rl_agent_config.json

{
  "encoder": "answerdotai/ModernBERT-large",
  "head_layers": 2,
  "max_len": 2048,
  "head_max_len": 320,
  "max_prefixes": 6,
  "act_costs": {
    "escalate": 0.5
  },
  "cost_wrong_act": 3.0,
  "amp_dtype": "bf16",
  "model_name": "coding-decision-agent",
  "temperature": [
    1.116161,
    1.091507,
    1.2
  ],
  "training": {
    "updates": 7313,
    "epochs_completed": 1,
    "hours": 1.96,
    "world_size": 1,
    "fine_tuned_from_checkpoint": true
  },
  "gradient_checkpointing": false,
  "max_tokens_per_batch": 16384,
  "fine_tuned": true,
  "head_max_len_train": 320
}