	10.0	7500	0.2717	0.8933
0.2639	11.0	8250	0.2693	0.8967
0.2576	12.0	9000	0.2726	0.8967
0.2998	13.0	9750	0.2655	0.905
0.2222	14.0	10500	0.2676	0.8933
0.2757	15.0	11250	0.2607	0.8933
0.1644	16.0	12000	0.2662	0.91
0.2069	17.0	12750	0.2656	0.9033
0.2175	18.0	13500	0.2618	0.9067
0.2174	19.0	14250	0.2668	0.9
0.1626	20.0	15000	0.2708	0.8983
0.1772	21.0	15750	0.2632	0.9017
0.1739	22.0	16500	0.2644	0.9017
0.2129	23.0	17250	0.2644	0.8983
0.1768	24.0	18000	0.2642	0.8983
0.1436	25.0	18750	0.2692	0.8933
0.1864	26.0	19500	0.2647	0.8983
0.13	27.0	20250	0.2627	0.8967
0.1786	28.0	21000	0.2674	0.8967
0.1885	29.0	21750	0.2653	0.895
0.1896	30.0	22500	0.2757	0.8867
0.1887	31.0	23250	0.2629	0.8983
0.1377	32.0	24000	0.2703	0.89
0.1805	33.0	24750	0.2693	0.8917
0.1524	34.0	25500	0.2706	0.89
0.1113	35.0	26250	0.2737	0.8883
0.153	36.0	27000	0.2742	0.8867
0.1281	37.0	27750	0.2787	0.8817
0.112	38.0	28500	0.2764	0.885
0.1149	39.0	29250	0.2767	0.885
0.136	40.0	30000	0.2752	0.8833
0.1297	41.0	30750	0.2749	0.8867
0.1614	42.0	31500	0.2776	0.8833
0.1176	43.0	32250	0.2769	0.8817
0.1355	44.0	33000	0.2814	0.8817
0.1418	45.0	33750	0.2806	0.8833
0.1165	46.0	34500	0.2801	0.8817
0.1556	47.0	35250	0.2815	0.88
0.1322	48.0	36000	0.2803	0.8817
0.1369	49.0	36750	0.2803	0.8833
0.1026	50.0	37500	0.2805	0.88

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 22, 2023
Updated: Dec 22, 2023