{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": null,
  "eval_steps": 500,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.6,
      "learning_rate": 5.625e-06,
      "loss": 5.6043,
      "reward": 14.4635,
      "step": 9
    },
    {
      "epoch": 1.27,
      "learning_rate": 9.989294616193018e-06,
      "loss": 2.8511,
      "reward": 14.7847,
      "step": 19
    },
    {
      "epoch": 1.93,
      "learning_rate": 9.800249271929645e-06,
      "loss": 1.8762,
      "reward": 14.1969,
      "step": 29
    },
    {
      "epoch": 2.6,
      "learning_rate": 9.38363377853754e-06,
      "loss": 1.5917,
      "reward": 13.6521,
      "step": 39
    },
    {
      "epoch": 3.27,
      "learning_rate": 8.759199037394888e-06,
      "loss": 1.1798,
      "reward": 13.6497,
      "step": 49
    },
    {
      "epoch": 3.93,
      "learning_rate": 7.956548241817914e-06,
      "loss": 0.7525,
      "reward": 14.6839,
      "step": 59
    },
    {
      "epoch": 4.6,
      "learning_rate": 7.0137334492936875e-06,
      "loss": 0.8999,
      "reward": 15.1988,
      "step": 69
    },
    {
      "epoch": 5.27,
      "learning_rate": 5.975451610080643e-06,
      "loss": 0.9507,
      "reward": 15.1846,
      "step": 79
    },
    {
      "epoch": 5.93,
      "learning_rate": 4.890925574827195e-06,
      "loss": 0.7962,
      "reward": 15.0285,
      "step": 89
    },
    {
      "epoch": 6.6,
      "learning_rate": 3.8115705383691354e-06,
      "loss": 0.9013,
      "reward": 15.9189,
      "step": 99
    },
    {
      "epoch": 7.27,
      "learning_rate": 2.7885565489049948e-06,
      "loss": 0.6388,
      "reward": 15.8048,
      "step": 109
    },
    {
      "epoch": 7.93,
      "learning_rate": 1.8703826390797047e-06,
      "loss": 0.3787,
      "reward": 15.6162,
      "step": 119
    },
    {
      "epoch": 8.6,
      "learning_rate": 1.100577584535592e-06,
      "loss": 0.6496,
      "reward": 16.7622,
      "step": 129
    },
    {
      "epoch": 9.27,
      "learning_rate": 5.156362923365587e-07,
      "loss": 0.3453,
      "reward": 16.8219,
      "step": 139
    },
    {
      "epoch": 9.93,
      "learning_rate": 1.4328965093369284e-07,
      "loss": 0.3208,
      "reward": 16.369,
      "step": 149
    }
  ],
  "logging_steps": 500,
  "max_steps": 150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10.0,
  "save_steps": 500,
  "stateful_callbacks": {},
  "total_flos": 0,
  "train_batch_size": null,
  "trial_name": null,
  "trial_params": null
}