{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7843137254901961,
  "eval_steps": 500,
  "global_step": 20,
  "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": 0.0625,
      "completions/max_length": 667.5,
      "completions/max_terminated_length": 452.0,
      "completions/mean_length": 222.4375,
      "completions/mean_terminated_length": 172.5089340209961,
      "completions/min_length": 15.5,
      "completions/min_terminated_length": 15.5,
      "epoch": 0.0784313725490196,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 10.582316398620605,
      "kl": -4.784070639640703e-09,
      "learning_rate": 5e-07,
      "loss": -0.118,
      "num_tokens": 7655.0,
      "reward": 0.08023529499769211,
      "reward_std": 0.023692099610343575,
      "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": 0.08023529499769211,
      "rewards/question_recreation_reward_func/std": 0.024613698944449425,
      "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": 984.5,
      "completions/max_terminated_length": 886.5,
      "completions/mean_length": 432.9375,
      "completions/mean_terminated_length": 351.4375,
      "completions/min_length": 74.5,
      "completions/min_terminated_length": 74.5,
      "epoch": 0.1568627450980392,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 6.236111164093018,
      "kl": 0.00019753339893213706,
      "learning_rate": 4.864543104251586e-07,
      "loss": -0.137,
      "num_tokens": 18678.0,
      "reward": -0.0831574909389019,
      "reward_std": 0.14662296720780432,
      "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": 0.016717517748475075,
      "rewards/question_recreation_reward_func/std": 0.008825697470456362,
      "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": -0.09987500309944153,
      "rewards/xmlcount_reward_func/std": 0.28248918056488037,
      "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": 0.0625,
      "completions/max_length": 862.5,
      "completions/max_terminated_length": 620.5,
      "completions/mean_length": 274.75,
      "completions/mean_terminated_length": 224.85714721679688,
      "completions/min_length": 32.5,
      "completions/min_terminated_length": 32.5,
      "epoch": 0.23529411764705882,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 8.984740257263184,
      "kl": 0.0007774862242513336,
      "learning_rate": 4.472851273490984e-07,
      "loss": -0.0403,
      "num_tokens": 27170.0,
      "reward": 0.10502731800079346,
      "reward_std": 0.03363147936761379,
      "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": 0.10502731800079346,
      "rewards/question_recreation_reward_func/std": 0.05110013298690319,
      "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": 0.125,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 631.0,
      "completions/mean_length": 316.5,
      "completions/mean_terminated_length": 215.4285888671875,
      "completions/min_length": 24.5,
      "completions/min_terminated_length": 24.5,
      "epoch": 0.3137254901960784,
      "frac_reward_zero_std": 0.125,
      "grad_norm": 20.830415725708008,
      "kl": 0.001665158382820664,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.1506,
      "num_tokens": 36330.0,
      "reward": 0.3101906329393387,
      "reward_std": 0.030688787577673793,
      "rewards/concensus_correctness_reward_func/mean": 0.0,
      "rewards/concensus_correctness_reward_func/std": 0.0,
      "rewards/consensus_reward_func/mean": 0.25,
      "rewards/consensus_reward_func/std": 0.4629100561141968,
      "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": 0.0601906543597579,
      "rewards/question_recreation_reward_func/std": 0.03427481045946479,
      "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": 883.0,
      "completions/max_terminated_length": 883.0,
      "completions/mean_length": 373.75,
      "completions/mean_terminated_length": 373.75,
      "completions/min_length": 42.0,
      "completions/min_terminated_length": 42.0,
      "epoch": 0.39215686274509803,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 4.482949733734131,
      "kl": 0.001862530603830237,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0358,
      "num_tokens": 46406.0,
      "reward": 0.04348368709906936,
      "reward_std": 0.021108464570716023,
      "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": 0.04348368709906936,
      "rewards/question_recreation_reward_func/std": 0.03131787059828639,
      "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": 0.1875,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 640.0,
      "completions/mean_length": 482.625,
      "completions/mean_terminated_length": 374.16668701171875,
      "completions/min_length": 82.5,
      "completions/min_terminated_length": 82.5,
      "epoch": 0.47058823529411764,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 8.272782325744629,
      "kl": 0.0026207715563941747,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0546,
      "num_tokens": 58224.0,
      "reward": 0.05969332344830036,
      "reward_std": 0.03567563369870186,
      "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": 0.04563082382082939,
      "rewards/question_recreation_reward_func/std": 0.03295238898135722,
      "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": 0.014062500093132257,
      "rewards/xmlcount_reward_func/std": 0.039774756878614426,
      "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": 0.1875,
      "completions/max_length": 677.0,
      "completions/max_terminated_length": 376.0,
      "completions/mean_length": 308.0,
      "completions/mean_terminated_length": 156.76250457763672,
      "completions/min_length": 64.0,
      "completions/min_terminated_length": 64.0,
      "epoch": 0.5490196078431373,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 14.544376373291016,
      "kl": 0.0033570137748029083,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.009,
      "num_tokens": 67248.0,
      "reward": 0.01620261650532484,
      "reward_std": 0.0063501952681690454,
      "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": 0.01620261650532484,
      "rewards/question_recreation_reward_func/std": 0.007352772634476423,
      "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": 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": 0.0625,
      "completions/max_length": 931.0,
      "completions/max_terminated_length": 800.5,
      "completions/mean_length": 343.6875,
      "completions/mean_terminated_length": 290.5982208251953,
      "completions/min_length": 30.5,
      "completions/min_terminated_length": 30.5,
      "epoch": 0.6274509803921569,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 8.895730018615723,
      "kl": 0.0031596484768670052,
      "learning_rate": 8.067960709356478e-08,
      "loss": -0.0141,
      "num_tokens": 76843.0,
      "reward": 0.07652556523680687,
      "reward_std": 0.02881058305501938,
      "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": 0.07652556523680687,
      "rewards/question_recreation_reward_func/std": 0.05606217496097088,
      "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": 0.125,
      "completions/max_length": 942.0,
      "completions/max_terminated_length": 656.5,
      "completions/mean_length": 427.3125,
      "completions/mean_terminated_length": 314.9791679382324,
      "completions/min_length": 89.0,
      "completions/min_terminated_length": 89.0,
      "epoch": 0.7058823529411765,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 4.773468494415283,
      "kl": 0.004317194048780948,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.1024,
      "num_tokens": 87776.0,
      "reward": 0.06278230529278517,
      "reward_std": 0.014868666417896748,
      "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": 0.06278230529278517,
      "rewards/question_recreation_reward_func/std": 0.038148720283061266,
      "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": 0.0,
      "completions/max_length": 574.5,
      "completions/max_terminated_length": 574.5,
      "completions/mean_length": 288.0625,
      "completions/mean_terminated_length": 288.0625,
      "completions/min_length": 45.5,
      "completions/min_terminated_length": 45.5,
      "epoch": 0.7843137254901961,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 6.394106864929199,
      "kl": 0.002251003446872346,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.1453,
      "num_tokens": 96481.0,
      "reward": 0.08274493180215359,
      "reward_std": 0.06434697424992919,
      "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": 0.07486993633210659,
      "rewards/question_recreation_reward_func/std": 0.05120457522571087,
      "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": 0.00787500012665987,
      "rewards/xmlcount_reward_func/std": 0.022273864597082138,
      "step": 20
    },
    {
      "epoch": 0.7843137254901961,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 0.018828855734318493,
      "train_runtime": 1548.9658,
      "train_samples_per_second": 0.103,
      "train_steps_per_second": 0.013
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 96481,
  "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
}