smids_5x_deit_base_adamax_001_fold2

hkivancoral/smids_5x_deit_base_adamax_001_fold2

smids_5x_deit_base_adamax_001_fold2 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

220

Public

Repo size

17.2 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: Dec 16, 2023
Updated: Dec 16, 2023
SHA: fc10a491

Base models

facebook/deit-base-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

smids_5x_deit_base_adamax_001_fold2

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

Loss: 1.1252
Accuracy: 0.8852

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: 0.001
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
0.3593	1.0	375	0.2868	0.8902
0.3012	2.0	750	0.2473	0.9085
0.3836	3.0	1125	0.3500	0.8619
0.1484	4.0	1500	0.3561	0.8819
0.142	5.0	1875	0.3496	0.8619
0.1054	6.0	2250	0.5030	0.8519
0.1132	7.0	2625	0.4021	0.8769
0.0387	8.0	3000	0.5600	0.8752
0.0412	9.0	3375	0.4804	0.8935
0.049	10.0	3750	0.4670	0.8902
0.0223	11.0	4125	0.5161	0.8852
0.0227	12.0	4500	0.5268	0.8802
0.029	13.0	4875	0.5511	0.8819
0.0101	14.0	5250	0.5655	0.8935
0.0239	15.0	5625	0.5903	0.8885
0.0204	16.0	6000	0.6826	0.8869
0.0387	17.0	6375	0.6581	0.8835
0.0045	18.0	6750	0.5940	0.8869
0.0004	19.0	7125	0.7563	0.8885
0.0271	20.0	7500	0.5791	0.9035
0.0211	21.0	7875	0.5981	0.8869
0.0086	22.0	8250	0.6990	0.8869
0.0146	23.0	8625	0.6527	0.8935
0.0006	24.0	9000	0.5903	0.8885
0.02	25.0	9375	0.6548	0.8952
0.0007	26.0	9750	0.7230	0.8952
0.0	27.0	10125	0.7646	0.9002
0.0	28.0	10500	0.8095	0.8852
0.0	29.0	10875	0.8926	0.8835
0.0	30.0	11250	0.8629	0.8819
0.0041	31.0	11625	0.8782	0.8819
0.0047	32.0	12000	0.8948	0.8819
0.0063	33.0	12375	0.9158	0.8752
0.0001	34.0	12750	0.9726	0.8918
0.0	35.0	13125	1.0164	0.8819
0.0	36.0	13500	1.0004	0.8869
0.0	37.0	13875	1.0193	0.8869
0.0	38.0	14250	1.0151	0.8935
0.0	39.0	14625	1.0231	0.8902
0.0035	40.0	15000	1.0298	0.8852
0.0	41.0	15375	1.0402	0.8902
0.0028	42.0	15750	1.0577	0.8869
0.0026	43.0	16125	1.0687	0.8819
0.0027	44.0	16500	1.0626	0.8852
0.0029	45.0	16875	1.0972	0.8835
0.0	46.0	17250	1.0976	0.8819
0.0055	47.0	17625	1.1056	0.8819
0.0	48.0	18000	1.1143	0.8852
0.0025	49.0	18375	1.1213	0.8835
0.0024	50.0	18750	1.1252	0.8852

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2

Task: Image Classification
Library: transformers
Type: vit
License: apache-2.0
Created: Dec 16, 2023
Updated: Dec 16, 2023