Orca: Progressive Learning from Complex Explanation Traces of GPT-4

Re:Orca: Progressive Learning from Complex Explanation Trace... by riku_iki on Tuesday June 13, 2023 @02:23PM (#36314541)

> one can produce high quality training data with the LLM itself which the next iteration of that model can use. Rinse and repeat.

it may be higher quality, but far from perfection.

After many rinses and repeats dataset will accumulate significant amount of errors.

[ Parent | on HN ]

Re:Orca: Progressive Learning from Complex Explanation Trace... by Tostino on Thursday June 15, 2023 @03:06AM (#36337329)

That depends. You can implement an error checking algorithm with the LLM itself to check for drift in meaning and loss of original context from version to version as you improve your training dataset, as well as measure performance as you train new versions of your LLM on that dataset.

[ Parent | on HN ]