{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": null,
  "eval_steps": 500,
  "global_step": 310,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.29,
      "learning_rate": 2.8125e-06,
      "loss": 2.9065,
      "reward": 11.2264,
      "step": 9
    },
    {
      "epoch": 0.61,
      "learning_rate": 5.9375e-06,
      "loss": 2.6597,
      "reward": 11.0573,
      "step": 19
    },
    {
      "epoch": 0.94,
      "learning_rate": 9.0625e-06,
      "loss": 1.7609,
      "reward": 11.9648,
      "step": 29
    },
    {
      "epoch": 1.26,
      "learning_rate": 9.985430661522333e-06,
      "loss": 1.2947,
      "reward": 13.177,
      "step": 39
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.914274958326507e-06,
      "loss": 0.7901,
      "reward": 13.7785,
      "step": 49
    },
    {
      "epoch": 1.9,
      "learning_rate": 9.784701678661045e-06,
      "loss": 0.4549,
      "reward": 14.603,
      "step": 59
    },
    {
      "epoch": 2.23,
      "learning_rate": 9.598251102025463e-06,
      "loss": 0.5224,
      "reward": 15.594,
      "step": 69
    },
    {
      "epoch": 2.55,
      "learning_rate": 9.357139626751308e-06,
      "loss": 0.3896,
      "reward": 15.697,
      "step": 79
    },
    {
      "epoch": 2.87,
      "learning_rate": 9.064233422958078e-06,
      "loss": 0.305,
      "reward": 16.4374,
      "step": 89
    },
    {
      "epoch": 3.19,
      "learning_rate": 8.723014361461633e-06,
      "loss": 0.3697,
      "reward": 16.539,
      "step": 99
    },
    {
      "epoch": 3.52,
      "learning_rate": 8.337538623649237e-06,
      "loss": 0.3504,
      "reward": 17.218,
      "step": 109
    },
    {
      "epoch": 3.84,
      "learning_rate": 7.912388484339012e-06,
      "loss": 0.3387,
      "reward": 16.595,
      "step": 119
    },
    {
      "epoch": 4.16,
      "learning_rate": 7.4526178407965396e-06,
      "loss": 0.3369,
      "reward": 17.3314,
      "step": 129
    },
    {
      "epoch": 4.48,
      "learning_rate": 6.963692135422872e-06,
      "loss": 0.1907,
      "reward": 17.0773,
      "step": 139
    },
    {
      "epoch": 4.81,
      "learning_rate": 6.451423386272312e-06,
      "loss": 0.2781,
      "reward": 17.3675,
      "step": 149
    },
    {
      "epoch": 5.13,
      "learning_rate": 5.921901097713317e-06,
      "loss": 0.2708,
      "reward": 17.4558,
      "step": 159
    },
    {
      "epoch": 5.45,
      "learning_rate": 5.381419872519763e-06,
      "loss": 0.2548,
      "reward": 18.2967,
      "step": 169
    },
    {
      "epoch": 5.77,
      "learning_rate": 4.83640458589112e-06,
      "loss": 0.1266,
      "reward": 18.4324,
      "step": 179
    },
    {
      "epoch": 6.1,
      "learning_rate": 4.293334010882164e-06,
      "loss": 0.2178,
      "reward": 17.8528,
      "step": 189
    },
    {
      "epoch": 6.42,
      "learning_rate": 3.7586638031314182e-06,
      "loss": 0.184,
      "reward": 18.424,
      "step": 199
    },
    {
      "epoch": 6.74,
      "learning_rate": 3.2387497603938327e-06,
      "loss": 0.2045,
      "reward": 18.8729,
      "step": 209
    },
    {
      "epoch": 7.06,
      "learning_rate": 2.739772269116402e-06,
      "loss": 0.1521,
      "reward": 19.1409,
      "step": 219
    },
    {
      "epoch": 7.39,
      "learning_rate": 2.2676628361847834e-06,
      "loss": 0.1096,
      "reward": 18.8351,
      "step": 229
    },
    {
      "epoch": 7.71,
      "learning_rate": 1.8280335791817733e-06,
      "loss": 0.1408,
      "reward": 18.8548,
      "step": 239
    },
    {
      "epoch": 8.03,
      "learning_rate": 1.4261105133297693e-06,
      "loss": 0.1674,
      "reward": 18.8099,
      "step": 249
    },
    {
      "epoch": 8.35,
      "learning_rate": 1.0666714281569152e-06,
      "loss": 0.1583,
      "reward": 18.7122,
      "step": 259
    },
    {
      "epoch": 8.68,
      "learning_rate": 7.539890923671061e-07,
      "loss": 0.1407,
      "reward": 18.8339,
      "step": 269
    },
    {
      "epoch": 9.0,
      "learning_rate": 4.917804620559202e-07,
      "loss": 0.1214,
      "reward": 18.7366,
      "step": 279
    },
    {
      "epoch": 9.32,
      "learning_rate": 2.8316249605087386e-07,
      "loss": 0.093,
      "reward": 18.8959,
      "step": 289
    },
    {
      "epoch": 9.65,
      "learning_rate": 1.3061510361333186e-07,
      "loss": 0.1226,
      "reward": 18.4177,
      "step": 299
    },
    {
      "epoch": 9.97,
      "learning_rate": 3.59516649547248e-08,
      "loss": 0.1234,
      "reward": 18.9226,
      "step": 309
    }
  ],
  "logging_steps": 500,
  "max_steps": 310,
  "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
}