{
  "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": 483.8125,
      "epoch": 0.7272727272727273,
      "grad_norm": 0.4184405207633972,
      "kl": 0.0007234725198941305,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 0.7045045606791973,
      "reward_std": 0.8394088111817837,
      "rewards/concensus_correctness_reward_func": 0.0078125,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.5646920502185822,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.1804999839514494,
      "step": 2
    },
    {
      "completion_length": 504.4642857142857,
      "epoch": 1.3636363636363638,
      "grad_norm": 0.5454363822937012,
      "kl": 0.0007511950097978115,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 1.0028131221021925,
      "reward_std": 1.126203939318657,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.2857142857142857,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.07142857142857142,
      "rewards/question_recreation_reward_func": 0.32374168400253567,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.3219285724418504,
      "step": 4
    },
    {
      "completion_length": 526.5,
      "epoch": 2.0,
      "grad_norm": 0.3296413719654083,
      "kl": 0.0006561284119795476,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 0.9751809239387512,
      "reward_std": 1.2371410812650407,
      "rewards/concensus_correctness_reward_func": -0.004071429371833801,
      "rewards/consensus_reward_func": 0.14285714285714285,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.14285714285714285,
      "rewards/question_recreation_reward_func": 0.5420380703040532,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.13364285869257791,
      "step": 6
    },
    {
      "completion_length": 464.34375,
      "epoch": 2.7272727272727275,
      "grad_norm": 0.4796897768974304,
      "kl": 0.0021317518876458053,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 0.9232642352581024,
      "reward_std": 1.166212558746338,
      "rewards/concensus_correctness_reward_func": 0.0078125,
      "rewards/consensus_reward_func": 0.375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.3210767302662134,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.219375004991889,
      "step": 8
    },
    {
      "completion_length": 598.6428571428571,
      "epoch": 3.3636363636363638,
      "grad_norm": 0.3463391959667206,
      "kl": 0.0007349734660238028,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 1.8327125289610453,
      "reward_std": 2.5424040130206516,
      "rewards/concensus_correctness_reward_func": 0.6923571420567376,
      "rewards/consensus_reward_func": 0.14285714285714285,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.42857142857142855,
      "rewards/question_recreation_reward_func": 0.6093196677310126,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.04039285225527627,
      "step": 10
    },
    {
      "completion_length": 501.64285714285717,
      "epoch": 4.0,
      "grad_norm": 0.24949033558368683,
      "kl": 0.0006643205872803394,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 0.7059421454157148,
      "reward_std": 0.8951797613075801,
      "rewards/concensus_correctness_reward_func": 0.017857142857142856,
      "rewards/consensus_reward_func": 0.21428571428571427,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.4061564419950758,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0676428633076804,
      "step": 12
    },
    {
      "completion_length": 557.3125,
      "epoch": 4.7272727272727275,
      "grad_norm": 0.41972818970680237,
      "kl": 0.0005867193431186024,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 1.082656467333436,
      "reward_std": 1.291143488138914,
      "rewards/concensus_correctness_reward_func": -0.013250000774860382,
      "rewards/consensus_reward_func": 0.375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.47859397903084755,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.007687479257583618,
      "step": 14
    },
    {
      "completion_length": 460.10714285714283,
      "epoch": 5.363636363636363,
      "grad_norm": 0.4573427736759186,
      "kl": 0.0008041951306430357,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 0.9158965008599418,
      "reward_std": 0.9635738602706364,
      "rewards/concensus_correctness_reward_func": 0.026785714285714284,
      "rewards/consensus_reward_func": 0.2857142857142857,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5480036437511444,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.03753571292119367,
      "step": 16
    },
    {
      "completion_length": 586.2857142857143,
      "epoch": 6.0,
      "grad_norm": 0.4108085334300995,
      "kl": 0.0005893616928785507,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 1.8432286190135139,
      "reward_std": 2.636557706764766,
      "rewards/concensus_correctness_reward_func": 0.6923571314130511,
      "rewards/consensus_reward_func": 0.42857142857142855,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.21428571428571427,
      "rewards/question_recreation_reward_func": 0.49419292381831575,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": -0.004035708095346179,
      "step": 18
    },
    {
      "completion_length": 548.59375,
      "epoch": 6.7272727272727275,
      "grad_norm": 0.36424583196640015,
      "kl": 0.0007183377165347338,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 2.033046916127205,
      "reward_std": 2.6044920682907104,
      "rewards/concensus_correctness_reward_func": 0.6058124899864197,
      "rewards/consensus_reward_func": 0.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.660671953111887,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.06343750469386578,
      "step": 20
    },
    {
      "epoch": 6.7272727272727275,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 7.809135922798304e-07,
      "train_runtime": 1529.8944,
      "train_samples_per_second": 0.209,
      "train_steps_per_second": 0.013
    }
  ],
  "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
}