{
  "model": {
    "student": "mii-llm/nesso-0.4B-agentic",
    "teacher": "giux78/nesso-3B",
    "teacher_device": "",
    "gradient_checkpointing": true
  },
  "bridge": {
    "eos_map": {
      "<|im_end|>": "<|eot_id|>"
    },
    "extra_stop_tokens": [
      "<|end_of_text|>"
    ],
    "probe_texts": []
  },
  "data": {
    "prompts_path": "/home/ecuser/ai/zagreus_competition/data/prompts_v3.jsonl",
    "shots_path": "/home/ecuser/ai/zagreus_competition/data/5_shots.jsonl",
    "dev_size": 500,
    "p_reference_shots": 0.8,
    "p_pool_shots": 0.1,
    "pool_shots_max_k": 5,
    "system_message": ""
  },
  "sampling": {
    "batch_prompts": 32,
    "group_size": 1,
    "temperature": 1.0,
    "max_new_tokens": 8,
    "cot_fraction": 0.0,
    "cot_max_new_tokens": 300,
    "gen_micro_seqs": 64
  },
  "train": {
    "output_dir": "/home/ecuser/ai/palingenesis/runs/opd_v3",
    "steps": 600,
    "learning_rate": 1e-05,
    "warmup_steps": 50,
    "lr_scheduler": "cosine",
    "max_grad_norm": 1.0,
    "loss_fn": "full_kl",
    "seed": 0,
    "score_micro_seqs": 8,
    "eval_every": 50,
    "eval_dev_samples": 200,
    "save_steps": 50,
    "keep_checkpoints": 0
  },
  "logging": {
    "log_every": 10,
    "use_wandb": false,
    "project": "palingenesis-opd",
    "run_name": ""
  }
}