bigscience-workshop/petals

Exploding gradients/weights/logits in a fine-tuning notebook

Open

#283 opened on Mar 10, 2023

View on GitHub
 (2 comments) (1 reaction) (1 assignee)Python (424 forks)batch import
buggood first issuehelp wanted

Repository metrics

Stars
 (8,248 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

Hello, after I successfully fine-tuned, I run to the last step and when generating text, the following error occurs. May I ask what is the reason?

image image

Contributor guide

Research direction
Check for exploding gradients by inspecting loss values and gradient norms during fine tuning. Look at model configuration and learning rate schedule.
Tech stack
pythonpytorch
Domain
backendmachine learning
Issue type
Bug
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.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Mostly clear
Prerequisites
PythonPyTorch
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
40