{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.46511627906976744,
  "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": 10.5,
      "completions/max_terminated_length": 10.5,
      "completions/mean_length": 7.25,
      "completions/mean_terminated_length": 7.25,
      "completions/min_length": 4.0,
      "completions/min_terminated_length": 4.0,
      "epoch": 0.09302325581395349,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "num_tokens": 1082.0,
      "reward": 1.631393849849701,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func/mean": 0.5,
      "rewards/concensus_correctness_reward_func/std": 0.5773502588272095,
      "rewards/consensus_reward_func/mean": 1.0,
      "rewards/consensus_reward_func/std": 1.154700517654419,
      "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": 0.13139405846595764,
      "rewards/question_recreation_reward_func/std": 0.052110755583271384,
      "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": 4.5,
      "completions/max_terminated_length": 4.5,
      "completions/mean_length": 4.25,
      "completions/mean_terminated_length": 4.25,
      "completions/min_length": 4.0,
      "completions/min_terminated_length": 4.0,
      "epoch": 0.18604651162790697,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 4.415111107797445e-07,
      "loss": 0.0,
      "num_tokens": 2140.0,
      "reward": 2.1135165691375732,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func/mean": 1.606000006198883,
      "rewards/concensus_correctness_reward_func/std": 1.8544490933418274,
      "rewards/consensus_reward_func/mean": 0.5,
      "rewards/consensus_reward_func/std": 0.5773502588272095,
      "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": 0.007516542566008866,
      "rewards/question_recreation_reward_func/std": 0.005180263542570174,
      "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": 23.5,
      "completions/max_terminated_length": 23.5,
      "completions/mean_length": 12.625,
      "completions/mean_terminated_length": 12.625,
      "completions/min_length": 3.0,
      "completions/min_terminated_length": 3.0,
      "epoch": 0.27906976744186046,
      "frac_reward_zero_std": 0.75,
      "grad_norm": 2.3283529770878886e-08,
      "kl": 0.0,
      "learning_rate": 2.934120444167326e-07,
      "loss": -0.0018,
      "num_tokens": 3265.0,
      "reward": 6.389079838991165,
      "reward_std": 0.008070557378232479,
      "rewards/concensus_correctness_reward_func/mean": 5.7769999504089355,
      "rewards/concensus_correctness_reward_func/std": 4.87630033493042,
      "rewards/consensus_reward_func/mean": 0.5,
      "rewards/consensus_reward_func/std": 0.5773502588272095,
      "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": 0.11207972513511777,
      "rewards/question_recreation_reward_func/std": 0.10706877056509256,
      "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": 4.5,
      "completions/max_terminated_length": 4.5,
      "completions/mean_length": 3.75,
      "completions/mean_terminated_length": 3.75,
      "completions/min_length": 3.0,
      "completions/min_terminated_length": 3.0,
      "epoch": 0.37209302325581395,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 3.3889150472532492e-06,
      "kl": 3.973643103449831e-08,
      "learning_rate": 1.2500000000000005e-07,
      "loss": 0.0,
      "num_tokens": 4319.0,
      "reward": 7.009408354759216,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func/mean": 5.938499987125397,
      "rewards/concensus_correctness_reward_func/std": 6.857189297676086,
      "rewards/consensus_reward_func/mean": 1.0,
      "rewards/consensus_reward_func/std": 1.154700517654419,
      "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": 0.07090835273265839,
      "rewards/question_recreation_reward_func/std": 0.00839561433531344,
      "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": 4.0,
      "completions/max_terminated_length": 4.0,
      "completions/mean_length": 4.0,
      "completions/mean_terminated_length": 4.0,
      "completions/min_length": 4.0,
      "completions/min_terminated_length": 4.0,
      "epoch": 0.46511627906976744,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 1.0900829465754214e-06,
      "kl": 1.4901161193847656e-08,
      "learning_rate": 1.507684480352292e-08,
      "loss": 0.0,
      "num_tokens": 5375.0,
      "reward": 3.7195547819137573,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func/mean": 2.1849999725818634,
      "rewards/concensus_correctness_reward_func/std": 0.5531015396118164,
      "rewards/consensus_reward_func/mean": 1.5,
      "rewards/consensus_reward_func/std": 0.5773502588272095,
      "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": 0.034554850310087204,
      "rewards/question_recreation_reward_func/std": 0.0,
      "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": 0.46511627906976744,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": -0.00035705565313498176,
      "train_runtime": 684.4145,
      "train_samples_per_second": 0.058,
      "train_steps_per_second": 0.015
    }
  ],
  "logging_steps": 2,
  "max_steps": 10,
  "num_input_tokens_seen": 5375,
  "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
}