{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "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": 20.0,
      "completions/max_terminated_length": 20.0,
      "completions/mean_length": 18.375,
      "completions/mean_terminated_length": 18.375,
      "completions/min_length": 16.5,
      "completions/min_terminated_length": 16.5,
      "epoch": 2.0,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 36.412506103515625,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.0211,
      "num_tokens": 1171.0,
      "reward": 0.04241397604346275,
      "reward_std": 0.0005018207884859294,
      "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": 0.04241397604346275,
      "rewards/question_recreation_reward_func/std": 0.003023179975571111,
      "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": 19.5,
      "completions/max_terminated_length": 19.5,
      "completions/mean_length": 17.25,
      "completions/mean_terminated_length": 17.25,
      "completions/min_length": 15.0,
      "completions/min_terminated_length": 15.0,
      "epoch": 4.0,
      "frac_reward_zero_std": 0.75,
      "grad_norm": 0.0011490473989397287,
      "kl": 0.023425381630659103,
      "learning_rate": 4.415111107797445e-07,
      "loss": 0.0141,
      "num_tokens": 2333.0,
      "reward": 0.05135399103164673,
      "reward_std": 0.0004492544394452125,
      "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": 0.05135399103164673,
      "rewards/question_recreation_reward_func/std": 0.0013169957674108446,
      "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": 20.0,
      "completions/max_terminated_length": 20.0,
      "completions/mean_length": 16.75,
      "completions/mean_terminated_length": 16.75,
      "completions/min_length": 12.5,
      "completions/min_terminated_length": 12.5,
      "epoch": 6.0,
      "frac_reward_zero_std": 0.75,
      "grad_norm": 0.002683391561731696,
      "kl": 0.01725853289826773,
      "learning_rate": 2.934120444167326e-07,
      "loss": -0.0337,
      "num_tokens": 3491.0,
      "reward": 0.04132162220776081,
      "reward_std": 0.00213236385025084,
      "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": 0.04132162220776081,
      "rewards/question_recreation_reward_func/std": 0.005779752740636468,
      "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": 22.0,
      "completions/max_terminated_length": 22.0,
      "completions/mean_length": 19.125,
      "completions/mean_terminated_length": 19.125,
      "completions/min_length": 16.5,
      "completions/min_terminated_length": 16.5,
      "epoch": 8.0,
      "frac_reward_zero_std": 0.75,
      "grad_norm": 0.01040867529809475,
      "kl": 0.013252663193270564,
      "learning_rate": 1.2500000000000005e-07,
      "loss": 0.015,
      "num_tokens": 4668.0,
      "reward": 0.051251694560050964,
      "reward_std": 0.000197974281036295,
      "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": 0.051251694560050964,
      "rewards/question_recreation_reward_func/std": 0.0009621602948755026,
      "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": 22.0,
      "completions/max_terminated_length": 22.0,
      "completions/mean_length": 19.125,
      "completions/mean_terminated_length": 19.125,
      "completions/min_length": 16.5,
      "completions/min_terminated_length": 16.5,
      "epoch": 10.0,
      "frac_reward_zero_std": 0.75,
      "grad_norm": 0.0034917769953608513,
      "kl": 0.010507109924219549,
      "learning_rate": 1.507684480352292e-08,
      "loss": 0.0297,
      "num_tokens": 5845.0,
      "reward": 0.042627327144145966,
      "reward_std": 0.000197974281036295,
      "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": 0.042627327144145966,
      "rewards/question_recreation_reward_func/std": 0.0031550577841699123,
      "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": 10.0,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": 0.009235620871186257,
      "train_runtime": 604.9853,
      "train_samples_per_second": 0.066,
      "train_steps_per_second": 0.017
    }
  ],
  "logging_steps": 2,
  "max_steps": 10,
  "num_input_tokens_seen": 5845,
  "num_train_epochs": 10,
  "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
}