{
  "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": 395.34375,
      "epoch": 0.1,
      "grad_norm": 2.942415714263916,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": -0.0,
      "reward": 4.82016151829157,
      "reward_std": 0.3854319729580311,
      "rewards/concensus_correctness_reward_func": 1.6233750209212303,
      "rewards/consensus_reward_func": 1.6875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.8228491918416694,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.6864374991273507,
      "step": 2
    },
    {
      "completion_length": 603.625,
      "epoch": 0.2,
      "grad_norm": 3.712937116622925,
      "kl": 0.007950323895784095,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 6.120330538367853,
      "reward_std": 0.8978197081014514,
      "rewards/concensus_correctness_reward_func": 2.37100001424551,
      "rewards/consensus_reward_func": 1.875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.9387369712349027,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.8105937503278255,
      "step": 4
    },
    {
      "completion_length": 451.78125,
      "epoch": 0.3,
      "grad_norm": 2.235194683074951,
      "kl": 0.02212194656021893,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 5.639864379772916,
      "reward_std": 0.10886181774549186,
      "rewards/concensus_correctness_reward_func": 1.8710000216960907,
      "rewards/consensus_reward_func": 1.875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.9393020665738732,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.8295625001192093,
      "step": 6
    },
    {
      "completion_length": 600.5,
      "epoch": 0.4,
      "grad_norm": 1.8900405168533325,
      "kl": 0.023399058531140327,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 5.101709506008774,
      "reward_std": 0.13587851080228575,
      "rewards/concensus_correctness_reward_func": 1.68825002014637,
      "rewards/consensus_reward_func": 1.625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.8575533987022936,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.8059062492102385,
      "step": 8
    },
    {
      "completion_length": 597.75,
      "epoch": 0.5,
      "grad_norm": 1.7744187116622925,
      "kl": 0.0325103204959305,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 5.327111101709306,
      "reward_std": 0.15980166662484407,
      "rewards/concensus_correctness_reward_func": 1.7175000235438347,
      "rewards/consensus_reward_func": 1.8125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.9372050231322646,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.8599062506109476,
      "step": 10
    },
    {
      "completion_length": 333.0,
      "epoch": 0.6,
      "grad_norm": 3.0704152584075928,
      "kl": 0.061392479052301496,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0001,
      "reward": 5.442457564175129,
      "reward_std": 0.18317094245139742,
      "rewards/concensus_correctness_reward_func": 1.8037500232458115,
      "rewards/consensus_reward_func": 1.875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.9111139676533639,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.8525937497615814,
      "step": 12
    },
    {
      "completion_length": 166.90625,
      "epoch": 0.7,
      "grad_norm": 2.7164864540100098,
      "kl": 0.0852923730853945,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0001,
      "reward": 5.533616041764617,
      "reward_std": 0.028979253096622415,
      "rewards/concensus_correctness_reward_func": 1.8037500232458115,
      "rewards/consensus_reward_func": 1.875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.9400849614758044,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.9147812500596046,
      "step": 14
    },
    {
      "completion_length": 172.8125,
      "epoch": 0.8,
      "grad_norm": 4.465137004852295,
      "kl": 0.08196320277056657,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0001,
      "reward": 4.294622145476751,
      "reward_std": 0.24379761278396472,
      "rewards/concensus_correctness_reward_func": 1.382750015705824,
      "rewards/consensus_reward_func": 1.4375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.7603097828105092,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.7140624998137355,
      "step": 16
    },
    {
      "completion_length": 167.0625,
      "epoch": 0.9,
      "grad_norm": 0.8931539058685303,
      "kl": 0.0848374804481864,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0001,
      "reward": 5.734549235552549,
      "reward_std": 0.0494141704402864,
      "rewards/concensus_correctness_reward_func": 1.9335000216960907,
      "rewards/consensus_reward_func": 1.75,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.9111743867397308,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.8898750003427267,
      "step": 18
    },
    {
      "completion_length": 168.1875,
      "epoch": 1.0,
      "grad_norm": 2.627840042114258,
      "kl": 0.08800861740019172,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0001,
      "reward": 4.813556069973856,
      "reward_std": 0.05021095206029713,
      "rewards/concensus_correctness_reward_func": 1.56325002014637,
      "rewards/consensus_reward_func": 1.625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.8363062436692417,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.7890000008046627,
      "step": 20
    },
    {
      "epoch": 1.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 5.336687299859477e-05,
      "train_runtime": 34232.129,
      "train_samples_per_second": 0.009,
      "train_steps_per_second": 0.001
    }
  ],
  "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
}