{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "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": 172.34375,
      "epoch": 0.1,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 4.965903258506806e-07,
      "loss": 0.0,
      "reward": 7.173999786376953,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 2.1740000247955322,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "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": 148.34375,
      "epoch": 0.2,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 4.698684378016222e-07,
      "loss": 0.0,
      "reward": 6.502800479531288,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 1.9240000247955322,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.9381756756920367,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.46875,
      "rewards/xmlcount_reward_func": 1.171875,
      "step": 4
    },
    {
      "completion_length": 155.71875,
      "epoch": 0.3,
      "grad_norm": 0.20881563425064087,
      "kl": 0.0,
      "learning_rate": 4.193203929064353e-07,
      "loss": 0.0,
      "reward": 6.48287507891655,
      "reward_std": 0.027621358633041382,
      "rewards/concensus_correctness_reward_func": 1.9240000247955322,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.9377815315383486,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.453125,
      "rewards/xmlcount_reward_func": 1.16796875,
      "step": 6
    },
    {
      "completion_length": 163.96875,
      "epoch": 0.4,
      "grad_norm": 0.000114446971565485,
      "kl": 4.300008587504456e-06,
      "learning_rate": 3.5042385616324236e-07,
      "loss": 0.0,
      "reward": 6.502529338002205,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 1.9240000247955322,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.9379045307578053,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.46875,
      "rewards/xmlcount_reward_func": 1.171875,
      "step": 8
    },
    {
      "completion_length": 157.375,
      "epoch": 0.5,
      "grad_norm": 0.5446047782897949,
      "kl": 0.0001298928803025179,
      "learning_rate": 2.706448363680831e-07,
      "loss": 0.0,
      "reward": 6.650198072195053,
      "reward_std": 0.033660705492366105,
      "rewards/concensus_correctness_reward_func": 1.9240000247955322,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.9996357783675194,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.484375,
      "rewards/xmlcount_reward_func": 1.2421875,
      "step": 10
    },
    {
      "completion_length": 149.3125,
      "epoch": 0.6,
      "grad_norm": 0.4448278248310089,
      "kl": 0.0004106627923707862,
      "learning_rate": 1.886286282148002e-07,
      "loss": 0.0,
      "reward": 6.502377584576607,
      "reward_std": 8.448336302535608e-05,
      "rewards/concensus_correctness_reward_func": 1.9240000247955322,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.9377527463366278,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.46875,
      "rewards/xmlcount_reward_func": 1.171875,
      "step": 12
    },
    {
      "completion_length": 164.0625,
      "epoch": 0.7,
      "grad_norm": 1.1067951917648315,
      "kl": 0.0022055969420762267,
      "learning_rate": 1.1326296046939333e-07,
      "loss": 0.0,
      "reward": 6.483567997813225,
      "reward_std": 0.2251170426607132,
      "rewards/concensus_correctness_reward_func": 1.8638750240206718,
      "rewards/consensus_reward_func": 1.9375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.9907869584858418,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.46875,
      "rewards/xmlcount_reward_func": 1.22265625,
      "step": 14
    },
    {
      "completion_length": 139.3125,
      "epoch": 0.8,
      "grad_norm": 0.0019641099497675896,
      "kl": 0.0017838500052675954,
      "learning_rate": 5.271487265090163e-08,
      "loss": 0.0,
      "reward": 6.12624990940094,
      "reward_std": 0.20103928446769714,
      "rewards/concensus_correctness_reward_func": 1.8638750240206718,
      "rewards/consensus_reward_func": 1.9375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.8756563392817043,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.40625,
      "rewards/xmlcount_reward_func": 1.04296875,
      "step": 16
    },
    {
      "completion_length": 158.4375,
      "epoch": 0.9,
      "grad_norm": 0.002797660417854786,
      "kl": 0.004285544854155887,
      "learning_rate": 1.3545689574841341e-08,
      "loss": 0.0,
      "reward": 7.378788709640503,
      "reward_std": 0.06393811851739883,
      "rewards/concensus_correctness_reward_func": 2.2990000247955322,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.375,
      "rewards/question_recreation_reward_func": 0.9980701506137848,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.46875,
      "rewards/xmlcount_reward_func": 1.2379687502980232,
      "step": 18
    },
    {
      "completion_length": 156.0,
      "epoch": 1.0,
      "grad_norm": 0.003137073712423444,
      "kl": 0.0021101009342601174,
      "learning_rate": 0.0,
      "loss": 0.0,
      "reward": 6.375521436333656,
      "reward_std": 0.2902469038963318,
      "rewards/concensus_correctness_reward_func": 1.9888750240206718,
      "rewards/consensus_reward_func": 1.9375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.8475841016770573,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.421875,
      "rewards/xmlcount_reward_func": 1.0546875,
      "step": 20
    },
    {
      "epoch": 1.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 2.1189417271472165e-06,
      "train_runtime": 3419.3014,
      "train_samples_per_second": 0.094,
      "train_steps_per_second": 0.006
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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
}