{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.7272727272727275,
  "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": 485.375,
      "epoch": 0.7272727272727273,
      "grad_norm": 0.46356967091560364,
      "kl": 0.0006885775619593915,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 1.2886099740862846,
      "reward_std": 1.0936285629868507,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.6098599601536989,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.3037500036880374,
      "step": 2
    },
    {
      "completion_length": 412.67857142857144,
      "epoch": 1.3636363636363638,
      "grad_norm": 0.4725421071052551,
      "kl": 0.0007597233883903495,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 0.05788119988782065,
      "reward_std": 0.9135433307715825,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.07142857142857142,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.36470261961221695,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.37825000498976025,
      "step": 4
    },
    {
      "completion_length": 445.67857142857144,
      "epoch": 2.0,
      "grad_norm": 0.3603663146495819,
      "kl": 0.0006844874088918525,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 0.8103399872779846,
      "reward_std": 1.038728028535843,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.2857142857142857,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5441256782838276,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": -0.037357138735907416,
      "step": 6
    },
    {
      "completion_length": 454.59375,
      "epoch": 2.7272727272727275,
      "grad_norm": 0.28744569420814514,
      "kl": 0.0006660163635388017,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 0.7709572687745094,
      "reward_std": 1.0267691239714622,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.43351975828409195,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.07181250862777233,
      "step": 8
    },
    {
      "completion_length": 441.07142857142856,
      "epoch": 3.3636363636363638,
      "grad_norm": 0.5901888608932495,
      "kl": 0.0007456234972258764,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 0.8694685186658587,
      "reward_std": 1.0195827228682381,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.2857142857142857,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6238256778035846,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.0400714459163802,
      "step": 10
    },
    {
      "completion_length": 447.64285714285717,
      "epoch": 4.0,
      "grad_norm": 0.2877914607524872,
      "kl": 0.0006377353607344308,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 0.9620583398001534,
      "reward_std": 1.000628330877849,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.35714285714285715,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.627058357000351,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.022142855184418813,
      "step": 12
    },
    {
      "completion_length": 460.875,
      "epoch": 4.7272727272727275,
      "grad_norm": 0.3677603006362915,
      "kl": 0.0006959485108382069,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 0.7318503968417645,
      "reward_std": 0.8866724520921707,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.48185040429234505,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0625000037252903,
      "step": 14
    },
    {
      "completion_length": 508.2142857142857,
      "epoch": 5.363636363636363,
      "grad_norm": 0.4596138000488281,
      "kl": 0.0007280998480772334,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 0.8560242014271873,
      "reward_std": 0.8382286131381989,
      "rewards/concensus_correctness_reward_func": 0.033285713621548245,
      "rewards/consensus_reward_func": 0.21428571428571427,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5611670400415149,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.04728572656001363,
      "step": 16
    },
    {
      "completion_length": 382.7857142857143,
      "epoch": 6.0,
      "grad_norm": 0.24859537184238434,
      "kl": 0.0007194839459511318,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 0.8212329830442157,
      "reward_std": 0.8151673674583435,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.07142857142857142,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5104115701147488,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.03571428571428571,
      "rewards/xmlcount_reward_func": 0.2036785834601947,
      "step": 18
    },
    {
      "completion_length": 432.375,
      "epoch": 6.7272727272727275,
      "grad_norm": 0.4400365352630615,
      "kl": 0.0006472563909483142,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 0.8123836005106568,
      "reward_std": 0.9522764729335904,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5303210988640785,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.09456250071525574,
      "step": 20
    },
    {
      "epoch": 6.7272727272727275,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 6.273632436659682e-07,
      "train_runtime": 590.7803,
      "train_samples_per_second": 0.542,
      "train_steps_per_second": 0.034
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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
}