{
  "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": 44.0,
      "completions/max_terminated_length": 44.0,
      "completions/mean_length": 37.5,
      "completions/mean_terminated_length": 37.5,
      "completions/min_length": 31.0,
      "completions/min_terminated_length": 31.0,
      "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": 2648.0,
      "reward": 1.6252106428146362,
      "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": 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": 1.0,
      "rewards/final_correctness_reward_func/std": 1.069045066833496,
      "rewards/question_recreation_reward_func/mean": 0.12671070359647274,
      "rewards/question_recreation_reward_func/std": 0.11452235607430339,
      "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": 0.4985000044107437,
      "rewards/xmlcount_reward_func/std": 0.0005345235695131123,
      "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": 44.0,
      "completions/max_terminated_length": 44.0,
      "completions/mean_length": 37.5,
      "completions/mean_terminated_length": 37.5,
      "completions/min_length": 31.0,
      "completions/min_terminated_length": 31.0,
      "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": 5296.0,
      "reward": 1.6252106428146362,
      "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": 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": 1.0,
      "rewards/final_correctness_reward_func/std": 1.069045066833496,
      "rewards/question_recreation_reward_func/mean": 0.12671070359647274,
      "rewards/question_recreation_reward_func/std": 0.11452235607430339,
      "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": 0.4985000044107437,
      "rewards/xmlcount_reward_func/std": 0.0005345235695131123,
      "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": 56.0,
      "completions/max_terminated_length": 56.0,
      "completions/mean_length": 43.5,
      "completions/mean_terminated_length": 43.5,
      "completions/min_length": 31.0,
      "completions/min_terminated_length": 31.0,
      "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": 8040.0,
      "reward": 1.2229787409305573,
      "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": 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": 0.5,
      "rewards/final_correctness_reward_func/std": 0.534522533416748,
      "rewards/question_recreation_reward_func/mean": 0.22397876530885696,
      "rewards/question_recreation_reward_func/std": 0.22274477779865265,
      "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": 0.49900001287460327,
      "rewards/xmlcount_reward_func/std": 0.0010690471390262246,
      "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": 56.0,
      "completions/max_terminated_length": 56.0,
      "completions/mean_length": 43.5,
      "completions/mean_terminated_length": 43.5,
      "completions/min_length": 31.0,
      "completions/min_terminated_length": 31.0,
      "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": 10784.0,
      "reward": 1.0384200811386108,
      "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": 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": 0.5,
      "rewards/final_correctness_reward_func/std": 0.534522533416748,
      "rewards/question_recreation_reward_func/mean": 0.03942018747329712,
      "rewards/question_recreation_reward_func/std": 0.004121434438275173,
      "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": 0.49900001287460327,
      "rewards/xmlcount_reward_func/std": 0.0010690471390262246,
      "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": 44.0,
      "completions/max_terminated_length": 44.0,
      "completions/mean_length": 37.5,
      "completions/mean_terminated_length": 37.5,
      "completions/min_length": 31.0,
      "completions/min_terminated_length": 31.0,
      "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": 13432.0,
      "reward": 1.5381457805633545,
      "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": 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": 1.0,
      "rewards/final_correctness_reward_func/std": 1.069045066833496,
      "rewards/question_recreation_reward_func/mean": 0.039645951241254807,
      "rewards/question_recreation_reward_func/std": 0.003880080836097477,
      "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": 0.4985000044107437,
      "rewards/xmlcount_reward_func/std": 0.0005345235695131123,
      "step": 10
    },
    {
      "epoch": 9.666666666666666,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": 0.0,
      "train_runtime": 615.6926,
      "train_samples_per_second": 0.26,
      "train_steps_per_second": 0.032
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 13432,
  "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": 2,
  "trial_name": null,
  "trial_params": null
}