{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.5002344116268167,
  "eval_steps": 500,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 4.999956573574533e-05,
      "loss": 0.9781,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.999826295806815e-05,
      "loss": 0.9708,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.999609171222846e-05,
      "loss": 0.9112,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.99930520736578e-05,
      "loss": 0.9353,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.998914414795668e-05,
      "loss": 0.8337,
      "step": 25
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.99843680708909e-05,
      "loss": 0.8133,
      "step": 30
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.997872400838682e-05,
      "loss": 0.8195,
      "step": 35
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.997221215652562e-05,
      "loss": 0.7842,
      "step": 40
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.9964832741536444e-05,
      "loss": 0.7454,
      "step": 45
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.9956586019788584e-05,
      "loss": 0.7732,
      "step": 50
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.9947472277782584e-05,
      "loss": 0.7903,
      "step": 55
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.993749183214021e-05,
      "loss": 0.8053,
      "step": 60
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.992664502959351e-05,
      "loss": 0.7508,
      "step": 65
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.991493224697281e-05,
      "loss": 0.7461,
      "step": 70
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.990235389119352e-05,
      "loss": 0.747,
      "step": 75
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.9888910399242065e-05,
      "loss": 0.734,
      "step": 80
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.987460223816067e-05,
      "loss": 0.736,
      "step": 85
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.985942990503119e-05,
      "loss": 0.7058,
      "step": 90
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.984339392695777e-05,
      "loss": 0.6632,
      "step": 95
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.9826494861048576e-05,
      "loss": 0.7428,
      "step": 100
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.980873329439644e-05,
      "loss": 0.7101,
      "step": 105
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.979010984405842e-05,
      "loss": 0.6687,
      "step": 110
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.9770625157034436e-05,
      "loss": 0.6999,
      "step": 115
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.975027991024473e-05,
      "loss": 0.6625,
      "step": 120
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.972907481050637e-05,
      "loss": 0.7781,
      "step": 125
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.970701059450872e-05,
      "loss": 0.6394,
      "step": 130
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.968408802878778e-05,
      "loss": 0.6739,
      "step": 135
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.9660307909699645e-05,
      "loss": 0.7285,
      "step": 140
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.963567106339276e-05,
      "loss": 0.7181,
      "step": 145
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.961017834577927e-05,
      "loss": 0.6995,
      "step": 150
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.958383064250525e-05,
      "loss": 0.6791,
      "step": 155
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.955662886891995e-05,
      "loss": 0.7085,
      "step": 160
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.952857397004401e-05,
      "loss": 0.6656,
      "step": 165
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.949966692053663e-05,
      "loss": 0.7306,
      "step": 170
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.946990872466164e-05,
      "loss": 0.663,
      "step": 175
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.943930041625272e-05,
      "loss": 0.6459,
      "step": 180
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.940784305867741e-05,
      "loss": 0.6371,
      "step": 185
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.937553774480018e-05,
      "loss": 0.7068,
      "step": 190
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.934238559694448e-05,
      "loss": 0.7062,
      "step": 195
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.9308387766853725e-05,
      "loss": 0.6465,
      "step": 200
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.92735454356513e-05,
      "loss": 0.7055,
      "step": 205
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.9237859813799535e-05,
      "loss": 0.6427,
      "step": 210
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.9201332141057623e-05,
      "loss": 0.6281,
      "step": 215
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.9163963686438575e-05,
      "loss": 0.6499,
      "step": 220
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.912575574816511e-05,
      "loss": 0.6558,
      "step": 225
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.908670965362457e-05,
      "loss": 0.6523,
      "step": 230
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.9046826759322825e-05,
      "loss": 0.6378,
      "step": 235
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.9006108450837095e-05,
      "loss": 0.6463,
      "step": 240
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.8964556142767845e-05,
      "loss": 0.6825,
      "step": 245
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.892217127868965e-05,
      "loss": 0.6576,
      "step": 250
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.8878955331101026e-05,
      "loss": 0.687,
      "step": 255
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.8834909801373264e-05,
      "loss": 0.6567,
      "step": 260
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.879003621969831e-05,
      "loss": 0.6697,
      "step": 265
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.874433614503554e-05,
      "loss": 0.6451,
      "step": 270
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.869781116505768e-05,
      "loss": 0.6601,
      "step": 275
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.8650462896095597e-05,
      "loss": 0.677,
      "step": 280
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.860229298308213e-05,
      "loss": 0.676,
      "step": 285
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.8553303099495e-05,
      "loss": 0.6286,
      "step": 290
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.8503494947298634e-05,
      "loss": 0.6844,
      "step": 295
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.845287025688503e-05,
      "loss": 0.6389,
      "step": 300
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.8401430787013666e-05,
      "loss": 0.641,
      "step": 305
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.8349178324750387e-05,
      "loss": 0.6959,
      "step": 310
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.8296114685405324e-05,
      "loss": 0.6356,
      "step": 315
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.824224171246981e-05,
      "loss": 0.6673,
      "step": 320
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.8187561277552374e-05,
      "loss": 0.5884,
      "step": 325
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.813207528031366e-05,
      "loss": 0.6729,
      "step": 330
    },
    {
      "epoch": 0.63,
      "learning_rate": 4.807578564840051e-05,
      "loss": 0.6228,
      "step": 335
    },
    {
      "epoch": 0.64,
      "learning_rate": 4.801869433737891e-05,
      "loss": 0.6136,
      "step": 340
    },
    {
      "epoch": 0.65,
      "learning_rate": 4.796080333066613e-05,
      "loss": 0.634,
      "step": 345
    },
    {
      "epoch": 0.66,
      "learning_rate": 4.790211463946174e-05,
      "loss": 0.6636,
      "step": 350
    },
    {
      "epoch": 0.67,
      "learning_rate": 4.784263030267781e-05,
      "loss": 0.64,
      "step": 355
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.7782352386868035e-05,
      "loss": 0.6477,
      "step": 360
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.7721282986155945e-05,
      "loss": 0.6591,
      "step": 365
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.7659424222162165e-05,
      "loss": 0.626,
      "step": 370
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.7596778243930694e-05,
      "loss": 0.6154,
      "step": 375
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.7533347227854265e-05,
      "loss": 0.6612,
      "step": 380
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.7469133377598695e-05,
      "loss": 0.6235,
      "step": 385
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.740413892402639e-05,
      "loss": 0.6507,
      "step": 390
    },
    {
      "epoch": 0.74,
      "learning_rate": 4.7338366125118775e-05,
      "loss": 0.6008,
      "step": 395
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.727181726589789e-05,
      "loss": 0.611,
      "step": 400
    },
    {
      "epoch": 0.76,
      "learning_rate": 4.7204494658346996e-05,
      "loss": 0.638,
      "step": 405
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.713640064133025e-05,
      "loss": 0.6045,
      "step": 410
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.706753758051145e-05,
      "loss": 0.6266,
      "step": 415
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.699790786827188e-05,
      "loss": 0.6175,
      "step": 420
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.6927513923627124e-05,
      "loss": 0.6393,
      "step": 425
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.68563581921431e-05,
      "loss": 0.6792,
      "step": 430
    },
    {
      "epoch": 0.82,
      "learning_rate": 4.6784443145851074e-05,
      "loss": 0.6274,
      "step": 435
    },
    {
      "epoch": 0.83,
      "learning_rate": 4.671177128316176e-05,
      "loss": 0.6671,
      "step": 440
    },
    {
      "epoch": 0.83,
      "learning_rate": 4.663834512877853e-05,
      "loss": 0.6933,
      "step": 445
    },
    {
      "epoch": 0.84,
      "learning_rate": 4.6564167233609736e-05,
      "loss": 0.6553,
      "step": 450
    },
    {
      "epoch": 0.85,
      "learning_rate": 4.648924017468003e-05,
      "loss": 0.6261,
      "step": 455
    },
    {
      "epoch": 0.86,
      "learning_rate": 4.6413566555040896e-05,
      "loss": 0.6421,
      "step": 460
    },
    {
      "epoch": 0.87,
      "learning_rate": 4.633714900368018e-05,
      "loss": 0.6464,
      "step": 465
    },
    {
      "epoch": 0.88,
      "learning_rate": 4.625999017543075e-05,
      "loss": 0.6902,
      "step": 470
    },
    {
      "epoch": 0.89,
      "learning_rate": 4.618209275087829e-05,
      "loss": 0.655,
      "step": 475
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.610345943626817e-05,
      "loss": 0.5977,
      "step": 480
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.602409296341141e-05,
      "loss": 0.6449,
      "step": 485
    },
    {
      "epoch": 0.92,
      "learning_rate": 4.5943996089589775e-05,
      "loss": 0.6055,
      "step": 490
    },
    {
      "epoch": 0.93,
      "learning_rate": 4.586317159746001e-05,
      "loss": 0.6475,
      "step": 495
    },
    {
      "epoch": 0.94,
      "learning_rate": 4.5781622294957136e-05,
      "loss": 0.6492,
      "step": 500
    },
    {
      "epoch": 0.95,
      "learning_rate": 4.569935101519692e-05,
      "loss": 0.6209,
      "step": 505
    },
    {
      "epoch": 0.96,
      "learning_rate": 4.561636061637745e-05,
      "loss": 0.6437,
      "step": 510
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.553265398167981e-05,
      "loss": 0.616,
      "step": 515
    },
    {
      "epoch": 0.98,
      "learning_rate": 4.5448234019167945e-05,
      "loss": 0.6512,
      "step": 520
    },
    {
      "epoch": 0.98,
      "learning_rate": 4.536310366168763e-05,
      "loss": 0.6408,
      "step": 525
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.5277265866764565e-05,
      "loss": 0.6349,
      "step": 530
    },
    {
      "epoch": 1.0,
      "learning_rate": 4.519072361650163e-05,
      "loss": 0.6541,
      "step": 535
    },
    {
      "epoch": 1.01,
      "learning_rate": 4.5103479917475286e-05,
      "loss": 0.6365,
      "step": 540
    },
    {
      "epoch": 1.02,
      "learning_rate": 4.501553780063113e-05,
      "loss": 0.5719,
      "step": 545
    },
    {
      "epoch": 1.03,
      "learning_rate": 4.4926900321178595e-05,
      "loss": 0.5938,
      "step": 550
    },
    {
      "epoch": 1.04,
      "learning_rate": 4.483757055848479e-05,
      "loss": 0.6431,
      "step": 555
    },
    {
      "epoch": 1.05,
      "learning_rate": 4.4747551615967534e-05,
      "loss": 0.6333,
      "step": 560
    },
    {
      "epoch": 1.06,
      "learning_rate": 4.4656846620987557e-05,
      "loss": 0.6413,
      "step": 565
    },
    {
      "epoch": 1.07,
      "learning_rate": 4.4565458724739825e-05,
      "loss": 0.639,
      "step": 570
    },
    {
      "epoch": 1.08,
      "learning_rate": 4.447339110214405e-05,
      "loss": 0.6792,
      "step": 575
    },
    {
      "epoch": 1.09,
      "learning_rate": 4.438064695173446e-05,
      "loss": 0.606,
      "step": 580
    },
    {
      "epoch": 1.1,
      "learning_rate": 4.428722949554857e-05,
      "loss": 0.6392,
      "step": 585
    },
    {
      "epoch": 1.11,
      "learning_rate": 4.419314197901537e-05,
      "loss": 0.5808,
      "step": 590
    },
    {
      "epoch": 1.12,
      "learning_rate": 4.4098387670842466e-05,
      "loss": 0.5524,
      "step": 595
    },
    {
      "epoch": 1.13,
      "learning_rate": 4.400296986290258e-05,
      "loss": 0.5939,
      "step": 600
    },
    {
      "epoch": 1.13,
      "learning_rate": 4.390689187011917e-05,
      "loss": 0.6328,
      "step": 605
    },
    {
      "epoch": 1.14,
      "learning_rate": 4.3810157030351276e-05,
      "loss": 0.6542,
      "step": 610
    },
    {
      "epoch": 1.15,
      "learning_rate": 4.371276870427753e-05,
      "loss": 0.5911,
      "step": 615
    },
    {
      "epoch": 1.16,
      "learning_rate": 4.3614730275279457e-05,
      "loss": 0.6093,
      "step": 620
    },
    {
      "epoch": 1.17,
      "learning_rate": 4.351604514932387e-05,
      "loss": 0.5915,
      "step": 625
    },
    {
      "epoch": 1.18,
      "learning_rate": 4.341671675484459e-05,
      "loss": 0.6436,
      "step": 630
    },
    {
      "epoch": 1.19,
      "learning_rate": 4.331674854262331e-05,
      "loss": 0.6547,
      "step": 635
    },
    {
      "epoch": 1.2,
      "learning_rate": 4.321614398566972e-05,
      "loss": 0.6356,
      "step": 640
    },
    {
      "epoch": 1.21,
      "learning_rate": 4.3114906579100853e-05,
      "loss": 0.6458,
      "step": 645
    },
    {
      "epoch": 1.22,
      "learning_rate": 4.301303984001967e-05,
      "loss": 0.6527,
      "step": 650
    },
    {
      "epoch": 1.23,
      "learning_rate": 4.291054730739286e-05,
      "loss": 0.6872,
      "step": 655
    },
    {
      "epoch": 1.24,
      "learning_rate": 4.2807432541927865e-05,
      "loss": 0.5961,
      "step": 660
    },
    {
      "epoch": 1.25,
      "learning_rate": 4.2703699125949245e-05,
      "loss": 0.6227,
      "step": 665
    },
    {
      "epoch": 1.26,
      "learning_rate": 4.259935066327415e-05,
      "loss": 0.6541,
      "step": 670
    },
    {
      "epoch": 1.27,
      "learning_rate": 4.2494390779087187e-05,
      "loss": 0.654,
      "step": 675
    },
    {
      "epoch": 1.28,
      "learning_rate": 4.238882311981441e-05,
      "loss": 0.6677,
      "step": 680
    },
    {
      "epoch": 1.28,
      "learning_rate": 4.228265135299669e-05,
      "loss": 0.568,
      "step": 685
    },
    {
      "epoch": 1.29,
      "learning_rate": 4.2175879167162304e-05,
      "loss": 0.5655,
      "step": 690
    },
    {
      "epoch": 1.3,
      "learning_rate": 4.206851027169871e-05,
      "loss": 0.5781,
      "step": 695
    },
    {
      "epoch": 1.31,
      "learning_rate": 4.196054839672382e-05,
      "loss": 0.599,
      "step": 700
    },
    {
      "epoch": 1.32,
      "learning_rate": 4.1851997292956255e-05,
      "loss": 0.6432,
      "step": 705
    },
    {
      "epoch": 1.33,
      "learning_rate": 4.174286073158516e-05,
      "loss": 0.685,
      "step": 710
    },
    {
      "epoch": 1.34,
      "learning_rate": 4.163314250413913e-05,
      "loss": 0.6159,
      "step": 715
    },
    {
      "epoch": 1.35,
      "learning_rate": 4.152284642235452e-05,
      "loss": 0.6293,
      "step": 720
    },
    {
      "epoch": 1.36,
      "learning_rate": 4.141197631804298e-05,
      "loss": 0.608,
      "step": 725
    },
    {
      "epoch": 1.37,
      "learning_rate": 4.1300536042958354e-05,
      "loss": 0.6286,
      "step": 730
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.118852946866291e-05,
      "loss": 0.6234,
      "step": 735
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.107596048639274e-05,
      "loss": 0.6079,
      "step": 740
    },
    {
      "epoch": 1.4,
      "learning_rate": 4.0962833006922675e-05,
      "loss": 0.6374,
      "step": 745
    },
    {
      "epoch": 1.41,
      "learning_rate": 4.0849150960430356e-05,
      "loss": 0.6089,
      "step": 750
    },
    {
      "epoch": 1.42,
      "learning_rate": 4.0734918296359716e-05,
      "loss": 0.6256,
      "step": 755
    },
    {
      "epoch": 1.43,
      "learning_rate": 4.0620138983283785e-05,
      "loss": 0.59,
      "step": 760
    },
    {
      "epoch": 1.43,
      "learning_rate": 4.050481700876677e-05,
      "loss": 0.5918,
      "step": 765
    },
    {
      "epoch": 1.44,
      "learning_rate": 4.038895637922559e-05,
      "loss": 0.5828,
      "step": 770
    },
    {
      "epoch": 1.45,
      "learning_rate": 4.027256111979063e-05,
      "loss": 0.6087,
      "step": 775
    },
    {
      "epoch": 1.46,
      "learning_rate": 4.015563527416595e-05,
      "loss": 0.6005,
      "step": 780
    },
    {
      "epoch": 1.47,
      "learning_rate": 4.003818290448876e-05,
      "loss": 0.6306,
      "step": 785
    },
    {
      "epoch": 1.48,
      "learning_rate": 3.992020809118832e-05,
      "loss": 0.5853,
      "step": 790
    },
    {
      "epoch": 1.49,
      "learning_rate": 3.980171493284418e-05,
      "loss": 0.6681,
      "step": 795
    },
    {
      "epoch": 1.5,
      "learning_rate": 3.9682707546043785e-05,
      "loss": 0.6093,
      "step": 800
    }
  ],
  "logging_steps": 5,
  "max_steps": 2665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 100,
  "total_flos": 6.268370894910259e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}