{
  "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": 214.0625,
      "epoch": 0.5714285714285714,
      "grad_norm": 129.29193115234375,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 3.2055165767669678,
      "reward_std": 0.3085313138435595,
      "rewards/concensus_correctness_reward_func": 0.7296249940991402,
      "rewards/consensus_reward_func": 0.8125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6392978364601731,
      "rewards/soft_format_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.21875,
      "rewards/xmlcount_reward_func": 0.7897187536582351,
      "step": 2
    },
    {
      "completion_length": 130.45833333333334,
      "epoch": 1.0,
      "grad_norm": 23.675512313842773,
      "kl": 0.07788466417696327,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0001,
      "reward": 5.991452674070994,
      "reward_std": 0.33198659618695575,
      "rewards/concensus_correctness_reward_func": 1.8323333412408829,
      "rewards/consensus_reward_func": 1.4166666666666667,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.16666666666666666,
      "rewards/question_recreation_reward_func": 0.9455776462952296,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.4375,
      "rewards/xmlcount_reward_func": 1.1927083333333333,
      "step": 4
    },
    {
      "completion_length": 163.71875,
      "epoch": 1.5714285714285714,
      "grad_norm": 31.248865127563477,
      "kl": 0.15762662113411352,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0002,
      "reward": 5.097857855260372,
      "reward_std": 1.0911973172042053,
      "rewards/concensus_correctness_reward_func": 1.5450625084340572,
      "rewards/consensus_reward_func": 1.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.8670765832066536,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.359375,
      "rewards/xmlcount_reward_func": 1.0763437524437904,
      "step": 6
    },
    {
      "completion_length": 153.45833333333334,
      "epoch": 2.0,
      "grad_norm": 59.27997970581055,
      "kl": 5.424358828614156,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0041,
      "reward": 4.880958507458369,
      "reward_std": 0.7015785239636898,
      "rewards/concensus_correctness_reward_func": 1.1009166582177083,
      "rewards/consensus_reward_func": 1.3333333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.9571251372496287,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.3541666666666667,
      "rewards/xmlcount_reward_func": 1.1354166666666667,
      "step": 8
    },
    {
      "completion_length": 159.84375,
      "epoch": 2.571428571428571,
      "grad_norm": 22.492767333984375,
      "kl": 3.40459524304606,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0034,
      "reward": 5.54975700378418,
      "reward_std": 0.4386998292757198,
      "rewards/concensus_correctness_reward_func": 1.5714374966919422,
      "rewards/consensus_reward_func": 1.375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.9585695303976536,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.328125,
      "rewards/xmlcount_reward_func": 1.1916250064969063,
      "step": 10
    },
    {
      "completion_length": 128.125,
      "epoch": 3.0,
      "grad_norm": 13.225279808044434,
      "kl": 0.43122306823109585,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0003,
      "reward": 6.302078684171041,
      "reward_std": 0.05914810299873352,
      "rewards/concensus_correctness_reward_func": 1.7683333444098632,
      "rewards/consensus_reward_func": 1.8333333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.9768286347389221,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.4791666666666667,
      "rewards/xmlcount_reward_func": 1.2444166739781697,
      "step": 12
    },
    {
      "completion_length": 138.78125,
      "epoch": 3.571428571428571,
      "grad_norm": 34.572078704833984,
      "kl": 2.4331941911950707,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0024,
      "reward": 5.1307472586631775,
      "reward_std": 1.0153084722987842,
      "rewards/concensus_correctness_reward_func": 1.2935625012032688,
      "rewards/consensus_reward_func": 1.375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.8988097123801708,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.359375,
      "rewards/xmlcount_reward_func": 1.2040000036358833,
      "step": 14
    },
    {
      "completion_length": 147.54166666666666,
      "epoch": 4.0,
      "grad_norm": 0.5938521027565002,
      "kl": 45.33216493514677,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.034,
      "reward": 5.661058286825816,
      "reward_std": 0.6594598864515623,
      "rewards/concensus_correctness_reward_func": 1.617166668176651,
      "rewards/consensus_reward_func": 1.3333333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.16666666666666666,
      "rewards/question_recreation_reward_func": 0.9611416161060333,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.3958333333333333,
      "rewards/xmlcount_reward_func": 1.186916669209798,
      "step": 16
    },
    {
      "completion_length": 137.96875,
      "epoch": 4.571428571428571,
      "grad_norm": 129.46636962890625,
      "kl": 14.352025136118755,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0144,
      "reward": 5.41445254907012,
      "reward_std": 0.7548820912343217,
      "rewards/concensus_correctness_reward_func": 1.496062494814396,
      "rewards/consensus_reward_func": 1.5625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.8958275727927685,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.328125,
      "rewards/xmlcount_reward_func": 1.1319375038146973,
      "step": 18
    },
    {
      "completion_length": 150.33333333333334,
      "epoch": 5.0,
      "grad_norm": 23.762697219848633,
      "kl": 328.1498412267926,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.2461,
      "reward": 5.554007162650426,
      "reward_std": 0.5768525426586469,
      "rewards/concensus_correctness_reward_func": 1.6576666782299678,
      "rewards/consensus_reward_func": 1.1666666666666667,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.16666666666666666,
      "rewards/question_recreation_reward_func": 0.9640488177537918,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.3958333333333333,
      "rewards/xmlcount_reward_func": 1.203125,
      "step": 20
    },
    {
      "epoch": 5.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 0.030490872963127913,
      "train_runtime": 111.1256,
      "train_samples_per_second": 2.88,
      "train_steps_per_second": 0.18
    }
  ],
  "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
}