{
  "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": 47.5,
      "completions/max_terminated_length": 47.5,
      "completions/mean_length": 41.375,
      "completions/mean_terminated_length": 41.375,
      "completions/min_length": 37.0,
      "completions/min_terminated_length": 37.0,
      "epoch": 2.0,
      "frac_reward_zero_std": 0.75,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": -0.0063,
      "num_tokens": 1355.0,
      "reward": 0.5854154527187347,
      "reward_std": 0.0009854354429990053,
      "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": 0.08541545830667019,
      "rewards/question_recreation_reward_func/std": 0.057605274370871484,
      "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": 0.5,
      "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": 48.0,
      "completions/max_terminated_length": 48.0,
      "completions/mean_length": 39.25,
      "completions/mean_terminated_length": 39.25,
      "completions/min_length": 28.0,
      "completions/min_terminated_length": 28.0,
      "epoch": 4.0,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 9.636852264404297,
      "kl": 0.02098847759043565,
      "learning_rate": 4.415111107797445e-07,
      "loss": -0.0376,
      "num_tokens": 2693.0,
      "reward": 0.47920550405979156,
      "reward_std": 0.08743657803279348,
      "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": 0.041955491527915,
      "rewards/question_recreation_reward_func/std": 0.00228323187911883,
      "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": 0.4372500032186508,
      "rewards/xmlcount_reward_func/std": 0.12550000101327896,
      "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": 49.0,
      "completions/max_terminated_length": 49.0,
      "completions/mean_length": 42.5,
      "completions/mean_terminated_length": 42.5,
      "completions/min_length": 38.5,
      "completions/min_terminated_length": 38.5,
      "epoch": 6.0,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 10.108943939208984,
      "kl": 0.011130992257676553,
      "learning_rate": 2.934120444167326e-07,
      "loss": 0.0088,
      "num_tokens": 4057.0,
      "reward": 0.5809410214424133,
      "reward_std": 0.005224586755502969,
      "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": 0.08094101399183273,
      "rewards/question_recreation_reward_func/std": 0.0538091630442068,
      "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": 0.5,
      "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": 70.5,
      "completions/max_terminated_length": 70.5,
      "completions/mean_length": 48.875,
      "completions/mean_terminated_length": 48.875,
      "completions/min_length": 37.0,
      "completions/min_terminated_length": 37.0,
      "epoch": 8.0,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 0.0004040227795485407,
      "kl": 0.017657065225648694,
      "learning_rate": 1.2500000000000005e-07,
      "loss": 0.0664,
      "num_tokens": 5472.0,
      "reward": 0.475370854139328,
      "reward_std": 0.0956975594162941,
      "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": 0.04062086530029774,
      "rewards/question_recreation_reward_func/std": 0.004772845219122246,
      "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": 0.4347499907016754,
      "rewards/xmlcount_reward_func/std": 0.13050000369548798,
      "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": 44.0,
      "completions/max_terminated_length": 44.0,
      "completions/mean_length": 41.0,
      "completions/mean_terminated_length": 41.0,
      "completions/min_length": 38.0,
      "completions/min_terminated_length": 38.0,
      "epoch": 10.0,
      "frac_reward_zero_std": 0.75,
      "grad_norm": 8.019640922546387,
      "kl": 0.001891768868517829,
      "learning_rate": 1.507684480352292e-08,
      "loss": 0.0,
      "num_tokens": 6824.0,
      "reward": 0.5831517577171326,
      "reward_std": 0.0021489623468369246,
      "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": 0.08315177075564861,
      "rewards/question_recreation_reward_func/std": 0.05820586674963124,
      "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": 0.5,
      "rewards/xmlcount_reward_func/std": 0.0,
      "step": 10
    },
    {
      "epoch": 10.0,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": 0.006285320222377777,
      "train_runtime": 1166.67,
      "train_samples_per_second": 0.034,
      "train_steps_per_second": 0.009
    }
  ],
  "logging_steps": 2,
  "max_steps": 10,
  "num_input_tokens_seen": 6824,
  "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
}