{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "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": 294.875,
      "epoch": 0.42105263157894735,
      "grad_norm": 7.388230323791504,
      "kl": 0.0018326228964724578,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 0.23368853772990406,
      "reward_std": 0.298145150532946,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.09978228050749749,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.07140624802559614,
      "step": 2
    },
    {
      "completion_length": 365.21875,
      "epoch": 0.8421052631578947,
      "grad_norm": 23.853408813476562,
      "kl": 0.005862652775249444,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 0.23603129759430885,
      "reward_std": 0.30246378132142127,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.12512504076585174,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.11090624984353781,
      "step": 4
    },
    {
      "completion_length": 226.0,
      "epoch": 1.2105263157894737,
      "grad_norm": 7.582596778869629,
      "kl": 0.0031690104099522743,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 0.16822473385504313,
      "reward_std": 0.5507601164281368,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.07142857142857142,
      "rewards/question_recreation_reward_func": 0.1537961567352925,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.05699999790106501,
      "step": 6
    },
    {
      "completion_length": 385.09375,
      "epoch": 1.631578947368421,
      "grad_norm": 2.9946677684783936,
      "kl": 0.001347492725471966,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 0.21872268104925752,
      "reward_std": 0.6904346485389397,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.2022851686924696,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.10856249555945396,
      "step": 8
    },
    {
      "completion_length": 446.85714285714283,
      "epoch": 2.0,
      "grad_norm": 0.9212186336517334,
      "kl": 0.0022978045121167918,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 0.13073402217456273,
      "reward_std": 0.3137416091880628,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.13244829353477275,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.001714284930910383,
      "step": 10
    },
    {
      "completion_length": 368.5625,
      "epoch": 2.4210526315789473,
      "grad_norm": 1.7672561407089233,
      "kl": 0.0013554280303651467,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": -0.1324465568177402,
      "reward_std": 0.6439249363029376,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.09061592211946845,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.22306250617839396,
      "step": 12
    },
    {
      "completion_length": 217.71875,
      "epoch": 2.8421052631578947,
      "grad_norm": 51.95741653442383,
      "kl": 0.0025395552984264214,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 0.18613064312376082,
      "reward_std": 0.20095090114045888,
      "rewards/concensus_correctness_reward_func": 0.0013749999925494194,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.1167868955526501,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.06796875037252903,
      "step": 14
    },
    {
      "completion_length": 276.2142857142857,
      "epoch": 3.2105263157894735,
      "grad_norm": 29.23552131652832,
      "kl": 0.0017278649694552378,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 0.2764262727328709,
      "reward_std": 0.45395882214818684,
      "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": 0.16878341936639377,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.03621428566319602,
      "step": 16
    },
    {
      "completion_length": 319.46875,
      "epoch": 3.6315789473684212,
      "grad_norm": 52.476932525634766,
      "kl": 0.004187825550616253,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 0.058828551205806434,
      "reward_std": 0.11632925440790132,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.0568285504123196,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0020000003278255463,
      "step": 18
    },
    {
      "completion_length": 451.92857142857144,
      "epoch": 4.0,
      "grad_norm": 6.4608612060546875,
      "kl": 0.0014391274640469679,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 0.09713409947497505,
      "reward_std": 0.34493599299873623,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.07142857142857142,
      "rewards/question_recreation_reward_func": 0.1079555196421487,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.08224999904632568,
      "step": 20
    },
    {
      "epoch": 4.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 2.47737436893658e-06,
      "train_runtime": 471.1429,
      "train_samples_per_second": 0.679,
      "train_steps_per_second": 0.042
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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
}