ChristianMDahl/segFormer_ver1_horizontal

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

• Train Loss: 0.1767
• Validation Loss: 0.1918
• Epoch: 19

Model description

Model for horizontal lines

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
0.3302	0.2673	0
0.2515	0.2329	1
0.2335	0.2197	2
0.2226	0.2125	3
0.2153	0.2083	4
0.2105	0.2039	5
0.2061	0.2023	6
0.2025	0.2013	7
0.1995	0.2015	8
0.1960	0.1976	9
0.1938	0.1966	10
0.1909	0.1973	11
0.1882	0.1936	12
0.1865	0.1951	13
0.1845	0.1942	14
0.1826	0.1953	15
0.1810	0.1934	16
0.1794	0.1928	17
0.1782	0.1919	18
0.1767	0.1918	19

Framework versions

• Transformers 4.28.1
• TensorFlow 2.10.1
• Datasets 2.12.0
• Tokenizers 0.13.0.dev0