{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5882352941176471,
  "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": 14.0,
      "completions/max_terminated_length": 14.0,
      "completions/mean_length": 11.25,
      "completions/mean_terminated_length": 11.25,
      "completions/min_length": 8.5,
      "completions/min_terminated_length": 8.5,
      "epoch": 0.11764705882352941,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "num_tokens": 1114.0,
      "reward": 2.2253319025039673,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func/mean": 0.9810000061988831,
      "rewards/concensus_correctness_reward_func/std": 1.1327612400054932,
      "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": 0.5,
      "rewards/final_correctness_reward_func/std": 0.5773502588272095,
      "rewards/question_recreation_reward_func/mean": 0.11908186599612236,
      "rewards/question_recreation_reward_func/std": 0.018562591867521405,
      "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": 0.12525000050663948,
      "rewards/xmlcount_reward_func/std": 0.14462624117732048,
      "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": 0.125,
      "completions/max_length": 130.0,
      "completions/max_terminated_length": 11.5,
      "completions/mean_length": 37.375,
      "completions/mean_terminated_length": 6.5,
      "completions/min_length": 4.0,
      "completions/min_terminated_length": 4.0,
      "epoch": 0.23529411764705882,
      "frac_reward_zero_std": 0.75,
      "grad_norm": 14.441303253173828,
      "kl": 0.0,
      "learning_rate": 4.415111107797445e-07,
      "loss": -0.0278,
      "num_tokens": 2437.0,
      "reward": 1.0109836300835013,
      "reward_std": 0.003495625453069806,
      "rewards/concensus_correctness_reward_func/mean": 0.0,
      "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": 0.010983609594404697,
      "rewards/question_recreation_reward_func/std": 0.00478315120562911,
      "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": 27.0,
      "completions/max_terminated_length": 27.0,
      "completions/mean_length": 14.0,
      "completions/mean_terminated_length": 14.0,
      "completions/min_length": 6.5,
      "completions/min_terminated_length": 6.5,
      "epoch": 0.35294117647058826,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 22.528961181640625,
      "kl": 0.0022524516189150745,
      "learning_rate": 2.934120444167326e-07,
      "loss": -0.0087,
      "num_tokens": 3573.0,
      "reward": 0.6154132783412933,
      "reward_std": 0.0022592578316107392,
      "rewards/concensus_correctness_reward_func/mean": 0.4790000021457672,
      "rewards/concensus_correctness_reward_func/std": 0.5531015992164612,
      "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": 0.011163299903273582,
      "rewards/question_recreation_reward_func/std": 0.0054640877060592175,
      "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": 0.12525000050663948,
      "rewards/xmlcount_reward_func/std": 0.14462624117732048,
      "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": 0.47058823529411764,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 4.430883109307615e-06,
      "kl": 7.227063179016113e-07,
      "learning_rate": 1.2500000000000005e-07,
      "loss": 0.0,
      "num_tokens": 4629.0,
      "reward": 3.321390450000763,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func/mean": 2.259999990463257,
      "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": 0.061390502378344536,
      "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": 103.0,
      "completions/max_terminated_length": 103.0,
      "completions/mean_length": 35.0,
      "completions/mean_terminated_length": 35.0,
      "completions/min_length": 4.0,
      "completions/min_terminated_length": 4.0,
      "epoch": 0.5882352941176471,
      "frac_reward_zero_std": 0.75,
      "grad_norm": 19.857900619506836,
      "kl": 0.004790606792084873,
      "learning_rate": 1.507684480352292e-08,
      "loss": 0.0087,
      "num_tokens": 5933.0,
      "reward": 1.2049373164772987,
      "reward_std": 0.015522590838372707,
      "rewards/concensus_correctness_reward_func/mean": 0.125,
      "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": 0.07993736304342747,
      "rewards/question_recreation_reward_func/std": 0.028143223375082016,
      "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": 0.5882352941176471,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": -0.005555021618306633,
      "train_runtime": 686.0977,
      "train_samples_per_second": 0.058,
      "train_steps_per_second": 0.015
    }
  ],
  "logging_steps": 2,
  "max_steps": 10,
  "num_input_tokens_seen": 5933,
  "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
}