{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.9411764705882355,
  "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": 628.0,
      "completions/max_terminated_length": 293.0,
      "completions/mean_length": 176.4375,
      "completions/mean_terminated_length": 123.19642639160156,
      "completions/min_length": 8.0,
      "completions/min_terminated_length": 8.0,
      "epoch": 0.47058823529411764,
      "grad_norm": 51.56406784057617,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.3766,
      "num_tokens": 6919.0,
      "reward": 0.3104562256485224,
      "reward_std": 0.32131396047770977,
      "rewards/concensus_correctness_reward_func/mean": 0.03125,
      "rewards/concensus_correctness_reward_func/std": 0.0883883461356163,
      "rewards/consensus_reward_func/mean": 0.25,
      "rewards/consensus_reward_func/std": 0.46291008591651917,
      "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": 0.02920621819794178,
      "rewards/question_recreation_reward_func/std": 0.023029986768960953,
      "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": 419.5,
      "completions/max_terminated_length": 419.5,
      "completions/mean_length": 305.375,
      "completions/mean_terminated_length": 305.375,
      "completions/min_length": 193.5,
      "completions/min_terminated_length": 193.5,
      "epoch": 0.9411764705882353,
      "grad_norm": 11.458623886108398,
      "kl": 0.0007662410207558423,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0561,
      "num_tokens": 14324.0,
      "reward": 0.023023009300231934,
      "reward_std": 0.01096764812245965,
      "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": 0.023023009300231934,
      "rewards/question_recreation_reward_func/std": 0.015222020447254181,
      "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": 367.0,
      "completions/max_terminated_length": 367.0,
      "completions/mean_length": 114.125,
      "completions/mean_terminated_length": 114.125,
      "completions/min_length": 8.0,
      "completions/min_terminated_length": 8.0,
      "epoch": 1.4705882352941178,
      "grad_norm": 44.851749420166016,
      "kl": 0.0016121815278893337,
      "learning_rate": 4.472851273490984e-07,
      "loss": -0.0794,
      "num_tokens": 20246.0,
      "reward": 0.17371663451194763,
      "reward_std": 0.0570271871984005,
      "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": 0.17371663451194763,
      "rewards/question_recreation_reward_func/std": 0.06652013398706913,
      "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": 305.0,
      "completions/max_terminated_length": 305.0,
      "completions/mean_length": 152.5625,
      "completions/mean_terminated_length": 152.5625,
      "completions/min_length": 42.0,
      "completions/min_terminated_length": 42.0,
      "epoch": 1.9411764705882353,
      "grad_norm": 9.940235137939453,
      "kl": 0.000744940982258413,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0534,
      "num_tokens": 27557.0,
      "reward": 0.02366686426103115,
      "reward_std": 0.008607423398643732,
      "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": 0.023666863329708576,
      "rewards/question_recreation_reward_func/std": 0.017653593327850103,
      "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": 509.0,
      "completions/max_terminated_length": 509.0,
      "completions/mean_length": 250.5,
      "completions/mean_terminated_length": 250.5,
      "completions/min_length": 64.5,
      "completions/min_terminated_length": 64.5,
      "epoch": 2.4705882352941178,
      "grad_norm": 5.178226470947266,
      "kl": 0.0007074162567732856,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.199,
      "num_tokens": 35661.0,
      "reward": 0.08728898875415325,
      "reward_std": 0.025852903723716736,
      "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": 0.08728898782283068,
      "rewards/question_recreation_reward_func/std": 0.03699528565630317,
      "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": 0.0,
      "completions/max_length": 304.5,
      "completions/max_terminated_length": 304.5,
      "completions/mean_length": 166.875,
      "completions/mean_terminated_length": 166.875,
      "completions/min_length": 82.5,
      "completions/min_terminated_length": 82.5,
      "epoch": 2.9411764705882355,
      "grad_norm": 9.689749717712402,
      "kl": 0.0008264059497378184,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.2115,
      "num_tokens": 42270.0,
      "reward": 0.20029596518725157,
      "reward_std": 0.19888783944770694,
      "rewards/concensus_correctness_reward_func/mean": 0.0,
      "rewards/concensus_correctness_reward_func/std": 0.0,
      "rewards/consensus_reward_func/mean": 0.125,
      "rewards/consensus_reward_func/std": 0.3535533845424652,
      "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": 0.07529596518725157,
      "rewards/question_recreation_reward_func/std": 0.03689309814944863,
      "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": 0.0,
      "completions/max_length": 426.5,
      "completions/max_terminated_length": 426.5,
      "completions/mean_length": 159.5,
      "completions/mean_terminated_length": 159.5,
      "completions/min_length": 2.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 3.4705882352941178,
      "grad_norm": 8.103471755981445,
      "kl": 0.0017809901619330049,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0366,
      "num_tokens": 48918.0,
      "reward": 0.01776011288166046,
      "reward_std": 0.006043280474841595,
      "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": 0.01776011334732175,
      "rewards/question_recreation_reward_func/std": 0.017151668202131987,
      "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": 0.0,
      "completions/max_length": 217.5,
      "completions/max_terminated_length": 217.5,
      "completions/mean_length": 112.6875,
      "completions/mean_terminated_length": 112.6875,
      "completions/min_length": 52.5,
      "completions/min_terminated_length": 52.5,
      "epoch": 3.9411764705882355,
      "grad_norm": 8.5344877243042,
      "kl": 0.0009168514661723748,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.2618,
      "num_tokens": 55559.0,
      "reward": 0.14910611137747765,
      "reward_std": 0.18657799949869514,
      "rewards/concensus_correctness_reward_func/mean": 0.0,
      "rewards/concensus_correctness_reward_func/std": 0.0,
      "rewards/consensus_reward_func/mean": 0.125,
      "rewards/consensus_reward_func/std": 0.3535533845424652,
      "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": 0.02410610392689705,
      "rewards/question_recreation_reward_func/std": 0.02181409765034914,
      "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": 0.0,
      "completions/max_length": 281.5,
      "completions/max_terminated_length": 281.5,
      "completions/mean_length": 118.0,
      "completions/mean_terminated_length": 118.0,
      "completions/min_length": 18.5,
      "completions/min_terminated_length": 18.5,
      "epoch": 4.470588235294118,
      "grad_norm": 19.964595794677734,
      "kl": 0.0011214540027140174,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.2282,
      "num_tokens": 61543.0,
      "reward": 0.32675740122795105,
      "reward_std": 0.044070890406146646,
      "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": 0.46291008591651917,
      "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": 0.07675742218270898,
      "rewards/question_recreation_reward_func/std": 0.03963730251416564,
      "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": 221.0,
      "completions/max_terminated_length": 221.0,
      "completions/mean_length": 119.3125,
      "completions/mean_terminated_length": 119.3125,
      "completions/min_length": 62.5,
      "completions/min_terminated_length": 62.5,
      "epoch": 4.9411764705882355,
      "grad_norm": 14.930213928222656,
      "kl": 0.0009697647255961783,
      "learning_rate": 3.4096741493194193e-09,
      "loss": -0.0206,
      "num_tokens": 67694.0,
      "reward": 0.2407371997833252,
      "reward_std": 0.20068720169365406,
      "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": 0.125,
      "rewards/final_correctness_reward_func/std": 0.3535533845424652,
      "rewards/question_recreation_reward_func/mean": 0.11573721468448639,
      "rewards/question_recreation_reward_func/std": 0.07402005046606064,
      "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": 20
    },
    {
      "epoch": 4.9411764705882355,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 0.13233287669718266,
      "train_runtime": 164161.8368,
      "train_samples_per_second": 0.001,
      "train_steps_per_second": 0.0
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 67694,
  "num_train_epochs": 5,
  "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
}