{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9872340425531915,
  "eval_steps": 100,
  "global_step": 29,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 606.7750289916992,
      "epoch": 0.1702127659574468,
      "grad_norm": 1.29706609249115,
      "kl": 0.0004105091094970703,
      "learning_rate": 2.956412726139078e-06,
      "loss": 0.0,
      "reward": 0.656696455180645,
      "reward_std": 0.3180967397987843,
      "rewards/accuracy_reward": 0.655915205180645,
      "rewards/format_reward": 0.0007812500349245966,
      "step": 5
    },
    {
      "completion_length": 619.802035522461,
      "epoch": 0.3404255319148936,
      "grad_norm": 0.2793990969657898,
      "kl": 0.006754302978515625,
      "learning_rate": 2.4946839873611927e-06,
      "loss": 0.0003,
      "reward": 0.7372768193483352,
      "reward_std": 0.24473994337022303,
      "rewards/accuracy_reward": 0.7371652126312256,
      "rewards/format_reward": 0.00011160714784637093,
      "step": 10
    },
    {
      "completion_length": 639.6226806640625,
      "epoch": 0.5106382978723404,
      "grad_norm": 0.14878229796886444,
      "kl": 0.002895164489746094,
      "learning_rate": 1.6808050203829845e-06,
      "loss": 0.0001,
      "reward": 0.7362723529338837,
      "reward_std": 0.21787264123558997,
      "rewards/accuracy_reward": 0.7361607447266578,
      "rewards/format_reward": 0.00011160714784637093,
      "step": 15
    },
    {
      "completion_length": 620.3491317749024,
      "epoch": 0.6808510638297872,
      "grad_norm": 0.3235343396663666,
      "kl": 0.0030170440673828124,
      "learning_rate": 8.029152419343472e-07,
      "loss": 0.0001,
      "reward": 0.7439732491970062,
      "reward_std": 0.19663761276751757,
      "rewards/accuracy_reward": 0.7439732491970062,
      "rewards/format_reward": 0.0,
      "step": 20
    },
    {
      "completion_length": 626.3246917724609,
      "epoch": 0.851063829787234,
      "grad_norm": 0.17587672173976898,
      "kl": 0.00351715087890625,
      "learning_rate": 1.718159615201853e-07,
      "loss": 0.0001,
      "reward": 0.7379464641213417,
      "reward_std": 0.19247310273349286,
      "rewards/accuracy_reward": 0.7379464641213417,
      "rewards/format_reward": 0.0,
      "step": 25
    },
    {
      "completion_length": 613.0961494445801,
      "epoch": 0.9872340425531915,
      "kl": 0.0030832290649414062,
      "reward": 0.7661830689758062,
      "reward_std": 0.20291359443217516,
      "rewards/accuracy_reward": 0.7661830689758062,
      "rewards/format_reward": 0.0,
      "step": 29,
      "total_flos": 0.0,
      "train_loss": -0.0007466705064871348,
      "train_runtime": 14898.3188,
      "train_samples_per_second": 0.503,
      "train_steps_per_second": 0.002
    }
  ],
  "logging_steps": 5,
  "max_steps": 29,
  "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": 32,
  "trial_name": null,
  "trial_params": null
}