smids_3x_deit_tiny_sgd_0001_fold5

hkivancoral/smids_3x_deit_tiny_sgd_0001_fold5

smids_3x_deit_tiny_sgd_0001_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

2% of all-time downloads

All-time downloads

475

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 12, 2023
Updated: Dec 12, 2023
SHA: 89870660

Base models

facebook/deit-tiny-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

smids_3x_deit_tiny_sgd_0001_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: 0.5739
Accuracy: 0.775

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: 0.0001
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
1.1702	1.0	225	1.1979	0.3733
1.1054	2.0	450	1.1279	0.4033
1.0995	3.0	675	1.0911	0.4167
1.0744	4.0	900	1.0627	0.4367
1.0062	5.0	1125	1.0378	0.45
1.0305	6.0	1350	1.0143	0.4633
1.0048	7.0	1575	0.9914	0.4917
0.9977	8.0	1800	0.9686	0.515
0.8819	9.0	2025	0.9464	0.5283
0.899	10.0	2250	0.9249	0.5517
0.8919	11.0	2475	0.9036	0.5633
0.887	12.0	2700	0.8832	0.5833
0.8706	13.0	2925	0.8626	0.5983
0.8705	14.0	3150	0.8429	0.6117
0.7649	15.0	3375	0.8245	0.6267
0.8058	16.0	3600	0.8064	0.6383
0.7948	17.0	3825	0.7895	0.6517
0.7127	18.0	4050	0.7738	0.66
0.7637	19.0	4275	0.7581	0.665
0.7239	20.0	4500	0.7434	0.6717
0.7375	21.0	4725	0.7293	0.685
0.7685	22.0	4950	0.7159	0.6917
0.7357	23.0	5175	0.7032	0.7
0.7155	24.0	5400	0.6916	0.7067
0.6674	25.0	5625	0.6809	0.7133
0.6906	26.0	5850	0.6707	0.7183
0.7171	27.0	6075	0.6612	0.725
0.6365	28.0	6300	0.6523	0.725
0.6614	29.0	6525	0.6441	0.73
0.6178	30.0	6750	0.6364	0.7367
0.6066	31.0	6975	0.6295	0.7417
0.6191	32.0	7200	0.6230	0.7467
0.6396	33.0	7425	0.6169	0.7533
0.5735	34.0	7650	0.6116	0.76
0.6004	35.0	7875	0.6067	0.76
0.61	36.0	8100	0.6022	0.7633
0.6	37.0	8325	0.5980	0.765
0.6039	38.0	8550	0.5941	0.7683
0.5538	39.0	8775	0.5906	0.7667
0.5453	40.0	9000	0.5875	0.77
0.603	41.0	9225	0.5848	0.77
0.606	42.0	9450	0.5825	0.7733
0.5852	43.0	9675	0.5804	0.7733
0.6705	44.0	9900	0.5786	0.7733
0.6134	45.0	10125	0.5771	0.7733
0.5569	46.0	10350	0.5759	0.7733
0.6464	47.0	10575	0.5750	0.7733
0.605	48.0	10800	0.5744	0.775
0.5703	49.0	11025	0.5740	0.775
0.5837	50.0	11250	0.5739	0.775

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 12, 2023
Updated: Dec 12, 2023