Commit History
-
Run 3: Qwen2.5-0.5B GRPO 500 steps | reward 0.96→1.75 | conflict 0.375→0.1875 | dashboard chart | agents wired
0a0a4fc -
add lora checkpoints and training updates
099deaf -
Fix: task difficulty counts, dashboard legend modal, training metrics, reward curve, /metrics/history endpoint
cfa1b2b
-
feat: implement full multi-agent realism (agent specialization, conflict injection, partial observability, logging, metrics export)
14d515d
