OpenAI

Partial degradation of finetuned models outputs
Resolved·Degraded performance

After further investigation, this issue does not appear as widespread as initially thought. No known issue has been detected. We will continue to monitor for any incorrect outputs.

Sat, Sep 17, 2022, 01:03 AM
(2 years ago)
·
Affected components
Updates

Resolved

After further investigation, this issue does not appear as widespread as initially thought. No known issue has been detected. We will continue to monitor for any incorrect outputs.

Sat, Sep 17, 2022, 01:03 AM

Investigating

We are noticing certain inference calls to fine tuned models producing output that is incorrect.

Fri, Sep 16, 2022, 07:42 PM(5 hours earlier)
Powered by

Availability metrics are reported at an aggregate level across all tiers, models and error types. Individual customer availability may vary depending on their subscription tier as well as the specific model and API features in use.