smids_1x_deit_tiny_adamax_0001_fold3

hkivancoral/smids_1x_deit_tiny_adamax_0001_fold3

smids_1x_deit_tiny_adamax_0001_fold3 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

3% of all-time downloads

All-time downloads

578

Public

Parameters

5.5M

1.8 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors22.1 MB · 99%

At a glance

Task: Image Classification
Library: transformers
License: apache-2.0
Model type: vit
Access: Public
Created: Dec 5, 2023
Updated: Dec 5, 2023
SHA: 87f79362

Base models

facebook/deit-tiny-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

smids_1x_deit_tiny_adamax_0001_fold3

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: 0.7938
Accuracy: 0.8883

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
0.3497	1.0	75	0.3438	0.8583
0.2686	2.0	150	0.4010	0.835
0.2132	3.0	225	0.3099	0.895
0.1475	4.0	300	0.4693	0.8433
0.07	5.0	375	0.3951	0.8967
0.0348	6.0	450	0.4706	0.8833
0.1076	7.0	525	0.4897	0.8817
0.0371	8.0	600	0.5659	0.8817
0.0539	9.0	675	0.5525	0.8917
0.0289	10.0	750	0.6768	0.8783
0.053	11.0	825	0.5526	0.9017
0.0394	12.0	900	0.6804	0.8867
0.0028	13.0	975	0.6916	0.8717
0.0003	14.0	1050	0.6282	0.8983
0.0001	15.0	1125	0.6544	0.8883
0.0001	16.0	1200	0.6284	0.9
0.0001	17.0	1275	0.6590	0.89
0.0087	18.0	1350	0.7168	0.885
0.0041	19.0	1425	0.6749	0.8933
0.0108	20.0	1500	0.7413	0.885
0.0001	21.0	1575	0.6857	0.8867
0.0	22.0	1650	0.7103	0.8833
0.0055	23.0	1725	0.7459	0.8883
0.0	24.0	1800	0.7428	0.8833
0.0	25.0	1875	0.7179	0.885
0.0041	26.0	1950	0.7150	0.8883
0.0	27.0	2025	0.7370	0.8833
0.0	28.0	2100	0.7342	0.885
0.0	29.0	2175	0.7378	0.8833
0.0	30.0	2250	0.7711	0.8883
0.0	31.0	2325	0.7434	0.8883
0.0	32.0	2400	0.7467	0.8883
0.0	33.0	2475	0.7543	0.885
0.0049	34.0	2550	0.7604	0.885
0.0078	35.0	2625	0.7800	0.8833
0.0032	36.0	2700	0.7784	0.885
0.0024	37.0	2775	0.7619	0.89
0.0	38.0	2850	0.7714	0.89
0.0	39.0	2925	0.7703	0.8883
0.0	40.0	3000	0.7842	0.885
0.0	41.0	3075	0.7774	0.8867
0.0028	42.0	3150	0.7773	0.8883
0.003	43.0	3225	0.7810	0.8867
0.0	44.0	3300	0.7850	0.8867
0.0027	45.0	3375	0.7856	0.8867
0.0025	46.0	3450	0.7889	0.8883
0.0052	47.0	3525	0.7872	0.8883
0.0	48.0	3600	0.7928	0.8883
0.0	49.0	3675	0.7922	0.8867
0.0045	50.0	3750	0.7938	0.8883

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0

Task: Image Classification
Library: transformers
Type: vit
License: apache-2.0
Created: Dec 5, 2023
Updated: Dec 5, 2023