You can deploy this model and start earning money today!

Niraya666/
wmc_v2_swin-tiny-patch4-window7-224_base_wm811k_cls_contra_learning_1017_6_cls

Name: wmc_v2_swin-tiny-patch4-window7-224_base_wm811k_cls_contra_learning_1017_6_cls
Availability: InStock

transformers

safetensors

swin

generated_from_trainer

microsoft/swin-tiny-patch4-window7-224

finetune

apache-2.0

endpoints_compatible

Views

No views yet

wmc_v2_swin-tiny-patch4-window7-224_base_wm811k_cls_contra_learning_1017_6_cls

This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0632
Accuracy: 0.9760
Precision: 0.9607
Recall: 0.9621
F1: 0.9611

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: 2e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
1.131	0.1697	100	0.6398	0.7195	0.6527	0.5655	0.5087
0.6353	0.3394	200	0.2183	0.9314	0.8628	0.8571	0.8592
0.5429	0.5091	300	0.1273	0.9594	0.9347	0.8905	0.9073
0.4432	0.6788	400	0.1040	0.9680	0.9322	0.9489	0.9397
0.4109	0.8485	500	0.0998	0.9697	0.9508	0.9442	0.9474
0.3775	1.0182	600	0.1209	0.9573	0.9323	0.9382	0.9326
0.3661	1.1880	700	0.0968	0.9697	0.9313	0.9579	0.9428
0.3609	1.3577	800	0.0879	0.9707	0.9479	0.9524	0.9498
0.3393	1.5274	900	0.0785	0.9734	0.9536	0.9566	0.9547
0.3242	1.6971	1000	0.0773	0.9732	0.9456	0.9626	0.9533
0.3307	1.8668	1100	0.0626	0.9781	0.9631	0.9601	0.9615
0.3325	2.0365	1200	0.0662	0.9767	0.9575	0.9637	0.9603
0.2889	2.2062	1300	0.0609	0.9780	0.9526	0.9673	0.9594
0.2818	2.3759	1400	0.0656	0.9762	0.9566	0.9619	0.9588
0.3038	2.5456	1500	0.0561	0.9795	0.9666	0.9633	0.9647
0.2823	2.7153	1600	0.0610	0.9781	0.9590	0.9668	0.9626
0.2478	2.8850	1700	0.0632	0.9760	0.9607	0.9621	0.9611

Framework versions

Transformers 4.45.2
Pytorch 2.4.1+cu121
Datasets 3.0.1
Tokenizers 0.20.1

Niraya666/wmc_v2_swin-tiny-patch4-window7-224_base_wm811k_cls_contra_learning_1017_6_cls

wmc_v2_swin-tiny-patch4-window7-224_base_wm811k_cls_contra_learning_1017_6_cls

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Niraya666/
wmc_v2_swin-tiny-patch4-window7-224_base_wm811k_cls_contra_learning_1017_6_cls