{
  "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": 17.0,
      "completions/max_terminated_length": 17.0,
      "completions/mean_length": 17.0,
      "completions/mean_terminated_length": 17.0,
      "completions/min_length": 17.0,
      "completions/min_terminated_length": 17.0,
      "epoch": 2.0,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "num_tokens": 1160.0,
      "reward": 1.4721624851226807,
      "reward_std": 0.0,
      "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": 1.0,
      "rewards/final_correctness_reward_func/std": 1.154700517654419,
      "rewards/question_recreation_reward_func/mean": 0.010162601247429848,
      "rewards/question_recreation_reward_func/std": 0.0014081713743507862,
      "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": 0.4620000123977661,
      "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": 17.0,
      "completions/max_terminated_length": 17.0,
      "completions/mean_length": 17.0,
      "completions/mean_terminated_length": 17.0,
      "completions/min_length": 17.0,
      "completions/min_terminated_length": 17.0,
      "epoch": 4.0,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 4.415111107797445e-07,
      "loss": 0.0,
      "num_tokens": 2320.0,
      "reward": 1.4741950035095215,
      "reward_std": 0.0,
      "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": 1.0,
      "rewards/final_correctness_reward_func/std": 1.154700517654419,
      "rewards/question_recreation_reward_func/mean": 0.012195121496915817,
      "rewards/question_recreation_reward_func/std": 0.0028163427487015724,
      "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": 0.4620000123977661,
      "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": 17.0,
      "completions/max_terminated_length": 17.0,
      "completions/mean_length": 17.0,
      "completions/mean_terminated_length": 17.0,
      "completions/min_length": 17.0,
      "completions/min_terminated_length": 17.0,
      "epoch": 6.0,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 2.934120444167326e-07,
      "loss": 0.0,
      "num_tokens": 3480.0,
      "reward": 1.4721624851226807,
      "reward_std": 0.0,
      "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": 1.0,
      "rewards/final_correctness_reward_func/std": 1.154700517654419,
      "rewards/question_recreation_reward_func/mean": 0.010162601247429848,
      "rewards/question_recreation_reward_func/std": 0.0014081713743507862,
      "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": 0.4620000123977661,
      "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": 17.0,
      "completions/max_terminated_length": 17.0,
      "completions/mean_length": 17.0,
      "completions/mean_terminated_length": 17.0,
      "completions/min_length": 17.0,
      "completions/min_terminated_length": 17.0,
      "epoch": 8.0,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 1.2500000000000005e-07,
      "loss": 0.0,
      "num_tokens": 4640.0,
      "reward": 1.4741950035095215,
      "reward_std": 0.0,
      "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": 1.0,
      "rewards/final_correctness_reward_func/std": 1.154700517654419,
      "rewards/question_recreation_reward_func/mean": 0.012195121496915817,
      "rewards/question_recreation_reward_func/std": 0.0028163427487015724,
      "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": 0.4620000123977661,
      "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": 17.0,
      "completions/max_terminated_length": 17.0,
      "completions/mean_length": 17.0,
      "completions/mean_terminated_length": 17.0,
      "completions/min_length": 17.0,
      "completions/min_terminated_length": 17.0,
      "epoch": 10.0,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 1.507684480352292e-08,
      "loss": 0.0,
      "num_tokens": 5800.0,
      "reward": 1.4721624851226807,
      "reward_std": 0.0,
      "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": 1.0,
      "rewards/final_correctness_reward_func/std": 1.154700517654419,
      "rewards/question_recreation_reward_func/mean": 0.010162601247429848,
      "rewards/question_recreation_reward_func/std": 0.0014081713743507862,
      "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": 0.4620000123977661,
      "rewards/xmlcount_reward_func/std": 0.0,
      "step": 10
    },
    {
      "epoch": 10.0,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": 0.0,
      "train_runtime": 482.1804,
      "train_samples_per_second": 0.083,
      "train_steps_per_second": 0.021
    }
  ],
  "logging_steps": 2,
  "max_steps": 10,
  "num_input_tokens_seen": 5800,
  "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
}