smids_3x_deit_base_sgd_0001_fold3

hkivancoral/smids_3x_deit_base_sgd_0001_fold3

smids_3x_deit_base_sgd_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

209

Public

Repo size

16.5 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 11, 2023
Updated: Dec 11, 2023
SHA: 5df39a28

Base models

facebook/deit-base-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

smids_3x_deit_base_sgd_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: 0.6484
Accuracy: 0.7833

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
1.0943	1.0	225	1.0944	0.385
1.0886	2.0	450	1.0814	0.4183
1.0651	3.0	675	1.0687	0.4433
1.0331	4.0	900	1.0558	0.47
1.0336	5.0	1125	1.0425	0.495
1.0015	6.0	1350	1.0281	0.5283
0.9943	7.0	1575	1.0128	0.5417
1.0159	8.0	1800	0.9962	0.5633
0.9416	9.0	2025	0.9786	0.58
0.9487	10.0	2250	0.9602	0.605
0.9205	11.0	2475	0.9418	0.6283
0.9048	12.0	2700	0.9232	0.6467
0.8976	13.0	2925	0.9053	0.6583
0.8732	14.0	3150	0.8879	0.6683
0.8572	15.0	3375	0.8714	0.6867
0.8436	16.0	3600	0.8558	0.6917
0.8538	17.0	3825	0.8409	0.705
0.8276	18.0	4050	0.8268	0.7117
0.7944	19.0	4275	0.8134	0.72
0.7901	20.0	4500	0.8009	0.7283
0.7811	21.0	4725	0.7889	0.735
0.7752	22.0	4950	0.7777	0.735
0.7747	23.0	5175	0.7670	0.7367
0.7558	24.0	5400	0.7570	0.735
0.7382	25.0	5625	0.7476	0.7383
0.7437	26.0	5850	0.7388	0.7433
0.713	27.0	6075	0.7303	0.7467
0.7178	28.0	6300	0.7225	0.75
0.7125	29.0	6525	0.7152	0.7583
0.6668	30.0	6750	0.7082	0.7633
0.681	31.0	6975	0.7018	0.765
0.7053	32.0	7200	0.6957	0.7633
0.7058	33.0	7425	0.6901	0.765
0.6687	34.0	7650	0.6848	0.77
0.6808	35.0	7875	0.6800	0.7717
0.7094	36.0	8100	0.6756	0.7717
0.6409	37.0	8325	0.6716	0.775
0.6467	38.0	8550	0.6679	0.775
0.6641	39.0	8775	0.6646	0.7783
0.6586	40.0	9000	0.6616	0.7783
0.6383	41.0	9225	0.6590	0.7817
0.6999	42.0	9450	0.6566	0.7817
0.615	43.0	9675	0.6546	0.7833
0.6607	44.0	9900	0.6528	0.7833
0.6399	45.0	10125	0.6514	0.7817
0.6503	46.0	10350	0.6503	0.7833
0.6327	47.0	10575	0.6494	0.7833
0.6452	48.0	10800	0.6488	0.7833
0.6566	49.0	11025	0.6485	0.7833
0.6339	50.0	11250	0.6484	0.7833

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 11, 2023
Updated: Dec 11, 2023