segcrack9k_conglomerate_train_test

This model is a fine-tuned version of nvidia/mit-b5 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0298
• Mean Iou: 0.3639
• Mean Accuracy: 0.7278
• Overall Accuracy: 0.7278
• Accuracy Background: nan
• Accuracy Crack: 0.7278
• Iou Background: 0.0
• Iou Crack: 0.7278

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: 6e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Accuracy Background	Accuracy Crack	Iou Background	Iou Crack
0.0374	0.18	1000	0.0410	0.2472	0.4944	0.4944	nan	0.4944	0.0	0.4944
0.0337	0.36	2000	0.0341	0.3749	0.7497	0.7497	nan	0.7497	0.0	0.7497
0.0209	0.55	3000	0.0318	0.3335	0.6670	0.6670	nan	0.6670	0.0	0.6670
0.0099	0.73	4000	0.0315	0.3371	0.6743	0.6743	nan	0.6743	0.0	0.6743
0.026	0.91	5000	0.0298	0.3639	0.7278	0.7278	nan	0.7278	0.0	0.7278

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.0
• Tokenizers 0.13.3