{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "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": 365.546875,
      "epoch": 0.2,
      "grad_norm": 48.464141845703125,
      "kl": 0.2741623129550135,
      "learning_rate": 5e-07,
      "loss": 0.0003,
      "reward": 0.5328550898702815,
      "reward_std": 0.5821793463255744,
      "rewards/concensus_correctness_reward_func": 0.04249999951571226,
      "rewards/consensus_reward_func": 0.03125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.15625,
      "rewards/question_recreation_reward_func": 0.1691363404970616,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.13371874974109232,
      "step": 2
    },
    {
      "completion_length": 329.390625,
      "epoch": 0.4,
      "grad_norm": 40.2426643371582,
      "kl": 0.46259763339185156,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0005,
      "reward": 0.5276293288916349,
      "reward_std": 0.6059933826327324,
      "rewards/concensus_correctness_reward_func": 0.03962500020861626,
      "rewards/consensus_reward_func": 0.03125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.15625,
      "rewards/question_recreation_reward_func": 0.12744185369228944,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.17306249774992466,
      "step": 4
    },
    {
      "completion_length": 397.421875,
      "epoch": 0.6,
      "grad_norm": 36.80036163330078,
      "kl": 0.14088008002727292,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0001,
      "reward": 0.7648750487715006,
      "reward_std": 0.7097170217894018,
      "rewards/concensus_correctness_reward_func": 0.05981249921023846,
      "rewards/consensus_reward_func": 0.09375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.21875,
      "rewards/question_recreation_reward_func": 0.2059375497046858,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.18662500428035855,
      "step": 6
    },
    {
      "completion_length": 336.609375,
      "epoch": 0.8,
      "grad_norm": 5.585159778594971,
      "kl": 0.052440633764490485,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0001,
      "reward": 0.48294639913365245,
      "reward_std": 0.596011420013383,
      "rewards/concensus_correctness_reward_func": 0.026593749411404133,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.09375,
      "rewards/question_recreation_reward_func": 0.18702452059369534,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0078125,
      "rewards/xmlcount_reward_func": 0.16776562668383121,
      "step": 8
    },
    {
      "completion_length": 424.1875,
      "epoch": 1.0,
      "grad_norm": 7.8572564125061035,
      "kl": 11.62281682959292,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0116,
      "reward": 0.4830020550871268,
      "reward_std": 0.4901028564199805,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.03125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.16051768220495433,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.22873437637463212,
      "step": 10
    },
    {
      "completion_length": 325.859375,
      "epoch": 1.2,
      "grad_norm": 23.677793502807617,
      "kl": 0.88124192043324,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0009,
      "reward": 0.6852804254740477,
      "reward_std": 0.879037992330268,
      "rewards/concensus_correctness_reward_func": 0.09137500077486038,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.15625,
      "rewards/question_recreation_reward_func": 0.2148429078515619,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.2228124924004078,
      "step": 12
    },
    {
      "completion_length": 367.578125,
      "epoch": 1.4,
      "grad_norm": 134.31704711914062,
      "kl": 35.08971463656053,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0351,
      "reward": 0.9296793777029961,
      "reward_std": 0.9322110824286938,
      "rewards/concensus_correctness_reward_func": 0.043343749828636646,
      "rewards/consensus_reward_func": 0.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.21875,
      "rewards/question_recreation_reward_func": 0.20807001693174243,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0078125,
      "rewards/xmlcount_reward_func": 0.26420312630943954,
      "step": 14
    },
    {
      "completion_length": 455.671875,
      "epoch": 1.6,
      "grad_norm": 4.028388500213623,
      "kl": 0.04040217574220151,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 0.7450143881142139,
      "reward_std": 0.7296095467172563,
      "rewards/concensus_correctness_reward_func": 0.08962499909102917,
      "rewards/consensus_reward_func": 0.09375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.24062378116650507,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0078125,
      "rewards/xmlcount_reward_func": 0.12570312432944775,
      "step": 16
    },
    {
      "completion_length": 376.484375,
      "epoch": 1.8,
      "grad_norm": 9.968994140625,
      "kl": 0.04569235083181411,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 0.5937786751892418,
      "reward_std": 0.7739827702753246,
      "rewards/concensus_correctness_reward_func": 0.05674999952316284,
      "rewards/consensus_reward_func": 0.03125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.16788804030511528,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.2128906303551048,
      "step": 18
    },
    {
      "completion_length": 398.6875,
      "epoch": 2.0,
      "grad_norm": 13.42526626586914,
      "kl": 0.07575743750203401,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0001,
      "reward": 0.8230987135320902,
      "reward_std": 0.7707659895531833,
      "rewards/concensus_correctness_reward_func": 0.02800000086426735,
      "rewards/consensus_reward_func": 0.03125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.15625,
      "rewards/question_recreation_reward_func": 0.27567685034591705,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.33192187175154686,
      "step": 20
    },
    {
      "epoch": 2.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 0.004868576209992171,
      "train_runtime": 1468.8334,
      "train_samples_per_second": 0.436,
      "train_steps_per_second": 0.014
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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
}