{
  "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": 473.125,
      "epoch": 0.7272727272727273,
      "grad_norm": 0.5780012011528015,
      "kl": 0.0018195659504272044,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 0.7852539010345936,
      "reward_std": 0.6700366213917732,
      "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": 0.6348789054900408,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.15037500904873013,
      "step": 2
    },
    {
      "completion_length": 461.32142857142856,
      "epoch": 1.3636363636363638,
      "grad_norm": 0.43347495794296265,
      "kl": 0.0015060585823708347,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 1.1546246686152049,
      "reward_std": 0.9197601931435722,
      "rewards/concensus_correctness_reward_func": 0.03864285775593349,
      "rewards/consensus_reward_func": 0.35714285714285715,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.41933891496488024,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.3395000100135803,
      "step": 4
    },
    {
      "completion_length": 553.6785714285714,
      "epoch": 2.0,
      "grad_norm": 0.24650119245052338,
      "kl": 0.001656832073682121,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 1.446252771786281,
      "reward_std": 1.6744095257350378,
      "rewards/concensus_correctness_reward_func": 0.19264285692146846,
      "rewards/consensus_reward_func": 0.7857142857142857,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5666455977729389,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.09874998139483589,
      "step": 6
    },
    {
      "completion_length": 489.90625,
      "epoch": 2.7272727272727275,
      "grad_norm": 0.36353105306625366,
      "kl": 0.0016505489984410815,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 1.2562414929270744,
      "reward_std": 1.0721860602498055,
      "rewards/concensus_correctness_reward_func": 0.05324999988079071,
      "rewards/consensus_reward_func": 0.375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5846789591014385,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.2276875041425228,
      "step": 8
    },
    {
      "completion_length": 500.7142857142857,
      "epoch": 3.3636363636363638,
      "grad_norm": 0.5545067191123962,
      "kl": 0.0017322281741404108,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 1.230509843145098,
      "reward_std": 1.23474839755467,
      "rewards/concensus_correctness_reward_func": 0.0247142847095217,
      "rewards/consensus_reward_func": 0.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.07142857142857142,
      "rewards/question_recreation_reward_func": 0.3760812836033957,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.25828570978982107,
      "step": 10
    },
    {
      "completion_length": 540.7142857142857,
      "epoch": 4.0,
      "grad_norm": 0.2851618528366089,
      "kl": 0.0018666927935555577,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 0.9000063027654376,
      "reward_std": 0.8522530368396214,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.14285714285714285,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5019705896931035,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.2373214289546013,
      "step": 12
    },
    {
      "completion_length": 490.59375,
      "epoch": 4.7272727272727275,
      "grad_norm": 0.43547067046165466,
      "kl": 0.0016540642027393915,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 0.7657471336424351,
      "reward_std": 0.8933027181774378,
      "rewards/concensus_correctness_reward_func": 0.02162499912083149,
      "rewards/consensus_reward_func": 0.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.44059090316295624,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.1160312567371875,
      "step": 14
    },
    {
      "completion_length": 456.0,
      "epoch": 5.363636363636363,
      "grad_norm": 0.427194744348526,
      "kl": 0.0021815421558650477,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 1.1721123542104448,
      "reward_std": 0.9155192162309375,
      "rewards/concensus_correctness_reward_func": 0.0684285717351096,
      "rewards/consensus_reward_func": 0.2857142857142857,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.43671950165714535,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.38124998978206087,
      "step": 16
    },
    {
      "completion_length": 458.92857142857144,
      "epoch": 6.0,
      "grad_norm": 0.5137476325035095,
      "kl": 0.00196937275385218,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 1.2816025529588972,
      "reward_std": 1.0332180857658386,
      "rewards/concensus_correctness_reward_func": 0.031071428741727556,
      "rewards/consensus_reward_func": 0.35714285714285715,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5437096644725118,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.3318214310067041,
      "step": 18
    },
    {
      "completion_length": 501.9375,
      "epoch": 6.7272727272727275,
      "grad_norm": 0.6245306730270386,
      "kl": 0.0016426051588496193,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 0.8476437460631132,
      "reward_std": 0.9873409513384104,
      "rewards/concensus_correctness_reward_func": 0.0521249994635582,
      "rewards/consensus_reward_func": 0.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5099562611430883,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.0824374994263053,
      "step": 20
    },
    {
      "epoch": 6.7272727272727275,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 1.6401619859607309e-06,
      "train_runtime": 1223.4771,
      "train_samples_per_second": 0.262,
      "train_steps_per_second": 0.016
    }
  ],
  "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
}