{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.9574468085106385,
  "eval_steps": 500,
  "global_step": 372,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05319148936170213,
      "grad_norm": 2.453125,
      "learning_rate": 7.935238627346029e-06,
      "loss": 1.0178,
      "step": 5
    },
    {
      "epoch": 0.10638297872340426,
      "grad_norm": 1.90625,
      "learning_rate": 1.7854286911528565e-05,
      "loss": 0.9868,
      "step": 10
    },
    {
      "epoch": 0.1595744680851064,
      "grad_norm": 1.71875,
      "learning_rate": 2.7773335195711106e-05,
      "loss": 0.9207,
      "step": 15
    },
    {
      "epoch": 0.2127659574468085,
      "grad_norm": 1.90625,
      "learning_rate": 3.769238347989364e-05,
      "loss": 0.9234,
      "step": 20
    },
    {
      "epoch": 0.26595744680851063,
      "grad_norm": 1.7109375,
      "learning_rate": 4.7611431764076175e-05,
      "loss": 0.8535,
      "step": 25
    },
    {
      "epoch": 0.3191489361702128,
      "grad_norm": 1.7890625,
      "learning_rate": 5.753048004825872e-05,
      "loss": 0.8737,
      "step": 30
    },
    {
      "epoch": 0.3723404255319149,
      "grad_norm": 1.765625,
      "learning_rate": 6.744952833244124e-05,
      "loss": 0.8314,
      "step": 35
    },
    {
      "epoch": 0.425531914893617,
      "grad_norm": 1.75,
      "learning_rate": 6.941566007038542e-05,
      "loss": 0.8324,
      "step": 40
    },
    {
      "epoch": 0.4787234042553192,
      "grad_norm": 1.5625,
      "learning_rate": 6.934388466345933e-05,
      "loss": 0.8325,
      "step": 45
    },
    {
      "epoch": 0.5319148936170213,
      "grad_norm": 1.484375,
      "learning_rate": 6.921705905677817e-05,
      "loss": 0.7441,
      "step": 50
    },
    {
      "epoch": 0.5851063829787234,
      "grad_norm": 1.4140625,
      "learning_rate": 6.903545231778275e-05,
      "loss": 0.8058,
      "step": 55
    },
    {
      "epoch": 0.6382978723404256,
      "grad_norm": 1.515625,
      "learning_rate": 6.879944973507346e-05,
      "loss": 0.8016,
      "step": 60
    },
    {
      "epoch": 0.6914893617021277,
      "grad_norm": 1.390625,
      "learning_rate": 6.850955200099949e-05,
      "loss": 0.7364,
      "step": 65
    },
    {
      "epoch": 0.7446808510638298,
      "grad_norm": 1.4921875,
      "learning_rate": 6.816637414941277e-05,
      "loss": 0.7176,
      "step": 70
    },
    {
      "epoch": 0.7978723404255319,
      "grad_norm": 1.28125,
      "learning_rate": 6.777064425084002e-05,
      "loss": 0.6915,
      "step": 75
    },
    {
      "epoch": 0.851063829787234,
      "grad_norm": 1.21875,
      "learning_rate": 6.732320186784154e-05,
      "loss": 0.6654,
      "step": 80
    },
    {
      "epoch": 0.9042553191489362,
      "grad_norm": 1.265625,
      "learning_rate": 6.682499627383332e-05,
      "loss": 0.6093,
      "step": 85
    },
    {
      "epoch": 0.9574468085106383,
      "grad_norm": 1.4921875,
      "learning_rate": 6.627708443915185e-05,
      "loss": 0.597,
      "step": 90
    },
    {
      "epoch": 0.9893617021276596,
      "eval_loss": 0.6273989677429199,
      "eval_runtime": 18.5736,
      "eval_samples_per_second": 15.721,
      "eval_steps_per_second": 7.861,
      "step": 93
    },
    {
      "epoch": 1.0106382978723405,
      "grad_norm": 1.046875,
      "learning_rate": 6.56806287886338e-05,
      "loss": 0.5524,
      "step": 95
    },
    {
      "epoch": 1.0638297872340425,
      "grad_norm": 1.5859375,
      "learning_rate": 6.503689473546842e-05,
      "loss": 0.368,
      "step": 100
    },
    {
      "epoch": 1.1170212765957448,
      "grad_norm": 1.0859375,
      "learning_rate": 6.434724799655444e-05,
      "loss": 0.4125,
      "step": 105
    },
    {
      "epoch": 1.1702127659574468,
      "grad_norm": 2.484375,
      "learning_rate": 6.361315169505714e-05,
      "loss": 0.4224,
      "step": 110
    },
    {
      "epoch": 1.2234042553191489,
      "grad_norm": 1.265625,
      "learning_rate": 6.283616325631279e-05,
      "loss": 0.389,
      "step": 115
    },
    {
      "epoch": 1.2765957446808511,
      "grad_norm": 1.59375,
      "learning_rate": 6.201793110366593e-05,
      "loss": 0.4041,
      "step": 120
    },
    {
      "epoch": 1.3297872340425532,
      "grad_norm": 1.2109375,
      "learning_rate": 6.116019116124924e-05,
      "loss": 0.3353,
      "step": 125
    },
    {
      "epoch": 1.3829787234042552,
      "grad_norm": 1.0390625,
      "learning_rate": 6.026476317112594e-05,
      "loss": 0.3782,
      "step": 130
    },
    {
      "epoch": 1.4361702127659575,
      "grad_norm": 1.0546875,
      "learning_rate": 5.933354683260767e-05,
      "loss": 0.3213,
      "step": 135
    },
    {
      "epoch": 1.4893617021276595,
      "grad_norm": 1.203125,
      "learning_rate": 5.836851777193884e-05,
      "loss": 0.3487,
      "step": 140
    },
    {
      "epoch": 1.5425531914893615,
      "grad_norm": 1.171875,
      "learning_rate": 5.7371723350897874e-05,
      "loss": 0.3598,
      "step": 145
    },
    {
      "epoch": 1.5957446808510638,
      "grad_norm": 1.0546875,
      "learning_rate": 5.634527832320745e-05,
      "loss": 0.3477,
      "step": 150
    },
    {
      "epoch": 1.648936170212766,
      "grad_norm": 1.1640625,
      "learning_rate": 5.529136034796919e-05,
      "loss": 0.3577,
      "step": 155
    },
    {
      "epoch": 1.702127659574468,
      "grad_norm": 1.2421875,
      "learning_rate": 5.421220536964117e-05,
      "loss": 0.3336,
      "step": 160
    },
    {
      "epoch": 1.7553191489361701,
      "grad_norm": 0.97265625,
      "learning_rate": 5.311010287435973e-05,
      "loss": 0.3394,
      "step": 165
    },
    {
      "epoch": 1.8085106382978724,
      "grad_norm": 1.0234375,
      "learning_rate": 5.1987391032669876e-05,
      "loss": 0.3255,
      "step": 170
    },
    {
      "epoch": 1.8617021276595744,
      "grad_norm": 1.0078125,
      "learning_rate": 5.084645173896887e-05,
      "loss": 0.3493,
      "step": 175
    },
    {
      "epoch": 1.9148936170212765,
      "grad_norm": 1.0625,
      "learning_rate": 4.968970555818745e-05,
      "loss": 0.3236,
      "step": 180
    },
    {
      "epoch": 1.9680851063829787,
      "grad_norm": 0.92578125,
      "learning_rate": 4.8519606590429275e-05,
      "loss": 0.3471,
      "step": 185
    },
    {
      "epoch": 1.978723404255319,
      "eval_loss": 0.4493549168109894,
      "eval_runtime": 18.4912,
      "eval_samples_per_second": 15.791,
      "eval_steps_per_second": 7.896,
      "step": 186
    },
    {
      "epoch": 2.021276595744681,
      "grad_norm": 0.8125,
      "learning_rate": 4.733863726446376e-05,
      "loss": 0.275,
      "step": 190
    },
    {
      "epoch": 2.074468085106383,
      "grad_norm": 0.6875,
      "learning_rate": 4.614930307111805e-05,
      "loss": 0.1776,
      "step": 195
    },
    {
      "epoch": 2.127659574468085,
      "grad_norm": 0.75390625,
      "learning_rate": 4.49541272477416e-05,
      "loss": 0.1978,
      "step": 200
    },
    {
      "epoch": 2.1808510638297873,
      "grad_norm": 0.8828125,
      "learning_rate": 4.375564542502052e-05,
      "loss": 0.1901,
      "step": 205
    },
    {
      "epoch": 2.2340425531914896,
      "grad_norm": 1.3203125,
      "learning_rate": 4.2556400247498865e-05,
      "loss": 0.1859,
      "step": 210
    },
    {
      "epoch": 2.2872340425531914,
      "grad_norm": 0.73046875,
      "learning_rate": 4.1358935979219476e-05,
      "loss": 0.1814,
      "step": 215
    },
    {
      "epoch": 2.3404255319148937,
      "grad_norm": 0.7109375,
      "learning_rate": 4.016579310592914e-05,
      "loss": 0.1697,
      "step": 220
    },
    {
      "epoch": 2.393617021276596,
      "grad_norm": 0.89453125,
      "learning_rate": 3.8979502945299524e-05,
      "loss": 0.1779,
      "step": 225
    },
    {
      "epoch": 2.4468085106382977,
      "grad_norm": 0.65625,
      "learning_rate": 3.7802582276598663e-05,
      "loss": 0.1608,
      "step": 230
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.55078125,
      "learning_rate": 3.663752800120652e-05,
      "loss": 0.1612,
      "step": 235
    },
    {
      "epoch": 2.5531914893617023,
      "grad_norm": 0.953125,
      "learning_rate": 3.548681184530257e-05,
      "loss": 0.1611,
      "step": 240
    },
    {
      "epoch": 2.6063829787234045,
      "grad_norm": 0.71875,
      "learning_rate": 3.435287511596386e-05,
      "loss": 0.1778,
      "step": 245
    },
    {
      "epoch": 2.6595744680851063,
      "grad_norm": 0.5859375,
      "learning_rate": 3.323812352179894e-05,
      "loss": 0.1653,
      "step": 250
    },
    {
      "epoch": 2.7127659574468086,
      "grad_norm": 0.76953125,
      "learning_rate": 3.214492206910587e-05,
      "loss": 0.1565,
      "step": 255
    },
    {
      "epoch": 2.7659574468085104,
      "grad_norm": 0.6015625,
      "learning_rate": 3.107559004438238e-05,
      "loss": 0.1452,
      "step": 260
    },
    {
      "epoch": 2.8191489361702127,
      "grad_norm": 0.81640625,
      "learning_rate": 3.0032396093833086e-05,
      "loss": 0.1574,
      "step": 265
    },
    {
      "epoch": 2.872340425531915,
      "grad_norm": 0.71484375,
      "learning_rate": 2.9017553410312856e-05,
      "loss": 0.1733,
      "step": 270
    },
    {
      "epoch": 2.925531914893617,
      "grad_norm": 0.6640625,
      "learning_rate": 2.8033215037917425e-05,
      "loss": 0.1406,
      "step": 275
    },
    {
      "epoch": 2.9680851063829787,
      "eval_loss": 0.3713552951812744,
      "eval_runtime": 18.5312,
      "eval_samples_per_second": 15.757,
      "eval_steps_per_second": 7.879,
      "step": 279
    },
    {
      "epoch": 2.978723404255319,
      "grad_norm": 0.75390625,
      "learning_rate": 2.7081469304183043e-05,
      "loss": 0.1598,
      "step": 280
    },
    {
      "epoch": 3.0319148936170213,
      "grad_norm": 0.73046875,
      "learning_rate": 2.616433538958562e-05,
      "loss": 0.1067,
      "step": 285
    },
    {
      "epoch": 3.0851063829787235,
      "grad_norm": 0.5546875,
      "learning_rate": 2.5283759043739265e-05,
      "loss": 0.0771,
      "step": 290
    },
    {
      "epoch": 3.1382978723404253,
      "grad_norm": 0.53515625,
      "learning_rate": 2.4441608457382394e-05,
      "loss": 0.0756,
      "step": 295
    },
    {
      "epoch": 3.1914893617021276,
      "grad_norm": 0.7734375,
      "learning_rate": 2.3639670298909187e-05,
      "loss": 0.0723,
      "step": 300
    },
    {
      "epoch": 3.24468085106383,
      "grad_norm": 0.6171875,
      "learning_rate": 2.287964592385515e-05,
      "loss": 0.076,
      "step": 305
    },
    {
      "epoch": 3.297872340425532,
      "grad_norm": 0.76171875,
      "learning_rate": 2.216314776537855e-05,
      "loss": 0.0883,
      "step": 310
    },
    {
      "epoch": 3.351063829787234,
      "grad_norm": 0.75,
      "learning_rate": 2.149169591339558e-05,
      "loss": 0.0718,
      "step": 315
    },
    {
      "epoch": 3.404255319148936,
      "grad_norm": 0.734375,
      "learning_rate": 2.08667148896267e-05,
      "loss": 0.0757,
      "step": 320
    },
    {
      "epoch": 3.4574468085106385,
      "grad_norm": 0.74609375,
      "learning_rate": 2.028953062539607e-05,
      "loss": 0.0693,
      "step": 325
    },
    {
      "epoch": 3.5106382978723403,
      "grad_norm": 0.6953125,
      "learning_rate": 1.9761367648596e-05,
      "loss": 0.0742,
      "step": 330
    },
    {
      "epoch": 3.5638297872340425,
      "grad_norm": 0.78125,
      "learning_rate": 1.9283346485784222e-05,
      "loss": 0.0692,
      "step": 335
    },
    {
      "epoch": 3.617021276595745,
      "grad_norm": 0.86328125,
      "learning_rate": 1.8856481284925694e-05,
      "loss": 0.0769,
      "step": 340
    },
    {
      "epoch": 3.670212765957447,
      "grad_norm": 0.51171875,
      "learning_rate": 1.8481677663822384e-05,
      "loss": 0.0736,
      "step": 345
    },
    {
      "epoch": 3.723404255319149,
      "grad_norm": 0.57421875,
      "learning_rate": 1.815973078879573e-05,
      "loss": 0.0665,
      "step": 350
    },
    {
      "epoch": 3.776595744680851,
      "grad_norm": 0.7890625,
      "learning_rate": 1.789132368769791e-05,
      "loss": 0.0664,
      "step": 355
    },
    {
      "epoch": 3.829787234042553,
      "grad_norm": 0.56640625,
      "learning_rate": 1.7677025800831022e-05,
      "loss": 0.0634,
      "step": 360
    },
    {
      "epoch": 3.882978723404255,
      "grad_norm": 0.412109375,
      "learning_rate": 1.7517291772848414e-05,
      "loss": 0.0553,
      "step": 365
    },
    {
      "epoch": 3.9361702127659575,
      "grad_norm": 0.498046875,
      "learning_rate": 1.7412460488201273e-05,
      "loss": 0.068,
      "step": 370
    },
    {
      "epoch": 3.9574468085106385,
      "eval_loss": 0.33195412158966064,
      "eval_runtime": 18.482,
      "eval_samples_per_second": 15.799,
      "eval_steps_per_second": 7.9,
      "step": 372
    }
  ],
  "logging_steps": 5,
  "max_steps": 376,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.809962648758911e+18,
  "train_batch_size": 14,
  "trial_name": null,
  "trial_params": null
}