{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.7272727272727275,
  "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": 493.09375,
      "epoch": 0.7272727272727273,
      "grad_norm": 19.217636108398438,
      "kl": 0.0011702408446581103,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 1.405498445034027,
      "reward_std": 0.94932034984231,
      "rewards/concensus_correctness_reward_func": 0.017999999225139618,
      "rewards/consensus_reward_func": 0.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.47096719685941935,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.03125,
      "rewards/xmlcount_reward_func": 0.38528125965967774,
      "step": 2
    },
    {
      "completion_length": 477.2142857142857,
      "epoch": 1.3636363636363638,
      "grad_norm": 0.34427568316459656,
      "kl": 0.0007293328609583634,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 0.7860592518533979,
      "reward_std": 0.8674239729131971,
      "rewards/concensus_correctness_reward_func": 0.030142856495720998,
      "rewards/consensus_reward_func": 0.42857142857142855,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.374666411961828,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": -0.06517856248787471,
      "step": 4
    },
    {
      "completion_length": 464.17857142857144,
      "epoch": 2.0,
      "grad_norm": 0.2992457449436188,
      "kl": 0.0007828814975385155,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 1.2176040070397514,
      "reward_std": 0.9366523197719029,
      "rewards/concensus_correctness_reward_func": 0.08085714067731585,
      "rewards/consensus_reward_func": 0.42857142857142855,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.423675468989781,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.2845000113759722,
      "step": 6
    },
    {
      "completion_length": 416.875,
      "epoch": 2.7272727272727275,
      "grad_norm": 1.6301639080047607,
      "kl": 0.001307578495470807,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 1.0240302421152592,
      "reward_std": 0.9169644303619862,
      "rewards/concensus_correctness_reward_func": 0.04437499865889549,
      "rewards/consensus_reward_func": 0.3125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.39487397111952305,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.2566562509164214,
      "step": 8
    },
    {
      "completion_length": 488.2857142857143,
      "epoch": 3.3636363636363638,
      "grad_norm": 0.41716712713241577,
      "kl": 0.0012800927756221167,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 1.2444563167435783,
      "reward_std": 1.2771144764763969,
      "rewards/concensus_correctness_reward_func": 0.06314285578472274,
      "rewards/consensus_reward_func": 0.35714285714285715,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.3460634670087269,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.46024998809610096,
      "step": 10
    },
    {
      "completion_length": 451.60714285714283,
      "epoch": 4.0,
      "grad_norm": 0.22203044593334198,
      "kl": 0.000720701870575015,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 1.0469175236565726,
      "reward_std": 1.0470092296600342,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.42857142857142855,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5656318260090691,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.03485713792698724,
      "step": 12
    },
    {
      "completion_length": 515.53125,
      "epoch": 4.7272727272727275,
      "grad_norm": 0.5425270795822144,
      "kl": 0.0007404747229884379,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 1.1888295784592628,
      "reward_std": 0.8663323745131493,
      "rewards/concensus_correctness_reward_func": 0.07324999943375587,
      "rewards/consensus_reward_func": 0.3125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.42651709727942944,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.37656251387670636,
      "step": 14
    },
    {
      "completion_length": 498.82142857142856,
      "epoch": 5.363636363636363,
      "grad_norm": 0.4237583577632904,
      "kl": 0.0007124320171507341,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 1.024352667587144,
      "reward_std": 0.6125156283378601,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.35714285714285715,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5225669869354793,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.14464285969734192,
      "step": 16
    },
    {
      "completion_length": 447.64285714285717,
      "epoch": 6.0,
      "grad_norm": 0.24781115353107452,
      "kl": 0.0006924252333452127,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 1.0331759282520838,
      "reward_std": 0.9632131372179303,
      "rewards/concensus_correctness_reward_func": 0.08085714067731585,
      "rewards/consensus_reward_func": 0.2857142857142857,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.3932830457176481,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.2733214327267238,
      "step": 18
    },
    {
      "completion_length": 481.5625,
      "epoch": 6.7272727272727275,
      "grad_norm": 0.5104337334632874,
      "kl": 0.0007607093502883799,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 1.1216800138354301,
      "reward_std": 0.8741806000471115,
      "rewards/concensus_correctness_reward_func": 0.05274999886751175,
      "rewards/consensus_reward_func": 0.375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.3667425373569131,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.03125,
      "rewards/xmlcount_reward_func": 0.23343750461935997,
      "step": 20
    },
    {
      "epoch": 6.7272727272727275,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 8.081094904355268e-07,
      "train_runtime": 611.7777,
      "train_samples_per_second": 0.523,
      "train_steps_per_second": 0.033
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 4,
  "trial_name": null,
  "trial_params": null
}