{
  "accelerator_kwargs": {},
  "adap_kl_ctrl": false,
  "backward_batch_size": 5,
  "batch_size": 60,
  "cliprange": 0.2,
  "cliprange_value": 0.2,
  "compare_steps": 1,
  "early_stopping": true,
  "exp_name": "morlhf",
  "forward_batch_size": null,
  "gamma": 1,
  "global_backward_batch_size": 20,
  "global_batch_size": 240,
  "gradient_accumulation_steps": 5,
  "horizon": 10000,
  "init_kl_coef": 0.1,
  "is_encoder_decoder": false,
  "is_peft_model": true,
  "kl_penalty": "kl",
  "lam": 0.95,
  "learning_rate": 1e-05,
  "log_with": "wandb",
  "max_grad_norm": 0.5,
  "mini_batch_size": 1,
  "model_name": "unsloth/Qwen2.5-7B",
  "optimize_cuda_cache": true,
  "optimize_device_cache": false,
  "ppo_epochs": 4,
  "project_kwargs": {},
  "push_to_hub_if_best_kwargs": {},
  "query_dataset": "imdb",
  "ratio_threshold": 10.0,
  "remove_unused_columns": true,
  "reward_model": "sentiment-analysis:lvwerra/distilbert-imdb",
  "score_clip": null,
  "seed": 0,
  "steps": 20000,
  "target": 3,
  "target_kl": 1,
  "task_name": null,
  "tracker_kwargs": {
    "wandb": {
      "name": "maxmin-dpo-init-kl-coef-0.1-fix-lora"
    }
  },
  "tracker_project_name": "morlhf",
  "use_score_norm": false,
  "use_score_scaling": false,
  "vf_coef": 0.1,
  "whiten_rewards": false,
  "world_size": 4
}