smids_5x_deit_base_rms_001_fold2

hkivancoral/smids_5x_deit_base_rms_001_fold2

smids_5x_deit_base_rms_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

1% of all-time downloads

All-time downloads

296

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 17, 2023
Updated: Dec 17, 2023
SHA: 29cb978a

Base models

facebook/deit-base-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

smids_5x_deit_base_rms_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: 0.6861
Accuracy: 0.7953

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
0.9457	1.0	375	0.8476	0.5324
0.8382	2.0	750	0.8448	0.5391
0.809	3.0	1125	0.7879	0.5424
0.745	4.0	1500	0.7390	0.6323
0.7171	5.0	1875	0.7030	0.6622
0.6968	6.0	2250	0.7889	0.6456
0.6875	7.0	2625	0.6388	0.7072
0.6501	8.0	3000	0.6553	0.7038
0.651	9.0	3375	0.5748	0.7354
0.6283	10.0	3750	0.5788	0.7421
0.6238	11.0	4125	0.5592	0.7621
0.6557	12.0	4500	0.5567	0.7471
0.5365	13.0	4875	0.5457	0.7704
0.6238	14.0	5250	0.5542	0.7571
0.5702	15.0	5625	0.5827	0.7321
0.4879	16.0	6000	0.5598	0.7671
0.5127	17.0	6375	0.5330	0.7687
0.4935	18.0	6750	0.5680	0.7537
0.5245	19.0	7125	0.5110	0.7837
0.4876	20.0	7500	0.5252	0.7804
0.4771	21.0	7875	0.5233	0.7770
0.5009	22.0	8250	0.5096	0.8003
0.4963	23.0	8625	0.5344	0.7870
0.4814	24.0	9000	0.5289	0.8087
0.4304	25.0	9375	0.5706	0.7854
0.4721	26.0	9750	0.5627	0.7637
0.4743	27.0	10125	0.5566	0.7770
0.387	28.0	10500	0.5497	0.7953
0.4853	29.0	10875	0.5210	0.7887
0.347	30.0	11250	0.5276	0.8120
0.4668	31.0	11625	0.5138	0.8136
0.424	32.0	12000	0.5446	0.7787
0.4005	33.0	12375	0.5357	0.8020
0.4114	34.0	12750	0.5259	0.7903
0.3661	35.0	13125	0.5604	0.7903
0.3542	36.0	13500	0.5807	0.7987
0.3711	37.0	13875	0.5589	0.8037
0.3372	38.0	14250	0.5483	0.8003
0.3656	39.0	14625	0.6008	0.7704
0.3244	40.0	15000	0.5754	0.8120
0.3484	41.0	15375	0.5934	0.7970
0.3143	42.0	15750	0.6293	0.7937
0.3053	43.0	16125	0.5834	0.7920
0.3117	44.0	16500	0.5894	0.7970
0.3041	45.0	16875	0.6216	0.7887
0.284	46.0	17250	0.6533	0.7953
0.36	47.0	17625	0.6167	0.7987
0.2345	48.0	18000	0.6554	0.8003
0.2899	49.0	18375	0.6795	0.7937
0.264	50.0	18750	0.6861	0.7953

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