Layer Norm Weight Decay
Applying weight decay to LayerNorm and bias parameters hurts training and can prevent convergence in transformers.
Applying weight decay to LayerNorm and bias parameters hurts training and can prevent convergence in transformers.
What this failure is
Layer Norm Weight Decay is a Training Stability failure seen during ML training runs. Applying weight decay to LayerNorm and bias parameters hurts training and can prevent convergence in transformers. Common tags: Weight Decay, Layer Norm, Adamw, Fine Tuning.
Is this what broke your run? Paste your log.
You're reading about Layer Norm Weight Decay. 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.
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.
Why it happens (the mechanism)
Weight decay applied to LayerNorm gamma and bias. Weight decay applied to embedding layer. AdamW with default parameter groups includes all params. No normalization in weight decay application. 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
- Model doesn't converge with weight decay
- Validation loss is unstable
- Weight decay hurts transformer training
Common symptoms and what they mean
| Symptom | Why it happens |
|---|---|
| Validation loss is much higher than expected | Weight decay applied to LayerNorm gamma and bias |
| Loss spikes with weight decay | Weight decay applied to embedding layer |
| Fine-tuning underperforms training from scratch | AdamW with default parameter groups includes all params |
Which systems are affected
- Fine-tuning transformer models
- Training transformers with AdamW
- Vision transformer training
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: Validation loss is much higher than expected
- ✓Verified signal present: Loss spikes with weight decay
- ✓Verified signal present: Fine-tuning underperforms training from scratch
- ✓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 analysisNo 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 extensionRelated failures to investigate next
Root cause
- Weight decay applied to LayerNorm gamma and bias
- Weight decay applied to embedding layer
- AdamW with default parameter groups includes all params
- No normalization in weight decay application
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.
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.