We're hosting an in-person LLM bootcamp in the SF Bay Area on November 14, 2023. Join us if you want to see the most up-to-date materials for building and learning LLM-powered products in a hands-on environment.

https://www.scale.bythebay.io/llm-workshop

I hope to see some of you there!

—————————————— —– ———————————– How to hyper-tune your model parameters?
More videos at https://course.fullstackdeeplearning.com

Resume
– Deep learning models are literally full of hyper parameters. Finding the best configuration for these variables in a high-dimensional space is not trivial.
– Searching for hyperparameters is an iterative process limited by computing power, money and time. Therefore, it would be very useful to have software that allows you to search through hyperparameter settings.
– Hyperopt is a Python library for serial and parallel optimization of difficult search spaces, which can contain real, discrete and conditional dimensions.
– SigOpt is an optimization-as-a-service API that allows users to seamlessly tune configuration parameters in AI and ML models.
– Tune is a Python library for tuning hyperparameters at any scale, developed under the open source project Ray.
– Weights & Biases has a nice feature called “Hyperparameter Sweeps” – a way to efficiently select the right model for a given data set using the tool.

Please take the opportunity to connect and share this video with your friends and family if you find it helpful.