{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.3333333333333335,
  "eval_steps": 500,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 801.625,
      "epoch": 0.6666666666666666,
      "grad_norm": 0.18746021389961243,
      "kl": 0.0006261965318117291,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 3.6409082263708115,
      "reward_std": 0.4210821060696617,
      "rewards/concensus_correctness_reward_func": 0.4505000002682209,
      "rewards/consensus_reward_func": 1.75,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.875,
      "rewards/question_recreation_reward_func": 0.924158051609993,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.35874999314546585,
      "step": 2
    },
    {
      "completion_length": 871.4375,
      "epoch": 1.3333333333333333,
      "grad_norm": 0.12069115787744522,
      "kl": 0.00044926370537723415,
      "learning_rate": 4.415111107797445e-07,
      "loss": 0.0,
      "reward": 2.633436232805252,
      "reward_std": 0.9920646006939933,
      "rewards/concensus_correctness_reward_func": 0.03125,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.5,
      "rewards/question_recreation_reward_func": 0.766436249949038,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.6642499938607216,
      "step": 4
    },
    {
      "completion_length": 849.125,
      "epoch": 2.0,
      "grad_norm": 0.20697245001792908,
      "kl": 0.0006716910502291285,
      "learning_rate": 2.934120444167326e-07,
      "loss": 0.0,
      "reward": 3.569378450512886,
      "reward_std": 0.44148997496813536,
      "rewards/concensus_correctness_reward_func": 0.4817500002682209,
      "rewards/consensus_reward_func": 1.75,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.875,
      "rewards/question_recreation_reward_func": 0.9107533767819405,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.4481250047683716,
      "step": 6
    },
    {
      "completion_length": 810.25,
      "epoch": 2.6666666666666665,
      "grad_norm": 0.13334907591342926,
      "kl": 0.0008067244671110529,
      "learning_rate": 1.2500000000000005e-07,
      "loss": 0.0,
      "reward": 3.0999062806367874,
      "reward_std": 0.22628834086935967,
      "rewards/concensus_correctness_reward_func": 0.4817500002682209,
      "rewards/consensus_reward_func": 1.75,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.75,
      "rewards/question_recreation_reward_func": 0.8422812595963478,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.7241249866783619,
      "step": 8
    },
    {
      "completion_length": 835.9375,
      "epoch": 3.3333333333333335,
      "grad_norm": 0.13740289211273193,
      "kl": 0.00047284221727750264,
      "learning_rate": 1.507684480352292e-08,
      "loss": 0.0,
      "reward": 3.812468647956848,
      "reward_std": 0.4933229257585481,
      "rewards/concensus_correctness_reward_func": 0.46875,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.0,
      "rewards/question_recreation_reward_func": 0.8575310036540031,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.5138124972581863,
      "step": 10
    },
    {
      "epoch": 3.3333333333333335,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": 8.405368248531885e-07,
      "train_runtime": 8375.9497,
      "train_samples_per_second": 0.01,
      "train_steps_per_second": 0.001
    }
  ],
  "logging_steps": 2,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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
}