{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.4,
  "eval_steps": 500,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 60.875,
      "epoch": 0.8,
      "grad_norm": 11.54460620880127,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": -0.0,
      "reward": 1.057928904891014,
      "reward_std": 0.4130301158875227,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.75,
      "rewards/question_recreation_reward_func": 0.22980391420423985,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.078125,
      "step": 2
    },
    {
      "completion_length": 46.0,
      "epoch": 1.4,
      "grad_norm": 20.20862579345703,
      "kl": 0.0006413682131096721,
      "learning_rate": 4.415111107797445e-07,
      "loss": 0.0,
      "reward": 2.403201421101888,
      "reward_std": 0.11947024613618851,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 2.0,
      "rewards/question_recreation_reward_func": 0.2782013813654582,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.125,
      "step": 4
    },
    {
      "completion_length": 65.33333333333333,
      "epoch": 2.0,
      "grad_norm": 7.1093010902404785,
      "kl": 0.003498752814872811,
      "learning_rate": 2.934120444167326e-07,
      "loss": 0.0,
      "reward": 0.9607302248477936,
      "reward_std": 0.028399634330223005,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.6666666666666666,
      "rewards/question_recreation_reward_func": 0.16906354576349258,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.125,
      "step": 6
    },
    {
      "completion_length": 53.625,
      "epoch": 2.8,
      "grad_norm": 18.270339965820312,
      "kl": 0.014321320282761008,
      "learning_rate": 1.2500000000000005e-07,
      "loss": 0.0,
      "reward": 1.302920363843441,
      "reward_std": 0.06874886981677264,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.0,
      "rewards/question_recreation_reward_func": 0.2091703936457634,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.09375,
      "step": 8
    },
    {
      "completion_length": 57.0,
      "epoch": 3.4,
      "grad_norm": 11.339275360107422,
      "kl": 0.014808982765922943,
      "learning_rate": 1.507684480352292e-08,
      "loss": 0.0,
      "reward": 1.7219081123669941,
      "reward_std": 0.02633840839068095,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.3333333333333333,
      "rewards/question_recreation_reward_func": 0.263574759165446,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.125,
      "step": 10
    },
    {
      "epoch": 3.4,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": 5.096610766486265e-06,
      "train_runtime": 1640.2429,
      "train_samples_per_second": 0.024,
      "train_steps_per_second": 0.006
    }
  ],
  "logging_steps": 2,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}