{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 1552,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012890750886239123,
      "grad_norm": 1.7974083423614502,
      "learning_rate": 1.153846153846154e-05,
      "loss": 2.5309,
      "step": 10
    },
    {
      "epoch": 0.025781501772478246,
      "grad_norm": 0.9546365737915039,
      "learning_rate": 2.435897435897436e-05,
      "loss": 2.2805,
      "step": 20
    },
    {
      "epoch": 0.03867225265871737,
      "grad_norm": 0.6726247072219849,
      "learning_rate": 3.717948717948718e-05,
      "loss": 1.9329,
      "step": 30
    },
    {
      "epoch": 0.05156300354495649,
      "grad_norm": 0.5635246634483337,
      "learning_rate": 5e-05,
      "loss": 1.7205,
      "step": 40
    },
    {
      "epoch": 0.06445375443119562,
      "grad_norm": 0.48018646240234375,
      "learning_rate": 6.282051282051282e-05,
      "loss": 1.6227,
      "step": 50
    },
    {
      "epoch": 0.07734450531743474,
      "grad_norm": 0.4588874578475952,
      "learning_rate": 7.564102564102564e-05,
      "loss": 1.565,
      "step": 60
    },
    {
      "epoch": 0.09023525620367387,
      "grad_norm": 0.5382615923881531,
      "learning_rate": 8.846153846153847e-05,
      "loss": 1.5151,
      "step": 70
    },
    {
      "epoch": 0.10312600708991299,
      "grad_norm": 0.5467047691345215,
      "learning_rate": 0.00010128205128205129,
      "loss": 1.4629,
      "step": 80
    },
    {
      "epoch": 0.11601675797615212,
      "grad_norm": 0.5823647379875183,
      "learning_rate": 0.0001141025641025641,
      "loss": 1.457,
      "step": 90
    },
    {
      "epoch": 0.12890750886239125,
      "grad_norm": 0.6547259092330933,
      "learning_rate": 0.00012692307692307693,
      "loss": 1.4192,
      "step": 100
    },
    {
      "epoch": 0.14179825974863036,
      "grad_norm": 0.5140829086303711,
      "learning_rate": 0.00013974358974358974,
      "loss": 1.3869,
      "step": 110
    },
    {
      "epoch": 0.15468901063486948,
      "grad_norm": 0.6194220185279846,
      "learning_rate": 0.00015256410256410255,
      "loss": 1.365,
      "step": 120
    },
    {
      "epoch": 0.1675797615211086,
      "grad_norm": 0.6340938806533813,
      "learning_rate": 0.0001653846153846154,
      "loss": 1.3559,
      "step": 130
    },
    {
      "epoch": 0.18047051240734774,
      "grad_norm": 0.5935661792755127,
      "learning_rate": 0.00017820512820512823,
      "loss": 1.3447,
      "step": 140
    },
    {
      "epoch": 0.19336126329358685,
      "grad_norm": 0.5271995663642883,
      "learning_rate": 0.00019102564102564104,
      "loss": 1.3229,
      "step": 150
    },
    {
      "epoch": 0.20625201417982597,
      "grad_norm": 0.5766036510467529,
      "learning_rate": 0.00019999772102388783,
      "loss": 1.3238,
      "step": 160
    },
    {
      "epoch": 0.2191427650660651,
      "grad_norm": 0.4888124167919159,
      "learning_rate": 0.0001999572087826214,
      "loss": 1.3371,
      "step": 170
    },
    {
      "epoch": 0.23203351595230423,
      "grad_norm": 0.5345163345336914,
      "learning_rate": 0.00019986607624302306,
      "loss": 1.3455,
      "step": 180
    },
    {
      "epoch": 0.24492426683854335,
      "grad_norm": 0.4851045310497284,
      "learning_rate": 0.00019972436955640487,
      "loss": 1.3176,
      "step": 190
    },
    {
      "epoch": 0.2578150177247825,
      "grad_norm": 0.47015997767448425,
      "learning_rate": 0.0001995321604858227,
      "loss": 1.3131,
      "step": 200
    },
    {
      "epoch": 0.2707057686110216,
      "grad_norm": 0.5002295970916748,
      "learning_rate": 0.00019928954636973373,
      "loss": 1.2997,
      "step": 210
    },
    {
      "epoch": 0.2835965194972607,
      "grad_norm": 0.46887412667274475,
      "learning_rate": 0.00019899665007270265,
      "loss": 1.279,
      "step": 220
    },
    {
      "epoch": 0.2964872703834998,
      "grad_norm": 0.4887183606624603,
      "learning_rate": 0.00019865361992318033,
      "loss": 1.2773,
      "step": 230
    },
    {
      "epoch": 0.30937802126973896,
      "grad_norm": 0.49127480387687683,
      "learning_rate": 0.00019826062963838753,
      "loss": 1.2674,
      "step": 240
    },
    {
      "epoch": 0.3222687721559781,
      "grad_norm": 0.49845078587532043,
      "learning_rate": 0.0001978178782363411,
      "loss": 1.2723,
      "step": 250
    },
    {
      "epoch": 0.3351595230422172,
      "grad_norm": 0.4858417809009552,
      "learning_rate": 0.00019732558993506723,
      "loss": 1.273,
      "step": 260
    },
    {
      "epoch": 0.34805027392845633,
      "grad_norm": 0.47399166226387024,
      "learning_rate": 0.00019678401403905307,
      "loss": 1.2629,
      "step": 270
    },
    {
      "epoch": 0.3609410248146955,
      "grad_norm": 0.47289639711380005,
      "learning_rate": 0.0001961934248129941,
      "loss": 1.2408,
      "step": 280
    },
    {
      "epoch": 0.37383177570093457,
      "grad_norm": 0.48805466294288635,
      "learning_rate": 0.00019555412134290102,
      "loss": 1.2421,
      "step": 290
    },
    {
      "epoch": 0.3867225265871737,
      "grad_norm": 0.47072649002075195,
      "learning_rate": 0.00019486642738463674,
      "loss": 1.2583,
      "step": 300
    },
    {
      "epoch": 0.39961327747341285,
      "grad_norm": 0.4364190101623535,
      "learning_rate": 0.00019413069119995994,
      "loss": 1.2377,
      "step": 310
    },
    {
      "epoch": 0.41250402835965194,
      "grad_norm": 0.4522920250892639,
      "learning_rate": 0.0001933472853801586,
      "loss": 1.2331,
      "step": 320
    },
    {
      "epoch": 0.4253947792458911,
      "grad_norm": 0.46202462911605835,
      "learning_rate": 0.0001925166066573624,
      "loss": 1.2277,
      "step": 330
    },
    {
      "epoch": 0.4382855301321302,
      "grad_norm": 0.43247494101524353,
      "learning_rate": 0.00019163907570362963,
      "loss": 1.2369,
      "step": 340
    },
    {
      "epoch": 0.4511762810183693,
      "grad_norm": 0.47149762511253357,
      "learning_rate": 0.00019071513691791079,
      "loss": 1.2394,
      "step": 350
    },
    {
      "epoch": 0.46406703190460846,
      "grad_norm": 0.44876205921173096,
      "learning_rate": 0.00018974525820099607,
      "loss": 1.2318,
      "step": 360
    },
    {
      "epoch": 0.47695778279084755,
      "grad_norm": 0.44522625207901,
      "learning_rate": 0.00018872993071856114,
      "loss": 1.2214,
      "step": 370
    },
    {
      "epoch": 0.4898485336770867,
      "grad_norm": 0.45371952652931213,
      "learning_rate": 0.0001876696686524314,
      "loss": 1.2152,
      "step": 380
    },
    {
      "epoch": 0.5027392845633258,
      "grad_norm": 0.45091456174850464,
      "learning_rate": 0.00018656500894018987,
      "loss": 1.2025,
      "step": 390
    },
    {
      "epoch": 0.515630035449565,
      "grad_norm": 0.47521355748176575,
      "learning_rate": 0.00018541651100326175,
      "loss": 1.2107,
      "step": 400
    },
    {
      "epoch": 0.528520786335804,
      "grad_norm": 0.4451088607311249,
      "learning_rate": 0.0001842247564636121,
      "loss": 1.1974,
      "step": 410
    },
    {
      "epoch": 0.5414115372220432,
      "grad_norm": 0.4933655858039856,
      "learning_rate": 0.0001829903488492013,
      "loss": 1.1847,
      "step": 420
    },
    {
      "epoch": 0.5543022881082823,
      "grad_norm": 0.4385446608066559,
      "learning_rate": 0.00018171391328834638,
      "loss": 1.1925,
      "step": 430
    },
    {
      "epoch": 0.5671930389945214,
      "grad_norm": 0.46878549456596375,
      "learning_rate": 0.0001803960961931439,
      "loss": 1.176,
      "step": 440
    },
    {
      "epoch": 0.5800837898807606,
      "grad_norm": 0.45197296142578125,
      "learning_rate": 0.000179037564932114,
      "loss": 1.1888,
      "step": 450
    },
    {
      "epoch": 0.5929745407669996,
      "grad_norm": 0.4496542811393738,
      "learning_rate": 0.00017763900749223196,
      "loss": 1.1823,
      "step": 460
    },
    {
      "epoch": 0.6058652916532388,
      "grad_norm": 0.4356934428215027,
      "learning_rate": 0.00017620113213051797,
      "loss": 1.1877,
      "step": 470
    },
    {
      "epoch": 0.6187560425394779,
      "grad_norm": 0.46125900745391846,
      "learning_rate": 0.00017472466701536193,
      "loss": 1.1797,
      "step": 480
    },
    {
      "epoch": 0.6316467934257171,
      "grad_norm": 0.45797720551490784,
      "learning_rate": 0.0001732103598577645,
      "loss": 1.1777,
      "step": 490
    },
    {
      "epoch": 0.6445375443119562,
      "grad_norm": 0.4385370910167694,
      "learning_rate": 0.0001716589775326817,
      "loss": 1.1562,
      "step": 500
    },
    {
      "epoch": 0.6574282951981953,
      "grad_norm": 0.46976742148399353,
      "learning_rate": 0.00017007130569066413,
      "loss": 1.1677,
      "step": 510
    },
    {
      "epoch": 0.6703190460844344,
      "grad_norm": 0.46103382110595703,
      "learning_rate": 0.00016844814835998825,
      "loss": 1.1776,
      "step": 520
    },
    {
      "epoch": 0.6832097969706735,
      "grad_norm": 0.5240194201469421,
      "learning_rate": 0.00016679032753948056,
      "loss": 1.1489,
      "step": 530
    },
    {
      "epoch": 0.6961005478569127,
      "grad_norm": 0.4437713027000427,
      "learning_rate": 0.00016509868278224125,
      "loss": 1.1721,
      "step": 540
    },
    {
      "epoch": 0.7089912987431518,
      "grad_norm": 0.4481850862503052,
      "learning_rate": 0.00016337407077047784,
      "loss": 1.1613,
      "step": 550
    },
    {
      "epoch": 0.721882049629391,
      "grad_norm": 0.46106868982315063,
      "learning_rate": 0.00016161736488166462,
      "loss": 1.155,
      "step": 560
    },
    {
      "epoch": 0.73477280051563,
      "grad_norm": 0.4505125880241394,
      "learning_rate": 0.000159829454746247,
      "loss": 1.159,
      "step": 570
    },
    {
      "epoch": 0.7476635514018691,
      "grad_norm": 0.4489360749721527,
      "learning_rate": 0.00015801124579711525,
      "loss": 1.1794,
      "step": 580
    },
    {
      "epoch": 0.7605543022881083,
      "grad_norm": 0.4428081214427948,
      "learning_rate": 0.0001561636588110753,
      "loss": 1.1524,
      "step": 590
    },
    {
      "epoch": 0.7734450531743474,
      "grad_norm": 0.4341617226600647,
      "learning_rate": 0.00015428762944254932,
      "loss": 1.1497,
      "step": 600
    },
    {
      "epoch": 0.7863358040605866,
      "grad_norm": 0.43959757685661316,
      "learning_rate": 0.00015238410774974186,
      "loss": 1.1364,
      "step": 610
    },
    {
      "epoch": 0.7992265549468257,
      "grad_norm": 0.456399530172348,
      "learning_rate": 0.00015045405771351193,
      "loss": 1.1266,
      "step": 620
    },
    {
      "epoch": 0.8121173058330647,
      "grad_norm": 0.4572042226791382,
      "learning_rate": 0.00014849845674919364,
      "loss": 1.1417,
      "step": 630
    },
    {
      "epoch": 0.8250080567193039,
      "grad_norm": 0.4575168788433075,
      "learning_rate": 0.00014651829521161424,
      "loss": 1.1532,
      "step": 640
    },
    {
      "epoch": 0.837898807605543,
      "grad_norm": 0.4344440996646881,
      "learning_rate": 0.00014451457589355872,
      "loss": 1.137,
      "step": 650
    },
    {
      "epoch": 0.8507895584917822,
      "grad_norm": 0.4362059235572815,
      "learning_rate": 0.00014248831351793592,
      "loss": 1.1408,
      "step": 660
    },
    {
      "epoch": 0.8636803093780213,
      "grad_norm": 0.46403059363365173,
      "learning_rate": 0.0001404405342239028,
      "loss": 1.1227,
      "step": 670
    },
    {
      "epoch": 0.8765710602642603,
      "grad_norm": 0.47248131036758423,
      "learning_rate": 0.0001383722750472074,
      "loss": 1.1363,
      "step": 680
    },
    {
      "epoch": 0.8894618111504995,
      "grad_norm": 0.4404482841491699,
      "learning_rate": 0.00013628458339501348,
      "loss": 1.1179,
      "step": 690
    },
    {
      "epoch": 0.9023525620367386,
      "grad_norm": 0.4384572207927704,
      "learning_rate": 0.00013417851651547307,
      "loss": 1.1066,
      "step": 700
    },
    {
      "epoch": 0.9152433129229778,
      "grad_norm": 0.4435371458530426,
      "learning_rate": 0.0001320551409623149,
      "loss": 1.12,
      "step": 710
    },
    {
      "epoch": 0.9281340638092169,
      "grad_norm": 0.5222971439361572,
      "learning_rate": 0.00012991553205472092,
      "loss": 1.1164,
      "step": 720
    },
    {
      "epoch": 0.941024814695456,
      "grad_norm": 0.45858514308929443,
      "learning_rate": 0.00012776077333276326,
      "loss": 1.1182,
      "step": 730
    },
    {
      "epoch": 0.9539155655816951,
      "grad_norm": 0.45299065113067627,
      "learning_rate": 0.0001255919560086783,
      "loss": 1.1174,
      "step": 740
    },
    {
      "epoch": 0.9668063164679342,
      "grad_norm": 0.4541768729686737,
      "learning_rate": 0.0001234101784142553,
      "loss": 1.1221,
      "step": 750
    },
    {
      "epoch": 0.9796970673541734,
      "grad_norm": 0.4411795139312744,
      "learning_rate": 0.0001212165454446196,
      "loss": 1.1113,
      "step": 760
    },
    {
      "epoch": 0.9925878182404125,
      "grad_norm": 0.4533502161502838,
      "learning_rate": 0.00011901216799869188,
      "loss": 1.1122,
      "step": 770
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6748553734614313,
      "eval_first_token_accuracy": 0.8449519230769231,
      "eval_loss": 1.118744134902954,
      "eval_runtime": 727.7965,
      "eval_samples_per_second": 6.851,
      "eval_steps_per_second": 0.429,
      "step": 776
    },
    {
      "epoch": 1.0051563003544957,
      "grad_norm": 0.4265609085559845,
      "learning_rate": 0.0001167981624166072,
      "loss": 1.0876,
      "step": 780
    },
    {
      "epoch": 1.0180470512407347,
      "grad_norm": 0.48834115266799927,
      "learning_rate": 0.00011457564991437823,
      "loss": 1.0156,
      "step": 790
    },
    {
      "epoch": 1.030937802126974,
      "grad_norm": 0.4989129602909088,
      "learning_rate": 0.00011234575601608957,
      "loss": 1.0072,
      "step": 800
    },
    {
      "epoch": 1.043828553013213,
      "grad_norm": 0.4992086887359619,
      "learning_rate": 0.00011010960998391002,
      "loss": 1.0185,
      "step": 810
    },
    {
      "epoch": 1.0567193038994522,
      "grad_norm": 0.5244722366333008,
      "learning_rate": 0.00010786834424621211,
      "loss": 1.013,
      "step": 820
    },
    {
      "epoch": 1.0696100547856913,
      "grad_norm": 0.5480940937995911,
      "learning_rate": 0.000105623093824088,
      "loss": 1.0116,
      "step": 830
    },
    {
      "epoch": 1.0825008056719303,
      "grad_norm": 0.49391430616378784,
      "learning_rate": 0.00010337499575655249,
      "loss": 0.9852,
      "step": 840
    },
    {
      "epoch": 1.0953915565581696,
      "grad_norm": 0.48984748125076294,
      "learning_rate": 0.00010112518852472414,
      "loss": 1.0052,
      "step": 850
    },
    {
      "epoch": 1.1082823074444086,
      "grad_norm": 0.5330230593681335,
      "learning_rate": 9.887481147527588e-05,
      "loss": 1.0058,
      "step": 860
    },
    {
      "epoch": 1.1211730583306478,
      "grad_norm": 0.4981665313243866,
      "learning_rate": 9.66250042434475e-05,
      "loss": 1.0037,
      "step": 870
    },
    {
      "epoch": 1.1340638092168869,
      "grad_norm": 0.5282273888587952,
      "learning_rate": 9.437690617591202e-05,
      "loss": 0.9962,
      "step": 880
    },
    {
      "epoch": 1.1469545601031261,
      "grad_norm": 0.5284985303878784,
      "learning_rate": 9.213165575378793e-05,
      "loss": 1.0142,
      "step": 890
    },
    {
      "epoch": 1.1598453109893652,
      "grad_norm": 0.5249062776565552,
      "learning_rate": 8.989039001609e-05,
      "loss": 1.0031,
      "step": 900
    },
    {
      "epoch": 1.1727360618756042,
      "grad_norm": 0.5115840435028076,
      "learning_rate": 8.765424398391047e-05,
      "loss": 1.0149,
      "step": 910
    },
    {
      "epoch": 1.1856268127618435,
      "grad_norm": 0.5123730897903442,
      "learning_rate": 8.54243500856218e-05,
      "loss": 0.9993,
      "step": 920
    },
    {
      "epoch": 1.1985175636480825,
      "grad_norm": 0.5423418879508972,
      "learning_rate": 8.320183758339284e-05,
      "loss": 0.9911,
      "step": 930
    },
    {
      "epoch": 1.2114083145343217,
      "grad_norm": 0.5046626925468445,
      "learning_rate": 8.098783200130813e-05,
      "loss": 0.9909,
      "step": 940
    },
    {
      "epoch": 1.2242990654205608,
      "grad_norm": 0.5180662870407104,
      "learning_rate": 7.878345455538043e-05,
      "loss": 0.9852,
      "step": 950
    },
    {
      "epoch": 1.2371898163067998,
      "grad_norm": 0.5029054880142212,
      "learning_rate": 7.65898215857447e-05,
      "loss": 0.984,
      "step": 960
    },
    {
      "epoch": 1.250080567193039,
      "grad_norm": 0.5463522672653198,
      "learning_rate": 7.440804399132173e-05,
      "loss": 0.994,
      "step": 970
    },
    {
      "epoch": 1.262971318079278,
      "grad_norm": 0.517109215259552,
      "learning_rate": 7.223922666723678e-05,
      "loss": 0.9825,
      "step": 980
    },
    {
      "epoch": 1.2758620689655173,
      "grad_norm": 0.5118828415870667,
      "learning_rate": 7.00844679452791e-05,
      "loss": 0.9941,
      "step": 990
    },
    {
      "epoch": 1.2887528198517564,
      "grad_norm": 0.5242361426353455,
      "learning_rate": 6.794485903768513e-05,
      "loss": 0.9787,
      "step": 1000
    },
    {
      "epoch": 1.3016435707379954,
      "grad_norm": 0.5021597743034363,
      "learning_rate": 6.5821483484527e-05,
      "loss": 0.9871,
      "step": 1010
    },
    {
      "epoch": 1.3145343216242347,
      "grad_norm": 0.5013926029205322,
      "learning_rate": 6.371541660498652e-05,
      "loss": 0.9859,
      "step": 1020
    },
    {
      "epoch": 1.3274250725104737,
      "grad_norm": 0.5455625057220459,
      "learning_rate": 6.162772495279265e-05,
      "loss": 0.9731,
      "step": 1030
    },
    {
      "epoch": 1.340315823396713,
      "grad_norm": 0.5966176986694336,
      "learning_rate": 5.955946577609721e-05,
      "loss": 1.0026,
      "step": 1040
    },
    {
      "epoch": 1.353206574282952,
      "grad_norm": 0.5418857336044312,
      "learning_rate": 5.75116864820641e-05,
      "loss": 0.9798,
      "step": 1050
    },
    {
      "epoch": 1.366097325169191,
      "grad_norm": 0.5456270575523376,
      "learning_rate": 5.548542410644132e-05,
      "loss": 0.9737,
      "step": 1060
    },
    {
      "epoch": 1.3789880760554303,
      "grad_norm": 0.5252659916877747,
      "learning_rate": 5.3481704788385786e-05,
      "loss": 0.9775,
      "step": 1070
    },
    {
      "epoch": 1.3918788269416693,
      "grad_norm": 0.5047706961631775,
      "learning_rate": 5.150154325080636e-05,
      "loss": 0.9755,
      "step": 1080
    },
    {
      "epoch": 1.4047695778279086,
      "grad_norm": 0.5461093187332153,
      "learning_rate": 4.954594228648807e-05,
      "loss": 0.9716,
      "step": 1090
    },
    {
      "epoch": 1.4176603287141476,
      "grad_norm": 0.5116148591041565,
      "learning_rate": 4.761589225025811e-05,
      "loss": 0.9821,
      "step": 1100
    },
    {
      "epoch": 1.4305510796003866,
      "grad_norm": 0.5131816267967224,
      "learning_rate": 4.571237055745074e-05,
      "loss": 0.9857,
      "step": 1110
    },
    {
      "epoch": 1.4434418304866259,
      "grad_norm": 0.5409175157546997,
      "learning_rate": 4.383634118892472e-05,
      "loss": 0.9768,
      "step": 1120
    },
    {
      "epoch": 1.456332581372865,
      "grad_norm": 0.5277559757232666,
      "learning_rate": 4.1988754202884775e-05,
      "loss": 0.965,
      "step": 1130
    },
    {
      "epoch": 1.4692233322591042,
      "grad_norm": 0.522885799407959,
      "learning_rate": 4.0170545253752986e-05,
      "loss": 0.9576,
      "step": 1140
    },
    {
      "epoch": 1.4821140831453432,
      "grad_norm": 0.5148813128471375,
      "learning_rate": 3.838263511833542e-05,
      "loss": 0.9676,
      "step": 1150
    },
    {
      "epoch": 1.4950048340315822,
      "grad_norm": 0.5167680978775024,
      "learning_rate": 3.662592922952218e-05,
      "loss": 0.9694,
      "step": 1160
    },
    {
      "epoch": 1.5078955849178215,
      "grad_norm": 0.5245492458343506,
      "learning_rate": 3.4901317217758764e-05,
      "loss": 0.9603,
      "step": 1170
    },
    {
      "epoch": 1.5207863358040608,
      "grad_norm": 0.51069176197052,
      "learning_rate": 3.3209672460519425e-05,
      "loss": 0.9687,
      "step": 1180
    },
    {
      "epoch": 1.5336770866902998,
      "grad_norm": 0.5380834341049194,
      "learning_rate": 3.155185164001176e-05,
      "loss": 0.9653,
      "step": 1190
    },
    {
      "epoch": 1.5465678375765388,
      "grad_norm": 0.5268071889877319,
      "learning_rate": 2.9928694309335914e-05,
      "loss": 0.9785,
      "step": 1200
    },
    {
      "epoch": 1.5594585884627779,
      "grad_norm": 0.5809852480888367,
      "learning_rate": 2.8341022467318335e-05,
      "loss": 0.9628,
      "step": 1210
    },
    {
      "epoch": 1.572349339349017,
      "grad_norm": 0.5032438635826111,
      "learning_rate": 2.678964014223553e-05,
      "loss": 0.9641,
      "step": 1220
    },
    {
      "epoch": 1.5852400902352564,
      "grad_norm": 0.5497922897338867,
      "learning_rate": 2.52753329846381e-05,
      "loss": 0.969,
      "step": 1230
    },
    {
      "epoch": 1.5981308411214954,
      "grad_norm": 0.5357956886291504,
      "learning_rate": 2.3798867869482044e-05,
      "loss": 0.9598,
      "step": 1240
    },
    {
      "epoch": 1.6110215920077344,
      "grad_norm": 0.5199883580207825,
      "learning_rate": 2.2360992507768052e-05,
      "loss": 0.9733,
      "step": 1250
    },
    {
      "epoch": 1.6239123428939735,
      "grad_norm": 0.5282153487205505,
      "learning_rate": 2.096243506788602e-05,
      "loss": 0.9565,
      "step": 1260
    },
    {
      "epoch": 1.6368030937802127,
      "grad_norm": 0.5048473477363586,
      "learning_rate": 1.9603903806856106e-05,
      "loss": 0.9506,
      "step": 1270
    },
    {
      "epoch": 1.649693844666452,
      "grad_norm": 0.5167466998100281,
      "learning_rate": 1.8286086711653605e-05,
      "loss": 0.9618,
      "step": 1280
    },
    {
      "epoch": 1.662584595552691,
      "grad_norm": 0.5307776927947998,
      "learning_rate": 1.7009651150798712e-05,
      "loss": 0.9708,
      "step": 1290
    },
    {
      "epoch": 1.67547534643893,
      "grad_norm": 0.5388936400413513,
      "learning_rate": 1.577524353638791e-05,
      "loss": 0.9672,
      "step": 1300
    },
    {
      "epoch": 1.688366097325169,
      "grad_norm": 0.5254285931587219,
      "learning_rate": 1.4583488996738293e-05,
      "loss": 0.9615,
      "step": 1310
    },
    {
      "epoch": 1.7012568482114083,
      "grad_norm": 0.5476789474487305,
      "learning_rate": 1.3434991059810153e-05,
      "loss": 0.9772,
      "step": 1320
    },
    {
      "epoch": 1.7141475990976476,
      "grad_norm": 0.5789813995361328,
      "learning_rate": 1.2330331347568636e-05,
      "loss": 0.9613,
      "step": 1330
    },
    {
      "epoch": 1.7270383499838866,
      "grad_norm": 0.5327284336090088,
      "learning_rate": 1.1270069281438866e-05,
      "loss": 0.96,
      "step": 1340
    },
    {
      "epoch": 1.7399291008701256,
      "grad_norm": 0.5267541408538818,
      "learning_rate": 1.0254741799003976e-05,
      "loss": 0.9668,
      "step": 1350
    },
    {
      "epoch": 1.7528198517563647,
      "grad_norm": 0.5468846559524536,
      "learning_rate": 9.284863082089224e-06,
      "loss": 0.9686,
      "step": 1360
    },
    {
      "epoch": 1.765710602642604,
      "grad_norm": 0.6118249297142029,
      "learning_rate": 8.360924296370376e-06,
      "loss": 0.9679,
      "step": 1370
    },
    {
      "epoch": 1.7786013535288432,
      "grad_norm": 0.535074770450592,
      "learning_rate": 7.4833933426376345e-06,
      "loss": 0.957,
      "step": 1380
    },
    {
      "epoch": 1.7914921044150822,
      "grad_norm": 0.5529636144638062,
      "learning_rate": 6.652714619841405e-06,
      "loss": 0.9498,
      "step": 1390
    },
    {
      "epoch": 1.8043828553013213,
      "grad_norm": 0.5263587236404419,
      "learning_rate": 5.869308800040074e-06,
      "loss": 0.9551,
      "step": 1400
    },
    {
      "epoch": 1.8172736061875603,
      "grad_norm": 0.5330998301506042,
      "learning_rate": 5.133572615363269e-06,
      "loss": 0.9545,
      "step": 1410
    },
    {
      "epoch": 1.8301643570737995,
      "grad_norm": 0.5292595624923706,
      "learning_rate": 4.445878657098978e-06,
      "loss": 0.958,
      "step": 1420
    },
    {
      "epoch": 1.8430551079600388,
      "grad_norm": 0.536263644695282,
      "learning_rate": 3.806575187005901e-06,
      "loss": 0.96,
      "step": 1430
    },
    {
      "epoch": 1.8559458588462778,
      "grad_norm": 0.5184710025787354,
      "learning_rate": 3.2159859609469436e-06,
      "loss": 0.9556,
      "step": 1440
    },
    {
      "epoch": 1.8688366097325169,
      "grad_norm": 0.5328414440155029,
      "learning_rate": 2.6744100649327974e-06,
      "loss": 0.9576,
      "step": 1450
    },
    {
      "epoch": 1.881727360618756,
      "grad_norm": 0.5515352487564087,
      "learning_rate": 2.1821217636589176e-06,
      "loss": 0.9769,
      "step": 1460
    },
    {
      "epoch": 1.8946181115049952,
      "grad_norm": 0.5316532850265503,
      "learning_rate": 1.7393703616124802e-06,
      "loss": 0.9587,
      "step": 1470
    },
    {
      "epoch": 1.9075088623912344,
      "grad_norm": 0.521430492401123,
      "learning_rate": 1.3463800768196866e-06,
      "loss": 0.9687,
      "step": 1480
    },
    {
      "epoch": 1.9203996132774734,
      "grad_norm": 0.5210091471672058,
      "learning_rate": 1.0033499272973701e-06,
      "loss": 0.9604,
      "step": 1490
    },
    {
      "epoch": 1.9332903641637125,
      "grad_norm": 0.530375063419342,
      "learning_rate": 7.104536302662834e-07,
      "loss": 0.9459,
      "step": 1500
    },
    {
      "epoch": 1.9461811150499515,
      "grad_norm": 0.5609223246574402,
      "learning_rate": 4.678395141773373e-07,
      "loss": 0.9529,
      "step": 1510
    },
    {
      "epoch": 1.9590718659361908,
      "grad_norm": 0.5311603546142578,
      "learning_rate": 2.756304435951429e-07,
      "loss": 0.9477,
      "step": 1520
    },
    {
      "epoch": 1.97196261682243,
      "grad_norm": 0.561936616897583,
      "learning_rate": 1.3392375697696136e-07,
      "loss": 0.9538,
      "step": 1530
    },
    {
      "epoch": 1.984853367708669,
      "grad_norm": 0.5377177000045776,
      "learning_rate": 4.279121737859049e-08,
      "loss": 0.9633,
      "step": 1540
    },
    {
      "epoch": 1.997744118594908,
      "grad_norm": 0.5239057540893555,
      "learning_rate": 2.2789761121688735e-09,
      "loss": 0.9598,
      "step": 1550
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6875442401796923,
      "eval_first_token_accuracy": 0.8729967948717948,
      "eval_loss": 1.0595165491104126,
      "eval_runtime": 684.7375,
      "eval_samples_per_second": 7.282,
      "eval_steps_per_second": 0.456,
      "step": 1552
    }
  ],
  "logging_steps": 10,
  "max_steps": 1552,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0014393801042297e+19,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}