rl_agent_config.json

{
  "encoder": "jhu-clsp/mmBERT-base",
  "head_layers": 2,
  "max_len": 1024,
  "head_max_len": 256,
  "max_prefixes": 6,
  "act_costs": {
    "escalate": 0.5
  },
  "cost_wrong_act": 3.0,
  "amp_dtype": "bf16",
  "model_name": "rl-agent",
  "temperature": [
    1.0,
    1.0,
    1.0
  ],
  "temperature_by_options": {
    "noul:2": 1.85,
    "choice:2": 2.0,
    "choice:6-10": 5.0
  },
  "training": {
    "updates": 15987,
    "epochs_completed": 4,
    "hours": 4.97,
    "world_size": 1,
    "fine_tuned_from_checkpoint": false,
    "pi_scanner_finetune": {
      "rows": 184203,
      "epochs": 4,
      "best_epoch": 3,
      "seed": 5,
      "excluded": []
    }
  }
}