exemple2-finetuned-segments

This model is a fine-tuned version of nvidia/mit-b0 on the segments/sidewalk-semantic dataset.

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
No log	1.0	5	3.5279	0.0125	0.0416	0.1024	[0.003071310796148687, 0.1616174857459709, 0.0, 0.0, 0.0022739959938265523, 0.0, 0.0005909869482034998, 0.0017997990408432924, 0.0, 0.05474664289453949, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.09700429854115147, 0.0, 0.04184948021660935, 0.0006682389937106918, 0.0, 0.0, 0.00415553197202368, 0.004015113955619657, 0.0, 0.0, 6.202127329674078e-05, 0.05336540352809607, 0.0, 0.0, 0.0, 0.00025955435304111186, 0.0, 0.0]	[0.0032144853023359787, 0.18635872416872554, nan, 0.0, 0.0038356619632496504, nan, 0.0010970621048716994, 0.008956864181701621, nan, 0.06383171787997526, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.11043176613738219, nan, 0.051045006388159, 0.02862641327880683, nan, nan, 0.34138655462184875, 0.049846125151543415, 0.0, nan, 6.220517339692085e-05, 0.10777804260728432, 0.0, 0.0, 0.0, 0.0002737135463322385, 0.0, nan]

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2