segformer-b0-finetuned-brooks-or-dunn

This model is a fine-tuned version of nvidia/mit-b0 on the q2-jlbar/BrooksOrDunn dataset. It achieves the following results on the evaluation set:

• Loss: 0.1158
• Mean Iou: nan
• Mean Accuracy: nan
• Overall Accuracy: nan
• Per Category Iou: [nan, nan]
• Per Category Accuracy: [nan, nan]

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: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Per Category Iou	Per Category Accuracy
0.5153	4.0	20	0.5276	nan	nan	nan	[nan, nan]	[nan, nan]
0.4082	8.0	40	0.3333	nan	nan	nan	[nan, nan]	[nan, nan]
0.3157	12.0	60	0.2773	nan	nan	nan	[nan, nan]	[nan, nan]
0.2911	16.0	80	0.2389	nan	nan	nan	[nan, nan]	[nan, nan]
0.2395	20.0	100	0.1982	nan	nan	nan	[nan, nan]	[nan, nan]
0.2284	24.0	120	0.1745	nan	nan	nan	[nan, nan]	[nan, nan]
0.1818	28.0	140	0.1595	nan	nan	nan	[nan, nan]	[nan, nan]
0.1549	32.0	160	0.1556	nan	nan	nan	[nan, nan]	[nan, nan]
0.1351	36.0	180	0.1387	nan	nan	nan	[nan, nan]	[nan, nan]
0.1254	40.0	200	0.1263	nan	nan	nan	[nan, nan]	[nan, nan]
0.1412	44.0	220	0.1190	nan	nan	nan	[nan, nan]	[nan, nan]
0.1179	48.0	240	0.1158	nan	nan	nan	[nan, nan]	[nan, nan]

Framework versions

• Transformers 4.19.2
• Pytorch 1.11.0
• Datasets 2.2.2
• Tokenizers 0.12.1