{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7072135785007072,
  "eval_steps": 100,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 8.987653272773745e-06,
      "loss": 0.5127,
      "step": 10
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.950680842949738e-06,
      "loss": 0.2702,
      "step": 20
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.88928559430839e-06,
      "loss": 0.2002,
      "step": 30
    },
    {
      "epoch": 0.09,
      "learning_rate": 8.80380442924435e-06,
      "loss": 0.1616,
      "step": 40
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.694706420036745e-06,
      "loss": 0.1754,
      "step": 50
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.562590234845845e-06,
      "loss": 0.184,
      "step": 60
    },
    {
      "epoch": 0.17,
      "learning_rate": 8.408180852560864e-06,
      "loss": 0.141,
      "step": 70
    },
    {
      "epoch": 0.19,
      "learning_rate": 8.232325584525908e-06,
      "loss": 0.1414,
      "step": 80
    },
    {
      "epoch": 0.21,
      "learning_rate": 8.035989424974636e-06,
      "loss": 0.1235,
      "step": 90
    },
    {
      "epoch": 0.24,
      "learning_rate": 7.820249755687773e-06,
      "loss": 0.1389,
      "step": 100
    },
    {
      "epoch": 0.24,
      "eval_accuracy": 0.0,
      "eval_loss": 0.035761188715696335,
      "eval_runtime": 32.8918,
      "eval_samples_per_second": 85.979,
      "eval_steps_per_second": 14.35,
      "step": 100
    },
    {
      "epoch": 0.26,
      "learning_rate": 7.586290433931348e-06,
      "loss": 0.0967,
      "step": 110
    },
    {
      "epoch": 0.28,
      "learning_rate": 7.3353952961177e-06,
      "loss": 0.1373,
      "step": 120
    },
    {
      "epoch": 0.31,
      "learning_rate": 7.068941112837489e-06,
      "loss": 0.0957,
      "step": 130
    },
    {
      "epoch": 0.33,
      "learning_rate": 6.788390033921493e-06,
      "loss": 0.0884,
      "step": 140
    },
    {
      "epoch": 0.35,
      "learning_rate": 6.495281564989449e-06,
      "loss": 0.0918,
      "step": 150
    },
    {
      "epoch": 0.38,
      "learning_rate": 6.191224119514071e-06,
      "loss": 0.085,
      "step": 160
    },
    {
      "epoch": 0.4,
      "learning_rate": 5.877886192757761e-06,
      "loss": 0.1101,
      "step": 170
    },
    {
      "epoch": 0.42,
      "learning_rate": 5.556987206014427e-06,
      "loss": 0.1185,
      "step": 180
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.23028807139807e-06,
      "loss": 0.1112,
      "step": 190
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.899581528953207e-06,
      "loss": 0.104,
      "step": 200
    },
    {
      "epoch": 0.47,
      "eval_accuracy": 0.0,
      "eval_loss": 0.028301144018769264,
      "eval_runtime": 33.4946,
      "eval_samples_per_second": 84.431,
      "eval_steps_per_second": 14.092,
      "step": 200
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.566682309111617e-06,
      "loss": 0.0972,
      "step": 210
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.233417174478286e-06,
      "loss": 0.0902,
      "step": 220
    },
    {
      "epoch": 0.54,
      "learning_rate": 3.901614895591586e-06,
      "loss": 0.0726,
      "step": 230
    },
    {
      "epoch": 0.57,
      "learning_rate": 3.573096215665058e-06,
      "loss": 0.0724,
      "step": 240
    },
    {
      "epoch": 0.59,
      "learning_rate": 3.249663859378603e-06,
      "loss": 0.0974,
      "step": 250
    },
    {
      "epoch": 0.61,
      "learning_rate": 2.9330926405452062e-06,
      "loss": 0.0793,
      "step": 260
    },
    {
      "epoch": 0.64,
      "learning_rate": 2.6251197229366963e-06,
      "loss": 0.0901,
      "step": 270
    },
    {
      "epoch": 0.66,
      "learning_rate": 2.3274350877116486e-06,
      "loss": 0.0731,
      "step": 280
    },
    {
      "epoch": 0.68,
      "learning_rate": 2.0416722597547573e-06,
      "loss": 0.0836,
      "step": 290
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.7693993438163312e-06,
      "loss": 0.0881,
      "step": 300
    },
    {
      "epoch": 0.71,
      "eval_accuracy": 0.0,
      "eval_loss": 0.01625123806297779,
      "eval_runtime": 33.119,
      "eval_samples_per_second": 85.389,
      "eval_steps_per_second": 14.252,
      "step": 300
    }
  ],
  "logging_steps": 10,
  "max_steps": 424,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}