{
  "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": 1.9980267284282718e-05,
      "loss": 1.1284,
      "step": 1
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.9510565162951538e-05,
      "loss": 1.1279,
      "step": 5
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 1.1117,
      "step": 10
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.5877852522924733e-05,
      "loss": 1.0956,
      "step": 15
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.3090169943749475e-05,
      "loss": 1.0814,
      "step": 20
    },
    {
      "epoch": 0.49,
      "learning_rate": 1e-05,
      "loss": 1.0748,
      "step": 25
    },
    {
      "epoch": 0.59,
      "learning_rate": 6.909830056250527e-06,
      "loss": 1.0705,
      "step": 30
    },
    {
      "epoch": 0.67,
      "eval_loss": 1.066253662109375,
      "eval_runtime": 359.4454,
      "eval_samples_per_second": 64.293,
      "eval_steps_per_second": 1.007,
      "step": 34
    },
    {
      "epoch": 0.67,
      "step": 34,
      "total_flos": 5.175876094263296e+16,
      "train_loss": 1.0919692165711348,
      "train_runtime": 10581.6037,
      "train_samples_per_second": 19.644,
      "train_steps_per_second": 0.005
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 5.175876094263296e+16,
  "trial_name": null,
  "trial_params": null
}