segmentation

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: -0.9095
• Mean Iou: 0.2514
• Mean Accuracy: 1.0
• Overall Accuracy: 1.0
• Per Category Iou: [0.25135050741608117]
• Per Category Accuracy: [1.0]

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: 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	Per Category Iou	Per Category Accuracy
-0.906	0.1905	20	-0.5145	0.2514	1.0	1.0	[0.25135050741608117]	[1.0]
-1.2793	0.3810	40	-0.7514	0.2514	1.0	1.0	[0.25135050741608117]	[1.0]
-3.2567	0.5714	60	-0.9282	0.2514	1.0	1.0	[0.25135050741608117]	[1.0]
-3.8327	0.7619	80	-0.9024	0.2514	1.0	1.0	[0.25135050741608117]	[1.0]
-2.1622	0.9524	100	-0.9095	0.2514	1.0	1.0	[0.25135050741608117]	[1.0]

Framework versions

• Transformers 4.41.2
• Pytorch 2.2.0
• Datasets 2.20.0
• Tokenizers 0.19.1