{
  "best_metric": 0.51440329218107,
  "best_model_checkpoint": "./save_phi2_ft_lora/checkpoint-2500",
  "epoch": 0.7268498328245384,
  "eval_steps": 500,
  "global_step": 2500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0029073993312981536,
      "grad_norm": 4.615232944488525,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 6.6211,
      "step": 10
    },
    {
      "epoch": 0.005814798662596307,
      "grad_norm": 5.528043746948242,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 6.5222,
      "step": 20
    },
    {
      "epoch": 0.00872219799389446,
      "grad_norm": 6.019925594329834,
      "learning_rate": 3e-06,
      "loss": 6.4104,
      "step": 30
    },
    {
      "epoch": 0.011629597325192614,
      "grad_norm": 7.163036823272705,
      "learning_rate": 4.000000000000001e-06,
      "loss": 6.0366,
      "step": 40
    },
    {
      "epoch": 0.01453699665649077,
      "grad_norm": 7.888458251953125,
      "learning_rate": 5e-06,
      "loss": 5.4618,
      "step": 50
    },
    {
      "epoch": 0.01744439598778892,
      "grad_norm": 9.86289119720459,
      "learning_rate": 6e-06,
      "loss": 4.526,
      "step": 60
    },
    {
      "epoch": 0.020351795319087075,
      "grad_norm": 9.114004135131836,
      "learning_rate": 7.000000000000001e-06,
      "loss": 3.2234,
      "step": 70
    },
    {
      "epoch": 0.02325919465038523,
      "grad_norm": 6.198110103607178,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.6796,
      "step": 80
    },
    {
      "epoch": 0.026166593981683386,
      "grad_norm": 1.2424126863479614,
      "learning_rate": 9e-06,
      "loss": 0.6189,
      "step": 90
    },
    {
      "epoch": 0.02907399331298154,
      "grad_norm": 0.20757392048835754,
      "learning_rate": 1e-05,
      "loss": 0.2989,
      "step": 100
    },
    {
      "epoch": 0.03198139264427969,
      "grad_norm": 0.19180330634117126,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 0.3434,
      "step": 110
    },
    {
      "epoch": 0.03488879197557784,
      "grad_norm": 0.17373745143413544,
      "learning_rate": 1.2e-05,
      "loss": 0.2775,
      "step": 120
    },
    {
      "epoch": 0.037796191306876,
      "grad_norm": 0.14247311651706696,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 0.291,
      "step": 130
    },
    {
      "epoch": 0.04070359063817415,
      "grad_norm": 0.1189289391040802,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 0.2549,
      "step": 140
    },
    {
      "epoch": 0.043610989969472304,
      "grad_norm": 0.11715172231197357,
      "learning_rate": 1.5e-05,
      "loss": 0.2334,
      "step": 150
    },
    {
      "epoch": 0.04651838930077046,
      "grad_norm": 0.16550108790397644,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.2515,
      "step": 160
    },
    {
      "epoch": 0.04942578863206862,
      "grad_norm": 0.13685165345668793,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 0.2757,
      "step": 170
    },
    {
      "epoch": 0.05233318796336677,
      "grad_norm": 0.13247624039649963,
      "learning_rate": 1.8e-05,
      "loss": 0.2336,
      "step": 180
    },
    {
      "epoch": 0.055240587294664925,
      "grad_norm": 0.13763906061649323,
      "learning_rate": 1.9e-05,
      "loss": 0.2169,
      "step": 190
    },
    {
      "epoch": 0.05814798662596308,
      "grad_norm": 0.1327727884054184,
      "learning_rate": 2e-05,
      "loss": 0.2007,
      "step": 200
    },
    {
      "epoch": 0.06105538595726123,
      "grad_norm": 0.1083875447511673,
      "learning_rate": 2.1e-05,
      "loss": 0.2181,
      "step": 210
    },
    {
      "epoch": 0.06396278528855938,
      "grad_norm": 0.12445604056119919,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.2969,
      "step": 220
    },
    {
      "epoch": 0.06687018461985754,
      "grad_norm": 0.15511994063854218,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 0.1868,
      "step": 230
    },
    {
      "epoch": 0.06977758395115569,
      "grad_norm": 0.13466577231884003,
      "learning_rate": 2.4e-05,
      "loss": 0.25,
      "step": 240
    },
    {
      "epoch": 0.07268498328245385,
      "grad_norm": 0.06756726652383804,
      "learning_rate": 2.5e-05,
      "loss": 0.1809,
      "step": 250
    },
    {
      "epoch": 0.075592382613752,
      "grad_norm": 0.1573372632265091,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.1963,
      "step": 260
    },
    {
      "epoch": 0.07849978194505015,
      "grad_norm": 0.13099811971187592,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 0.1984,
      "step": 270
    },
    {
      "epoch": 0.0814071812763483,
      "grad_norm": 0.11419626325368881,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.1665,
      "step": 280
    },
    {
      "epoch": 0.08431458060764646,
      "grad_norm": 0.10189209878444672,
      "learning_rate": 2.9e-05,
      "loss": 0.1749,
      "step": 290
    },
    {
      "epoch": 0.08722197993894461,
      "grad_norm": 0.12042666226625443,
      "learning_rate": 3e-05,
      "loss": 0.1528,
      "step": 300
    },
    {
      "epoch": 0.09012937927024277,
      "grad_norm": 0.08344505727291107,
      "learning_rate": 3.1e-05,
      "loss": 0.181,
      "step": 310
    },
    {
      "epoch": 0.09303677860154091,
      "grad_norm": 0.11566774547100067,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.1363,
      "step": 320
    },
    {
      "epoch": 0.09594417793283908,
      "grad_norm": 0.1531219631433487,
      "learning_rate": 3.3e-05,
      "loss": 0.1564,
      "step": 330
    },
    {
      "epoch": 0.09885157726413724,
      "grad_norm": 0.08966905623674393,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 0.1281,
      "step": 340
    },
    {
      "epoch": 0.10175897659543538,
      "grad_norm": 0.08444681763648987,
      "learning_rate": 3.5e-05,
      "loss": 0.1258,
      "step": 350
    },
    {
      "epoch": 0.10466637592673354,
      "grad_norm": 0.10482101142406464,
      "learning_rate": 3.6e-05,
      "loss": 0.1292,
      "step": 360
    },
    {
      "epoch": 0.10757377525803169,
      "grad_norm": 0.14638499915599823,
      "learning_rate": 3.7e-05,
      "loss": 0.1829,
      "step": 370
    },
    {
      "epoch": 0.11048117458932985,
      "grad_norm": 0.1461925059556961,
      "learning_rate": 3.8e-05,
      "loss": 0.2158,
      "step": 380
    },
    {
      "epoch": 0.113388573920628,
      "grad_norm": 0.16068245470523834,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 0.2219,
      "step": 390
    },
    {
      "epoch": 0.11629597325192616,
      "grad_norm": 0.13314808905124664,
      "learning_rate": 4e-05,
      "loss": 0.1622,
      "step": 400
    },
    {
      "epoch": 0.1192033725832243,
      "grad_norm": 0.13541767001152039,
      "learning_rate": 4.1e-05,
      "loss": 0.1363,
      "step": 410
    },
    {
      "epoch": 0.12211077191452246,
      "grad_norm": 0.14549389481544495,
      "learning_rate": 4.2e-05,
      "loss": 0.1664,
      "step": 420
    },
    {
      "epoch": 0.12501817124582063,
      "grad_norm": 0.09966716170310974,
      "learning_rate": 4.3e-05,
      "loss": 0.1446,
      "step": 430
    },
    {
      "epoch": 0.12792557057711876,
      "grad_norm": 0.10374356061220169,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.1302,
      "step": 440
    },
    {
      "epoch": 0.13083296990841692,
      "grad_norm": 0.10534253716468811,
      "learning_rate": 4.5e-05,
      "loss": 0.1612,
      "step": 450
    },
    {
      "epoch": 0.13374036923971508,
      "grad_norm": 0.14981906116008759,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.1782,
      "step": 460
    },
    {
      "epoch": 0.13664776857101324,
      "grad_norm": 0.08772515505552292,
      "learning_rate": 4.7e-05,
      "loss": 0.1303,
      "step": 470
    },
    {
      "epoch": 0.13955516790231137,
      "grad_norm": 0.14555956423282623,
      "learning_rate": 4.8e-05,
      "loss": 0.1259,
      "step": 480
    },
    {
      "epoch": 0.14246256723360953,
      "grad_norm": 0.08366917818784714,
      "learning_rate": 4.9e-05,
      "loss": 0.1827,
      "step": 490
    },
    {
      "epoch": 0.1453699665649077,
      "grad_norm": 0.13676565885543823,
      "learning_rate": 5e-05,
      "loss": 0.1563,
      "step": 500
    },
    {
      "epoch": 0.1453699665649077,
      "eval_accuracy": 0.4444444444444444,
      "step": 500
    },
    {
      "epoch": 0.1453699665649077,
      "eval_loss": 0.15286579728126526,
      "eval_runtime": 120.6585,
      "eval_samples_per_second": 2.014,
      "eval_steps_per_second": 2.014,
      "step": 500
    },
    {
      "epoch": 0.14827736589620585,
      "grad_norm": 0.16602879762649536,
      "learning_rate": 4.982987410683906e-05,
      "loss": 0.1322,
      "step": 510
    },
    {
      "epoch": 0.151184765227504,
      "grad_norm": 0.12974093854427338,
      "learning_rate": 4.965974821367813e-05,
      "loss": 0.1432,
      "step": 520
    },
    {
      "epoch": 0.15409216455880215,
      "grad_norm": 0.10730555653572083,
      "learning_rate": 4.948962232051719e-05,
      "loss": 0.1344,
      "step": 530
    },
    {
      "epoch": 0.1569995638901003,
      "grad_norm": 0.09881391376256943,
      "learning_rate": 4.931949642735625e-05,
      "loss": 0.1207,
      "step": 540
    },
    {
      "epoch": 0.15990696322139847,
      "grad_norm": 0.15530119836330414,
      "learning_rate": 4.9149370534195306e-05,
      "loss": 0.2084,
      "step": 550
    },
    {
      "epoch": 0.1628143625526966,
      "grad_norm": 0.1018906682729721,
      "learning_rate": 4.8979244641034366e-05,
      "loss": 0.1465,
      "step": 560
    },
    {
      "epoch": 0.16572176188399476,
      "grad_norm": 0.11174057424068451,
      "learning_rate": 4.8809118747873425e-05,
      "loss": 0.1704,
      "step": 570
    },
    {
      "epoch": 0.16862916121529292,
      "grad_norm": 0.13199737668037415,
      "learning_rate": 4.863899285471249e-05,
      "loss": 0.1376,
      "step": 580
    },
    {
      "epoch": 0.17153656054659108,
      "grad_norm": 0.12376833707094193,
      "learning_rate": 4.846886696155155e-05,
      "loss": 0.1848,
      "step": 590
    },
    {
      "epoch": 0.17444395987788922,
      "grad_norm": 0.10838288813829422,
      "learning_rate": 4.829874106839061e-05,
      "loss": 0.1327,
      "step": 600
    },
    {
      "epoch": 0.17735135920918738,
      "grad_norm": 0.09848768264055252,
      "learning_rate": 4.8128615175229676e-05,
      "loss": 0.1807,
      "step": 610
    },
    {
      "epoch": 0.18025875854048554,
      "grad_norm": 0.10199768096208572,
      "learning_rate": 4.7958489282068736e-05,
      "loss": 0.1475,
      "step": 620
    },
    {
      "epoch": 0.1831661578717837,
      "grad_norm": 0.1114463359117508,
      "learning_rate": 4.7788363388907795e-05,
      "loss": 0.1458,
      "step": 630
    },
    {
      "epoch": 0.18607355720308183,
      "grad_norm": 0.09931254386901855,
      "learning_rate": 4.7618237495746855e-05,
      "loss": 0.1572,
      "step": 640
    },
    {
      "epoch": 0.18898095653438,
      "grad_norm": 0.07883786410093307,
      "learning_rate": 4.7448111602585914e-05,
      "loss": 0.1502,
      "step": 650
    },
    {
      "epoch": 0.19188835586567815,
      "grad_norm": 0.1312653124332428,
      "learning_rate": 4.7277985709424973e-05,
      "loss": 0.1306,
      "step": 660
    },
    {
      "epoch": 0.1947957551969763,
      "grad_norm": 0.10453817993402481,
      "learning_rate": 4.710785981626404e-05,
      "loss": 0.1516,
      "step": 670
    },
    {
      "epoch": 0.19770315452827447,
      "grad_norm": 0.13967570662498474,
      "learning_rate": 4.69377339231031e-05,
      "loss": 0.1976,
      "step": 680
    },
    {
      "epoch": 0.2006105538595726,
      "grad_norm": 0.09553707391023636,
      "learning_rate": 4.676760802994216e-05,
      "loss": 0.1291,
      "step": 690
    },
    {
      "epoch": 0.20351795319087077,
      "grad_norm": 0.14968940615653992,
      "learning_rate": 4.6597482136781225e-05,
      "loss": 0.1669,
      "step": 700
    },
    {
      "epoch": 0.20642535252216893,
      "grad_norm": 0.10163428634405136,
      "learning_rate": 4.642735624362028e-05,
      "loss": 0.1727,
      "step": 710
    },
    {
      "epoch": 0.2093327518534671,
      "grad_norm": 0.13607974350452423,
      "learning_rate": 4.6257230350459343e-05,
      "loss": 0.1473,
      "step": 720
    },
    {
      "epoch": 0.21224015118476522,
      "grad_norm": 0.0766085609793663,
      "learning_rate": 4.60871044572984e-05,
      "loss": 0.1419,
      "step": 730
    },
    {
      "epoch": 0.21514755051606338,
      "grad_norm": 0.11004997789859772,
      "learning_rate": 4.591697856413746e-05,
      "loss": 0.1344,
      "step": 740
    },
    {
      "epoch": 0.21805494984736154,
      "grad_norm": 0.10307681560516357,
      "learning_rate": 4.574685267097653e-05,
      "loss": 0.1355,
      "step": 750
    },
    {
      "epoch": 0.2209623491786597,
      "grad_norm": 0.098714679479599,
      "learning_rate": 4.557672677781559e-05,
      "loss": 0.1565,
      "step": 760
    },
    {
      "epoch": 0.22386974850995783,
      "grad_norm": 0.1346523016691208,
      "learning_rate": 4.540660088465465e-05,
      "loss": 0.1675,
      "step": 770
    },
    {
      "epoch": 0.226777147841256,
      "grad_norm": 0.12962771952152252,
      "learning_rate": 4.5236474991493714e-05,
      "loss": 0.1058,
      "step": 780
    },
    {
      "epoch": 0.22968454717255415,
      "grad_norm": 0.14412884414196014,
      "learning_rate": 4.5066349098332766e-05,
      "loss": 0.198,
      "step": 790
    },
    {
      "epoch": 0.23259194650385231,
      "grad_norm": 0.14253386855125427,
      "learning_rate": 4.4896223205171826e-05,
      "loss": 0.1319,
      "step": 800
    },
    {
      "epoch": 0.23549934583515045,
      "grad_norm": 0.2203107625246048,
      "learning_rate": 4.472609731201089e-05,
      "loss": 0.1729,
      "step": 810
    },
    {
      "epoch": 0.2384067451664486,
      "grad_norm": 0.09438087791204453,
      "learning_rate": 4.455597141884995e-05,
      "loss": 0.1558,
      "step": 820
    },
    {
      "epoch": 0.24131414449774677,
      "grad_norm": 0.09754593670368195,
      "learning_rate": 4.438584552568901e-05,
      "loss": 0.1729,
      "step": 830
    },
    {
      "epoch": 0.24422154382904493,
      "grad_norm": 0.1403294950723648,
      "learning_rate": 4.421571963252808e-05,
      "loss": 0.1871,
      "step": 840
    },
    {
      "epoch": 0.24712894316034306,
      "grad_norm": 0.11251681298017502,
      "learning_rate": 4.4045593739367136e-05,
      "loss": 0.1726,
      "step": 850
    },
    {
      "epoch": 0.25003634249164125,
      "grad_norm": 0.13492991030216217,
      "learning_rate": 4.3875467846206196e-05,
      "loss": 0.1349,
      "step": 860
    },
    {
      "epoch": 0.2529437418229394,
      "grad_norm": 0.11674369871616364,
      "learning_rate": 4.3705341953045255e-05,
      "loss": 0.2088,
      "step": 870
    },
    {
      "epoch": 0.2558511411542375,
      "grad_norm": 0.09339413791894913,
      "learning_rate": 4.3535216059884315e-05,
      "loss": 0.1656,
      "step": 880
    },
    {
      "epoch": 0.2587585404855357,
      "grad_norm": 0.10234147310256958,
      "learning_rate": 4.3365090166723374e-05,
      "loss": 0.1495,
      "step": 890
    },
    {
      "epoch": 0.26166593981683384,
      "grad_norm": 0.09566229581832886,
      "learning_rate": 4.319496427356244e-05,
      "loss": 0.109,
      "step": 900
    },
    {
      "epoch": 0.26457333914813197,
      "grad_norm": 0.10038291662931442,
      "learning_rate": 4.30248383804015e-05,
      "loss": 0.1849,
      "step": 910
    },
    {
      "epoch": 0.26748073847943016,
      "grad_norm": 0.12414570152759552,
      "learning_rate": 4.285471248724056e-05,
      "loss": 0.1476,
      "step": 920
    },
    {
      "epoch": 0.2703881378107283,
      "grad_norm": 0.0866188034415245,
      "learning_rate": 4.2684586594079625e-05,
      "loss": 0.1339,
      "step": 930
    },
    {
      "epoch": 0.2732955371420265,
      "grad_norm": 0.20008312165737152,
      "learning_rate": 4.2514460700918685e-05,
      "loss": 0.1865,
      "step": 940
    },
    {
      "epoch": 0.2762029364733246,
      "grad_norm": 0.09849795699119568,
      "learning_rate": 4.2344334807757744e-05,
      "loss": 0.1293,
      "step": 950
    },
    {
      "epoch": 0.27911033580462274,
      "grad_norm": 0.11204036325216293,
      "learning_rate": 4.2174208914596803e-05,
      "loss": 0.1817,
      "step": 960
    },
    {
      "epoch": 0.28201773513592093,
      "grad_norm": 0.0960935726761818,
      "learning_rate": 4.200408302143586e-05,
      "loss": 0.1454,
      "step": 970
    },
    {
      "epoch": 0.28492513446721907,
      "grad_norm": 0.12531103193759918,
      "learning_rate": 4.183395712827492e-05,
      "loss": 0.126,
      "step": 980
    },
    {
      "epoch": 0.28783253379851725,
      "grad_norm": 0.1162460595369339,
      "learning_rate": 4.166383123511399e-05,
      "loss": 0.1634,
      "step": 990
    },
    {
      "epoch": 0.2907399331298154,
      "grad_norm": 0.06354565173387527,
      "learning_rate": 4.149370534195305e-05,
      "loss": 0.0986,
      "step": 1000
    },
    {
      "epoch": 0.2907399331298154,
      "eval_accuracy": 0.48148148148148145,
      "step": 1000
    },
    {
      "epoch": 0.2907399331298154,
      "eval_loss": 0.14855271577835083,
      "eval_runtime": 120.8042,
      "eval_samples_per_second": 2.012,
      "eval_steps_per_second": 2.012,
      "step": 1000
    },
    {
      "epoch": 0.2936473324611135,
      "grad_norm": 0.0838373601436615,
      "learning_rate": 4.132357944879211e-05,
      "loss": 0.1266,
      "step": 1010
    },
    {
      "epoch": 0.2965547317924117,
      "grad_norm": 0.10404589027166367,
      "learning_rate": 4.1153453555631173e-05,
      "loss": 0.1411,
      "step": 1020
    },
    {
      "epoch": 0.29946213112370984,
      "grad_norm": 0.137540802359581,
      "learning_rate": 4.0983327662470226e-05,
      "loss": 0.1719,
      "step": 1030
    },
    {
      "epoch": 0.302369530455008,
      "grad_norm": 0.10742737352848053,
      "learning_rate": 4.081320176930929e-05,
      "loss": 0.181,
      "step": 1040
    },
    {
      "epoch": 0.30527692978630616,
      "grad_norm": 0.14736784994602203,
      "learning_rate": 4.064307587614835e-05,
      "loss": 0.1544,
      "step": 1050
    },
    {
      "epoch": 0.3081843291176043,
      "grad_norm": 0.15068358182907104,
      "learning_rate": 4.047294998298741e-05,
      "loss": 0.1359,
      "step": 1060
    },
    {
      "epoch": 0.3110917284489025,
      "grad_norm": 0.12078270316123962,
      "learning_rate": 4.030282408982648e-05,
      "loss": 0.1304,
      "step": 1070
    },
    {
      "epoch": 0.3139991277802006,
      "grad_norm": 0.12046414613723755,
      "learning_rate": 4.013269819666554e-05,
      "loss": 0.1379,
      "step": 1080
    },
    {
      "epoch": 0.31690652711149875,
      "grad_norm": 0.13933445513248444,
      "learning_rate": 3.9962572303504596e-05,
      "loss": 0.1413,
      "step": 1090
    },
    {
      "epoch": 0.31981392644279694,
      "grad_norm": 0.09172947704792023,
      "learning_rate": 3.9792446410343656e-05,
      "loss": 0.1316,
      "step": 1100
    },
    {
      "epoch": 0.32272132577409507,
      "grad_norm": 0.11812902987003326,
      "learning_rate": 3.9622320517182715e-05,
      "loss": 0.1322,
      "step": 1110
    },
    {
      "epoch": 0.3256287251053932,
      "grad_norm": 0.1187342032790184,
      "learning_rate": 3.9452194624021774e-05,
      "loss": 0.138,
      "step": 1120
    },
    {
      "epoch": 0.3285361244366914,
      "grad_norm": 0.10506665706634521,
      "learning_rate": 3.928206873086084e-05,
      "loss": 0.1324,
      "step": 1130
    },
    {
      "epoch": 0.3314435237679895,
      "grad_norm": 0.06862190365791321,
      "learning_rate": 3.91119428376999e-05,
      "loss": 0.1375,
      "step": 1140
    },
    {
      "epoch": 0.3343509230992877,
      "grad_norm": 0.07644759863615036,
      "learning_rate": 3.894181694453896e-05,
      "loss": 0.1384,
      "step": 1150
    },
    {
      "epoch": 0.33725832243058584,
      "grad_norm": 0.12909413874149323,
      "learning_rate": 3.8771691051378026e-05,
      "loss": 0.1251,
      "step": 1160
    },
    {
      "epoch": 0.340165721761884,
      "grad_norm": 0.10902974754571915,
      "learning_rate": 3.8601565158217085e-05,
      "loss": 0.1,
      "step": 1170
    },
    {
      "epoch": 0.34307312109318217,
      "grad_norm": 0.09570310264825821,
      "learning_rate": 3.8431439265056145e-05,
      "loss": 0.1901,
      "step": 1180
    },
    {
      "epoch": 0.3459805204244803,
      "grad_norm": 0.11525869369506836,
      "learning_rate": 3.8261313371895204e-05,
      "loss": 0.1072,
      "step": 1190
    },
    {
      "epoch": 0.34888791975577843,
      "grad_norm": 0.1647326499223709,
      "learning_rate": 3.809118747873426e-05,
      "loss": 0.2477,
      "step": 1200
    },
    {
      "epoch": 0.3517953190870766,
      "grad_norm": 0.1333259642124176,
      "learning_rate": 3.792106158557332e-05,
      "loss": 0.1682,
      "step": 1210
    },
    {
      "epoch": 0.35470271841837475,
      "grad_norm": 0.11220316588878632,
      "learning_rate": 3.775093569241239e-05,
      "loss": 0.1399,
      "step": 1220
    },
    {
      "epoch": 0.35761011774967294,
      "grad_norm": 0.11679007858037949,
      "learning_rate": 3.758080979925145e-05,
      "loss": 0.1792,
      "step": 1230
    },
    {
      "epoch": 0.3605175170809711,
      "grad_norm": 0.11699705570936203,
      "learning_rate": 3.741068390609051e-05,
      "loss": 0.159,
      "step": 1240
    },
    {
      "epoch": 0.3634249164122692,
      "grad_norm": 0.13930341601371765,
      "learning_rate": 3.7240558012929574e-05,
      "loss": 0.1233,
      "step": 1250
    },
    {
      "epoch": 0.3663323157435674,
      "grad_norm": 0.11168822646141052,
      "learning_rate": 3.7070432119768633e-05,
      "loss": 0.1277,
      "step": 1260
    },
    {
      "epoch": 0.3692397150748655,
      "grad_norm": 0.10844167321920395,
      "learning_rate": 3.6900306226607686e-05,
      "loss": 0.1857,
      "step": 1270
    },
    {
      "epoch": 0.37214711440616366,
      "grad_norm": 0.1075616255402565,
      "learning_rate": 3.673018033344675e-05,
      "loss": 0.1169,
      "step": 1280
    },
    {
      "epoch": 0.37505451373746185,
      "grad_norm": 0.12448868900537491,
      "learning_rate": 3.656005444028581e-05,
      "loss": 0.2439,
      "step": 1290
    },
    {
      "epoch": 0.37796191306876,
      "grad_norm": 0.10500267148017883,
      "learning_rate": 3.638992854712487e-05,
      "loss": 0.117,
      "step": 1300
    },
    {
      "epoch": 0.38086931240005817,
      "grad_norm": 0.12791551649570465,
      "learning_rate": 3.621980265396394e-05,
      "loss": 0.13,
      "step": 1310
    },
    {
      "epoch": 0.3837767117313563,
      "grad_norm": 0.1264408826828003,
      "learning_rate": 3.6049676760803e-05,
      "loss": 0.1121,
      "step": 1320
    },
    {
      "epoch": 0.38668411106265443,
      "grad_norm": 0.1253873109817505,
      "learning_rate": 3.5879550867642056e-05,
      "loss": 0.1384,
      "step": 1330
    },
    {
      "epoch": 0.3895915103939526,
      "grad_norm": 0.08832169324159622,
      "learning_rate": 3.570942497448112e-05,
      "loss": 0.1477,
      "step": 1340
    },
    {
      "epoch": 0.39249890972525076,
      "grad_norm": 0.14027167856693268,
      "learning_rate": 3.5539299081320175e-05,
      "loss": 0.2171,
      "step": 1350
    },
    {
      "epoch": 0.39540630905654894,
      "grad_norm": 0.11315055191516876,
      "learning_rate": 3.536917318815924e-05,
      "loss": 0.1606,
      "step": 1360
    },
    {
      "epoch": 0.3983137083878471,
      "grad_norm": 0.09444567561149597,
      "learning_rate": 3.51990472949983e-05,
      "loss": 0.1284,
      "step": 1370
    },
    {
      "epoch": 0.4012211077191452,
      "grad_norm": 0.11262746155261993,
      "learning_rate": 3.502892140183736e-05,
      "loss": 0.1411,
      "step": 1380
    },
    {
      "epoch": 0.4041285070504434,
      "grad_norm": 0.17679522931575775,
      "learning_rate": 3.4858795508676426e-05,
      "loss": 0.1981,
      "step": 1390
    },
    {
      "epoch": 0.40703590638174153,
      "grad_norm": 0.18890735507011414,
      "learning_rate": 3.4688669615515486e-05,
      "loss": 0.1676,
      "step": 1400
    },
    {
      "epoch": 0.40994330571303966,
      "grad_norm": 0.09281571209430695,
      "learning_rate": 3.4518543722354545e-05,
      "loss": 0.1136,
      "step": 1410
    },
    {
      "epoch": 0.41285070504433785,
      "grad_norm": 0.13167564570903778,
      "learning_rate": 3.4348417829193604e-05,
      "loss": 0.1586,
      "step": 1420
    },
    {
      "epoch": 0.415758104375636,
      "grad_norm": 0.09986082464456558,
      "learning_rate": 3.4178291936032664e-05,
      "loss": 0.1607,
      "step": 1430
    },
    {
      "epoch": 0.4186655037069342,
      "grad_norm": 0.13981035351753235,
      "learning_rate": 3.400816604287172e-05,
      "loss": 0.1439,
      "step": 1440
    },
    {
      "epoch": 0.4215729030382323,
      "grad_norm": 0.11107143759727478,
      "learning_rate": 3.383804014971079e-05,
      "loss": 0.1382,
      "step": 1450
    },
    {
      "epoch": 0.42448030236953044,
      "grad_norm": 0.06783778220415115,
      "learning_rate": 3.366791425654985e-05,
      "loss": 0.1138,
      "step": 1460
    },
    {
      "epoch": 0.4273877017008286,
      "grad_norm": 0.11150864511728287,
      "learning_rate": 3.349778836338891e-05,
      "loss": 0.1709,
      "step": 1470
    },
    {
      "epoch": 0.43029510103212676,
      "grad_norm": 0.1245250254869461,
      "learning_rate": 3.3327662470227975e-05,
      "loss": 0.1323,
      "step": 1480
    },
    {
      "epoch": 0.4332025003634249,
      "grad_norm": 0.13299217820167542,
      "learning_rate": 3.3157536577067034e-05,
      "loss": 0.1311,
      "step": 1490
    },
    {
      "epoch": 0.4361098996947231,
      "grad_norm": 0.09196653217077255,
      "learning_rate": 3.298741068390609e-05,
      "loss": 0.121,
      "step": 1500
    },
    {
      "epoch": 0.4361098996947231,
      "eval_accuracy": 0.46502057613168724,
      "step": 1500
    },
    {
      "epoch": 0.4361098996947231,
      "eval_loss": 0.1465623825788498,
      "eval_runtime": 120.6266,
      "eval_samples_per_second": 2.014,
      "eval_steps_per_second": 2.014,
      "step": 1500
    },
    {
      "epoch": 0.4390172990260212,
      "grad_norm": 0.08671022951602936,
      "learning_rate": 3.281728479074515e-05,
      "loss": 0.1774,
      "step": 1510
    },
    {
      "epoch": 0.4419246983573194,
      "grad_norm": 0.1013597920536995,
      "learning_rate": 3.264715889758421e-05,
      "loss": 0.147,
      "step": 1520
    },
    {
      "epoch": 0.44483209768861753,
      "grad_norm": 0.13395969569683075,
      "learning_rate": 3.247703300442327e-05,
      "loss": 0.141,
      "step": 1530
    },
    {
      "epoch": 0.44773949701991567,
      "grad_norm": 0.08484592288732529,
      "learning_rate": 3.230690711126234e-05,
      "loss": 0.1315,
      "step": 1540
    },
    {
      "epoch": 0.45064689635121385,
      "grad_norm": 0.10540632903575897,
      "learning_rate": 3.21367812181014e-05,
      "loss": 0.2186,
      "step": 1550
    },
    {
      "epoch": 0.453554295682512,
      "grad_norm": 0.08647104352712631,
      "learning_rate": 3.196665532494046e-05,
      "loss": 0.1464,
      "step": 1560
    },
    {
      "epoch": 0.4564616950138101,
      "grad_norm": 0.11477908492088318,
      "learning_rate": 3.179652943177952e-05,
      "loss": 0.1229,
      "step": 1570
    },
    {
      "epoch": 0.4593690943451083,
      "grad_norm": 0.139444500207901,
      "learning_rate": 3.162640353861858e-05,
      "loss": 0.1722,
      "step": 1580
    },
    {
      "epoch": 0.46227649367640644,
      "grad_norm": 0.12302656471729279,
      "learning_rate": 3.1456277645457635e-05,
      "loss": 0.161,
      "step": 1590
    },
    {
      "epoch": 0.46518389300770463,
      "grad_norm": 0.13583935797214508,
      "learning_rate": 3.12861517522967e-05,
      "loss": 0.2173,
      "step": 1600
    },
    {
      "epoch": 0.46809129233900276,
      "grad_norm": 0.10586286336183548,
      "learning_rate": 3.111602585913576e-05,
      "loss": 0.1394,
      "step": 1610
    },
    {
      "epoch": 0.4709986916703009,
      "grad_norm": 0.1407371312379837,
      "learning_rate": 3.094589996597482e-05,
      "loss": 0.1452,
      "step": 1620
    },
    {
      "epoch": 0.4739060910015991,
      "grad_norm": 0.15980814397335052,
      "learning_rate": 3.0775774072813886e-05,
      "loss": 0.1929,
      "step": 1630
    },
    {
      "epoch": 0.4768134903328972,
      "grad_norm": 0.1253122240304947,
      "learning_rate": 3.0605648179652946e-05,
      "loss": 0.1423,
      "step": 1640
    },
    {
      "epoch": 0.4797208896641954,
      "grad_norm": 0.17438402771949768,
      "learning_rate": 3.043552228649201e-05,
      "loss": 0.1604,
      "step": 1650
    },
    {
      "epoch": 0.48262828899549354,
      "grad_norm": 0.13970227539539337,
      "learning_rate": 3.0265396393331068e-05,
      "loss": 0.1355,
      "step": 1660
    },
    {
      "epoch": 0.48553568832679167,
      "grad_norm": 0.12440519034862518,
      "learning_rate": 3.0095270500170124e-05,
      "loss": 0.1693,
      "step": 1670
    },
    {
      "epoch": 0.48844308765808986,
      "grad_norm": 0.136091947555542,
      "learning_rate": 2.9925144607009187e-05,
      "loss": 0.118,
      "step": 1680
    },
    {
      "epoch": 0.491350486989388,
      "grad_norm": 0.13912110030651093,
      "learning_rate": 2.975501871384825e-05,
      "loss": 0.1481,
      "step": 1690
    },
    {
      "epoch": 0.4942578863206861,
      "grad_norm": 0.10817007720470428,
      "learning_rate": 2.958489282068731e-05,
      "loss": 0.1343,
      "step": 1700
    },
    {
      "epoch": 0.4971652856519843,
      "grad_norm": 0.12969084084033966,
      "learning_rate": 2.941476692752637e-05,
      "loss": 0.1333,
      "step": 1710
    },
    {
      "epoch": 0.5000726849832825,
      "grad_norm": 0.13414813578128815,
      "learning_rate": 2.9244641034365434e-05,
      "loss": 0.1526,
      "step": 1720
    },
    {
      "epoch": 0.5029800843145806,
      "grad_norm": 0.13201922178268433,
      "learning_rate": 2.9074515141204494e-05,
      "loss": 0.1567,
      "step": 1730
    },
    {
      "epoch": 0.5058874836458788,
      "grad_norm": 0.14282363653182983,
      "learning_rate": 2.8904389248043557e-05,
      "loss": 0.1667,
      "step": 1740
    },
    {
      "epoch": 0.5087948829771769,
      "grad_norm": 0.09702622145414352,
      "learning_rate": 2.8734263354882613e-05,
      "loss": 0.1246,
      "step": 1750
    },
    {
      "epoch": 0.511702282308475,
      "grad_norm": 0.1287912130355835,
      "learning_rate": 2.8564137461721676e-05,
      "loss": 0.099,
      "step": 1760
    },
    {
      "epoch": 0.5146096816397733,
      "grad_norm": 0.10358964651823044,
      "learning_rate": 2.8394011568560735e-05,
      "loss": 0.122,
      "step": 1770
    },
    {
      "epoch": 0.5175170809710714,
      "grad_norm": 0.12403380870819092,
      "learning_rate": 2.8223885675399798e-05,
      "loss": 0.1731,
      "step": 1780
    },
    {
      "epoch": 0.5204244803023695,
      "grad_norm": 0.11310795694589615,
      "learning_rate": 2.8053759782238857e-05,
      "loss": 0.1394,
      "step": 1790
    },
    {
      "epoch": 0.5233318796336677,
      "grad_norm": 0.15226072072982788,
      "learning_rate": 2.788363388907792e-05,
      "loss": 0.1521,
      "step": 1800
    },
    {
      "epoch": 0.5262392789649658,
      "grad_norm": 0.11242180317640305,
      "learning_rate": 2.7713507995916983e-05,
      "loss": 0.167,
      "step": 1810
    },
    {
      "epoch": 0.5291466782962639,
      "grad_norm": 0.10229990631341934,
      "learning_rate": 2.7543382102756042e-05,
      "loss": 0.115,
      "step": 1820
    },
    {
      "epoch": 0.5320540776275622,
      "grad_norm": 0.11430121213197708,
      "learning_rate": 2.7373256209595098e-05,
      "loss": 0.1323,
      "step": 1830
    },
    {
      "epoch": 0.5349614769588603,
      "grad_norm": 0.0750517025589943,
      "learning_rate": 2.720313031643416e-05,
      "loss": 0.1896,
      "step": 1840
    },
    {
      "epoch": 0.5378688762901584,
      "grad_norm": 0.10639439523220062,
      "learning_rate": 2.7033004423273224e-05,
      "loss": 0.1511,
      "step": 1850
    },
    {
      "epoch": 0.5407762756214566,
      "grad_norm": 0.10970495641231537,
      "learning_rate": 2.6862878530112283e-05,
      "loss": 0.1456,
      "step": 1860
    },
    {
      "epoch": 0.5436836749527547,
      "grad_norm": 0.14610768854618073,
      "learning_rate": 2.6692752636951346e-05,
      "loss": 0.1407,
      "step": 1870
    },
    {
      "epoch": 0.546591074284053,
      "grad_norm": 0.0982876867055893,
      "learning_rate": 2.652262674379041e-05,
      "loss": 0.1484,
      "step": 1880
    },
    {
      "epoch": 0.5494984736153511,
      "grad_norm": 0.10405632108449936,
      "learning_rate": 2.635250085062947e-05,
      "loss": 0.147,
      "step": 1890
    },
    {
      "epoch": 0.5524058729466492,
      "grad_norm": 0.1323215663433075,
      "learning_rate": 2.618237495746853e-05,
      "loss": 0.1866,
      "step": 1900
    },
    {
      "epoch": 0.5553132722779474,
      "grad_norm": 0.08775471895933151,
      "learning_rate": 2.6012249064307587e-05,
      "loss": 0.098,
      "step": 1910
    },
    {
      "epoch": 0.5582206716092455,
      "grad_norm": 0.09187202900648117,
      "learning_rate": 2.584212317114665e-05,
      "loss": 0.1555,
      "step": 1920
    },
    {
      "epoch": 0.5611280709405437,
      "grad_norm": 0.11878269165754318,
      "learning_rate": 2.567199727798571e-05,
      "loss": 0.1181,
      "step": 1930
    },
    {
      "epoch": 0.5640354702718419,
      "grad_norm": 0.07616838067770004,
      "learning_rate": 2.5501871384824772e-05,
      "loss": 0.1979,
      "step": 1940
    },
    {
      "epoch": 0.56694286960314,
      "grad_norm": 0.12157191336154938,
      "learning_rate": 2.533174549166383e-05,
      "loss": 0.1479,
      "step": 1950
    },
    {
      "epoch": 0.5698502689344381,
      "grad_norm": 0.08891995251178741,
      "learning_rate": 2.5161619598502894e-05,
      "loss": 0.1184,
      "step": 1960
    },
    {
      "epoch": 0.5727576682657363,
      "grad_norm": 0.12914909422397614,
      "learning_rate": 2.4991493705341954e-05,
      "loss": 0.1533,
      "step": 1970
    },
    {
      "epoch": 0.5756650675970345,
      "grad_norm": 0.1337321698665619,
      "learning_rate": 2.4821367812181017e-05,
      "loss": 0.1564,
      "step": 1980
    },
    {
      "epoch": 0.5785724669283326,
      "grad_norm": 0.13483311235904694,
      "learning_rate": 2.4651241919020076e-05,
      "loss": 0.1648,
      "step": 1990
    },
    {
      "epoch": 0.5814798662596308,
      "grad_norm": 0.10340965539216995,
      "learning_rate": 2.448111602585914e-05,
      "loss": 0.125,
      "step": 2000
    },
    {
      "epoch": 0.5814798662596308,
      "eval_accuracy": 0.49794238683127573,
      "step": 2000
    },
    {
      "epoch": 0.5814798662596308,
      "eval_loss": 0.14546644687652588,
      "eval_runtime": 121.0771,
      "eval_samples_per_second": 2.007,
      "eval_steps_per_second": 2.007,
      "step": 2000
    },
    {
      "epoch": 0.5843872655909289,
      "grad_norm": 0.10115203261375427,
      "learning_rate": 2.4310990132698198e-05,
      "loss": 0.1131,
      "step": 2010
    },
    {
      "epoch": 0.587294664922227,
      "grad_norm": 0.11895623058080673,
      "learning_rate": 2.4140864239537258e-05,
      "loss": 0.1153,
      "step": 2020
    },
    {
      "epoch": 0.5902020642535252,
      "grad_norm": 0.0888802632689476,
      "learning_rate": 2.397073834637632e-05,
      "loss": 0.1441,
      "step": 2030
    },
    {
      "epoch": 0.5931094635848234,
      "grad_norm": 0.12660273909568787,
      "learning_rate": 2.3800612453215383e-05,
      "loss": 0.1529,
      "step": 2040
    },
    {
      "epoch": 0.5960168629161215,
      "grad_norm": 0.10489198565483093,
      "learning_rate": 2.363048656005444e-05,
      "loss": 0.1342,
      "step": 2050
    },
    {
      "epoch": 0.5989242622474197,
      "grad_norm": 0.13198301196098328,
      "learning_rate": 2.3460360666893502e-05,
      "loss": 0.1622,
      "step": 2060
    },
    {
      "epoch": 0.6018316615787178,
      "grad_norm": 0.08899589627981186,
      "learning_rate": 2.3290234773732565e-05,
      "loss": 0.1691,
      "step": 2070
    },
    {
      "epoch": 0.604739060910016,
      "grad_norm": 0.11825095117092133,
      "learning_rate": 2.3120108880571624e-05,
      "loss": 0.1397,
      "step": 2080
    },
    {
      "epoch": 0.6076464602413142,
      "grad_norm": 0.11306699365377426,
      "learning_rate": 2.2949982987410684e-05,
      "loss": 0.1317,
      "step": 2090
    },
    {
      "epoch": 0.6105538595726123,
      "grad_norm": 0.085251085460186,
      "learning_rate": 2.2779857094249747e-05,
      "loss": 0.1163,
      "step": 2100
    },
    {
      "epoch": 0.6134612589039105,
      "grad_norm": 0.09645051509141922,
      "learning_rate": 2.2609731201088806e-05,
      "loss": 0.1138,
      "step": 2110
    },
    {
      "epoch": 0.6163686582352086,
      "grad_norm": 0.10509444028139114,
      "learning_rate": 2.243960530792787e-05,
      "loss": 0.149,
      "step": 2120
    },
    {
      "epoch": 0.6192760575665067,
      "grad_norm": 0.13281555473804474,
      "learning_rate": 2.2269479414766928e-05,
      "loss": 0.1502,
      "step": 2130
    },
    {
      "epoch": 0.622183456897805,
      "grad_norm": 0.08020918071269989,
      "learning_rate": 2.209935352160599e-05,
      "loss": 0.1294,
      "step": 2140
    },
    {
      "epoch": 0.6250908562291031,
      "grad_norm": 0.10006445646286011,
      "learning_rate": 2.192922762844505e-05,
      "loss": 0.1153,
      "step": 2150
    },
    {
      "epoch": 0.6279982555604012,
      "grad_norm": 0.20892204344272614,
      "learning_rate": 2.1759101735284113e-05,
      "loss": 0.1805,
      "step": 2160
    },
    {
      "epoch": 0.6309056548916994,
      "grad_norm": 0.13679496943950653,
      "learning_rate": 2.1588975842123173e-05,
      "loss": 0.1123,
      "step": 2170
    },
    {
      "epoch": 0.6338130542229975,
      "grad_norm": 0.20436090230941772,
      "learning_rate": 2.1418849948962232e-05,
      "loss": 0.2282,
      "step": 2180
    },
    {
      "epoch": 0.6367204535542956,
      "grad_norm": 0.0943446233868599,
      "learning_rate": 2.1248724055801295e-05,
      "loss": 0.1288,
      "step": 2190
    },
    {
      "epoch": 0.6396278528855939,
      "grad_norm": 0.08362103998661041,
      "learning_rate": 2.1078598162640358e-05,
      "loss": 0.1278,
      "step": 2200
    },
    {
      "epoch": 0.642535252216892,
      "grad_norm": 0.11366961151361465,
      "learning_rate": 2.0908472269479414e-05,
      "loss": 0.115,
      "step": 2210
    },
    {
      "epoch": 0.6454426515481901,
      "grad_norm": 0.090823233127594,
      "learning_rate": 2.0738346376318477e-05,
      "loss": 0.1179,
      "step": 2220
    },
    {
      "epoch": 0.6483500508794883,
      "grad_norm": 0.12734675407409668,
      "learning_rate": 2.056822048315754e-05,
      "loss": 0.1367,
      "step": 2230
    },
    {
      "epoch": 0.6512574502107864,
      "grad_norm": 0.5848974585533142,
      "learning_rate": 2.03980945899966e-05,
      "loss": 0.1157,
      "step": 2240
    },
    {
      "epoch": 0.6541648495420846,
      "grad_norm": 0.08575470000505447,
      "learning_rate": 2.0227968696835658e-05,
      "loss": 0.1735,
      "step": 2250
    },
    {
      "epoch": 0.6570722488733828,
      "grad_norm": 0.09076444059610367,
      "learning_rate": 2.005784280367472e-05,
      "loss": 0.1414,
      "step": 2260
    },
    {
      "epoch": 0.6599796482046809,
      "grad_norm": 0.15823446214199066,
      "learning_rate": 1.988771691051378e-05,
      "loss": 0.1464,
      "step": 2270
    },
    {
      "epoch": 0.662887047535979,
      "grad_norm": 0.1579420417547226,
      "learning_rate": 1.9717591017352843e-05,
      "loss": 0.1669,
      "step": 2280
    },
    {
      "epoch": 0.6657944468672772,
      "grad_norm": 0.11068382859230042,
      "learning_rate": 1.9547465124191903e-05,
      "loss": 0.1743,
      "step": 2290
    },
    {
      "epoch": 0.6687018461985754,
      "grad_norm": 0.09305164217948914,
      "learning_rate": 1.9377339231030962e-05,
      "loss": 0.1481,
      "step": 2300
    },
    {
      "epoch": 0.6716092455298736,
      "grad_norm": 0.1341511458158493,
      "learning_rate": 1.9207213337870025e-05,
      "loss": 0.1199,
      "step": 2310
    },
    {
      "epoch": 0.6745166448611717,
      "grad_norm": 0.09602607041597366,
      "learning_rate": 1.9037087444709088e-05,
      "loss": 0.1393,
      "step": 2320
    },
    {
      "epoch": 0.6774240441924698,
      "grad_norm": 0.14141052961349487,
      "learning_rate": 1.8866961551548147e-05,
      "loss": 0.1189,
      "step": 2330
    },
    {
      "epoch": 0.680331443523768,
      "grad_norm": 0.10962352156639099,
      "learning_rate": 1.8696835658387207e-05,
      "loss": 0.1972,
      "step": 2340
    },
    {
      "epoch": 0.6832388428550662,
      "grad_norm": 0.11629267781972885,
      "learning_rate": 1.852670976522627e-05,
      "loss": 0.1648,
      "step": 2350
    },
    {
      "epoch": 0.6861462421863643,
      "grad_norm": 0.14257384836673737,
      "learning_rate": 1.8356583872065332e-05,
      "loss": 0.1906,
      "step": 2360
    },
    {
      "epoch": 0.6890536415176625,
      "grad_norm": 0.1146107092499733,
      "learning_rate": 1.8186457978904388e-05,
      "loss": 0.1632,
      "step": 2370
    },
    {
      "epoch": 0.6919610408489606,
      "grad_norm": 0.16012772917747498,
      "learning_rate": 1.801633208574345e-05,
      "loss": 0.138,
      "step": 2380
    },
    {
      "epoch": 0.6948684401802587,
      "grad_norm": 0.14589470624923706,
      "learning_rate": 1.7846206192582514e-05,
      "loss": 0.1451,
      "step": 2390
    },
    {
      "epoch": 0.6977758395115569,
      "grad_norm": 0.1040879562497139,
      "learning_rate": 1.7676080299421573e-05,
      "loss": 0.1402,
      "step": 2400
    },
    {
      "epoch": 0.7006832388428551,
      "grad_norm": 0.11645939201116562,
      "learning_rate": 1.7505954406260633e-05,
      "loss": 0.1637,
      "step": 2410
    },
    {
      "epoch": 0.7035906381741532,
      "grad_norm": 0.1045243889093399,
      "learning_rate": 1.7335828513099695e-05,
      "loss": 0.1235,
      "step": 2420
    },
    {
      "epoch": 0.7064980375054514,
      "grad_norm": 0.08904137462377548,
      "learning_rate": 1.7165702619938755e-05,
      "loss": 0.1348,
      "step": 2430
    },
    {
      "epoch": 0.7094054368367495,
      "grad_norm": 0.1161481961607933,
      "learning_rate": 1.6995576726777818e-05,
      "loss": 0.1225,
      "step": 2440
    },
    {
      "epoch": 0.7123128361680476,
      "grad_norm": 0.10629335045814514,
      "learning_rate": 1.6825450833616877e-05,
      "loss": 0.1173,
      "step": 2450
    },
    {
      "epoch": 0.7152202354993459,
      "grad_norm": 0.11692572385072708,
      "learning_rate": 1.6655324940455937e-05,
      "loss": 0.1225,
      "step": 2460
    },
    {
      "epoch": 0.718127634830644,
      "grad_norm": 0.13012786209583282,
      "learning_rate": 1.6485199047295e-05,
      "loss": 0.1336,
      "step": 2470
    },
    {
      "epoch": 0.7210350341619421,
      "grad_norm": 0.1442546844482422,
      "learning_rate": 1.6315073154134062e-05,
      "loss": 0.1755,
      "step": 2480
    },
    {
      "epoch": 0.7239424334932403,
      "grad_norm": 0.10278443247079849,
      "learning_rate": 1.614494726097312e-05,
      "loss": 0.1191,
      "step": 2490
    },
    {
      "epoch": 0.7268498328245384,
      "grad_norm": 0.12166904658079147,
      "learning_rate": 1.597482136781218e-05,
      "loss": 0.1458,
      "step": 2500
    },
    {
      "epoch": 0.7268498328245384,
      "eval_accuracy": 0.51440329218107,
      "step": 2500
    },
    {
      "epoch": 0.7268498328245384,
      "eval_loss": 0.14491653442382812,
      "eval_runtime": 121.2093,
      "eval_samples_per_second": 2.005,
      "eval_steps_per_second": 2.005,
      "step": 2500
    }
  ],
  "logging_steps": 10,
  "max_steps": 3439,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.286826483712e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}