{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 10000,
  "global_step": 7414,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.27,
      "learning_rate": 9.444575162494078e-05,
      "loss": 1.6153,
      "step": 1000
    },
    {
      "epoch": 0.54,
      "learning_rate": 6.678323142825601e-05,
      "loss": 1.0533,
      "step": 2000
    },
    {
      "epoch": 0.81,
      "learning_rate": 5.452828012447608e-05,
      "loss": 0.9275,
      "step": 3000
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.4133015871047974,
      "eval_runtime": 198.396,
      "eval_samples_per_second": 5.056,
      "eval_steps_per_second": 0.635,
      "step": 3707
    },
    {
      "epoch": 1.08,
      "learning_rate": 4.722287581247039e-05,
      "loss": 0.7803,
      "step": 4000
    },
    {
      "epoch": 1.35,
      "learning_rate": 4.223742416388575e-05,
      "loss": 0.5688,
      "step": 5000
    },
    {
      "epoch": 1.62,
      "learning_rate": 3.8557316642456684e-05,
      "loss": 0.556,
      "step": 6000
    },
    {
      "epoch": 1.89,
      "learning_rate": 3.56971387408811e-05,
      "loss": 0.5531,
      "step": 7000
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.454437255859375,
      "eval_runtime": 198.5735,
      "eval_samples_per_second": 5.051,
      "eval_steps_per_second": 0.635,
      "step": 7414
    }
  ],
  "logging_steps": 1000,
  "max_steps": 7414,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 2.310114740327547e+17,
  "trial_name": null,
  "trial_params": null
}