{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.3389830508474576,
  "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": 440.1875,
      "epoch": 0.13559322033898305,
      "grad_norm": 2.6397361755371094,
      "kl": 0.23365284595638514,
      "learning_rate": 4.965903258506806e-07,
      "loss": 0.0002,
      "reward": 2.529710963368416,
      "reward_std": 2.834677182137966,
      "rewards/concensus_correctness_reward_func": 0.7976874969899654,
      "rewards/consensus_reward_func": 0.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.6875,
      "rewards/question_recreation_reward_func": 0.47633595019578934,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.03125,
      "rewards/xmlcount_reward_func": 0.34943751245737076,
      "step": 2
    },
    {
      "completion_length": 420.5625,
      "epoch": 0.2711864406779661,
      "grad_norm": 3.800398826599121,
      "kl": 0.25170137733221054,
      "learning_rate": 4.698684378016222e-07,
      "loss": 0.0003,
      "reward": 2.206221915781498,
      "reward_std": 2.4925178214907646,
      "rewards/concensus_correctness_reward_func": 0.7796249948441982,
      "rewards/consensus_reward_func": 0.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.5625,
      "rewards/question_recreation_reward_func": 0.4767844695597887,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.03125,
      "rewards/xmlcount_reward_func": 0.16856250911951065,
      "step": 4
    },
    {
      "completion_length": 443.625,
      "epoch": 0.4067796610169492,
      "grad_norm": 3.21205472946167,
      "kl": 0.20815220894291997,
      "learning_rate": 4.193203929064353e-07,
      "loss": 0.0002,
      "reward": 2.6189979696646333,
      "reward_std": 4.510454621165991,
      "rewards/concensus_correctness_reward_func": 1.3033749982714653,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.6875,
      "rewards/question_recreation_reward_func": 0.4360604081302881,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": -0.07356248795986176,
      "step": 6
    },
    {
      "completion_length": 418.28125,
      "epoch": 0.5423728813559322,
      "grad_norm": 2.976470470428467,
      "kl": 0.22151856869459152,
      "learning_rate": 3.5042385616324236e-07,
      "loss": 0.0002,
      "reward": 2.7691685780882835,
      "reward_std": 2.0635689543560147,
      "rewards/concensus_correctness_reward_func": 0.7698125019669533,
      "rewards/consensus_reward_func": 0.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.0,
      "rewards/question_recreation_reward_func": 0.48498106747865677,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.3112500011920929,
      "step": 8
    },
    {
      "completion_length": 365.59375,
      "epoch": 0.6779661016949152,
      "grad_norm": 2.282454252243042,
      "kl": 0.227860270999372,
      "learning_rate": 2.706448363680831e-07,
      "loss": 0.0002,
      "reward": 1.5446543842554092,
      "reward_std": 1.3974873423576355,
      "rewards/concensus_correctness_reward_func": 0.12262500077486038,
      "rewards/consensus_reward_func": 0.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.46612313482910395,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.03125,
      "rewards/xmlcount_reward_func": 0.4871562458574772,
      "step": 10
    },
    {
      "completion_length": 479.3125,
      "epoch": 0.8135593220338984,
      "grad_norm": 1.3404556512832642,
      "kl": 0.15829397086054087,
      "learning_rate": 1.886286282148002e-07,
      "loss": 0.0002,
      "reward": 1.287272036075592,
      "reward_std": 1.4873889423906803,
      "rewards/concensus_correctness_reward_func": 0.09025000035762787,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.3125,
      "rewards/question_recreation_reward_func": 0.576834574341774,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.22956250980496407,
      "step": 12
    },
    {
      "completion_length": 234.6875,
      "epoch": 0.9491525423728814,
      "grad_norm": 3.240541934967041,
      "kl": 0.23888456635177135,
      "learning_rate": 1.1326296046939333e-07,
      "loss": 0.0002,
      "reward": 3.257312387228012,
      "reward_std": 2.7849474009126425,
      "rewards/concensus_correctness_reward_func": 0.7554375007748604,
      "rewards/consensus_reward_func": 0.3125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.0625,
      "rewards/question_recreation_reward_func": 0.3787498604506254,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.046875,
      "rewards/xmlcount_reward_func": 0.7012499868869781,
      "step": 14
    },
    {
      "completion_length": 210.17857142857142,
      "epoch": 1.0677966101694916,
      "grad_norm": 2.6126480102539062,
      "kl": 0.34211112558841705,
      "learning_rate": 5.271487265090163e-08,
      "loss": 0.0003,
      "reward": 2.1737994636808122,
      "reward_std": 0.999560724411692,
      "rewards/concensus_correctness_reward_func": 0.14014285802841187,
      "rewards/consensus_reward_func": 0.21428571428571427,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.5714285714285714,
      "rewards/question_recreation_reward_func": 0.34758515522948336,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.8825000013623919,
      "step": 16
    },
    {
      "completion_length": 490.6875,
      "epoch": 1.2033898305084745,
      "grad_norm": 1.6640560626983643,
      "kl": 0.20682895462960005,
      "learning_rate": 1.3545689574841341e-08,
      "loss": 0.0002,
      "reward": 2.524849906563759,
      "reward_std": 2.5721453316509724,
      "rewards/concensus_correctness_reward_func": 0.6849999986588955,
      "rewards/consensus_reward_func": 0.3125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.8125,
      "rewards/question_recreation_reward_func": 0.5558498464524746,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0625,
      "rewards/xmlcount_reward_func": 0.09649999439716339,
      "step": 18
    },
    {
      "completion_length": 479.46875,
      "epoch": 1.3389830508474576,
      "grad_norm": 2.2770586013793945,
      "kl": 0.1806422220543027,
      "learning_rate": 0.0,
      "loss": 0.0002,
      "reward": 4.977065123617649,
      "reward_std": 4.180357031524181,
      "rewards/concensus_correctness_reward_func": 3.1328125,
      "rewards/consensus_reward_func": 0.375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.625,
      "rewards/question_recreation_reward_func": 0.47609641402959824,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.35253123939037323,
      "step": 20
    },
    {
      "epoch": 1.3389830508474576,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 0.00022269619221333415,
      "train_runtime": 773.4856,
      "train_samples_per_second": 0.414,
      "train_steps_per_second": 0.026
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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
}