smids_10x_deit_tiny_sgd_0001_fold2

hkivancoral/smids_10x_deit_tiny_sgd_0001_fold2

smids_10x_deit_tiny_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

418

Public

Repo size

1.1 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin22.2 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: adee16d3

Base models

facebook/deit-tiny-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

smids_10x_deit_tiny_sgd_0001_fold2

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: 0.4154
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
1.0614	1.0	750	1.0774	0.4276
0.9244	2.0	1500	0.9849	0.5008
0.8719	3.0	2250	0.9059	0.5474
0.8364	4.0	3000	0.8357	0.6140
0.7154	5.0	3750	0.7698	0.6589
0.7009	6.0	4500	0.7160	0.7038
0.6226	7.0	5250	0.6676	0.7321
0.5568	8.0	6000	0.6320	0.7521
0.5746	9.0	6750	0.6030	0.7604
0.5421	10.0	7500	0.5805	0.7671
0.5134	11.0	8250	0.5611	0.7737
0.5557	12.0	9000	0.5444	0.7770
0.5053	13.0	9750	0.5297	0.7804
0.4226	14.0	10500	0.5183	0.7887
0.4645	15.0	11250	0.5092	0.7903
0.4059	16.0	12000	0.5013	0.7920
0.421	17.0	12750	0.4951	0.7987
0.4242	18.0	13500	0.4876	0.7970
0.4439	19.0	14250	0.4811	0.7970
0.4437	20.0	15000	0.4767	0.7987
0.4454	21.0	15750	0.4711	0.8037
0.3749	22.0	16500	0.4658	0.8037
0.3717	23.0	17250	0.4614	0.8053
0.3725	24.0	18000	0.4568	0.8053
0.4228	25.0	18750	0.4527	0.8136
0.4364	26.0	19500	0.4498	0.8103
0.4024	27.0	20250	0.4458	0.8203
0.3741	28.0	21000	0.4427	0.8220
0.38	29.0	21750	0.4402	0.8203
0.3796	30.0	22500	0.4372	0.8236
0.3538	31.0	23250	0.4351	0.8253
0.3869	32.0	24000	0.4332	0.8253
0.3759	33.0	24750	0.4310	0.8286
0.394	34.0	25500	0.4290	0.8270
0.3753	35.0	26250	0.4274	0.8270
0.4036	36.0	27000	0.4252	0.8303
0.3883	37.0	27750	0.4241	0.8336
0.3856	38.0	28500	0.4227	0.8336
0.3479	39.0	29250	0.4214	0.8336
0.4431	40.0	30000	0.4201	0.8336
0.391	41.0	30750	0.4193	0.8336
0.3751	42.0	31500	0.4184	0.8336
0.3523	43.0	32250	0.4178	0.8336
0.3279	44.0	33000	0.4171	0.8336
0.341	45.0	33750	0.4165	0.8353
0.3735	46.0	34500	0.4161	0.8353
0.3807	47.0	35250	0.4158	0.8353
0.373	48.0	36000	0.4155	0.8386
0.3296	49.0	36750	0.4154	0.8386
0.3593	50.0	37500	0.4154	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