{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5,
  "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": 4.0,
      "completions/max_terminated_length": 4.0,
      "completions/mean_length": 4.0,
      "completions/mean_terminated_length": 4.0,
      "completions/min_length": 4.0,
      "completions/min_terminated_length": 4.0,
      "epoch": 0.1,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "num_tokens": 1056.0,
      "reward": 2.501505732536316,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func/mean": 0.968999981880188,
      "rewards/concensus_correctness_reward_func/std": 1.1189048290252686,
      "rewards/consensus_reward_func/mean": 1.5,
      "rewards/consensus_reward_func/std": 0.5773502588272095,
      "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": 0.03250573016703129,
      "rewards/question_recreation_reward_func/std": 0.0031549197155982256,
      "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": 18.0,
      "completions/max_terminated_length": 18.0,
      "completions/mean_length": 7.5,
      "completions/mean_terminated_length": 7.5,
      "completions/min_length": 4.0,
      "completions/min_terminated_length": 4.0,
      "epoch": 0.2,
      "frac_reward_zero_std": 0.75,
      "grad_norm": 64.29496765136719,
      "kl": 0.0,
      "learning_rate": 4.415111107797445e-07,
      "loss": 0.1375,
      "num_tokens": 2140.0,
      "reward": 2.162332773208618,
      "reward_std": 0.691501259803772,
      "rewards/concensus_correctness_reward_func/mean": 0.9030000418424606,
      "rewards/concensus_correctness_reward_func/std": 0.6905781626701355,
      "rewards/consensus_reward_func/mean": 1.25,
      "rewards/consensus_reward_func/std": 1.0773502588272095,
      "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": 0.009332760702818632,
      "rewards/question_recreation_reward_func/std": 0.00458485318813473,
      "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": 11.5,
      "completions/max_terminated_length": 11.5,
      "completions/mean_length": 7.75,
      "completions/mean_terminated_length": 7.75,
      "completions/min_length": 4.0,
      "completions/min_terminated_length": 4.0,
      "epoch": 0.3,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.005112084560096264,
      "kl": 0.005986911244690418,
      "learning_rate": 2.934120444167326e-07,
      "loss": 0.0,
      "num_tokens": 3226.0,
      "reward": 2.0115684112533927,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func/mean": 1.0,
      "rewards/concensus_correctness_reward_func/std": 0.0,
      "rewards/consensus_reward_func/mean": 1.0,
      "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": 0.01156841404736042,
      "rewards/question_recreation_reward_func/std": 0.006134120747447014,
      "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": 4.0,
      "completions/max_terminated_length": 4.0,
      "completions/mean_length": 4.0,
      "completions/mean_terminated_length": 4.0,
      "completions/min_length": 4.0,
      "completions/min_terminated_length": 4.0,
      "epoch": 0.4,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.00172651547472924,
      "kl": 7.607042789459229e-05,
      "learning_rate": 1.2500000000000005e-07,
      "loss": 0.0,
      "num_tokens": 4282.0,
      "reward": 3.807758629322052,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func/mean": 2.254500061273575,
      "rewards/concensus_correctness_reward_func/std": 0.3516063094139099,
      "rewards/consensus_reward_func/mean": 1.5,
      "rewards/consensus_reward_func/std": 0.5773502588272095,
      "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": 0.05325863230973482,
      "rewards/question_recreation_reward_func/std": 0.0009418438421562314,
      "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": 11.5,
      "completions/max_terminated_length": 11.5,
      "completions/mean_length": 7.75,
      "completions/mean_terminated_length": 7.75,
      "completions/min_length": 4.0,
      "completions/min_terminated_length": 4.0,
      "epoch": 0.5,
      "frac_reward_zero_std": 0.75,
      "grad_norm": 0.00020738673629239202,
      "kl": 0.005593676585704088,
      "learning_rate": 1.507684480352292e-08,
      "loss": 0.0,
      "num_tokens": 5368.0,
      "reward": 3.2286359071731567,
      "reward_std": 2.38063839788083e-05,
      "rewards/concensus_correctness_reward_func/mean": 2.180999994277954,
      "rewards/concensus_correctness_reward_func/std": 2.0057148337364197,
      "rewards/consensus_reward_func/mean": 1.0,
      "rewards/consensus_reward_func/std": 1.154700517654419,
      "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": 0.04763588309288025,
      "rewards/question_recreation_reward_func/std": 0.010593654587864876,
      "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": 0.5,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": 0.027499935874280367,
      "train_runtime": 464.5869,
      "train_samples_per_second": 0.086,
      "train_steps_per_second": 0.022
    }
  ],
  "logging_steps": 2,
  "max_steps": 10,
  "num_input_tokens_seen": 5368,
  "num_train_epochs": 1,
  "save_steps": 10,
  "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
}