smids_3x_deit_base_sgd_00001_fold2

hkivancoral/smids_3x_deit_base_sgd_00001_fold2

smids_3x_deit_base_sgd_00001_fold2 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

279

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 12, 2023
Updated: Dec 12, 2023
SHA: 67d3248d

Base models

facebook/deit-base-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

smids_3x_deit_base_sgd_00001_fold2

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: 1.0800
Accuracy: 0.3960

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: 1e-05
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
1.1076	1.0	225	1.1068	0.3378
1.1268	2.0	450	1.1056	0.3344
1.1054	3.0	675	1.1044	0.3378
1.1083	4.0	900	1.1032	0.3361
1.1053	5.0	1125	1.1021	0.3344
1.0996	6.0	1350	1.1010	0.3378
1.1167	7.0	1575	1.0999	0.3461
1.1117	8.0	1800	1.0989	0.3478
1.1001	9.0	2025	1.0979	0.3494
1.0985	10.0	2250	1.0970	0.3527
1.088	11.0	2475	1.0961	0.3561
1.1055	12.0	2700	1.0952	0.3594
1.1011	13.0	2925	1.0943	0.3661
1.0919	14.0	3150	1.0935	0.3727
1.097	15.0	3375	1.0927	0.3727
1.1083	16.0	3600	1.0919	0.3744
1.099	17.0	3825	1.0911	0.3727
1.0873	18.0	4050	1.0904	0.3710
1.0775	19.0	4275	1.0897	0.3694
1.1063	20.0	4500	1.0890	0.3677
1.0977	21.0	4725	1.0884	0.3710
1.0779	22.0	4950	1.0878	0.3727
1.0723	23.0	5175	1.0872	0.3694
1.0778	24.0	5400	1.0866	0.3727
1.0917	25.0	5625	1.0861	0.3727
1.0896	26.0	5850	1.0856	0.3744
1.0859	27.0	6075	1.0851	0.3760
1.0933	28.0	6300	1.0846	0.3760
1.0926	29.0	6525	1.0842	0.3794
1.0799	30.0	6750	1.0838	0.3810
1.0805	31.0	6975	1.0834	0.3827
1.078	32.0	7200	1.0830	0.3810
1.0795	33.0	7425	1.0827	0.3860
1.0907	34.0	7650	1.0823	0.3860
1.0893	35.0	7875	1.0820	0.3860
1.0658	36.0	8100	1.0818	0.3894
1.0887	37.0	8325	1.0815	0.3910
1.0779	38.0	8550	1.0813	0.3910
1.0768	39.0	8775	1.0810	0.3927
1.089	40.0	9000	1.0809	0.3927
1.0766	41.0	9225	1.0807	0.3927
1.0713	42.0	9450	1.0805	0.3927
1.0786	43.0	9675	1.0804	0.3927
1.0932	44.0	9900	1.0803	0.3927
1.0641	45.0	10125	1.0802	0.3943
1.0516	46.0	10350	1.0801	0.3943
1.0624	47.0	10575	1.0801	0.3960
1.0722	48.0	10800	1.0801	0.3960
1.0714	49.0	11025	1.0800	0.3960
1.0822	50.0	11250	1.0800	0.3960

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 12, 2023
Updated: Dec 12, 2023