smids_3x_deit_base_sgd_001_fold4

hkivancoral/smids_3x_deit_base_sgd_001_fold4

smids_3x_deit_base_sgd_001_fold4 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

199

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 11, 2023
Updated: Dec 11, 2023
SHA: b7be3c12

Base models

facebook/deit-base-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

smids_3x_deit_base_sgd_001_fold4

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: 0.3344
Accuracy: 0.8767

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
0.9564	1.0	225	0.9423	0.64
0.7113	2.0	450	0.7214	0.7733
0.5639	3.0	675	0.5832	0.8017
0.5094	4.0	900	0.5049	0.8183
0.4968	5.0	1125	0.4596	0.825
0.3617	6.0	1350	0.4304	0.8383
0.4108	7.0	1575	0.4105	0.84
0.4388	8.0	1800	0.3975	0.845
0.3859	9.0	2025	0.3855	0.845
0.3342	10.0	2250	0.3790	0.85
0.3561	11.0	2475	0.3717	0.8533
0.3675	12.0	2700	0.3673	0.855
0.2823	13.0	2925	0.3617	0.86
0.2556	14.0	3150	0.3581	0.8583
0.2719	15.0	3375	0.3554	0.86
0.2758	16.0	3600	0.3520	0.86
0.2583	17.0	3825	0.3508	0.8617
0.2892	18.0	4050	0.3484	0.8633
0.3042	19.0	4275	0.3478	0.8683
0.2293	20.0	4500	0.3445	0.8667
0.2549	21.0	4725	0.3434	0.8717
0.2441	22.0	4950	0.3424	0.8683
0.2463	23.0	5175	0.3417	0.8683
0.2314	24.0	5400	0.3394	0.8667
0.2319	25.0	5625	0.3388	0.8683
0.2172	26.0	5850	0.3384	0.8667
0.2256	27.0	6075	0.3381	0.8667
0.212	28.0	6300	0.3381	0.8683
0.1974	29.0	6525	0.3386	0.87
0.2121	30.0	6750	0.3373	0.8683
0.2143	31.0	6975	0.3372	0.87
0.2062	32.0	7200	0.3362	0.8717
0.2495	33.0	7425	0.3366	0.8717
0.1945	34.0	7650	0.3360	0.8733
0.203	35.0	7875	0.3362	0.8717
0.2268	36.0	8100	0.3356	0.875
0.1902	37.0	8325	0.3348	0.8733
0.2187	38.0	8550	0.3349	0.875
0.2032	39.0	8775	0.3350	0.875
0.2156	40.0	9000	0.3342	0.875
0.2119	41.0	9225	0.3346	0.8767
0.2354	42.0	9450	0.3345	0.8767
0.1983	43.0	9675	0.3345	0.8767
0.2529	44.0	9900	0.3343	0.8767
0.2248	45.0	10125	0.3345	0.875
0.2133	46.0	10350	0.3343	0.8767
0.2026	47.0	10575	0.3344	0.8767
0.2376	48.0	10800	0.3344	0.8767
0.241	49.0	11025	0.3344	0.8767
0.2159	50.0	11250	0.3344	0.8767

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