smids_5x_deit_base_rms_0001_fold3

hkivancoral/smids_5x_deit_base_rms_0001_fold3

smids_5x_deit_base_rms_0001_fold3 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

258

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 18, 2023
Updated: Dec 18, 2023
SHA: e5ee003d

Base models

facebook/deit-base-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

smids_5x_deit_base_rms_0001_fold3

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: 1.0537
Accuracy: 0.9033

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
0.2482	1.0	375	0.3175	0.8933
0.1437	2.0	750	0.2994	0.91
0.0829	3.0	1125	0.4831	0.8717
0.0657	4.0	1500	0.4645	0.87
0.0415	5.0	1875	0.5452	0.895
0.0518	6.0	2250	0.4649	0.89
0.0246	7.0	2625	0.4579	0.8933
0.0124	8.0	3000	0.5092	0.8933
0.0196	9.0	3375	0.6123	0.885
0.0528	10.0	3750	0.5846	0.89
0.0162	11.0	4125	0.6461	0.89
0.0269	12.0	4500	0.6644	0.89
0.0189	13.0	4875	0.6691	0.8867
0.013	14.0	5250	0.5509	0.895
0.0125	15.0	5625	0.6239	0.8867
0.042	16.0	6000	0.5644	0.8967
0.0002	17.0	6375	0.7253	0.8967
0.0067	18.0	6750	0.7652	0.8983
0.0166	19.0	7125	0.7033	0.8983
0.0136	20.0	7500	0.7542	0.8867
0.0035	21.0	7875	0.8364	0.8883
0.0092	22.0	8250	0.7788	0.89
0.0366	23.0	8625	0.7487	0.8933
0.0057	24.0	9000	0.8195	0.8933
0.0002	25.0	9375	0.6186	0.9
0.0001	26.0	9750	0.7244	0.9017
0.0002	27.0	10125	0.8368	0.8883
0.0004	28.0	10500	0.8205	0.895
0.0421	29.0	10875	0.8404	0.89
0.0033	30.0	11250	0.8091	0.8967
0.0	31.0	11625	0.7929	0.8967
0.0109	32.0	12000	0.8783	0.8883
0.0	33.0	12375	0.8591	0.8917
0.0	34.0	12750	0.9822	0.89
0.0	35.0	13125	0.9216	0.8933
0.0	36.0	13500	0.9855	0.895
0.0	37.0	13875	0.8868	0.9017
0.0	38.0	14250	0.9047	0.9017
0.0	39.0	14625	0.9416	0.9017
0.0033	40.0	15000	0.8937	0.91
0.0117	41.0	15375	1.0141	0.8967
0.0	42.0	15750	1.0456	0.9
0.0	43.0	16125	1.0341	0.9017
0.0	44.0	16500	1.0394	0.9033
0.0	45.0	16875	1.0421	0.905
0.0	46.0	17250	1.0425	0.9017
0.0	47.0	17625	1.0481	0.905
0.0	48.0	18000	1.0506	0.9033
0.0	49.0	18375	1.0518	0.905
0.0	50.0	18750	1.0537	0.9033

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 18, 2023
Updated: Dec 18, 2023