{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05333333333333334,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 49.39791831970215,
      "epoch": 0.0026666666666666666,
      "grad_norm": 2.0543670654296875,
      "kl": 0.0,
      "learning_rate": 9.988749999999998e-07,
      "loss": 0.0,
      "reward": 0.7812500149011612,
      "reward_std": 0.07898591235280036,
      "rewards/accuracy_reward": 0.7812500149011612,
      "rewards/format_reward": 0.0,
      "step": 10
    },
    {
      "completion_length": 49.31250114440918,
      "epoch": 0.005333333333333333,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 9.97625e-07,
      "loss": 0.0,
      "reward": 0.8270833492279053,
      "reward_std": 0.055086643993854524,
      "rewards/accuracy_reward": 0.8270833492279053,
      "rewards/format_reward": 0.0,
      "step": 20
    },
    {
      "completion_length": 47.689584732055664,
      "epoch": 0.008,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 9.96375e-07,
      "loss": 0.0,
      "reward": 0.8666666746139526,
      "reward_std": 0.02957112304866314,
      "rewards/accuracy_reward": 0.8666666746139526,
      "rewards/format_reward": 0.0,
      "step": 30
    },
    {
      "completion_length": 46.74375114440918,
      "epoch": 0.010666666666666666,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 9.95125e-07,
      "loss": 0.0,
      "reward": 0.7645833373069764,
      "reward_std": 0.021764283627271654,
      "rewards/accuracy_reward": 0.7645833373069764,
      "rewards/format_reward": 0.0,
      "step": 40
    },
    {
      "completion_length": 46.62708435058594,
      "epoch": 0.013333333333333334,
      "grad_norm": 5.9468488693237305,
      "kl": 0.0,
      "learning_rate": 9.938749999999999e-07,
      "loss": 0.0,
      "reward": 0.7562500178813935,
      "reward_std": 0.041129202023148535,
      "rewards/accuracy_reward": 0.7562500178813935,
      "rewards/format_reward": 0.0,
      "step": 50
    },
    {
      "completion_length": 43.75833435058594,
      "epoch": 0.016,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 9.926249999999999e-07,
      "loss": 0.0,
      "reward": 0.7791666775941849,
      "reward_std": 0.05818194076418877,
      "rewards/accuracy_reward": 0.7791666775941849,
      "rewards/format_reward": 0.0,
      "step": 60
    },
    {
      "completion_length": 41.90833435058594,
      "epoch": 0.018666666666666668,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 9.913749999999999e-07,
      "loss": 0.0,
      "reward": 0.7645833492279053,
      "reward_std": 0.0550866425037384,
      "rewards/accuracy_reward": 0.7645833492279053,
      "rewards/format_reward": 0.0,
      "step": 70
    },
    {
      "completion_length": 40.07916793823242,
      "epoch": 0.021333333333333333,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 9.90125e-07,
      "loss": 0.0,
      "reward": 0.7770833373069763,
      "reward_std": 0.0317061148583889,
      "rewards/accuracy_reward": 0.7770833373069763,
      "rewards/format_reward": 0.0,
      "step": 80
    },
    {
      "completion_length": 38.35000114440918,
      "epoch": 0.024,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 9.88875e-07,
      "loss": 0.0,
      "reward": 0.7645833432674408,
      "reward_std": 0.060581305995583534,
      "rewards/accuracy_reward": 0.7645833432674408,
      "rewards/format_reward": 0.0,
      "step": 90
    },
    {
      "completion_length": 37.939584732055664,
      "epoch": 0.02666666666666667,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 9.87625e-07,
      "loss": 0.0,
      "reward": 0.7979166746139527,
      "reward_std": 0.028219255805015563,
      "rewards/accuracy_reward": 0.7979166746139527,
      "rewards/format_reward": 0.0,
      "step": 100
    },
    {
      "completion_length": 37.908334732055664,
      "epoch": 0.029333333333333333,
      "grad_norm": 5.802574634552002,
      "kl": 0.0,
      "learning_rate": 9.86375e-07,
      "loss": 0.0,
      "reward": 0.8333333432674408,
      "reward_std": 0.045271995663642886,
      "rewards/accuracy_reward": 0.8333333432674408,
      "rewards/format_reward": 0.0,
      "step": 110
    },
    {
      "completion_length": 37.3604175567627,
      "epoch": 0.032,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 9.85125e-07,
      "loss": 0.0,
      "reward": 0.7812500119209289,
      "reward_std": 0.027258946374058724,
      "rewards/accuracy_reward": 0.7812500119209289,
      "rewards/format_reward": 0.0,
      "step": 120
    },
    {
      "completion_length": 37.42083473205567,
      "epoch": 0.034666666666666665,
      "grad_norm": 2.0744457244873047,
      "kl": 0.0,
      "learning_rate": 9.83875e-07,
      "loss": 0.0,
      "reward": 0.8125000178813935,
      "reward_std": 0.02686738669872284,
      "rewards/accuracy_reward": 0.8125000178813935,
      "rewards/format_reward": 0.0,
      "step": 130
    },
    {
      "completion_length": 37.39583473205566,
      "epoch": 0.037333333333333336,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 9.82625e-07,
      "loss": 0.0,
      "reward": 0.7708333492279053,
      "reward_std": 0.07484312132000923,
      "rewards/accuracy_reward": 0.7708333492279053,
      "rewards/format_reward": 0.0,
      "step": 140
    },
    {
      "completion_length": 37.16458435058594,
      "epoch": 0.04,
      "grad_norm": 4.576603889465332,
      "kl": 0.0,
      "learning_rate": 9.81375e-07,
      "loss": 0.0,
      "reward": 0.7645833492279053,
      "reward_std": 0.028219255059957503,
      "rewards/accuracy_reward": 0.7645833492279053,
      "rewards/format_reward": 0.0,
      "step": 150
    },
    {
      "completion_length": 37.14375114440918,
      "epoch": 0.042666666666666665,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 9.80125e-07,
      "loss": 0.0,
      "reward": 0.7958333432674408,
      "reward_std": 0.03506578803062439,
      "rewards/accuracy_reward": 0.7958333432674408,
      "rewards/format_reward": 0.0,
      "step": 160
    },
    {
      "completion_length": 35.55625114440918,
      "epoch": 0.04533333333333334,
      "grad_norm": 1.8064866065979004,
      "kl": 0.0,
      "learning_rate": 9.78875e-07,
      "loss": 0.0,
      "reward": 0.7145833492279052,
      "reward_std": 0.05953380987048149,
      "rewards/accuracy_reward": 0.7145833492279052,
      "rewards/format_reward": 0.0,
      "step": 170
    },
    {
      "completion_length": 34.5791675567627,
      "epoch": 0.048,
      "grad_norm": 2.790367364883423,
      "kl": 0.0,
      "learning_rate": 9.77625e-07,
      "loss": 0.0,
      "reward": 0.8020833432674408,
      "reward_std": 0.06502847410738469,
      "rewards/accuracy_reward": 0.8020833432674408,
      "rewards/format_reward": 0.0,
      "step": 180
    },
    {
      "completion_length": 34.96250114440918,
      "epoch": 0.050666666666666665,
      "grad_norm": 2.381667137145996,
      "kl": 0.0,
      "learning_rate": 9.76375e-07,
      "loss": 0.0,
      "reward": 0.7625000238418579,
      "reward_std": 0.04998354017734528,
      "rewards/accuracy_reward": 0.7604166865348816,
      "rewards/format_reward": 0.002083333395421505,
      "step": 190
    },
    {
      "completion_length": 33.00416793823242,
      "epoch": 0.05333333333333334,
      "grad_norm": 3.4813380241394043,
      "kl": 0.0,
      "learning_rate": 9.75125e-07,
      "loss": 0.0,
      "reward": 0.7333333492279053,
      "reward_std": 0.03707359582185745,
      "rewards/accuracy_reward": 0.7333333492279053,
      "rewards/format_reward": 0.0,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 8000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}