{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.752688172043011,
  "eval_steps": 1000,
  "global_step": 18000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005973715651135006,
      "grad_norm": 8.9375,
      "learning_rate": 2e-06,
      "loss": 1.3168,
      "step": 1
    },
    {
      "epoch": 0.05973715651135006,
      "grad_norm": 0.61328125,
      "learning_rate": 0.0002,
      "loss": 0.5503,
      "step": 100
    },
    {
      "epoch": 0.11947431302270012,
      "grad_norm": 0.314453125,
      "learning_rate": 0.0004,
      "loss": 0.3885,
      "step": 200
    },
    {
      "epoch": 0.17921146953405018,
      "grad_norm": 0.298828125,
      "learning_rate": 0.0006,
      "loss": 0.3758,
      "step": 300
    },
    {
      "epoch": 0.23894862604540024,
      "grad_norm": 0.12890625,
      "learning_rate": 0.0008,
      "loss": 0.363,
      "step": 400
    },
    {
      "epoch": 0.2986857825567503,
      "grad_norm": 0.1943359375,
      "learning_rate": 0.001,
      "loss": 0.3567,
      "step": 500
    },
    {
      "epoch": 0.35842293906810035,
      "grad_norm": 0.11181640625,
      "learning_rate": 0.0012,
      "loss": 0.3435,
      "step": 600
    },
    {
      "epoch": 0.41816009557945044,
      "grad_norm": 0.12109375,
      "learning_rate": 0.0014,
      "loss": 0.3415,
      "step": 700
    },
    {
      "epoch": 0.4778972520908005,
      "grad_norm": 0.09130859375,
      "learning_rate": 0.0016,
      "loss": 0.3394,
      "step": 800
    },
    {
      "epoch": 0.5376344086021505,
      "grad_norm": 0.11572265625,
      "learning_rate": 0.0018000000000000002,
      "loss": 0.345,
      "step": 900
    },
    {
      "epoch": 0.5973715651135006,
      "grad_norm": 0.07421875,
      "learning_rate": 0.002,
      "loss": 0.3177,
      "step": 1000
    },
    {
      "epoch": 0.6571087216248507,
      "grad_norm": 0.06494140625,
      "learning_rate": 0.0019998292504580526,
      "loss": 0.3318,
      "step": 1100
    },
    {
      "epoch": 0.7168458781362007,
      "grad_norm": 0.1455078125,
      "learning_rate": 0.001999317060143023,
      "loss": 0.3229,
      "step": 1200
    },
    {
      "epoch": 0.7765830346475507,
      "grad_norm": 0.1298828125,
      "learning_rate": 0.001998463603967434,
      "loss": 0.3145,
      "step": 1300
    },
    {
      "epoch": 0.8363201911589009,
      "grad_norm": 0.0732421875,
      "learning_rate": 0.0019972691733857882,
      "loss": 0.3158,
      "step": 1400
    },
    {
      "epoch": 0.8960573476702509,
      "grad_norm": 0.13671875,
      "learning_rate": 0.0019957341762950344,
      "loss": 0.3132,
      "step": 1500
    },
    {
      "epoch": 0.955794504181601,
      "grad_norm": 0.11572265625,
      "learning_rate": 0.001993859136895274,
      "loss": 0.3011,
      "step": 1600
    },
    {
      "epoch": 1.015531660692951,
      "grad_norm": 0.125,
      "learning_rate": 0.0019916446955107426,
      "loss": 0.3014,
      "step": 1700
    },
    {
      "epoch": 1.075268817204301,
      "grad_norm": 0.11279296875,
      "learning_rate": 0.001989091608371146,
      "loss": 0.3,
      "step": 1800
    },
    {
      "epoch": 1.135005973715651,
      "grad_norm": 0.08544921875,
      "learning_rate": 0.0019862007473534027,
      "loss": 0.3016,
      "step": 1900
    },
    {
      "epoch": 1.1947431302270013,
      "grad_norm": 0.10791015625,
      "learning_rate": 0.001982973099683902,
      "loss": 0.2991,
      "step": 2000
    },
    {
      "epoch": 1.2544802867383513,
      "grad_norm": 0.103515625,
      "learning_rate": 0.001979409767601366,
      "loss": 0.2974,
      "step": 2100
    },
    {
      "epoch": 1.3142174432497014,
      "grad_norm": 0.08056640625,
      "learning_rate": 0.001975511967980437,
      "loss": 0.2903,
      "step": 2200
    },
    {
      "epoch": 1.3739545997610514,
      "grad_norm": 0.109375,
      "learning_rate": 0.001971281031916114,
      "loss": 0.2796,
      "step": 2300
    },
    {
      "epoch": 1.4336917562724014,
      "grad_norm": 0.125,
      "learning_rate": 0.0019667184042691877,
      "loss": 0.2746,
      "step": 2400
    },
    {
      "epoch": 1.4934289127837514,
      "grad_norm": 0.10400390625,
      "learning_rate": 0.001961825643172819,
      "loss": 0.2766,
      "step": 2500
    },
    {
      "epoch": 1.5531660692951015,
      "grad_norm": 0.06494140625,
      "learning_rate": 0.0019566044195004407,
      "loss": 0.2739,
      "step": 2600
    },
    {
      "epoch": 1.6129032258064515,
      "grad_norm": 0.12255859375,
      "learning_rate": 0.0019510565162951536,
      "loss": 0.2677,
      "step": 2700
    },
    {
      "epoch": 1.6726403823178018,
      "grad_norm": 0.0869140625,
      "learning_rate": 0.0019451838281608197,
      "loss": 0.2605,
      "step": 2800
    },
    {
      "epoch": 1.7323775388291518,
      "grad_norm": 0.08837890625,
      "learning_rate": 0.0019389883606150567,
      "loss": 0.259,
      "step": 2900
    },
    {
      "epoch": 1.7921146953405018,
      "grad_norm": 0.1279296875,
      "learning_rate": 0.0019324722294043557,
      "loss": 0.256,
      "step": 3000
    },
    {
      "epoch": 1.8518518518518519,
      "grad_norm": 0.1279296875,
      "learning_rate": 0.0019256376597815564,
      "loss": 0.246,
      "step": 3100
    },
    {
      "epoch": 1.911589008363202,
      "grad_norm": 0.12890625,
      "learning_rate": 0.001918486985745923,
      "loss": 0.2431,
      "step": 3200
    },
    {
      "epoch": 1.971326164874552,
      "grad_norm": 0.083984375,
      "learning_rate": 0.0019110226492460884,
      "loss": 0.2364,
      "step": 3300
    },
    {
      "epoch": 2.031063321385902,
      "grad_norm": 0.0927734375,
      "learning_rate": 0.0019032471993461289,
      "loss": 0.2306,
      "step": 3400
    },
    {
      "epoch": 2.090800477897252,
      "grad_norm": 0.087890625,
      "learning_rate": 0.0018951632913550625,
      "loss": 0.2331,
      "step": 3500
    },
    {
      "epoch": 2.150537634408602,
      "grad_norm": 0.091796875,
      "learning_rate": 0.0018867736859200619,
      "loss": 0.2291,
      "step": 3600
    },
    {
      "epoch": 2.2102747909199523,
      "grad_norm": 0.0849609375,
      "learning_rate": 0.0018780812480836979,
      "loss": 0.227,
      "step": 3700
    },
    {
      "epoch": 2.270011947431302,
      "grad_norm": 0.1015625,
      "learning_rate": 0.0018690889463055284,
      "loss": 0.2255,
      "step": 3800
    },
    {
      "epoch": 2.3297491039426523,
      "grad_norm": 0.0703125,
      "learning_rate": 0.0018597998514483724,
      "loss": 0.2165,
      "step": 3900
    },
    {
      "epoch": 2.3894862604540026,
      "grad_norm": 0.091796875,
      "learning_rate": 0.0018502171357296143,
      "loss": 0.2157,
      "step": 4000
    },
    {
      "epoch": 2.4492234169653524,
      "grad_norm": 0.08740234375,
      "learning_rate": 0.0018403440716378927,
      "loss": 0.2086,
      "step": 4100
    },
    {
      "epoch": 2.5089605734767026,
      "grad_norm": 0.111328125,
      "learning_rate": 0.0018301840308155505,
      "loss": 0.2077,
      "step": 4200
    },
    {
      "epoch": 2.5686977299880525,
      "grad_norm": 0.09619140625,
      "learning_rate": 0.0018197404829072212,
      "loss": 0.201,
      "step": 4300
    },
    {
      "epoch": 2.6284348864994027,
      "grad_norm": 0.11083984375,
      "learning_rate": 0.0018090169943749475,
      "loss": 0.1991,
      "step": 4400
    },
    {
      "epoch": 2.6881720430107525,
      "grad_norm": 0.0830078125,
      "learning_rate": 0.0017980172272802398,
      "loss": 0.1961,
      "step": 4500
    },
    {
      "epoch": 2.7479091995221028,
      "grad_norm": 0.10107421875,
      "learning_rate": 0.0017867449380334832,
      "loss": 0.1934,
      "step": 4600
    },
    {
      "epoch": 2.807646356033453,
      "grad_norm": 0.1064453125,
      "learning_rate": 0.0017752039761111298,
      "loss": 0.1862,
      "step": 4700
    },
    {
      "epoch": 2.867383512544803,
      "grad_norm": 0.08154296875,
      "learning_rate": 0.001763398282741103,
      "loss": 0.1849,
      "step": 4800
    },
    {
      "epoch": 2.927120669056153,
      "grad_norm": 0.0869140625,
      "learning_rate": 0.0017513318895568735,
      "loss": 0.1828,
      "step": 4900
    },
    {
      "epoch": 2.986857825567503,
      "grad_norm": 0.09619140625,
      "learning_rate": 0.001739008917220659,
      "loss": 0.1769,
      "step": 5000
    },
    {
      "epoch": 3.046594982078853,
      "grad_norm": 0.107421875,
      "learning_rate": 0.0017264335740162242,
      "loss": 0.1729,
      "step": 5100
    },
    {
      "epoch": 3.106332138590203,
      "grad_norm": 0.0859375,
      "learning_rate": 0.0017136101544117524,
      "loss": 0.1745,
      "step": 5200
    },
    {
      "epoch": 3.166069295101553,
      "grad_norm": 0.107421875,
      "learning_rate": 0.0017005430375932908,
      "loss": 0.1742,
      "step": 5300
    },
    {
      "epoch": 3.225806451612903,
      "grad_norm": 0.08837890625,
      "learning_rate": 0.0016872366859692627,
      "loss": 0.175,
      "step": 5400
    },
    {
      "epoch": 3.2855436081242533,
      "grad_norm": 0.126953125,
      "learning_rate": 0.0016736956436465573,
      "loss": 0.1643,
      "step": 5500
    },
    {
      "epoch": 3.3452807646356035,
      "grad_norm": 0.07666015625,
      "learning_rate": 0.0016599245348787228,
      "loss": 0.1651,
      "step": 5600
    },
    {
      "epoch": 3.4050179211469533,
      "grad_norm": 0.12158203125,
      "learning_rate": 0.0016459280624867873,
      "loss": 0.1613,
      "step": 5700
    },
    {
      "epoch": 3.4647550776583036,
      "grad_norm": 0.1396484375,
      "learning_rate": 0.001631711006253251,
      "loss": 0.1586,
      "step": 5800
    },
    {
      "epoch": 3.5244922341696534,
      "grad_norm": 0.09228515625,
      "learning_rate": 0.001617278221289793,
      "loss": 0.1601,
      "step": 5900
    },
    {
      "epoch": 3.5842293906810037,
      "grad_norm": 0.0888671875,
      "learning_rate": 0.0016026346363792565,
      "loss": 0.1515,
      "step": 6000
    },
    {
      "epoch": 3.6439665471923535,
      "grad_norm": 0.1259765625,
      "learning_rate": 0.0015877852522924731,
      "loss": 0.1492,
      "step": 6100
    },
    {
      "epoch": 3.7037037037037037,
      "grad_norm": 0.0771484375,
      "learning_rate": 0.0015727351400805052,
      "loss": 0.1514,
      "step": 6200
    },
    {
      "epoch": 3.763440860215054,
      "grad_norm": 0.0771484375,
      "learning_rate": 0.0015574894393428856,
      "loss": 0.1462,
      "step": 6300
    },
    {
      "epoch": 3.823178016726404,
      "grad_norm": 0.078125,
      "learning_rate": 0.0015420533564724495,
      "loss": 0.143,
      "step": 6400
    },
    {
      "epoch": 3.882915173237754,
      "grad_norm": 0.0673828125,
      "learning_rate": 0.0015264321628773558,
      "loss": 0.1426,
      "step": 6500
    },
    {
      "epoch": 3.942652329749104,
      "grad_norm": 0.07421875,
      "learning_rate": 0.001510631193180907,
      "loss": 0.1391,
      "step": 6600
    },
    {
      "epoch": 4.002389486260454,
      "grad_norm": 0.10107421875,
      "learning_rate": 0.001494655843399779,
      "loss": 0.1355,
      "step": 6700
    },
    {
      "epoch": 4.062126642771804,
      "grad_norm": 0.0791015625,
      "learning_rate": 0.0014785115691012866,
      "loss": 0.1335,
      "step": 6800
    },
    {
      "epoch": 4.121863799283154,
      "grad_norm": 0.09375,
      "learning_rate": 0.0014622038835403132,
      "loss": 0.1398,
      "step": 6900
    },
    {
      "epoch": 4.181600955794504,
      "grad_norm": 0.08203125,
      "learning_rate": 0.0014457383557765385,
      "loss": 0.1342,
      "step": 7000
    },
    {
      "epoch": 4.241338112305854,
      "grad_norm": 0.1064453125,
      "learning_rate": 0.001429120608772609,
      "loss": 0.135,
      "step": 7100
    },
    {
      "epoch": 4.301075268817204,
      "grad_norm": 0.07958984375,
      "learning_rate": 0.0014123563174739035,
      "loss": 0.1297,
      "step": 7200
    },
    {
      "epoch": 4.360812425328555,
      "grad_norm": 0.0927734375,
      "learning_rate": 0.0013954512068705424,
      "loss": 0.1294,
      "step": 7300
    },
    {
      "epoch": 4.4205495818399045,
      "grad_norm": 0.09423828125,
      "learning_rate": 0.0013784110500423103,
      "loss": 0.1257,
      "step": 7400
    },
    {
      "epoch": 4.480286738351254,
      "grad_norm": 0.076171875,
      "learning_rate": 0.0013612416661871532,
      "loss": 0.1249,
      "step": 7500
    },
    {
      "epoch": 4.540023894862604,
      "grad_norm": 0.064453125,
      "learning_rate": 0.0013439489186339282,
      "loss": 0.1243,
      "step": 7600
    },
    {
      "epoch": 4.599761051373955,
      "grad_norm": 0.07275390625,
      "learning_rate": 0.0013265387128400831,
      "loss": 0.1191,
      "step": 7700
    },
    {
      "epoch": 4.659498207885305,
      "grad_norm": 0.06591796875,
      "learning_rate": 0.0013090169943749475,
      "loss": 0.1188,
      "step": 7800
    },
    {
      "epoch": 4.7192353643966545,
      "grad_norm": 0.0703125,
      "learning_rate": 0.0012913897468893247,
      "loss": 0.1174,
      "step": 7900
    },
    {
      "epoch": 4.778972520908005,
      "grad_norm": 0.061279296875,
      "learning_rate": 0.0012736629900720832,
      "loss": 0.1168,
      "step": 8000
    },
    {
      "epoch": 4.838709677419355,
      "grad_norm": 0.06640625,
      "learning_rate": 0.0012558427775944357,
      "loss": 0.1135,
      "step": 8100
    },
    {
      "epoch": 4.898446833930705,
      "grad_norm": 0.09912109375,
      "learning_rate": 0.0012379351950426187,
      "loss": 0.1117,
      "step": 8200
    },
    {
      "epoch": 4.958183990442055,
      "grad_norm": 0.05712890625,
      "learning_rate": 0.0012199463578396689,
      "loss": 0.1092,
      "step": 8300
    },
    {
      "epoch": 5.017921146953405,
      "grad_norm": 0.07861328125,
      "learning_rate": 0.0012018824091570102,
      "loss": 0.1091,
      "step": 8400
    },
    {
      "epoch": 5.077658303464755,
      "grad_norm": 0.0859375,
      "learning_rate": 0.0011837495178165704,
      "loss": 0.1086,
      "step": 8500
    },
    {
      "epoch": 5.137395459976105,
      "grad_norm": 0.06103515625,
      "learning_rate": 0.00116555387618413,
      "loss": 0.109,
      "step": 8600
    },
    {
      "epoch": 5.197132616487456,
      "grad_norm": 0.0869140625,
      "learning_rate": 0.0011473016980546376,
      "loss": 0.1071,
      "step": 8700
    },
    {
      "epoch": 5.256869772998805,
      "grad_norm": 0.0703125,
      "learning_rate": 0.0011289992165302034,
      "loss": 0.1081,
      "step": 8800
    },
    {
      "epoch": 5.316606929510155,
      "grad_norm": 0.0869140625,
      "learning_rate": 0.001110652681891501,
      "loss": 0.1061,
      "step": 8900
    },
    {
      "epoch": 5.376344086021505,
      "grad_norm": 0.123046875,
      "learning_rate": 0.001092268359463302,
      "loss": 0.1044,
      "step": 9000
    },
    {
      "epoch": 5.436081242532856,
      "grad_norm": 0.07177734375,
      "learning_rate": 0.001073852527474874,
      "loss": 0.1004,
      "step": 9100
    },
    {
      "epoch": 5.4958183990442055,
      "grad_norm": 0.09130859375,
      "learning_rate": 0.00105541147491597,
      "loss": 0.1004,
      "step": 9200
    },
    {
      "epoch": 5.555555555555555,
      "grad_norm": 0.058837890625,
      "learning_rate": 0.0010369514993891452,
      "loss": 0.098,
      "step": 9300
    },
    {
      "epoch": 5.615292712066906,
      "grad_norm": 0.057861328125,
      "learning_rate": 0.00101847890495913,
      "loss": 0.0989,
      "step": 9400
    },
    {
      "epoch": 5.675029868578256,
      "grad_norm": 0.07421875,
      "learning_rate": 0.001,
      "loss": 0.0954,
      "step": 9500
    },
    {
      "epoch": 5.734767025089606,
      "grad_norm": 0.09375,
      "learning_rate": 0.0009815210950408703,
      "loss": 0.0955,
      "step": 9600
    },
    {
      "epoch": 5.7945041816009555,
      "grad_norm": 0.0654296875,
      "learning_rate": 0.0009630485006108553,
      "loss": 0.094,
      "step": 9700
    },
    {
      "epoch": 5.854241338112306,
      "grad_norm": 0.06787109375,
      "learning_rate": 0.0009445885250840301,
      "loss": 0.0924,
      "step": 9800
    },
    {
      "epoch": 5.913978494623656,
      "grad_norm": 0.06298828125,
      "learning_rate": 0.0009261474725251261,
      "loss": 0.0911,
      "step": 9900
    },
    {
      "epoch": 5.973715651135006,
      "grad_norm": 0.054443359375,
      "learning_rate": 0.0009077316405366981,
      "loss": 0.0902,
      "step": 10000
    },
    {
      "epoch": 6.033452807646356,
      "grad_norm": 0.0673828125,
      "learning_rate": 0.0008893473181084994,
      "loss": 0.0891,
      "step": 10100
    },
    {
      "epoch": 6.093189964157706,
      "grad_norm": 0.06103515625,
      "learning_rate": 0.000871000783469797,
      "loss": 0.0914,
      "step": 10200
    },
    {
      "epoch": 6.152927120669056,
      "grad_norm": 0.053466796875,
      "learning_rate": 0.0008526983019453623,
      "loss": 0.0872,
      "step": 10300
    },
    {
      "epoch": 6.212664277180406,
      "grad_norm": 0.08740234375,
      "learning_rate": 0.00083444612381587,
      "loss": 0.0903,
      "step": 10400
    },
    {
      "epoch": 6.272401433691757,
      "grad_norm": 0.0712890625,
      "learning_rate": 0.0008162504821834296,
      "loss": 0.0858,
      "step": 10500
    },
    {
      "epoch": 6.332138590203106,
      "grad_norm": 0.051513671875,
      "learning_rate": 0.00079811759084299,
      "loss": 0.0876,
      "step": 10600
    },
    {
      "epoch": 6.391875746714456,
      "grad_norm": 0.05810546875,
      "learning_rate": 0.0007800536421603317,
      "loss": 0.0874,
      "step": 10700
    },
    {
      "epoch": 6.451612903225806,
      "grad_norm": 0.060546875,
      "learning_rate": 0.0007620648049573815,
      "loss": 0.0834,
      "step": 10800
    },
    {
      "epoch": 6.511350059737157,
      "grad_norm": 0.05859375,
      "learning_rate": 0.0007441572224055644,
      "loss": 0.0814,
      "step": 10900
    },
    {
      "epoch": 6.571087216248507,
      "grad_norm": 0.06494140625,
      "learning_rate": 0.0007263370099279172,
      "loss": 0.0822,
      "step": 11000
    },
    {
      "epoch": 6.630824372759856,
      "grad_norm": 0.04833984375,
      "learning_rate": 0.0007086102531106754,
      "loss": 0.0814,
      "step": 11100
    },
    {
      "epoch": 6.690561529271207,
      "grad_norm": 0.072265625,
      "learning_rate": 0.0006909830056250527,
      "loss": 0.0803,
      "step": 11200
    },
    {
      "epoch": 6.750298685782557,
      "grad_norm": 0.052734375,
      "learning_rate": 0.0006734612871599168,
      "loss": 0.0802,
      "step": 11300
    },
    {
      "epoch": 6.810035842293907,
      "grad_norm": 0.053955078125,
      "learning_rate": 0.0006560510813660718,
      "loss": 0.0781,
      "step": 11400
    },
    {
      "epoch": 6.8697729988052565,
      "grad_norm": 0.051025390625,
      "learning_rate": 0.0006387583338128471,
      "loss": 0.0779,
      "step": 11500
    },
    {
      "epoch": 6.929510155316607,
      "grad_norm": 0.08544921875,
      "learning_rate": 0.0006215889499576897,
      "loss": 0.0783,
      "step": 11600
    },
    {
      "epoch": 6.989247311827957,
      "grad_norm": 0.0732421875,
      "learning_rate": 0.0006045487931294575,
      "loss": 0.0765,
      "step": 11700
    },
    {
      "epoch": 7.048984468339307,
      "grad_norm": 0.062255859375,
      "learning_rate": 0.0005876436825260967,
      "loss": 0.0764,
      "step": 11800
    },
    {
      "epoch": 7.1087216248506575,
      "grad_norm": 0.06298828125,
      "learning_rate": 0.000570879391227391,
      "loss": 0.0773,
      "step": 11900
    },
    {
      "epoch": 7.168458781362007,
      "grad_norm": 0.056640625,
      "learning_rate": 0.0005542616442234618,
      "loss": 0.0759,
      "step": 12000
    },
    {
      "epoch": 7.228195937873357,
      "grad_norm": 0.042236328125,
      "learning_rate": 0.0005377961164596869,
      "loss": 0.0783,
      "step": 12100
    },
    {
      "epoch": 7.287933094384707,
      "grad_norm": 0.053955078125,
      "learning_rate": 0.0005214884308987136,
      "loss": 0.0757,
      "step": 12200
    },
    {
      "epoch": 7.347670250896058,
      "grad_norm": 0.053955078125,
      "learning_rate": 0.0005053441566002214,
      "loss": 0.0768,
      "step": 12300
    },
    {
      "epoch": 7.407407407407407,
      "grad_norm": 0.0556640625,
      "learning_rate": 0.0004893688068190932,
      "loss": 0.0746,
      "step": 12400
    },
    {
      "epoch": 7.467144563918757,
      "grad_norm": 0.0537109375,
      "learning_rate": 0.0004735678371226441,
      "loss": 0.0749,
      "step": 12500
    },
    {
      "epoch": 7.526881720430108,
      "grad_norm": 0.057861328125,
      "learning_rate": 0.00045794664352755057,
      "loss": 0.0728,
      "step": 12600
    },
    {
      "epoch": 7.586618876941458,
      "grad_norm": 0.05419921875,
      "learning_rate": 0.0004425105606571145,
      "loss": 0.0732,
      "step": 12700
    },
    {
      "epoch": 7.646356033452808,
      "grad_norm": 0.0498046875,
      "learning_rate": 0.00042726485991949483,
      "loss": 0.0731,
      "step": 12800
    },
    {
      "epoch": 7.706093189964157,
      "grad_norm": 0.05859375,
      "learning_rate": 0.00041221474770752696,
      "loss": 0.0728,
      "step": 12900
    },
    {
      "epoch": 7.765830346475508,
      "grad_norm": 0.046630859375,
      "learning_rate": 0.0003973653636207437,
      "loss": 0.072,
      "step": 13000
    },
    {
      "epoch": 7.825567502986858,
      "grad_norm": 0.043212890625,
      "learning_rate": 0.0003827217787102072,
      "loss": 0.0718,
      "step": 13100
    },
    {
      "epoch": 7.885304659498208,
      "grad_norm": 0.0400390625,
      "learning_rate": 0.0003682889937467493,
      "loss": 0.0721,
      "step": 13200
    },
    {
      "epoch": 7.945041816009558,
      "grad_norm": 0.047607421875,
      "learning_rate": 0.00035407193751321286,
      "loss": 0.0703,
      "step": 13300
    },
    {
      "epoch": 1.004778972520908,
      "grad_norm": 0.057861328125,
      "learning_rate": 0.0003400754651212776,
      "loss": 0.0716,
      "step": 13400
    },
    {
      "epoch": 1.064516129032258,
      "grad_norm": 0.049072265625,
      "learning_rate": 0.0003263043563534428,
      "loss": 0.0711,
      "step": 13500
    },
    {
      "epoch": 1.124253285543608,
      "grad_norm": 0.039794921875,
      "learning_rate": 0.0003127633140307373,
      "loss": 0.0714,
      "step": 13600
    },
    {
      "epoch": 1.183990442054958,
      "grad_norm": 0.046630859375,
      "learning_rate": 0.00029945696240670904,
      "loss": 0.0728,
      "step": 13700
    },
    {
      "epoch": 1.2437275985663083,
      "grad_norm": 0.06005859375,
      "learning_rate": 0.00028638984558824776,
      "loss": 0.0733,
      "step": 13800
    },
    {
      "epoch": 1.3034647550776584,
      "grad_norm": 0.04833984375,
      "learning_rate": 0.000273566425983776,
      "loss": 0.071,
      "step": 13900
    },
    {
      "epoch": 1.3632019115890084,
      "grad_norm": 0.042724609375,
      "learning_rate": 0.000260991082779341,
      "loss": 0.0729,
      "step": 14000
    },
    {
      "epoch": 1.4229390681003584,
      "grad_norm": 0.0380859375,
      "learning_rate": 0.00024866811044312666,
      "loss": 0.0711,
      "step": 14100
    },
    {
      "epoch": 1.4826762246117084,
      "grad_norm": 0.043701171875,
      "learning_rate": 0.00023660171725889702,
      "loss": 0.0704,
      "step": 14200
    },
    {
      "epoch": 1.5424133811230587,
      "grad_norm": 0.04931640625,
      "learning_rate": 0.0002247960238888701,
      "loss": 0.0705,
      "step": 14300
    },
    {
      "epoch": 1.6021505376344085,
      "grad_norm": 0.04638671875,
      "learning_rate": 0.00021325506196651677,
      "loss": 0.0709,
      "step": 14400
    },
    {
      "epoch": 1.6618876941457588,
      "grad_norm": 0.034423828125,
      "learning_rate": 0.0002019827727197605,
      "loss": 0.0708,
      "step": 14500
    },
    {
      "epoch": 1.7216248506571086,
      "grad_norm": 0.04541015625,
      "learning_rate": 0.00019098300562505265,
      "loss": 0.0692,
      "step": 14600
    },
    {
      "epoch": 1.7813620071684588,
      "grad_norm": 0.056396484375,
      "learning_rate": 0.000180259517092779,
      "loss": 0.0702,
      "step": 14700
    },
    {
      "epoch": 1.8410991636798089,
      "grad_norm": 0.050048828125,
      "learning_rate": 0.00016981596918444952,
      "loss": 0.0701,
      "step": 14800
    },
    {
      "epoch": 1.900836320191159,
      "grad_norm": 0.049560546875,
      "learning_rate": 0.0001596559283621074,
      "loss": 0.0695,
      "step": 14900
    },
    {
      "epoch": 1.960573476702509,
      "grad_norm": 0.05224609375,
      "learning_rate": 0.00014978286427038602,
      "loss": 0.0701,
      "step": 15000
    },
    {
      "epoch": 2.020310633213859,
      "grad_norm": 0.05419921875,
      "learning_rate": 0.00014020014855162756,
      "loss": 0.0684,
      "step": 15100
    },
    {
      "epoch": 2.080047789725209,
      "grad_norm": 0.040283203125,
      "learning_rate": 0.00013091105369447166,
      "loss": 0.072,
      "step": 15200
    },
    {
      "epoch": 2.139784946236559,
      "grad_norm": 0.040283203125,
      "learning_rate": 0.00012191875191630208,
      "loss": 0.0695,
      "step": 15300
    },
    {
      "epoch": 2.1995221027479093,
      "grad_norm": 0.051025390625,
      "learning_rate": 0.00011322631407993811,
      "loss": 0.0717,
      "step": 15400
    },
    {
      "epoch": 2.2592592592592595,
      "grad_norm": 0.046142578125,
      "learning_rate": 0.00010483670864493777,
      "loss": 0.0721,
      "step": 15500
    },
    {
      "epoch": 2.3189964157706093,
      "grad_norm": 0.036865234375,
      "learning_rate": 9.675280065387115e-05,
      "loss": 0.0704,
      "step": 15600
    },
    {
      "epoch": 2.378733572281959,
      "grad_norm": 0.040771484375,
      "learning_rate": 8.897735075391155e-05,
      "loss": 0.0711,
      "step": 15700
    },
    {
      "epoch": 2.4384707287933094,
      "grad_norm": 0.0322265625,
      "learning_rate": 8.151301425407698e-05,
      "loss": 0.0698,
      "step": 15800
    },
    {
      "epoch": 2.4982078853046596,
      "grad_norm": 0.043701171875,
      "learning_rate": 7.43623402184438e-05,
      "loss": 0.07,
      "step": 15900
    },
    {
      "epoch": 2.5579450418160095,
      "grad_norm": 0.041015625,
      "learning_rate": 6.75277705956443e-05,
      "loss": 0.0694,
      "step": 16000
    },
    {
      "epoch": 2.6176821983273597,
      "grad_norm": 0.046630859375,
      "learning_rate": 6.1011639384943586e-05,
      "loss": 0.0713,
      "step": 16100
    },
    {
      "epoch": 2.67741935483871,
      "grad_norm": 0.037353515625,
      "learning_rate": 5.481617183918053e-05,
      "loss": 0.069,
      "step": 16200
    },
    {
      "epoch": 2.7371565113500598,
      "grad_norm": 0.0380859375,
      "learning_rate": 4.894348370484647e-05,
      "loss": 0.0701,
      "step": 16300
    },
    {
      "epoch": 2.7968936678614096,
      "grad_norm": 0.04296875,
      "learning_rate": 4.339558049955927e-05,
      "loss": 0.0692,
      "step": 16400
    },
    {
      "epoch": 2.85663082437276,
      "grad_norm": 0.043212890625,
      "learning_rate": 3.817435682718096e-05,
      "loss": 0.0692,
      "step": 16500
    },
    {
      "epoch": 2.91636798088411,
      "grad_norm": 0.05078125,
      "learning_rate": 3.3281595730812576e-05,
      "loss": 0.0696,
      "step": 16600
    },
    {
      "epoch": 2.97610513739546,
      "grad_norm": 0.041015625,
      "learning_rate": 2.8718968083886077e-05,
      "loss": 0.0695,
      "step": 16700
    },
    {
      "epoch": 3.03584229390681,
      "grad_norm": 0.053955078125,
      "learning_rate": 2.44880320195634e-05,
      "loss": 0.0686,
      "step": 16800
    },
    {
      "epoch": 3.09557945041816,
      "grad_norm": 0.041015625,
      "learning_rate": 2.059023239863411e-05,
      "loss": 0.0713,
      "step": 16900
    },
    {
      "epoch": 3.15531660692951,
      "grad_norm": 0.04248046875,
      "learning_rate": 1.7026900316098216e-05,
      "loss": 0.069,
      "step": 17000
    },
    {
      "epoch": 3.21505376344086,
      "grad_norm": 0.0498046875,
      "learning_rate": 1.3799252646597427e-05,
      "loss": 0.0726,
      "step": 17100
    },
    {
      "epoch": 3.2747909199522103,
      "grad_norm": 0.04248046875,
      "learning_rate": 1.0908391628854042e-05,
      "loss": 0.0703,
      "step": 17200
    },
    {
      "epoch": 3.3345280764635605,
      "grad_norm": 0.049560546875,
      "learning_rate": 8.355304489257254e-06,
      "loss": 0.0711,
      "step": 17300
    },
    {
      "epoch": 3.3942652329749103,
      "grad_norm": 0.059814453125,
      "learning_rate": 6.140863104726391e-06,
      "loss": 0.072,
      "step": 17400
    },
    {
      "epoch": 3.4540023894862606,
      "grad_norm": 0.046142578125,
      "learning_rate": 4.265823704965532e-06,
      "loss": 0.0696,
      "step": 17500
    },
    {
      "epoch": 3.5137395459976104,
      "grad_norm": 0.0693359375,
      "learning_rate": 2.730826614211979e-06,
      "loss": 0.0685,
      "step": 17600
    },
    {
      "epoch": 3.5734767025089607,
      "grad_norm": 0.055419921875,
      "learning_rate": 1.5363960325660565e-06,
      "loss": 0.07,
      "step": 17700
    },
    {
      "epoch": 3.6332138590203105,
      "grad_norm": 0.046630859375,
      "learning_rate": 6.829398569770939e-07,
      "loss": 0.0708,
      "step": 17800
    },
    {
      "epoch": 3.6929510155316607,
      "grad_norm": 0.049560546875,
      "learning_rate": 1.7074954194729043e-07,
      "loss": 0.0694,
      "step": 17900
    },
    {
      "epoch": 3.752688172043011,
      "grad_norm": 0.036865234375,
      "learning_rate": 0.0,
      "loss": 0.0694,
      "step": 18000
    }
  ],
  "logging_steps": 100,
  "max_steps": 18000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 11,
  "save_steps": 3000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": true,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.467487355285709e+17,
  "train_batch_size": 6,
  "trial_name": null,
  "trial_params": null
}