{
  "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": 390.03125,
      "epoch": 0.5714285714285714,
      "grad_norm": 4.594613552093506,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 1.5640735495835543,
      "reward_std": 1.0756708699045703,
      "rewards/concensus_correctness_reward_func": 0.12306250259280205,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.6395110553130507,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.42649999633431435,
      "step": 2
    },
    {
      "completion_length": 333.4166666666667,
      "epoch": 1.0,
      "grad_norm": 3.120675802230835,
      "kl": 0.000950229751955097,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 2.7605074644088745,
      "reward_std": 1.5603865360996376,
      "rewards/concensus_correctness_reward_func": 1.001249998807907,
      "rewards/consensus_reward_func": 0.16666666666666666,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.4166666666666667,
      "rewards/question_recreation_reward_func": 0.6655908338725567,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.5103333368897438,
      "step": 4
    },
    {
      "completion_length": 387.25,
      "epoch": 1.5714285714285714,
      "grad_norm": 3.850229263305664,
      "kl": 0.0018060091351799201,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 1.1355717438273132,
      "reward_std": 0.8171830275095999,
      "rewards/concensus_correctness_reward_func": 0.08443750068545341,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.47488424426410347,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.2637499973643571,
      "step": 6
    },
    {
      "completion_length": 452.9583333333333,
      "epoch": 2.0,
      "grad_norm": 2.610008955001831,
      "kl": 0.0022001210648644096,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 2.4789030564328036,
      "reward_std": 2.4222442638128996,
      "rewards/concensus_correctness_reward_func": 1.029000001649062,
      "rewards/consensus_reward_func": 0.3333333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.5990280422071615,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.26754167303442955,
      "step": 8
    },
    {
      "completion_length": 278.625,
      "epoch": 2.571428571428571,
      "grad_norm": 6.401039123535156,
      "kl": 0.0036217248416505754,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 2.4230608055368066,
      "reward_std": 1.5129187877755612,
      "rewards/concensus_correctness_reward_func": 0.8043124955147505,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.5613733162172139,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.6823750017210841,
      "step": 10
    },
    {
      "completion_length": 423.5416666666667,
      "epoch": 3.0,
      "grad_norm": 2.7323479652404785,
      "kl": 0.0030003479526688657,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 1.9484529917438824,
      "reward_std": 0.8329733513916532,
      "rewards/concensus_correctness_reward_func": 0.2524166703224182,
      "rewards/consensus_reward_func": 0.3333333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.3333333333333333,
      "rewards/question_recreation_reward_func": 0.5193696220715841,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.5099999979138374,
      "step": 12
    },
    {
      "completion_length": 400.25,
      "epoch": 3.571428571428571,
      "grad_norm": 4.567859172821045,
      "kl": 0.0042203699485980906,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 2.257055907510221,
      "reward_std": 2.6319831679575145,
      "rewards/concensus_correctness_reward_func": 0.8898124992847443,
      "rewards/consensus_reward_func": 0.375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.4455558266490698,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.29668750055134296,
      "step": 14
    },
    {
      "completion_length": 317.6666666666667,
      "epoch": 4.0,
      "grad_norm": 2.69461989402771,
      "kl": 0.01197023045582076,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 1.6769403691093128,
      "reward_std": 1.2003674041479826,
      "rewards/concensus_correctness_reward_func": 0.1905000035961469,
      "rewards/consensus_reward_func": 0.4166666666666667,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.08333333333333333,
      "rewards/question_recreation_reward_func": 0.5291903335601091,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.45725000090897083,
      "step": 16
    },
    {
      "completion_length": 338.125,
      "epoch": 4.571428571428571,
      "grad_norm": 6.53850793838501,
      "kl": 0.005134969163918868,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 1.880478024482727,
      "reward_std": 1.034826172864996,
      "rewards/concensus_correctness_reward_func": 0.23850000277161598,
      "rewards/consensus_reward_func": 0.3125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.5909155270783231,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.613562504760921,
      "step": 18
    },
    {
      "completion_length": 324.6666666666667,
      "epoch": 5.0,
      "grad_norm": 3.0015549659729004,
      "kl": 0.006128522703268875,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 1.5900338552892208,
      "reward_std": 0.6957436619947354,
      "rewards/concensus_correctness_reward_func": 0.15366666515668234,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.464533847446243,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.4718333389610052,
      "step": 20
    },
    {
      "epoch": 5.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 3.3445656299591063e-06,
      "train_runtime": 338.4825,
      "train_samples_per_second": 0.945,
      "train_steps_per_second": 0.059
    }
  ],
  "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
}