{
  "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": 241.375,
      "epoch": 0.5714285714285714,
      "grad_norm": 18.91314125061035,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 4.494268886744976,
      "reward_std": 0.659155557746999,
      "rewards/concensus_correctness_reward_func": 1.9506250014528632,
      "rewards/consensus_reward_func": 0.9375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.7150813667103648,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0625,
      "rewards/xmlcount_reward_func": 0.8285625139251351,
      "step": 2
    },
    {
      "completion_length": 170.20833333333334,
      "epoch": 1.0,
      "grad_norm": 21.518081665039062,
      "kl": 1.1660978463478386,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0009,
      "reward": 5.892316182454427,
      "reward_std": 0.7085997781444652,
      "rewards/concensus_correctness_reward_func": 1.924833317597707,
      "rewards/consensus_reward_func": 1.4166666666666667,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.9082745363314947,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.1875,
      "rewards/xmlcount_reward_func": 1.2050416767597198,
      "step": 4
    },
    {
      "completion_length": 168.78125,
      "epoch": 1.5714285714285714,
      "grad_norm": 28654.76953125,
      "kl": 1190.526932534296,
      "learning_rate": 4.472851273490984e-07,
      "loss": 1.1905,
      "reward": 5.072421103715897,
      "reward_std": 1.378951239719754,
      "rewards/concensus_correctness_reward_func": 1.4344375059008598,
      "rewards/consensus_reward_func": 1.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.375,
      "rewards/question_recreation_reward_func": 0.8482648283243179,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.109375,
      "rewards/xmlcount_reward_func": 1.0553437564522028,
      "step": 6
    },
    {
      "completion_length": 203.79166666666666,
      "epoch": 2.0,
      "grad_norm": 91.56695556640625,
      "kl": 14.810836016510924,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0111,
      "reward": 4.737937867641449,
      "reward_std": 0.6826455221356204,
      "rewards/concensus_correctness_reward_func": 1.1815833238263924,
      "rewards/consensus_reward_func": 1.3333333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.9630212336778641,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.125,
      "rewards/xmlcount_reward_func": 1.1350000252326329,
      "step": 8
    },
    {
      "completion_length": 170.1875,
      "epoch": 2.571428571428571,
      "grad_norm": 50.522186279296875,
      "kl": 16.655639334581792,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0167,
      "reward": 5.022570252418518,
      "reward_std": 2.068594033829868,
      "rewards/concensus_correctness_reward_func": 1.6066250018775463,
      "rewards/consensus_reward_func": 1.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.8850077828392386,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.078125,
      "rewards/xmlcount_reward_func": 1.0778124928474426,
      "step": 10
    },
    {
      "completion_length": 133.54166666666666,
      "epoch": 3.0,
      "grad_norm": 597.9561767578125,
      "kl": 47.79180937260389,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0358,
      "reward": 5.702193597952525,
      "reward_std": 0.3240309691561076,
      "rewards/concensus_correctness_reward_func": 1.697833323230346,
      "rewards/consensus_reward_func": 1.5833333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.16666666666666666,
      "rewards/question_recreation_reward_func": 0.9767769972483317,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.10416666666666667,
      "rewards/xmlcount_reward_func": 1.1734166741371155,
      "step": 12
    },
    {
      "completion_length": 170.53125,
      "epoch": 3.571428571428571,
      "grad_norm": 31.776348114013672,
      "kl": 1.4045644905418158,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0014,
      "reward": 5.180432453751564,
      "reward_std": 0.39799850789131597,
      "rewards/concensus_correctness_reward_func": 1.376062492839992,
      "rewards/consensus_reward_func": 1.4375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.988057479262352,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.109375,
      "rewards/xmlcount_reward_func": 1.1444375179708004,
      "step": 14
    },
    {
      "completion_length": 180.91666666666666,
      "epoch": 4.0,
      "grad_norm": 27.417720794677734,
      "kl": 28.36734463647008,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0213,
      "reward": 4.723206460475922,
      "reward_std": 0.8197268722578883,
      "rewards/concensus_correctness_reward_func": 1.172333334883054,
      "rewards/consensus_reward_func": 1.0833333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.3333333333333333,
      "rewards/question_recreation_reward_func": 0.9045815169811249,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.08333333333333333,
      "rewards/xmlcount_reward_func": 1.1462916831175487,
      "step": 16
    },
    {
      "completion_length": 198.0,
      "epoch": 4.571428571428571,
      "grad_norm": 37.20878219604492,
      "kl": 37.27795463940129,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0373,
      "reward": 4.845614403486252,
      "reward_std": 0.5414760503917933,
      "rewards/concensus_correctness_reward_func": 1.4188124909996986,
      "rewards/consensus_reward_func": 1.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.9487081132829189,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.09375,
      "rewards/xmlcount_reward_func": 1.0718437694013119,
      "step": 18
    },
    {
      "completion_length": 181.08333333333334,
      "epoch": 5.0,
      "grad_norm": 37.08019256591797,
      "kl": 2.6332666520029306,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.002,
      "reward": 6.089526116847992,
      "reward_std": 2.58219914448758,
      "rewards/concensus_correctness_reward_func": 2.7640000035365424,
      "rewards/consensus_reward_func": 1.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.08333333333333333,
      "rewards/question_recreation_reward_func": 0.9599844515323639,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.14583333333333334,
      "rewards/xmlcount_reward_func": 1.1363750000794728,
      "step": 20
    },
    {
      "epoch": 5.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 0.13169335020356812,
      "train_runtime": 89.9305,
      "train_samples_per_second": 3.558,
      "train_steps_per_second": 0.222
    }
  ],
  "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
}