{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.999958205046044,
  "global_step": 13458,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11,
      "learning_rate": 0.0001,
      "loss": 2.4,
      "step": 500
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001,
      "loss": 2.2965,
      "step": 1000
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001,
      "loss": 2.2586,
      "step": 1500
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001,
      "loss": 2.245,
      "step": 2000
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001,
      "loss": 2.2312,
      "step": 2500
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001,
      "loss": 2.2206,
      "step": 3000
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001,
      "loss": 2.2027,
      "step": 3500
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001,
      "loss": 2.1966,
      "step": 4000
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001,
      "loss": 2.1853,
      "step": 4500
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0001,
      "loss": 2.166,
      "step": 5000
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0001,
      "loss": 2.1599,
      "step": 5500
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0001,
      "loss": 2.1534,
      "step": 6000
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0001,
      "loss": 2.1479,
      "step": 6500
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0001,
      "loss": 2.1441,
      "step": 7000
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0001,
      "loss": 2.1358,
      "step": 7500
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0001,
      "loss": 2.1329,
      "step": 8000
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0001,
      "loss": 2.1304,
      "step": 8500
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.0001,
      "loss": 2.1218,
      "step": 9000
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.0001,
      "loss": 2.1122,
      "step": 9500
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0001,
      "loss": 2.1087,
      "step": 10000
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.0001,
      "loss": 2.1033,
      "step": 10500
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.0001,
      "loss": 2.0944,
      "step": 11000
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.0001,
      "loss": 2.0979,
      "step": 11500
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.0001,
      "loss": 2.0932,
      "step": 12000
    },
    {
      "epoch": 2.79,
      "learning_rate": 0.0001,
      "loss": 2.0974,
      "step": 12500
    },
    {
      "epoch": 2.9,
      "learning_rate": 0.0001,
      "loss": 2.0908,
      "step": 13000
    },
    {
      "epoch": 3.0,
      "step": 13458,
      "total_flos": 2.4893531036709274e+17,
      "train_loss": 2.16356847261068,
      "train_runtime": 35990.7276,
      "train_samples_per_second": 23.932,
      "train_steps_per_second": 0.374
    }
  ],
  "max_steps": 13458,
  "num_train_epochs": 3,
  "total_flos": 2.4893531036709274e+17,
  "trial_name": null,
  "trial_params": null
}