{
  "grpo": {
    "num_generations": 4,
    "temperature": 0.9,
    "max_completion_length": 512,
    "num_iterations": 1,
    "beta": 0.0,
    "epsilon": 0.2
  },
  "training": {
    "per_device_train_batch_size": 1,
    "gradient_accumulation_steps": 8,
    "learning_rate": 5e-06,
    "num_train_epochs": 3,
    "warmup_ratio": 0.1,
    "lr_scheduler_type": "cosine",
    "bf16": false,
    "logging_steps": 10,
    "save_steps": 500,
    "save_total_limit": 3,
    "fp16": true
  },
  "model": {
    "name_or_path": "kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s3.1",
    "trust_remote_code": true,
    "dtype": "float16"
  },
  "vllm_flags": [
    "--enforce-eager",
    "--dtype",
    "float16"
  ],
  "lora": {
    "r": 16,
    "alpha": 32,
    "target_modules": [
      "q_proj",
      "k_proj",
      "v_proj",
      "o_proj",
      "gate_proj",
      "up_proj",
      "down_proj"
    ],
    "dropout": 0.05,
    "task_type": "CAUSAL_LM",
    "bias": "none"
  }
}