{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.7272727272727275,
  "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": 451.9375,
      "epoch": 0.7272727272727273,
      "grad_norm": 0.7232304215431213,
      "kl": 0.0007251942770380992,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 0.8825128134340048,
      "reward_std": 0.8280513994395733,
      "rewards/concensus_correctness_reward_func": 0.03125,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.4776690669823438,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.12359376437962055,
      "step": 2
    },
    {
      "completion_length": 384.89285714285717,
      "epoch": 1.3636363636363638,
      "grad_norm": 0.47073861956596375,
      "kl": 0.0007757767827050495,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 1.294478407927922,
      "reward_std": 1.155406423977443,
      "rewards/concensus_correctness_reward_func": 0.07928571530750819,
      "rewards/consensus_reward_func": 0.2857142857142857,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5570141162191119,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.3724642949444907,
      "step": 4
    },
    {
      "completion_length": 499.2142857142857,
      "epoch": 2.0,
      "grad_norm": 0.38764122128486633,
      "kl": 0.0006331562222580292,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 0.5406170295817512,
      "reward_std": 0.7747882178851536,
      "rewards/concensus_correctness_reward_func": -0.02057142768587385,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.3577598599450929,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.203428572842053,
      "step": 6
    },
    {
      "completion_length": 407.59375,
      "epoch": 2.7272727272727275,
      "grad_norm": 0.5390964150428772,
      "kl": 0.0007188639283413067,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 1.0355992168188095,
      "reward_std": 0.9637473821640015,
      "rewards/concensus_correctness_reward_func": 0.015625,
      "rewards/consensus_reward_func": 0.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.4846929647028446,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.03125,
      "rewards/xmlcount_reward_func": 0.3165312595665455,
      "step": 8
    },
    {
      "completion_length": 483.57142857142856,
      "epoch": 3.3636363636363638,
      "grad_norm": 0.44560787081718445,
      "kl": 0.002613968012155965,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 1.1905730473143714,
      "reward_std": 1.1236634595053536,
      "rewards/concensus_correctness_reward_func": 0.03128571595464434,
      "rewards/consensus_reward_func": 0.14285714285714285,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.576287350484303,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.03571428571428571,
      "rewards/xmlcount_reward_func": 0.4044285725269999,
      "step": 10
    },
    {
      "completion_length": 431.2142857142857,
      "epoch": 4.0,
      "grad_norm": 0.4702626168727875,
      "kl": 0.0008000809300158705,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 1.0454602496964591,
      "reward_std": 1.1673859911305564,
      "rewards/concensus_correctness_reward_func": 0.07271428619112287,
      "rewards/consensus_reward_func": 0.21428571428571427,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5286387588296618,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.03571428571428571,
      "rewards/xmlcount_reward_func": 0.19410714507102966,
      "step": 12
    },
    {
      "completion_length": 556.8125,
      "epoch": 4.7272727272727275,
      "grad_norm": 0.3356538414955139,
      "kl": 0.0007390652317553759,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 0.8033288135193288,
      "reward_std": 0.9975028149783611,
      "rewards/concensus_correctness_reward_func": 0.013250000774860382,
      "rewards/consensus_reward_func": 0.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5072350464761257,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.09534374810755253,
      "step": 14
    },
    {
      "completion_length": 612.5357142857143,
      "epoch": 5.363636363636363,
      "grad_norm": 0.3366808295249939,
      "kl": 0.0006597392369128231,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 0.6460457103593009,
      "reward_std": 0.9941988076482501,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.07142857142857142,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5144028418830463,
      "rewards/soft_format_reward_func": 0.017857142857142856,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.04235714886869703,
      "step": 16
    },
    {
      "completion_length": 455.4642857142857,
      "epoch": 6.0,
      "grad_norm": 0.2828987240791321,
      "kl": 0.0006825344836605447,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 0.8336544313601085,
      "reward_std": 0.9096535529409137,
      "rewards/concensus_correctness_reward_func": 0.07271428619112287,
      "rewards/consensus_reward_func": 0.21428571428571427,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5023329832724163,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.044321424194744656,
      "step": 18
    },
    {
      "completion_length": 435.0,
      "epoch": 6.7272727272727275,
      "grad_norm": 0.6178954243659973,
      "kl": 0.000745428740628995,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 0.7092596250586212,
      "reward_std": 0.778787343762815,
      "rewards/concensus_correctness_reward_func": 0.013250000774860382,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.3585409049410373,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.21246875869110227,
      "step": 20
    },
    {
      "epoch": 6.7272727272727275,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 8.262990149887628e-07,
      "train_runtime": 613.9599,
      "train_samples_per_second": 0.521,
      "train_steps_per_second": 0.033
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 4,
  "trial_name": null,
  "trial_params": null
}