vit-base-patch16-224-Trial006-007-008-YEL_STEM2

sbaner24/vit-base-patch16-224-Trial006-007-008-YEL_STEM2

vit-base-patch16-224-Trial006-007-008-YEL_STEM2 is a image classification model from sbaner24. 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

262

Public

Repo size

33.3 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: Jul 12, 2023
Updated: Nov 14, 2023
SHA: 3b59c73c

Datasets

imagefolder

Model card

From the Hugging Face model README

vit-base-patch16-224-Trial006-007-008-YEL_STEM2

This model is a fine-tuned version of google/vit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.0188
Accuracy: 1.0

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: 5e-05
train_batch_size: 60
eval_batch_size: 60
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 240
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
0.7014	0.94	4	0.6789	0.5872
0.6242	1.88	8	0.6182	0.6147
0.5903	2.82	12	0.5147	0.8165
0.516	4.0	17	0.4137	0.8440
0.4612	4.94	21	0.3127	0.8899
0.3615	5.88	25	0.2448	0.8899
0.2899	6.82	29	0.2502	0.9083
0.3271	8.0	34	0.2268	0.8899
0.3765	8.94	38	0.1419	0.9266
0.2954	9.88	42	0.1233	0.9450
0.2187	10.82	46	0.1541	0.9358
0.3391	12.0	51	0.1575	0.9266
0.2027	12.94	55	0.0838	0.9908
0.2894	13.88	59	0.0852	0.9633
0.1972	14.82	63	0.0648	0.9908
0.1533	16.0	68	0.0884	0.9908
0.1588	16.94	72	0.0951	0.9633
0.1746	17.88	76	0.0793	0.9725
0.2386	18.82	80	0.1204	0.9633
0.1226	20.0	85	0.0502	0.9633
0.1901	20.94	89	0.0188	1.0
0.1305	21.88	93	0.0244	0.9908
0.1695	22.82	97	0.0186	1.0
0.2682	24.0	102	0.0460	0.9817
0.1956	24.94	106	0.0328	0.9817
0.1651	25.88	110	0.0493	0.9817
0.1841	26.82	114	0.0168	1.0
0.1897	28.0	119	0.0139	1.0
0.2088	28.94	123	0.0195	1.0
0.1386	29.88	127	0.0483	0.9817
0.1544	30.82	131	0.0258	0.9817
0.1293	32.0	136	0.0461	0.9725
0.1696	32.94	140	0.0207	0.9908
0.1793	33.88	144	0.0182	1.0
0.1545	34.82	148	0.0361	0.9817
0.141	36.0	153	0.0455	0.9817
0.138	36.94	157	0.0175	0.9908
0.1382	37.88	161	0.0359	0.9817
0.163	38.82	165	0.0463	0.9817
0.1374	40.0	170	0.0153	0.9908
0.1993	40.94	174	0.0116	1.0
0.1471	41.88	178	0.0199	0.9817
0.1414	42.82	182	0.0330	0.9817
0.1494	44.0	187	0.0228	0.9817
0.1367	44.94	191	0.0174	0.9817
0.1529	45.88	195	0.0162	0.9817
0.1365	46.82	199	0.0153	0.9908
0.1301	47.06	200	0.0152	0.9908

Framework versions

Transformers 4.30.0.dev0
Pytorch 1.12.1
Datasets 2.12.0
Tokenizers 0.13.1

Task: Image Classification
Library: transformers
Type: vit
License: apache-2.0
Created: Jul 12, 2023
Updated: Nov 14, 2023