{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "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": 102.625,
      "epoch": 0.1,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 7.87720650434494,
      "reward_std": 0.007132848259061575,
      "rewards/concensus_correctness_reward_func": 3.226000055670738,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.8699563220143318,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.4375,
      "rewards/xmlcount_reward_func": 1.09375,
      "step": 2
    },
    {
      "completion_length": 103.0625,
      "epoch": 0.2,
      "grad_norm": 3.626250982284546,
      "kl": 0.008273726458654096,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 7.306777089834213,
      "reward_std": 0.24014047719538212,
      "rewards/concensus_correctness_reward_func": 2.9752500355243683,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.841433115536347,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.328125,
      "rewards/xmlcount_reward_func": 1.0369687527418137,
      "step": 4
    },
    {
      "completion_length": 100.46875,
      "epoch": 0.3,
      "grad_norm": 0.0043119946494698524,
      "kl": 0.002871839186809666,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 7.470003575086594,
      "reward_std": 0.05245847627520561,
      "rewards/concensus_correctness_reward_func": 2.975250020623207,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.8755971881037112,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.421875,
      "rewards/xmlcount_reward_func": 1.0722812488675117,
      "step": 6
    },
    {
      "completion_length": 104.5,
      "epoch": 0.4,
      "grad_norm": 0.006978105287998915,
      "kl": 0.0060060035466449335,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 7.258690625429153,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 2.8510000109672546,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.8764404423709493,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.4375,
      "rewards/xmlcount_reward_func": 1.09375,
      "step": 8
    },
    {
      "completion_length": 96.46875,
      "epoch": 0.5,
      "grad_norm": 0.006472651846706867,
      "kl": 0.011245302681345493,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 7.7571210861206055,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 3.1005000472068787,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.8753709198790602,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.4375,
      "rewards/xmlcount_reward_func": 1.09375,
      "step": 10
    },
    {
      "completion_length": 106.46875,
      "epoch": 0.6,
      "grad_norm": 1.1906661987304688,
      "kl": 0.0061447054031305015,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 7.6786112785339355,
      "reward_std": 0.00010806451609823853,
      "rewards/concensus_correctness_reward_func": 2.975250020623207,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.9377360942889936,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.46875,
      "rewards/xmlcount_reward_func": 1.171875,
      "step": 12
    },
    {
      "completion_length": 107.65625,
      "epoch": 0.7,
      "grad_norm": 0.014152617193758488,
      "kl": 0.010811327054398134,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 8.179757595062256,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 3.2257500290870667,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.375,
      "rewards/question_recreation_reward_func": 0.9383823529351503,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.46875,
      "rewards/xmlcount_reward_func": 1.171875,
      "step": 14
    },
    {
      "completion_length": 78.65625,
      "epoch": 0.8,
      "grad_norm": 0.005709171760827303,
      "kl": 0.007365495897829533,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 7.164727538824081,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 2.975250020623207,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.7519773502135649,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.375,
      "rewards/xmlcount_reward_func": 0.9375,
      "step": 16
    },
    {
      "completion_length": 87.625,
      "epoch": 0.9,
      "grad_norm": 0.024852579459547997,
      "kl": 0.013064336191746406,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 8.087053120136261,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 3.351250037550926,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.5,
      "rewards/question_recreation_reward_func": 0.8139279344177339,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.40625,
      "rewards/xmlcount_reward_func": 1.015625,
      "step": 18
    },
    {
      "completion_length": 86.5,
      "epoch": 1.0,
      "grad_norm": 0.02088344842195511,
      "kl": 0.007403904091916047,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 7.5858025550842285,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 3.1002500355243683,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.8136774091544794,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.40625,
      "rewards/xmlcount_reward_func": 1.015625,
      "step": 20
    },
    {
      "epoch": 1.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 7.323394038394327e-06,
      "train_runtime": 4905.0742,
      "train_samples_per_second": 0.065,
      "train_steps_per_second": 0.004
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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
}