{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 19.666666666666668,
  "eval_steps": 500,
  "global_step": 20,
  "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": 1.6666666666666665,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "num_tokens": 2080.0,
      "reward": 3.9265516996383667,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func/mean": 1.9120000004768372,
      "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": 0.014551669359207153,
      "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": 3.6666666666666665,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "num_tokens": 4160.0,
      "reward": 3.9265516996383667,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func/mean": 1.9120000004768372,
      "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": 0.014551669359207153,
      "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": 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": 5.666666666666667,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "num_tokens": 6240.0,
      "reward": 3.9244987964630127,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func/mean": 1.9140000343322754,
      "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": 0.010498687624931335,
      "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": 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": 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": 7.666666666666667,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "num_tokens": 8320.0,
      "reward": 3.9251632690429688,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func/mean": 1.9120000004768372,
      "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": 0.013163329334929585,
      "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": 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": 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": 9.666666666666666,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "num_tokens": 10400.0,
      "reward": 3.9251632690429688,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func/mean": 1.9120000004768372,
      "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": 0.013163329334929585,
      "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": 10
    },
    {
      "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": 11.666666666666666,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "num_tokens": 12480.0,
      "reward": 3.9244987964630127,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func/mean": 1.9140000343322754,
      "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": 0.010498687624931335,
      "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": 12
    },
    {
      "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": 13.666666666666666,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "num_tokens": 14560.0,
      "reward": 3.921721935272217,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func/mean": 1.9140000343322754,
      "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": 0.0077220075763762,
      "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": 14
    },
    {
      "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": 15.666666666666666,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "num_tokens": 16640.0,
      "reward": 3.9265516996383667,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func/mean": 1.9120000004768372,
      "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": 0.014551669359207153,
      "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": 16
    },
    {
      "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": 17.666666666666668,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "num_tokens": 18720.0,
      "reward": 3.9231103658676147,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func/mean": 1.9140000343322754,
      "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": 0.009110347600653768,
      "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": 18
    },
    {
      "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": 19.666666666666668,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "num_tokens": 20800.0,
      "reward": 3.9231103658676147,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func/mean": 1.9140000343322754,
      "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": 0.009110347600653768,
      "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": 20
    },
    {
      "epoch": 19.666666666666668,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 0.0,
      "train_runtime": 356.5869,
      "train_samples_per_second": 0.224,
      "train_steps_per_second": 0.056
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 20800,
  "num_train_epochs": 20,
  "save_steps": 25,
  "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": 1,
  "trial_name": null,
  "trial_params": null
}