{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.23573785950023574,
  "eval_steps": 100,
  "global_step": 100,
  "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
    }
  ],
  "logging_steps": 10,
  "max_steps": 424,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}