The Future is Fine Tuned (with Dev Rishi, Predibase)
Thinking Machines: AI & Philosophy
00:00
Fine-tuning Machine Learning Algorithms
Exploring the challenges and advancements in fine-tuning machine learning algorithms, including data availability issues, historical problems with data sets, and the evolution of parameter tweaking for better results. The conversation also delves into fine-tuning a GPT4 model, discussing factors like learning rate, batch size, epochs, and the simplification of the fine-tuning process through default settings and hyperparameter optimization.
Transcript
Play full episode
