{
  "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": 614.3402082443238,
      "epoch": 0.14925373134328357,
      "grad_norm": 0.17787058651447296,
      "kl": 0.0007179558277130127,
      "learning_rate": 2.981532510892707e-06,
      "loss": 0.0,
      "reward": 0.6806919943541289,
      "reward_std": 0.3078685597516596,
      "rewards/accuracy_reward": 0.6806919943541289,
      "rewards/format_reward": 0.0,
      "step": 10
    },
    {
      "completion_length": 603.5415452957153,
      "epoch": 0.29850746268656714,
      "grad_norm": 0.08805952966213226,
      "kl": 0.002512192726135254,
      "learning_rate": 2.6657189421854562e-06,
      "loss": 0.0001,
      "reward": 0.7568080699071288,
      "reward_std": 0.204924710188061,
      "rewards/accuracy_reward": 0.7568080699071288,
      "rewards/format_reward": 0.0,
      "step": 20
    },
    {
      "completion_length": 584.7102952957154,
      "epoch": 0.44776119402985076,
      "grad_norm": 0.09644156694412231,
      "kl": 0.002950286865234375,
      "learning_rate": 2.03755192431795e-06,
      "loss": 0.0001,
      "reward": 0.7686384269967675,
      "reward_std": 0.1692981747444719,
      "rewards/accuracy_reward": 0.7686384269967675,
      "rewards/format_reward": 0.0,
      "step": 30
    },
    {
      "completion_length": 586.5085081100464,
      "epoch": 0.5970149253731343,
      "grad_norm": 0.07653246074914932,
      "kl": 0.003155517578125,
      "learning_rate": 1.2653483024396534e-06,
      "loss": 0.0001,
      "reward": 0.7679687846451998,
      "reward_std": 0.1707028009928763,
      "rewards/accuracy_reward": 0.7679687846451998,
      "rewards/format_reward": 0.0,
      "step": 40
    },
    {
      "completion_length": 583.7289344787598,
      "epoch": 0.746268656716418,
      "grad_norm": 0.07442683726549149,
      "kl": 0.0033095359802246095,
      "learning_rate": 5.560194134252441e-07,
      "loss": 0.0001,
      "reward": 0.7731027137488127,
      "reward_std": 0.16860086238011718,
      "rewards/accuracy_reward": 0.7731027137488127,
      "rewards/format_reward": 0.0,
      "step": 50
    },
    {
      "completion_length": 580.679044342041,
      "epoch": 0.8955223880597015,
      "grad_norm": 0.09306953102350235,
      "kl": 0.0032823562622070314,
      "learning_rate": 9.962936025419756e-08,
      "loss": 0.0001,
      "reward": 0.7728794995695353,
      "reward_std": 0.16449202131479979,
      "rewards/accuracy_reward": 0.7728794995695353,
      "rewards/format_reward": 0.0,
      "step": 60
    },
    {
      "completion_length": 569.7491228921073,
      "epoch": 1.0,
      "kl": 0.0034044810703822543,
      "reward": 0.783216441316264,
      "reward_std": 0.1508938535116613,
      "rewards/accuracy_reward": 0.783216441316264,
      "rewards/format_reward": 0.0,
      "step": 67,
      "total_flos": 0.0,
      "train_loss": 0.00010928502410594652,
      "train_runtime": 12024.2367,
      "train_samples_per_second": 0.624,
      "train_steps_per_second": 0.006
    }
  ],
  "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
}