RVC-Project/Retrieval-based-Voice-Conversion-WebUI

Why Very Big Spike in Learning Curve

Open

#1,743 opened on Jan 19, 2024

View on GitHub
 (1 comment) (0 reactions) (0 assignees)Python (18,427 stars) (2,849 forks)batch import
bughelp wanted

Description

As you see in the below image the curve is almost ok till 10K steps then it again goes to 9K steps backward and then again goes forward. why this happened ? is something wrong ?

Screenshot 2024-01-19 152016

This spike is shows in all graphs.

Screenshot 2024-01-19 152102

Contributor guide

Tech stack
pythonpytorch
Domain
machine learningai
Issue type
research
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
fresh
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
clear
Prerequisites
training basicsloss curve analysis
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
35
Research direction
Investigate the training code to understand potential causes of the spike. Check for learning rate schedulers (e.g., ReduceLROnPlateau), data shuffling, or gradient accumulation steps. Look at the loss function and optimizer settings in the training script. Compare with similar issues or documentation in the repository.