{
  "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": 472.75,
      "epoch": 0.1,
      "grad_norm": 4.972134113311768,
      "kl": 0.0,
      "learning_rate": 4.965903258506806e-07,
      "loss": -0.0,
      "reward": 0.8231485052965581,
      "reward_std": 1.2553124479018152,
      "rewards/concensus_correctness_reward_func": 0.13868749793618917,
      "rewards/consensus_reward_func": 0.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.38033601630013436,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.07087501464411616,
      "step": 2
    },
    {
      "completion_length": 404.34375,
      "epoch": 0.2,
      "grad_norm": 7.311157703399658,
      "kl": 0.0009687572946859291,
      "learning_rate": 4.698684378016222e-07,
      "loss": 0.0,
      "reward": 0.47689660359174013,
      "reward_std": 0.7753186682239175,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.28077160858083516,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.07112499827053398,
      "step": 4
    },
    {
      "completion_length": 397.8125,
      "epoch": 0.3,
      "grad_norm": 12.540438652038574,
      "kl": 0.001213116767758038,
      "learning_rate": 4.193203929064353e-07,
      "loss": 0.0,
      "reward": 0.320636167190969,
      "reward_std": 0.6216559750464512,
      "rewards/concensus_correctness_reward_func": 0.03693750128149986,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.1836361801251769,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.08743749931454659,
      "step": 6
    },
    {
      "completion_length": 253.09375,
      "epoch": 0.4,
      "grad_norm": 117.53514862060547,
      "kl": 0.04831917503543082,
      "learning_rate": 3.5042385616324236e-07,
      "loss": 0.0,
      "reward": 0.3986110386031214,
      "reward_std": 0.4029649797012098,
      "rewards/concensus_correctness_reward_func": 0.015625,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.2335172927705571,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.08696874883025885,
      "step": 8
    },
    {
      "completion_length": 313.5625,
      "epoch": 0.5,
      "grad_norm": 8.876846313476562,
      "kl": 0.00187252888281364,
      "learning_rate": 2.706448363680831e-07,
      "loss": 0.0,
      "reward": 0.46869485336355865,
      "reward_std": 0.6680965052219108,
      "rewards/concensus_correctness_reward_func": -0.011062500067055225,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.28053860645741224,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.01171874301508069,
      "step": 10
    },
    {
      "completion_length": 403.1875,
      "epoch": 0.6,
      "grad_norm": 6.0552473068237305,
      "kl": 0.0020919858761772048,
      "learning_rate": 1.886286282148002e-07,
      "loss": 0.0,
      "reward": 0.5102090919390321,
      "reward_std": 0.9569540836382657,
      "rewards/concensus_correctness_reward_func": 0.10056249983608723,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.30486532411305234,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.08271874906495214,
      "step": 12
    },
    {
      "completion_length": 457.28125,
      "epoch": 0.7,
      "grad_norm": 4.433928489685059,
      "kl": 0.0026758583626360632,
      "learning_rate": 1.1326296046939333e-07,
      "loss": 0.0,
      "reward": 0.9141725162044168,
      "reward_std": 0.7021154585527256,
      "rewards/concensus_correctness_reward_func": 0.02274999930523336,
      "rewards/consensus_reward_func": 0.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.4190162750892341,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.2224062472814694,
      "step": 14
    },
    {
      "completion_length": 321.5,
      "epoch": 0.8,
      "grad_norm": 20.360118865966797,
      "kl": 0.0045296397038328,
      "learning_rate": 5.271487265090163e-08,
      "loss": 0.0,
      "reward": 0.5812048423686065,
      "reward_std": 0.5352981987709882,
      "rewards/concensus_correctness_reward_func": 0.03956250101327896,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.3840485939872451,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.029906250536441803,
      "step": 16
    },
    {
      "completion_length": 505.71875,
      "epoch": 0.9,
      "grad_norm": 5.112046718597412,
      "kl": 0.0033627474076638464,
      "learning_rate": 1.3545689574841341e-08,
      "loss": 0.0,
      "reward": 0.8375814352184534,
      "reward_std": 0.8647369077662006,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.3907376849092543,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.3218437498435378,
      "step": 18
    },
    {
      "completion_length": 352.875,
      "epoch": 1.0,
      "grad_norm": 3.8864283561706543,
      "kl": 0.0029916863204562105,
      "learning_rate": 0.0,
      "loss": 0.0,
      "reward": 1.0474416308570653,
      "reward_std": 0.6638899724930525,
      "rewards/concensus_correctness_reward_func": 0.09231250081211329,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.4742853690404445,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.1683437500614673,
      "step": 20
    },
    {
      "epoch": 1.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 6.804741133237258e-06,
      "train_runtime": 399.5968,
      "train_samples_per_second": 0.801,
      "train_steps_per_second": 0.05
    }
  ],
  "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
}