smids_3x_deit_base_sgd_001_fold5

hkivancoral/smids_3x_deit_base_sgd_001_fold5

smids_3x_deit_base_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

207

Public

Repo size

16.8 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: f5703fb7

Base models

facebook/deit-base-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

smids_3x_deit_base_sgd_001_fold5

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: 0.2858
Accuracy: 0.8733

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
0.9502	1.0	225	0.9617	0.575
0.7701	2.0	450	0.7420	0.7533
0.6098	3.0	675	0.5976	0.7833
0.477	4.0	900	0.5110	0.805
0.4263	5.0	1125	0.4583	0.82
0.414	6.0	1350	0.4227	0.8233
0.4045	7.0	1575	0.3990	0.8233
0.4145	8.0	1800	0.3808	0.8267
0.3701	9.0	2025	0.3676	0.8383
0.3094	10.0	2250	0.3582	0.845
0.3923	11.0	2475	0.3474	0.845
0.3461	12.0	2700	0.3427	0.8467
0.3684	13.0	2925	0.3332	0.8483
0.3232	14.0	3150	0.3290	0.8517
0.2418	15.0	3375	0.3249	0.855
0.2931	16.0	3600	0.3205	0.8517
0.2688	17.0	3825	0.3173	0.8533
0.3031	18.0	4050	0.3158	0.8567
0.2623	19.0	4275	0.3109	0.8517
0.298	20.0	4500	0.3083	0.8533
0.2399	21.0	4725	0.3072	0.8583
0.2519	22.0	4950	0.3035	0.8633
0.2394	23.0	5175	0.3028	0.86
0.254	24.0	5400	0.3011	0.8633
0.232	25.0	5625	0.3006	0.865
0.2794	26.0	5850	0.2984	0.865
0.2948	27.0	6075	0.2979	0.8633
0.2603	28.0	6300	0.2957	0.87
0.2519	29.0	6525	0.2949	0.8617
0.2151	30.0	6750	0.2933	0.8667
0.1937	31.0	6975	0.2918	0.8683
0.2408	32.0	7200	0.2919	0.87
0.2318	33.0	7425	0.2909	0.87
0.1908	34.0	7650	0.2902	0.8717
0.2103	35.0	7875	0.2898	0.87
0.2236	36.0	8100	0.2888	0.8717
0.2275	37.0	8325	0.2884	0.87
0.2349	38.0	8550	0.2885	0.87
0.1941	39.0	8775	0.2873	0.8683
0.2123	40.0	9000	0.2867	0.8667
0.2183	41.0	9225	0.2867	0.8683
0.2291	42.0	9450	0.2862	0.8667
0.2371	43.0	9675	0.2863	0.8717
0.2487	44.0	9900	0.2863	0.8717
0.2098	45.0	10125	0.2862	0.8717
0.2225	46.0	10350	0.2861	0.8733
0.2189	47.0	10575	0.2859	0.8733
0.2461	48.0	10800	0.2858	0.8733
0.2284	49.0	11025	0.2858	0.8733
0.236	50.0	11250	0.2858	0.8733

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