Omar280X/passport_line_segmentation

This model is a fine-tuned version of nvidia/segformer-b0-finetuned-ade-512-512 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0672
• Validation Loss: 0.0692
• Epoch: 19

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:

• optimizer: {'name': 'Adam', 'learning_rate': 6e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Validation Loss	Epoch
0.2073	0.1095	0
0.1047	0.0942	1
0.0941	0.0874	2
0.0884	0.0843	3
0.0846	0.0809	4
0.0818	0.0787	5
0.0795	0.0764	6
0.0775	0.0751	7
0.0760	0.0744	8
0.0747	0.0732	9
0.0736	0.0724	10
0.0726	0.0719	11
0.0718	0.0711	12
0.0711	0.0712	13
0.0706	0.0706	14
0.0697	0.0700	15
0.0690	0.0697	16
0.0684	0.0696	17
0.0679	0.0692	18
0.0672	0.0692	19

Framework versions

• Transformers 4.37.2
• TensorFlow 2.10.0
• Datasets 3.1.0
• Tokenizers 0.15.2