{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.24253644989585743,
  "global_step": 2096,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1.9997685720897943e-05,
      "loss": 2.316,
      "step": 1
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.969914371673224e-05,
      "loss": 2.907,
      "step": 131
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.9398287433464477e-05,
      "loss": 2.8073,
      "step": 262
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.9095116871094656e-05,
      "loss": 2.7381,
      "step": 393
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.8791946308724832e-05,
      "loss": 2.6726,
      "step": 524
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.848877574635501e-05,
      "loss": 2.5643,
      "step": 655
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.818560518398519e-05,
      "loss": 2.4772,
      "step": 786
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.788243462161537e-05,
      "loss": 2.4839,
      "step": 917
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.7579264059245548e-05,
      "loss": 2.5131,
      "step": 1048
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.7276093496875727e-05,
      "loss": 2.4251,
      "step": 1179
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.6972922934505902e-05,
      "loss": 2.4532,
      "step": 1310
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.667206665123814e-05,
      "loss": 2.4152,
      "step": 1441
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.636889608886832e-05,
      "loss": 2.419,
      "step": 1572
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.6065725526498498e-05,
      "loss": 2.4077,
      "step": 1703
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.5762554964128677e-05,
      "loss": 2.4091,
      "step": 1834
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.5459384401758853e-05,
      "loss": 2.4614,
      "step": 1965
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.5156213839389032e-05,
      "loss": 2.3945,
      "step": 2096
    }
  ],
  "max_steps": 8642,
  "num_train_epochs": 1,
  "total_flos": 3903267218128896.0,
  "trial_name": null,
  "trial_params": null
}