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": {
    "choice:3-5": 1.35,
    "score:3-5": 1.35
  },
  "training": {
    "updates": 15987,
    "epochs_completed": 4,
    "hours": 4.97,
    "world_size": 1,
    "fine_tuned_from_checkpoint": true,
    "routing_finetune": {
      "rows": 9214,
      "synthetic_rows": 767,
      "epochs": 2,
      "select": "acc",
      "best_val_criterion": -0.8558,
      "temperatures": {
        "Q1_rubric_choice": 1.3,
        "Q2_minimal_choice": 1.4,
        "Q3_difficulty_score": 1.35
      },
      "seed": 1
    }
  }
}