{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4166666666666667,
  "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": 105.0,
      "completions/max_terminated_length": 105.0,
      "completions/mean_length": 79.25,
      "completions/mean_terminated_length": 79.25,
      "completions/min_length": 61.0,
      "completions/min_terminated_length": 61.0,
      "epoch": 0.041666666666666664,
      "grad_norm": 19.425622940063477,
      "kl": 0.0,
      "learning_rate": 0.0,
      "loss": -0.0238,
      "num_tokens": 829.0,
      "reward": 0.033818572759628296,
      "reward_std": 0.014064152725040913,
      "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": 0.033818572759628296,
      "rewards/question_recreation_reward_func/std": 0.015592413954436779,
      "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": 1
    },
    {
      "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": 157.0,
      "completions/max_terminated_length": 157.0,
      "completions/mean_length": 62.0,
      "completions/mean_terminated_length": 62.0,
      "completions/min_length": 11.0,
      "completions/min_terminated_length": 11.0,
      "epoch": 0.08333333333333333,
      "grad_norm": 10.577459335327148,
      "kl": 0.0,
      "learning_rate": 1e-06,
      "loss": 0.1346,
      "num_tokens": 1589.0,
      "reward": 0.02579352632164955,
      "reward_std": 0.0022206564899533987,
      "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": 0.03729352727532387,
      "rewards/question_recreation_reward_func/std": 0.02176251821219921,
      "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": -0.011500000022351742,
      "rewards/xmlcount_reward_func/std": 0.023000000044703484,
      "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": 60.0,
      "completions/max_terminated_length": 60.0,
      "completions/mean_length": 37.75,
      "completions/mean_terminated_length": 37.75,
      "completions/min_length": 17.0,
      "completions/min_terminated_length": 17.0,
      "epoch": 0.125,
      "grad_norm": 63.17714309692383,
      "kl": 0.022556406212970614,
      "learning_rate": 9.698463103929541e-07,
      "loss": -0.0353,
      "num_tokens": 2252.0,
      "reward": 0.0233759805560112,
      "reward_std": 0.0036189700476825237,
      "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": 0.02337597869336605,
      "rewards/question_recreation_reward_func/std": 0.006528852041810751,
      "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": 3
    },
    {
      "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": 23.75,
      "completions/mean_terminated_length": 23.75,
      "completions/min_length": 6.0,
      "completions/min_terminated_length": 6.0,
      "epoch": 0.16666666666666666,
      "grad_norm": 78.41133117675781,
      "kl": 0.004607599810697138,
      "learning_rate": 8.83022221559489e-07,
      "loss": -0.0235,
      "num_tokens": 2859.0,
      "reward": 0.120003342628479,
      "reward_std": 0.01657889410853386,
      "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": 0.0575033500790596,
      "rewards/question_recreation_reward_func/std": 0.04737204685807228,
      "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": 0.0625,
      "rewards/xmlcount_reward_func/std": 0.07216878235340118,
      "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": 98.0,
      "completions/max_terminated_length": 98.0,
      "completions/mean_length": 62.25,
      "completions/mean_terminated_length": 62.25,
      "completions/min_length": 42.0,
      "completions/min_terminated_length": 42.0,
      "epoch": 0.20833333333333334,
      "grad_norm": 27.737390518188477,
      "kl": 0.0020544964354485273,
      "learning_rate": 7.5e-07,
      "loss": 0.1576,
      "num_tokens": 3620.0,
      "reward": 0.22436219453811646,
      "reward_std": 0.2421010583639145,
      "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": 0.042862214148044586,
      "rewards/question_recreation_reward_func/std": 0.01811356097459793,
      "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": 0.18150000274181366,
      "rewards/xmlcount_reward_func/std": 0.2375619113445282,
      "step": 5
    },
    {
      "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": 66.0,
      "completions/max_terminated_length": 66.0,
      "completions/mean_length": 53.75,
      "completions/mean_terminated_length": 53.75,
      "completions/min_length": 38.0,
      "completions/min_terminated_length": 38.0,
      "epoch": 0.25,
      "grad_norm": 30.05788230895996,
      "kl": 0.11974160745739937,
      "learning_rate": 5.868240888334652e-07,
      "loss": -0.1373,
      "num_tokens": 4347.0,
      "reward": 0.06295251846313477,
      "reward_std": 0.04794733226299286,
      "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": 0.031702518463134766,
      "rewards/question_recreation_reward_func/std": 0.010227867402136326,
      "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": 0.03125,
      "rewards/xmlcount_reward_func/std": 0.0625,
      "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": 0.25,
      "completions/max_length": 448.0,
      "completions/max_terminated_length": 435.0,
      "completions/mean_length": 243.5,
      "completions/mean_terminated_length": 175.3333282470703,
      "completions/min_length": 17.0,
      "completions/min_terminated_length": 17.0,
      "epoch": 0.2916666666666667,
      "grad_norm": 6.3190836906433105,
      "kl": 0.013644359540194273,
      "learning_rate": 4.131759111665348e-07,
      "loss": 0.5802,
      "num_tokens": 5833.0,
      "reward": 0.1428598016500473,
      "reward_std": 0.15640608966350555,
      "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": 0.0803598091006279,
      "rewards/question_recreation_reward_func/std": 0.06639377772808075,
      "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": 0.0625,
      "rewards/xmlcount_reward_func/std": 0.125,
      "step": 7
    },
    {
      "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": 72.0,
      "completions/max_terminated_length": 72.0,
      "completions/mean_length": 31.75,
      "completions/mean_terminated_length": 31.75,
      "completions/min_length": 6.0,
      "completions/min_terminated_length": 6.0,
      "epoch": 0.3333333333333333,
      "grad_norm": 69.37403106689453,
      "kl": 0.660507733002305,
      "learning_rate": 2.500000000000001e-07,
      "loss": -0.0009,
      "num_tokens": 6472.0,
      "reward": 0.08257974684238434,
      "reward_std": 0.10520116984844208,
      "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": 0.024079740047454834,
      "rewards/question_recreation_reward_func/std": 0.0149986008182168,
      "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": 0.05849999934434891,
      "rewards/xmlcount_reward_func/std": 0.13300000131130219,
      "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": 0.25,
      "completions/max_length": 448.0,
      "completions/max_terminated_length": 345.0,
      "completions/mean_length": 230.5,
      "completions/mean_terminated_length": 158.0,
      "completions/min_length": 56.0,
      "completions/min_terminated_length": 56.0,
      "epoch": 0.375,
      "grad_norm": 8.065352439880371,
      "kl": 0.008895490551367402,
      "learning_rate": 1.1697777844051104e-07,
      "loss": 0.5052,
      "num_tokens": 7906.0,
      "reward": -0.4270660877227783,
      "reward_std": 0.9292497038841248,
      "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": 0.16618388891220093,
      "rewards/question_recreation_reward_func/std": 0.13774648308753967,
      "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": -0.5932499766349792,
      "rewards/xmlcount_reward_func/std": 1.2711997032165527,
      "step": 9
    },
    {
      "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": 84.0,
      "completions/max_terminated_length": 84.0,
      "completions/mean_length": 37.0,
      "completions/mean_terminated_length": 37.0,
      "completions/min_length": 5.0,
      "completions/min_terminated_length": 5.0,
      "epoch": 0.4166666666666667,
      "grad_norm": 71.09834289550781,
      "kl": 0.057335725985467434,
      "learning_rate": 3.015368960704584e-08,
      "loss": 0.0504,
      "num_tokens": 8566.0,
      "reward": 0.14473699033260345,
      "reward_std": 0.09234187006950378,
      "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": 0.019736986607313156,
      "rewards/question_recreation_reward_func/std": 0.008162936195731163,
      "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": 0.125,
      "rewards/xmlcount_reward_func/std": 0.10206207633018494,
      "step": 10
    },
    {
      "epoch": 0.4166666666666667,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": 0.12070619501173496,
      "train_runtime": 3637.1703,
      "train_samples_per_second": 0.011,
      "train_steps_per_second": 0.003
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 8566,
  "num_train_epochs": 1,
  "save_steps": 25,
  "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
}