Modelpublic

Darayut/segformer-b0-layout-detection

sourceHugging Faceupdated 8mo agoView on Hugging Face

0likes14downloads

Model Card

segformer-b0-layout-detection

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

—Loss: 0.3110
—Mean Iou: 0.3996

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: 4e-05
—trainbatchsize: 8
—evalbatchsize: 8
—seed: 42
—optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
—lrschedulertype: cosine
—lrschedulerwarmup_steps: 1000
—training_steps: 9000
—mixedprecisiontraining: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou
0.153	0.1111	1000	0.3118	0.3967
0.1057	0.2222	2000	0.3459	0.3848
0.126	0.3333	3000	0.3548	0.3988
0.1396	0.4444	4000	0.3250	0.3521
0.1342	0.5556	5000	0.3074	0.3322
0.1383	0.6667	6000	0.3300	0.3915
0.1206	0.7778	7000	0.3209	0.3811
0.1348	0.8889	8000	0.3179	0.3781
0.1418	1.0363	9000	0.3110	0.3996

Framework versions

—Transformers 4.57.1
—Pytorch 2.8.0+cu126
—Datasets 4.4.2
—Tokenizers 0.22.1