{
  "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": 560.875,
      "epoch": 0.5714285714285714,
      "grad_norm": 3.723012924194336,
      "kl": 0.001292824381380342,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 0.2683439403772354,
      "reward_std": 0.4880548566579819,
      "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": 0.18340644519776106,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.08493749611079693,
      "step": 2
    },
    {
      "completion_length": 368.5,
      "epoch": 1.0,
      "grad_norm": 2.7846364974975586,
      "kl": 0.0019923485233448446,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 0.3504849374294281,
      "reward_std": 0.5885173020263513,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.16666666666666666,
      "rewards/question_recreation_reward_func": 0.32073493115603924,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.13691666078132889,
      "step": 4
    },
    {
      "completion_length": 404.0625,
      "epoch": 1.5714285714285714,
      "grad_norm": 1.3856635093688965,
      "kl": 0.001339340211416129,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 0.17506105825304985,
      "reward_std": 0.17539560986915603,
      "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": 0.26862356066703796,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.09356250427663326,
      "step": 6
    },
    {
      "completion_length": 362.5833333333333,
      "epoch": 2.0,
      "grad_norm": 3.5829715728759766,
      "kl": 0.0027290927149200193,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 0.13131776824593544,
      "reward_std": 1.2102658259512584,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.3333333333333333,
      "rewards/question_recreation_reward_func": 0.34065108249584836,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.5426666289567947,
      "step": 8
    },
    {
      "completion_length": 574.5625,
      "epoch": 2.571428571428571,
      "grad_norm": 1.413923740386963,
      "kl": 0.001252249610843137,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 0.6071861740201712,
      "reward_std": 0.5157831413671374,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.2425611785147339,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.2396250031888485,
      "step": 10
    },
    {
      "completion_length": 349.0833333333333,
      "epoch": 3.0,
      "grad_norm": 0.9041206240653992,
      "kl": 0.0015493201305313657,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 0.0826210839052995,
      "reward_std": 0.5416930752495924,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.16666666666666666,
      "rewards/question_recreation_reward_func": 0.2487044216444095,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.3327499922985832,
      "step": 12
    },
    {
      "completion_length": 445.6875,
      "epoch": 3.571428571428571,
      "grad_norm": 2.1271238327026367,
      "kl": 0.011247969196119811,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 0.35610084887593985,
      "reward_std": 0.3311492399079725,
      "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": 0.19797584787011147,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.033125000074505806,
      "step": 14
    },
    {
      "completion_length": 408.8333333333333,
      "epoch": 4.0,
      "grad_norm": 0.9073309302330017,
      "kl": 0.0028479883524899683,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 0.3536644255121549,
      "reward_std": 0.37826905337472755,
      "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": 0.20783109093705812,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.14583333333333334,
      "step": 16
    },
    {
      "completion_length": 434.5625,
      "epoch": 4.571428571428571,
      "grad_norm": 1.3901129961013794,
      "kl": 0.0013948993582744151,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 0.8019987307488918,
      "reward_std": 0.349066823546309,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.22418621787801385,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.3278125021606684,
      "step": 18
    },
    {
      "completion_length": 317.75,
      "epoch": 5.0,
      "grad_norm": 1.5961576700210571,
      "kl": 0.0014533416154639174,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 0.8478754280755917,
      "reward_std": 0.8306181892597427,
      "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": 0.5190421013782421,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.32883333166440326,
      "step": 20
    },
    {
      "epoch": 5.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 2.425745412892866e-06,
      "train_runtime": 177.9462,
      "train_samples_per_second": 0.899,
      "train_steps_per_second": 0.112
    }
  ],
  "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": 2,
  "trial_name": null,
  "trial_params": null
}