Taewhoo/qwen3.5-9b-proteomics-rl-step150
019
qwen3.5-9b-proteomics — RL step 150
RL checkpoint (step 150) of the proteomics co-scientist run (series: sft → rl-step25 → 56 → 75 → 100 → 125 → 150). Internal eval100 score at this step: 0.48.
RL checkpoint (step 150) of the proteomics co-scientist run (series: sft → rl-step25 → 56 → 75 → 100 → 125 → 150). Internal eval100 score at this step: 0.48.