{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.4324324324324325,
  "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": 8.3125,
      "epoch": 0.14414414414414414,
      "grad_norm": 19.17816162109375,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 1.581678017450031,
      "reward_std": 0.09327375888824463,
      "rewards/concensus_correctness_reward_func": 0.24056249886052683,
      "rewards/consensus_reward_func": 1.3125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.02861549676163122,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 2
    },
    {
      "completion_length": 3.59375,
      "epoch": 0.2882882882882883,
      "grad_norm": 54.003597259521484,
      "kl": 0.0057574408129767995,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 1.8427463320549577,
      "reward_std": 0.08771874010562897,
      "rewards/concensus_correctness_reward_func": 0.4990000035613775,
      "rewards/consensus_reward_func": 1.3125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.031246319558704272,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 4
    },
    {
      "completion_length": 7.8125,
      "epoch": 0.43243243243243246,
      "grad_norm": 0.00025395405828021467,
      "kl": 0.001715799282113295,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 2.195782383554615,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 0.41325001046061516,
      "rewards/consensus_reward_func": 1.75,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.03253235557349399,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 6
    },
    {
      "completion_length": 6.71875,
      "epoch": 0.5765765765765766,
      "grad_norm": 15.033347129821777,
      "kl": 0.037265406065227324,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 2.0335406224476174,
      "reward_std": 0.17979902774095535,
      "rewards/concensus_correctness_reward_func": 0.3605000004172325,
      "rewards/consensus_reward_func": 1.625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.04804061644244939,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 8
    },
    {
      "completion_length": 11.21875,
      "epoch": 0.7207207207207207,
      "grad_norm": 3.437758207321167,
      "kl": 0.015125086178926495,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 1.498489588033408,
      "reward_std": 0.09418269171146676,
      "rewards/concensus_correctness_reward_func": 0.12400000146590173,
      "rewards/consensus_reward_func": 1.3125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.06198958713503089,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 10
    },
    {
      "completion_length": 5.875,
      "epoch": 0.8648648648648649,
      "grad_norm": 40.72884750366211,
      "kl": 0.07916541388276599,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0001,
      "reward": 2.217431016266346,
      "reward_std": 0.175310879945755,
      "rewards/concensus_correctness_reward_func": 0.4908750057220459,
      "rewards/consensus_reward_func": 1.6875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.03905599995050579,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 12
    },
    {
      "completion_length": 4.666666666666667,
      "epoch": 1.0,
      "grad_norm": 0.0005821126396767795,
      "kl": 0.043508860270182484,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 3.4743243026236694,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 1.846400006612142,
      "rewards/consensus_reward_func": 1.6,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.027924280675748984,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 14
    },
    {
      "completion_length": 5.375,
      "epoch": 1.1441441441441442,
      "grad_norm": 0.007315310183912516,
      "kl": 0.0007841990336601157,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 2.0436925697140396,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 0.37912500463426113,
      "rewards/consensus_reward_func": 1.625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.039567558211274445,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 16
    },
    {
      "completion_length": 4.25,
      "epoch": 1.2882882882882882,
      "grad_norm": 0.015381651930510998,
      "kl": 0.0016820762306686277,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 2.259079163253773,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 0.4855000004172325,
      "rewards/consensus_reward_func": 1.75,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.02357914694584906,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 18
    },
    {
      "completion_length": 4.5625,
      "epoch": 1.4324324324324325,
      "grad_norm": 49.89079284667969,
      "kl": 0.04839727417565598,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 2.2943748831748962,
      "reward_std": 0.00014778331387788057,
      "rewards/concensus_correctness_reward_func": 0.3815000019967556,
      "rewards/consensus_reward_func": 1.875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.037874873145483434,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 20
    },
    {
      "epoch": 1.4324324324324325,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 2.3087571327096158e-05,
      "train_runtime": 1560.9796,
      "train_samples_per_second": 0.205,
      "train_steps_per_second": 0.013
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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
}