{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9884169884169884,
  "eval_steps": 100,
  "global_step": 32,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 287.9553693771362,
      "epoch": 0.15444015444015444,
      "grad_norm": 712.992919921875,
      "kl": 3.120312976837158,
      "learning_rate": 1.9937122098932428e-05,
      "loss": 0.1248,
      "reward": 0.6392857432365417,
      "reward_std": 0.24748737085610628,
      "rewards/accuracy_reward": 0.11250000586733222,
      "rewards/format_reward": 0.5267857377417385,
      "step": 5
    },
    {
      "completion_length": 76.98839626312255,
      "epoch": 0.3088803088803089,
      "grad_norm": 0.6054267287254333,
      "kl": 0.269256591796875,
      "learning_rate": 1.78183148246803e-05,
      "loss": 0.0108,
      "reward": 1.0053571820259095,
      "reward_std": 0.13131982944905757,
      "rewards/accuracy_reward": 0.058928574342280625,
      "rewards/format_reward": 0.946428595483303,
      "step": 10
    },
    {
      "completion_length": 53.2321453332901,
      "epoch": 0.46332046332046334,
      "grad_norm": 0.6564269661903381,
      "kl": 0.46717529296875,
      "learning_rate": 1.3302790619551673e-05,
      "loss": 0.0187,
      "reward": 1.0392857573926448,
      "reward_std": 0.13637059200555085,
      "rewards/accuracy_reward": 0.09196429075673222,
      "rewards/format_reward": 0.9473214484751225,
      "step": 15
    },
    {
      "completion_length": 94.31786141395568,
      "epoch": 0.6177606177606177,
      "grad_norm": 0.3075297772884369,
      "kl": 0.252783203125,
      "learning_rate": 7.774790660436857e-06,
      "loss": 0.0101,
      "reward": 1.0741071864962577,
      "reward_std": 0.13005714006721975,
      "rewards/accuracy_reward": 0.10446429094299674,
      "rewards/format_reward": 0.9696428716182709,
      "step": 20
    },
    {
      "completion_length": 132.22054238319396,
      "epoch": 0.7722007722007722,
      "grad_norm": 0.4520126283168793,
      "kl": 0.225750732421875,
      "learning_rate": 2.9289321881345257e-06,
      "loss": 0.009,
      "reward": 1.0294643245637416,
      "reward_std": 0.17046323977410793,
      "rewards/accuracy_reward": 0.09375000428408384,
      "rewards/format_reward": 0.935714315623045,
      "step": 25
    },
    {
      "completion_length": 143.1794707775116,
      "epoch": 0.9266409266409267,
      "grad_norm": 0.4325202405452728,
      "kl": 0.220745849609375,
      "learning_rate": 2.507208781817638e-07,
      "loss": 0.0088,
      "reward": 1.0116071835160256,
      "reward_std": 0.16036171615123748,
      "rewards/accuracy_reward": 0.08125000409781932,
      "rewards/format_reward": 0.9303571656346321,
      "step": 30
    },
    {
      "completion_length": 134.81697022914886,
      "epoch": 0.9884169884169884,
      "kl": 0.248382568359375,
      "reward": 1.020089328289032,
      "reward_std": 0.12311234045773745,
      "rewards/accuracy_reward": 0.07589286053553224,
      "rewards/format_reward": 0.944196455180645,
      "step": 32,
      "total_flos": 0.0,
      "train_loss": 0.029145897831767797,
      "train_runtime": 1931.8778,
      "train_samples_per_second": 1.875,
      "train_steps_per_second": 0.017
    }
  ],
  "logging_steps": 5,
  "max_steps": 32,
  "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": 2,
  "trial_name": null,
  "trial_params": null
}