[
  {
    "loss": 0.0,
    "grad_norm": 33.0,
    "learning_rate": 5e-07,
    "completion_length": 87.5125,
    "rewards/real_reward_fn": -0.08881250247359276,
    "reward": -0.08881250247359276,
    "reward_std": 0.1590106257237494,
    "kl": 0.0008317360421642661,
    "epoch": 0.16,
    "step": 5
  },
  {
    "loss": 0.0,
    "grad_norm": 55.25,
    "learning_rate": 5e-07,
    "completion_length": 85.86875,
    "rewards/real_reward_fn": -0.08131250264123083,
    "reward": -0.08131250264123083,
    "reward_std": 0.1880020027048886,
    "kl": 0.001102981199801434,
    "epoch": 0.32,
    "step": 10
  },
  {
    "loss": 0.0,
    "grad_norm": 39.0,
    "learning_rate": 5e-07,
    "completion_length": 83.225,
    "rewards/real_reward_fn": 0.02462499784305692,
    "reward": 0.02462499784305692,
    "reward_std": 0.13523416444659234,
    "kl": 0.001013497701205779,
    "epoch": 0.48,
    "step": 15
  },
  {
    "loss": 0.0,
    "grad_norm": 27.125,
    "learning_rate": 5e-07,
    "completion_length": 80.8125,
    "rewards/real_reward_fn": -0.08068750295788049,
    "reward": -0.08068750295788049,
    "reward_std": 0.18747167382389307,
    "kl": 0.0011422165334806778,
    "epoch": 0.64,
    "step": 20
  },
  {
    "loss": 0.0,
    "grad_norm": 30.5,
    "learning_rate": 5e-07,
    "completion_length": 80.29375,
    "rewards/real_reward_fn": -0.03431250210851431,
    "reward": -0.03431250210851431,
    "reward_std": 0.18764845319092274,
    "kl": 0.0010913557125604711,
    "epoch": 0.8,
    "step": 25
  },
  {
    "loss": 0.0,
    "grad_norm": 58.0,
    "learning_rate": 5e-07,
    "completion_length": 80.575,
    "rewards/real_reward_fn": 0.024874999094754456,
    "reward": 0.024874999094754456,
    "reward_std": 0.1568009190261364,
    "kl": 0.0010487768857274204,
    "epoch": 0.96,
    "step": 30
  },
  {
    "loss": 0.0,
    "grad_norm": 35.0,
    "learning_rate": 5e-07,
    "completion_length": 76.90441176470588,
    "rewards/real_reward_fn": -0.05720588389564963,
    "reward": -0.05720588389564963,
    "reward_std": 0.14079742714324417,
    "kl": 0.0010246854611015057,
    "epoch": 1.096,
    "step": 35
  },
  {
    "loss": 0.0,
    "grad_norm": 28.125,
    "learning_rate": 5e-07,
    "completion_length": 83.84375,
    "rewards/real_reward_fn": -0.02056250227615237,
    "reward": -0.02056250227615237,
    "reward_std": 0.14504527123644947,
    "kl": 0.001108163884782698,
    "epoch": 1.256,
    "step": 40
  },
  {
    "loss": 0.0,
    "grad_norm": 32.0,
    "learning_rate": 5e-07,
    "completion_length": 79.25,
    "rewards/real_reward_fn": 0.021437497437000276,
    "reward": 0.021437497437000276,
    "reward_std": 0.17562763625755906,
    "kl": 0.0010782188706798478,
    "epoch": 1.416,
    "step": 45
  },
  {
    "loss": 0.0,
    "grad_norm": 35.75,
    "learning_rate": 5e-07,
    "completion_length": 86.08125,
    "rewards/real_reward_fn": -0.032250001840293405,
    "reward": -0.032250001840293405,
    "reward_std": 0.16334165595471858,
    "kl": 0.0010450664689415135,
    "epoch": 1.576,
    "step": 50
  },
  {
    "train_runtime": 1158.1834,
    "train_samples_per_second": 0.691,
    "train_steps_per_second": 0.043,
    "total_flos": 0.0,
    "train_loss": 4.1337845323141666e-05,
    "epoch": 1.576,
    "step": 50
  }
]