Omar280X/crack_segmentation_b2

This model is a fine-tuned version of nvidia/segformer-b2-finetuned-ade-512-512 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0021
• Validation Loss: 0.0020
• Epoch: 9

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
0.0248	0.0045	0
0.0044	0.0036	1
0.0037	0.0032	2
0.0033	0.0029	3
0.0029	0.0026	4
0.0027	0.0025	5
0.0025	0.0023	6
0.0024	0.0022	7
0.0022	0.0021	8
0.0021	0.0020	9

Framework versions

• Transformers 4.37.0
• TensorFlow 2.10.0
• Tokenizers 0.15.2