{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "global_step": 12316,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "learning_rate": 4.7978239688210455e-05,
      "loss": 0.2689,
      "step": 500
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.595241961675869e-05,
      "loss": 0.193,
      "step": 1000
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.392253978564469e-05,
      "loss": 0.183,
      "step": 1500
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.189265995453069e-05,
      "loss": 0.1763,
      "step": 2000
    },
    {
      "epoch": 0.41,
      "learning_rate": 3.986278012341669e-05,
      "loss": 0.1727,
      "step": 2500
    },
    {
      "epoch": 0.49,
      "learning_rate": 3.7832900292302696e-05,
      "loss": 0.1702,
      "step": 3000
    },
    {
      "epoch": 0.57,
      "learning_rate": 3.5803020461188695e-05,
      "loss": 0.1678,
      "step": 3500
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.37731406300747e-05,
      "loss": 0.1645,
      "step": 4000
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.1743260798960706e-05,
      "loss": 0.1629,
      "step": 4500
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.9713380967846704e-05,
      "loss": 0.1608,
      "step": 5000
    },
    {
      "epoch": 0.89,
      "learning_rate": 2.768350113673271e-05,
      "loss": 0.1587,
      "step": 5500
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.565362130561871e-05,
      "loss": 0.1561,
      "step": 6000
    },
    {
      "epoch": 1.06,
      "learning_rate": 2.362374147450471e-05,
      "loss": 0.1453,
      "step": 6500
    },
    {
      "epoch": 1.14,
      "learning_rate": 2.1593861643390713e-05,
      "loss": 0.1399,
      "step": 7000
    },
    {
      "epoch": 1.22,
      "learning_rate": 1.9563981812276715e-05,
      "loss": 0.139,
      "step": 7500
    },
    {
      "epoch": 1.3,
      "learning_rate": 1.7534101981162717e-05,
      "loss": 0.139,
      "step": 8000
    },
    {
      "epoch": 1.38,
      "learning_rate": 1.5504222150048715e-05,
      "loss": 0.1382,
      "step": 8500
    },
    {
      "epoch": 1.46,
      "learning_rate": 1.3474342318934719e-05,
      "loss": 0.1381,
      "step": 9000
    },
    {
      "epoch": 1.54,
      "learning_rate": 1.1444462487820721e-05,
      "loss": 0.1366,
      "step": 9500
    },
    {
      "epoch": 1.62,
      "learning_rate": 9.414582656706723e-06,
      "loss": 0.1365,
      "step": 10000
    },
    {
      "epoch": 1.71,
      "learning_rate": 7.384702825592725e-06,
      "loss": 0.1348,
      "step": 10500
    },
    {
      "epoch": 1.79,
      "learning_rate": 5.358882754140955e-06,
      "loss": 0.1351,
      "step": 11000
    },
    {
      "epoch": 1.87,
      "learning_rate": 3.3290029230269568e-06,
      "loss": 0.1343,
      "step": 11500
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.2991230919129588e-06,
      "loss": 0.1339,
      "step": 12000
    },
    {
      "epoch": 2.0,
      "step": 12316,
      "total_flos": 4101375688441856.0,
      "train_loss": 0.15709904239873834,
      "train_runtime": 1021.7988,
      "train_samples_per_second": 771.383,
      "train_steps_per_second": 12.053
    }
  ],
  "max_steps": 12316,
  "num_train_epochs": 2,
  "total_flos": 4101375688441856.0,
  "trial_name": null,
  "trial_params": null
}