{
  "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": 307.5,
      "completions/max_terminated_length": 307.5,
      "completions/mean_length": 263.375,
      "completions/mean_terminated_length": 263.375,
      "completions/min_length": 209.0,
      "completions/min_terminated_length": 209.0,
      "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": 4155.0,
      "reward": 6.239135265350342,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func/mean": 2.0,
      "rewards/concensus_correctness_reward_func/std": 0.0,
      "rewards/consensus_reward_func/mean": 2.0,
      "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": 0.48913562297821045,
      "rewards/question_recreation_reward_func/std": 0.49358050525188446,
      "rewards/soft_format_reward_func/mean": 0.0,
      "rewards/soft_format_reward_func/std": 0.0,
      "rewards/strict_format_reward_func/mean": 0.5,
      "rewards/strict_format_reward_func/std": 0.0,
      "rewards/xmlcount_reward_func/mean": 1.25,
      "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": 323.5,
      "completions/max_terminated_length": 323.5,
      "completions/mean_length": 271.25,
      "completions/mean_terminated_length": 271.25,
      "completions/min_length": 206.0,
      "completions/min_terminated_length": 206.0,
      "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": 8373.0,
      "reward": 6.239135265350342,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func/mean": 2.0,
      "rewards/concensus_correctness_reward_func/std": 0.0,
      "rewards/consensus_reward_func/mean": 2.0,
      "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": 0.48913562297821045,
      "rewards/question_recreation_reward_func/std": 0.49358050525188446,
      "rewards/soft_format_reward_func/mean": 0.0,
      "rewards/soft_format_reward_func/std": 0.0,
      "rewards/strict_format_reward_func/mean": 0.5,
      "rewards/strict_format_reward_func/std": 0.0,
      "rewards/xmlcount_reward_func/mean": 1.25,
      "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": 315.0,
      "completions/max_terminated_length": 315.0,
      "completions/mean_length": 267.875,
      "completions/mean_terminated_length": 267.875,
      "completions/min_length": 205.0,
      "completions/min_terminated_length": 205.0,
      "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": 12564.0,
      "reward": 6.2451043128967285,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func/mean": 2.0,
      "rewards/concensus_correctness_reward_func/std": 0.0,
      "rewards/consensus_reward_func/mean": 2.0,
      "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": 0.4951046109199524,
      "rewards/question_recreation_reward_func/std": 0.5381311774253845,
      "rewards/soft_format_reward_func/mean": 0.0,
      "rewards/soft_format_reward_func/std": 0.0,
      "rewards/strict_format_reward_func/mean": 0.5,
      "rewards/strict_format_reward_func/std": 0.0,
      "rewards/xmlcount_reward_func/mean": 1.25,
      "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": 323.0,
      "completions/max_terminated_length": 323.0,
      "completions/mean_length": 274.875,
      "completions/mean_terminated_length": 274.875,
      "completions/min_length": 214.0,
      "completions/min_terminated_length": 214.0,
      "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": 16811.0,
      "reward": 6.074583053588867,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func/mean": 2.0,
      "rewards/concensus_correctness_reward_func/std": 0.0,
      "rewards/consensus_reward_func/mean": 2.0,
      "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": 0.3245830535888672,
      "rewards/question_recreation_reward_func/std": 0.33200282603502274,
      "rewards/soft_format_reward_func/mean": 0.0,
      "rewards/soft_format_reward_func/std": 0.0,
      "rewards/strict_format_reward_func/mean": 0.5,
      "rewards/strict_format_reward_func/std": 0.0,
      "rewards/xmlcount_reward_func/mean": 1.25,
      "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": 285.0,
      "completions/max_terminated_length": 285.0,
      "completions/mean_length": 256.25,
      "completions/mean_terminated_length": 256.25,
      "completions/min_length": 226.0,
      "completions/min_terminated_length": 226.0,
      "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": 20909.0,
      "reward": 6.075939893722534,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func/mean": 2.0,
      "rewards/concensus_correctness_reward_func/std": 0.0,
      "rewards/consensus_reward_func/mean": 2.0,
      "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": 0.32593993842601776,
      "rewards/question_recreation_reward_func/std": 0.33043602854013443,
      "rewards/soft_format_reward_func/mean": 0.0,
      "rewards/soft_format_reward_func/std": 0.0,
      "rewards/strict_format_reward_func/mean": 0.5,
      "rewards/strict_format_reward_func/std": 0.0,
      "rewards/xmlcount_reward_func/mean": 1.25,
      "rewards/xmlcount_reward_func/std": 0.0,
      "step": 10
    },
    {
      "epoch": 9.666666666666666,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": 0.0,
      "train_runtime": 469.5187,
      "train_samples_per_second": 0.17,
      "train_steps_per_second": 0.043
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 20909,
  "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": 1,
  "trial_name": null,
  "trial_params": null
}