smids_5x_deit_base_sgd_00001_fold2

hkivancoral/smids_5x_deit_base_sgd_00001_fold2

smids_5x_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

2% of all-time downloads

All-time downloads

354

Public

Repo size

34.7 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 17, 2023
Updated: Dec 17, 2023
SHA: eb16d11b

Base models

facebook/deit-base-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

smids_5x_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: 1.0641
Accuracy: 0.4459

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
1.1035	1.0	375	1.1062	0.3344
1.1126	2.0	750	1.1043	0.3344
1.104	3.0	1125	1.1024	0.3344
1.1172	4.0	1500	1.1007	0.3428
1.1218	5.0	1875	1.0990	0.3494
1.103	6.0	2250	1.0973	0.3544
1.0899	7.0	2625	1.0957	0.3594
1.1072	8.0	3000	1.0942	0.3661
1.0922	9.0	3375	1.0926	0.3744
1.0843	10.0	3750	1.0912	0.3727
1.081	11.0	4125	1.0898	0.3710
1.0891	12.0	4500	1.0884	0.3760
1.0709	13.0	4875	1.0871	0.3777
1.0708	14.0	5250	1.0858	0.3827
1.0647	15.0	5625	1.0846	0.3827
1.0675	16.0	6000	1.0834	0.3877
1.0777	17.0	6375	1.0822	0.3927
1.1021	18.0	6750	1.0811	0.3943
1.075	19.0	7125	1.0800	0.3993
1.08	20.0	7500	1.0789	0.3977
1.0665	21.0	7875	1.0779	0.4010
1.0636	22.0	8250	1.0769	0.4010
1.0724	23.0	8625	1.0760	0.4043
1.075	24.0	9000	1.0751	0.4093
1.0668	25.0	9375	1.0742	0.4077
1.0648	26.0	9750	1.0734	0.4160
1.0792	27.0	10125	1.0726	0.4176
1.068	28.0	10500	1.0718	0.4160
1.0536	29.0	10875	1.0711	0.4160
1.0571	30.0	11250	1.0704	0.4193
1.055	31.0	11625	1.0698	0.4226
1.0604	32.0	12000	1.0691	0.4226
1.0502	33.0	12375	1.0686	0.4260
1.0518	34.0	12750	1.0680	0.4243
1.0472	35.0	13125	1.0675	0.4276
1.0642	36.0	13500	1.0670	0.4309
1.052	37.0	13875	1.0666	0.4309
1.0617	38.0	14250	1.0662	0.4309
1.0473	39.0	14625	1.0658	0.4359
1.0678	40.0	15000	1.0655	0.4393
1.0397	41.0	15375	1.0652	0.4393
1.0482	42.0	15750	1.0650	0.4393
1.0333	43.0	16125	1.0647	0.4393
1.0512	44.0	16500	1.0645	0.4409
1.0593	45.0	16875	1.0644	0.4409
1.0581	46.0	17250	1.0643	0.4409
1.043	47.0	17625	1.0642	0.4426
1.0454	48.0	18000	1.0641	0.4443
1.0474	49.0	18375	1.0641	0.4459
1.0427	50.0	18750	1.0641	0.4459

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 17, 2023
Updated: Dec 17, 2023