{
  "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": 23.0,
      "completions/mean_terminated_length": 23.0,
      "completions/min_length": 4.0,
      "completions/min_terminated_length": 4.0,
      "epoch": 1.6666666666666665,
      "frac_reward_zero_std": 0.75,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": -0.0,
      "num_tokens": 2232.0,
      "reward": 2.269645094871521,
      "reward_std": 0.00031144413514994085,
      "rewards/concensus_correctness_reward_func/mean": 1.0,
      "rewards/concensus_correctness_reward_func/std": 1.154700517654419,
      "rewards/consensus_reward_func/mean": 1.0,
      "rewards/consensus_reward_func/std": 1.154700517654419,
      "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": 0.019645093008875847,
      "rewards/question_recreation_reward_func/std": 0.005905917612835765,
      "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": 0.25,
      "rewards/xmlcount_reward_func/std": 0.28867512941360474,
      "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": 26.5,
      "completions/max_terminated_length": 26.5,
      "completions/mean_length": 21.0,
      "completions/mean_terminated_length": 21.0,
      "completions/min_length": 4.5,
      "completions/min_terminated_length": 4.5,
      "epoch": 3.6666666666666665,
      "frac_reward_zero_std": 0.75,
      "grad_norm": 0.007225025910884142,
      "kl": 0.08381480269599706,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0001,
      "num_tokens": 4448.0,
      "reward": 2.2057676911354065,
      "reward_std": 0.09018055349588394,
      "rewards/concensus_correctness_reward_func/mean": 1.0,
      "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": 0.01826777681708336,
      "rewards/question_recreation_reward_func/std": 0.0025345622561872005,
      "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": 0.1875,
      "rewards/xmlcount_reward_func/std": 0.125,
      "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,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 2.3013335521682166e-05,
      "kl": 0.07562753558158875,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0001,
      "num_tokens": 6528.0,
      "reward": 4.010498523712158,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func/mean": 2.0,
      "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,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 5.243593022896675e-06,
      "kl": 0.07563213258981705,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0001,
      "num_tokens": 8608.0,
      "reward": 4.013163328170776,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func/mean": 2.0,
      "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,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 3.89444176107645e-06,
      "kl": 0.15084898471832275,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0002,
      "num_tokens": 10688.0,
      "reward": 4.013163328170776,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func/mean": 2.0,
      "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
    },
    {
      "epoch": 9.666666666666666,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": 7.71828243159689e-05,
      "train_runtime": 343.8612,
      "train_samples_per_second": 0.233,
      "train_steps_per_second": 0.058
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 10688,
  "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": 1,
  "trial_name": null,
  "trial_params": null
}