{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6699507389162561,
  "eval_steps": 500,
  "global_step": 34,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.6872,
      "step": 1
    },
    {
      "epoch": 0.1,
      "learning_rate": 2e-05,
      "loss": 1.6916,
      "step": 5
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.9396926207859085e-05,
      "loss": 1.6413,
      "step": 10
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.766044443118978e-05,
      "loss": 1.5492,
      "step": 15
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 1.472,
      "step": 20
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.1736481776669307e-05,
      "loss": 1.4242,
      "step": 25
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.263518223330698e-06,
      "loss": 1.3968,
      "step": 30
    },
    {
      "epoch": 0.67,
      "eval_loss": 1.3765043020248413,
      "eval_runtime": 912.4951,
      "eval_samples_per_second": 25.326,
      "eval_steps_per_second": 0.397,
      "step": 34
    },
    {
      "epoch": 0.67,
      "step": 34,
      "total_flos": 5.175876094263296e+16,
      "train_loss": 1.513783251537996,
      "train_runtime": 28807.9926,
      "train_samples_per_second": 7.216,
      "train_steps_per_second": 0.002
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 5.175876094263296e+16,
  "trial_name": null,
  "trial_params": null
}