{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.43478260869565216,
  "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": 58.5,
      "completions/max_terminated_length": 58.5,
      "completions/mean_length": 36.625,
      "completions/mean_terminated_length": 36.625,
      "completions/min_length": 20.5,
      "completions/min_terminated_length": 20.5,
      "epoch": 0.08695652173913043,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 42.607154846191406,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.104,
      "num_tokens": 1317.0,
      "reward": 0.2697029113769531,
      "reward_std": 0.06398913823068142,
      "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": 0.009077915921807289,
      "rewards/question_recreation_reward_func/std": 0.009524198016151786,
      "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": 0.2606250084936619,
      "rewards/xmlcount_reward_func/std": 0.10797951556742191,
      "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": 97.0,
      "completions/max_terminated_length": 97.0,
      "completions/mean_length": 46.625,
      "completions/mean_terminated_length": 46.625,
      "completions/min_length": 23.0,
      "completions/min_terminated_length": 23.0,
      "epoch": 0.17391304347826086,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 72.13888549804688,
      "kl": 0.016350419347872958,
      "learning_rate": 4.415111107797445e-07,
      "loss": 0.0001,
      "num_tokens": 2714.0,
      "reward": 0.3842458426952362,
      "reward_std": 0.1307172253727913,
      "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": 0.08724584802985191,
      "rewards/question_recreation_reward_func/std": 0.02099667303264141,
      "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": 0.296999990940094,
      "rewards/xmlcount_reward_func/std": 0.12750041857361794,
      "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": 34.5,
      "completions/max_terminated_length": 34.5,
      "completions/mean_length": 26.875,
      "completions/mean_terminated_length": 26.875,
      "completions/min_length": 20.0,
      "completions/min_terminated_length": 20.0,
      "epoch": 0.2608695652173913,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 40.991939544677734,
      "kl": 0.05134714557789266,
      "learning_rate": 2.934120444167326e-07,
      "loss": 0.0068,
      "num_tokens": 3953.0,
      "reward": 0.39916859567165375,
      "reward_std": 0.056330110877752304,
      "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": 0.004543595423456281,
      "rewards/question_recreation_reward_func/std": 0.009087190846912563,
      "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": 0.3946250081062317,
      "rewards/xmlcount_reward_func/std": 0.055458297953009605,
      "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": 117.5,
      "completions/max_terminated_length": 117.5,
      "completions/mean_length": 47.5,
      "completions/mean_terminated_length": 47.5,
      "completions/min_length": 18.5,
      "completions/min_terminated_length": 18.5,
      "epoch": 0.34782608695652173,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 39.77725601196289,
      "kl": 0.0206502788932994,
      "learning_rate": 1.2500000000000005e-07,
      "loss": 0.2759,
      "num_tokens": 5357.0,
      "reward": 0.5431624054908752,
      "reward_std": 0.4544815495610237,
      "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": 0.25,
      "rewards/final_correctness_reward_func/std": 0.5,
      "rewards/question_recreation_reward_func/mean": 0.024537368677556515,
      "rewards/question_recreation_reward_func/std": 0.018834506161510944,
      "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": 0.26862500607967377,
      "rewards/xmlcount_reward_func/std": 0.13356759771704674,
      "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": 47.5,
      "completions/max_terminated_length": 47.5,
      "completions/mean_length": 27.875,
      "completions/mean_terminated_length": 27.875,
      "completions/min_length": 20.0,
      "completions/min_terminated_length": 20.0,
      "epoch": 0.43478260869565216,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 69.54534149169922,
      "kl": 0.023991694557480514,
      "learning_rate": 1.507684480352292e-08,
      "loss": 0.0467,
      "num_tokens": 6604.0,
      "reward": 1.1605660021305084,
      "reward_std": 0.4542441703379154,
      "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": 0.75,
      "rewards/final_correctness_reward_func/std": 1.0773502588272095,
      "rewards/question_recreation_reward_func/mean": 0.06994102522730827,
      "rewards/question_recreation_reward_func/std": 0.02063577761873603,
      "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": 0.34062498807907104,
      "rewards/xmlcount_reward_func/std": 0.11164618656039238,
      "step": 10
    },
    {
      "epoch": 0.43478260869565216,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": 0.08669190295040607,
      "train_runtime": 717.6828,
      "train_samples_per_second": 0.056,
      "train_steps_per_second": 0.014
    }
  ],
  "logging_steps": 2,
  "max_steps": 10,
  "num_input_tokens_seen": 6604,
  "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
}