{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 4.0,
      "epoch": 0.5714285714285714,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 4.170433700084686,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 2.125,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.045433690887875855,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 2
    },
    {
      "completion_length": 4.0,
      "epoch": 1.0,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 4.382551312446594,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 2.3333333333333335,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.049217987223528326,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 4
    },
    {
      "completion_length": 4.0,
      "epoch": 1.5714285714285714,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 4.2960715889930725,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 2.25,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.04607159286388196,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 6
    },
    {
      "completion_length": 4.0,
      "epoch": 2.0,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 4.215034127235413,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 2.1666666666666665,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.04836745125552019,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 8
    },
    {
      "completion_length": 4.0,
      "epoch": 2.571428571428571,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 4.163609206676483,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 2.125,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.038609186274698004,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 10
    },
    {
      "completion_length": 4.0,
      "epoch": 3.0,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 4.391650636990865,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 2.3333333333333335,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.05831732670776546,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 12
    },
    {
      "completion_length": 4.0,
      "epoch": 3.571428571428571,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 4.298481434583664,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 2.25,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.04848141656839289,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 14
    },
    {
      "completion_length": 4.0,
      "epoch": 4.0,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 4.211820999781291,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 2.1666666666666665,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.04515435298283895,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 16
    },
    {
      "completion_length": 4.0,
      "epoch": 4.571428571428571,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 4.43020036816597,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 2.375,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.05520035425433889,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 18
    },
    {
      "completion_length": 4.0,
      "epoch": 5.0,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 4.036195755004883,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 2.0,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.036195769401577614,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 20
    },
    {
      "epoch": 5.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 0.0,
      "train_runtime": 2178.6687,
      "train_samples_per_second": 0.147,
      "train_steps_per_second": 0.009
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 25,
  "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
}