{
  "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": 0.5093,
      "reward": 3.7168,
      "step": 9
    },
    {
      "epoch": 0.61,
      "learning_rate": 5.9375e-06,
      "loss": 0.3901,
      "reward": 3.9072,
      "step": 19
    },
    {
      "epoch": 0.94,
      "learning_rate": 9.0625e-06,
      "loss": 0.3463,
      "reward": 3.795,
      "step": 29
    },
    {
      "epoch": 1.26,
      "learning_rate": 9.985430661522333e-06,
      "loss": 0.1907,
      "reward": 4.8141,
      "step": 39
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.914274958326507e-06,
      "loss": 0.1381,
      "reward": 4.9855,
      "step": 49
    },
    {
      "epoch": 1.9,
      "learning_rate": 9.784701678661045e-06,
      "loss": 0.1166,
      "reward": 5.1631,
      "step": 59
    },
    {
      "epoch": 2.23,
      "learning_rate": 9.598251102025463e-06,
      "loss": 0.1019,
      "reward": 5.3393,
      "step": 69
    },
    {
      "epoch": 2.55,
      "learning_rate": 9.357139626751308e-06,
      "loss": 0.0751,
      "reward": 5.4161,
      "step": 79
    },
    {
      "epoch": 2.87,
      "learning_rate": 9.064233422958078e-06,
      "loss": 0.1013,
      "reward": 5.4679,
      "step": 89
    },
    {
      "epoch": 3.19,
      "learning_rate": 8.723014361461633e-06,
      "loss": 0.0473,
      "reward": 5.523,
      "step": 99
    },
    {
      "epoch": 3.52,
      "learning_rate": 8.337538623649237e-06,
      "loss": 0.0388,
      "reward": 5.5629,
      "step": 109
    },
    {
      "epoch": 3.84,
      "learning_rate": 7.912388484339012e-06,
      "loss": 0.0874,
      "reward": 5.3349,
      "step": 119
    },
    {
      "epoch": 4.16,
      "learning_rate": 7.4526178407965396e-06,
      "loss": 0.0367,
      "reward": 5.4507,
      "step": 129
    },
    {
      "epoch": 4.48,
      "learning_rate": 6.963692135422872e-06,
      "loss": 0.0387,
      "reward": 5.6017,
      "step": 139
    },
    {
      "epoch": 4.81,
      "learning_rate": 6.451423386272312e-06,
      "loss": 0.0302,
      "reward": 5.798,
      "step": 149
    },
    {
      "epoch": 5.13,
      "learning_rate": 5.921901097713317e-06,
      "loss": 0.0424,
      "reward": 5.7266,
      "step": 159
    },
    {
      "epoch": 5.45,
      "learning_rate": 5.381419872519763e-06,
      "loss": 0.0397,
      "reward": 5.762,
      "step": 169
    },
    {
      "epoch": 5.77,
      "learning_rate": 4.83640458589112e-06,
      "loss": 0.0327,
      "reward": 5.7574,
      "step": 179
    },
    {
      "epoch": 6.1,
      "learning_rate": 4.293334010882164e-06,
      "loss": 0.0301,
      "reward": 5.7441,
      "step": 189
    },
    {
      "epoch": 6.42,
      "learning_rate": 3.7586638031314182e-06,
      "loss": 0.0149,
      "reward": 5.8132,
      "step": 199
    },
    {
      "epoch": 6.74,
      "learning_rate": 3.2387497603938327e-06,
      "loss": 0.0367,
      "reward": 5.7579,
      "step": 209
    },
    {
      "epoch": 7.06,
      "learning_rate": 2.739772269116402e-06,
      "loss": 0.0369,
      "reward": 5.7852,
      "step": 219
    },
    {
      "epoch": 7.39,
      "learning_rate": 2.2676628361847834e-06,
      "loss": 0.038,
      "reward": 5.7178,
      "step": 229
    },
    {
      "epoch": 7.71,
      "learning_rate": 1.8280335791817733e-06,
      "loss": 0.0198,
      "reward": 5.8608,
      "step": 239
    },
    {
      "epoch": 8.03,
      "learning_rate": 1.4261105133297693e-06,
      "loss": 0.0323,
      "reward": 5.7764,
      "step": 249
    },
    {
      "epoch": 8.35,
      "learning_rate": 1.0666714281569152e-06,
      "loss": 0.0215,
      "reward": 5.8996,
      "step": 259
    },
    {
      "epoch": 8.68,
      "learning_rate": 7.539890923671061e-07,
      "loss": 0.0206,
      "reward": 5.8818,
      "step": 269
    },
    {
      "epoch": 9.0,
      "learning_rate": 4.917804620559202e-07,
      "loss": 0.0445,
      "reward": 5.689,
      "step": 279
    },
    {
      "epoch": 9.32,
      "learning_rate": 2.8316249605087386e-07,
      "loss": 0.0234,
      "reward": 6.027,
      "step": 289
    },
    {
      "epoch": 9.65,
      "learning_rate": 1.3061510361333186e-07,
      "loss": 0.0142,
      "reward": 5.8128,
      "step": 299
    },
    {
      "epoch": 9.97,
      "learning_rate": 3.59516649547248e-08,
      "loss": 0.0158,
      "reward": 5.8429,
      "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
}