{
  "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": 104.09375,
      "epoch": 0.1,
      "grad_norm": 25.348953247070312,
      "kl": 0.0,
      "learning_rate": 4.965903258506806e-07,
      "loss": 0.0,
      "reward": 0.13653645635349676,
      "reward_std": 0.04201191869651666,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.13653645635349676,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 2
    },
    {
      "completion_length": 147.34375,
      "epoch": 0.2,
      "grad_norm": 12.91701889038086,
      "kl": 0.0023361076132459857,
      "learning_rate": 4.698684378016222e-07,
      "loss": 0.0,
      "reward": 0.13926166243618354,
      "reward_std": 0.11621385781472782,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.07532416592584923,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0014375000027939677,
      "step": 4
    },
    {
      "completion_length": 205.875,
      "epoch": 0.3,
      "grad_norm": 12.690685272216797,
      "kl": 0.012232648907229304,
      "learning_rate": 4.193203929064353e-07,
      "loss": 0.0,
      "reward": 0.08384110947372392,
      "reward_std": 0.02645172486154479,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.08384110947372392,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 6
    },
    {
      "completion_length": 196.46875,
      "epoch": 0.4,
      "grad_norm": 7.485862731933594,
      "kl": 0.009418848934728885,
      "learning_rate": 3.5042385616324236e-07,
      "loss": 0.0,
      "reward": 0.06871419967501424,
      "reward_std": 0.05813445482272073,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.07905795014812611,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.010343750473111868,
      "step": 8
    },
    {
      "completion_length": 201.25,
      "epoch": 0.5,
      "grad_norm": 9.880281448364258,
      "kl": 0.04116427912231302,
      "learning_rate": 2.706448363680831e-07,
      "loss": 0.0,
      "reward": 0.07922810240415856,
      "reward_std": 0.2537691785219067,
      "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": 0.051415600057225674,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.09718749858438969,
      "step": 10
    },
    {
      "completion_length": 225.34375,
      "epoch": 0.6,
      "grad_norm": 6.051862716674805,
      "kl": 0.011327921754855197,
      "learning_rate": 1.886286282148002e-07,
      "loss": 0.0,
      "reward": 0.04080450284527615,
      "reward_std": 0.06154873145715101,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.07552325155120343,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.03471875051036477,
      "step": 12
    },
    {
      "completion_length": 218.5,
      "epoch": 0.7,
      "grad_norm": 10.04811954498291,
      "kl": 0.02201609269832261,
      "learning_rate": 1.1326296046939333e-07,
      "loss": 0.0,
      "reward": 0.1823840587749146,
      "reward_std": 0.19762307521159528,
      "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": 0.06916530313901603,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.01178124942816794,
      "step": 14
    },
    {
      "completion_length": 299.0,
      "epoch": 0.8,
      "grad_norm": 3.884591579437256,
      "kl": 0.007397845016384963,
      "learning_rate": 5.271487265090163e-08,
      "loss": 0.0,
      "reward": 0.061117040779208764,
      "reward_std": 0.017384805101301026,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.061117040779208764,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 16
    },
    {
      "completion_length": 171.59375,
      "epoch": 0.9,
      "grad_norm": 9.748741149902344,
      "kl": 0.016323405121511314,
      "learning_rate": 1.3545689574841341e-08,
      "loss": 0.0,
      "reward": -0.1813788224826567,
      "reward_std": 0.5616935793786979,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.06830867152893916,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.3121875002980232,
      "step": 18
    },
    {
      "completion_length": 249.875,
      "epoch": 1.0,
      "grad_norm": 7.876495361328125,
      "kl": 0.015546673323115101,
      "learning_rate": 0.0,
      "loss": 0.0,
      "reward": 0.1155103390919976,
      "reward_std": 0.05686859134584665,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.1029790886095725,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.012531249783933163,
      "step": 20
    },
    {
      "epoch": 1.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 1.3833772391080856e-05,
      "train_runtime": 14443.4782,
      "train_samples_per_second": 0.022,
      "train_steps_per_second": 0.001
    }
  ],
  "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
}