{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 2500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008,
      "grad_norm": 0.3058140892912027,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.5786,
      "step": 10
    },
    {
      "epoch": 0.016,
      "grad_norm": 0.31255981400696337,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.5032,
      "step": 20
    },
    {
      "epoch": 0.024,
      "grad_norm": 0.16719945295611136,
      "learning_rate": 4.800000000000001e-06,
      "loss": 0.3901,
      "step": 30
    },
    {
      "epoch": 0.032,
      "grad_norm": 0.11095534933859139,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 0.2978,
      "step": 40
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.1114769024399936,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.2631,
      "step": 50
    },
    {
      "epoch": 0.048,
      "grad_norm": 0.10411559733650633,
      "learning_rate": 9.600000000000001e-06,
      "loss": 0.242,
      "step": 60
    },
    {
      "epoch": 0.056,
      "grad_norm": 0.08350193155299954,
      "learning_rate": 1.1200000000000001e-05,
      "loss": 0.2214,
      "step": 70
    },
    {
      "epoch": 0.064,
      "grad_norm": 0.10529290900139675,
      "learning_rate": 1.2800000000000001e-05,
      "loss": 0.2134,
      "step": 80
    },
    {
      "epoch": 0.072,
      "grad_norm": 0.09284266871657494,
      "learning_rate": 1.4400000000000001e-05,
      "loss": 0.2122,
      "step": 90
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.09938443320990606,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.2035,
      "step": 100
    },
    {
      "epoch": 0.088,
      "grad_norm": 0.10023595945326495,
      "learning_rate": 1.76e-05,
      "loss": 0.1841,
      "step": 110
    },
    {
      "epoch": 0.096,
      "grad_norm": 0.0695781552706901,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 0.1877,
      "step": 120
    },
    {
      "epoch": 0.104,
      "grad_norm": 0.07598876239857685,
      "learning_rate": 1.9999781283802247e-05,
      "loss": 0.1868,
      "step": 130
    },
    {
      "epoch": 0.112,
      "grad_norm": 0.08623180966304644,
      "learning_rate": 1.999803161162393e-05,
      "loss": 0.2111,
      "step": 140
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.08260588578713098,
      "learning_rate": 1.999453257340926e-05,
      "loss": 0.1958,
      "step": 150
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.07792179475378579,
      "learning_rate": 1.9989284781388617e-05,
      "loss": 0.1835,
      "step": 160
    },
    {
      "epoch": 0.136,
      "grad_norm": 0.07928527753977362,
      "learning_rate": 1.9982289153773648e-05,
      "loss": 0.1912,
      "step": 170
    },
    {
      "epoch": 0.144,
      "grad_norm": 0.08357416949011726,
      "learning_rate": 1.9973546914596622e-05,
      "loss": 0.1885,
      "step": 180
    },
    {
      "epoch": 0.152,
      "grad_norm": 0.08456641175983287,
      "learning_rate": 1.996305959349627e-05,
      "loss": 0.1841,
      "step": 190
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.0901579451770012,
      "learning_rate": 1.9950829025450116e-05,
      "loss": 0.1806,
      "step": 200
    },
    {
      "epoch": 0.168,
      "grad_norm": 0.07982438004177704,
      "learning_rate": 1.993685735045343e-05,
      "loss": 0.1769,
      "step": 210
    },
    {
      "epoch": 0.176,
      "grad_norm": 0.10398225393987126,
      "learning_rate": 1.9921147013144782e-05,
      "loss": 0.1895,
      "step": 220
    },
    {
      "epoch": 0.184,
      "grad_norm": 0.1099351584849273,
      "learning_rate": 1.9903700762378303e-05,
      "loss": 0.18,
      "step": 230
    },
    {
      "epoch": 0.192,
      "grad_norm": 0.09703206171895983,
      "learning_rate": 1.9884521650742718e-05,
      "loss": 0.17,
      "step": 240
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.09289058414749175,
      "learning_rate": 1.9863613034027224e-05,
      "loss": 0.1699,
      "step": 250
    },
    {
      "epoch": 0.208,
      "grad_norm": 0.08208598708089178,
      "learning_rate": 1.9840978570634338e-05,
      "loss": 0.1843,
      "step": 260
    },
    {
      "epoch": 0.216,
      "grad_norm": 0.08483871139912566,
      "learning_rate": 1.9816622220939762e-05,
      "loss": 0.1756,
      "step": 270
    },
    {
      "epoch": 0.224,
      "grad_norm": 0.08382234577690319,
      "learning_rate": 1.9790548246599447e-05,
      "loss": 0.1746,
      "step": 280
    },
    {
      "epoch": 0.232,
      "grad_norm": 0.11261586530879426,
      "learning_rate": 1.976276120980393e-05,
      "loss": 0.1739,
      "step": 290
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.0777808773898071,
      "learning_rate": 1.973326597248006e-05,
      "loss": 0.1791,
      "step": 300
    },
    {
      "epoch": 0.248,
      "grad_norm": 0.0786352615035203,
      "learning_rate": 1.9702067695440333e-05,
      "loss": 0.1732,
      "step": 310
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.07355004150569275,
      "learning_rate": 1.966917183747987e-05,
      "loss": 0.1737,
      "step": 320
    },
    {
      "epoch": 0.264,
      "grad_norm": 0.08213670035333703,
      "learning_rate": 1.9634584154421316e-05,
      "loss": 0.1777,
      "step": 330
    },
    {
      "epoch": 0.272,
      "grad_norm": 0.07217668674817151,
      "learning_rate": 1.95983106981077e-05,
      "loss": 0.1695,
      "step": 340
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.07669208676566047,
      "learning_rate": 1.9560357815343577e-05,
      "loss": 0.1717,
      "step": 350
    },
    {
      "epoch": 0.288,
      "grad_norm": 0.07736091266235384,
      "learning_rate": 1.9520732146784493e-05,
      "loss": 0.1718,
      "step": 360
    },
    {
      "epoch": 0.296,
      "grad_norm": 0.08315079692157626,
      "learning_rate": 1.947944062577507e-05,
      "loss": 0.1776,
      "step": 370
    },
    {
      "epoch": 0.304,
      "grad_norm": 0.09135194147148734,
      "learning_rate": 1.9436490477135877e-05,
      "loss": 0.173,
      "step": 380
    },
    {
      "epoch": 0.312,
      "grad_norm": 0.0809078717299552,
      "learning_rate": 1.93918892158993e-05,
      "loss": 0.1773,
      "step": 390
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.07427395281421514,
      "learning_rate": 1.934564464599461e-05,
      "loss": 0.17,
      "step": 400
    },
    {
      "epoch": 0.328,
      "grad_norm": 0.07398454431370932,
      "learning_rate": 1.9297764858882516e-05,
      "loss": 0.181,
      "step": 410
    },
    {
      "epoch": 0.336,
      "grad_norm": 0.0792882992648581,
      "learning_rate": 1.924825823213939e-05,
      "loss": 0.1627,
      "step": 420
    },
    {
      "epoch": 0.344,
      "grad_norm": 0.0861604357608397,
      "learning_rate": 1.9197133427991437e-05,
      "loss": 0.1731,
      "step": 430
    },
    {
      "epoch": 0.352,
      "grad_norm": 0.07755055594882805,
      "learning_rate": 1.9144399391799043e-05,
      "loss": 0.1703,
      "step": 440
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.08634385297265851,
      "learning_rate": 1.909006535049163e-05,
      "loss": 0.1695,
      "step": 450
    },
    {
      "epoch": 0.368,
      "grad_norm": 0.07460615095270867,
      "learning_rate": 1.903414081095315e-05,
      "loss": 0.1808,
      "step": 460
    },
    {
      "epoch": 0.376,
      "grad_norm": 0.08366554725021544,
      "learning_rate": 1.897663555835872e-05,
      "loss": 0.1687,
      "step": 470
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.11050801098711051,
      "learning_rate": 1.8917559654462474e-05,
      "loss": 0.1693,
      "step": 480
    },
    {
      "epoch": 0.392,
      "grad_norm": 0.07102922397109013,
      "learning_rate": 1.8856923435837024e-05,
      "loss": 0.1654,
      "step": 490
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.07992253400672722,
      "learning_rate": 1.879473751206489e-05,
      "loss": 0.164,
      "step": 500
    },
    {
      "epoch": 0.408,
      "grad_norm": 0.08055086025032311,
      "learning_rate": 1.8731012763882132e-05,
      "loss": 0.1713,
      "step": 510
    },
    {
      "epoch": 0.416,
      "grad_norm": 0.0737582298851665,
      "learning_rate": 1.8665760341274505e-05,
      "loss": 0.1691,
      "step": 520
    },
    {
      "epoch": 0.424,
      "grad_norm": 0.07526226505268085,
      "learning_rate": 1.859899166152657e-05,
      "loss": 0.1612,
      "step": 530
    },
    {
      "epoch": 0.432,
      "grad_norm": 0.07994952744363151,
      "learning_rate": 1.8530718407223976e-05,
      "loss": 0.1741,
      "step": 540
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.06771882882851786,
      "learning_rate": 1.8460952524209355e-05,
      "loss": 0.1771,
      "step": 550
    },
    {
      "epoch": 0.448,
      "grad_norm": 0.07925796602812565,
      "learning_rate": 1.8389706219492147e-05,
      "loss": 0.1658,
      "step": 560
    },
    {
      "epoch": 0.456,
      "grad_norm": 0.07737563218705418,
      "learning_rate": 1.831699195911272e-05,
      "loss": 0.1713,
      "step": 570
    },
    {
      "epoch": 0.464,
      "grad_norm": 0.07405191205739156,
      "learning_rate": 1.8242822465961177e-05,
      "loss": 0.1687,
      "step": 580
    },
    {
      "epoch": 0.472,
      "grad_norm": 0.08527959453273458,
      "learning_rate": 1.8167210717551224e-05,
      "loss": 0.1645,
      "step": 590
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.08246899769527764,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 0.1606,
      "step": 600
    },
    {
      "epoch": 0.488,
      "grad_norm": 0.07147580637020562,
      "learning_rate": 1.8011713624460608e-05,
      "loss": 0.1628,
      "step": 610
    },
    {
      "epoch": 0.496,
      "grad_norm": 0.07722727076416155,
      "learning_rate": 1.793185548726878e-05,
      "loss": 0.1759,
      "step": 620
    },
    {
      "epoch": 0.504,
      "grad_norm": 0.06844389954410786,
      "learning_rate": 1.785060950503568e-05,
      "loss": 0.1748,
      "step": 630
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.07174329525930123,
      "learning_rate": 1.7767989893455696e-05,
      "loss": 0.1713,
      "step": 640
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.08532370630535416,
      "learning_rate": 1.7684011108568593e-05,
      "loss": 0.1622,
      "step": 650
    },
    {
      "epoch": 0.528,
      "grad_norm": 0.06580211643615225,
      "learning_rate": 1.759868784423009e-05,
      "loss": 0.1593,
      "step": 660
    },
    {
      "epoch": 0.536,
      "grad_norm": 0.07333177241207892,
      "learning_rate": 1.7512035029540887e-05,
      "loss": 0.1611,
      "step": 670
    },
    {
      "epoch": 0.544,
      "grad_norm": 0.08247160155974288,
      "learning_rate": 1.74240678262345e-05,
      "loss": 0.157,
      "step": 680
    },
    {
      "epoch": 0.552,
      "grad_norm": 0.06614899961508676,
      "learning_rate": 1.73348016260244e-05,
      "loss": 0.1635,
      "step": 690
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.08619484121470282,
      "learning_rate": 1.7244252047910893e-05,
      "loss": 0.1675,
      "step": 700
    },
    {
      "epoch": 0.568,
      "grad_norm": 0.08412526181881948,
      "learning_rate": 1.7152434935448257e-05,
      "loss": 0.1562,
      "step": 710
    },
    {
      "epoch": 0.576,
      "grad_norm": 0.07223298445136259,
      "learning_rate": 1.705936635397259e-05,
      "loss": 0.1687,
      "step": 720
    },
    {
      "epoch": 0.584,
      "grad_norm": 0.06857251106754064,
      "learning_rate": 1.6965062587790823e-05,
      "loss": 0.1663,
      "step": 730
    },
    {
      "epoch": 0.592,
      "grad_norm": 0.06696835945973133,
      "learning_rate": 1.6869540137331445e-05,
      "loss": 0.1674,
      "step": 740
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.06686201633689924,
      "learning_rate": 1.6772815716257414e-05,
      "loss": 0.174,
      "step": 750
    },
    {
      "epoch": 0.608,
      "grad_norm": 0.08123286118785028,
      "learning_rate": 1.667490624854173e-05,
      "loss": 0.1667,
      "step": 760
    },
    {
      "epoch": 0.616,
      "grad_norm": 0.14148707567389088,
      "learning_rate": 1.6575828865506246e-05,
      "loss": 0.1682,
      "step": 770
    },
    {
      "epoch": 0.624,
      "grad_norm": 0.06485016340695926,
      "learning_rate": 1.647560090282419e-05,
      "loss": 0.1574,
      "step": 780
    },
    {
      "epoch": 0.632,
      "grad_norm": 0.0867889552062448,
      "learning_rate": 1.63742398974869e-05,
      "loss": 0.1629,
      "step": 790
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.06811973631019821,
      "learning_rate": 1.6271763584735373e-05,
      "loss": 0.163,
      "step": 800
    },
    {
      "epoch": 0.648,
      "grad_norm": 0.08610829160689334,
      "learning_rate": 1.616818989495711e-05,
      "loss": 0.1584,
      "step": 810
    },
    {
      "epoch": 0.656,
      "grad_norm": 0.06829743878657456,
      "learning_rate": 1.6063536950548825e-05,
      "loss": 0.1611,
      "step": 820
    },
    {
      "epoch": 0.664,
      "grad_norm": 0.07996846689663462,
      "learning_rate": 1.595782306274553e-05,
      "loss": 0.1728,
      "step": 830
    },
    {
      "epoch": 0.672,
      "grad_norm": 0.06827784189424038,
      "learning_rate": 1.5851066728416617e-05,
      "loss": 0.1657,
      "step": 840
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.09993992156719474,
      "learning_rate": 1.5743286626829437e-05,
      "loss": 0.1577,
      "step": 850
    },
    {
      "epoch": 0.688,
      "grad_norm": 0.0904528328527498,
      "learning_rate": 1.5634501616380967e-05,
      "loss": 0.1738,
      "step": 860
    },
    {
      "epoch": 0.696,
      "grad_norm": 0.07536916136620567,
      "learning_rate": 1.5524730731298136e-05,
      "loss": 0.1724,
      "step": 870
    },
    {
      "epoch": 0.704,
      "grad_norm": 0.07771163955093588,
      "learning_rate": 1.541399317830738e-05,
      "loss": 0.1587,
      "step": 880
    },
    {
      "epoch": 0.712,
      "grad_norm": 0.06870339623694065,
      "learning_rate": 1.530230833327405e-05,
      "loss": 0.1662,
      "step": 890
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.08541842938568546,
      "learning_rate": 1.5189695737812153e-05,
      "loss": 0.1625,
      "step": 900
    },
    {
      "epoch": 0.728,
      "grad_norm": 0.07174614527960509,
      "learning_rate": 1.5076175095865171e-05,
      "loss": 0.1716,
      "step": 910
    },
    {
      "epoch": 0.736,
      "grad_norm": 0.07173726830388383,
      "learning_rate": 1.4961766270258422e-05,
      "loss": 0.1564,
      "step": 920
    },
    {
      "epoch": 0.744,
      "grad_norm": 0.07774148753609791,
      "learning_rate": 1.4846489279223653e-05,
      "loss": 0.1688,
      "step": 930
    },
    {
      "epoch": 0.752,
      "grad_norm": 0.07047837351321116,
      "learning_rate": 1.473036429289641e-05,
      "loss": 0.1671,
      "step": 940
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.07209116510890862,
      "learning_rate": 1.461341162978688e-05,
      "loss": 0.1636,
      "step": 950
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.0825643122647062,
      "learning_rate": 1.4495651753224706e-05,
      "loss": 0.1589,
      "step": 960
    },
    {
      "epoch": 0.776,
      "grad_norm": 0.09574339039828667,
      "learning_rate": 1.437710526777852e-05,
      "loss": 0.1663,
      "step": 970
    },
    {
      "epoch": 0.784,
      "grad_norm": 0.07179601153688872,
      "learning_rate": 1.4257792915650728e-05,
      "loss": 0.1583,
      "step": 980
    },
    {
      "epoch": 0.792,
      "grad_norm": 0.07652431647542295,
      "learning_rate": 1.4137735573048232e-05,
      "loss": 0.1514,
      "step": 990
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.0686398495128086,
      "learning_rate": 1.4016954246529697e-05,
      "loss": 0.1504,
      "step": 1000
    },
    {
      "epoch": 0.808,
      "grad_norm": 0.06508028906617441,
      "learning_rate": 1.3895470069330003e-05,
      "loss": 0.1599,
      "step": 1010
    },
    {
      "epoch": 0.816,
      "grad_norm": 0.07608940173232373,
      "learning_rate": 1.377330429766256e-05,
      "loss": 0.1612,
      "step": 1020
    },
    {
      "epoch": 0.824,
      "grad_norm": 0.06899267345664216,
      "learning_rate": 1.3650478307000059e-05,
      "loss": 0.1575,
      "step": 1030
    },
    {
      "epoch": 0.832,
      "grad_norm": 0.06256387504627259,
      "learning_rate": 1.3527013588334415e-05,
      "loss": 0.1652,
      "step": 1040
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.07396943401991835,
      "learning_rate": 1.3402931744416432e-05,
      "loss": 0.1538,
      "step": 1050
    },
    {
      "epoch": 0.848,
      "grad_norm": 0.06825533554005977,
      "learning_rate": 1.3278254485975977e-05,
      "loss": 0.16,
      "step": 1060
    },
    {
      "epoch": 0.856,
      "grad_norm": 0.07700315050313282,
      "learning_rate": 1.3153003627923217e-05,
      "loss": 0.1551,
      "step": 1070
    },
    {
      "epoch": 0.864,
      "grad_norm": 0.07759623789607299,
      "learning_rate": 1.3027201085531633e-05,
      "loss": 0.1635,
      "step": 1080
    },
    {
      "epoch": 0.872,
      "grad_norm": 0.07689613377715925,
      "learning_rate": 1.2900868870603502e-05,
      "loss": 0.1587,
      "step": 1090
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.07385835492768326,
      "learning_rate": 1.2774029087618448e-05,
      "loss": 0.1709,
      "step": 1100
    },
    {
      "epoch": 0.888,
      "grad_norm": 0.06043191054467158,
      "learning_rate": 1.2646703929865817e-05,
      "loss": 0.1637,
      "step": 1110
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.07533708016400092,
      "learning_rate": 1.2518915675561482e-05,
      "loss": 0.1682,
      "step": 1120
    },
    {
      "epoch": 0.904,
      "grad_norm": 0.06791483038650707,
      "learning_rate": 1.2390686683949799e-05,
      "loss": 0.1444,
      "step": 1130
    },
    {
      "epoch": 0.912,
      "grad_norm": 0.0815779013214324,
      "learning_rate": 1.2262039391391405e-05,
      "loss": 0.1569,
      "step": 1140
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.07372313932075553,
      "learning_rate": 1.213299630743747e-05,
      "loss": 0.1523,
      "step": 1150
    },
    {
      "epoch": 0.928,
      "grad_norm": 0.08636256799085817,
      "learning_rate": 1.2003580010891214e-05,
      "loss": 0.1563,
      "step": 1160
    },
    {
      "epoch": 0.936,
      "grad_norm": 0.0717205138861145,
      "learning_rate": 1.187381314585725e-05,
      "loss": 0.1647,
      "step": 1170
    },
    {
      "epoch": 0.944,
      "grad_norm": 0.07005503393261057,
      "learning_rate": 1.1743718417779518e-05,
      "loss": 0.1663,
      "step": 1180
    },
    {
      "epoch": 0.952,
      "grad_norm": 0.07064996616100924,
      "learning_rate": 1.1613318589468512e-05,
      "loss": 0.1589,
      "step": 1190
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.0662381053536627,
      "learning_rate": 1.148263647711842e-05,
      "loss": 0.161,
      "step": 1200
    },
    {
      "epoch": 0.968,
      "grad_norm": 0.07589095377012324,
      "learning_rate": 1.135169494631497e-05,
      "loss": 0.1676,
      "step": 1210
    },
    {
      "epoch": 0.976,
      "grad_norm": 0.07324628362518953,
      "learning_rate": 1.1220516908034602e-05,
      "loss": 0.1621,
      "step": 1220
    },
    {
      "epoch": 0.984,
      "grad_norm": 0.07087940558217348,
      "learning_rate": 1.1089125314635727e-05,
      "loss": 0.163,
      "step": 1230
    },
    {
      "epoch": 0.992,
      "grad_norm": 0.08079771757264623,
      "learning_rate": 1.0957543155842703e-05,
      "loss": 0.1594,
      "step": 1240
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.06413004885280083,
      "learning_rate": 1.0825793454723325e-05,
      "loss": 0.1554,
      "step": 1250
    },
    {
      "epoch": 1.008,
      "grad_norm": 0.05476172368624532,
      "learning_rate": 1.0693899263660442e-05,
      "loss": 0.1102,
      "step": 1260
    },
    {
      "epoch": 1.016,
      "grad_norm": 0.05632412500843437,
      "learning_rate": 1.0561883660318456e-05,
      "loss": 0.1028,
      "step": 1270
    },
    {
      "epoch": 1.024,
      "grad_norm": 0.05646598003617287,
      "learning_rate": 1.0429769743605406e-05,
      "loss": 0.1108,
      "step": 1280
    },
    {
      "epoch": 1.032,
      "grad_norm": 0.06842048425083827,
      "learning_rate": 1.0297580629631324e-05,
      "loss": 0.1046,
      "step": 1290
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.0597248090009715,
      "learning_rate": 1.0165339447663586e-05,
      "loss": 0.1035,
      "step": 1300
    },
    {
      "epoch": 1.048,
      "grad_norm": 0.07398432585579974,
      "learning_rate": 1.0033069336079952e-05,
      "loss": 0.0987,
      "step": 1310
    },
    {
      "epoch": 1.056,
      "grad_norm": 0.06505084369381099,
      "learning_rate": 9.900793438320037e-06,
      "loss": 0.0981,
      "step": 1320
    },
    {
      "epoch": 1.064,
      "grad_norm": 0.06284724491257883,
      "learning_rate": 9.768534898835864e-06,
      "loss": 0.1079,
      "step": 1330
    },
    {
      "epoch": 1.072,
      "grad_norm": 0.06844723724817173,
      "learning_rate": 9.636316859042258e-06,
      "loss": 0.1062,
      "step": 1340
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.06837187272099314,
      "learning_rate": 9.504162453267776e-06,
      "loss": 0.1056,
      "step": 1350
    },
    {
      "epoch": 1.088,
      "grad_norm": 0.07008372679481019,
      "learning_rate": 9.372094804706867e-06,
      "loss": 0.1024,
      "step": 1360
    },
    {
      "epoch": 1.096,
      "grad_norm": 0.05573557646176466,
      "learning_rate": 9.24013702137397e-06,
      "loss": 0.1004,
      "step": 1370
    },
    {
      "epoch": 1.104,
      "grad_norm": 0.061630742090732805,
      "learning_rate": 9.108312192060298e-06,
      "loss": 0.0958,
      "step": 1380
    },
    {
      "epoch": 1.112,
      "grad_norm": 0.0626839943409606,
      "learning_rate": 8.97664338229395e-06,
      "loss": 0.1025,
      "step": 1390
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.061119158952486805,
      "learning_rate": 8.84515363030414e-06,
      "loss": 0.0995,
      "step": 1400
    },
    {
      "epoch": 1.1280000000000001,
      "grad_norm": 0.05757909222944341,
      "learning_rate": 8.713865942990143e-06,
      "loss": 0.1027,
      "step": 1410
    },
    {
      "epoch": 1.1360000000000001,
      "grad_norm": 0.06947100250068435,
      "learning_rate": 8.582803291895758e-06,
      "loss": 0.1111,
      "step": 1420
    },
    {
      "epoch": 1.144,
      "grad_norm": 0.0562229609672269,
      "learning_rate": 8.451988609189987e-06,
      "loss": 0.108,
      "step": 1430
    },
    {
      "epoch": 1.152,
      "grad_norm": 0.06930898413364359,
      "learning_rate": 8.321444783654524e-06,
      "loss": 0.1078,
      "step": 1440
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.06571389182101994,
      "learning_rate": 8.191194656678905e-06,
      "loss": 0.0988,
      "step": 1450
    },
    {
      "epoch": 1.168,
      "grad_norm": 0.06275542671231407,
      "learning_rate": 8.06126101826392e-06,
      "loss": 0.0961,
      "step": 1460
    },
    {
      "epoch": 1.176,
      "grad_norm": 0.06782279303820063,
      "learning_rate": 7.931666603034034e-06,
      "loss": 0.1024,
      "step": 1470
    },
    {
      "epoch": 1.184,
      "grad_norm": 0.06578749140882915,
      "learning_rate": 7.80243408625947e-06,
      "loss": 0.0961,
      "step": 1480
    },
    {
      "epoch": 1.192,
      "grad_norm": 0.061803419288976154,
      "learning_rate": 7.673586079888699e-06,
      "loss": 0.1062,
      "step": 1490
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.0717440728997515,
      "learning_rate": 7.545145128592009e-06,
      "loss": 0.0989,
      "step": 1500
    },
    {
      "epoch": 1.208,
      "grad_norm": 0.06490247759799975,
      "learning_rate": 7.4171337058168365e-06,
      "loss": 0.1045,
      "step": 1510
    },
    {
      "epoch": 1.216,
      "grad_norm": 0.06226994133294724,
      "learning_rate": 7.28957420985556e-06,
      "loss": 0.0997,
      "step": 1520
    },
    {
      "epoch": 1.224,
      "grad_norm": 0.07083340324266124,
      "learning_rate": 7.16248895992645e-06,
      "loss": 0.1002,
      "step": 1530
    },
    {
      "epoch": 1.232,
      "grad_norm": 0.07767517880074136,
      "learning_rate": 7.035900192268464e-06,
      "loss": 0.1132,
      "step": 1540
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.06462545486578795,
      "learning_rate": 6.909830056250527e-06,
      "loss": 0.1028,
      "step": 1550
    },
    {
      "epoch": 1.248,
      "grad_norm": 0.0754203548519236,
      "learning_rate": 6.784300610496049e-06,
      "loss": 0.1051,
      "step": 1560
    },
    {
      "epoch": 1.256,
      "grad_norm": 0.06592132565995444,
      "learning_rate": 6.659333819023291e-06,
      "loss": 0.1047,
      "step": 1570
    },
    {
      "epoch": 1.264,
      "grad_norm": 0.06961461995248241,
      "learning_rate": 6.534951547402322e-06,
      "loss": 0.1049,
      "step": 1580
    },
    {
      "epoch": 1.272,
      "grad_norm": 0.06511899962594735,
      "learning_rate": 6.411175558929152e-06,
      "loss": 0.106,
      "step": 1590
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.05916934075813879,
      "learning_rate": 6.2880275108177915e-06,
      "loss": 0.1046,
      "step": 1600
    },
    {
      "epoch": 1.288,
      "grad_norm": 0.07134708360913396,
      "learning_rate": 6.165528950410884e-06,
      "loss": 0.1076,
      "step": 1610
    },
    {
      "epoch": 1.296,
      "grad_norm": 0.06849648011516535,
      "learning_rate": 6.04370131140952e-06,
      "loss": 0.1007,
      "step": 1620
    },
    {
      "epoch": 1.304,
      "grad_norm": 0.0672608182320331,
      "learning_rate": 5.922565910122967e-06,
      "loss": 0.0973,
      "step": 1630
    },
    {
      "epoch": 1.312,
      "grad_norm": 0.07780002144539479,
      "learning_rate": 5.802143941738945e-06,
      "loss": 0.1077,
      "step": 1640
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.06521931109585341,
      "learning_rate": 5.6824564766150724e-06,
      "loss": 0.108,
      "step": 1650
    },
    {
      "epoch": 1.328,
      "grad_norm": 0.0837775649233135,
      "learning_rate": 5.563524456592163e-06,
      "loss": 0.1002,
      "step": 1660
    },
    {
      "epoch": 1.336,
      "grad_norm": 0.06954289449761725,
      "learning_rate": 5.445368691330008e-06,
      "loss": 0.1049,
      "step": 1670
    },
    {
      "epoch": 1.3439999999999999,
      "grad_norm": 0.06577591748805732,
      "learning_rate": 5.328009854666303e-06,
      "loss": 0.0984,
      "step": 1680
    },
    {
      "epoch": 1.3519999999999999,
      "grad_norm": 0.06001848210345022,
      "learning_rate": 5.211468480999304e-06,
      "loss": 0.1049,
      "step": 1690
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 0.05950122818785273,
      "learning_rate": 5.095764961694923e-06,
      "loss": 0.104,
      "step": 1700
    },
    {
      "epoch": 1.3679999999999999,
      "grad_norm": 0.056395399165830855,
      "learning_rate": 4.980919541518796e-06,
      "loss": 0.1005,
      "step": 1710
    },
    {
      "epoch": 1.376,
      "grad_norm": 0.06573253422421312,
      "learning_rate": 4.866952315094088e-06,
      "loss": 0.1009,
      "step": 1720
    },
    {
      "epoch": 1.384,
      "grad_norm": 0.07121035158602729,
      "learning_rate": 4.753883223385467e-06,
      "loss": 0.0983,
      "step": 1730
    },
    {
      "epoch": 1.392,
      "grad_norm": 0.06524819896068156,
      "learning_rate": 4.641732050210032e-06,
      "loss": 0.1051,
      "step": 1740
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.06825918255074036,
      "learning_rate": 4.530518418775734e-06,
      "loss": 0.094,
      "step": 1750
    },
    {
      "epoch": 1.408,
      "grad_norm": 0.07443611934581895,
      "learning_rate": 4.420261788247841e-06,
      "loss": 0.1025,
      "step": 1760
    },
    {
      "epoch": 1.416,
      "grad_norm": 0.06453930101827404,
      "learning_rate": 4.3109814503441894e-06,
      "loss": 0.1023,
      "step": 1770
    },
    {
      "epoch": 1.424,
      "grad_norm": 0.06508573006276362,
      "learning_rate": 4.202696525959667e-06,
      "loss": 0.1042,
      "step": 1780
    },
    {
      "epoch": 1.432,
      "grad_norm": 0.059065263422893345,
      "learning_rate": 4.0954259618206295e-06,
      "loss": 0.109,
      "step": 1790
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.06698134546589794,
      "learning_rate": 3.989188527169749e-06,
      "loss": 0.1031,
      "step": 1800
    },
    {
      "epoch": 1.448,
      "grad_norm": 0.07037002941100785,
      "learning_rate": 3.884002810481959e-06,
      "loss": 0.1106,
      "step": 1810
    },
    {
      "epoch": 1.456,
      "grad_norm": 0.05841985205150354,
      "learning_rate": 3.7798872162119948e-06,
      "loss": 0.0987,
      "step": 1820
    },
    {
      "epoch": 1.464,
      "grad_norm": 0.0593910919321036,
      "learning_rate": 3.676859961574162e-06,
      "loss": 0.0994,
      "step": 1830
    },
    {
      "epoch": 1.472,
      "grad_norm": 0.06578904279209549,
      "learning_rate": 3.5749390733548382e-06,
      "loss": 0.0998,
      "step": 1840
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.06370094131872989,
      "learning_rate": 3.4741423847583134e-06,
      "loss": 0.1008,
      "step": 1850
    },
    {
      "epoch": 1.488,
      "grad_norm": 0.05739668138835314,
      "learning_rate": 3.3744875322865035e-06,
      "loss": 0.1016,
      "step": 1860
    },
    {
      "epoch": 1.496,
      "grad_norm": 0.062215363243071836,
      "learning_rate": 3.2759919526530536e-06,
      "loss": 0.1032,
      "step": 1870
    },
    {
      "epoch": 1.504,
      "grad_norm": 0.0715569328821687,
      "learning_rate": 3.178672879732435e-06,
      "loss": 0.0958,
      "step": 1880
    },
    {
      "epoch": 1.512,
      "grad_norm": 0.05841095850206598,
      "learning_rate": 3.0825473415445073e-06,
      "loss": 0.1002,
      "step": 1890
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.0617717625489719,
      "learning_rate": 2.9876321572751143e-06,
      "loss": 0.1034,
      "step": 1900
    },
    {
      "epoch": 1.528,
      "grad_norm": 0.06062020772334433,
      "learning_rate": 2.8939439343332086e-06,
      "loss": 0.0973,
      "step": 1910
    },
    {
      "epoch": 1.536,
      "grad_norm": 0.059698562886373666,
      "learning_rate": 2.8014990654450325e-06,
      "loss": 0.1006,
      "step": 1920
    },
    {
      "epoch": 1.544,
      "grad_norm": 0.06376657349003535,
      "learning_rate": 2.7103137257858867e-06,
      "loss": 0.0935,
      "step": 1930
    },
    {
      "epoch": 1.552,
      "grad_norm": 0.07743391292616765,
      "learning_rate": 2.6204038701499056e-06,
      "loss": 0.1026,
      "step": 1940
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.06924240453610515,
      "learning_rate": 2.5317852301584642e-06,
      "loss": 0.1053,
      "step": 1950
    },
    {
      "epoch": 1.568,
      "grad_norm": 0.05897566595897626,
      "learning_rate": 2.4444733115075823e-06,
      "loss": 0.1007,
      "step": 1960
    },
    {
      "epoch": 1.576,
      "grad_norm": 0.061747152948674104,
      "learning_rate": 2.3584833912548887e-06,
      "loss": 0.1023,
      "step": 1970
    },
    {
      "epoch": 1.584,
      "grad_norm": 0.06279470086154411,
      "learning_rate": 2.2738305151465646e-06,
      "loss": 0.0967,
      "step": 1980
    },
    {
      "epoch": 1.592,
      "grad_norm": 0.06372313419732084,
      "learning_rate": 2.190529494984782e-06,
      "loss": 0.0937,
      "step": 1990
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.061625905799104846,
      "learning_rate": 2.1085949060360654e-06,
      "loss": 0.0911,
      "step": 2000
    },
    {
      "epoch": 1.608,
      "grad_norm": 0.0678362739569136,
      "learning_rate": 2.0280410844810426e-06,
      "loss": 0.1065,
      "step": 2010
    },
    {
      "epoch": 1.616,
      "grad_norm": 0.06643434332226122,
      "learning_rate": 1.9488821249060297e-06,
      "loss": 0.103,
      "step": 2020
    },
    {
      "epoch": 1.624,
      "grad_norm": 0.06165743807147769,
      "learning_rate": 1.8711318778368792e-06,
      "loss": 0.1019,
      "step": 2030
    },
    {
      "epoch": 1.6320000000000001,
      "grad_norm": 0.07358372056477895,
      "learning_rate": 1.7948039473155553e-06,
      "loss": 0.1041,
      "step": 2040
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.06806526736977143,
      "learning_rate": 1.7199116885197996e-06,
      "loss": 0.1032,
      "step": 2050
    },
    {
      "epoch": 1.6480000000000001,
      "grad_norm": 0.06919391837094059,
      "learning_rate": 1.646468205426377e-06,
      "loss": 0.098,
      "step": 2060
    },
    {
      "epoch": 1.6560000000000001,
      "grad_norm": 0.07710033571374911,
      "learning_rate": 1.5744863485182537e-06,
      "loss": 0.1039,
      "step": 2070
    },
    {
      "epoch": 1.6640000000000001,
      "grad_norm": 0.07419656560471355,
      "learning_rate": 1.5039787125361327e-06,
      "loss": 0.0992,
      "step": 2080
    },
    {
      "epoch": 1.6720000000000002,
      "grad_norm": 0.06441503783003091,
      "learning_rate": 1.4349576342747462e-06,
      "loss": 0.1009,
      "step": 2090
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 0.0587805726462111,
      "learning_rate": 1.367435190424261e-06,
      "loss": 0.1002,
      "step": 2100
    },
    {
      "epoch": 1.688,
      "grad_norm": 0.06818045135041786,
      "learning_rate": 1.3014231954572287e-06,
      "loss": 0.1032,
      "step": 2110
    },
    {
      "epoch": 1.696,
      "grad_norm": 0.06850284991866502,
      "learning_rate": 1.2369331995613664e-06,
      "loss": 0.1013,
      "step": 2120
    },
    {
      "epoch": 1.704,
      "grad_norm": 0.07505851534344943,
      "learning_rate": 1.1739764866186309e-06,
      "loss": 0.095,
      "step": 2130
    },
    {
      "epoch": 1.712,
      "grad_norm": 0.07008959733086773,
      "learning_rate": 1.112564072230863e-06,
      "loss": 0.102,
      "step": 2140
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.05689031064270844,
      "learning_rate": 1.0527067017923654e-06,
      "loss": 0.1026,
      "step": 2150
    },
    {
      "epoch": 1.728,
      "grad_norm": 0.07596542582163048,
      "learning_rate": 9.944148486097793e-07,
      "loss": 0.1034,
      "step": 2160
    },
    {
      "epoch": 1.736,
      "grad_norm": 0.06093771036580793,
      "learning_rate": 9.376987120695547e-07,
      "loss": 0.0997,
      "step": 2170
    },
    {
      "epoch": 1.744,
      "grad_norm": 0.07428382141394303,
      "learning_rate": 8.825682158533555e-07,
      "loss": 0.1082,
      "step": 2180
    },
    {
      "epoch": 1.752,
      "grad_norm": 0.08399394161052269,
      "learning_rate": 8.290330062017015e-07,
      "loss": 0.1052,
      "step": 2190
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.0668059758680316,
      "learning_rate": 7.771024502261526e-07,
      "loss": 0.099,
      "step": 2200
    },
    {
      "epoch": 1.768,
      "grad_norm": 0.0679292033158011,
      "learning_rate": 7.267856342703461e-07,
      "loss": 0.1066,
      "step": 2210
    },
    {
      "epoch": 1.776,
      "grad_norm": 0.058093075805745104,
      "learning_rate": 6.780913623201346e-07,
      "loss": 0.0989,
      "step": 2220
    },
    {
      "epoch": 1.784,
      "grad_norm": 0.06223534910150451,
      "learning_rate": 6.310281544631547e-07,
      "loss": 0.0975,
      "step": 2230
    },
    {
      "epoch": 1.792,
      "grad_norm": 0.0661429754113188,
      "learning_rate": 5.856042453980526e-07,
      "loss": 0.0987,
      "step": 2240
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.061050405248751057,
      "learning_rate": 5.418275829936537e-07,
      "loss": 0.0998,
      "step": 2250
    },
    {
      "epoch": 1.808,
      "grad_norm": 0.056130252404826796,
      "learning_rate": 4.997058268983135e-07,
      "loss": 0.0932,
      "step": 2260
    },
    {
      "epoch": 1.8159999999999998,
      "grad_norm": 0.06066847959463214,
      "learning_rate": 4.592463471997022e-07,
      "loss": 0.0974,
      "step": 2270
    },
    {
      "epoch": 1.8239999999999998,
      "grad_norm": 0.0643399844655628,
      "learning_rate": 4.204562231352516e-07,
      "loss": 0.1057,
      "step": 2280
    },
    {
      "epoch": 1.8319999999999999,
      "grad_norm": 0.060150289880508086,
      "learning_rate": 3.83342241853496e-07,
      "loss": 0.0994,
      "step": 2290
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 0.06796944373259835,
      "learning_rate": 3.4791089722651437e-07,
      "loss": 0.1072,
      "step": 2300
    },
    {
      "epoch": 1.8479999999999999,
      "grad_norm": 0.06759971647919732,
      "learning_rate": 3.1416838871368925e-07,
      "loss": 0.1063,
      "step": 2310
    },
    {
      "epoch": 1.8559999999999999,
      "grad_norm": 0.067835192233575,
      "learning_rate": 2.8212062027698995e-07,
      "loss": 0.1006,
      "step": 2320
    },
    {
      "epoch": 1.8639999999999999,
      "grad_norm": 0.07157931341704744,
      "learning_rate": 2.5177319934793995e-07,
      "loss": 0.1042,
      "step": 2330
    },
    {
      "epoch": 1.8719999999999999,
      "grad_norm": 0.06616867154511055,
      "learning_rate": 2.2313143584648423e-07,
      "loss": 0.0978,
      "step": 2340
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.10047393373201215,
      "learning_rate": 1.9620034125190645e-07,
      "loss": 0.0977,
      "step": 2350
    },
    {
      "epoch": 1.888,
      "grad_norm": 0.06073465869846798,
      "learning_rate": 1.7098462772596302e-07,
      "loss": 0.107,
      "step": 2360
    },
    {
      "epoch": 1.896,
      "grad_norm": 0.0619748402288604,
      "learning_rate": 1.474887072883935e-07,
      "loss": 0.098,
      "step": 2370
    },
    {
      "epoch": 1.904,
      "grad_norm": 0.06634025194054122,
      "learning_rate": 1.2571669104494254e-07,
      "loss": 0.0934,
      "step": 2380
    },
    {
      "epoch": 1.912,
      "grad_norm": 0.07694308017805654,
      "learning_rate": 1.0567238846803995e-07,
      "loss": 0.1058,
      "step": 2390
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.060586005493788085,
      "learning_rate": 8.735930673024806e-08,
      "loss": 0.0929,
      "step": 2400
    },
    {
      "epoch": 1.928,
      "grad_norm": 0.07076099012369173,
      "learning_rate": 7.078065009060941e-08,
      "loss": 0.1053,
      "step": 2410
    },
    {
      "epoch": 1.936,
      "grad_norm": 0.07088076731988013,
      "learning_rate": 5.5939319333998546e-08,
      "loss": 0.0994,
      "step": 2420
    },
    {
      "epoch": 1.944,
      "grad_norm": 0.06859911115828961,
      "learning_rate": 4.2837911263562406e-08,
      "loss": 0.1046,
      "step": 2430
    },
    {
      "epoch": 1.952,
      "grad_norm": 0.09088957264396723,
      "learning_rate": 3.147871824635717e-08,
      "loss": 0.1021,
      "step": 2440
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.06296850339427222,
      "learning_rate": 2.1863727812254653e-08,
      "loss": 0.0992,
      "step": 2450
    },
    {
      "epoch": 1.968,
      "grad_norm": 0.06311334916073906,
      "learning_rate": 1.3994622306173766e-08,
      "loss": 0.1047,
      "step": 2460
    },
    {
      "epoch": 1.976,
      "grad_norm": 0.06846458491142236,
      "learning_rate": 7.872778593728258e-09,
      "loss": 0.102,
      "step": 2470
    },
    {
      "epoch": 1.984,
      "grad_norm": 0.06333619567681512,
      "learning_rate": 3.499267820307184e-09,
      "loss": 0.0979,
      "step": 2480
    },
    {
      "epoch": 1.992,
      "grad_norm": 0.06011655948198505,
      "learning_rate": 8.748552236603758e-10,
      "loss": 0.1016,
      "step": 2490
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.06939915779075108,
      "learning_rate": 0.0,
      "loss": 0.096,
      "step": 2500
    },
    {
      "epoch": 2.0,
      "step": 2500,
      "total_flos": 22262632857600.0,
      "train_loss": 0.140902588391304,
      "train_runtime": 9768.7089,
      "train_samples_per_second": 8.189,
      "train_steps_per_second": 0.256
    }
  ],
  "logging_steps": 10,
  "max_steps": 2500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 22262632857600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}