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.
We experienced a period of elevated error rates and increased processing delays for fine-tuning jobs on the babbage-002 and davinci-002 models. The root cause has been identified and a fix implemented. Jobs for these two models are processing normally, and jobs for other models (gpt-3.5-turbo-0613, etc) were not impacted.
No components marked as affected
Resolved
We experienced a period of elevated error rates and increased processing delays for fine-tuning jobs on the babbage-002 and davinci-002 models. The root cause has been identified and a fix implemented. Jobs for these two models are processing normally, and jobs for other models (gpt-3.5-turbo-0613, etc) were not impacted.