smids_5x_deit_base_sgd_0001_fold2

hkivancoral/smids_5x_deit_base_sgd_0001_fold2

smids_5x_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

2% of all-time downloads

All-time downloads

189

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 17, 2023
Updated: Dec 17, 2023
SHA: 3faa490b

Base models

facebook/deit-base-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

smids_5x_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: 0.5171
Accuracy: 0.7937

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
1.0836	1.0	375	1.0885	0.3760
1.0675	2.0	750	1.0687	0.4210
1.0197	3.0	1125	1.0472	0.4792
1.0069	4.0	1500	1.0227	0.5291
0.9845	5.0	1875	0.9951	0.5757
0.9186	6.0	2250	0.9649	0.6023
0.8937	7.0	2625	0.9335	0.6240
0.9019	8.0	3000	0.9023	0.6306
0.8424	9.0	3375	0.8722	0.6539
0.8294	10.0	3750	0.8441	0.6755
0.7985	11.0	4125	0.8177	0.7038
0.7783	12.0	4500	0.7929	0.7138
0.7207	13.0	4875	0.7700	0.7238
0.7333	14.0	5250	0.7486	0.7321
0.7101	15.0	5625	0.7288	0.7471
0.6525	16.0	6000	0.7103	0.7554
0.6829	17.0	6375	0.6933	0.7521
0.6709	18.0	6750	0.6776	0.7604
0.637	19.0	7125	0.6631	0.7654
0.6386	20.0	7500	0.6498	0.7704
0.6136	21.0	7875	0.6376	0.7704
0.6058	22.0	8250	0.6264	0.7704
0.5884	23.0	8625	0.6162	0.7704
0.5772	24.0	9000	0.6067	0.7737
0.5613	25.0	9375	0.5979	0.7754
0.5696	26.0	9750	0.5898	0.7787
0.5932	27.0	10125	0.5824	0.7804
0.5407	28.0	10500	0.5756	0.7837
0.561	29.0	10875	0.5693	0.7837
0.5293	30.0	11250	0.5636	0.7854
0.5123	31.0	11625	0.5583	0.7870
0.5488	32.0	12000	0.5534	0.7870
0.4911	33.0	12375	0.5488	0.7870
0.5069	34.0	12750	0.5447	0.7870
0.5187	35.0	13125	0.5409	0.7887
0.5044	36.0	13500	0.5375	0.7903
0.5147	37.0	13875	0.5344	0.7903
0.4787	38.0	14250	0.5316	0.7920
0.5048	39.0	14625	0.5290	0.7920
0.5066	40.0	15000	0.5268	0.7920
0.5145	41.0	15375	0.5248	0.7937
0.4726	42.0	15750	0.5230	0.7937
0.4727	43.0	16125	0.5215	0.7937
0.5222	44.0	16500	0.5202	0.7937
0.4881	45.0	16875	0.5192	0.7937
0.5004	46.0	17250	0.5184	0.7937
0.4865	47.0	17625	0.5178	0.7937
0.4651	48.0	18000	0.5174	0.7937
0.4822	49.0	18375	0.5172	0.7937
0.4937	50.0	18750	0.5171	0.7937

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 17, 2023
Updated: Dec 17, 2023