qrdlgit

> Fit consists of 2 steps, search and final fit. The "last trained model" is the best model during search and final fit with your entire training set. During the...

Is that really self-distillation? It sounds more like synthetic data generation and you're still distilling ChatGPT into the model. Don't get me wrong, it's a great approach and lets people...

Right, but it's the intelligence of ChatGPT you're distilling into your model. If a child learning math gives 4 answers to a math question, and then a teacher tells him...

I think a part of the issue above is that it's not the best example, as berries are a shorter form of the word raspberry and city is a shorter...

Also, make sure you 'debug' your question. Ask GPT4 why it might answer in a particular way. You may have to rephrase your question about why it hallucinated a bunch...

You are correct, my prompt addition didn't help. I think adding 'Ocean island' is probably a more appropriate resolution here. As an aside, I just got out my intro to...

Did this ever get done? Right now I use a beep but a notification would be really really helpful

Some more, brainstorming with gpt4: Sports Betting or Fantasy Sports,Social Media Trend Prediction, Climate change temps, CDC stuff (flus, etc), Polling (rcp daily averages?) An idea might be to use...

https://arxiv.org/pdf/2305.10601.pdf

Custom-eval.md is obsolete after the refactor, right? Eg, the evals.check_sampled_text used in arithmetic.py has been removed from Eval. See here - https://github.com/openai/evals/pull/579/files#diff-b14c6017190edd8585b6766159928c2a27512bab71a3ce84a027fc283dcfb240L101 I think it's now using the OpenAI completion...