Taewhoo/qwen3.5-9b-proteomics-rl-step75
020
qwen3.5-9b-proteomics — RL step 75
RL checkpoint (step 75) of the proteomics co-scientist run (series: sft → rl-step25 → rl-step75 → rl-step100). Internal eval100 score at this step: 0.25.
RL checkpoint (step 75) of the proteomics co-scientist run (series: sft → rl-step25 → rl-step75 → rl-step100). Internal eval100 score at this step: 0.25.