{
  "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": 130.25,
      "epoch": 0.5714285714285714,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 8.6635000705719,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 2.9135000109672546,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.0,
      "rewards/question_recreation_reward_func": 1.0,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.5,
      "rewards/xmlcount_reward_func": 1.25,
      "step": 2
    },
    {
      "completion_length": 99.83333333333333,
      "epoch": 1.0,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 8.663999716440836,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 2.580666700998942,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.3333333333333333,
      "rewards/question_recreation_reward_func": 1.0,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.5,
      "rewards/xmlcount_reward_func": 1.25,
      "step": 4
    },
    {
      "completion_length": 116.75,
      "epoch": 1.5714285714285714,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 9.162999749183655,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 2.9130000472068787,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.5,
      "rewards/question_recreation_reward_func": 1.0,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.5,
      "rewards/xmlcount_reward_func": 1.25,
      "step": 6
    },
    {
      "completion_length": 118.5,
      "epoch": 2.0,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 7.998000144958496,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 2.58133331934611,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.6666666666666666,
      "rewards/question_recreation_reward_func": 1.0,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.5,
      "rewards/xmlcount_reward_func": 1.25,
      "step": 8
    },
    {
      "completion_length": 119.0,
      "epoch": 2.571428571428571,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 9.16349995136261,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 2.9135000109672546,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.5,
      "rewards/question_recreation_reward_func": 1.0,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.5,
      "rewards/xmlcount_reward_func": 1.25,
      "step": 10
    },
    {
      "completion_length": 123.0,
      "epoch": 3.0,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 7.99733320871989,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 2.580666700998942,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.6666666666666666,
      "rewards/question_recreation_reward_func": 1.0,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.5,
      "rewards/xmlcount_reward_func": 1.25,
      "step": 12
    },
    {
      "completion_length": 122.375,
      "epoch": 3.571428571428571,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 8.162999868392944,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 2.4130000472068787,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.0,
      "rewards/question_recreation_reward_func": 1.0,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.5,
      "rewards/xmlcount_reward_func": 1.25,
      "step": 14
    },
    {
      "completion_length": 109.33333333333333,
      "epoch": 4.0,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 9.33133331934611,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 3.247999986012777,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.3333333333333333,
      "rewards/question_recreation_reward_func": 1.0,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.5,
      "rewards/xmlcount_reward_func": 1.25,
      "step": 16
    },
    {
      "completion_length": 107.375,
      "epoch": 4.571428571428571,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 9.162999749183655,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 2.9130000472068787,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.5,
      "rewards/question_recreation_reward_func": 1.0,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.5,
      "rewards/xmlcount_reward_func": 1.25,
      "step": 18
    },
    {
      "completion_length": 131.83333333333334,
      "epoch": 5.0,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 7.998000144958496,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 2.58133331934611,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.6666666666666666,
      "rewards/question_recreation_reward_func": 1.0,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.5,
      "rewards/xmlcount_reward_func": 1.25,
      "step": 20
    },
    {
      "epoch": 5.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 0.0,
      "train_runtime": 1057.9837,
      "train_samples_per_second": 0.076,
      "train_steps_per_second": 0.019
    }
  ],
  "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
}