{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.021333333333333333,
  "eval_steps": 500,
  "global_step": 1600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 9.973379823589855e-05,
      "loss": 0.9998,
      "step": 100
    },
    {
      "epoch": 0.0,
      "learning_rate": 9.768246469067398e-05,
      "loss": 0.662,
      "step": 200
    },
    {
      "epoch": 0.0,
      "learning_rate": 9.368401626831595e-05,
      "loss": 0.6356,
      "step": 300
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.790172973019013e-05,
      "loss": 0.6246,
      "step": 400
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.057172492067261e-05,
      "loss": 0.6121,
      "step": 500
    },
    {
      "epoch": 0.01,
      "learning_rate": 7.19933228062164e-05,
      "loss": 0.5909,
      "step": 600
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.25168226947001e-05,
      "loss": 0.6235,
      "step": 700
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.2529197752674375e-05,
      "loss": 0.5756,
      "step": 800
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.2438292944488385e-05,
      "loss": 0.6051,
      "step": 900
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.265617067092651e-05,
      "loss": 0.5944,
      "step": 1000
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.3582284188701738e-05,
      "loss": 0.6004,
      "step": 1100
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.5587165924725604e-05,
      "loss": 0.6087,
      "step": 1200
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.997296773331465e-06,
      "loss": 0.591,
      "step": 1300
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.081774239152941e-06,
      "loss": 0.581,
      "step": 1400
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.0413238324436415e-06,
      "loss": 0.5992,
      "step": 1500
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.0243683979949126e-10,
      "loss": 0.5871,
      "step": 1600
    }
  ],
  "logging_steps": 100,
  "max_steps": 1600,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 6.53458201903104e+16,
  "trial_name": null,
  "trial_params": null
}