custom-object-test4

This model is a fine-tuned version of nvidia/mit-b0 on the sungile/custom-object-masking5 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2992
• Mean Iou: 0.0
• Mean Accuracy: nan
• Overall Accuracy: nan
• Accuracy Unknown: nan
• Accuracy Background: nan
• Accuracy Object: nan
• Iou Unknown: 0.0
• Iou Background: 0.0
• Iou Object: 0.0

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: 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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Accuracy Unknown	Accuracy Background	Accuracy Object	Iou Unknown	Iou Background	Iou Object
1.0218	0.25	20	1.0125	0.0	nan	nan	nan	nan	nan	0.0	0.0	0.0
0.8291	0.5	40	0.7527	0.0	nan	nan	nan	nan	nan	0.0	0.0	0.0
0.7097	0.75	60	0.6208	0.0	nan	nan	nan	nan	nan	0.0	0.0	0.0
0.606	1.0	80	0.5042	0.0	nan	nan	nan	nan	nan	0.0	0.0	0.0
0.5577	1.25	100	0.4111	0.0	nan	nan	nan	nan	nan	0.0	0.0	0.0
0.4422	1.5	120	0.4041	0.0	nan	nan	nan	nan	nan	0.0	0.0	0.0
0.3799	1.75	140	0.3846	0.0	nan	nan	nan	nan	nan	0.0	0.0	0.0
0.3578	2.0	160	0.3197	0.0	nan	nan	nan	nan	nan	0.0	0.0	nan
0.3401	2.25	180	0.3423	0.0	nan	nan	nan	nan	nan	0.0	0.0	nan
0.3223	2.5	200	0.3077	0.0	nan	nan	nan	nan	nan	0.0	0.0	0.0
0.3068	2.75	220	0.3110	0.0	nan	nan	nan	nan	nan	0.0	0.0	0.0
0.2823	3.0	240	0.2992	0.0	nan	nan	nan	nan	nan	0.0	0.0	0.0

Framework versions

• Transformers 4.47.1
• Pytorch 2.1.0+cu118
• Datasets 3.2.0
• Tokenizers 0.21.0