{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "global_step": 33746,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 4.925917145735791e-05,
      "loss": 3.8221,
      "step": 500
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.851834291471582e-05,
      "loss": 3.4549,
      "step": 1000
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.777751437207373e-05,
      "loss": 3.3319,
      "step": 1500
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.703668582943164e-05,
      "loss": 3.2774,
      "step": 2000
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.629585728678955e-05,
      "loss": 3.2101,
      "step": 2500
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.555502874414746e-05,
      "loss": 3.1803,
      "step": 3000
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.4814200201505366e-05,
      "loss": 3.1927,
      "step": 3500
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.4073371658863275e-05,
      "loss": 3.1548,
      "step": 4000
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.3332543116221184e-05,
      "loss": 3.1122,
      "step": 4500
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.259171457357909e-05,
      "loss": 3.0989,
      "step": 5000
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.1850886030937e-05,
      "loss": 3.075,
      "step": 5500
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.111005748829491e-05,
      "loss": 3.065,
      "step": 6000
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.036922894565282e-05,
      "loss": 3.0739,
      "step": 6500
    },
    {
      "epoch": 0.41,
      "learning_rate": 3.962840040301073e-05,
      "loss": 3.0578,
      "step": 7000
    },
    {
      "epoch": 0.44,
      "learning_rate": 3.888757186036864e-05,
      "loss": 3.0648,
      "step": 7500
    },
    {
      "epoch": 0.47,
      "learning_rate": 3.814674331772655e-05,
      "loss": 3.0336,
      "step": 8000
    },
    {
      "epoch": 0.5,
      "learning_rate": 3.7405914775084456e-05,
      "loss": 3.0216,
      "step": 8500
    },
    {
      "epoch": 0.53,
      "learning_rate": 3.6665086232442365e-05,
      "loss": 2.9867,
      "step": 9000
    },
    {
      "epoch": 0.56,
      "learning_rate": 3.5924257689800274e-05,
      "loss": 2.9942,
      "step": 9500
    },
    {
      "epoch": 0.59,
      "learning_rate": 3.5183429147158183e-05,
      "loss": 2.9679,
      "step": 10000
    },
    {
      "epoch": 0.62,
      "learning_rate": 3.444260060451609e-05,
      "loss": 2.9864,
      "step": 10500
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.3701772061874e-05,
      "loss": 2.9922,
      "step": 11000
    },
    {
      "epoch": 0.68,
      "learning_rate": 3.296094351923191e-05,
      "loss": 2.9836,
      "step": 11500
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.222011497658982e-05,
      "loss": 2.9676,
      "step": 12000
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.147928643394773e-05,
      "loss": 2.9757,
      "step": 12500
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.073845789130564e-05,
      "loss": 2.9746,
      "step": 13000
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.9997629348663547e-05,
      "loss": 2.9523,
      "step": 13500
    },
    {
      "epoch": 0.83,
      "learning_rate": 2.9256800806021456e-05,
      "loss": 2.9345,
      "step": 14000
    },
    {
      "epoch": 0.86,
      "learning_rate": 2.8515972263379365e-05,
      "loss": 2.9482,
      "step": 14500
    },
    {
      "epoch": 0.89,
      "learning_rate": 2.7775143720737274e-05,
      "loss": 2.9369,
      "step": 15000
    },
    {
      "epoch": 0.92,
      "learning_rate": 2.7034315178095183e-05,
      "loss": 2.9248,
      "step": 15500
    },
    {
      "epoch": 0.95,
      "learning_rate": 2.6293486635453092e-05,
      "loss": 2.893,
      "step": 16000
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.5552658092810998e-05,
      "loss": 2.9236,
      "step": 16500
    },
    {
      "epoch": 1.01,
      "learning_rate": 2.481182955016891e-05,
      "loss": 2.8986,
      "step": 17000
    },
    {
      "epoch": 1.04,
      "learning_rate": 2.407100100752682e-05,
      "loss": 2.8414,
      "step": 17500
    },
    {
      "epoch": 1.07,
      "learning_rate": 2.333017246488473e-05,
      "loss": 2.8639,
      "step": 18000
    },
    {
      "epoch": 1.1,
      "learning_rate": 2.2589343922242637e-05,
      "loss": 2.8561,
      "step": 18500
    },
    {
      "epoch": 1.13,
      "learning_rate": 2.1848515379600546e-05,
      "loss": 2.8553,
      "step": 19000
    },
    {
      "epoch": 1.16,
      "learning_rate": 2.1107686836958456e-05,
      "loss": 2.8641,
      "step": 19500
    },
    {
      "epoch": 1.19,
      "learning_rate": 2.0366858294316365e-05,
      "loss": 2.896,
      "step": 20000
    },
    {
      "epoch": 1.21,
      "learning_rate": 1.9626029751674274e-05,
      "loss": 2.8837,
      "step": 20500
    },
    {
      "epoch": 1.24,
      "learning_rate": 1.8885201209032183e-05,
      "loss": 2.8799,
      "step": 21000
    },
    {
      "epoch": 1.27,
      "learning_rate": 1.8144372666390092e-05,
      "loss": 2.8677,
      "step": 21500
    },
    {
      "epoch": 1.3,
      "learning_rate": 1.7403544123748e-05,
      "loss": 2.8618,
      "step": 22000
    },
    {
      "epoch": 1.33,
      "learning_rate": 1.666271558110591e-05,
      "loss": 2.8484,
      "step": 22500
    },
    {
      "epoch": 1.36,
      "learning_rate": 1.592188703846382e-05,
      "loss": 2.8276,
      "step": 23000
    },
    {
      "epoch": 1.39,
      "learning_rate": 1.518105849582173e-05,
      "loss": 2.8684,
      "step": 23500
    },
    {
      "epoch": 1.42,
      "learning_rate": 1.4440229953179637e-05,
      "loss": 2.8236,
      "step": 24000
    },
    {
      "epoch": 1.45,
      "learning_rate": 1.3699401410537546e-05,
      "loss": 2.8551,
      "step": 24500
    },
    {
      "epoch": 1.48,
      "learning_rate": 1.2958572867895455e-05,
      "loss": 2.8524,
      "step": 25000
    },
    {
      "epoch": 1.51,
      "learning_rate": 1.2217744325253364e-05,
      "loss": 2.8609,
      "step": 25500
    },
    {
      "epoch": 1.54,
      "learning_rate": 1.1476915782611273e-05,
      "loss": 2.839,
      "step": 26000
    },
    {
      "epoch": 1.57,
      "learning_rate": 1.0736087239969182e-05,
      "loss": 2.8376,
      "step": 26500
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.995258697327091e-06,
      "loss": 2.8293,
      "step": 27000
    },
    {
      "epoch": 1.63,
      "learning_rate": 9.254430154685e-06,
      "loss": 2.8262,
      "step": 27500
    },
    {
      "epoch": 1.66,
      "learning_rate": 8.51360161204291e-06,
      "loss": 2.8106,
      "step": 28000
    },
    {
      "epoch": 1.69,
      "learning_rate": 7.772773069400818e-06,
      "loss": 2.8243,
      "step": 28500
    },
    {
      "epoch": 1.72,
      "learning_rate": 7.031944526758727e-06,
      "loss": 2.8452,
      "step": 29000
    },
    {
      "epoch": 1.75,
      "learning_rate": 6.291115984116637e-06,
      "loss": 2.7935,
      "step": 29500
    },
    {
      "epoch": 1.78,
      "learning_rate": 5.550287441474546e-06,
      "loss": 2.8216,
      "step": 30000
    },
    {
      "epoch": 1.81,
      "learning_rate": 4.809458898832455e-06,
      "loss": 2.8083,
      "step": 30500
    },
    {
      "epoch": 1.84,
      "learning_rate": 4.068630356190364e-06,
      "loss": 2.8216,
      "step": 31000
    },
    {
      "epoch": 1.87,
      "learning_rate": 3.3278018135482724e-06,
      "loss": 2.8277,
      "step": 31500
    },
    {
      "epoch": 1.9,
      "learning_rate": 2.586973270906182e-06,
      "loss": 2.82,
      "step": 32000
    },
    {
      "epoch": 1.93,
      "learning_rate": 1.8461447282640907e-06,
      "loss": 2.839,
      "step": 32500
    },
    {
      "epoch": 1.96,
      "learning_rate": 1.1053161856219998e-06,
      "loss": 2.8287,
      "step": 33000
    },
    {
      "epoch": 1.99,
      "learning_rate": 3.644876429799088e-07,
      "loss": 2.8189,
      "step": 33500
    },
    {
      "epoch": 2.0,
      "step": 33746,
      "total_flos": 4.844299814948045e+16,
      "train_loss": 2.9583861975510755,
      "train_runtime": 11802.9622,
      "train_samples_per_second": 11.436,
      "train_steps_per_second": 2.859
    }
  ],
  "max_steps": 33746,
  "num_train_epochs": 2,
  "total_flos": 4.844299814948045e+16,
  "trial_name": null,
  "trial_params": null
}