smids_3x_deit_base_sgd_001_fold1

hkivancoral/smids_3x_deit_base_sgd_001_fold1

smids_3x_deit_base_sgd_001_fold1 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

3% of all-time downloads

All-time downloads

196

Public

Repo size

16.1 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 11, 2023
Updated: Dec 11, 2023
SHA: 173c772b

Base models

facebook/deit-base-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

smids_3x_deit_base_sgd_001_fold1

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: 0.2890
Accuracy: 0.8881

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
1.0344	1.0	226	1.0573	0.3890
0.8639	2.0	452	0.8826	0.6477
0.7159	3.0	678	0.7365	0.7446
0.6314	4.0	904	0.6382	0.7679
0.597	5.0	1130	0.5681	0.7863
0.5391	6.0	1356	0.5171	0.8114
0.4375	7.0	1582	0.4782	0.8197
0.4581	8.0	1808	0.4491	0.8230
0.4008	9.0	2034	0.4274	0.8347
0.3889	10.0	2260	0.4080	0.8397
0.3787	11.0	2486	0.3914	0.8481
0.3295	12.0	2712	0.3805	0.8531
0.2853	13.0	2938	0.3695	0.8564
0.2978	14.0	3164	0.3604	0.8614
0.3683	15.0	3390	0.3519	0.8631
0.3241	16.0	3616	0.3458	0.8681
0.2768	17.0	3842	0.3403	0.8664
0.2702	18.0	4068	0.3347	0.8715
0.3185	19.0	4294	0.3297	0.8698
0.2447	20.0	4520	0.3262	0.8748
0.2875	21.0	4746	0.3219	0.8731
0.306	22.0	4972	0.3191	0.8765
0.3078	23.0	5198	0.3168	0.8765
0.3159	24.0	5424	0.3134	0.8781
0.2262	25.0	5650	0.3107	0.8815
0.3153	26.0	5876	0.3083	0.8815
0.237	27.0	6102	0.3073	0.8831
0.2672	28.0	6328	0.3044	0.8815
0.1997	29.0	6554	0.3037	0.8815
0.3208	30.0	6780	0.3027	0.8831
0.2656	31.0	7006	0.3004	0.8848
0.2803	32.0	7232	0.2988	0.8865
0.1992	33.0	7458	0.2984	0.8848
0.2153	34.0	7684	0.2965	0.8865
0.2588	35.0	7910	0.2955	0.8848
0.2121	36.0	8136	0.2953	0.8848
0.2496	37.0	8362	0.2940	0.8881
0.2614	38.0	8588	0.2931	0.8865
0.2271	39.0	8814	0.2926	0.8865
0.1865	40.0	9040	0.2917	0.8881
0.1777	41.0	9266	0.2916	0.8865
0.2413	42.0	9492	0.2907	0.8881
0.2247	43.0	9718	0.2903	0.8865
0.1658	44.0	9944	0.2899	0.8881
0.2589	45.0	10170	0.2898	0.8865
0.2258	46.0	10396	0.2894	0.8881
0.2122	47.0	10622	0.2892	0.8881
0.2435	48.0	10848	0.2891	0.8881
0.1811	49.0	11074	0.2890	0.8881
0.2047	50.0	11300	0.2890	0.8881

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 11, 2023
Updated: Dec 11, 2023