{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.8,
  "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": 0.1875,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 390.0,
      "completions/mean_length": 320.5,
      "completions/mean_terminated_length": 166.0357151031494,
      "completions/min_length": 18.5,
      "completions/min_terminated_length": 18.5,
      "epoch": 1.8,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 13.776973724365234,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.0991,
      "num_tokens": 9224.0,
      "reward": 0.06882327049970627,
      "reward_std": 0.029990280978381634,
      "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": 0.06882327049970627,
      "rewards/question_recreation_reward_func/std": 0.047005095053464174,
      "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": 0.125,
      "completions/max_length": 699.5,
      "completions/max_terminated_length": 607.0,
      "completions/mean_length": 290.875,
      "completions/mean_terminated_length": 193.4791717529297,
      "completions/min_length": 5.0,
      "completions/min_terminated_length": 5.0,
      "epoch": 3.8,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 11.026899337768555,
      "kl": 0.0011377405207895208,
      "learning_rate": 4.864543104251586e-07,
      "loss": -0.0341,
      "num_tokens": 17974.0,
      "reward": 0.13937734812498093,
      "reward_std": 0.06329425051808357,
      "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": 0.13937734812498093,
      "rewards/question_recreation_reward_func/std": 0.07533928006887436,
      "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": 0.25,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 345.0,
      "completions/mean_length": 340.0,
      "completions/mean_terminated_length": 112.00000381469727,
      "completions/min_length": 15.5,
      "completions/min_terminated_length": 15.5,
      "epoch": 5.8,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 5.603325366973877,
      "kl": 0.0009242366522812517,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.1496,
      "num_tokens": 27510.0,
      "reward": 0.09400873444974422,
      "reward_std": 0.06265044631436467,
      "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": 0.09400873444974422,
      "rewards/question_recreation_reward_func/std": 0.07358316518366337,
      "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": 490.5,
      "completions/max_terminated_length": 490.5,
      "completions/mean_length": 196.3125,
      "completions/mean_terminated_length": 196.3125,
      "completions/min_length": 8.5,
      "completions/min_terminated_length": 8.5,
      "epoch": 7.8,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 11.331869125366211,
      "kl": 0.003321434611279983,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0419,
      "num_tokens": 34747.0,
      "reward": 0.08949379064142704,
      "reward_std": 0.042363014072179794,
      "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": 0.08949379064142704,
      "rewards/question_recreation_reward_func/std": 0.05983787029981613,
      "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": 0.0625,
      "completions/max_length": 750.5,
      "completions/max_terminated_length": 456.5,
      "completions/mean_length": 192.5,
      "completions/mean_terminated_length": 137.23214721679688,
      "completions/min_length": 7.5,
      "completions/min_terminated_length": 7.5,
      "epoch": 9.8,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 13.011316299438477,
      "kl": 0.004956400036462583,
      "learning_rate": 3.1137137178519977e-07,
      "loss": -0.0044,
      "num_tokens": 41923.0,
      "reward": 0.11588690988719463,
      "reward_std": 0.04010107275098562,
      "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": 0.10807440988719463,
      "rewards/question_recreation_reward_func/std": 0.0751601941883564,
      "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": 0.0078125,
      "rewards/xmlcount_reward_func/std": 0.022097086533904076,
      "step": 10
    },
    {
      "epoch": 9.8,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": 0.050427977740764615,
      "train_runtime": 870.114,
      "train_samples_per_second": 0.184,
      "train_steps_per_second": 0.023
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 41923,
  "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
}