{
  "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": 188.90625,
      "epoch": 0.5714285714285714,
      "grad_norm": 11.504660606384277,
      "kl": 0.0,
      "learning_rate": 4.965903258506806e-07,
      "loss": 0.0,
      "reward": 3.6299600526690483,
      "reward_std": 0.651573613169603,
      "rewards/concensus_correctness_reward_func": 0.7819999903440475,
      "rewards/consensus_reward_func": 1.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.77814756706357,
      "rewards/soft_format_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.171875,
      "rewards/xmlcount_reward_func": 0.8198125020135194,
      "step": 2
    },
    {
      "completion_length": 139.29166666666666,
      "epoch": 1.0,
      "grad_norm": 19.680736541748047,
      "kl": 0.018907852994743735,
      "learning_rate": 4.698684378016222e-07,
      "loss": 0.0,
      "reward": 6.1616571346918745,
      "reward_std": 0.4250478910592695,
      "rewards/concensus_correctness_reward_func": 1.862833318610986,
      "rewards/consensus_reward_func": 1.5833333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.16666666666666666,
      "rewards/question_recreation_reward_func": 0.9973237961530685,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.3541666666666667,
      "rewards/xmlcount_reward_func": 1.1973333358764648,
      "step": 4
    },
    {
      "completion_length": 144.9375,
      "epoch": 1.5714285714285714,
      "grad_norm": 23.490110397338867,
      "kl": 0.24136288941372186,
      "learning_rate": 4.193203929064353e-07,
      "loss": 0.0002,
      "reward": 5.961412996053696,
      "reward_std": 0.5539119137974922,
      "rewards/concensus_correctness_reward_func": 1.8196874968707561,
      "rewards/consensus_reward_func": 1.5625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.9034442752599716,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.390625,
      "rewards/xmlcount_reward_func": 1.22265625,
      "step": 6
    },
    {
      "completion_length": 157.95833333333334,
      "epoch": 2.0,
      "grad_norm": 11.857107162475586,
      "kl": 0.6173685067333281,
      "learning_rate": 3.5042385616324236e-07,
      "loss": 0.0005,
      "reward": 5.671488285064697,
      "reward_std": 0.6377726250017682,
      "rewards/concensus_correctness_reward_func": 1.3618333016832669,
      "rewards/consensus_reward_func": 1.8333333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.940946638584137,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.3125,
      "rewards/xmlcount_reward_func": 1.2228749990463257,
      "step": 8
    },
    {
      "completion_length": 137.90625,
      "epoch": 2.571428571428571,
      "grad_norm": 19.347959518432617,
      "kl": 7.246092613320798,
      "learning_rate": 2.706448363680831e-07,
      "loss": 0.0072,
      "reward": 5.676198855042458,
      "reward_std": 0.36480392375960946,
      "rewards/concensus_correctness_reward_func": 1.6264374908059835,
      "rewards/consensus_reward_func": 1.5625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.8661676824558526,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.328125,
      "rewards/xmlcount_reward_func": 1.16796875,
      "step": 10
    },
    {
      "completion_length": 143.5,
      "epoch": 3.0,
      "grad_norm": 9.921439170837402,
      "kl": 0.7624614595746001,
      "learning_rate": 1.886286282148002e-07,
      "loss": 0.0006,
      "reward": 6.447582880655925,
      "reward_std": 0.052944420681645475,
      "rewards/concensus_correctness_reward_func": 1.7801666458447774,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.9799163043498993,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.4375,
      "rewards/xmlcount_reward_func": 1.25,
      "step": 12
    },
    {
      "completion_length": 143.15625,
      "epoch": 3.571428571428571,
      "grad_norm": 22.13187026977539,
      "kl": 1.8785493820905685,
      "learning_rate": 1.1326296046939333e-07,
      "loss": 0.0019,
      "reward": 5.9165933430194855,
      "reward_std": 0.3377845502400305,
      "rewards/concensus_correctness_reward_func": 1.6038749888539314,
      "rewards/consensus_reward_func": 1.75,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.9151558466255665,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.359375,
      "rewards/xmlcount_reward_func": 1.2256875038146973,
      "step": 14
    },
    {
      "completion_length": 136.83333333333334,
      "epoch": 4.0,
      "grad_norm": 6.5841965675354,
      "kl": 14.041547794515887,
      "learning_rate": 5.271487265090163e-08,
      "loss": 0.0105,
      "reward": 5.688777546087901,
      "reward_std": 0.5299860953819007,
      "rewards/concensus_correctness_reward_func": 1.557333316653967,
      "rewards/consensus_reward_func": 1.3333333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.16666666666666666,
      "rewards/question_recreation_reward_func": 0.9697359601656595,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.4375,
      "rewards/xmlcount_reward_func": 1.2242083350817363,
      "step": 16
    },
    {
      "completion_length": 142.4375,
      "epoch": 4.571428571428571,
      "grad_norm": 77.4472885131836,
      "kl": 2.3539611261803657,
      "learning_rate": 1.3545689574841341e-08,
      "loss": 0.0024,
      "reward": 6.306179732084274,
      "reward_std": 0.5243307306227507,
      "rewards/concensus_correctness_reward_func": 1.7168749906122684,
      "rewards/consensus_reward_func": 1.875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.976023480296135,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.4375,
      "rewards/xmlcount_reward_func": 1.23828125,
      "step": 18
    },
    {
      "completion_length": 146.875,
      "epoch": 5.0,
      "grad_norm": 674.2899780273438,
      "kl": 40.880931643148266,
      "learning_rate": 0.0,
      "loss": 0.0307,
      "reward": 5.47615905602773,
      "reward_std": 0.3092364342495178,
      "rewards/concensus_correctness_reward_func": 1.635416644314925,
      "rewards/consensus_reward_func": 1.4166666666666667,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.9729507366816202,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.2708333333333333,
      "rewards/xmlcount_reward_func": 1.1802916675806046,
      "step": 20
    },
    {
      "epoch": 5.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 0.0053957260796778424,
      "train_runtime": 95.7573,
      "train_samples_per_second": 3.342,
      "train_steps_per_second": 0.209
    }
  ],
  "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
}