{
  "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": 229.40625,
      "epoch": 0.5714285714285714,
      "grad_norm": 8.94824504852295,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": -0.0,
      "reward": 3.6037507504224777,
      "reward_std": 0.3731326290871948,
      "rewards/concensus_correctness_reward_func": 0.676999993622303,
      "rewards/consensus_reward_func": 0.875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.7892507291398942,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.234375,
      "rewards/xmlcount_reward_func": 0.9656250048428774,
      "step": 2
    },
    {
      "completion_length": 125.875,
      "epoch": 1.0,
      "grad_norm": 14.84840202331543,
      "kl": 0.46425252586292726,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0003,
      "reward": 6.8231503168741865,
      "reward_std": 0.10737764012689392,
      "rewards/concensus_correctness_reward_func": 2.1921666661898294,
      "rewards/consensus_reward_func": 1.6666666666666667,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.3333333333333333,
      "rewards/question_recreation_reward_func": 0.9018170038859049,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.4791666666666667,
      "rewards/xmlcount_reward_func": 1.25,
      "step": 4
    },
    {
      "completion_length": 132.59375,
      "epoch": 1.5714285714285714,
      "grad_norm": 254.22254943847656,
      "kl": 11.826677680423018,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0118,
      "reward": 6.039749294519424,
      "reward_std": 0.6479331548325717,
      "rewards/concensus_correctness_reward_func": 1.6617499887943268,
      "rewards/consensus_reward_func": 1.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.9921555258333683,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.40625,
      "rewards/xmlcount_reward_func": 1.2295937538146973,
      "step": 6
    },
    {
      "completion_length": 171.375,
      "epoch": 2.0,
      "grad_norm": 19.998477935791016,
      "kl": 340.6913535793622,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.2555,
      "reward": 5.803202708562215,
      "reward_std": 0.16267990817626318,
      "rewards/concensus_correctness_reward_func": 1.4191666543483734,
      "rewards/consensus_reward_func": 1.8333333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.08333333333333333,
      "rewards/question_recreation_reward_func": 0.9248277222116789,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.3541666666666667,
      "rewards/xmlcount_reward_func": 1.1883750061194103,
      "step": 8
    },
    {
      "completion_length": 146.1875,
      "epoch": 2.571428571428571,
      "grad_norm": 513047.0,
      "kl": 35970.45797069557,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 35.9705,
      "reward": 5.927468925714493,
      "reward_std": 0.30307131272275,
      "rewards/concensus_correctness_reward_func": 1.6851249858736992,
      "rewards/consensus_reward_func": 1.5625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.9142189472913742,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.40625,
      "rewards/xmlcount_reward_func": 1.234375,
      "step": 10
    },
    {
      "completion_length": 128.20833333333334,
      "epoch": 3.0,
      "grad_norm": 116.38948822021484,
      "kl": 18.222534152989585,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0137,
      "reward": 6.312762300173442,
      "reward_std": 0.2930445207554537,
      "rewards/concensus_correctness_reward_func": 1.7012499918540318,
      "rewards/consensus_reward_func": 1.75,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.16666666666666666,
      "rewards/question_recreation_reward_func": 0.9923039476076762,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.4583333333333333,
      "rewards/xmlcount_reward_func": 1.2442083358764648,
      "step": 12
    },
    {
      "completion_length": 153.875,
      "epoch": 3.571428571428571,
      "grad_norm": 487.3103332519531,
      "kl": 15.634163164300844,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0156,
      "reward": 6.4225940108299255,
      "reward_std": 0.4366847704950487,
      "rewards/concensus_correctness_reward_func": 1.8357499986886978,
      "rewards/consensus_reward_func": 1.75,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.3125,
      "rewards/question_recreation_reward_func": 0.9323440082371235,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.40625,
      "rewards/xmlcount_reward_func": 1.185750000178814,
      "step": 14
    },
    {
      "completion_length": 143.75,
      "epoch": 4.0,
      "grad_norm": 32.51670455932617,
      "kl": 24.17860255079965,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0181,
      "reward": 5.551972270011902,
      "reward_std": 0.7521393178030849,
      "rewards/concensus_correctness_reward_func": 1.5078333169221878,
      "rewards/consensus_reward_func": 1.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.9879722644885381,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.3541666666666667,
      "rewards/xmlcount_reward_func": 1.2020000020662944,
      "step": 16
    },
    {
      "completion_length": 144.78125,
      "epoch": 4.571428571428571,
      "grad_norm": 15.651232719421387,
      "kl": 1.0096438335021958,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.001,
      "reward": 6.347037583589554,
      "reward_std": 0.3279493277950678,
      "rewards/concensus_correctness_reward_func": 1.7443749941885471,
      "rewards/consensus_reward_func": 1.8125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.9502876587212086,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.46875,
      "rewards/xmlcount_reward_func": 1.2461249977350235,
      "step": 18
    },
    {
      "completion_length": 147.58333333333334,
      "epoch": 5.0,
      "grad_norm": 14.92544937133789,
      "kl": 23.108698587554198,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0173,
      "reward": 5.848908384641011,
      "reward_std": 0.16538670177881917,
      "rewards/concensus_correctness_reward_func": 1.6329999913771946,
      "rewards/consensus_reward_func": 1.3333333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.9971583286921183,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.3958333333333333,
      "rewards/xmlcount_reward_func": 1.2395833333333333,
      "step": 20
    },
    {
      "epoch": 5.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 3.6303929208574117,
      "train_runtime": 122.946,
      "train_samples_per_second": 2.603,
      "train_steps_per_second": 0.163
    }
  ],
  "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
}