Commit History
-
Update model references: Llama 3.3 70B → Llama 3.1 8B Instant, runtime 19.8min → ~10min
1e308ec -
Update greedy baseline numbers from latest test_local run; recalculate lifts
a251104
-
Reduce rollouts easy=2 medium=3 hard=3 — target ~15min runtime with buffer for judge overhead
219555f
-
Cut easy rollouts 3→2 to stay under 20min; update GRPO scores; fill config/tasks.yaml
3e4a196
-
Initial submission: Cascade Containment
1c03487