{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.5,
  "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": 57.0,
      "completions/max_terminated_length": 57.0,
      "completions/mean_length": 57.0,
      "completions/mean_terminated_length": 57.0,
      "completions/min_length": 57.0,
      "completions/min_terminated_length": 57.0,
      "epoch": 1.5,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 1e-06,
      "loss": 0.0,
      "num_tokens": 5008.0,
      "reward": 3.707615375518799,
      "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": 1.0,
      "rewards/consensus_reward_func/std": 1.069045066833496,
      "rewards/cumulative_reward_2/mean": 0.0,
      "rewards/cumulative_reward_2/std": 0.0,
      "rewards/final_correctness_reward_func/mean": 1.5,
      "rewards/final_correctness_reward_func/std": 0.534522533416748,
      "rewards/question_recreation_reward_func/mean": 0.009615384973585606,
      "rewards/question_recreation_reward_func/std": 0.0,
      "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": 1.1979999542236328,
      "rewards/xmlcount_reward_func/std": 0.00213812617585063,
      "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": 57.0,
      "completions/max_terminated_length": 57.0,
      "completions/mean_length": 57.0,
      "completions/mean_terminated_length": 57.0,
      "completions/min_length": 57.0,
      "completions/min_terminated_length": 57.0,
      "epoch": 3.5,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 9.729086208503173e-07,
      "loss": 0.0,
      "num_tokens": 10016.0,
      "reward": 3.707615375518799,
      "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": 1.0,
      "rewards/consensus_reward_func/std": 1.069045066833496,
      "rewards/cumulative_reward_2/mean": 0.0,
      "rewards/cumulative_reward_2/std": 0.0,
      "rewards/final_correctness_reward_func/mean": 1.5,
      "rewards/final_correctness_reward_func/std": 0.534522533416748,
      "rewards/question_recreation_reward_func/mean": 0.009615384973585606,
      "rewards/question_recreation_reward_func/std": 0.0,
      "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": 1.1979999542236328,
      "rewards/xmlcount_reward_func/std": 0.00213812617585063,
      "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": 54.0,
      "completions/max_terminated_length": 54.0,
      "completions/mean_length": 54.0,
      "completions/mean_terminated_length": 54.0,
      "completions/min_length": 54.0,
      "completions/min_terminated_length": 54.0,
      "epoch": 5.5,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 8.945702546981968e-07,
      "loss": 0.0,
      "num_tokens": 15000.0,
      "reward": 3.199000120162964,
      "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": 1.0,
      "rewards/consensus_reward_func/std": 1.069045066833496,
      "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": 0.0,
      "rewards/question_recreation_reward_func/std": 0.0,
      "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": 1.1990000009536743,
      "rewards/xmlcount_reward_func/std": 0.001069063087925315,
      "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": 57.0,
      "completions/max_terminated_length": 57.0,
      "completions/mean_length": 57.0,
      "completions/mean_terminated_length": 57.0,
      "completions/min_length": 57.0,
      "completions/min_terminated_length": 57.0,
      "epoch": 7.5,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 7.734740790612136e-07,
      "loss": 0.0,
      "num_tokens": 19984.0,
      "reward": 3.220520257949829,
      "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": 1.0,
      "rewards/consensus_reward_func/std": 1.069045066833496,
      "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": 0.02152014710009098,
      "rewards/question_recreation_reward_func/std": 0.0,
      "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": 1.1990000009536743,
      "rewards/xmlcount_reward_func/std": 0.001069063087925315,
      "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": 57.0,
      "completions/max_terminated_length": 57.0,
      "completions/mean_length": 57.0,
      "completions/mean_terminated_length": 57.0,
      "completions/min_length": 57.0,
      "completions/min_terminated_length": 57.0,
      "epoch": 9.5,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 6.227427435703995e-07,
      "loss": 0.0,
      "num_tokens": 24992.0,
      "reward": 3.719520330429077,
      "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": 1.0,
      "rewards/consensus_reward_func/std": 1.069045066833496,
      "rewards/cumulative_reward_2/mean": 0.0,
      "rewards/cumulative_reward_2/std": 0.0,
      "rewards/final_correctness_reward_func/mean": 1.5,
      "rewards/final_correctness_reward_func/std": 0.534522533416748,
      "rewards/question_recreation_reward_func/mean": 0.02152014710009098,
      "rewards/question_recreation_reward_func/std": 0.0,
      "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": 1.1979999542236328,
      "rewards/xmlcount_reward_func/std": 0.00213812617585063,
      "step": 10
    },
    {
      "epoch": 9.5,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": 0.0,
      "train_runtime": 1956.0702,
      "train_samples_per_second": 0.082,
      "train_steps_per_second": 0.01
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 24992,
  "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": 8,
  "trial_name": null,
  "trial_params": null
}