smids_3x_deit_base_sgd_0001_fold2

hkivancoral/smids_3x_deit_base_sgd_0001_fold2

smids_3x_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

194

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: 95265e69

Base models

facebook/deit-base-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

smids_3x_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: 0.6553
Accuracy: 0.7621

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
1.0893	1.0	225	1.0953	0.3594
1.0864	2.0	450	1.0828	0.3794
1.0622	3.0	675	1.0705	0.4160
1.0459	4.0	900	1.0580	0.4509
1.0341	5.0	1125	1.0447	0.4759
1.0064	6.0	1350	1.0303	0.5108
1.0054	7.0	1575	1.0147	0.5341
0.9891	8.0	1800	0.9981	0.5674
0.9621	9.0	2025	0.9806	0.5890
0.9335	10.0	2250	0.9622	0.6040
0.9046	11.0	2475	0.9439	0.6206
0.9082	12.0	2700	0.9257	0.6240
0.8902	13.0	2925	0.9080	0.6323
0.874	14.0	3150	0.8909	0.6406
0.8732	15.0	3375	0.8749	0.6556
0.8692	16.0	3600	0.8594	0.6622
0.8439	17.0	3825	0.8446	0.6755
0.8058	18.0	4050	0.8304	0.6839
0.7984	19.0	4275	0.8173	0.7005
0.7908	20.0	4500	0.8048	0.7055
0.7871	21.0	4725	0.7931	0.7171
0.8093	22.0	4950	0.7821	0.7238
0.7796	23.0	5175	0.7716	0.7288
0.7539	24.0	5400	0.7616	0.7421
0.756	25.0	5625	0.7522	0.7438
0.733	26.0	5850	0.7434	0.7454
0.7398	27.0	6075	0.7351	0.7488
0.7143	28.0	6300	0.7274	0.7488
0.7155	29.0	6525	0.7202	0.7504
0.7131	30.0	6750	0.7134	0.7488
0.6651	31.0	6975	0.7071	0.7488
0.6923	32.0	7200	0.7012	0.7521
0.674	33.0	7425	0.6957	0.7521
0.6414	34.0	7650	0.6907	0.7537
0.6882	35.0	7875	0.6860	0.7571
0.6787	36.0	8100	0.6817	0.7571
0.6546	37.0	8325	0.6777	0.7587
0.6468	38.0	8550	0.6741	0.7587
0.6253	39.0	8775	0.6708	0.7554
0.6533	40.0	9000	0.6679	0.7571
0.6108	41.0	9225	0.6653	0.7571
0.6451	42.0	9450	0.6630	0.7587
0.6128	43.0	9675	0.6611	0.7604
0.6504	44.0	9900	0.6594	0.7604
0.6566	45.0	10125	0.6581	0.7621
0.6606	46.0	10350	0.6570	0.7621
0.615	47.0	10575	0.6562	0.7621
0.653	48.0	10800	0.6557	0.7621
0.6663	49.0	11025	0.6554	0.7621
0.6208	50.0	11250	0.6553	0.7621

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