rl_agent_config.json

{
  "encoder": "jhu-clsp/mmBERT-base",
  "head_layers": 2,
  "max_len": 384,
  "head_max_len": 128,
  "max_prefixes": 6,
  "act_costs": {
    "escalate": 0.5
  },
  "cost_wrong_act": 3.0,
  "amp_dtype": "bf16",
  "model_name": "s1-code-v2",
  "temperature": [
    1.0,
    1.0,
    1.0459754467010498
  ],
  "training": {
    "updates": 15987,
    "epochs_completed": 4,
    "hours": 4.97,
    "world_size": 1,
    "fine_tuned_from_checkpoint": false
  },
  "fine_tuned": true,
  "temperature_calibrated": true
}