{
  "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": 38.0,
      "completions/max_terminated_length": 38.0,
      "completions/mean_length": 36.0,
      "completions/mean_terminated_length": 36.0,
      "completions/min_length": 34.0,
      "completions/min_terminated_length": 34.0,
      "epoch": 1.6666666666666665,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "num_tokens": 2624.0,
      "reward": 1.544047236442566,
      "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": 1.0,
      "rewards/final_correctness_reward_func/std": 1.069045066833496,
      "rewards/question_recreation_reward_func/mean": 0.04404727555811405,
      "rewards/question_recreation_reward_func/std": 0.006210642866790295,
      "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": 0.5,
      "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": 38.0,
      "completions/max_terminated_length": 38.0,
      "completions/mean_length": 36.0,
      "completions/mean_terminated_length": 36.0,
      "completions/min_length": 34.0,
      "completions/min_terminated_length": 34.0,
      "epoch": 3.6666666666666665,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "num_tokens": 5248.0,
      "reward": 1.544047236442566,
      "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": 1.0,
      "rewards/final_correctness_reward_func/std": 1.069045066833496,
      "rewards/question_recreation_reward_func/mean": 0.04404727555811405,
      "rewards/question_recreation_reward_func/std": 0.006210642866790295,
      "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": 0.5,
      "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": 36.5,
      "completions/max_terminated_length": 36.5,
      "completions/mean_length": 35.25,
      "completions/mean_terminated_length": 35.25,
      "completions/min_length": 34.0,
      "completions/min_terminated_length": 34.0,
      "epoch": 5.666666666666667,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "num_tokens": 7860.0,
      "reward": 1.0439621806144714,
      "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": 0.5,
      "rewards/final_correctness_reward_func/std": 0.534522533416748,
      "rewards/question_recreation_reward_func/mean": 0.04396216757595539,
      "rewards/question_recreation_reward_func/std": 0.0011157767912663985,
      "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": 0.5,
      "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": 36.5,
      "completions/max_terminated_length": 36.5,
      "completions/mean_length": 35.25,
      "completions/mean_terminated_length": 35.25,
      "completions/min_length": 34.0,
      "completions/min_terminated_length": 34.0,
      "epoch": 7.666666666666667,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "num_tokens": 10472.0,
      "reward": 1.039027601480484,
      "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": 0.5,
      "rewards/final_correctness_reward_func/std": 0.534522533416748,
      "rewards/question_recreation_reward_func/mean": 0.039027515798807144,
      "rewards/question_recreation_reward_func/std": 0.005258616900391644,
      "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": 0.5,
      "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": 38.0,
      "completions/max_terminated_length": 38.0,
      "completions/mean_length": 36.0,
      "completions/mean_terminated_length": 36.0,
      "completions/min_length": 34.0,
      "completions/min_terminated_length": 34.0,
      "epoch": 9.666666666666666,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "num_tokens": 13096.0,
      "reward": 1.5389521718025208,
      "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": 1.0,
      "rewards/final_correctness_reward_func/std": 1.069045066833496,
      "rewards/question_recreation_reward_func/mean": 0.038952119648456573,
      "rewards/question_recreation_reward_func/std": 0.005339219787856564,
      "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": 0.5,
      "rewards/xmlcount_reward_func/std": 0.0,
      "step": 10
    },
    {
      "epoch": 9.666666666666666,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": 0.0,
      "train_runtime": 489.7862,
      "train_samples_per_second": 0.327,
      "train_steps_per_second": 0.041
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 13096,
  "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
}