{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9999529153260613,
  "eval_steps": 10000,
  "global_step": 1991,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 9.497739829231542e-05,
      "loss": 0.1028,
      "step": 100
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.995479658463084e-05,
      "loss": 0.1144,
      "step": 200
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.493219487694626e-05,
      "loss": 0.1181,
      "step": 300
    },
    {
      "epoch": 0.2,
      "learning_rate": 7.990959316926167e-05,
      "loss": 0.1163,
      "step": 400
    },
    {
      "epoch": 0.25,
      "learning_rate": 7.48869914615771e-05,
      "loss": 0.1128,
      "step": 500
    },
    {
      "epoch": 0.3,
      "learning_rate": 6.986438975389252e-05,
      "loss": 0.1126,
      "step": 600
    },
    {
      "epoch": 0.35,
      "learning_rate": 6.484178804620794e-05,
      "loss": 0.1125,
      "step": 700
    },
    {
      "epoch": 0.4,
      "learning_rate": 5.981918633852336e-05,
      "loss": 0.1092,
      "step": 800
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.479658463083878e-05,
      "loss": 0.1047,
      "step": 900
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.977398292315419e-05,
      "loss": 0.1046,
      "step": 1000
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.475138121546962e-05,
      "loss": 0.0999,
      "step": 1100
    },
    {
      "epoch": 0.6,
      "learning_rate": 3.972877950778504e-05,
      "loss": 0.0952,
      "step": 1200
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.470617780010045e-05,
      "loss": 0.0928,
      "step": 1300
    },
    {
      "epoch": 0.7,
      "learning_rate": 2.968357609241587e-05,
      "loss": 0.0945,
      "step": 1400
    },
    {
      "epoch": 0.75,
      "learning_rate": 2.466097438473129e-05,
      "loss": 0.0916,
      "step": 1500
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.963837267704671e-05,
      "loss": 0.0914,
      "step": 1600
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.4615770969362131e-05,
      "loss": 0.0917,
      "step": 1700
    },
    {
      "epoch": 0.9,
      "learning_rate": 9.59316926167755e-06,
      "loss": 0.0912,
      "step": 1800
    },
    {
      "epoch": 0.95,
      "learning_rate": 4.5705675539929685e-06,
      "loss": 0.0914,
      "step": 1900
    },
    {
      "epoch": 1.0,
      "step": 1991,
      "total_flos": 4.238662023983923e+16,
      "train_loss": 0.1019569671914423,
      "train_runtime": 12051.5325,
      "train_samples_per_second": 84.59,
      "train_steps_per_second": 0.165
    }
  ],
  "logging_steps": 100,
  "max_steps": 1991,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 4.238662023983923e+16,
  "trial_name": null,
  "trial_params": null
}