{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 8.0,
  "global_step": 1016,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "learning_rate": 7.352941176470588e-05,
      "loss": 1.8364,
      "step": 25
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00014705882352941175,
      "loss": 1.5206,
      "step": 50
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00022058823529411765,
      "loss": 1.3468,
      "step": 75
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002941176470588235,
      "loss": 1.2031,
      "step": 100
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002924507658643326,
      "loss": 1.164,
      "step": 125
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00028424507658643324,
      "loss": 1.1668,
      "step": 150
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0002760393873085339,
      "loss": 1.1376,
      "step": 175
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0002678336980306345,
      "loss": 1.1364,
      "step": 200
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0002596280087527352,
      "loss": 1.1428,
      "step": 225
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.00025142231947483586,
      "loss": 1.1199,
      "step": 250
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.0002432166301969365,
      "loss": 1.1082,
      "step": 275
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.0002350109409190372,
      "loss": 1.0847,
      "step": 300
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.00022680525164113784,
      "loss": 1.0876,
      "step": 325
    },
    {
      "epoch": 2.76,
      "learning_rate": 0.00021859956236323848,
      "loss": 1.0707,
      "step": 350
    },
    {
      "epoch": 2.95,
      "learning_rate": 0.00021039387308533915,
      "loss": 1.0751,
      "step": 375
    },
    {
      "epoch": 3.15,
      "learning_rate": 0.00020218818380743982,
      "loss": 1.0455,
      "step": 400
    },
    {
      "epoch": 3.35,
      "learning_rate": 0.00019398249452954046,
      "loss": 1.0147,
      "step": 425
    },
    {
      "epoch": 3.54,
      "learning_rate": 0.0001857768052516411,
      "loss": 1.0264,
      "step": 450
    },
    {
      "epoch": 3.74,
      "learning_rate": 0.00017757111597374177,
      "loss": 1.0394,
      "step": 475
    },
    {
      "epoch": 3.94,
      "learning_rate": 0.00016936542669584244,
      "loss": 1.0227,
      "step": 500
    },
    {
      "epoch": 4.13,
      "learning_rate": 0.00016115973741794308,
      "loss": 0.9655,
      "step": 525
    },
    {
      "epoch": 4.33,
      "learning_rate": 0.00015295404814004375,
      "loss": 0.9475,
      "step": 550
    },
    {
      "epoch": 4.53,
      "learning_rate": 0.0001447483588621444,
      "loss": 0.9504,
      "step": 575
    },
    {
      "epoch": 4.72,
      "learning_rate": 0.00013654266958424506,
      "loss": 0.9587,
      "step": 600
    },
    {
      "epoch": 4.92,
      "learning_rate": 0.00012833698030634573,
      "loss": 0.9719,
      "step": 625
    },
    {
      "epoch": 5.12,
      "learning_rate": 0.00012013129102844638,
      "loss": 0.8956,
      "step": 650
    },
    {
      "epoch": 5.31,
      "learning_rate": 0.00011192560175054703,
      "loss": 0.8823,
      "step": 675
    },
    {
      "epoch": 5.51,
      "learning_rate": 0.0001037199124726477,
      "loss": 0.8843,
      "step": 700
    },
    {
      "epoch": 5.71,
      "learning_rate": 9.551422319474836e-05,
      "loss": 0.8957,
      "step": 725
    },
    {
      "epoch": 5.91,
      "learning_rate": 8.7308533916849e-05,
      "loss": 0.8821,
      "step": 750
    },
    {
      "epoch": 6.1,
      "learning_rate": 7.910284463894967e-05,
      "loss": 0.8634,
      "step": 775
    },
    {
      "epoch": 6.3,
      "learning_rate": 7.089715536105033e-05,
      "loss": 0.8226,
      "step": 800
    },
    {
      "epoch": 6.5,
      "learning_rate": 6.269146608315098e-05,
      "loss": 0.8,
      "step": 825
    },
    {
      "epoch": 6.69,
      "learning_rate": 5.448577680525164e-05,
      "loss": 0.8168,
      "step": 850
    },
    {
      "epoch": 6.89,
      "learning_rate": 4.628008752735229e-05,
      "loss": 0.8226,
      "step": 875
    },
    {
      "epoch": 7.09,
      "learning_rate": 3.807439824945295e-05,
      "loss": 0.7947,
      "step": 900
    },
    {
      "epoch": 7.28,
      "learning_rate": 2.9868708971553607e-05,
      "loss": 0.7753,
      "step": 925
    },
    {
      "epoch": 7.48,
      "learning_rate": 2.1663019693654265e-05,
      "loss": 0.7767,
      "step": 950
    },
    {
      "epoch": 7.68,
      "learning_rate": 1.3457330415754924e-05,
      "loss": 0.7665,
      "step": 975
    },
    {
      "epoch": 7.87,
      "learning_rate": 5.251641137855579e-06,
      "loss": 0.7603,
      "step": 1000
    }
  ],
  "max_steps": 1016,
  "num_train_epochs": 8,
  "total_flos": 8.384119188750336e+16,
  "trial_name": null,
  "trial_params": null
}