Skip to content

LR Too Low

Learning rate too low causes slow convergence, plateau at high loss, or training to appear stuck.

Quick answer

Learning rate too low causes slow convergence, plateau at high loss, or training to appear stuck.

Training Stability#learning-rate#too-low#slow-convergence#training-stability#hyperparameter

What this failure is

LR Too Low is a Training Stability failure seen during ML training runs. Learning rate too low causes slow convergence, plateau at high loss, or training to appear stuck. Common tags: Learning Rate, Too Low, Slow Convergence, Training Stability.

Live diagnosis, no signup

Is this what broke your run? Paste your log.

You're reading about LR Too Low. Paste your own crash log or traceback below and get the real root cause for YOUR run, not this generic entry. No account, no card. Logs are masked at ingress and never saved to account history.

training_logs.txt
No log to hand? Try one:

3 free diagnoses/day

Want 14 days on the Scale plan?

Request an evaluation code. A verified workplace organization activates up to 50 diagnoses a day, alerts, history, and follow-up questions. No credit card or automatic subscription.

Evaluate one incident

Why it happens (the mechanism)

Learning rate too low for model. Adam epsilon too high. No learning rate warmup. Optimizer beta values wrong. Taken together, these mechanisms explain why the failure is reproducible, why it tends to surface on specific workloads or scales, and why generic mitigation attempts often fall short without addressing the underlying cause.

What you'll observe

  • Loss decreases very slowly
  • Loss plateaus at high value
  • Training seems stuck

Common symptoms and what they mean

SymptomWhy it happens
Loss curve is flatLearning rate too low for model
Validation accuracy is lowAdam epsilon too high
Training takes very longNo learning rate warmup

Which systems are affected

  • New model training
  • Hyperparameter search
  • Conservative training setup

How to confirm this is the problem

Use this checklist to test the hypothesis against a small reproduction. No single line proves the root cause, so preserve the preceding events and compare one variable at a time.

  • Reproduce the failure from a clean checkpoint/seed: the symptom must appear without warm-up state from a previous run.
  • Verified signal present: Loss curve is flat
  • Verified signal present: Validation accuracy is low
  • Verified signal present: Training takes very long
  • A targeted fix from the "How to fix it" section eliminates or substantially reduces the symptom within one validation pass.

The fix and the prevention pattern

The root cause is on this page and stays free. A free account adds the exact remediation steps, saved history, and the fix on every entry in the encyclopedia.

Sign up free. Unlock the full analysis

No credit card. Daily allowance follows verified trust tier. Instant access.

Diagnose this failure in VS Code

Select the traceback or open the failed terminal, then run Denpex locally to see the initiating rank, collateral failures, exact fix, and verification command without uploading the log.

Install the free VS Code extension

Root cause

  • Learning rate too low for model
  • Adam epsilon too high
  • No learning rate warmup
  • Optimizer beta values wrong

The fix and how to prevent it

Evaluate Denpex on your own logs

Request a Scale evaluation code. A verified workplace organization activates 14 days with up to 50 diagnoses a day. Every account keeps its current diagnosis allowance and gets a verification path. No card or automatic subscription.

We send a single-use code tied to that address. Static provider and TLD rules do not reject valid addresses. Account trust determines the benefit after signup.

Don't just read the fix, diagnose your run

The encyclopedia tells you what went wrong. Denpex tells you what went wrong in YOUR training run. With your logs, your config, and your stack.