rmsProp_VitB-p16-384-2e-4-batch_16_epoch_4_classes_24

ZaneHorrible/rmsProp_VitB-p16-384-2e-4-batch_16_epoch_4_classes_24

rmsProp_VitB-p16-384-2e-4-batch_16_epoch_4_classes_24 is a image classification model from ZaneHorrible. 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

631

Public

Parameters

86.1M

345 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors344 MB · 100%

At a glance

Task: Image Classification
Library: transformers
License: apache-2.0
Model type: vit
Access: Public
Created: May 15, 2024
Updated: May 15, 2024
SHA: f470137c

Base models

google/vit-base-patch16-384

Datasets

imagefolder

Model card

From the Hugging Face model README

rmsProp_VitB-p16-384-2e-4-batch_16_epoch_4_classes_24

This model is a fine-tuned version of google/vit-base-patch16-384 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.0544
Accuracy: 0.9856

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: 0.0002
train_batch_size: 16
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 2
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
3.0503	0.07	100	3.0273	0.0934
2.2522	0.14	200	2.4833	0.2328
1.5093	0.21	300	1.3361	0.5503
1.0645	0.28	400	1.0976	0.6580
0.5308	0.35	500	0.5680	0.8161
0.3545	0.42	600	0.3870	0.8664
0.2051	0.49	700	0.3348	0.9023
0.2241	0.56	800	0.1545	0.9411
0.2165	0.63	900	0.1722	0.9569
0.1589	0.7	1000	0.1554	0.9497
0.0647	0.77	1100	0.1400	0.9483
0.1178	0.84	1200	0.2000	0.9411
0.0518	0.91	1300	0.1856	0.9483
0.0433	0.97	1400	0.1573	0.9468
0.0228	1.04	1500	0.1156	0.9626
0.1261	1.11	1600	0.0628	0.9727
0.001	1.18	1700	0.0730	0.9770
0.0515	1.25	1800	0.1589	0.9468
0.0195	1.32	1900	0.1114	0.9641
0.0696	1.39	2000	0.1507	0.9555
0.0006	1.46	2100	0.0799	0.9741
0.0063	1.53	2200	0.0979	0.9684
0.0337	1.6	2300	0.1191	0.9598
0.0261	1.67	2400	0.0839	0.9727
0.001	1.74	2500	0.0911	0.9770
0.001	1.81	2600	0.0726	0.9799
0.0003	1.88	2700	0.0581	0.9842
0.0004	1.95	2800	0.0544	0.9856

Framework versions

Transformers 4.39.3
Pytorch 2.1.2
Datasets 2.18.0
Tokenizers 0.15.2

Task: Image Classification
Library: transformers
Type: vit
License: apache-2.0
Created: May 15, 2024
Updated: May 15, 2024