smids_5x_deit_base_rms_001_fold4

hkivancoral/smids_5x_deit_base_rms_001_fold4

smids_5x_deit_base_rms_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

301

Public

Repo size

16.8 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: 349b8b7a

Base models

facebook/deit-base-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

smids_5x_deit_base_rms_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: 0.7070
Accuracy: 0.8

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
1.11	1.0	375	1.0993	0.325
0.9143	2.0	750	0.8093	0.5633
0.8119	3.0	1125	0.7905	0.58
0.8256	4.0	1500	0.7664	0.5933
0.7841	5.0	1875	0.7359	0.6383
0.7919	6.0	2250	0.7445	0.6033
0.7749	7.0	2625	0.6951	0.6567
0.741	8.0	3000	0.7702	0.6017
0.6745	9.0	3375	0.6771	0.6967
0.6495	10.0	3750	0.6304	0.7267
0.6291	11.0	4125	0.6937	0.665
0.6399	12.0	4500	0.6515	0.7017
0.559	13.0	4875	0.7230	0.6783
0.6232	14.0	5250	0.5711	0.76
0.6438	15.0	5625	0.5759	0.725
0.5708	16.0	6000	0.5672	0.7433
0.5817	17.0	6375	0.5983	0.7367
0.5534	18.0	6750	0.5595	0.7633
0.5539	19.0	7125	0.5109	0.7767
0.5681	20.0	7500	0.5115	0.7667
0.481	21.0	7875	0.5451	0.765
0.5126	22.0	8250	0.5810	0.7383
0.5213	23.0	8625	0.5434	0.7467
0.4811	24.0	9000	0.5453	0.7833
0.4831	25.0	9375	0.5703	0.7617
0.4515	26.0	9750	0.5020	0.795
0.4363	27.0	10125	0.5213	0.7733
0.4104	28.0	10500	0.5450	0.76
0.4526	29.0	10875	0.5543	0.76
0.4959	30.0	11250	0.5151	0.7683
0.5018	31.0	11625	0.5269	0.7933
0.4267	32.0	12000	0.5138	0.7933
0.464	33.0	12375	0.5486	0.7883
0.4612	34.0	12750	0.5500	0.7867
0.3667	35.0	13125	0.5319	0.7983
0.3692	36.0	13500	0.6112	0.77
0.443	37.0	13875	0.5427	0.8
0.431	38.0	14250	0.5062	0.7967
0.3837	39.0	14625	0.5492	0.7867
0.421	40.0	15000	0.6140	0.7883
0.3456	41.0	15375	0.6505	0.7817
0.3528	42.0	15750	0.6246	0.7733
0.383	43.0	16125	0.6178	0.7933
0.3235	44.0	16500	0.6286	0.7933
0.3165	45.0	16875	0.6316	0.7933
0.3289	46.0	17250	0.6422	0.7933
0.3499	47.0	17625	0.6701	0.8
0.2803	48.0	18000	0.6802	0.7917
0.279	49.0	18375	0.6961	0.8017
0.2671	50.0	18750	0.7070	0.8

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