{
  "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": 235.125,
      "epoch": 0.5714285714285714,
      "grad_norm": 0.719251275062561,
      "kl": 0.018632536637596786,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 7.403837613761425,
      "reward_std": 2.832583747804165,
      "rewards/concensus_correctness_reward_func": 4.842500004917383,
      "rewards/consensus_reward_func": 0.8125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.75,
      "rewards/question_recreation_reward_func": 0.4324629046022892,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.5507500108797103,
      "step": 2
    },
    {
      "completion_length": 194.33333333333334,
      "epoch": 1.0,
      "grad_norm": 0.5000922083854675,
      "kl": 0.024344088820119698,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 7.088017543156941,
      "reward_std": 6.5747577746709185,
      "rewards/concensus_correctness_reward_func": 4.4671666622161865,
      "rewards/consensus_reward_func": 0.4166666666666667,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.0833333333333333,
      "rewards/question_recreation_reward_func": 0.40068403134743374,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.020833333333333332,
      "rewards/xmlcount_reward_func": 0.6993333399295807,
      "step": 4
    },
    {
      "completion_length": 231.625,
      "epoch": 1.5714285714285714,
      "grad_norm": 0.6255844235420227,
      "kl": 0.019780708593316376,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 8.139673069119453,
      "reward_std": 7.334193199872971,
      "rewards/concensus_correctness_reward_func": 5.883750019595027,
      "rewards/consensus_reward_func": 0.75,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.625,
      "rewards/question_recreation_reward_func": 0.3895164867863059,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.49140624701976776,
      "step": 6
    },
    {
      "completion_length": 269.5416666666667,
      "epoch": 2.0,
      "grad_norm": 0.2735935151576996,
      "kl": 0.014208727516233921,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 5.879089325666428,
      "reward_std": 5.360636328657468,
      "rewards/concensus_correctness_reward_func": 3.9179166158040366,
      "rewards/consensus_reward_func": 0.3333333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.5833333333333334,
      "rewards/question_recreation_reward_func": 0.5887975841760635,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.4557083236674468,
      "step": 8
    },
    {
      "completion_length": 263.03125,
      "epoch": 2.571428571428571,
      "grad_norm": 5.347126007080078,
      "kl": 0.025529303937219083,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 7.180706441402435,
      "reward_std": 6.711122043430805,
      "rewards/concensus_correctness_reward_func": 4.514312498271465,
      "rewards/consensus_reward_func": 0.6875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.0625,
      "rewards/question_recreation_reward_func": 0.4703629408031702,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.03125,
      "rewards/xmlcount_reward_func": 0.4147812370210886,
      "step": 10
    },
    {
      "completion_length": 230.125,
      "epoch": 3.0,
      "grad_norm": 0.6963402032852173,
      "kl": 0.018198103954394657,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 5.397032817204793,
      "reward_std": 6.055237953861554,
      "rewards/concensus_correctness_reward_func": 2.6818333392341933,
      "rewards/consensus_reward_func": 0.5833333333333334,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.8333333333333334,
      "rewards/question_recreation_reward_func": 0.5188660720984141,
      "rewards/soft_format_reward_func": 0.020833333333333332,
      "rewards/strict_format_reward_func": 0.08333333333333333,
      "rewards/xmlcount_reward_func": 0.6755000154177347,
      "step": 12
    },
    {
      "completion_length": 299.9375,
      "epoch": 3.571428571428571,
      "grad_norm": 1.6188445091247559,
      "kl": 0.021726008621044457,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 3.9324587620794773,
      "reward_std": 4.088885299861431,
      "rewards/concensus_correctness_reward_func": 1.7436874955892563,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.875,
      "rewards/question_recreation_reward_func": 0.5333650894463062,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.5147812645882368,
      "step": 14
    },
    {
      "completion_length": 279.0416666666667,
      "epoch": 4.0,
      "grad_norm": 2.9491569995880127,
      "kl": 0.020901469358553488,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 5.768438816070557,
      "reward_std": 6.013046940167745,
      "rewards/concensus_correctness_reward_func": 3.805833319822947,
      "rewards/consensus_reward_func": 0.4166666666666667,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.75,
      "rewards/question_recreation_reward_func": 0.378230491032203,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.020833333333333332,
      "rewards/xmlcount_reward_func": 0.39687501390775043,
      "step": 16
    },
    {
      "completion_length": 269.3125,
      "epoch": 4.571428571428571,
      "grad_norm": 0.7207682728767395,
      "kl": 0.02037756727077067,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 6.214492678642273,
      "reward_std": 6.405277006328106,
      "rewards/concensus_correctness_reward_func": 3.3895000256597996,
      "rewards/consensus_reward_func": 0.5625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.1875,
      "rewards/question_recreation_reward_func": 0.5334614105522633,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.5259062573313713,
      "step": 18
    },
    {
      "completion_length": 229.41666666666666,
      "epoch": 5.0,
      "grad_norm": 0.5527974367141724,
      "kl": 0.020960483389596146,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 6.4655817945798235,
      "reward_std": 4.613384789476792,
      "rewards/concensus_correctness_reward_func": 4.316916664441426,
      "rewards/consensus_reward_func": 0.4166666666666667,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.6666666666666666,
      "rewards/question_recreation_reward_func": 0.48474862178166706,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.020833333333333332,
      "rewards/xmlcount_reward_func": 0.5597500167787075,
      "step": 20
    },
    {
      "epoch": 5.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 1.798100684027304e-05,
      "train_runtime": 564.6712,
      "train_samples_per_second": 0.567,
      "train_steps_per_second": 0.035
    }
  ],
  "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": 4,
  "trial_name": null,
  "trial_params": null
}