/tags/nemo-rl/ Recent content in NeMo-RL on Life and AI Hugo -- 0.160.0 en-us Fri, 13 Mar 2026 00:00:00 +0000 /posts/trading-llm/ Fri, 13 Mar 2026 00:00:00 +0000 /posts/trading-llm/ How I fine-tuned a 4B parameter LLM into a trading decision model using a 5-stage SFT waterfall and weighted CCE loss, then why I'm pivoting to GRPO reinforcement learning.