{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.666666666666666,
  "eval_steps": 500,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 5.0,
      "completions/max_terminated_length": 5.0,
      "completions/mean_length": 4.5,
      "completions/mean_terminated_length": 4.5,
      "completions/min_length": 4.0,
      "completions/min_terminated_length": 4.0,
      "epoch": 0.6666666666666666,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 0.0,
      "loss": 0.0,
      "num_tokens": 530.0,
      "reward": 0.008066109381616116,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func/mean": 0.0,
      "rewards/concensus_correctness_reward_func/std": 0.0,
      "rewards/consensus_reward_func/mean": 0.0,
      "rewards/consensus_reward_func/std": 0.0,
      "rewards/cumulative_reward_2/mean": 0.0,
      "rewards/cumulative_reward_2/std": 0.0,
      "rewards/final_correctness_reward_func/mean": 0.0,
      "rewards/final_correctness_reward_func/std": 0.0,
      "rewards/question_recreation_reward_func/mean": 0.008066109381616116,
      "rewards/question_recreation_reward_func/std": 0.003943240735679865,
      "rewards/soft_format_reward_func/mean": 0.0,
      "rewards/soft_format_reward_func/std": 0.0,
      "rewards/strict_format_reward_func/mean": 0.0,
      "rewards/strict_format_reward_func/std": 0.0,
      "rewards/xmlcount_reward_func/mean": 0.0,
      "rewards/xmlcount_reward_func/std": 0.0,
      "step": 1
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 349.0,
      "completions/max_terminated_length": 349.0,
      "completions/mean_length": 118.25,
      "completions/mean_terminated_length": 118.25,
      "completions/min_length": 4.0,
      "completions/min_terminated_length": 4.0,
      "epoch": 1.6666666666666665,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 20.83260154724121,
      "kl": 0.0,
      "learning_rate": 1e-06,
      "loss": -0.0666,
      "num_tokens": 1515.0,
      "reward": 0.04304097592830658,
      "reward_std": 0.015776073560118675,
      "rewards/concensus_correctness_reward_func/mean": 0.0,
      "rewards/concensus_correctness_reward_func/std": 0.0,
      "rewards/consensus_reward_func/mean": 0.0,
      "rewards/consensus_reward_func/std": 0.0,
      "rewards/cumulative_reward_2/mean": 0.0,
      "rewards/cumulative_reward_2/std": 0.0,
      "rewards/final_correctness_reward_func/mean": 0.0,
      "rewards/final_correctness_reward_func/std": 0.0,
      "rewards/question_recreation_reward_func/mean": 0.04304097965359688,
      "rewards/question_recreation_reward_func/std": 0.03550219535827637,
      "rewards/soft_format_reward_func/mean": 0.0,
      "rewards/soft_format_reward_func/std": 0.0,
      "rewards/strict_format_reward_func/mean": 0.0,
      "rewards/strict_format_reward_func/std": 0.0,
      "rewards/xmlcount_reward_func/mean": 0.0,
      "rewards/xmlcount_reward_func/std": 0.0,
      "step": 2
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 81.0,
      "completions/max_terminated_length": 81.0,
      "completions/mean_length": 55.5,
      "completions/mean_terminated_length": 55.5,
      "completions/min_length": 5.0,
      "completions/min_terminated_length": 5.0,
      "epoch": 2.6666666666666665,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 18.529109954833984,
      "kl": 0.010792357847094536,
      "learning_rate": 9.931806517013612e-07,
      "loss": -0.0009,
      "num_tokens": 2249.0,
      "reward": 0.022436685860157013,
      "reward_std": 0.02014855481684208,
      "rewards/concensus_correctness_reward_func/mean": 0.0,
      "rewards/concensus_correctness_reward_func/std": 0.0,
      "rewards/consensus_reward_func/mean": 0.0,
      "rewards/consensus_reward_func/std": 0.0,
      "rewards/cumulative_reward_2/mean": 0.0,
      "rewards/cumulative_reward_2/std": 0.0,
      "rewards/final_correctness_reward_func/mean": 0.0,
      "rewards/final_correctness_reward_func/std": 0.0,
      "rewards/question_recreation_reward_func/mean": 0.022436687722802162,
      "rewards/question_recreation_reward_func/std": 0.022550448775291443,
      "rewards/soft_format_reward_func/mean": 0.0,
      "rewards/soft_format_reward_func/std": 0.0,
      "rewards/strict_format_reward_func/mean": 0.0,
      "rewards/strict_format_reward_func/std": 0.0,
      "rewards/xmlcount_reward_func/mean": 0.0,
      "rewards/xmlcount_reward_func/std": 0.0,
      "step": 3
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 136.0,
      "completions/max_terminated_length": 136.0,
      "completions/mean_length": 60.5,
      "completions/mean_terminated_length": 60.5,
      "completions/min_length": 29.0,
      "completions/min_terminated_length": 29.0,
      "epoch": 3.6666666666666665,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 18.628131866455078,
      "kl": 0.018510018475353718,
      "learning_rate": 9.729086208503173e-07,
      "loss": 0.0023,
      "num_tokens": 3003.0,
      "reward": 0.04145018756389618,
      "reward_std": 0.01120975986123085,
      "rewards/concensus_correctness_reward_func/mean": 0.0,
      "rewards/concensus_correctness_reward_func/std": 0.0,
      "rewards/consensus_reward_func/mean": 0.0,
      "rewards/consensus_reward_func/std": 0.0,
      "rewards/cumulative_reward_2/mean": 0.0,
      "rewards/cumulative_reward_2/std": 0.0,
      "rewards/final_correctness_reward_func/mean": 0.0,
      "rewards/final_correctness_reward_func/std": 0.0,
      "rewards/question_recreation_reward_func/mean": 0.04145018756389618,
      "rewards/question_recreation_reward_func/std": 0.018993662670254707,
      "rewards/soft_format_reward_func/mean": 0.0,
      "rewards/soft_format_reward_func/std": 0.0,
      "rewards/strict_format_reward_func/mean": 0.0,
      "rewards/strict_format_reward_func/std": 0.0,
      "rewards/xmlcount_reward_func/mean": 0.0,
      "rewards/xmlcount_reward_func/std": 0.0,
      "step": 4
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 170.0,
      "completions/max_terminated_length": 170.0,
      "completions/mean_length": 78.0,
      "completions/mean_terminated_length": 78.0,
      "completions/min_length": 44.0,
      "completions/min_terminated_length": 44.0,
      "epoch": 4.666666666666667,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 21.398902893066406,
      "kl": 0.02564714290201664,
      "learning_rate": 9.397368756032444e-07,
      "loss": -0.0002,
      "num_tokens": 3827.0,
      "reward": 0.04360058531165123,
      "reward_std": 0.019069546833634377,
      "rewards/concensus_correctness_reward_func/mean": 0.0,
      "rewards/concensus_correctness_reward_func/std": 0.0,
      "rewards/consensus_reward_func/mean": 0.0,
      "rewards/consensus_reward_func/std": 0.0,
      "rewards/cumulative_reward_2/mean": 0.0,
      "rewards/cumulative_reward_2/std": 0.0,
      "rewards/final_correctness_reward_func/mean": 0.0,
      "rewards/final_correctness_reward_func/std": 0.0,
      "rewards/question_recreation_reward_func/mean": 0.04360058903694153,
      "rewards/question_recreation_reward_func/std": 0.03016830049455166,
      "rewards/soft_format_reward_func/mean": 0.0,
      "rewards/soft_format_reward_func/std": 0.0,
      "rewards/strict_format_reward_func/mean": 0.0,
      "rewards/strict_format_reward_func/std": 0.0,
      "rewards/xmlcount_reward_func/mean": 0.0,
      "rewards/xmlcount_reward_func/std": 0.0,
      "step": 5
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.25,
      "completions/max_length": 448.0,
      "completions/max_terminated_length": 312.0,
      "completions/mean_length": 237.5,
      "completions/mean_terminated_length": 167.3333282470703,
      "completions/min_length": 53.0,
      "completions/min_terminated_length": 53.0,
      "epoch": 5.666666666666667,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 9.696209907531738,
      "kl": 0.01045918045565486,
      "learning_rate": 8.945702546981968e-07,
      "loss": 0.4365,
      "num_tokens": 5289.0,
      "reward": 0.049925900995731354,
      "reward_std": 0.03584723174571991,
      "rewards/concensus_correctness_reward_func/mean": 0.0,
      "rewards/concensus_correctness_reward_func/std": 0.0,
      "rewards/consensus_reward_func/mean": 0.0,
      "rewards/consensus_reward_func/std": 0.0,
      "rewards/cumulative_reward_2/mean": 0.0,
      "rewards/cumulative_reward_2/std": 0.0,
      "rewards/final_correctness_reward_func/mean": 0.0,
      "rewards/final_correctness_reward_func/std": 0.0,
      "rewards/question_recreation_reward_func/mean": 0.049925900995731354,
      "rewards/question_recreation_reward_func/std": 0.05122767388820648,
      "rewards/soft_format_reward_func/mean": 0.0,
      "rewards/soft_format_reward_func/std": 0.0,
      "rewards/strict_format_reward_func/mean": 0.0,
      "rewards/strict_format_reward_func/std": 0.0,
      "rewards/xmlcount_reward_func/mean": 0.0,
      "rewards/xmlcount_reward_func/std": 0.0,
      "step": 6
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 242.0,
      "completions/max_terminated_length": 242.0,
      "completions/mean_length": 155.0,
      "completions/mean_terminated_length": 155.0,
      "completions/min_length": 73.0,
      "completions/min_terminated_length": 73.0,
      "epoch": 6.666666666666667,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 15.864484786987305,
      "kl": 0.03179105278104544,
      "learning_rate": 8.386407858128706e-07,
      "loss": 0.0013,
      "num_tokens": 6421.0,
      "reward": 0.15269064903259277,
      "reward_std": 0.10605468600988388,
      "rewards/concensus_correctness_reward_func/mean": 0.0,
      "rewards/concensus_correctness_reward_func/std": 0.0,
      "rewards/consensus_reward_func/mean": 0.0,
      "rewards/consensus_reward_func/std": 0.0,
      "rewards/cumulative_reward_2/mean": 0.0,
      "rewards/cumulative_reward_2/std": 0.0,
      "rewards/final_correctness_reward_func/mean": 0.0,
      "rewards/final_correctness_reward_func/std": 0.0,
      "rewards/question_recreation_reward_func/mean": 0.15269066393375397,
      "rewards/question_recreation_reward_func/std": 0.08726509660482407,
      "rewards/soft_format_reward_func/mean": 0.0,
      "rewards/soft_format_reward_func/std": 0.0,
      "rewards/strict_format_reward_func/mean": 0.0,
      "rewards/strict_format_reward_func/std": 0.0,
      "rewards/xmlcount_reward_func/mean": 0.0,
      "rewards/xmlcount_reward_func/std": 0.0,
      "step": 7
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 399.0,
      "completions/max_terminated_length": 399.0,
      "completions/mean_length": 155.0,
      "completions/mean_terminated_length": 155.0,
      "completions/min_length": 56.0,
      "completions/min_terminated_length": 56.0,
      "epoch": 7.666666666666667,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 12.931903839111328,
      "kl": 0.019137650728225708,
      "learning_rate": 7.734740790612136e-07,
      "loss": -0.1577,
      "num_tokens": 7553.0,
      "reward": 0.033152759075164795,
      "reward_std": 0.021638408303260803,
      "rewards/concensus_correctness_reward_func/mean": 0.0,
      "rewards/concensus_correctness_reward_func/std": 0.0,
      "rewards/consensus_reward_func/mean": 0.0,
      "rewards/consensus_reward_func/std": 0.0,
      "rewards/cumulative_reward_2/mean": 0.0,
      "rewards/cumulative_reward_2/std": 0.0,
      "rewards/final_correctness_reward_func/mean": 0.0,
      "rewards/final_correctness_reward_func/std": 0.0,
      "rewards/question_recreation_reward_func/mean": 0.033152759075164795,
      "rewards/question_recreation_reward_func/std": 0.02055053785443306,
      "rewards/soft_format_reward_func/mean": 0.0,
      "rewards/soft_format_reward_func/std": 0.0,
      "rewards/strict_format_reward_func/mean": 0.0,
      "rewards/strict_format_reward_func/std": 0.0,
      "rewards/xmlcount_reward_func/mean": 0.0,
      "rewards/xmlcount_reward_func/std": 0.0,
      "step": 8
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 165.0,
      "completions/max_terminated_length": 165.0,
      "completions/mean_length": 66.5,
      "completions/mean_terminated_length": 66.5,
      "completions/min_length": 21.0,
      "completions/min_terminated_length": 21.0,
      "epoch": 8.666666666666666,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 18.175880432128906,
      "kl": 0.05631773918867111,
      "learning_rate": 7.008477123264847e-07,
      "loss": 0.0023,
      "num_tokens": 8331.0,
      "reward": 0.46325623989105225,
      "reward_std": 0.15417525172233582,
      "rewards/concensus_correctness_reward_func/mean": 0.0,
      "rewards/concensus_correctness_reward_func/std": 0.0,
      "rewards/consensus_reward_func/mean": 0.0,
      "rewards/consensus_reward_func/std": 0.0,
      "rewards/cumulative_reward_2/mean": 0.0,
      "rewards/cumulative_reward_2/std": 0.0,
      "rewards/final_correctness_reward_func/mean": 0.0,
      "rewards/final_correctness_reward_func/std": 0.0,
      "rewards/question_recreation_reward_func/mean": 0.46325621008872986,
      "rewards/question_recreation_reward_func/std": 0.3278234899044037,
      "rewards/soft_format_reward_func/mean": 0.0,
      "rewards/soft_format_reward_func/std": 0.0,
      "rewards/strict_format_reward_func/mean": 0.0,
      "rewards/strict_format_reward_func/std": 0.0,
      "rewards/xmlcount_reward_func/mean": 0.0,
      "rewards/xmlcount_reward_func/std": 0.0,
      "step": 9
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.25,
      "completions/max_length": 448.0,
      "completions/max_terminated_length": 60.0,
      "completions/mean_length": 134.25,
      "completions/mean_terminated_length": 29.66666603088379,
      "completions/min_length": 9.0,
      "completions/min_terminated_length": 9.0,
      "epoch": 9.666666666666666,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 33.21858596801758,
      "kl": 0.08339919522404671,
      "learning_rate": 6.227427435703995e-07,
      "loss": 0.1206,
      "num_tokens": 9380.0,
      "reward": 0.02673748880624771,
      "reward_std": 0.013278969563543797,
      "rewards/concensus_correctness_reward_func/mean": 0.0,
      "rewards/concensus_correctness_reward_func/std": 0.0,
      "rewards/consensus_reward_func/mean": 0.0,
      "rewards/consensus_reward_func/std": 0.0,
      "rewards/cumulative_reward_2/mean": 0.0,
      "rewards/cumulative_reward_2/std": 0.0,
      "rewards/final_correctness_reward_func/mean": 0.0,
      "rewards/final_correctness_reward_func/std": 0.0,
      "rewards/question_recreation_reward_func/mean": 0.02673749066889286,
      "rewards/question_recreation_reward_func/std": 0.014883634634315968,
      "rewards/soft_format_reward_func/mean": 0.0,
      "rewards/soft_format_reward_func/std": 0.0,
      "rewards/strict_format_reward_func/mean": 0.0,
      "rewards/strict_format_reward_func/std": 0.0,
      "rewards/xmlcount_reward_func/mean": 0.0,
      "rewards/xmlcount_reward_func/std": 0.0,
      "step": 10
    },
    {
      "epoch": 9.666666666666666,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": 0.03374993056058884,
      "train_runtime": 12750.2138,
      "train_samples_per_second": 0.006,
      "train_steps_per_second": 0.002
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 9380,
  "num_train_epochs": 10,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}