{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 1484,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.00019999751023913506,
      "loss": 1.726,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019999004108051845,
      "loss": 1.6889,
      "step": 20
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019997759289607853,
      "loss": 1.7184,
      "step": 30
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019996016630567534,
      "loss": 1.4497,
      "step": 40
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019993776217706971,
      "loss": 1.4543,
      "step": 50
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019991038162588018,
      "loss": 1.5685,
      "step": 60
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019987802601552718,
      "loss": 1.5524,
      "step": 70
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019984069695716533,
      "loss": 1.477,
      "step": 80
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001997983963096033,
      "loss": 1.4757,
      "step": 90
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019975112617921098,
      "loss": 1.4486,
      "step": 100
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001996988889198147,
      "loss": 1.461,
      "step": 110
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001996416871325803,
      "loss": 1.4589,
      "step": 120
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019957952366588306,
      "loss": 1.4624,
      "step": 130
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001995124016151664,
      "loss": 1.399,
      "step": 140
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001994403243227874,
      "loss": 1.424,
      "step": 150
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019936329537785052,
      "loss": 1.3211,
      "step": 160
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019928131861602876,
      "loss": 1.279,
      "step": 170
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001991943981193728,
      "loss": 1.3186,
      "step": 180
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019910253821610771,
      "loss": 1.2727,
      "step": 190
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019900574348041727,
      "loss": 1.3562,
      "step": 200
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001989040187322164,
      "loss": 1.4529,
      "step": 210
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019879736903691107,
      "loss": 1.2631,
      "step": 220
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019868579970514598,
      "loss": 1.285,
      "step": 230
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019856931629254028,
      "loss": 1.3466,
      "step": 240
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019844792459941082,
      "loss": 1.3003,
      "step": 250
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019832163067048334,
      "loss": 1.2173,
      "step": 260
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019819044079459142,
      "loss": 1.2895,
      "step": 270
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019805436150436352,
      "loss": 1.3731,
      "step": 280
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019791339957589738,
      "loss": 1.1251,
      "step": 290
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019776756202842294,
      "loss": 1.2362,
      "step": 300
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001976168561239525,
      "loss": 1.3371,
      "step": 310
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019746128936691938,
      "loss": 1.2906,
      "step": 320
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019730086950380403,
      "loss": 1.1032,
      "step": 330
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019713560452274838,
      "loss": 1.1211,
      "step": 340
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019696550265315806,
      "loss": 1.1438,
      "step": 350
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019679057236529266,
      "loss": 1.2266,
      "step": 360
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019661082236984386,
      "loss": 1.3422,
      "step": 370
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019642626161750176,
      "loss": 1.3473,
      "step": 380
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00019623689929850908,
      "loss": 1.2263,
      "step": 390
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001960427448422037,
      "loss": 1.0773,
      "step": 400
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019584380791654894,
      "loss": 1.099,
      "step": 410
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00019564009842765225,
      "loss": 1.1754,
      "step": 420
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00019543162651927188,
      "loss": 1.2885,
      "step": 430
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00019521840257231182,
      "loss": 1.2681,
      "step": 440
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00019500043720430482,
      "loss": 1.1195,
      "step": 450
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00019477774126888377,
      "loss": 1.1689,
      "step": 460
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00019455032585524116,
      "loss": 1.0643,
      "step": 470
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001943182022875769,
      "loss": 1.0415,
      "step": 480
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00019408138212453454,
      "loss": 1.1249,
      "step": 490
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00019383987715862553,
      "loss": 0.9767,
      "step": 500
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00019359369941564212,
      "loss": 1.0936,
      "step": 510
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0001933428611540585,
      "loss": 1.1746,
      "step": 520
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00019308737486442045,
      "loss": 1.0178,
      "step": 530
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00019282725326872323,
      "loss": 0.91,
      "step": 540
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00019256250931977826,
      "loss": 0.9748,
      "step": 550
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00019229315620056806,
      "loss": 1.1454,
      "step": 560
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001920192073235896,
      "loss": 0.9785,
      "step": 570
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00019174067633018682,
      "loss": 1.0508,
      "step": 580
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019145757708987105,
      "loss": 1.0429,
      "step": 590
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001911699236996305,
      "loss": 0.8784,
      "step": 600
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00019087773048322818,
      "loss": 1.0023,
      "step": 610
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00019058101199048887,
      "loss": 0.8826,
      "step": 620
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00019027978299657436,
      "loss": 1.1243,
      "step": 630
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00018997405850124785,
      "loss": 1.1292,
      "step": 640
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.000189663853728127,
      "loss": 1.1113,
      "step": 650
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00018934918412392596,
      "loss": 0.9625,
      "step": 660
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00018903006535768598,
      "loss": 0.9192,
      "step": 670
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00018870651331999542,
      "loss": 1.1748,
      "step": 680
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00018837854412219826,
      "loss": 0.7678,
      "step": 690
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00018804617409559198,
      "loss": 0.9359,
      "step": 700
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0001877094197906143,
      "loss": 0.7756,
      "step": 710
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00018736829797601903,
      "loss": 1.0965,
      "step": 720
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.000187022825638041,
      "loss": 0.7658,
      "step": 730
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00018667301997955037,
      "loss": 0.8303,
      "step": 740
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00018631889841919596,
      "loss": 0.6526,
      "step": 750
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00018596047859053777,
      "loss": 0.8849,
      "step": 760
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00018559777834116904,
      "loss": 0.8624,
      "step": 770
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00018523081573182753,
      "loss": 1.0776,
      "step": 780
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00018485960903549613,
      "loss": 1.0613,
      "step": 790
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00018448417673649293,
      "loss": 0.7977,
      "step": 800
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0001841045375295508,
      "loss": 1.0102,
      "step": 810
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0001837207103188866,
      "loss": 0.9193,
      "step": 820
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00018333271421725966,
      "loss": 0.791,
      "step": 830
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0001829405685450202,
      "loss": 0.7282,
      "step": 840
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00018254429282914717,
      "loss": 0.909,
      "step": 850
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00018214390680227588,
      "loss": 0.7082,
      "step": 860
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00018173943040171567,
      "loss": 0.7878,
      "step": 870
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00018133088376845672,
      "loss": 0.7337,
      "step": 880
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0001809182872461674,
      "loss": 0.8767,
      "step": 890
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00018050166138018127,
      "loss": 0.9053,
      "step": 900
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00018008102691647378,
      "loss": 0.9425,
      "step": 910
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00017965640480062947,
      "loss": 0.8695,
      "step": 920
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0001792278161767989,
      "loss": 0.8363,
      "step": 930
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00017879528238664568,
      "loss": 0.8174,
      "step": 940
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00017835882496828391,
      "loss": 0.8841,
      "step": 950
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00017791846565520558,
      "loss": 1.0871,
      "step": 960
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00017747422637519837,
      "loss": 0.8819,
      "step": 970
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00017702612924925376,
      "loss": 0.9717,
      "step": 980
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0001765741965904655,
      "loss": 0.9332,
      "step": 990
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00017611845090291856,
      "loss": 0.9255,
      "step": 1000
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00017565891488056847,
      "loss": 0.8273,
      "step": 1010
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0001751956114061113,
      "loss": 1.0004,
      "step": 1020
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00017472856354984427,
      "loss": 0.6283,
      "step": 1030
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00017425779456851684,
      "loss": 0.7763,
      "step": 1040
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00017378332790417273,
      "loss": 0.7186,
      "step": 1050
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00017330518718298264,
      "loss": 0.6694,
      "step": 1060
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00017282339621406764,
      "loss": 0.7898,
      "step": 1070
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00017233797898831373,
      "loss": 0.8441,
      "step": 1080
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00017184895967717716,
      "loss": 0.8105,
      "step": 1090
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00017135636263148078,
      "loss": 0.6729,
      "step": 1100
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00017086021238020153,
      "loss": 0.81,
      "step": 1110
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00017036053362924896,
      "loss": 0.5832,
      "step": 1120
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00016985735126023505,
      "loss": 0.597,
      "step": 1130
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00016935069032923526,
      "loss": 0.714,
      "step": 1140
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0001688405760655407,
      "loss": 1.0678,
      "step": 1150
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.000168327033870402,
      "loss": 0.5946,
      "step": 1160
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00016781008931576432,
      "loss": 0.8521,
      "step": 1170
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00016728976814299413,
      "loss": 0.8702,
      "step": 1180
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0001667660962615973,
      "loss": 0.6877,
      "step": 1190
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00016623909974792888,
      "loss": 0.787,
      "step": 1200
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00016570880484389488,
      "loss": 0.6594,
      "step": 1210
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00016517523795564528,
      "loss": 0.7966,
      "step": 1220
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00016463842565225914,
      "loss": 0.8111,
      "step": 1230
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00016409839466442178,
      "loss": 0.7495,
      "step": 1240
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00016355517188309363,
      "loss": 0.5614,
      "step": 1250
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00016300878435817113,
      "loss": 0.8317,
      "step": 1260
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00016245925929713977,
      "loss": 0.7025,
      "step": 1270
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00016190662406371937,
      "loss": 0.8666,
      "step": 1280
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0001613509061765015,
      "loss": 0.6441,
      "step": 1290
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00016079213330757913,
      "loss": 0.491,
      "step": 1300
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00016023033328116862,
      "loss": 0.5865,
      "step": 1310
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00015966553407222443,
      "loss": 0.5936,
      "step": 1320
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00015909776380504585,
      "loss": 0.72,
      "step": 1330
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00015852705075187674,
      "loss": 0.6545,
      "step": 1340
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00015795342333149755,
      "loss": 0.4781,
      "step": 1350
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0001573769101078104,
      "loss": 0.858,
      "step": 1360
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00015679753978841654,
      "loss": 0.712,
      "step": 1370
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00015621534122318683,
      "loss": 0.5954,
      "step": 1380
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.0001556303434028254,
      "loss": 0.7352,
      "step": 1390
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00015504257545742584,
      "loss": 0.5647,
      "step": 1400
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0001544520666550207,
      "loss": 0.7925,
      "step": 1410
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00015385884640012408,
      "loss": 0.8434,
      "step": 1420
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.00015326294423226755,
      "loss": 0.7084,
      "step": 1430
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00015266438982452897,
      "loss": 0.75,
      "step": 1440
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0001520632129820552,
      "loss": 0.896,
      "step": 1450
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0001514594436405777,
      "loss": 0.664,
      "step": 1460
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00015085311186492206,
      "loss": 0.7149,
      "step": 1470
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.00015024424784751078,
      "loss": 0.7642,
      "step": 1480
    }
  ],
  "logging_steps": 10,
  "max_steps": 4452,
  "num_train_epochs": 6,
  "save_steps": 500,
  "total_flos": 7755360321208320.0,
  "trial_name": null,
  "trial_params": null
}