{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "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": 0.5,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 199.0,
      "completions/mean_length": 194.375,
      "completions/mean_terminated_length": 172.5,
      "completions/min_length": 151.5,
      "completions/min_terminated_length": 151.5,
      "epoch": 2.0,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 8.42098331451416,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.0055,
      "num_tokens": 2579.0,
      "reward": 0.014096824452280998,
      "reward_std": 0.00433365476783365,
      "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": 0.014096824452280998,
      "rewards/question_recreation_reward_func/std": 0.007435560924932361,
      "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": 0.375,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 167.5,
      "completions/mean_length": 182.375,
      "completions/mean_terminated_length": 134.91666412353516,
      "completions/min_length": 102.5,
      "completions/min_terminated_length": 102.5,
      "epoch": 4.0,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 9.635068893432617,
      "kl": 0.0003269764692959143,
      "learning_rate": 4.415111107797445e-07,
      "loss": 0.0833,
      "num_tokens": 5062.0,
      "reward": 0.012714702636003494,
      "reward_std": 0.004921070067211986,
      "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": 0.012714702636003494,
      "rewards/question_recreation_reward_func/std": 0.011344576952978969,
      "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": 0.125,
      "completions/max_length": 237.5,
      "completions/max_terminated_length": 190.5,
      "completions/mean_length": 136.75,
      "completions/mean_terminated_length": 116.41666793823242,
      "completions/min_length": 30.0,
      "completions/min_terminated_length": 30.0,
      "epoch": 6.0,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 14.077054977416992,
      "kl": 0.0014197196724126115,
      "learning_rate": 2.934120444167326e-07,
      "loss": 0.0104,
      "num_tokens": 7180.0,
      "reward": 0.019166121259331703,
      "reward_std": 0.013739365618675947,
      "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": 0.019166121259331703,
      "rewards/question_recreation_reward_func/std": 0.018057925160974264,
      "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": 0.125,
      "completions/max_length": 239.5,
      "completions/max_terminated_length": 151.0,
      "completions/mean_length": 134.25,
      "completions/mean_terminated_length": 108.08333396911621,
      "completions/min_length": 39.0,
      "completions/min_terminated_length": 39.0,
      "epoch": 8.0,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 10.22560977935791,
      "kl": 0.004310431773774326,
      "learning_rate": 1.2500000000000005e-07,
      "loss": -0.054,
      "num_tokens": 9278.0,
      "reward": 0.013700914569199085,
      "reward_std": 0.00266791571630165,
      "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": 0.013700914569199085,
      "rewards/question_recreation_reward_func/std": 0.006989771965891123,
      "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": 0.125,
      "completions/max_length": 240.5,
      "completions/max_terminated_length": 211.5,
      "completions/mean_length": 145.5,
      "completions/mean_terminated_length": 133.5,
      "completions/min_length": 72.5,
      "completions/min_terminated_length": 72.5,
      "epoch": 10.0,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 10.423093795776367,
      "kl": 0.0022090721467975527,
      "learning_rate": 1.507684480352292e-08,
      "loss": -0.0387,
      "num_tokens": 11466.0,
      "reward": 0.02149433922022581,
      "reward_std": 0.007891800487414002,
      "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": 0.021494340151548386,
      "rewards/question_recreation_reward_func/std": 0.010832870844751596,
      "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": 10.0,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": 0.0012827153317630292,
      "train_runtime": 1329.0093,
      "train_samples_per_second": 0.03,
      "train_steps_per_second": 0.008
    }
  ],
  "logging_steps": 2,
  "max_steps": 10,
  "num_input_tokens_seen": 11466,
  "num_train_epochs": 10,
  "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
}