{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.4,
  "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": 61.5,
      "epoch": 0.8,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": -0.0,
      "reward": 1.796084702014923,
      "reward_std": 0.007014752831310034,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.5,
      "rewards/question_recreation_reward_func": 0.17108468152582645,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.125,
      "step": 2
    },
    {
      "completion_length": 90.5,
      "epoch": 1.4,
      "grad_norm": 6.7355570793151855,
      "kl": 0.0006590462605042072,
      "learning_rate": 4.415111107797445e-07,
      "loss": 0.0,
      "reward": 2.4892822901407876,
      "reward_std": 0.02238767563054959,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 2.0,
      "rewards/question_recreation_reward_func": 0.36428221066792804,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.125,
      "step": 4
    },
    {
      "completion_length": 61.0,
      "epoch": 2.0,
      "grad_norm": 2.9161038398742676,
      "kl": 0.0013541329723617916,
      "learning_rate": 2.934120444167326e-07,
      "loss": 0.0,
      "reward": 1.5693917274475098,
      "reward_std": 0.0041435409026841325,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.3333333333333333,
      "rewards/question_recreation_reward_func": 0.1110583816965421,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.125,
      "step": 6
    },
    {
      "completion_length": 66.5,
      "epoch": 2.8,
      "grad_norm": 5.4519829750061035,
      "kl": 0.0025089465470955474,
      "learning_rate": 1.2500000000000005e-07,
      "loss": 0.0,
      "reward": 1.8168215155601501,
      "reward_std": 0.020925488555803895,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.5,
      "rewards/question_recreation_reward_func": 0.19182147271931171,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.125,
      "step": 8
    },
    {
      "completion_length": 54.666666666666664,
      "epoch": 3.4,
      "grad_norm": 0.00030291583971120417,
      "kl": 0.0006291301785192142,
      "learning_rate": 1.507684480352292e-08,
      "loss": 0.0,
      "reward": 1.649997631708781,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.3333333333333333,
      "rewards/question_recreation_reward_func": 0.19166426112254462,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.125,
      "step": 10
    },
    {
      "epoch": 3.4,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": 2.266971819153696e-08,
      "train_runtime": 634.082,
      "train_samples_per_second": 0.063,
      "train_steps_per_second": 0.016
    }
  ],
  "logging_steps": 2,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 10,
  "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
}