segmentation_model_50ep_2

This model is a fine-tuned version of nvidia/mit-b0 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0151
• Mean Iou: 0.4992
• Mean Accuracy: 0.5002
• Overall Accuracy: 0.9980
• Per Category Iou: [0.9979567074182948, 0.0004395926441497546]
• Per Category Accuracy: [0.9999017103951866, 0.00046175157765122367]

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• 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
0.0176	12.1951	1000	0.0153	0.4991	0.5001	0.9978	[0.9978437819175541, 0.00041657987919183504]	[0.9997885648043022, 0.00046175157765122367]
0.0173	24.3902	2000	0.0153	0.4991	0.5001	0.9978	[0.9978095148690534, 0.0004100657472081357]	[0.999754230969827, 0.00046175157765122367]
0.0144	36.5854	3000	0.0146	0.4991	0.5001	0.9980	[0.9979986133831826, 0.00026932399676811203]	[0.9999440574585123, 0.00027705094659073417]
0.0208	48.7805	4000	0.0151	0.4992	0.5002	0.9980	[0.9979567074182948, 0.0004395926441497546]	[0.9999017103951866, 0.00046175157765122367]

Framework versions

• Transformers 4.46.3
• Pytorch 2.2.0
• Datasets 2.4.0
• Tokenizers 0.20.3