{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9992900248491303,
  "eval_steps": 500,
  "global_step": 2816,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 2.8037,
      "step": 50
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.999851133118102e-05,
      "loss": 2.4343,
      "step": 100
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.9972058436024328e-05,
      "loss": 2.233,
      "step": 150
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.9912624721856506e-05,
      "loss": 2.1259,
      "step": 200
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.9820406755172106e-05,
      "loss": 2.0545,
      "step": 250
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.9695709530580642e-05,
      "loss": 1.9909,
      "step": 300
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.9538945462090903e-05,
      "loss": 1.9676,
      "step": 350
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.9350633019124565e-05,
      "loss": 1.9318,
      "step": 400
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.913139501177033e-05,
      "loss": 1.897,
      "step": 450
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.888195653094972e-05,
      "loss": 1.8821,
      "step": 500
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.860314255030716e-05,
      "loss": 1.8568,
      "step": 550
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.8295875197755593e-05,
      "loss": 1.8416,
      "step": 600
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.796117070570155e-05,
      "loss": 1.8278,
      "step": 650
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.7600136050036265e-05,
      "loss": 1.8107,
      "step": 700
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.7213965289008755e-05,
      "loss": 1.799,
      "step": 750
    },
    {
      "epoch": 0.57,
      "learning_rate": 1.6803935614089426e-05,
      "loss": 1.7788,
      "step": 800
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.637140312588523e-05,
      "loss": 1.7629,
      "step": 850
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.5917798349076846e-05,
      "loss": 1.7656,
      "step": 900
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.5444621501211386e-05,
      "loss": 1.7521,
      "step": 950
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.4953437530998262e-05,
      "loss": 1.738,
      "step": 1000
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.4445870942518226e-05,
      "loss": 1.729,
      "step": 1050
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.3923600422463505e-05,
      "loss": 1.7321,
      "step": 1100
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.3388353288178595e-05,
      "loss": 1.7203,
      "step": 1150
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.284189977486371e-05,
      "loss": 1.7134,
      "step": 1200
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.228604718083506e-05,
      "loss": 1.7147,
      "step": 1250
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.1722633890205434e-05,
      "loss": 1.6945,
      "step": 1300
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.1153523292753974e-05,
      "loss": 1.6996,
      "step": 1350
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.0580597621094166e-05,
      "loss": 1.6959,
      "step": 1400
    },
    {
      "epoch": 1.03,
      "learning_rate": 1.0005751725522469e-05,
      "loss": 1.6188,
      "step": 1450
    },
    {
      "epoch": 1.06,
      "learning_rate": 9.430886807136206e-06,
      "loss": 1.6012,
      "step": 1500
    },
    {
      "epoch": 1.1,
      "learning_rate": 8.857904129947295e-06,
      "loss": 1.6043,
      "step": 1550
    },
    {
      "epoch": 1.14,
      "learning_rate": 8.288698732787898e-06,
      "loss": 1.602,
      "step": 1600
    },
    {
      "epoch": 1.17,
      "learning_rate": 7.725153161804767e-06,
      "loss": 1.604,
      "step": 1650
    },
    {
      "epoch": 1.21,
      "learning_rate": 7.169131244270906e-06,
      "loss": 1.6012,
      "step": 1700
    },
    {
      "epoch": 1.24,
      "learning_rate": 6.6224719243066386e-06,
      "loss": 1.5921,
      "step": 1750
    },
    {
      "epoch": 1.28,
      "learning_rate": 6.086983180897257e-06,
      "loss": 1.6,
      "step": 1800
    },
    {
      "epoch": 1.31,
      "learning_rate": 5.564436048322415e-06,
      "loss": 1.5887,
      "step": 1850
    },
    {
      "epoch": 1.35,
      "learning_rate": 5.056558758773566e-06,
      "loss": 1.59,
      "step": 1900
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.56503102653177e-06,
      "loss": 1.5835,
      "step": 1950
    },
    {
      "epoch": 1.42,
      "learning_rate": 4.091478492609857e-06,
      "loss": 1.5847,
      "step": 2000
    },
    {
      "epoch": 1.46,
      "learning_rate": 3.637467348232414e-06,
      "loss": 1.5934,
      "step": 2050
    },
    {
      "epoch": 1.49,
      "learning_rate": 3.2044991549353832e-06,
      "loss": 1.588,
      "step": 2100
    },
    {
      "epoch": 1.53,
      "learning_rate": 2.7940058784169543e-06,
      "loss": 1.5882,
      "step": 2150
    },
    {
      "epoch": 1.56,
      "learning_rate": 2.4073451525643566e-06,
      "loss": 1.5791,
      "step": 2200
    },
    {
      "epoch": 1.6,
      "learning_rate": 2.045795789319962e-06,
      "loss": 1.5802,
      "step": 2250
    },
    {
      "epoch": 1.63,
      "learning_rate": 1.710553549237043e-06,
      "loss": 1.5806,
      "step": 2300
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.402727186713303e-06,
      "loss": 1.5816,
      "step": 2350
    },
    {
      "epoch": 1.7,
      "learning_rate": 1.1233347829818563e-06,
      "loss": 1.5822,
      "step": 2400
    },
    {
      "epoch": 1.74,
      "learning_rate": 8.733003789876726e-07,
      "loss": 1.5751,
      "step": 2450
    },
    {
      "epoch": 1.77,
      "learning_rate": 6.534509192856453e-07,
      "loss": 1.5708,
      "step": 2500
    },
    {
      "epoch": 1.81,
      "learning_rate": 4.645135170677595e-07,
      "loss": 1.5777,
      "step": 2550
    },
    {
      "epoch": 1.85,
      "learning_rate": 3.0711304936486664e-07,
      "loss": 1.5673,
      "step": 2600
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.8177009037645633e-07,
      "loss": 1.5766,
      "step": 2650
    },
    {
      "epoch": 1.92,
      "learning_rate": 8.889918976358602e-08,
      "loss": 1.5677,
      "step": 2700
    },
    {
      "epoch": 1.95,
      "learning_rate": 2.8807501599226185e-08,
      "loss": 1.5849,
      "step": 2750
    },
    {
      "epoch": 1.99,
      "learning_rate": 1.6937685105011813e-09,
      "loss": 1.5809,
      "step": 2800
    },
    {
      "epoch": 2.0,
      "step": 2816,
      "total_flos": 2.1906737398074573e+17,
      "train_loss": 1.738261958414858,
      "train_runtime": 14007.5678,
      "train_samples_per_second": 16.084,
      "train_steps_per_second": 0.201
    }
  ],
  "logging_steps": 50,
  "max_steps": 2816,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 24000,
  "total_flos": 2.1906737398074573e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}