{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9898666666666667,
  "eval_steps": 100,
  "global_step": 58,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 603.8593917056918,
      "epoch": 0.08533333333333333,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 2.5e-06,
      "loss": 0.0,
      "reward": 0.6109375,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.6109375,
      "rewards/format_reward": 0.0,
      "step": 5
    },
    {
      "completion_length": 584.4031410098075,
      "epoch": 0.17066666666666666,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 2.956412726139078e-06,
      "loss": 0.0,
      "reward": 0.6375,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.6375,
      "rewards/format_reward": 0.0,
      "step": 10
    },
    {
      "completion_length": 600.2140792787075,
      "epoch": 0.256,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 2.7836719084521715e-06,
      "loss": 0.0,
      "reward": 0.6625,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.6609375,
      "rewards/format_reward": 0.0015625,
      "step": 15
    },
    {
      "completion_length": 591.8015787974,
      "epoch": 0.3413333333333333,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 2.4946839873611927e-06,
      "loss": 0.0,
      "reward": 0.6703125,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.6703125,
      "rewards/format_reward": 0.0,
      "step": 20
    },
    {
      "completion_length": 596.3640791006386,
      "epoch": 0.4266666666666667,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 2.1156192081791355e-06,
      "loss": 0.0,
      "reward": 0.6234375,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.621875,
      "rewards/format_reward": 0.0015625,
      "step": 25
    },
    {
      "completion_length": 615.087518073991,
      "epoch": 0.512,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 1.6808050203829845e-06,
      "loss": 0.0,
      "reward": 0.646875,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.6453125,
      "rewards/format_reward": 0.0015625,
      "step": 30
    },
    {
      "completion_length": 615.3468918040395,
      "epoch": 0.5973333333333334,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 1.2296174432791415e-06,
      "loss": 0.0,
      "reward": 0.6328125,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.63125,
      "rewards/format_reward": 0.0015625,
      "step": 35
    },
    {
      "completion_length": 595.034390886128,
      "epoch": 0.6826666666666666,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 8.029152419343472e-07,
      "loss": 0.0,
      "reward": 0.6328125,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.6328125,
      "rewards/format_reward": 0.0,
      "step": 40
    },
    {
      "completion_length": 596.4328294545412,
      "epoch": 0.768,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 4.3933982822017883e-07,
      "loss": 0.0,
      "reward": 0.65625,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.65625,
      "rewards/format_reward": 0.0,
      "step": 45
    },
    {
      "completion_length": 590.887516361475,
      "epoch": 0.8533333333333334,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 1.718159615201853e-07,
      "loss": 0.0,
      "reward": 0.65,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.65,
      "rewards/format_reward": 0.0,
      "step": 50
    },
    {
      "completion_length": 627.9453295856714,
      "epoch": 0.9386666666666666,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 2.4570139579284723e-08,
      "loss": 0.0,
      "reward": 0.659375,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.659375,
      "rewards/format_reward": 0.0,
      "step": 55
    },
    {
      "completion_length": 568.0260575544089,
      "epoch": 0.9898666666666667,
      "kl": 0.0,
      "reward": 0.6458333333333334,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.6458333333333334,
      "rewards/format_reward": 0.0,
      "step": 58,
      "total_flos": 0.0,
      "train_loss": 0.0,
      "train_runtime": 920571.4003,
      "train_samples_per_second": 0.008,
      "train_steps_per_second": 0.0
    }
  ],
  "logging_steps": 5,
  "max_steps": 58,
  "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
}