{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5,
  "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": 58.0,
      "completions/max_terminated_length": 58.0,
      "completions/mean_length": 38.375,
      "completions/mean_terminated_length": 38.375,
      "completions/min_length": 19.0,
      "completions/min_terminated_length": 19.0,
      "epoch": 0.1,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 31.189651489257812,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.0934,
      "num_tokens": 1331.0,
      "reward": 0.02184452023357153,
      "reward_std": 0.002218609442934394,
      "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": 0.021844521164894104,
      "rewards/question_recreation_reward_func/std": 0.00534467922989279,
      "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": 85.0,
      "completions/max_terminated_length": 85.0,
      "completions/mean_length": 41.75,
      "completions/mean_terminated_length": 41.75,
      "completions/min_length": 18.5,
      "completions/min_terminated_length": 18.5,
      "epoch": 0.2,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 32.58302688598633,
      "kl": 0.0030914566305000335,
      "learning_rate": 4.415111107797445e-07,
      "loss": 0.0511,
      "num_tokens": 2689.0,
      "reward": 0.03553825430572033,
      "reward_std": 0.008368940558284521,
      "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": 0.03553825430572033,
      "rewards/question_recreation_reward_func/std": 0.013820798601955175,
      "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": 35.5,
      "completions/max_terminated_length": 35.5,
      "completions/mean_length": 24.25,
      "completions/mean_terminated_length": 24.25,
      "completions/min_length": 16.0,
      "completions/min_terminated_length": 16.0,
      "epoch": 0.3,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 64.95323181152344,
      "kl": 0.012648301431909204,
      "learning_rate": 2.934120444167326e-07,
      "loss": -0.0003,
      "num_tokens": 3907.0,
      "reward": 0.04497586004436016,
      "reward_std": 0.018905424512922764,
      "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": 0.04497585818171501,
      "rewards/question_recreation_reward_func/std": 0.029728572815656662,
      "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": 40.0,
      "completions/max_terminated_length": 40.0,
      "completions/mean_length": 26.0,
      "completions/mean_terminated_length": 26.0,
      "completions/min_length": 16.0,
      "completions/min_terminated_length": 16.0,
      "epoch": 0.4,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 36.765655517578125,
      "kl": 0.026515229372307658,
      "learning_rate": 1.2500000000000005e-07,
      "loss": 0.0002,
      "num_tokens": 5139.0,
      "reward": 0.14473969209939241,
      "reward_std": 0.03182663442566991,
      "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": 0.1447396925650537,
      "rewards/question_recreation_reward_func/std": 0.037010627798736095,
      "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": 0.125,
      "completions/max_length": 148.5,
      "completions/max_terminated_length": 37.0,
      "completions/mean_length": 57.25,
      "completions/mean_terminated_length": 28.666666984558105,
      "completions/min_length": 23.5,
      "completions/min_terminated_length": 23.5,
      "epoch": 0.5,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 29.147811889648438,
      "kl": 0.026031473884359002,
      "learning_rate": 1.507684480352292e-08,
      "loss": -0.0001,
      "num_tokens": 6621.0,
      "reward": 0.12972894310951233,
      "reward_std": 0.053943948820233345,
      "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": 0.12972894310951233,
      "rewards/question_recreation_reward_func/std": 0.06683044042438269,
      "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": 0.5,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": 0.028863224387168884,
      "train_runtime": 851.9902,
      "train_samples_per_second": 0.047,
      "train_steps_per_second": 0.012
    }
  ],
  "logging_steps": 2,
  "max_steps": 10,
  "num_input_tokens_seen": 6621,
  "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
}