rl_agent_config.json

{
  "encoder": "jhu-clsp/mmBERT-base",
  "head_layers": 2,
  "max_len": 512,
  "head_max_len": 256,
  "max_prefixes": 6,
  "act_costs": {
    "escalate": 0.5
  },
  "cost_wrong_act": 3.0,
  "amp_dtype": "bf16",
  "model_name": "fin-laya-multilingual",
  "temperature": [
    1.0483462810516357,
    1.0,
    1.0
  ],
  "temperature_by_options": {
    "choice:3-5": 1.04791259765625,
    "choice:2": 1.05064058303833,
    "choice:6-10": 1.0429390668869019
  },
  "fine_tuned": true
}