{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9620253164556962,
  "eval_steps": 500,
  "global_step": 19,
  "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": 0.125,
      "completions/max_length": 931.0,
      "completions/max_terminated_length": 819.5,
      "completions/mean_length": 412.1875,
      "completions/mean_terminated_length": 329.5833435058594,
      "completions/min_length": 87.0,
      "completions/min_terminated_length": 87.0,
      "epoch": 0.10126582278481013,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 5.04105806350708,
      "kl": -5.448857809398078e-09,
      "learning_rate": 5e-07,
      "loss": 0.1398,
      "num_tokens": 10691.0,
      "reward": 0.01983704511076212,
      "reward_std": 0.008039223263040185,
      "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": 0.01983704511076212,
      "rewards/question_recreation_reward_func/std": 0.012273336760699749,
      "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": 0.125,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 569.0,
      "completions/mean_length": 401.1875,
      "completions/mean_terminated_length": 312.21429443359375,
      "completions/min_length": 53.5,
      "completions/min_terminated_length": 53.5,
      "epoch": 0.20253164556962025,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 3.7304916381835938,
      "kl": 0.0002279730260852375,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.1637,
      "num_tokens": 21206.0,
      "reward": -0.1395124290138483,
      "reward_std": 0.21926994435489178,
      "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": 0.010925075970590115,
      "rewards/question_recreation_reward_func/std": 0.009428349556401372,
      "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": -0.15043750405311584,
      "rewards/xmlcount_reward_func/std": 0.4255015254020691,
      "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": 0.125,
      "completions/max_length": 887.0,
      "completions/max_terminated_length": 672.5,
      "completions/mean_length": 362.0,
      "completions/mean_terminated_length": 257.3125,
      "completions/min_length": 12.5,
      "completions/min_terminated_length": 12.5,
      "epoch": 0.3037974683544304,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 7.230990886688232,
      "kl": 0.0008080850275291596,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.2574,
      "num_tokens": 31094.0,
      "reward": 0.022412247024476528,
      "reward_std": 0.011643366422504187,
      "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": 0.022412247024476528,
      "rewards/question_recreation_reward_func/std": 0.01874966360628605,
      "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": 0.1875,
      "completions/max_length": 862.5,
      "completions/max_terminated_length": 702.5,
      "completions/mean_length": 461.6875,
      "completions/mean_terminated_length": 357.3249969482422,
      "completions/min_length": 67.0,
      "completions/min_terminated_length": 67.0,
      "epoch": 0.4050632911392405,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 3.539825677871704,
      "kl": 0.0011349972373864148,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.2018,
      "num_tokens": 42577.0,
      "reward": 0.10562402009963989,
      "reward_std": 0.061309706419706345,
      "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": 0.10562402009963989,
      "rewards/question_recreation_reward_func/std": 0.05985743924975395,
      "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": 0.0625,
      "completions/max_length": 664.0,
      "completions/max_terminated_length": 436.5,
      "completions/mean_length": 222.4375,
      "completions/mean_terminated_length": 173.0357208251953,
      "completions/min_length": 4.5,
      "completions/min_terminated_length": 4.5,
      "epoch": 0.5063291139240507,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 13.28281021118164,
      "kl": 0.0055584801666554995,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0764,
      "num_tokens": 50232.0,
      "reward": 0.05675883777439594,
      "reward_std": 0.017147527541965246,
      "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": 0.05675883777439594,
      "rewards/question_recreation_reward_func/std": 0.02832796238362789,
      "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
    },
    {
      "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": 681.5,
      "completions/max_terminated_length": 319.0,
      "completions/mean_length": 298.25,
      "completions/mean_terminated_length": 195.8541717529297,
      "completions/min_length": 73.5,
      "completions/min_terminated_length": 73.5,
      "epoch": 0.6075949367088608,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 8.755450248718262,
      "kl": 0.0035302894830238074,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.2667,
      "num_tokens": 59100.0,
      "reward": 0.015352241694927216,
      "reward_std": 0.0057732411660254,
      "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": 0.015352241694927216,
      "rewards/question_recreation_reward_func/std": 0.006488756742328405,
      "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": 12
    },
    {
      "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": 991.0,
      "completions/max_terminated_length": 756.5,
      "completions/mean_length": 509.4375,
      "completions/mean_terminated_length": 421.9583435058594,
      "completions/min_length": 36.5,
      "completions/min_terminated_length": 36.5,
      "epoch": 0.7088607594936709,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 4.25427770614624,
      "kl": 0.001760676721460186,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.2682,
      "num_tokens": 71347.0,
      "reward": -0.05695461109280586,
      "reward_std": 0.22896763868629932,
      "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": 0.05810788832604885,
      "rewards/question_recreation_reward_func/std": 0.04673689045011997,
      "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": -0.11506249755620956,
      "rewards/xmlcount_reward_func/std": 0.3688294589519501,
      "step": 14
    },
    {
      "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": 214.0,
      "completions/max_terminated_length": 214.0,
      "completions/mean_length": 103.6875,
      "completions/mean_terminated_length": 103.6875,
      "completions/min_length": 5.0,
      "completions/min_terminated_length": 5.0,
      "epoch": 0.810126582278481,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 12.23747444152832,
      "kl": 0.007723030605120584,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0009,
      "num_tokens": 77102.0,
      "reward": 0.17531824856996536,
      "reward_std": 0.03592286352068186,
      "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": 0.17531824856996536,
      "rewards/question_recreation_reward_func/std": 0.045727355405688286,
      "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": 16
    },
    {
      "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": 0.0625,
      "completions/max_length": 824.0,
      "completions/max_terminated_length": 530.5,
      "completions/mean_length": 194.3125,
      "completions/mean_terminated_length": 137.34821701049805,
      "completions/min_length": 3.5,
      "completions/min_terminated_length": 3.5,
      "epoch": 0.9113924050632911,
      "frac_reward_zero_std": 0.125,
      "grad_norm": 9.846582412719727,
      "kl": 0.006351641248329543,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0552,
      "num_tokens": 84307.0,
      "reward": 0.13931425474584103,
      "reward_std": 0.058048633858561516,
      "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": 0.13931425474584103,
      "rewards/question_recreation_reward_func/std": 0.15117722004652023,
      "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": 18
    },
    {
      "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": 0.5,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 565.0,
      "completions/mean_length": 665.25,
      "completions/mean_terminated_length": 306.5,
      "completions/min_length": 5.0,
      "completions/min_terminated_length": 5.0,
      "epoch": 0.9620253164556962,
      "frac_reward_zero_std": 0.0,
      "kl": 0.002655731455888599,
      "num_tokens": 91677.0,
      "reward": 0.012782756239175797,
      "reward_std": 0.005160772241652012,
      "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": 0.012782756239175797,
      "rewards/question_recreation_reward_func/std": 0.008415077812969685,
      "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": 19,
      "total_flos": 0.0,
      "train_loss": 0.15644574165344238,
      "train_runtime": 1523.8731,
      "train_samples_per_second": 0.105,
      "train_steps_per_second": 0.013
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 91677,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}