{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.13402579996649355,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 4.99993842168232e-05,
      "loss": 1.2211,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9997536897627915e-05,
      "loss": 1.0276,
      "step": 20
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9994458133418e-05,
      "loss": 0.8587,
      "step": 30
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.999014807586154e-05,
      "loss": 0.7431,
      "step": 40
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9984606937283405e-05,
      "loss": 0.6841,
      "step": 50
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9977834990654804e-05,
      "loss": 0.6452,
      "step": 60
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.99698325695798e-05,
      "loss": 0.6347,
      "step": 70
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9960600068278876e-05,
      "loss": 0.6109,
      "step": 80
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.995013794156957e-05,
      "loss": 0.5911,
      "step": 90
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.993844670484401e-05,
      "loss": 0.5803,
      "step": 100
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.992552693404354e-05,
      "loss": 0.5902,
      "step": 110
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.991137926563036e-05,
      "loss": 0.5745,
      "step": 120
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.9896004396556176e-05,
      "loss": 0.5538,
      "step": 130
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.987940308422783e-05,
      "loss": 0.5495,
      "step": 140
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.986157614647005e-05,
      "loss": 0.5433,
      "step": 150
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.984252446148508e-05,
      "loss": 0.548,
      "step": 160
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.98222489678095e-05,
      "loss": 0.5361,
      "step": 170
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.980075066426796e-05,
      "loss": 0.5331,
      "step": 180
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.977803060992393e-05,
      "loss": 0.53,
      "step": 190
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.97540899240276e-05,
      "loss": 0.5135,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 4476,
  "num_train_epochs": 3,
  "save_steps": 200,
  "total_flos": 1.81903539565704e+18,
  "trial_name": null,
  "trial_params": null
}