vit-base-patch16-224-Trial006-007-008-YEL_STEM1

sbaner24/vit-base-patch16-224-Trial006-007-008-YEL_STEM1

vit-base-patch16-224-Trial006-007-008-YEL_STEM1 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

2% of all-time downloads

All-time downloads

243

Public

Repo size

31.9 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: 4d6f14c8

Datasets

imagefolder

Model card

From the Hugging Face model README

vit-base-patch16-224-Trial006-007-008-YEL_STEM1

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: 0.0457
Accuracy: 0.9912

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
0.7163	0.89	4	0.7036	0.5175
0.7183	2.0	9	0.6982	0.5439
0.6561	2.89	13	0.5914	0.6667
0.5799	4.0	18	0.6411	0.5526
0.5731	4.89	22	0.4833	0.8158
0.5162	6.0	27	0.4483	0.7807
0.4738	6.89	31	0.3961	0.8596
0.3283	8.0	36	0.2897	0.8772
0.3365	8.89	40	0.2774	0.8860
0.5987	10.0	45	0.2617	0.8947
0.3633	10.89	49	0.2661	0.8772
0.3342	12.0	54	0.2269	0.9211
0.3406	12.89	58	0.1903	0.9211
0.2331	14.0	63	0.2075	0.9123
0.2494	14.89	67	0.1345	0.9474
0.3143	16.0	72	0.1508	0.9298
0.2622	16.89	76	0.1267	0.9298
0.2894	18.0	81	0.0921	0.9737
0.2105	18.89	85	0.1058	0.9298
0.2011	20.0	90	0.1021	0.9561
0.1977	20.89	94	0.1122	0.9561
0.2685	22.0	99	0.1656	0.9298
0.2394	22.89	103	0.1197	0.9561
0.2394	24.0	108	0.1461	0.9211
0.1523	24.89	112	0.0969	0.9649
0.2231	26.0	117	0.0827	0.9649
0.1887	26.89	121	0.0979	0.9561
0.1656	28.0	126	0.0907	0.9386
0.1824	28.89	130	0.1009	0.9561
0.2443	30.0	135	0.1249	0.9474
0.2082	30.89	139	0.0755	0.9649
0.1276	32.0	144	0.0531	0.9825
0.1857	32.89	148	0.0707	0.9561
0.1676	34.0	153	0.0570	0.9825
0.1992	34.89	157	0.0591	0.9737
0.2283	36.0	162	0.0575	0.9737
0.2125	36.89	166	0.0519	0.9825
0.1915	38.0	171	0.0457	0.9912
0.1969	38.89	175	0.0644	0.9561
0.1522	40.0	180	0.0771	0.9561
0.1037	40.89	184	0.0557	0.9561
0.2348	42.0	189	0.0470	0.9737
0.1674	42.89	193	0.0469	0.9737
0.0874	44.0	198	0.0483	0.9737
0.1605	44.44	200	0.0485	0.9649

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