{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.425531914893617,
  "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": 0.0851063829787234,
      "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": 2.773157477378845,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func/mean": 1.2665000259876251,
      "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": 0.006657483754679561,
      "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": 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": 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": 0.1702127659574468,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 4.415111107797445e-07,
      "loss": 0.0,
      "num_tokens": 2112.0,
      "reward": 2.671488881111145,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func/mean": 1.656000018119812,
      "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": 0.015488910721614957,
      "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": 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": 51.0,
      "completions/max_terminated_length": 51.0,
      "completions/mean_length": 40.875,
      "completions/mean_terminated_length": 40.875,
      "completions/min_length": 31.0,
      "completions/min_terminated_length": 31.0,
      "epoch": 0.2553191489361702,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 24.188209533691406,
      "kl": 0.0006922552565811202,
      "learning_rate": 2.934120444167326e-07,
      "loss": 0.066,
      "num_tokens": 3463.0,
      "reward": 0.12109604850411415,
      "reward_std": 0.01923441980034113,
      "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": 0.12109604850411415,
      "rewards/question_recreation_reward_func/std": 0.019095160998404026,
      "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": 11.0,
      "completions/max_terminated_length": 11.0,
      "completions/mean_length": 5.875,
      "completions/mean_terminated_length": 5.875,
      "completions/min_length": 3.0,
      "completions/min_terminated_length": 3.0,
      "epoch": 0.3404255319148936,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 150.0901336669922,
      "kl": 0.0003200410428689793,
      "learning_rate": 1.2500000000000005e-07,
      "loss": -0.0004,
      "num_tokens": 4534.0,
      "reward": 1.6251622596755624,
      "reward_std": 0.0022238311357796192,
      "rewards/concensus_correctness_reward_func/mean": 0.609000027179718,
      "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": 0.016162254847586155,
      "rewards/question_recreation_reward_func/std": 0.004925040062516928,
      "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": 43.5,
      "completions/max_terminated_length": 43.5,
      "completions/mean_length": 27.0,
      "completions/mean_terminated_length": 27.0,
      "completions/min_length": 12.5,
      "completions/min_terminated_length": 12.5,
      "epoch": 0.425531914893617,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 34.003170013427734,
      "kl": 0.0032135010151250754,
      "learning_rate": 1.507684480352292e-08,
      "loss": 0.0236,
      "num_tokens": 5774.0,
      "reward": 0.9951896788552403,
      "reward_std": 0.0007218425162136555,
      "rewards/concensus_correctness_reward_func/mean": 0.4779999852180481,
      "rewards/concensus_correctness_reward_func/std": 0.5519468784332275,
      "rewards/consensus_reward_func/mean": 0.5,
      "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": 0.017189682461321354,
      "rewards/question_recreation_reward_func/std": 0.006342948647215962,
      "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": 0.425531914893617,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": 0.017834216356277466,
      "train_runtime": 1576.6026,
      "train_samples_per_second": 0.025,
      "train_steps_per_second": 0.006
    }
  ],
  "logging_steps": 2,
  "max_steps": 10,
  "num_input_tokens_seen": 5774,
  "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
}