smids_10x_deit_base_sgd_0001_fold2

hkivancoral/smids_10x_deit_base_sgd_0001_fold2

smids_10x_deit_base_sgd_0001_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

1% of all-time downloads

All-time downloads

273

Public

Repo size

17.5 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 21, 2023
Updated: Dec 21, 2023
SHA: 9116bd94

Base models

facebook/deit-base-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

smids_10x_deit_base_sgd_0001_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: 0.4033
Accuracy: 0.8386

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
1.0726	1.0	750	1.0697	0.4193
0.9885	2.0	1500	1.0230	0.5324
0.9161	3.0	2250	0.9631	0.6057
0.8922	4.0	3000	0.8962	0.6389
0.7847	5.0	3750	0.8318	0.6922
0.7649	6.0	4500	0.7745	0.7221
0.6927	7.0	5250	0.7242	0.7454
0.6518	8.0	6000	0.6810	0.7521
0.6316	9.0	6750	0.6449	0.7587
0.5913	10.0	7500	0.6145	0.7720
0.5908	11.0	8250	0.5890	0.7770
0.5365	12.0	9000	0.5673	0.7804
0.5035	13.0	9750	0.5486	0.7870
0.4588	14.0	10500	0.5325	0.7937
0.4827	15.0	11250	0.5186	0.7953
0.4605	16.0	12000	0.5064	0.8020
0.3999	17.0	12750	0.4957	0.8037
0.4114	18.0	13500	0.4861	0.8070
0.4361	19.0	14250	0.4777	0.8070
0.4491	20.0	15000	0.4702	0.8136
0.4325	21.0	15750	0.4634	0.8136
0.3856	22.0	16500	0.4573	0.8136
0.3915	23.0	17250	0.4519	0.8136
0.3628	24.0	18000	0.4469	0.8170
0.4391	25.0	18750	0.4425	0.8170
0.426	26.0	19500	0.4384	0.8153
0.3848	27.0	20250	0.4347	0.8170
0.4075	28.0	21000	0.4313	0.8236
0.367	29.0	21750	0.4282	0.8286
0.3873	30.0	22500	0.4254	0.8303
0.3615	31.0	23250	0.4227	0.8319
0.4147	32.0	24000	0.4203	0.8319
0.3687	33.0	24750	0.4182	0.8319
0.3673	34.0	25500	0.4163	0.8353
0.3984	35.0	26250	0.4145	0.8353
0.4014	36.0	27000	0.4129	0.8353
0.3649	37.0	27750	0.4114	0.8353
0.3739	38.0	28500	0.4101	0.8353
0.3864	39.0	29250	0.4088	0.8353
0.4645	40.0	30000	0.4079	0.8369
0.3819	41.0	30750	0.4069	0.8369
0.3624	42.0	31500	0.4061	0.8369
0.331	43.0	32250	0.4054	0.8369
0.3186	44.0	33000	0.4047	0.8369
0.3184	45.0	33750	0.4043	0.8369
0.3966	46.0	34500	0.4039	0.8386
0.364	47.0	35250	0.4036	0.8386
0.3848	48.0	36000	0.4034	0.8386
0.3506	49.0	36750	0.4033	0.8386
0.3494	50.0	37500	0.4033	0.8386

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 21, 2023
Updated: Dec 21, 2023