{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9893390191897654,
  "eval_steps": 100,
  "global_step": 58,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 442.65068969726565,
      "epoch": 0.08528784648187633,
      "grad_norm": 6.35717248916626,
      "kl": 0.0004929542541503906,
      "learning_rate": 2.5e-06,
      "loss": 0.0,
      "reward": 0.41696430593729017,
      "reward_std": 0.4544539041817188,
      "rewards/accuracy_reward": 0.12834822051227093,
      "rewards/format_reward": 0.28861608617007734,
      "step": 5
    },
    {
      "completion_length": 304.9187644958496,
      "epoch": 0.17057569296375266,
      "grad_norm": 2.1602344512939453,
      "kl": 0.026971435546875,
      "learning_rate": 2.956412726139078e-06,
      "loss": 0.0011,
      "reward": 0.986160759627819,
      "reward_std": 0.3372926861047745,
      "rewards/accuracy_reward": 0.11272321967408061,
      "rewards/format_reward": 0.873437537252903,
      "step": 10
    },
    {
      "completion_length": 365.3803741455078,
      "epoch": 0.255863539445629,
      "grad_norm": 0.33471256494522095,
      "kl": 0.03214263916015625,
      "learning_rate": 2.7836719084521715e-06,
      "loss": 0.0013,
      "reward": 1.298883980512619,
      "reward_std": 0.41679972484707833,
      "rewards/accuracy_reward": 0.37522323429584503,
      "rewards/format_reward": 0.923660759627819,
      "step": 15
    },
    {
      "completion_length": 378.46050758361815,
      "epoch": 0.3411513859275053,
      "grad_norm": 1.4841564893722534,
      "kl": 0.0420074462890625,
      "learning_rate": 2.4946839873611927e-06,
      "loss": 0.0017,
      "reward": 1.4825893670320511,
      "reward_std": 0.4033116206526756,
      "rewards/accuracy_reward": 0.5584821693599225,
      "rewards/format_reward": 0.9241071850061416,
      "step": 20
    },
    {
      "completion_length": 394.2165367126465,
      "epoch": 0.42643923240938164,
      "grad_norm": 0.28560909628868103,
      "kl": 0.0350738525390625,
      "learning_rate": 2.1156192081791355e-06,
      "loss": 0.0014,
      "reward": 1.512500062584877,
      "reward_std": 0.3465679492801428,
      "rewards/accuracy_reward": 0.5779018126428127,
      "rewards/format_reward": 0.9345982566475868,
      "step": 25
    },
    {
      "completion_length": 401.2672065734863,
      "epoch": 0.511727078891258,
      "grad_norm": 0.5306402444839478,
      "kl": 0.034088134765625,
      "learning_rate": 1.6808050203829845e-06,
      "loss": 0.0014,
      "reward": 1.5180804193019868,
      "reward_std": 0.3442438319325447,
      "rewards/accuracy_reward": 0.5779018104076385,
      "rewards/format_reward": 0.940178607404232,
      "step": 30
    },
    {
      "completion_length": 393.07434768676757,
      "epoch": 0.5970149253731343,
      "grad_norm": 0.2967917323112488,
      "kl": 0.0385345458984375,
      "learning_rate": 1.2296174432791415e-06,
      "loss": 0.0015,
      "reward": 1.5225447058677672,
      "reward_std": 0.34006611779332163,
      "rewards/accuracy_reward": 0.5747768118977546,
      "rewards/format_reward": 0.9477679014205933,
      "step": 35
    },
    {
      "completion_length": 390.0587242126465,
      "epoch": 0.6823027718550106,
      "grad_norm": 0.358806312084198,
      "kl": 0.0369537353515625,
      "learning_rate": 8.029152419343472e-07,
      "loss": 0.0015,
      "reward": 1.572321492433548,
      "reward_std": 0.313805010356009,
      "rewards/accuracy_reward": 0.6136160999536514,
      "rewards/format_reward": 0.9587054014205932,
      "step": 40
    },
    {
      "completion_length": 418.40091094970705,
      "epoch": 0.767590618336887,
      "grad_norm": 0.2598155736923218,
      "kl": 0.03328857421875,
      "learning_rate": 4.3933982822017883e-07,
      "loss": 0.0013,
      "reward": 1.5649554222822188,
      "reward_std": 0.3114229992032051,
      "rewards/accuracy_reward": 0.6140625312924385,
      "rewards/format_reward": 0.9508929029107094,
      "step": 45
    },
    {
      "completion_length": 422.549129486084,
      "epoch": 0.8528784648187633,
      "grad_norm": 0.2509433925151825,
      "kl": 0.034161376953125,
      "learning_rate": 1.718159615201853e-07,
      "loss": 0.0014,
      "reward": 1.5645089954137803,
      "reward_std": 0.3242972683161497,
      "rewards/accuracy_reward": 0.6129464544355869,
      "rewards/format_reward": 0.9515625432133674,
      "step": 50
    },
    {
      "completion_length": 419.257829284668,
      "epoch": 0.9381663113006397,
      "grad_norm": 0.3123314082622528,
      "kl": 0.0333709716796875,
      "learning_rate": 2.4570139579284723e-08,
      "loss": 0.0013,
      "reward": 1.5895090013742448,
      "reward_std": 0.326204876601696,
      "rewards/accuracy_reward": 0.6330357410013676,
      "rewards/format_reward": 0.9564732536673546,
      "step": 55
    },
    {
      "completion_length": 415.0018781026204,
      "epoch": 0.9893390191897654,
      "kl": 0.03472900390625,
      "reward": 1.5885417411724727,
      "reward_std": 0.29818206280469894,
      "rewards/accuracy_reward": 0.6279762176175913,
      "rewards/format_reward": 0.9605655198295912,
      "step": 58,
      "total_flos": 0.0,
      "train_loss": 0.0013394545973730192,
      "train_runtime": 6585.1769,
      "train_samples_per_second": 1.139,
      "train_steps_per_second": 0.009
    }
  ],
  "logging_steps": 5,
  "max_steps": 58,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "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": 16,
  "trial_name": null,
  "trial_params": null
}