rl_agent_config.json

{
  "encoder": "answerdotai/ModernBERT-large",
  "head_layers": 2,
  "max_len": 512,
  "head_max_len": 192,
  "max_prefixes": 6,
  "act_costs": {
    "escalate": 0.5
  },
  "cost_wrong_act": 3.0,
  "amp_dtype": "bf16",
  "model_name": "rl-agent",
  "temperature": [
    1.6369030475616455,
    1.2514300346374512,
    1.983399510383606
  ],
  "temperature_by_options": {
    "choice:3-5": 1.7601518630981445,
    "choice:6-10": 1.0000158548355103,
    "score:3-5": 1.2514300346374512,
    "noul:2": 1.983399510383606,
    "choice:11+": 0.10058280825614929,
    "choice:2": 1.9063563346862793
  },
  "training": {
    "updates": 7313,
    "epochs_completed": 1,
    "hours": 1.96,
    "world_size": 1,
    "fine_tuned_from_checkpoint": true
  }
}