{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 67,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 783.9694522857666,
      "epoch": 0.14925373134328357,
      "grad_norm": 0.05181676521897316,
      "kl": 0.005163563787937165,
      "learning_rate": 1.9876883405951378e-05,
      "loss": 0.0002,
      "reward": 0.434040200675372,
      "reward_std": 0.20802043355070055,
      "rewards/accuracy_reward": 0.434040200675372,
      "rewards/format_reward": 0.0,
      "step": 10
    },
    {
      "completion_length": 704.0053884506226,
      "epoch": 0.29850746268656714,
      "grad_norm": 0.053839247673749924,
      "kl": 0.024178695678710938,
      "learning_rate": 1.777145961456971e-05,
      "loss": 0.001,
      "reward": 0.6050223488360643,
      "reward_std": 0.2017547628376633,
      "rewards/accuracy_reward": 0.6050223488360643,
      "rewards/format_reward": 0.0,
      "step": 20
    },
    {
      "completion_length": 696.0905450820923,
      "epoch": 0.44776119402985076,
      "grad_norm": 0.05350080132484436,
      "kl": 0.034772491455078124,
      "learning_rate": 1.3583679495453e-05,
      "loss": 0.0014,
      "reward": 0.605022350512445,
      "reward_std": 0.19985151030123233,
      "rewards/accuracy_reward": 0.605022350512445,
      "rewards/format_reward": 0.0,
      "step": 30
    },
    {
      "completion_length": 729.1377559661865,
      "epoch": 0.5970149253731343,
      "grad_norm": 0.23939549922943115,
      "kl": 0.03041534423828125,
      "learning_rate": 8.43565534959769e-06,
      "loss": 0.0012,
      "reward": 0.5872768124565482,
      "reward_std": 0.19744328511878848,
      "rewards/accuracy_reward": 0.5872768124565482,
      "rewards/format_reward": 0.0,
      "step": 40
    },
    {
      "completion_length": 702.5680013656616,
      "epoch": 0.746268656716418,
      "grad_norm": 0.05750499665737152,
      "kl": 0.047086334228515624,
      "learning_rate": 3.7067960895016277e-06,
      "loss": 0.0019,
      "reward": 0.5887277035042644,
      "reward_std": 0.20520030087791383,
      "rewards/accuracy_reward": 0.5887277035042644,
      "rewards/format_reward": 0.0,
      "step": 50
    },
    {
      "completion_length": 710.974139213562,
      "epoch": 0.8955223880597015,
      "grad_norm": 0.07039864361286163,
      "kl": 0.06742630004882813,
      "learning_rate": 6.641957350279838e-07,
      "loss": 0.0027,
      "reward": 0.5754464564844965,
      "reward_std": 0.21752566741779447,
      "rewards/accuracy_reward": 0.5754464564844965,
      "rewards/format_reward": 0.0,
      "step": 60
    },
    {
      "completion_length": 711.0281990596226,
      "epoch": 1.0,
      "kl": 0.07862200055803571,
      "reward": 0.5738733240536281,
      "reward_std": 0.21155406614499433,
      "rewards/accuracy_reward": 0.5738733240536281,
      "rewards/format_reward": 0.0,
      "step": 67,
      "total_flos": 0.0,
      "train_loss": 0.001551433688780265,
      "train_runtime": 9967.0862,
      "train_samples_per_second": 0.752,
      "train_steps_per_second": 0.007
    }
  ],
  "logging_steps": 10,
  "max_steps": 67,
  "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": 1,
  "trial_name": null,
  "trial_params": null
}