Training an Expert Finance LLM
The Data Phoenix team invites you to our upcoming webinar, which will take place on June 12th at 10 a.m. PT.
Topic: Training an Expert Finance LLM
Speakers: Mark Kim-Huang (Co-founder and Chief Architect at Gradient)
Participation: free (but you’ll be required to register)
The challenge with financial agents successfully completing complex workflows like tabular reasoning or sentiment analysis often comes down to the reliability of executing numerous chained tasks together. Establishing the p99s necessary has to happen at the model level, yet most finance domain-specific LLMs are either only pre-training (BloombergGPT) or using supervised fine-tuning (FinBERT).
This presentation reveals how we transformed an open-source model into Albatross, capable of performing at the top of the leaderboard on chat as well as domain-specific tasks. Our journey involved an intensive data pipeline and training regiment, incorporating a combination of continual pre-training, fine-tuning, and preference optimization, to customize the model for the intricacies of financial tasks. We'll share our insights on overcoming the execution hurdle, which is often the downfall of AI projects in specialized domains.
Key Highlights of the Webinar:
Building Domain-Specific Models: Explore how to evolve an open-source model into a leading domain-specific model like Albatross - capable of excelling in both general and domain-specific tasks.
Model Transformation Techniques: Learn about the intensive data pipeline and training regimen that included continual pre-training, fine-tuning, and preference optimization.
Customization for Financial Tasks: Understand the specific strategies used to tailor Albatross for financial tasks, addressing the unique intricacies of this field.
Importance of Performance Metrics: Gain insight into why establishing high-performance benchmarks (like p99s) at the model level is crucial for success in finance-specific applications, where current financial LLMs often focus only on pre-training or supervised fine-tuning.
Speaker
Mark is a co-founder and Chief Architect at Gradient, a full stack AI platform that enables businesses to build customized agents to power enterprise workloads. Known for his pioneering work in LLMs and fine-tuning, Mark is a frequent contributor to the AI and MLOps community. Prior to Gradient, Mark led machine learning teams at Splunk and Box, transitioning over from a nearly decade-long career as an algorithmic trader at quantitative hedge funds like Stevens Capital, Paloma Partners, and TD Securities. Mark holds a dual bachelors degree in mathematics and finance from the University of Pennsylvania.