CTGAN training failed error "Loss became NaN" synthetic tabular data crash

TL;DR

Fix this in CTGAN by acting on the exact message first: lower the discriminator and generator learning rates, scan numeric columns for infinities and extreme outliers and clip or drop them, and confirm no numeric column is constant, then restart training from scratch rather than resuming the NaN run. Do not rerun the whole job unchanged, because the same inputs produce the same failure. Prove the fix on one table, batch or record set first, then rerun the full scope and reconcile the counts.

Loss became NaN

Use this when

• The operation in CTGAN fails with this exact message or symptom: Loss became NaN.
• The same failure repeats on retry with unchanged inputs.
• Generation, validation or export is blocked until this item completes.

Not for this skill when

• The message is an outage notice from the platform. Resolve that first, then return here if this error remains.
• The operation completes and you only disagree with its output quality. That is a quality review, not this failure.

Steps

1. Reproduce the failure with the smallest scope that still shows it in CTGAN, and copy the full message plus the table, column or job involved into the run notes. Verify: the error is reproduced on demand with a named scope, not only seen in a log.
2. Apply the specific fix for this error: lower the discriminator and generator learning rates, scan numeric columns for infinities and extreme outliers and clip or drop them, and confirm no numeric column is constant, then restart training from scratch rather than resuming the NaN run. Verify: the smallest failing scope now completes, or the named column, table or job behaves as the fix predicts.
3. Check the neighbouring tables, columns or jobs that share the same config, schema or credential, because this class of failure rarely affects only one item. Verify: the neighbouring items are listed and each is marked affected or clear.
4. Rerun the original operation in CTGAN on the previously failing scope, watching for the same message rather than assuming success from a quiet log. Verify: the operation completes and the original message does not appear.
5. Compare the result counts, distributions or status against the source in CTGAN so a silent partial success is caught before sign off. Verify: counts match the source or every difference is named and explained.
6. Record the fix, the triggering input and the verification result on the item so the next occurrence is recognised immediately. Verify: the record names the error, the fix applied and the evidence of success.

Why it happens

CTGAN training destabilises when a learning rate is too high for the value ranges in the table or when infinite and extreme values poison the gradients, which propagates NaN through the loss.

Variant phrasings

Loss became NaN

The verbatim form searchers paste from the terminal or console. Treat it identically: same fix, same single scope proof, then the full rerun.

How to fix - CTGAN training failed error "Loss became NaN" synthetic tabular data crash

The how-to phrasing for the same failure in CTGAN. The steps above apply unchanged; start at the reproduction step rather than skipping to the rerun.

CTGAN troubleshooting for this failure

The symptom-first phrasing used when the console hides the full message. Surface the full message first, confirm it matches the code block above, then follow the steps.

Compatibility: CTGAN at current versions, plus the platform API or console the query names; no extra tooling beyond the source system access needed to verify counts.

Provenance

Resolved from the public thread: https://vectle.com/posts/pst_Gjk7Ou5x1sqIeuDtdluBbA

Resolved from the public thread: https://vectle.com/posts/pst_Gjk7Ou5x1sqIeuDtdluBbA

Thread query: CTGAN training failed error "Loss became NaN" synthetic tabular data crash

TL;DR: Fix this in CTGAN by acting on the exact message first: lower the discriminator and generator learning rates, scan numeric columns for infinities and extreme outliers and clip or drop them, and confirm no numeric column is constant, then restart training from scratch rather than resuming the NaN run. Do not rerun the whole job unchanged, because the same inputs produce the same failure. Prove the fix on one table, batch or record set first, then rerun the full scope and reconcile the counts.