{
  "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": 0.2994475388615314,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.2223,
      "step": 10
    },
    {
      "epoch": 0.016,
      "grad_norm": 0.273631506204062,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.1771,
      "step": 20
    },
    {
      "epoch": 0.024,
      "grad_norm": 0.2130209890157738,
      "learning_rate": 4.800000000000001e-06,
      "loss": 0.1598,
      "step": 30
    },
    {
      "epoch": 0.032,
      "grad_norm": 0.18240027035932016,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 0.1619,
      "step": 40
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.20027988136436473,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.1724,
      "step": 50
    },
    {
      "epoch": 0.048,
      "grad_norm": 0.19349670254659063,
      "learning_rate": 9.600000000000001e-06,
      "loss": 0.1781,
      "step": 60
    },
    {
      "epoch": 0.056,
      "grad_norm": 0.1522942785320451,
      "learning_rate": 1.1200000000000001e-05,
      "loss": 0.1741,
      "step": 70
    },
    {
      "epoch": 0.064,
      "grad_norm": 0.20077878887262207,
      "learning_rate": 1.2800000000000001e-05,
      "loss": 0.1678,
      "step": 80
    },
    {
      "epoch": 0.072,
      "grad_norm": 0.2006526811340805,
      "learning_rate": 1.4400000000000001e-05,
      "loss": 0.1754,
      "step": 90
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.18403850144652611,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.1793,
      "step": 100
    },
    {
      "epoch": 0.088,
      "grad_norm": 0.17392033537978838,
      "learning_rate": 1.76e-05,
      "loss": 0.1669,
      "step": 110
    },
    {
      "epoch": 0.096,
      "grad_norm": 0.15129051337201097,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 0.177,
      "step": 120
    },
    {
      "epoch": 0.104,
      "grad_norm": 0.1686995282450159,
      "learning_rate": 1.9999781283802247e-05,
      "loss": 0.1838,
      "step": 130
    },
    {
      "epoch": 0.112,
      "grad_norm": 0.18454731582348338,
      "learning_rate": 1.999803161162393e-05,
      "loss": 0.2058,
      "step": 140
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.1594563484769184,
      "learning_rate": 1.999453257340926e-05,
      "loss": 0.1953,
      "step": 150
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.16207625262493944,
      "learning_rate": 1.9989284781388617e-05,
      "loss": 0.1871,
      "step": 160
    },
    {
      "epoch": 0.136,
      "grad_norm": 0.15859384233929794,
      "learning_rate": 1.9982289153773648e-05,
      "loss": 0.1948,
      "step": 170
    },
    {
      "epoch": 0.144,
      "grad_norm": 0.17122386425268052,
      "learning_rate": 1.9973546914596622e-05,
      "loss": 0.1954,
      "step": 180
    },
    {
      "epoch": 0.152,
      "grad_norm": 0.16538234415049946,
      "learning_rate": 1.996305959349627e-05,
      "loss": 0.1898,
      "step": 190
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.19838611436297024,
      "learning_rate": 1.9950829025450116e-05,
      "loss": 0.1903,
      "step": 200
    },
    {
      "epoch": 0.168,
      "grad_norm": 0.18275997172338,
      "learning_rate": 1.993685735045343e-05,
      "loss": 0.189,
      "step": 210
    },
    {
      "epoch": 0.176,
      "grad_norm": 0.19605227359376942,
      "learning_rate": 1.9921147013144782e-05,
      "loss": 0.202,
      "step": 220
    },
    {
      "epoch": 0.184,
      "grad_norm": 0.1510786730603492,
      "learning_rate": 1.9903700762378303e-05,
      "loss": 0.1906,
      "step": 230
    },
    {
      "epoch": 0.192,
      "grad_norm": 0.1731755052103561,
      "learning_rate": 1.9884521650742718e-05,
      "loss": 0.1818,
      "step": 240
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.1703147411704783,
      "learning_rate": 1.9863613034027224e-05,
      "loss": 0.1828,
      "step": 250
    },
    {
      "epoch": 0.208,
      "grad_norm": 0.16465949216497772,
      "learning_rate": 1.9840978570634338e-05,
      "loss": 0.1998,
      "step": 260
    },
    {
      "epoch": 0.216,
      "grad_norm": 0.13341671497634322,
      "learning_rate": 1.9816622220939762e-05,
      "loss": 0.1864,
      "step": 270
    },
    {
      "epoch": 0.224,
      "grad_norm": 0.162293542213837,
      "learning_rate": 1.9790548246599447e-05,
      "loss": 0.1892,
      "step": 280
    },
    {
      "epoch": 0.232,
      "grad_norm": 0.15597629673666613,
      "learning_rate": 1.976276120980393e-05,
      "loss": 0.1884,
      "step": 290
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.14793980628985084,
      "learning_rate": 1.973326597248006e-05,
      "loss": 0.1978,
      "step": 300
    },
    {
      "epoch": 0.248,
      "grad_norm": 0.1447727611743318,
      "learning_rate": 1.9702067695440333e-05,
      "loss": 0.1883,
      "step": 310
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.16933785764552192,
      "learning_rate": 1.966917183747987e-05,
      "loss": 0.1898,
      "step": 320
    },
    {
      "epoch": 0.264,
      "grad_norm": 0.1589759149940254,
      "learning_rate": 1.9634584154421316e-05,
      "loss": 0.1949,
      "step": 330
    },
    {
      "epoch": 0.272,
      "grad_norm": 0.12763481414215103,
      "learning_rate": 1.95983106981077e-05,
      "loss": 0.1855,
      "step": 340
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.13722214819739667,
      "learning_rate": 1.9560357815343577e-05,
      "loss": 0.1887,
      "step": 350
    },
    {
      "epoch": 0.288,
      "grad_norm": 0.17592856768775877,
      "learning_rate": 1.9520732146784493e-05,
      "loss": 0.1875,
      "step": 360
    },
    {
      "epoch": 0.296,
      "grad_norm": 0.1540007177537391,
      "learning_rate": 1.947944062577507e-05,
      "loss": 0.1995,
      "step": 370
    },
    {
      "epoch": 0.304,
      "grad_norm": 0.14462148850861567,
      "learning_rate": 1.9436490477135877e-05,
      "loss": 0.1905,
      "step": 380
    },
    {
      "epoch": 0.312,
      "grad_norm": 0.14275084054493534,
      "learning_rate": 1.93918892158993e-05,
      "loss": 0.1946,
      "step": 390
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.13709865630962415,
      "learning_rate": 1.934564464599461e-05,
      "loss": 0.1848,
      "step": 400
    },
    {
      "epoch": 0.328,
      "grad_norm": 0.12851355006510504,
      "learning_rate": 1.9297764858882516e-05,
      "loss": 0.2012,
      "step": 410
    },
    {
      "epoch": 0.336,
      "grad_norm": 0.14422766911430207,
      "learning_rate": 1.924825823213939e-05,
      "loss": 0.1796,
      "step": 420
    },
    {
      "epoch": 0.344,
      "grad_norm": 0.1456420238432456,
      "learning_rate": 1.9197133427991437e-05,
      "loss": 0.1894,
      "step": 430
    },
    {
      "epoch": 0.352,
      "grad_norm": 0.11424505824104754,
      "learning_rate": 1.9144399391799043e-05,
      "loss": 0.1855,
      "step": 440
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.1505170978234406,
      "learning_rate": 1.909006535049163e-05,
      "loss": 0.1826,
      "step": 450
    },
    {
      "epoch": 0.368,
      "grad_norm": 0.1325857585966927,
      "learning_rate": 1.903414081095315e-05,
      "loss": 0.1969,
      "step": 460
    },
    {
      "epoch": 0.376,
      "grad_norm": 0.12049306945186798,
      "learning_rate": 1.897663555835872e-05,
      "loss": 0.1852,
      "step": 470
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.1321067212261413,
      "learning_rate": 1.8917559654462474e-05,
      "loss": 0.1902,
      "step": 480
    },
    {
      "epoch": 0.392,
      "grad_norm": 0.12544038658282392,
      "learning_rate": 1.8856923435837024e-05,
      "loss": 0.1834,
      "step": 490
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.13754099065635406,
      "learning_rate": 1.879473751206489e-05,
      "loss": 0.1777,
      "step": 500
    },
    {
      "epoch": 0.408,
      "grad_norm": 0.14299681112215643,
      "learning_rate": 1.8731012763882132e-05,
      "loss": 0.1891,
      "step": 510
    },
    {
      "epoch": 0.416,
      "grad_norm": 0.12978945402957556,
      "learning_rate": 1.8665760341274505e-05,
      "loss": 0.1838,
      "step": 520
    },
    {
      "epoch": 0.424,
      "grad_norm": 0.12828927955187144,
      "learning_rate": 1.859899166152657e-05,
      "loss": 0.1775,
      "step": 530
    },
    {
      "epoch": 0.432,
      "grad_norm": 0.1399995330504017,
      "learning_rate": 1.8530718407223976e-05,
      "loss": 0.1949,
      "step": 540
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.1201971674290692,
      "learning_rate": 1.8460952524209355e-05,
      "loss": 0.1997,
      "step": 550
    },
    {
      "epoch": 0.448,
      "grad_norm": 0.14220963488029062,
      "learning_rate": 1.8389706219492147e-05,
      "loss": 0.1864,
      "step": 560
    },
    {
      "epoch": 0.456,
      "grad_norm": 0.12393318013758685,
      "learning_rate": 1.831699195911272e-05,
      "loss": 0.1932,
      "step": 570
    },
    {
      "epoch": 0.464,
      "grad_norm": 0.13175301413953197,
      "learning_rate": 1.8242822465961177e-05,
      "loss": 0.1868,
      "step": 580
    },
    {
      "epoch": 0.472,
      "grad_norm": 0.1439474730329765,
      "learning_rate": 1.8167210717551224e-05,
      "loss": 0.1825,
      "step": 590
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.1189834140430123,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 0.1793,
      "step": 600
    },
    {
      "epoch": 0.488,
      "grad_norm": 0.13694513887911383,
      "learning_rate": 1.8011713624460608e-05,
      "loss": 0.1838,
      "step": 610
    },
    {
      "epoch": 0.496,
      "grad_norm": 0.1342792821222079,
      "learning_rate": 1.793185548726878e-05,
      "loss": 0.1981,
      "step": 620
    },
    {
      "epoch": 0.504,
      "grad_norm": 0.12267440816211221,
      "learning_rate": 1.785060950503568e-05,
      "loss": 0.1945,
      "step": 630
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.14191462759384785,
      "learning_rate": 1.7767989893455696e-05,
      "loss": 0.1939,
      "step": 640
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.15143689437873276,
      "learning_rate": 1.7684011108568593e-05,
      "loss": 0.1832,
      "step": 650
    },
    {
      "epoch": 0.528,
      "grad_norm": 0.10997527630360879,
      "learning_rate": 1.759868784423009e-05,
      "loss": 0.1765,
      "step": 660
    },
    {
      "epoch": 0.536,
      "grad_norm": 0.1262528956359292,
      "learning_rate": 1.7512035029540887e-05,
      "loss": 0.1791,
      "step": 670
    },
    {
      "epoch": 0.544,
      "grad_norm": 0.15602459318561945,
      "learning_rate": 1.74240678262345e-05,
      "loss": 0.1743,
      "step": 680
    },
    {
      "epoch": 0.552,
      "grad_norm": 0.13025666149189777,
      "learning_rate": 1.73348016260244e-05,
      "loss": 0.1834,
      "step": 690
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.1387483634701272,
      "learning_rate": 1.7244252047910893e-05,
      "loss": 0.1844,
      "step": 700
    },
    {
      "epoch": 0.568,
      "grad_norm": 0.14296180482072157,
      "learning_rate": 1.7152434935448257e-05,
      "loss": 0.1728,
      "step": 710
    },
    {
      "epoch": 0.576,
      "grad_norm": 0.13975560544538343,
      "learning_rate": 1.705936635397259e-05,
      "loss": 0.1861,
      "step": 720
    },
    {
      "epoch": 0.584,
      "grad_norm": 0.11624329808561513,
      "learning_rate": 1.6965062587790823e-05,
      "loss": 0.1851,
      "step": 730
    },
    {
      "epoch": 0.592,
      "grad_norm": 0.12204929575785449,
      "learning_rate": 1.6869540137331445e-05,
      "loss": 0.1851,
      "step": 740
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.11843883632568544,
      "learning_rate": 1.6772815716257414e-05,
      "loss": 0.1926,
      "step": 750
    },
    {
      "epoch": 0.608,
      "grad_norm": 0.13379905247254648,
      "learning_rate": 1.667490624854173e-05,
      "loss": 0.1825,
      "step": 760
    },
    {
      "epoch": 0.616,
      "grad_norm": 0.14954402393242697,
      "learning_rate": 1.6575828865506246e-05,
      "loss": 0.184,
      "step": 770
    },
    {
      "epoch": 0.624,
      "grad_norm": 0.11855929270795366,
      "learning_rate": 1.647560090282419e-05,
      "loss": 0.1741,
      "step": 780
    },
    {
      "epoch": 0.632,
      "grad_norm": 0.15098593909944216,
      "learning_rate": 1.63742398974869e-05,
      "loss": 0.18,
      "step": 790
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.12622455885460282,
      "learning_rate": 1.6271763584735373e-05,
      "loss": 0.1795,
      "step": 800
    },
    {
      "epoch": 0.648,
      "grad_norm": 0.1214479548976728,
      "learning_rate": 1.616818989495711e-05,
      "loss": 0.1754,
      "step": 810
    },
    {
      "epoch": 0.656,
      "grad_norm": 0.11633961346066299,
      "learning_rate": 1.6063536950548825e-05,
      "loss": 0.1791,
      "step": 820
    },
    {
      "epoch": 0.664,
      "grad_norm": 0.1349935261273476,
      "learning_rate": 1.595782306274553e-05,
      "loss": 0.1901,
      "step": 830
    },
    {
      "epoch": 0.672,
      "grad_norm": 0.12313061321761182,
      "learning_rate": 1.5851066728416617e-05,
      "loss": 0.1813,
      "step": 840
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.16151825468675773,
      "learning_rate": 1.5743286626829437e-05,
      "loss": 0.1754,
      "step": 850
    },
    {
      "epoch": 0.688,
      "grad_norm": 0.14085102248573694,
      "learning_rate": 1.5634501616380967e-05,
      "loss": 0.1885,
      "step": 860
    },
    {
      "epoch": 0.696,
      "grad_norm": 0.14051153835159377,
      "learning_rate": 1.5524730731298136e-05,
      "loss": 0.1883,
      "step": 870
    },
    {
      "epoch": 0.704,
      "grad_norm": 0.10696859105735423,
      "learning_rate": 1.541399317830738e-05,
      "loss": 0.1785,
      "step": 880
    },
    {
      "epoch": 0.712,
      "grad_norm": 0.12489614347746164,
      "learning_rate": 1.530230833327405e-05,
      "loss": 0.1868,
      "step": 890
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.13020128972045483,
      "learning_rate": 1.5189695737812153e-05,
      "loss": 0.1803,
      "step": 900
    },
    {
      "epoch": 0.728,
      "grad_norm": 0.12378887718286205,
      "learning_rate": 1.5076175095865171e-05,
      "loss": 0.1885,
      "step": 910
    },
    {
      "epoch": 0.736,
      "grad_norm": 0.12669683188981912,
      "learning_rate": 1.4961766270258422e-05,
      "loss": 0.1735,
      "step": 920
    },
    {
      "epoch": 0.744,
      "grad_norm": 0.12139646601130864,
      "learning_rate": 1.4846489279223653e-05,
      "loss": 0.1842,
      "step": 930
    },
    {
      "epoch": 0.752,
      "grad_norm": 0.12564036718714786,
      "learning_rate": 1.473036429289641e-05,
      "loss": 0.1862,
      "step": 940
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.12879466675814272,
      "learning_rate": 1.461341162978688e-05,
      "loss": 0.1794,
      "step": 950
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.13118866753606923,
      "learning_rate": 1.4495651753224706e-05,
      "loss": 0.1752,
      "step": 960
    },
    {
      "epoch": 0.776,
      "grad_norm": 0.1397568247577318,
      "learning_rate": 1.437710526777852e-05,
      "loss": 0.1837,
      "step": 970
    },
    {
      "epoch": 0.784,
      "grad_norm": 0.1199748082038019,
      "learning_rate": 1.4257792915650728e-05,
      "loss": 0.1751,
      "step": 980
    },
    {
      "epoch": 0.792,
      "grad_norm": 0.1275568062184644,
      "learning_rate": 1.4137735573048232e-05,
      "loss": 0.1681,
      "step": 990
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.11731254237226522,
      "learning_rate": 1.4016954246529697e-05,
      "loss": 0.1672,
      "step": 1000
    },
    {
      "epoch": 0.808,
      "grad_norm": 0.12803490644945145,
      "learning_rate": 1.3895470069330003e-05,
      "loss": 0.1775,
      "step": 1010
    },
    {
      "epoch": 0.816,
      "grad_norm": 0.13148610169928593,
      "learning_rate": 1.377330429766256e-05,
      "loss": 0.179,
      "step": 1020
    },
    {
      "epoch": 0.824,
      "grad_norm": 0.12498379605499213,
      "learning_rate": 1.3650478307000059e-05,
      "loss": 0.1743,
      "step": 1030
    },
    {
      "epoch": 0.832,
      "grad_norm": 0.10768287920272084,
      "learning_rate": 1.3527013588334415e-05,
      "loss": 0.1798,
      "step": 1040
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.11876441348756149,
      "learning_rate": 1.3402931744416432e-05,
      "loss": 0.1669,
      "step": 1050
    },
    {
      "epoch": 0.848,
      "grad_norm": 0.11670565624337659,
      "learning_rate": 1.3278254485975977e-05,
      "loss": 0.176,
      "step": 1060
    },
    {
      "epoch": 0.856,
      "grad_norm": 0.12614319023396608,
      "learning_rate": 1.3153003627923217e-05,
      "loss": 0.1717,
      "step": 1070
    },
    {
      "epoch": 0.864,
      "grad_norm": 0.15423610893363637,
      "learning_rate": 1.3027201085531633e-05,
      "loss": 0.1787,
      "step": 1080
    },
    {
      "epoch": 0.872,
      "grad_norm": 0.1437966604387281,
      "learning_rate": 1.2900868870603502e-05,
      "loss": 0.1713,
      "step": 1090
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.13194227493290273,
      "learning_rate": 1.2774029087618448e-05,
      "loss": 0.1859,
      "step": 1100
    },
    {
      "epoch": 0.888,
      "grad_norm": 0.11652085362332747,
      "learning_rate": 1.2646703929865817e-05,
      "loss": 0.1798,
      "step": 1110
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.11917839406476669,
      "learning_rate": 1.2518915675561482e-05,
      "loss": 0.1868,
      "step": 1120
    },
    {
      "epoch": 0.904,
      "grad_norm": 0.11813364230838641,
      "learning_rate": 1.2390686683949799e-05,
      "loss": 0.1575,
      "step": 1130
    },
    {
      "epoch": 0.912,
      "grad_norm": 0.1196110875735261,
      "learning_rate": 1.2262039391391405e-05,
      "loss": 0.17,
      "step": 1140
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.12300092078788795,
      "learning_rate": 1.213299630743747e-05,
      "loss": 0.1682,
      "step": 1150
    },
    {
      "epoch": 0.928,
      "grad_norm": 0.1208425846118018,
      "learning_rate": 1.2003580010891214e-05,
      "loss": 0.1703,
      "step": 1160
    },
    {
      "epoch": 0.936,
      "grad_norm": 0.12083725425562747,
      "learning_rate": 1.187381314585725e-05,
      "loss": 0.1797,
      "step": 1170
    },
    {
      "epoch": 0.944,
      "grad_norm": 0.1178408143433832,
      "learning_rate": 1.1743718417779518e-05,
      "loss": 0.1792,
      "step": 1180
    },
    {
      "epoch": 0.952,
      "grad_norm": 0.11740271053188309,
      "learning_rate": 1.1613318589468512e-05,
      "loss": 0.1726,
      "step": 1190
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.1090840603269972,
      "learning_rate": 1.148263647711842e-05,
      "loss": 0.1756,
      "step": 1200
    },
    {
      "epoch": 0.968,
      "grad_norm": 0.124940945129332,
      "learning_rate": 1.135169494631497e-05,
      "loss": 0.1837,
      "step": 1210
    },
    {
      "epoch": 0.976,
      "grad_norm": 0.1257424082327308,
      "learning_rate": 1.1220516908034602e-05,
      "loss": 0.1785,
      "step": 1220
    },
    {
      "epoch": 0.984,
      "grad_norm": 0.11430280573700291,
      "learning_rate": 1.1089125314635727e-05,
      "loss": 0.1731,
      "step": 1230
    },
    {
      "epoch": 0.992,
      "grad_norm": 0.13276298761961705,
      "learning_rate": 1.0957543155842703e-05,
      "loss": 0.1718,
      "step": 1240
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.1161581920629144,
      "learning_rate": 1.0825793454723325e-05,
      "loss": 0.1696,
      "step": 1250
    },
    {
      "epoch": 1.008,
      "grad_norm": 0.09621449723576145,
      "learning_rate": 1.0693899263660442e-05,
      "loss": 0.1113,
      "step": 1260
    },
    {
      "epoch": 1.016,
      "grad_norm": 0.10015368517162866,
      "learning_rate": 1.0561883660318456e-05,
      "loss": 0.1003,
      "step": 1270
    },
    {
      "epoch": 1.024,
      "grad_norm": 0.1076609073322909,
      "learning_rate": 1.0429769743605406e-05,
      "loss": 0.1092,
      "step": 1280
    },
    {
      "epoch": 1.032,
      "grad_norm": 0.1209467723696444,
      "learning_rate": 1.0297580629631324e-05,
      "loss": 0.1047,
      "step": 1290
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.11347187764817329,
      "learning_rate": 1.0165339447663586e-05,
      "loss": 0.1012,
      "step": 1300
    },
    {
      "epoch": 1.048,
      "grad_norm": 0.13787078556126084,
      "learning_rate": 1.0033069336079952e-05,
      "loss": 0.0996,
      "step": 1310
    },
    {
      "epoch": 1.056,
      "grad_norm": 0.11234445761651994,
      "learning_rate": 9.900793438320037e-06,
      "loss": 0.0986,
      "step": 1320
    },
    {
      "epoch": 1.064,
      "grad_norm": 0.11599014325689881,
      "learning_rate": 9.768534898835864e-06,
      "loss": 0.1063,
      "step": 1330
    },
    {
      "epoch": 1.072,
      "grad_norm": 0.11347494815929351,
      "learning_rate": 9.636316859042258e-06,
      "loss": 0.1039,
      "step": 1340
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.12183008770849793,
      "learning_rate": 9.504162453267776e-06,
      "loss": 0.1032,
      "step": 1350
    },
    {
      "epoch": 1.088,
      "grad_norm": 0.11562604188712092,
      "learning_rate": 9.372094804706867e-06,
      "loss": 0.1011,
      "step": 1360
    },
    {
      "epoch": 1.096,
      "grad_norm": 0.10067772672412269,
      "learning_rate": 9.24013702137397e-06,
      "loss": 0.0972,
      "step": 1370
    },
    {
      "epoch": 1.104,
      "grad_norm": 0.11541149806656344,
      "learning_rate": 9.108312192060298e-06,
      "loss": 0.0958,
      "step": 1380
    },
    {
      "epoch": 1.112,
      "grad_norm": 0.129106816260335,
      "learning_rate": 8.97664338229395e-06,
      "loss": 0.1,
      "step": 1390
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.11074093024717463,
      "learning_rate": 8.84515363030414e-06,
      "loss": 0.0976,
      "step": 1400
    },
    {
      "epoch": 1.1280000000000001,
      "grad_norm": 0.10927701173789658,
      "learning_rate": 8.713865942990143e-06,
      "loss": 0.1004,
      "step": 1410
    },
    {
      "epoch": 1.1360000000000001,
      "grad_norm": 0.129800724137463,
      "learning_rate": 8.582803291895758e-06,
      "loss": 0.1097,
      "step": 1420
    },
    {
      "epoch": 1.144,
      "grad_norm": 0.1109925526353623,
      "learning_rate": 8.451988609189987e-06,
      "loss": 0.1047,
      "step": 1430
    },
    {
      "epoch": 1.152,
      "grad_norm": 0.12402578949666784,
      "learning_rate": 8.321444783654524e-06,
      "loss": 0.1079,
      "step": 1440
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.1112595703457445,
      "learning_rate": 8.191194656678905e-06,
      "loss": 0.0976,
      "step": 1450
    },
    {
      "epoch": 1.168,
      "grad_norm": 0.12036457116059705,
      "learning_rate": 8.06126101826392e-06,
      "loss": 0.0973,
      "step": 1460
    },
    {
      "epoch": 1.176,
      "grad_norm": 0.12090306774036914,
      "learning_rate": 7.931666603034034e-06,
      "loss": 0.1008,
      "step": 1470
    },
    {
      "epoch": 1.184,
      "grad_norm": 0.12317909704896644,
      "learning_rate": 7.80243408625947e-06,
      "loss": 0.0948,
      "step": 1480
    },
    {
      "epoch": 1.192,
      "grad_norm": 0.10705938042955583,
      "learning_rate": 7.673586079888699e-06,
      "loss": 0.1067,
      "step": 1490
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.14259766047955233,
      "learning_rate": 7.545145128592009e-06,
      "loss": 0.1007,
      "step": 1500
    },
    {
      "epoch": 1.208,
      "grad_norm": 0.11378740748534237,
      "learning_rate": 7.4171337058168365e-06,
      "loss": 0.103,
      "step": 1510
    },
    {
      "epoch": 1.216,
      "grad_norm": 0.11908875076001751,
      "learning_rate": 7.28957420985556e-06,
      "loss": 0.099,
      "step": 1520
    },
    {
      "epoch": 1.224,
      "grad_norm": 0.1177996071960852,
      "learning_rate": 7.16248895992645e-06,
      "loss": 0.0974,
      "step": 1530
    },
    {
      "epoch": 1.232,
      "grad_norm": 0.12558719327814405,
      "learning_rate": 7.035900192268464e-06,
      "loss": 0.1114,
      "step": 1540
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.12231602378332272,
      "learning_rate": 6.909830056250527e-06,
      "loss": 0.1017,
      "step": 1550
    },
    {
      "epoch": 1.248,
      "grad_norm": 0.1411428231676542,
      "learning_rate": 6.784300610496049e-06,
      "loss": 0.1037,
      "step": 1560
    },
    {
      "epoch": 1.256,
      "grad_norm": 0.11433442906651817,
      "learning_rate": 6.659333819023291e-06,
      "loss": 0.1017,
      "step": 1570
    },
    {
      "epoch": 1.264,
      "grad_norm": 0.1587733997288609,
      "learning_rate": 6.534951547402322e-06,
      "loss": 0.1022,
      "step": 1580
    },
    {
      "epoch": 1.272,
      "grad_norm": 0.11284632840723509,
      "learning_rate": 6.411175558929152e-06,
      "loss": 0.1016,
      "step": 1590
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.10824650118751981,
      "learning_rate": 6.2880275108177915e-06,
      "loss": 0.1027,
      "step": 1600
    },
    {
      "epoch": 1.288,
      "grad_norm": 0.13145070635475115,
      "learning_rate": 6.165528950410884e-06,
      "loss": 0.1066,
      "step": 1610
    },
    {
      "epoch": 1.296,
      "grad_norm": 0.13085006869996493,
      "learning_rate": 6.04370131140952e-06,
      "loss": 0.0992,
      "step": 1620
    },
    {
      "epoch": 1.304,
      "grad_norm": 0.12602863363341382,
      "learning_rate": 5.922565910122967e-06,
      "loss": 0.0953,
      "step": 1630
    },
    {
      "epoch": 1.312,
      "grad_norm": 0.1225471587130614,
      "learning_rate": 5.802143941738945e-06,
      "loss": 0.106,
      "step": 1640
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.11766655619511902,
      "learning_rate": 5.6824564766150724e-06,
      "loss": 0.1063,
      "step": 1650
    },
    {
      "epoch": 1.328,
      "grad_norm": 0.12243121066150191,
      "learning_rate": 5.563524456592163e-06,
      "loss": 0.1005,
      "step": 1660
    },
    {
      "epoch": 1.336,
      "grad_norm": 0.1137092367870251,
      "learning_rate": 5.445368691330008e-06,
      "loss": 0.1014,
      "step": 1670
    },
    {
      "epoch": 1.3439999999999999,
      "grad_norm": 0.11563617059718279,
      "learning_rate": 5.328009854666303e-06,
      "loss": 0.0963,
      "step": 1680
    },
    {
      "epoch": 1.3519999999999999,
      "grad_norm": 0.10812153213525164,
      "learning_rate": 5.211468480999304e-06,
      "loss": 0.1039,
      "step": 1690
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 0.10528899506093697,
      "learning_rate": 5.095764961694923e-06,
      "loss": 0.1003,
      "step": 1700
    },
    {
      "epoch": 1.3679999999999999,
      "grad_norm": 0.11815436297994328,
      "learning_rate": 4.980919541518796e-06,
      "loss": 0.0982,
      "step": 1710
    },
    {
      "epoch": 1.376,
      "grad_norm": 0.12086679854967129,
      "learning_rate": 4.866952315094088e-06,
      "loss": 0.0971,
      "step": 1720
    },
    {
      "epoch": 1.384,
      "grad_norm": 0.1216775616601072,
      "learning_rate": 4.753883223385467e-06,
      "loss": 0.0945,
      "step": 1730
    },
    {
      "epoch": 1.392,
      "grad_norm": 0.10648914490397961,
      "learning_rate": 4.641732050210032e-06,
      "loss": 0.1039,
      "step": 1740
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.11378893301113804,
      "learning_rate": 4.530518418775734e-06,
      "loss": 0.0935,
      "step": 1750
    },
    {
      "epoch": 1.408,
      "grad_norm": 0.13321885782018256,
      "learning_rate": 4.420261788247841e-06,
      "loss": 0.1007,
      "step": 1760
    },
    {
      "epoch": 1.416,
      "grad_norm": 0.1166412836830051,
      "learning_rate": 4.3109814503441894e-06,
      "loss": 0.1,
      "step": 1770
    },
    {
      "epoch": 1.424,
      "grad_norm": 0.12573437053218914,
      "learning_rate": 4.202696525959667e-06,
      "loss": 0.1018,
      "step": 1780
    },
    {
      "epoch": 1.432,
      "grad_norm": 0.10766865319844147,
      "learning_rate": 4.0954259618206295e-06,
      "loss": 0.1055,
      "step": 1790
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.11916472873837182,
      "learning_rate": 3.989188527169749e-06,
      "loss": 0.1006,
      "step": 1800
    },
    {
      "epoch": 1.448,
      "grad_norm": 0.12141420740790235,
      "learning_rate": 3.884002810481959e-06,
      "loss": 0.1053,
      "step": 1810
    },
    {
      "epoch": 1.456,
      "grad_norm": 0.10131664100763009,
      "learning_rate": 3.7798872162119948e-06,
      "loss": 0.095,
      "step": 1820
    },
    {
      "epoch": 1.464,
      "grad_norm": 0.10718874752624193,
      "learning_rate": 3.676859961574162e-06,
      "loss": 0.0966,
      "step": 1830
    },
    {
      "epoch": 1.472,
      "grad_norm": 0.11477403835967784,
      "learning_rate": 3.5749390733548382e-06,
      "loss": 0.0973,
      "step": 1840
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.10635089908850691,
      "learning_rate": 3.4741423847583134e-06,
      "loss": 0.0976,
      "step": 1850
    },
    {
      "epoch": 1.488,
      "grad_norm": 0.10600348235646671,
      "learning_rate": 3.3744875322865035e-06,
      "loss": 0.0974,
      "step": 1860
    },
    {
      "epoch": 1.496,
      "grad_norm": 0.1097923236145172,
      "learning_rate": 3.2759919526530536e-06,
      "loss": 0.1018,
      "step": 1870
    },
    {
      "epoch": 1.504,
      "grad_norm": 0.12057262052779812,
      "learning_rate": 3.178672879732435e-06,
      "loss": 0.0921,
      "step": 1880
    },
    {
      "epoch": 1.512,
      "grad_norm": 0.10322870417117935,
      "learning_rate": 3.0825473415445073e-06,
      "loss": 0.0969,
      "step": 1890
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.11162000352158546,
      "learning_rate": 2.9876321572751143e-06,
      "loss": 0.1004,
      "step": 1900
    },
    {
      "epoch": 1.528,
      "grad_norm": 0.11080139256806071,
      "learning_rate": 2.8939439343332086e-06,
      "loss": 0.0925,
      "step": 1910
    },
    {
      "epoch": 1.536,
      "grad_norm": 0.11129458730658273,
      "learning_rate": 2.8014990654450325e-06,
      "loss": 0.0965,
      "step": 1920
    },
    {
      "epoch": 1.544,
      "grad_norm": 0.11117549882577657,
      "learning_rate": 2.7103137257858867e-06,
      "loss": 0.0913,
      "step": 1930
    },
    {
      "epoch": 1.552,
      "grad_norm": 0.13048983161003938,
      "learning_rate": 2.6204038701499056e-06,
      "loss": 0.0992,
      "step": 1940
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.11734607541924097,
      "learning_rate": 2.5317852301584642e-06,
      "loss": 0.1012,
      "step": 1950
    },
    {
      "epoch": 1.568,
      "grad_norm": 0.1083555940829194,
      "learning_rate": 2.4444733115075823e-06,
      "loss": 0.0971,
      "step": 1960
    },
    {
      "epoch": 1.576,
      "grad_norm": 0.10908207209378103,
      "learning_rate": 2.3584833912548887e-06,
      "loss": 0.0979,
      "step": 1970
    },
    {
      "epoch": 1.584,
      "grad_norm": 0.11841797427563601,
      "learning_rate": 2.2738305151465646e-06,
      "loss": 0.0942,
      "step": 1980
    },
    {
      "epoch": 1.592,
      "grad_norm": 0.11315769991653934,
      "learning_rate": 2.190529494984782e-06,
      "loss": 0.0888,
      "step": 1990
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.11433802488811017,
      "learning_rate": 2.1085949060360654e-06,
      "loss": 0.0875,
      "step": 2000
    },
    {
      "epoch": 1.608,
      "grad_norm": 0.12338526437657736,
      "learning_rate": 2.0280410844810426e-06,
      "loss": 0.1007,
      "step": 2010
    },
    {
      "epoch": 1.616,
      "grad_norm": 0.1140721727012241,
      "learning_rate": 1.9488821249060297e-06,
      "loss": 0.0961,
      "step": 2020
    },
    {
      "epoch": 1.624,
      "grad_norm": 0.10596121333045593,
      "learning_rate": 1.8711318778368792e-06,
      "loss": 0.0955,
      "step": 2030
    },
    {
      "epoch": 1.6320000000000001,
      "grad_norm": 0.1216702589106228,
      "learning_rate": 1.7948039473155553e-06,
      "loss": 0.0992,
      "step": 2040
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.12842132114696375,
      "learning_rate": 1.7199116885197996e-06,
      "loss": 0.0961,
      "step": 2050
    },
    {
      "epoch": 1.6480000000000001,
      "grad_norm": 0.12054578218454282,
      "learning_rate": 1.646468205426377e-06,
      "loss": 0.0915,
      "step": 2060
    },
    {
      "epoch": 1.6560000000000001,
      "grad_norm": 0.13571464476020081,
      "learning_rate": 1.5744863485182537e-06,
      "loss": 0.1007,
      "step": 2070
    },
    {
      "epoch": 1.6640000000000001,
      "grad_norm": 0.09706739858443193,
      "learning_rate": 1.5039787125361327e-06,
      "loss": 0.094,
      "step": 2080
    },
    {
      "epoch": 1.6720000000000002,
      "grad_norm": 0.10675797230018248,
      "learning_rate": 1.4349576342747462e-06,
      "loss": 0.0938,
      "step": 2090
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 0.11223016492676532,
      "learning_rate": 1.367435190424261e-06,
      "loss": 0.0938,
      "step": 2100
    },
    {
      "epoch": 1.688,
      "grad_norm": 0.12732260810929744,
      "learning_rate": 1.3014231954572287e-06,
      "loss": 0.098,
      "step": 2110
    },
    {
      "epoch": 1.696,
      "grad_norm": 0.12300876323192528,
      "learning_rate": 1.2369331995613664e-06,
      "loss": 0.0964,
      "step": 2120
    },
    {
      "epoch": 1.704,
      "grad_norm": 0.12534390954335137,
      "learning_rate": 1.1739764866186309e-06,
      "loss": 0.0896,
      "step": 2130
    },
    {
      "epoch": 1.712,
      "grad_norm": 0.11609921777362982,
      "learning_rate": 1.112564072230863e-06,
      "loss": 0.0959,
      "step": 2140
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.10391980074321304,
      "learning_rate": 1.0527067017923654e-06,
      "loss": 0.0961,
      "step": 2150
    },
    {
      "epoch": 1.728,
      "grad_norm": 0.1278354882865009,
      "learning_rate": 9.944148486097793e-07,
      "loss": 0.0976,
      "step": 2160
    },
    {
      "epoch": 1.736,
      "grad_norm": 0.10681775464138107,
      "learning_rate": 9.376987120695547e-07,
      "loss": 0.0967,
      "step": 2170
    },
    {
      "epoch": 1.744,
      "grad_norm": 0.12461590835029315,
      "learning_rate": 8.825682158533555e-07,
      "loss": 0.1019,
      "step": 2180
    },
    {
      "epoch": 1.752,
      "grad_norm": 0.12925806225583442,
      "learning_rate": 8.290330062017015e-07,
      "loss": 0.0991,
      "step": 2190
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.12035123190303527,
      "learning_rate": 7.771024502261526e-07,
      "loss": 0.095,
      "step": 2200
    },
    {
      "epoch": 1.768,
      "grad_norm": 0.11830596930835367,
      "learning_rate": 7.267856342703461e-07,
      "loss": 0.1003,
      "step": 2210
    },
    {
      "epoch": 1.776,
      "grad_norm": 0.10309290288715313,
      "learning_rate": 6.780913623201346e-07,
      "loss": 0.0934,
      "step": 2220
    },
    {
      "epoch": 1.784,
      "grad_norm": 0.11823660601228905,
      "learning_rate": 6.310281544631547e-07,
      "loss": 0.091,
      "step": 2230
    },
    {
      "epoch": 1.792,
      "grad_norm": 0.1240524461220155,
      "learning_rate": 5.856042453980526e-07,
      "loss": 0.0933,
      "step": 2240
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.10954545218644868,
      "learning_rate": 5.418275829936537e-07,
      "loss": 0.095,
      "step": 2250
    },
    {
      "epoch": 1.808,
      "grad_norm": 0.09984478082295495,
      "learning_rate": 4.997058268983135e-07,
      "loss": 0.0884,
      "step": 2260
    },
    {
      "epoch": 1.8159999999999998,
      "grad_norm": 0.09980866667906611,
      "learning_rate": 4.592463471997022e-07,
      "loss": 0.091,
      "step": 2270
    },
    {
      "epoch": 1.8239999999999998,
      "grad_norm": 0.11065649275917133,
      "learning_rate": 4.204562231352516e-07,
      "loss": 0.0996,
      "step": 2280
    },
    {
      "epoch": 1.8319999999999999,
      "grad_norm": 0.10945247265836085,
      "learning_rate": 3.83342241853496e-07,
      "loss": 0.093,
      "step": 2290
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 0.11965279820742956,
      "learning_rate": 3.4791089722651437e-07,
      "loss": 0.1022,
      "step": 2300
    },
    {
      "epoch": 1.8479999999999999,
      "grad_norm": 0.1181705374127321,
      "learning_rate": 3.1416838871368925e-07,
      "loss": 0.1009,
      "step": 2310
    },
    {
      "epoch": 1.8559999999999999,
      "grad_norm": 0.11160263850458792,
      "learning_rate": 2.8212062027698995e-07,
      "loss": 0.0963,
      "step": 2320
    },
    {
      "epoch": 1.8639999999999999,
      "grad_norm": 0.13030757683951363,
      "learning_rate": 2.5177319934793995e-07,
      "loss": 0.0983,
      "step": 2330
    },
    {
      "epoch": 1.8719999999999999,
      "grad_norm": 0.11874772797683317,
      "learning_rate": 2.2313143584648423e-07,
      "loss": 0.092,
      "step": 2340
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.11341961857438242,
      "learning_rate": 1.9620034125190645e-07,
      "loss": 0.092,
      "step": 2350
    },
    {
      "epoch": 1.888,
      "grad_norm": 0.12018288004198623,
      "learning_rate": 1.7098462772596302e-07,
      "loss": 0.1013,
      "step": 2360
    },
    {
      "epoch": 1.896,
      "grad_norm": 0.1076575691013852,
      "learning_rate": 1.474887072883935e-07,
      "loss": 0.0911,
      "step": 2370
    },
    {
      "epoch": 1.904,
      "grad_norm": 0.11337036877085487,
      "learning_rate": 1.2571669104494254e-07,
      "loss": 0.0881,
      "step": 2380
    },
    {
      "epoch": 1.912,
      "grad_norm": 0.1610883586396456,
      "learning_rate": 1.0567238846803995e-07,
      "loss": 0.0977,
      "step": 2390
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.11183827260464378,
      "learning_rate": 8.735930673024806e-08,
      "loss": 0.0869,
      "step": 2400
    },
    {
      "epoch": 1.928,
      "grad_norm": 0.14085464266938202,
      "learning_rate": 7.078065009060941e-08,
      "loss": 0.0979,
      "step": 2410
    },
    {
      "epoch": 1.936,
      "grad_norm": 0.12681513850389028,
      "learning_rate": 5.5939319333998546e-08,
      "loss": 0.0955,
      "step": 2420
    },
    {
      "epoch": 1.944,
      "grad_norm": 0.12408511876527423,
      "learning_rate": 4.2837911263562406e-08,
      "loss": 0.0983,
      "step": 2430
    },
    {
      "epoch": 1.952,
      "grad_norm": 0.12057693933072995,
      "learning_rate": 3.147871824635717e-08,
      "loss": 0.0978,
      "step": 2440
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.12061596653924865,
      "learning_rate": 2.1863727812254653e-08,
      "loss": 0.0941,
      "step": 2450
    },
    {
      "epoch": 1.968,
      "grad_norm": 0.11057835512679115,
      "learning_rate": 1.3994622306173766e-08,
      "loss": 0.0977,
      "step": 2460
    },
    {
      "epoch": 1.976,
      "grad_norm": 0.12585430211339457,
      "learning_rate": 7.872778593728258e-09,
      "loss": 0.0958,
      "step": 2470
    },
    {
      "epoch": 1.984,
      "grad_norm": 0.11787146911875013,
      "learning_rate": 3.499267820307184e-09,
      "loss": 0.0919,
      "step": 2480
    },
    {
      "epoch": 1.992,
      "grad_norm": 0.1087435338716272,
      "learning_rate": 8.748552236603758e-10,
      "loss": 0.0936,
      "step": 2490
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.11470541946837681,
      "learning_rate": 0.0,
      "loss": 0.0898,
      "step": 2500
    },
    {
      "epoch": 2.0,
      "step": 2500,
      "total_flos": 22262632857600.0,
      "train_loss": 0.14060430166721344,
      "train_runtime": 9775.4364,
      "train_samples_per_second": 8.184,
      "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
}