How to set soft_start_annealing_schedule prams to training process reach to num_epochs?

[LoveNvidia]

Please provide the following information when requesting support.

• Hardware (T4/V100/Xavier/Nano/etc) : GTX-1080ti
• Network Type (Detectnet_v2/Faster_rcnn/Yolo_v4/LPRnet/Mask_rcnn/Classification/etc): lprnet/detectnet_v2
• TLT Version (Please run “tlt info --verbose” and share “docker_tag” here): TLT:3.0, docker_tag:v3.0-py3

Hi,
I want to train lprnet and detectnet_v2 on custom dataset, and this is my learning rate schedule:

training_config {
batch_size_per_gpu: 32
num_epochs: 120
learning_rate {
soft_start_annealing_schedule {
min_learning_rate: 5e-6
max_learning_rate: 5e-4
soft_start: 0.001
annealing: 0.7
}
}

The process of training continue to 61 epochs, but I set to 120.
I guest the end of training really related to values of soft_start/annealing and number of dataset.

I want to know how I can calculate these value to training process reach to num_epochs.

[Morganh]

See NVIDIA TAO Documentation for more info about soft_start.
NVIDIA TAO Documentation

[LoveNvidia]

This issues is handled in final version of TLT3.0.
But in the developer preview version of TLT3.0 this bus is not fixed.