{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 536,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0018656716417910447,
      "grad_norm": 2.57972321339612,
      "learning_rate": 1.8518518518518518e-07,
      "loss": 2.092,
      "step": 1
    },
    {
      "epoch": 0.009328358208955223,
      "grad_norm": 2.3735119503905793,
      "learning_rate": 9.259259259259259e-07,
      "loss": 2.0863,
      "step": 5
    },
    {
      "epoch": 0.018656716417910446,
      "grad_norm": 2.569828354184601,
      "learning_rate": 1.8518518518518519e-06,
      "loss": 2.0955,
      "step": 10
    },
    {
      "epoch": 0.027985074626865673,
      "grad_norm": 2.3365878728458847,
      "learning_rate": 2.7777777777777783e-06,
      "loss": 2.078,
      "step": 15
    },
    {
      "epoch": 0.03731343283582089,
      "grad_norm": 2.258292749629048,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 2.0535,
      "step": 20
    },
    {
      "epoch": 0.04664179104477612,
      "grad_norm": 2.046409624248939,
      "learning_rate": 4.62962962962963e-06,
      "loss": 1.9936,
      "step": 25
    },
    {
      "epoch": 0.055970149253731345,
      "grad_norm": 1.7763941617915107,
      "learning_rate": 5.555555555555557e-06,
      "loss": 1.9172,
      "step": 30
    },
    {
      "epoch": 0.06529850746268656,
      "grad_norm": 1.5289482279435747,
      "learning_rate": 6.481481481481482e-06,
      "loss": 1.8216,
      "step": 35
    },
    {
      "epoch": 0.07462686567164178,
      "grad_norm": 1.3374159627357958,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 1.7237,
      "step": 40
    },
    {
      "epoch": 0.08395522388059702,
      "grad_norm": 1.038988897758925,
      "learning_rate": 8.333333333333334e-06,
      "loss": 1.6205,
      "step": 45
    },
    {
      "epoch": 0.09328358208955224,
      "grad_norm": 0.5713243982808286,
      "learning_rate": 9.25925925925926e-06,
      "loss": 1.5364,
      "step": 50
    },
    {
      "epoch": 0.10261194029850747,
      "grad_norm": 0.3049992132098635,
      "learning_rate": 9.999893795201304e-06,
      "loss": 1.491,
      "step": 55
    },
    {
      "epoch": 0.11194029850746269,
      "grad_norm": 0.36148501744582134,
      "learning_rate": 9.996177100962714e-06,
      "loss": 1.473,
      "step": 60
    },
    {
      "epoch": 0.12126865671641791,
      "grad_norm": 0.37327333184682066,
      "learning_rate": 9.987154677711482e-06,
      "loss": 1.4594,
      "step": 65
    },
    {
      "epoch": 0.13059701492537312,
      "grad_norm": 0.31133363324217617,
      "learning_rate": 9.972836106879936e-06,
      "loss": 1.4442,
      "step": 70
    },
    {
      "epoch": 0.13992537313432835,
      "grad_norm": 0.2375327029162037,
      "learning_rate": 9.953236594185396e-06,
      "loss": 1.4258,
      "step": 75
    },
    {
      "epoch": 0.14925373134328357,
      "grad_norm": 0.19998776915472055,
      "learning_rate": 9.928376953482343e-06,
      "loss": 1.4093,
      "step": 80
    },
    {
      "epoch": 0.15858208955223882,
      "grad_norm": 0.19069793139067803,
      "learning_rate": 9.898283584658988e-06,
      "loss": 1.4029,
      "step": 85
    },
    {
      "epoch": 0.16791044776119404,
      "grad_norm": 0.17979433709822593,
      "learning_rate": 9.86298844560169e-06,
      "loss": 1.3876,
      "step": 90
    },
    {
      "epoch": 0.17723880597014927,
      "grad_norm": 0.1750060584120198,
      "learning_rate": 9.822529018257049e-06,
      "loss": 1.3842,
      "step": 95
    },
    {
      "epoch": 0.1865671641791045,
      "grad_norm": 0.17054790759610952,
      "learning_rate": 9.776948268827658e-06,
      "loss": 1.3756,
      "step": 100
    },
    {
      "epoch": 0.1958955223880597,
      "grad_norm": 0.17397761641849066,
      "learning_rate": 9.726294602143807e-06,
      "loss": 1.3544,
      "step": 105
    },
    {
      "epoch": 0.20522388059701493,
      "grad_norm": 0.17494592787959154,
      "learning_rate": 9.670621810259596e-06,
      "loss": 1.338,
      "step": 110
    },
    {
      "epoch": 0.21455223880597016,
      "grad_norm": 0.17874287198232588,
      "learning_rate": 9.609989015328052e-06,
      "loss": 1.3321,
      "step": 115
    },
    {
      "epoch": 0.22388059701492538,
      "grad_norm": 0.18177787677872814,
      "learning_rate": 9.544460606815901e-06,
      "loss": 1.3231,
      "step": 120
    },
    {
      "epoch": 0.2332089552238806,
      "grad_norm": 0.17485139906929326,
      "learning_rate": 9.474106173124667e-06,
      "loss": 1.3029,
      "step": 125
    },
    {
      "epoch": 0.24253731343283583,
      "grad_norm": 0.16541538036070813,
      "learning_rate": 9.399000427690736e-06,
      "loss": 1.2914,
      "step": 130
    },
    {
      "epoch": 0.251865671641791,
      "grad_norm": 0.15475993597407106,
      "learning_rate": 9.31922312964284e-06,
      "loss": 1.2731,
      "step": 135
    },
    {
      "epoch": 0.26119402985074625,
      "grad_norm": 0.14876033685341322,
      "learning_rate": 9.234858999101232e-06,
      "loss": 1.2612,
      "step": 140
    },
    {
      "epoch": 0.27052238805970147,
      "grad_norm": 0.13102260537341828,
      "learning_rate": 9.1459976272085e-06,
      "loss": 1.2406,
      "step": 145
    },
    {
      "epoch": 0.2798507462686567,
      "grad_norm": 0.1231370916125911,
      "learning_rate": 9.052733380987555e-06,
      "loss": 1.2402,
      "step": 150
    },
    {
      "epoch": 0.2891791044776119,
      "grad_norm": 0.11617076992843688,
      "learning_rate": 8.955165303127841e-06,
      "loss": 1.2287,
      "step": 155
    },
    {
      "epoch": 0.29850746268656714,
      "grad_norm": 0.10711292754756604,
      "learning_rate": 8.853397006806183e-06,
      "loss": 1.2293,
      "step": 160
    },
    {
      "epoch": 0.30783582089552236,
      "grad_norm": 0.10583142709305077,
      "learning_rate": 8.747536565653966e-06,
      "loss": 1.2196,
      "step": 165
    },
    {
      "epoch": 0.31716417910447764,
      "grad_norm": 0.10071371091495551,
      "learning_rate": 8.637696398987517e-06,
      "loss": 1.2218,
      "step": 170
    },
    {
      "epoch": 0.32649253731343286,
      "grad_norm": 0.09786904166381197,
      "learning_rate": 8.523993152423522e-06,
      "loss": 1.2076,
      "step": 175
    },
    {
      "epoch": 0.3358208955223881,
      "grad_norm": 0.09308216883502402,
      "learning_rate": 8.406547574006326e-06,
      "loss": 1.2069,
      "step": 180
    },
    {
      "epoch": 0.3451492537313433,
      "grad_norm": 0.09403316911201794,
      "learning_rate": 8.285484385978598e-06,
      "loss": 1.2151,
      "step": 185
    },
    {
      "epoch": 0.35447761194029853,
      "grad_norm": 0.09276385606464647,
      "learning_rate": 8.160932152331587e-06,
      "loss": 1.2033,
      "step": 190
    },
    {
      "epoch": 0.36380597014925375,
      "grad_norm": 0.09044032546865181,
      "learning_rate": 8.03302314227559e-06,
      "loss": 1.2028,
      "step": 195
    },
    {
      "epoch": 0.373134328358209,
      "grad_norm": 0.08960581233300505,
      "learning_rate": 7.90189318977564e-06,
      "loss": 1.2036,
      "step": 200
    },
    {
      "epoch": 0.3824626865671642,
      "grad_norm": 0.08546838672930177,
      "learning_rate": 7.767681549301576e-06,
      "loss": 1.1932,
      "step": 205
    },
    {
      "epoch": 0.3917910447761194,
      "grad_norm": 0.08706831337193889,
      "learning_rate": 7.630530747945672e-06,
      "loss": 1.2016,
      "step": 210
    },
    {
      "epoch": 0.40111940298507465,
      "grad_norm": 0.08501828118277771,
      "learning_rate": 7.490586434064893e-06,
      "loss": 1.1984,
      "step": 215
    },
    {
      "epoch": 0.41044776119402987,
      "grad_norm": 0.08231749758944934,
      "learning_rate": 7.3479972226084925e-06,
      "loss": 1.1934,
      "step": 220
    },
    {
      "epoch": 0.4197761194029851,
      "grad_norm": 0.0846325939740857,
      "learning_rate": 7.202914537295211e-06,
      "loss": 1.1871,
      "step": 225
    },
    {
      "epoch": 0.4291044776119403,
      "grad_norm": 0.0839943062987978,
      "learning_rate": 7.055492449807684e-06,
      "loss": 1.1847,
      "step": 230
    },
    {
      "epoch": 0.43843283582089554,
      "grad_norm": 0.0842974194320567,
      "learning_rate": 6.905887516174827e-06,
      "loss": 1.1823,
      "step": 235
    },
    {
      "epoch": 0.44776119402985076,
      "grad_norm": 0.08246202494295994,
      "learning_rate": 6.754258610515949e-06,
      "loss": 1.1874,
      "step": 240
    },
    {
      "epoch": 0.457089552238806,
      "grad_norm": 0.08059952388104133,
      "learning_rate": 6.60076675632314e-06,
      "loss": 1.1768,
      "step": 245
    },
    {
      "epoch": 0.4664179104477612,
      "grad_norm": 0.08278287209635887,
      "learning_rate": 6.445574955461134e-06,
      "loss": 1.1743,
      "step": 250
    },
    {
      "epoch": 0.47574626865671643,
      "grad_norm": 0.08064613485931339,
      "learning_rate": 6.288848015066211e-06,
      "loss": 1.1787,
      "step": 255
    },
    {
      "epoch": 0.48507462686567165,
      "grad_norm": 0.08402784054638568,
      "learning_rate": 6.130752372527981e-06,
      "loss": 1.1797,
      "step": 260
    },
    {
      "epoch": 0.4944029850746269,
      "grad_norm": 0.07813087594533498,
      "learning_rate": 5.9714559187399094e-06,
      "loss": 1.1814,
      "step": 265
    },
    {
      "epoch": 0.503731343283582,
      "grad_norm": 0.08253282031035683,
      "learning_rate": 5.811127819806277e-06,
      "loss": 1.1767,
      "step": 270
    },
    {
      "epoch": 0.5130597014925373,
      "grad_norm": 0.0795025665014561,
      "learning_rate": 5.649938337394932e-06,
      "loss": 1.1684,
      "step": 275
    },
    {
      "epoch": 0.5223880597014925,
      "grad_norm": 0.08201269451158993,
      "learning_rate": 5.4880586479265774e-06,
      "loss": 1.1704,
      "step": 280
    },
    {
      "epoch": 0.5317164179104478,
      "grad_norm": 0.08039664736174637,
      "learning_rate": 5.325660660792657e-06,
      "loss": 1.1704,
      "step": 285
    },
    {
      "epoch": 0.5410447761194029,
      "grad_norm": 0.08098088631592301,
      "learning_rate": 5.162916835794843e-06,
      "loss": 1.1722,
      "step": 290
    },
    {
      "epoch": 0.5503731343283582,
      "grad_norm": 0.08014102460089276,
      "learning_rate": 5e-06,
      "loss": 1.1748,
      "step": 295
    },
    {
      "epoch": 0.5597014925373134,
      "grad_norm": 0.08067154136929545,
      "learning_rate": 4.837083164205159e-06,
      "loss": 1.1741,
      "step": 300
    },
    {
      "epoch": 0.5690298507462687,
      "grad_norm": 0.07702944221391651,
      "learning_rate": 4.6743393392073435e-06,
      "loss": 1.1734,
      "step": 305
    },
    {
      "epoch": 0.5783582089552238,
      "grad_norm": 0.08366251841352572,
      "learning_rate": 4.511941352073424e-06,
      "loss": 1.1674,
      "step": 310
    },
    {
      "epoch": 0.5876865671641791,
      "grad_norm": 0.08401515307564614,
      "learning_rate": 4.3500616626050705e-06,
      "loss": 1.171,
      "step": 315
    },
    {
      "epoch": 0.5970149253731343,
      "grad_norm": 0.07880234388575032,
      "learning_rate": 4.188872180193723e-06,
      "loss": 1.1617,
      "step": 320
    },
    {
      "epoch": 0.6063432835820896,
      "grad_norm": 0.08075724129202204,
      "learning_rate": 4.028544081260093e-06,
      "loss": 1.1664,
      "step": 325
    },
    {
      "epoch": 0.6156716417910447,
      "grad_norm": 0.08145891878774718,
      "learning_rate": 3.869247627472021e-06,
      "loss": 1.1647,
      "step": 330
    },
    {
      "epoch": 0.625,
      "grad_norm": 0.07981030112455705,
      "learning_rate": 3.7111519849337908e-06,
      "loss": 1.1661,
      "step": 335
    },
    {
      "epoch": 0.6343283582089553,
      "grad_norm": 0.07719220748480114,
      "learning_rate": 3.554425044538868e-06,
      "loss": 1.164,
      "step": 340
    },
    {
      "epoch": 0.6436567164179104,
      "grad_norm": 0.07965079201392798,
      "learning_rate": 3.3992332436768615e-06,
      "loss": 1.1685,
      "step": 345
    },
    {
      "epoch": 0.6529850746268657,
      "grad_norm": 0.07929508580781615,
      "learning_rate": 3.2457413894840516e-06,
      "loss": 1.166,
      "step": 350
    },
    {
      "epoch": 0.6623134328358209,
      "grad_norm": 0.08260668169292941,
      "learning_rate": 3.0941124838251734e-06,
      "loss": 1.1641,
      "step": 355
    },
    {
      "epoch": 0.6716417910447762,
      "grad_norm": 0.07880705452928782,
      "learning_rate": 2.944507550192318e-06,
      "loss": 1.1697,
      "step": 360
    },
    {
      "epoch": 0.6809701492537313,
      "grad_norm": 0.08617336475255008,
      "learning_rate": 2.7970854627047893e-06,
      "loss": 1.1617,
      "step": 365
    },
    {
      "epoch": 0.6902985074626866,
      "grad_norm": 0.08504447838669933,
      "learning_rate": 2.6520027773915075e-06,
      "loss": 1.1694,
      "step": 370
    },
    {
      "epoch": 0.6996268656716418,
      "grad_norm": 0.08177432381677913,
      "learning_rate": 2.509413565935107e-06,
      "loss": 1.1663,
      "step": 375
    },
    {
      "epoch": 0.7089552238805971,
      "grad_norm": 0.08035338660262055,
      "learning_rate": 2.3694692520543293e-06,
      "loss": 1.1617,
      "step": 380
    },
    {
      "epoch": 0.7182835820895522,
      "grad_norm": 0.08099302263307083,
      "learning_rate": 2.2323184506984257e-06,
      "loss": 1.1601,
      "step": 385
    },
    {
      "epoch": 0.7276119402985075,
      "grad_norm": 0.0788199344055389,
      "learning_rate": 2.098106810224362e-06,
      "loss": 1.1678,
      "step": 390
    },
    {
      "epoch": 0.7369402985074627,
      "grad_norm": 0.0810220420611739,
      "learning_rate": 1.9669768577244107e-06,
      "loss": 1.1659,
      "step": 395
    },
    {
      "epoch": 0.746268656716418,
      "grad_norm": 0.07813643594984888,
      "learning_rate": 1.8390678476684143e-06,
      "loss": 1.1619,
      "step": 400
    },
    {
      "epoch": 0.7555970149253731,
      "grad_norm": 0.07787996158898178,
      "learning_rate": 1.7145156140214032e-06,
      "loss": 1.1647,
      "step": 405
    },
    {
      "epoch": 0.7649253731343284,
      "grad_norm": 0.08149237459503167,
      "learning_rate": 1.5934524259936757e-06,
      "loss": 1.1663,
      "step": 410
    },
    {
      "epoch": 0.7742537313432836,
      "grad_norm": 0.08133121141847001,
      "learning_rate": 1.4760068475764789e-06,
      "loss": 1.1481,
      "step": 415
    },
    {
      "epoch": 0.7835820895522388,
      "grad_norm": 0.07796965232583761,
      "learning_rate": 1.3623036010124845e-06,
      "loss": 1.1592,
      "step": 420
    },
    {
      "epoch": 0.792910447761194,
      "grad_norm": 0.07862074938919475,
      "learning_rate": 1.2524634343460335e-06,
      "loss": 1.1537,
      "step": 425
    },
    {
      "epoch": 0.8022388059701493,
      "grad_norm": 0.08047006906879658,
      "learning_rate": 1.1466029931938182e-06,
      "loss": 1.1575,
      "step": 430
    },
    {
      "epoch": 0.8115671641791045,
      "grad_norm": 0.07919282621278656,
      "learning_rate": 1.0448346968721596e-06,
      "loss": 1.1591,
      "step": 435
    },
    {
      "epoch": 0.8208955223880597,
      "grad_norm": 0.08069925871151505,
      "learning_rate": 9.472666190124457e-07,
      "loss": 1.1588,
      "step": 440
    },
    {
      "epoch": 0.8302238805970149,
      "grad_norm": 0.07925111301368296,
      "learning_rate": 8.540023727915015e-07,
      "loss": 1.1552,
      "step": 445
    },
    {
      "epoch": 0.8395522388059702,
      "grad_norm": 0.08107260891150957,
      "learning_rate": 7.651410008987698e-07,
      "loss": 1.1568,
      "step": 450
    },
    {
      "epoch": 0.8488805970149254,
      "grad_norm": 0.07855238487611285,
      "learning_rate": 6.807768703571616e-07,
      "loss": 1.1498,
      "step": 455
    },
    {
      "epoch": 0.8582089552238806,
      "grad_norm": 0.08067373717155321,
      "learning_rate": 6.009995723092655e-07,
      "loss": 1.163,
      "step": 460
    },
    {
      "epoch": 0.8675373134328358,
      "grad_norm": 0.083123312332487,
      "learning_rate": 5.258938268753344e-07,
      "loss": 1.155,
      "step": 465
    },
    {
      "epoch": 0.8768656716417911,
      "grad_norm": 0.07901297859441447,
      "learning_rate": 4.555393931841001e-07,
      "loss": 1.1615,
      "step": 470
    },
    {
      "epoch": 0.8861940298507462,
      "grad_norm": 0.07759270476319681,
      "learning_rate": 3.9001098467194907e-07,
      "loss": 1.1575,
      "step": 475
    },
    {
      "epoch": 0.8955223880597015,
      "grad_norm": 0.07822412070732043,
      "learning_rate": 3.2937818974040637e-07,
      "loss": 1.1597,
      "step": 480
    },
    {
      "epoch": 0.9048507462686567,
      "grad_norm": 0.0799398408165139,
      "learning_rate": 2.737053978561943e-07,
      "loss": 1.1602,
      "step": 485
    },
    {
      "epoch": 0.914179104477612,
      "grad_norm": 0.07777635865631954,
      "learning_rate": 2.2305173117234236e-07,
      "loss": 1.1568,
      "step": 490
    },
    {
      "epoch": 0.9235074626865671,
      "grad_norm": 0.08036060154131985,
      "learning_rate": 1.7747098174295208e-07,
      "loss": 1.1652,
      "step": 495
    },
    {
      "epoch": 0.9328358208955224,
      "grad_norm": 0.08306752546345667,
      "learning_rate": 1.3701155439831249e-07,
      "loss": 1.1558,
      "step": 500
    },
    {
      "epoch": 0.9421641791044776,
      "grad_norm": 0.07992649084819468,
      "learning_rate": 1.017164153410144e-07,
      "loss": 1.1566,
      "step": 505
    },
    {
      "epoch": 0.9514925373134329,
      "grad_norm": 0.07911970141612473,
      "learning_rate": 7.16230465176565e-08,
      "loss": 1.1559,
      "step": 510
    },
    {
      "epoch": 0.960820895522388,
      "grad_norm": 0.0846383351709255,
      "learning_rate": 4.6763405814604926e-08,
      "loss": 1.1514,
      "step": 515
    },
    {
      "epoch": 0.9701492537313433,
      "grad_norm": 0.07934050493191654,
      "learning_rate": 2.7163893120066288e-08,
      "loss": 1.1542,
      "step": 520
    },
    {
      "epoch": 0.9794776119402985,
      "grad_norm": 0.08167448133397126,
      "learning_rate": 1.284532228851998e-08,
      "loss": 1.161,
      "step": 525
    },
    {
      "epoch": 0.9888059701492538,
      "grad_norm": 0.07857080161491098,
      "learning_rate": 3.822899037286276e-09,
      "loss": 1.1579,
      "step": 530
    },
    {
      "epoch": 0.9981343283582089,
      "grad_norm": 0.07847093836951612,
      "learning_rate": 1.0620479869771772e-10,
      "loss": 1.1582,
      "step": 535
    },
    {
      "epoch": 1.0,
      "eval_runtime": 3.2225,
      "eval_samples_per_second": 3.103,
      "eval_steps_per_second": 0.931,
      "step": 536
    },
    {
      "epoch": 1.0,
      "step": 536,
      "total_flos": 555957746663424.0,
      "train_loss": 1.2752919873194908,
      "train_runtime": 16895.3411,
      "train_samples_per_second": 2.029,
      "train_steps_per_second": 0.032
    }
  ],
  "logging_steps": 5,
  "max_steps": 536,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 555957746663424.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}