{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6956521739130435,
  "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": 167.71875,
      "epoch": 0.06956521739130435,
      "grad_norm": 46.50515365600586,
      "kl": 0.0,
      "learning_rate": 4.965903258506806e-07,
      "loss": 0.0,
      "reward": 0.23886918861535378,
      "reward_std": 0.04501778557471425,
      "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": 0.11086919068475254,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.003000000026077032,
      "step": 2
    },
    {
      "completion_length": 213.9375,
      "epoch": 0.1391304347826087,
      "grad_norm": 199004.953125,
      "kl": 0.004053308793572796,
      "learning_rate": 4.698684378016222e-07,
      "loss": 0.0,
      "reward": 0.08304696858976968,
      "reward_std": 0.027729042252758518,
      "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": 0.08317196861025877,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.0001250000059371814,
      "step": 4
    },
    {
      "completion_length": 92.65625,
      "epoch": 0.20869565217391303,
      "grad_norm": 10.352762222290039,
      "kl": 0.011977128890293898,
      "learning_rate": 4.193203929064353e-07,
      "loss": 0.0,
      "reward": 0.29487171000801027,
      "reward_std": 0.11191323117236607,
      "rewards/concensus_correctness_reward_func": 0.014999999664723873,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.08846545231062919,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.00390625,
      "step": 6
    },
    {
      "completion_length": 138.34375,
      "epoch": 0.2782608695652174,
      "grad_norm": 44472596.0,
      "kl": 0.007592094505525893,
      "learning_rate": 3.5042385616324236e-07,
      "loss": 0.0,
      "reward": 0.15320231160148978,
      "reward_std": 0.131714646180626,
      "rewards/concensus_correctness_reward_func": 0.006562499795109034,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.0841398109914735,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 8
    },
    {
      "completion_length": 111.40625,
      "epoch": 0.34782608695652173,
      "grad_norm": 36.51017379760742,
      "kl": 0.2421079762170848,
      "learning_rate": 2.706448363680831e-07,
      "loss": 0.0002,
      "reward": 0.16755636170273647,
      "reward_std": 0.14275544960651132,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.10265011055162176,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.002406249986961484,
      "step": 10
    },
    {
      "completion_length": 112.75,
      "epoch": 0.41739130434782606,
      "grad_norm": 22.138507843017578,
      "kl": 0.003069994276302168,
      "learning_rate": 1.886286282148002e-07,
      "loss": 0.0,
      "reward": 0.13111776718869805,
      "reward_std": 0.03130402306851465,
      "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": 0.13111776718869805,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 12
    },
    {
      "completion_length": 230.28125,
      "epoch": 0.48695652173913045,
      "grad_norm": 16.621665954589844,
      "kl": 0.0028904032737955276,
      "learning_rate": 1.1326296046939333e-07,
      "loss": 0.0,
      "reward": 0.07638290524482727,
      "reward_std": 0.04352241018023051,
      "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": 0.07244540535612032,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.003937500063329935,
      "step": 14
    },
    {
      "completion_length": 212.46875,
      "epoch": 0.5565217391304348,
      "grad_norm": 31.35605812072754,
      "kl": 0.019228663304602378,
      "learning_rate": 5.271487265090163e-08,
      "loss": 0.0,
      "reward": 0.22756990580819547,
      "reward_std": 0.21891088442862383,
      "rewards/concensus_correctness_reward_func": 0.0078125,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.0947574048768729,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 16
    },
    {
      "completion_length": 216.84375,
      "epoch": 0.6260869565217392,
      "grad_norm": 11.983558654785156,
      "kl": 0.038972208321865764,
      "learning_rate": 1.3545689574841341e-08,
      "loss": 0.0,
      "reward": 0.0798949726158753,
      "reward_std": 0.03412955232488457,
      "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": 0.0798949726158753,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 18
    },
    {
      "completion_length": 193.875,
      "epoch": 0.6956521739130435,
      "grad_norm": 49818.66796875,
      "kl": 0.03839717447408475,
      "learning_rate": 0.0,
      "loss": 0.0,
      "reward": 0.07137113180942833,
      "reward_std": 0.025341270804347005,
      "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": 0.07137113180942833,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 20
    },
    {
      "epoch": 0.6956521739130435,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 3.689589379973768e-05,
      "train_runtime": 3788.7825,
      "train_samples_per_second": 0.084,
      "train_steps_per_second": 0.005
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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
}