{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9486271036315324,
  "global_step": 11000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09,
      "learning_rate": 7.374631268436578e-05,
      "loss": 3.876,
      "step": 500
    },
    {
      "epoch": 0.18,
      "learning_rate": 9.696569920844328e-05,
      "loss": 1.5925,
      "step": 1000
    },
    {
      "epoch": 0.27,
      "learning_rate": 9.2254052016585e-05,
      "loss": 1.2572,
      "step": 1500
    },
    {
      "epoch": 0.35,
      "learning_rate": 8.754240482472673e-05,
      "loss": 1.1371,
      "step": 2000
    },
    {
      "epoch": 0.44,
      "learning_rate": 8.283075763286845e-05,
      "loss": 1.0932,
      "step": 2500
    },
    {
      "epoch": 0.53,
      "learning_rate": 7.811911044101018e-05,
      "loss": 1.0323,
      "step": 3000
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.340746324915191e-05,
      "loss": 1.0333,
      "step": 3500
    },
    {
      "epoch": 0.71,
      "learning_rate": 6.869581605729364e-05,
      "loss": 0.9684,
      "step": 4000
    },
    {
      "epoch": 0.8,
      "learning_rate": 6.398416886543535e-05,
      "loss": 0.9606,
      "step": 4500
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.927252167357709e-05,
      "loss": 0.9397,
      "step": 5000
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.4560874481718815e-05,
      "loss": 0.8899,
      "step": 5500
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.0070745944976807,
      "eval_runtime": 18.4896,
      "eval_samples_per_second": 176.37,
      "eval_steps_per_second": 7.355,
      "step": 5645
    },
    {
      "epoch": 1.06,
      "learning_rate": 4.984922728986054e-05,
      "loss": 0.733,
      "step": 6000
    },
    {
      "epoch": 1.15,
      "learning_rate": 4.5137580098002266e-05,
      "loss": 0.6544,
      "step": 6500
    },
    {
      "epoch": 1.24,
      "learning_rate": 4.0425932906143985e-05,
      "loss": 0.6608,
      "step": 7000
    },
    {
      "epoch": 1.33,
      "learning_rate": 3.571428571428572e-05,
      "loss": 0.6493,
      "step": 7500
    },
    {
      "epoch": 1.42,
      "learning_rate": 3.100263852242744e-05,
      "loss": 0.6352,
      "step": 8000
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.629099133056917e-05,
      "loss": 0.6268,
      "step": 8500
    },
    {
      "epoch": 1.59,
      "learning_rate": 2.1579344138710894e-05,
      "loss": 0.6172,
      "step": 9000
    },
    {
      "epoch": 1.68,
      "learning_rate": 1.686769694685262e-05,
      "loss": 0.6159,
      "step": 9500
    },
    {
      "epoch": 1.77,
      "learning_rate": 1.2156049754994346e-05,
      "loss": 0.5908,
      "step": 10000
    },
    {
      "epoch": 1.86,
      "learning_rate": 7.444402563136073e-06,
      "loss": 0.59,
      "step": 10500
    },
    {
      "epoch": 1.95,
      "learning_rate": 2.7327553712777988e-06,
      "loss": 0.582,
      "step": 11000
    }
  ],
  "max_steps": 11290,
  "num_train_epochs": 2,
  "total_flos": 6.897685654641254e+16,
  "trial_name": null,
  "trial_params": null
}