{
  "best_metric": 0.3944380581378937,
  "best_model_checkpoint": "./FT_models/[LDH]0226_origin_data/checkpoint-3000",
  "epoch": 2.8483985765124555,
  "eval_steps": 500,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009489916963226572,
      "grad_norm": 0.9249091148376465,
      "learning_rate": 0.0001999995055317446,
      "loss": 2.3789,
      "step": 10
    },
    {
      "epoch": 0.018979833926453145,
      "grad_norm": 0.7498548030853271,
      "learning_rate": 0.0001999955498150411,
      "loss": 1.3794,
      "step": 20
    },
    {
      "epoch": 0.028469750889679714,
      "grad_norm": 0.7051133513450623,
      "learning_rate": 0.00019998763853811184,
      "loss": 1.2474,
      "step": 30
    },
    {
      "epoch": 0.03795966785290629,
      "grad_norm": 0.7239620685577393,
      "learning_rate": 0.00019997577201390606,
      "loss": 1.2512,
      "step": 40
    },
    {
      "epoch": 0.04744958481613286,
      "grad_norm": 0.5843775272369385,
      "learning_rate": 0.0001999599507118322,
      "loss": 1.1068,
      "step": 50
    },
    {
      "epoch": 0.05693950177935943,
      "grad_norm": 0.59147709608078,
      "learning_rate": 0.00019994017525773913,
      "loss": 1.1164,
      "step": 60
    },
    {
      "epoch": 0.066429418742586,
      "grad_norm": 0.6587395668029785,
      "learning_rate": 0.0001999164464338918,
      "loss": 1.063,
      "step": 70
    },
    {
      "epoch": 0.07591933570581258,
      "grad_norm": 0.5964196920394897,
      "learning_rate": 0.0001998887651789398,
      "loss": 1.0046,
      "step": 80
    },
    {
      "epoch": 0.08540925266903915,
      "grad_norm": 0.6036216020584106,
      "learning_rate": 0.0001998571325878806,
      "loss": 1.0529,
      "step": 90
    },
    {
      "epoch": 0.09489916963226572,
      "grad_norm": 0.7564125061035156,
      "learning_rate": 0.00019982154991201608,
      "loss": 1.0009,
      "step": 100
    },
    {
      "epoch": 0.10438908659549229,
      "grad_norm": 0.7184653282165527,
      "learning_rate": 0.00019978201855890308,
      "loss": 0.9723,
      "step": 110
    },
    {
      "epoch": 0.11387900355871886,
      "grad_norm": 0.6793704628944397,
      "learning_rate": 0.00019973854009229763,
      "loss": 0.9341,
      "step": 120
    },
    {
      "epoch": 0.12336892052194544,
      "grad_norm": 0.6832011342048645,
      "learning_rate": 0.00019969111623209323,
      "loss": 0.9873,
      "step": 130
    },
    {
      "epoch": 0.132858837485172,
      "grad_norm": 0.85871422290802,
      "learning_rate": 0.00019963974885425266,
      "loss": 0.9299,
      "step": 140
    },
    {
      "epoch": 0.1423487544483986,
      "grad_norm": 0.7056658267974854,
      "learning_rate": 0.00019958443999073397,
      "loss": 0.9533,
      "step": 150
    },
    {
      "epoch": 0.15183867141162516,
      "grad_norm": 0.7040665149688721,
      "learning_rate": 0.00019952519182940993,
      "loss": 0.8815,
      "step": 160
    },
    {
      "epoch": 0.16132858837485173,
      "grad_norm": 0.6971840262413025,
      "learning_rate": 0.0001994620067139815,
      "loss": 0.9461,
      "step": 170
    },
    {
      "epoch": 0.1708185053380783,
      "grad_norm": 0.7504563331604004,
      "learning_rate": 0.00019939488714388524,
      "loss": 0.8483,
      "step": 180
    },
    {
      "epoch": 0.18030842230130487,
      "grad_norm": 0.684840977191925,
      "learning_rate": 0.00019932383577419432,
      "loss": 0.9122,
      "step": 190
    },
    {
      "epoch": 0.18979833926453143,
      "grad_norm": 0.6745721101760864,
      "learning_rate": 0.0001992488554155135,
      "loss": 0.8271,
      "step": 200
    },
    {
      "epoch": 0.199288256227758,
      "grad_norm": 0.7717174887657166,
      "learning_rate": 0.0001991699490338681,
      "loss": 0.8124,
      "step": 210
    },
    {
      "epoch": 0.20877817319098457,
      "grad_norm": 0.7041401267051697,
      "learning_rate": 0.00019908711975058637,
      "loss": 0.8219,
      "step": 220
    },
    {
      "epoch": 0.21826809015421114,
      "grad_norm": 0.6780515909194946,
      "learning_rate": 0.00019900037084217637,
      "loss": 0.7733,
      "step": 230
    },
    {
      "epoch": 0.2277580071174377,
      "grad_norm": 0.7086532115936279,
      "learning_rate": 0.00019890970574019617,
      "loss": 0.7575,
      "step": 240
    },
    {
      "epoch": 0.2372479240806643,
      "grad_norm": 0.7180762887001038,
      "learning_rate": 0.00019881512803111796,
      "loss": 0.8863,
      "step": 250
    },
    {
      "epoch": 0.24673784104389088,
      "grad_norm": 0.8088333010673523,
      "learning_rate": 0.00019871664145618657,
      "loss": 0.7497,
      "step": 260
    },
    {
      "epoch": 0.25622775800711745,
      "grad_norm": 0.6337082386016846,
      "learning_rate": 0.00019861424991127115,
      "loss": 0.8269,
      "step": 270
    },
    {
      "epoch": 0.265717674970344,
      "grad_norm": 0.8026911020278931,
      "learning_rate": 0.00019850795744671116,
      "loss": 0.8229,
      "step": 280
    },
    {
      "epoch": 0.2752075919335706,
      "grad_norm": 0.8139302730560303,
      "learning_rate": 0.00019839776826715614,
      "loss": 0.78,
      "step": 290
    },
    {
      "epoch": 0.2846975088967972,
      "grad_norm": 0.8401020765304565,
      "learning_rate": 0.00019828368673139947,
      "loss": 0.6933,
      "step": 300
    },
    {
      "epoch": 0.2941874258600237,
      "grad_norm": 0.7387434840202332,
      "learning_rate": 0.00019816571735220583,
      "loss": 0.8241,
      "step": 310
    },
    {
      "epoch": 0.3036773428232503,
      "grad_norm": 0.7867814302444458,
      "learning_rate": 0.0001980438647961327,
      "loss": 0.695,
      "step": 320
    },
    {
      "epoch": 0.31316725978647686,
      "grad_norm": 0.6026145219802856,
      "learning_rate": 0.00019791813388334581,
      "loss": 0.8118,
      "step": 330
    },
    {
      "epoch": 0.32265717674970346,
      "grad_norm": 0.7333958148956299,
      "learning_rate": 0.00019778852958742853,
      "loss": 0.7278,
      "step": 340
    },
    {
      "epoch": 0.33214709371293,
      "grad_norm": 0.7646610140800476,
      "learning_rate": 0.00019765505703518496,
      "loss": 0.6802,
      "step": 350
    },
    {
      "epoch": 0.3416370106761566,
      "grad_norm": 0.8131152987480164,
      "learning_rate": 0.00019751772150643722,
      "loss": 0.766,
      "step": 360
    },
    {
      "epoch": 0.35112692763938314,
      "grad_norm": 0.7349848747253418,
      "learning_rate": 0.0001973765284338167,
      "loss": 0.6832,
      "step": 370
    },
    {
      "epoch": 0.36061684460260973,
      "grad_norm": 0.6821774244308472,
      "learning_rate": 0.00019723148340254892,
      "loss": 0.7976,
      "step": 380
    },
    {
      "epoch": 0.3701067615658363,
      "grad_norm": 0.6879362463951111,
      "learning_rate": 0.0001970825921502328,
      "loss": 0.7195,
      "step": 390
    },
    {
      "epoch": 0.37959667852906287,
      "grad_norm": 0.699598491191864,
      "learning_rate": 0.00019692986056661356,
      "loss": 0.7,
      "step": 400
    },
    {
      "epoch": 0.38908659549228947,
      "grad_norm": 0.6818081736564636,
      "learning_rate": 0.0001967732946933499,
      "loss": 0.6991,
      "step": 410
    },
    {
      "epoch": 0.398576512455516,
      "grad_norm": 0.6942121386528015,
      "learning_rate": 0.00019661290072377482,
      "loss": 0.7161,
      "step": 420
    },
    {
      "epoch": 0.4080664294187426,
      "grad_norm": 0.6413360834121704,
      "learning_rate": 0.0001964486850026507,
      "loss": 0.7084,
      "step": 430
    },
    {
      "epoch": 0.41755634638196915,
      "grad_norm": 0.6501904129981995,
      "learning_rate": 0.00019628065402591845,
      "loss": 0.7431,
      "step": 440
    },
    {
      "epoch": 0.42704626334519574,
      "grad_norm": 0.6739936470985413,
      "learning_rate": 0.0001961088144404403,
      "loss": 0.7081,
      "step": 450
    },
    {
      "epoch": 0.4365361803084223,
      "grad_norm": 0.7370271682739258,
      "learning_rate": 0.00019593317304373705,
      "loss": 0.7203,
      "step": 460
    },
    {
      "epoch": 0.4460260972716489,
      "grad_norm": 0.5882676243782043,
      "learning_rate": 0.00019575373678371909,
      "loss": 0.679,
      "step": 470
    },
    {
      "epoch": 0.4555160142348754,
      "grad_norm": 0.6047580242156982,
      "learning_rate": 0.0001955705127584117,
      "loss": 0.6712,
      "step": 480
    },
    {
      "epoch": 0.465005931198102,
      "grad_norm": 0.6153593063354492,
      "learning_rate": 0.00019538350821567404,
      "loss": 0.6788,
      "step": 490
    },
    {
      "epoch": 0.4744958481613286,
      "grad_norm": 0.6934164762496948,
      "learning_rate": 0.00019519273055291266,
      "loss": 0.6903,
      "step": 500
    },
    {
      "epoch": 0.4744958481613286,
      "eval_loss": 0.6663702130317688,
      "eval_runtime": 20.5638,
      "eval_samples_per_second": 15.415,
      "eval_steps_per_second": 7.732,
      "step": 500
    },
    {
      "epoch": 0.48398576512455516,
      "grad_norm": 0.6835016012191772,
      "learning_rate": 0.00019499818731678873,
      "loss": 0.6843,
      "step": 510
    },
    {
      "epoch": 0.49347568208778175,
      "grad_norm": 0.666349470615387,
      "learning_rate": 0.00019479988620291956,
      "loss": 0.6961,
      "step": 520
    },
    {
      "epoch": 0.5029655990510083,
      "grad_norm": 0.7474802732467651,
      "learning_rate": 0.00019459783505557424,
      "loss": 0.6614,
      "step": 530
    },
    {
      "epoch": 0.5124555160142349,
      "grad_norm": 0.6815286874771118,
      "learning_rate": 0.0001943920418673633,
      "loss": 0.6693,
      "step": 540
    },
    {
      "epoch": 0.5219454329774614,
      "grad_norm": 0.5686200261116028,
      "learning_rate": 0.0001941825147789225,
      "loss": 0.6946,
      "step": 550
    },
    {
      "epoch": 0.531435349940688,
      "grad_norm": 0.643159806728363,
      "learning_rate": 0.00019396926207859084,
      "loss": 0.6486,
      "step": 560
    },
    {
      "epoch": 0.5409252669039146,
      "grad_norm": 0.7110168933868408,
      "learning_rate": 0.00019375229220208276,
      "loss": 0.6459,
      "step": 570
    },
    {
      "epoch": 0.5504151838671412,
      "grad_norm": 0.6624748706817627,
      "learning_rate": 0.0001935316137321543,
      "loss": 0.6692,
      "step": 580
    },
    {
      "epoch": 0.5599051008303677,
      "grad_norm": 0.761031985282898,
      "learning_rate": 0.00019330723539826375,
      "loss": 0.6046,
      "step": 590
    },
    {
      "epoch": 0.5693950177935944,
      "grad_norm": 0.6096632480621338,
      "learning_rate": 0.0001930791660762262,
      "loss": 0.6775,
      "step": 600
    },
    {
      "epoch": 0.5788849347568209,
      "grad_norm": 0.6898393630981445,
      "learning_rate": 0.0001928474147878626,
      "loss": 0.6293,
      "step": 610
    },
    {
      "epoch": 0.5883748517200474,
      "grad_norm": 0.6664237380027771,
      "learning_rate": 0.0001926119907006426,
      "loss": 0.6274,
      "step": 620
    },
    {
      "epoch": 0.597864768683274,
      "grad_norm": 0.7034701704978943,
      "learning_rate": 0.00019237290312732226,
      "loss": 0.6334,
      "step": 630
    },
    {
      "epoch": 0.6073546856465006,
      "grad_norm": 0.5845565795898438,
      "learning_rate": 0.0001921301615255754,
      "loss": 0.6791,
      "step": 640
    },
    {
      "epoch": 0.6168446026097272,
      "grad_norm": 0.6939854025840759,
      "learning_rate": 0.00019188377549761963,
      "loss": 0.6554,
      "step": 650
    },
    {
      "epoch": 0.6263345195729537,
      "grad_norm": 0.6801786422729492,
      "learning_rate": 0.00019163375478983632,
      "loss": 0.6543,
      "step": 660
    },
    {
      "epoch": 0.6358244365361803,
      "grad_norm": 0.583102285861969,
      "learning_rate": 0.00019138010929238534,
      "loss": 0.6268,
      "step": 670
    },
    {
      "epoch": 0.6453143534994069,
      "grad_norm": 0.6107549667358398,
      "learning_rate": 0.0001911228490388136,
      "loss": 0.6274,
      "step": 680
    },
    {
      "epoch": 0.6548042704626335,
      "grad_norm": 0.6578108072280884,
      "learning_rate": 0.00019086198420565823,
      "loss": 0.6171,
      "step": 690
    },
    {
      "epoch": 0.66429418742586,
      "grad_norm": 0.6483505368232727,
      "learning_rate": 0.000190597525112044,
      "loss": 0.5673,
      "step": 700
    },
    {
      "epoch": 0.6737841043890866,
      "grad_norm": 0.698631763458252,
      "learning_rate": 0.00019032948221927524,
      "loss": 0.5675,
      "step": 710
    },
    {
      "epoch": 0.6832740213523132,
      "grad_norm": 0.6782714128494263,
      "learning_rate": 0.00019005786613042185,
      "loss": 0.5904,
      "step": 720
    },
    {
      "epoch": 0.6927639383155397,
      "grad_norm": 0.673217236995697,
      "learning_rate": 0.00018978268758989991,
      "loss": 0.622,
      "step": 730
    },
    {
      "epoch": 0.7022538552787663,
      "grad_norm": 0.6975003480911255,
      "learning_rate": 0.00018950395748304678,
      "loss": 0.6558,
      "step": 740
    },
    {
      "epoch": 0.7117437722419929,
      "grad_norm": 0.6466664671897888,
      "learning_rate": 0.0001892216868356904,
      "loss": 0.673,
      "step": 750
    },
    {
      "epoch": 0.7212336892052195,
      "grad_norm": 0.6829777359962463,
      "learning_rate": 0.00018893588681371303,
      "loss": 0.5808,
      "step": 760
    },
    {
      "epoch": 0.730723606168446,
      "grad_norm": 0.6941152811050415,
      "learning_rate": 0.00018864656872260985,
      "loss": 0.6232,
      "step": 770
    },
    {
      "epoch": 0.7402135231316725,
      "grad_norm": 0.7243316769599915,
      "learning_rate": 0.00018835374400704154,
      "loss": 0.5933,
      "step": 780
    },
    {
      "epoch": 0.7497034400948992,
      "grad_norm": 0.6251444816589355,
      "learning_rate": 0.00018805742425038145,
      "loss": 0.6116,
      "step": 790
    },
    {
      "epoch": 0.7591933570581257,
      "grad_norm": 0.646567165851593,
      "learning_rate": 0.00018775762117425777,
      "loss": 0.601,
      "step": 800
    },
    {
      "epoch": 0.7686832740213523,
      "grad_norm": 0.6085071563720703,
      "learning_rate": 0.00018745434663808942,
      "loss": 0.6603,
      "step": 810
    },
    {
      "epoch": 0.7781731909845789,
      "grad_norm": 0.6589152812957764,
      "learning_rate": 0.00018714761263861728,
      "loss": 0.5672,
      "step": 820
    },
    {
      "epoch": 0.7876631079478055,
      "grad_norm": 0.7008639574050903,
      "learning_rate": 0.00018683743130942928,
      "loss": 0.6363,
      "step": 830
    },
    {
      "epoch": 0.797153024911032,
      "grad_norm": 0.6070975065231323,
      "learning_rate": 0.00018652381492048083,
      "loss": 0.6075,
      "step": 840
    },
    {
      "epoch": 0.8066429418742586,
      "grad_norm": 0.7204874753952026,
      "learning_rate": 0.00018620677587760916,
      "loss": 0.5797,
      "step": 850
    },
    {
      "epoch": 0.8161328588374852,
      "grad_norm": 0.6779175400733948,
      "learning_rate": 0.00018588632672204264,
      "loss": 0.5729,
      "step": 860
    },
    {
      "epoch": 0.8256227758007118,
      "grad_norm": 0.5760260224342346,
      "learning_rate": 0.00018556248012990468,
      "loss": 0.5568,
      "step": 870
    },
    {
      "epoch": 0.8351126927639383,
      "grad_norm": 0.6586163640022278,
      "learning_rate": 0.0001852352489117124,
      "loss": 0.5734,
      "step": 880
    },
    {
      "epoch": 0.8446026097271648,
      "grad_norm": 0.6545649766921997,
      "learning_rate": 0.0001849046460118698,
      "loss": 0.6065,
      "step": 890
    },
    {
      "epoch": 0.8540925266903915,
      "grad_norm": 0.5810338258743286,
      "learning_rate": 0.00018457068450815562,
      "loss": 0.5435,
      "step": 900
    },
    {
      "epoch": 0.863582443653618,
      "grad_norm": 0.5936874151229858,
      "learning_rate": 0.00018423337761120618,
      "loss": 0.5878,
      "step": 910
    },
    {
      "epoch": 0.8730723606168446,
      "grad_norm": 0.6365971565246582,
      "learning_rate": 0.00018389273866399275,
      "loss": 0.5696,
      "step": 920
    },
    {
      "epoch": 0.8825622775800712,
      "grad_norm": 0.5335951447486877,
      "learning_rate": 0.00018354878114129367,
      "loss": 0.5848,
      "step": 930
    },
    {
      "epoch": 0.8920521945432978,
      "grad_norm": 0.6080604791641235,
      "learning_rate": 0.00018320151864916135,
      "loss": 0.5739,
      "step": 940
    },
    {
      "epoch": 0.9015421115065243,
      "grad_norm": 0.5476921200752258,
      "learning_rate": 0.00018285096492438424,
      "loss": 0.5474,
      "step": 950
    },
    {
      "epoch": 0.9110320284697508,
      "grad_norm": 0.6528366804122925,
      "learning_rate": 0.00018249713383394303,
      "loss": 0.542,
      "step": 960
    },
    {
      "epoch": 0.9205219454329775,
      "grad_norm": 0.5690432786941528,
      "learning_rate": 0.00018214003937446253,
      "loss": 0.5771,
      "step": 970
    },
    {
      "epoch": 0.930011862396204,
      "grad_norm": 0.7033817172050476,
      "learning_rate": 0.0001817796956716578,
      "loss": 0.537,
      "step": 980
    },
    {
      "epoch": 0.9395017793594306,
      "grad_norm": 0.6648123264312744,
      "learning_rate": 0.00018141611697977529,
      "loss": 0.5579,
      "step": 990
    },
    {
      "epoch": 0.9489916963226572,
      "grad_norm": 0.5434956550598145,
      "learning_rate": 0.0001810493176810292,
      "loss": 0.58,
      "step": 1000
    },
    {
      "epoch": 0.9489916963226572,
      "eval_loss": 0.5363849401473999,
      "eval_runtime": 20.4233,
      "eval_samples_per_second": 15.521,
      "eval_steps_per_second": 7.785,
      "step": 1000
    },
    {
      "epoch": 0.9584816132858838,
      "grad_norm": 0.6258216500282288,
      "learning_rate": 0.00018067931228503246,
      "loss": 0.6065,
      "step": 1010
    },
    {
      "epoch": 0.9679715302491103,
      "grad_norm": 0.49021461606025696,
      "learning_rate": 0.00018030611542822257,
      "loss": 0.5184,
      "step": 1020
    },
    {
      "epoch": 0.9774614472123369,
      "grad_norm": 0.6789380311965942,
      "learning_rate": 0.00017992974187328305,
      "loss": 0.558,
      "step": 1030
    },
    {
      "epoch": 0.9869513641755635,
      "grad_norm": 0.6128289103507996,
      "learning_rate": 0.000179550206508559,
      "loss": 0.5901,
      "step": 1040
    },
    {
      "epoch": 0.99644128113879,
      "grad_norm": 0.5243271589279175,
      "learning_rate": 0.00017916752434746856,
      "loss": 0.5455,
      "step": 1050
    },
    {
      "epoch": 1.0066429418742586,
      "grad_norm": 0.6114349365234375,
      "learning_rate": 0.00017878171052790868,
      "loss": 0.5706,
      "step": 1060
    },
    {
      "epoch": 1.0161328588374852,
      "grad_norm": 0.5785910487174988,
      "learning_rate": 0.00017839278031165658,
      "loss": 0.4914,
      "step": 1070
    },
    {
      "epoch": 1.0256227758007117,
      "grad_norm": 0.6278082132339478,
      "learning_rate": 0.00017800074908376584,
      "loss": 0.4585,
      "step": 1080
    },
    {
      "epoch": 1.0351126927639382,
      "grad_norm": 0.5266045331954956,
      "learning_rate": 0.0001776056323519579,
      "loss": 0.4257,
      "step": 1090
    },
    {
      "epoch": 1.0446026097271648,
      "grad_norm": 0.5933576226234436,
      "learning_rate": 0.00017720744574600863,
      "loss": 0.4579,
      "step": 1100
    },
    {
      "epoch": 1.0540925266903916,
      "grad_norm": 0.568048357963562,
      "learning_rate": 0.00017680620501712996,
      "loss": 0.4736,
      "step": 1110
    },
    {
      "epoch": 1.063582443653618,
      "grad_norm": 0.586031436920166,
      "learning_rate": 0.00017640192603734692,
      "loss": 0.4208,
      "step": 1120
    },
    {
      "epoch": 1.0730723606168446,
      "grad_norm": 0.632996141910553,
      "learning_rate": 0.00017599462479886974,
      "loss": 0.4518,
      "step": 1130
    },
    {
      "epoch": 1.0825622775800712,
      "grad_norm": 0.6920955777168274,
      "learning_rate": 0.00017558431741346122,
      "loss": 0.4593,
      "step": 1140
    },
    {
      "epoch": 1.0920521945432977,
      "grad_norm": 0.5045620799064636,
      "learning_rate": 0.00017517102011179933,
      "loss": 0.472,
      "step": 1150
    },
    {
      "epoch": 1.1015421115065243,
      "grad_norm": 0.5956369638442993,
      "learning_rate": 0.00017475474924283536,
      "loss": 0.446,
      "step": 1160
    },
    {
      "epoch": 1.1110320284697508,
      "grad_norm": 0.7154461741447449,
      "learning_rate": 0.000174335521273147,
      "loss": 0.4513,
      "step": 1170
    },
    {
      "epoch": 1.1205219454329776,
      "grad_norm": 0.5512189269065857,
      "learning_rate": 0.00017391335278628712,
      "loss": 0.4584,
      "step": 1180
    },
    {
      "epoch": 1.130011862396204,
      "grad_norm": 0.9251359105110168,
      "learning_rate": 0.0001734882604821276,
      "loss": 0.4276,
      "step": 1190
    },
    {
      "epoch": 1.1395017793594306,
      "grad_norm": 0.640958845615387,
      "learning_rate": 0.00017306026117619889,
      "loss": 0.4481,
      "step": 1200
    },
    {
      "epoch": 1.1489916963226572,
      "grad_norm": 0.5504414439201355,
      "learning_rate": 0.00017262937179902472,
      "loss": 0.4697,
      "step": 1210
    },
    {
      "epoch": 1.1584816132858837,
      "grad_norm": 0.575148344039917,
      "learning_rate": 0.00017219560939545246,
      "loss": 0.4614,
      "step": 1220
    },
    {
      "epoch": 1.1679715302491103,
      "grad_norm": 0.5111013650894165,
      "learning_rate": 0.0001717589911239788,
      "loss": 0.4314,
      "step": 1230
    },
    {
      "epoch": 1.1774614472123368,
      "grad_norm": 0.5844498872756958,
      "learning_rate": 0.00017131953425607104,
      "loss": 0.4628,
      "step": 1240
    },
    {
      "epoch": 1.1869513641755636,
      "grad_norm": 0.5282189846038818,
      "learning_rate": 0.00017087725617548385,
      "loss": 0.443,
      "step": 1250
    },
    {
      "epoch": 1.1964412811387901,
      "grad_norm": 0.5334432721138,
      "learning_rate": 0.00017043217437757164,
      "loss": 0.4927,
      "step": 1260
    },
    {
      "epoch": 1.2059311981020167,
      "grad_norm": 0.8024120926856995,
      "learning_rate": 0.00016998430646859654,
      "loss": 0.4808,
      "step": 1270
    },
    {
      "epoch": 1.2154211150652432,
      "grad_norm": 0.5527599453926086,
      "learning_rate": 0.00016953367016503182,
      "loss": 0.433,
      "step": 1280
    },
    {
      "epoch": 1.2249110320284697,
      "grad_norm": 0.6859824657440186,
      "learning_rate": 0.00016908028329286112,
      "loss": 0.4774,
      "step": 1290
    },
    {
      "epoch": 1.2344009489916963,
      "grad_norm": 0.592665433883667,
      "learning_rate": 0.0001686241637868734,
      "loss": 0.4595,
      "step": 1300
    },
    {
      "epoch": 1.2438908659549228,
      "grad_norm": 0.643675684928894,
      "learning_rate": 0.00016816532968995328,
      "loss": 0.4377,
      "step": 1310
    },
    {
      "epoch": 1.2533807829181494,
      "grad_norm": 0.5149793028831482,
      "learning_rate": 0.00016770379915236766,
      "loss": 0.4127,
      "step": 1320
    },
    {
      "epoch": 1.262870699881376,
      "grad_norm": 0.6323621273040771,
      "learning_rate": 0.00016723959043104728,
      "loss": 0.4821,
      "step": 1330
    },
    {
      "epoch": 1.2723606168446027,
      "grad_norm": 0.6195471882820129,
      "learning_rate": 0.00016677272188886483,
      "loss": 0.479,
      "step": 1340
    },
    {
      "epoch": 1.2818505338078292,
      "grad_norm": 0.6360680460929871,
      "learning_rate": 0.00016630321199390867,
      "loss": 0.4322,
      "step": 1350
    },
    {
      "epoch": 1.2913404507710557,
      "grad_norm": 0.614509642124176,
      "learning_rate": 0.00016583107931875192,
      "loss": 0.4992,
      "step": 1360
    },
    {
      "epoch": 1.3008303677342823,
      "grad_norm": 0.6960734724998474,
      "learning_rate": 0.00016535634253971794,
      "loss": 0.4765,
      "step": 1370
    },
    {
      "epoch": 1.3103202846975088,
      "grad_norm": 0.5039885640144348,
      "learning_rate": 0.00016487902043614173,
      "loss": 0.4437,
      "step": 1380
    },
    {
      "epoch": 1.3198102016607356,
      "grad_norm": 0.629076361656189,
      "learning_rate": 0.00016439913188962685,
      "loss": 0.4626,
      "step": 1390
    },
    {
      "epoch": 1.3293001186239621,
      "grad_norm": 0.538341760635376,
      "learning_rate": 0.0001639166958832985,
      "loss": 0.4166,
      "step": 1400
    },
    {
      "epoch": 1.3387900355871887,
      "grad_norm": 0.6629465222358704,
      "learning_rate": 0.00016343173150105278,
      "loss": 0.4736,
      "step": 1410
    },
    {
      "epoch": 1.3482799525504152,
      "grad_norm": 0.6603752374649048,
      "learning_rate": 0.0001629442579268016,
      "loss": 0.4522,
      "step": 1420
    },
    {
      "epoch": 1.3577698695136418,
      "grad_norm": 0.7585862874984741,
      "learning_rate": 0.0001624542944437139,
      "loss": 0.439,
      "step": 1430
    },
    {
      "epoch": 1.3672597864768683,
      "grad_norm": 0.5442929863929749,
      "learning_rate": 0.00016196186043345288,
      "loss": 0.4181,
      "step": 1440
    },
    {
      "epoch": 1.3767497034400948,
      "grad_norm": 0.5769705772399902,
      "learning_rate": 0.00016146697537540924,
      "loss": 0.4431,
      "step": 1450
    },
    {
      "epoch": 1.3862396204033214,
      "grad_norm": 0.6381351351737976,
      "learning_rate": 0.0001609696588459307,
      "loss": 0.4476,
      "step": 1460
    },
    {
      "epoch": 1.395729537366548,
      "grad_norm": 0.573300838470459,
      "learning_rate": 0.00016046993051754756,
      "loss": 0.4839,
      "step": 1470
    },
    {
      "epoch": 1.4052194543297747,
      "grad_norm": 0.607252836227417,
      "learning_rate": 0.0001599678101581945,
      "loss": 0.4528,
      "step": 1480
    },
    {
      "epoch": 1.4147093712930012,
      "grad_norm": 0.6059923768043518,
      "learning_rate": 0.00015946331763042867,
      "loss": 0.4493,
      "step": 1490
    },
    {
      "epoch": 1.4241992882562278,
      "grad_norm": 0.6414983868598938,
      "learning_rate": 0.00015895647289064396,
      "loss": 0.4455,
      "step": 1500
    },
    {
      "epoch": 1.4241992882562278,
      "eval_loss": 0.4805718660354614,
      "eval_runtime": 20.4306,
      "eval_samples_per_second": 15.516,
      "eval_steps_per_second": 7.782,
      "step": 1500
    },
    {
      "epoch": 1.4336892052194543,
      "grad_norm": 0.6877856850624084,
      "learning_rate": 0.0001584472959882815,
      "loss": 0.4553,
      "step": 1510
    },
    {
      "epoch": 1.4431791221826809,
      "grad_norm": 0.6739844679832458,
      "learning_rate": 0.0001579358070650367,
      "loss": 0.4682,
      "step": 1520
    },
    {
      "epoch": 1.4526690391459074,
      "grad_norm": 0.6030142903327942,
      "learning_rate": 0.00015742202635406235,
      "loss": 0.4521,
      "step": 1530
    },
    {
      "epoch": 1.4621589561091342,
      "grad_norm": 0.6368103623390198,
      "learning_rate": 0.0001569059741791684,
      "loss": 0.4458,
      "step": 1540
    },
    {
      "epoch": 1.4716488730723607,
      "grad_norm": 0.649683952331543,
      "learning_rate": 0.0001563876709540178,
      "loss": 0.4568,
      "step": 1550
    },
    {
      "epoch": 1.4811387900355872,
      "grad_norm": 0.5779871940612793,
      "learning_rate": 0.00015586713718131922,
      "loss": 0.4808,
      "step": 1560
    },
    {
      "epoch": 1.4906287069988138,
      "grad_norm": 0.5961576700210571,
      "learning_rate": 0.0001553443934520159,
      "loss": 0.4595,
      "step": 1570
    },
    {
      "epoch": 1.5001186239620403,
      "grad_norm": 0.5500461459159851,
      "learning_rate": 0.00015481946044447099,
      "loss": 0.4584,
      "step": 1580
    },
    {
      "epoch": 1.5096085409252669,
      "grad_norm": 0.7123764157295227,
      "learning_rate": 0.00015429235892364994,
      "loss": 0.4236,
      "step": 1590
    },
    {
      "epoch": 1.5190984578884934,
      "grad_norm": 0.6884598731994629,
      "learning_rate": 0.00015376310974029873,
      "loss": 0.4661,
      "step": 1600
    },
    {
      "epoch": 1.52858837485172,
      "grad_norm": 0.5527105331420898,
      "learning_rate": 0.0001532317338301192,
      "loss": 0.4307,
      "step": 1610
    },
    {
      "epoch": 1.5380782918149465,
      "grad_norm": 0.5720965266227722,
      "learning_rate": 0.00015269825221294098,
      "loss": 0.415,
      "step": 1620
    },
    {
      "epoch": 1.547568208778173,
      "grad_norm": 0.716526985168457,
      "learning_rate": 0.0001521626859918898,
      "loss": 0.48,
      "step": 1630
    },
    {
      "epoch": 1.5570581257413998,
      "grad_norm": 0.5414557456970215,
      "learning_rate": 0.00015162505635255287,
      "loss": 0.4943,
      "step": 1640
    },
    {
      "epoch": 1.5665480427046263,
      "grad_norm": 0.6315144896507263,
      "learning_rate": 0.0001510853845621409,
      "loss": 0.4427,
      "step": 1650
    },
    {
      "epoch": 1.5760379596678529,
      "grad_norm": 0.5746013522148132,
      "learning_rate": 0.00015054369196864644,
      "loss": 0.4148,
      "step": 1660
    },
    {
      "epoch": 1.5855278766310796,
      "grad_norm": 0.6795936226844788,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.4553,
      "step": 1670
    },
    {
      "epoch": 1.5950177935943062,
      "grad_norm": 0.6202004551887512,
      "learning_rate": 0.0001494543301632219,
      "loss": 0.4593,
      "step": 1680
    },
    {
      "epoch": 1.6045077105575327,
      "grad_norm": 0.49426236748695374,
      "learning_rate": 0.0001489067040435717,
      "loss": 0.4162,
      "step": 1690
    },
    {
      "epoch": 1.6139976275207593,
      "grad_norm": 0.6348617076873779,
      "learning_rate": 0.00014835714330369446,
      "loss": 0.4421,
      "step": 1700
    },
    {
      "epoch": 1.6234875444839858,
      "grad_norm": 0.5943213701248169,
      "learning_rate": 0.0001478056696827636,
      "loss": 0.491,
      "step": 1710
    },
    {
      "epoch": 1.6329774614472123,
      "grad_norm": 0.6268736124038696,
      "learning_rate": 0.00014725230499562119,
      "loss": 0.4144,
      "step": 1720
    },
    {
      "epoch": 1.6424673784104389,
      "grad_norm": 0.6147856712341309,
      "learning_rate": 0.00014669707113191483,
      "loss": 0.4089,
      "step": 1730
    },
    {
      "epoch": 1.6519572953736654,
      "grad_norm": 0.5978316068649292,
      "learning_rate": 0.00014613999005523174,
      "loss": 0.467,
      "step": 1740
    },
    {
      "epoch": 1.661447212336892,
      "grad_norm": 0.6331775784492493,
      "learning_rate": 0.00014558108380223012,
      "loss": 0.4489,
      "step": 1750
    },
    {
      "epoch": 1.6709371293001185,
      "grad_norm": 0.6398030519485474,
      "learning_rate": 0.00014502037448176734,
      "loss": 0.4383,
      "step": 1760
    },
    {
      "epoch": 1.680427046263345,
      "grad_norm": 0.6606591939926147,
      "learning_rate": 0.00014445788427402528,
      "loss": 0.4222,
      "step": 1770
    },
    {
      "epoch": 1.6899169632265718,
      "grad_norm": 0.644334077835083,
      "learning_rate": 0.00014389363542963306,
      "loss": 0.4403,
      "step": 1780
    },
    {
      "epoch": 1.6994068801897984,
      "grad_norm": 0.6094640493392944,
      "learning_rate": 0.00014332765026878687,
      "loss": 0.4433,
      "step": 1790
    },
    {
      "epoch": 1.708896797153025,
      "grad_norm": 0.6047070026397705,
      "learning_rate": 0.00014275995118036693,
      "loss": 0.4254,
      "step": 1800
    },
    {
      "epoch": 1.7183867141162514,
      "grad_norm": 0.612147331237793,
      "learning_rate": 0.00014219056062105193,
      "loss": 0.4544,
      "step": 1810
    },
    {
      "epoch": 1.7278766310794782,
      "grad_norm": 0.563838541507721,
      "learning_rate": 0.00014161950111443077,
      "loss": 0.4405,
      "step": 1820
    },
    {
      "epoch": 1.7373665480427047,
      "grad_norm": 0.6529393196105957,
      "learning_rate": 0.0001410467952501114,
      "loss": 0.4312,
      "step": 1830
    },
    {
      "epoch": 1.7468564650059313,
      "grad_norm": 0.663934588432312,
      "learning_rate": 0.00014047246568282736,
      "loss": 0.4421,
      "step": 1840
    },
    {
      "epoch": 1.7563463819691578,
      "grad_norm": 0.6207594871520996,
      "learning_rate": 0.00013989653513154165,
      "loss": 0.4365,
      "step": 1850
    },
    {
      "epoch": 1.7658362989323844,
      "grad_norm": 0.5731400847434998,
      "learning_rate": 0.0001393190263785479,
      "loss": 0.4202,
      "step": 1860
    },
    {
      "epoch": 1.775326215895611,
      "grad_norm": 0.5179402828216553,
      "learning_rate": 0.00013873996226856933,
      "loss": 0.4719,
      "step": 1870
    },
    {
      "epoch": 1.7848161328588374,
      "grad_norm": 0.40121665596961975,
      "learning_rate": 0.00013815936570785487,
      "loss": 0.4148,
      "step": 1880
    },
    {
      "epoch": 1.794306049822064,
      "grad_norm": 0.8414328694343567,
      "learning_rate": 0.00013757725966327322,
      "loss": 0.4648,
      "step": 1890
    },
    {
      "epoch": 1.8037959667852905,
      "grad_norm": 0.3349032998085022,
      "learning_rate": 0.00013699366716140435,
      "loss": 0.4168,
      "step": 1900
    },
    {
      "epoch": 1.813285883748517,
      "grad_norm": 0.6793477535247803,
      "learning_rate": 0.0001364086112876284,
      "loss": 0.4483,
      "step": 1910
    },
    {
      "epoch": 1.8227758007117436,
      "grad_norm": 0.5308493971824646,
      "learning_rate": 0.00013582211518521273,
      "loss": 0.4022,
      "step": 1920
    },
    {
      "epoch": 1.8322657176749704,
      "grad_norm": 0.5604270696640015,
      "learning_rate": 0.00013523420205439646,
      "loss": 0.4075,
      "step": 1930
    },
    {
      "epoch": 1.841755634638197,
      "grad_norm": 0.5878490805625916,
      "learning_rate": 0.00013464489515147238,
      "loss": 0.4337,
      "step": 1940
    },
    {
      "epoch": 1.8512455516014235,
      "grad_norm": 0.6031716465950012,
      "learning_rate": 0.00013405421778786737,
      "loss": 0.4655,
      "step": 1950
    },
    {
      "epoch": 1.8607354685646502,
      "grad_norm": 0.6215988993644714,
      "learning_rate": 0.00013346219332922016,
      "loss": 0.4715,
      "step": 1960
    },
    {
      "epoch": 1.8702253855278768,
      "grad_norm": 0.565021276473999,
      "learning_rate": 0.0001328688451944569,
      "loss": 0.4118,
      "step": 1970
    },
    {
      "epoch": 1.8797153024911033,
      "grad_norm": 0.5580743551254272,
      "learning_rate": 0.00013227419685486492,
      "loss": 0.4451,
      "step": 1980
    },
    {
      "epoch": 1.8892052194543298,
      "grad_norm": 0.7063333988189697,
      "learning_rate": 0.0001316782718331643,
      "loss": 0.4114,
      "step": 1990
    },
    {
      "epoch": 1.8986951364175564,
      "grad_norm": 0.534269392490387,
      "learning_rate": 0.00013108109370257712,
      "loss": 0.4029,
      "step": 2000
    },
    {
      "epoch": 1.8986951364175564,
      "eval_loss": 0.4455092251300812,
      "eval_runtime": 20.4087,
      "eval_samples_per_second": 15.533,
      "eval_steps_per_second": 7.791,
      "step": 2000
    },
    {
      "epoch": 1.908185053380783,
      "grad_norm": 0.5529626607894897,
      "learning_rate": 0.00013048268608589533,
      "loss": 0.4108,
      "step": 2010
    },
    {
      "epoch": 1.9176749703440095,
      "grad_norm": 0.673758327960968,
      "learning_rate": 0.00012988307265454597,
      "loss": 0.4219,
      "step": 2020
    },
    {
      "epoch": 1.927164887307236,
      "grad_norm": 0.6164252758026123,
      "learning_rate": 0.00012928227712765504,
      "loss": 0.4611,
      "step": 2030
    },
    {
      "epoch": 1.9366548042704625,
      "grad_norm": 0.6192930340766907,
      "learning_rate": 0.00012868032327110904,
      "loss": 0.4601,
      "step": 2040
    },
    {
      "epoch": 1.946144721233689,
      "grad_norm": 0.5321446061134338,
      "learning_rate": 0.00012807723489661495,
      "loss": 0.4112,
      "step": 2050
    },
    {
      "epoch": 1.9556346381969156,
      "grad_norm": 0.5794662237167358,
      "learning_rate": 0.0001274730358607583,
      "loss": 0.4915,
      "step": 2060
    },
    {
      "epoch": 1.9651245551601424,
      "grad_norm": 0.6252449750900269,
      "learning_rate": 0.00012686775006405946,
      "loss": 0.4307,
      "step": 2070
    },
    {
      "epoch": 1.974614472123369,
      "grad_norm": 0.6203203201293945,
      "learning_rate": 0.0001262614014500282,
      "loss": 0.4375,
      "step": 2080
    },
    {
      "epoch": 1.9841043890865955,
      "grad_norm": 0.617151141166687,
      "learning_rate": 0.00012565401400421651,
      "loss": 0.4517,
      "step": 2090
    },
    {
      "epoch": 1.993594306049822,
      "grad_norm": 0.681266188621521,
      "learning_rate": 0.00012504561175326985,
      "loss": 0.4245,
      "step": 2100
    },
    {
      "epoch": 2.0037959667852907,
      "grad_norm": 0.5491665005683899,
      "learning_rate": 0.0001244362187639767,
      "loss": 0.4221,
      "step": 2110
    },
    {
      "epoch": 2.0132858837485172,
      "grad_norm": 0.7722651958465576,
      "learning_rate": 0.0001238258591423165,
      "loss": 0.3264,
      "step": 2120
    },
    {
      "epoch": 2.022775800711744,
      "grad_norm": 0.6458817720413208,
      "learning_rate": 0.00012321455703250616,
      "loss": 0.3128,
      "step": 2130
    },
    {
      "epoch": 2.0322657176749703,
      "grad_norm": 0.5134835243225098,
      "learning_rate": 0.0001226023366160449,
      "loss": 0.3112,
      "step": 2140
    },
    {
      "epoch": 2.041755634638197,
      "grad_norm": 0.5023068785667419,
      "learning_rate": 0.00012198922211075778,
      "loss": 0.2929,
      "step": 2150
    },
    {
      "epoch": 2.0512455516014234,
      "grad_norm": 0.5612622499465942,
      "learning_rate": 0.00012137523776983757,
      "loss": 0.2943,
      "step": 2160
    },
    {
      "epoch": 2.06073546856465,
      "grad_norm": 0.5554709434509277,
      "learning_rate": 0.00012076040788088554,
      "loss": 0.3099,
      "step": 2170
    },
    {
      "epoch": 2.0702253855278765,
      "grad_norm": 0.5206819772720337,
      "learning_rate": 0.00012014475676495052,
      "loss": 0.2933,
      "step": 2180
    },
    {
      "epoch": 2.079715302491103,
      "grad_norm": 0.5239592790603638,
      "learning_rate": 0.000119528308775567,
      "loss": 0.2991,
      "step": 2190
    },
    {
      "epoch": 2.0892052194543296,
      "grad_norm": 0.5854765772819519,
      "learning_rate": 0.00011891108829779165,
      "loss": 0.3288,
      "step": 2200
    },
    {
      "epoch": 2.0986951364175566,
      "grad_norm": 0.7295845746994019,
      "learning_rate": 0.00011829311974723867,
      "loss": 0.3275,
      "step": 2210
    },
    {
      "epoch": 2.108185053380783,
      "grad_norm": 0.6106508374214172,
      "learning_rate": 0.00011767442756911417,
      "loss": 0.3111,
      "step": 2220
    },
    {
      "epoch": 2.1176749703440096,
      "grad_norm": 0.5574607849121094,
      "learning_rate": 0.00011705503623724898,
      "loss": 0.3194,
      "step": 2230
    },
    {
      "epoch": 2.127164887307236,
      "grad_norm": 0.5289790630340576,
      "learning_rate": 0.00011643497025313061,
      "loss": 0.3088,
      "step": 2240
    },
    {
      "epoch": 2.1366548042704627,
      "grad_norm": 0.5656944513320923,
      "learning_rate": 0.0001158142541449341,
      "loss": 0.3099,
      "step": 2250
    },
    {
      "epoch": 2.1461447212336893,
      "grad_norm": 0.594753086566925,
      "learning_rate": 0.0001151929124665516,
      "loss": 0.309,
      "step": 2260
    },
    {
      "epoch": 2.155634638196916,
      "grad_norm": 0.6289036870002747,
      "learning_rate": 0.00011457096979662114,
      "loss": 0.2948,
      "step": 2270
    },
    {
      "epoch": 2.1651245551601424,
      "grad_norm": 0.5498007535934448,
      "learning_rate": 0.00011394845073755455,
      "loss": 0.3082,
      "step": 2280
    },
    {
      "epoch": 2.174614472123369,
      "grad_norm": 0.5636598467826843,
      "learning_rate": 0.00011332537991456398,
      "loss": 0.2858,
      "step": 2290
    },
    {
      "epoch": 2.1841043890865954,
      "grad_norm": 0.6761645674705505,
      "learning_rate": 0.00011270178197468789,
      "loss": 0.332,
      "step": 2300
    },
    {
      "epoch": 2.193594306049822,
      "grad_norm": 0.5729044675827026,
      "learning_rate": 0.00011207768158581613,
      "loss": 0.326,
      "step": 2310
    },
    {
      "epoch": 2.2030842230130485,
      "grad_norm": 0.4295574724674225,
      "learning_rate": 0.00011145310343571411,
      "loss": 0.304,
      "step": 2320
    },
    {
      "epoch": 2.212574139976275,
      "grad_norm": 0.5968920588493347,
      "learning_rate": 0.0001108280722310462,
      "loss": 0.3205,
      "step": 2330
    },
    {
      "epoch": 2.2220640569395016,
      "grad_norm": 0.6211205720901489,
      "learning_rate": 0.00011020261269639842,
      "loss": 0.2823,
      "step": 2340
    },
    {
      "epoch": 2.231553973902728,
      "grad_norm": 0.6108773946762085,
      "learning_rate": 0.00010957674957330042,
      "loss": 0.324,
      "step": 2350
    },
    {
      "epoch": 2.241043890865955,
      "grad_norm": 0.8250358700752258,
      "learning_rate": 0.00010895050761924668,
      "loss": 0.3359,
      "step": 2360
    },
    {
      "epoch": 2.2505338078291817,
      "grad_norm": 0.5284693837165833,
      "learning_rate": 0.00010832391160671729,
      "loss": 0.3122,
      "step": 2370
    },
    {
      "epoch": 2.260023724792408,
      "grad_norm": 0.5513204336166382,
      "learning_rate": 0.00010769698632219794,
      "loss": 0.3264,
      "step": 2380
    },
    {
      "epoch": 2.2695136417556347,
      "grad_norm": 0.6842665672302246,
      "learning_rate": 0.00010706975656519946,
      "loss": 0.3047,
      "step": 2390
    },
    {
      "epoch": 2.2790035587188613,
      "grad_norm": 0.545037031173706,
      "learning_rate": 0.00010644224714727681,
      "loss": 0.3115,
      "step": 2400
    },
    {
      "epoch": 2.288493475682088,
      "grad_norm": 0.5622695088386536,
      "learning_rate": 0.00010581448289104758,
      "loss": 0.3158,
      "step": 2410
    },
    {
      "epoch": 2.2979833926453144,
      "grad_norm": 0.6832267642021179,
      "learning_rate": 0.00010518648862921012,
      "loss": 0.3298,
      "step": 2420
    },
    {
      "epoch": 2.307473309608541,
      "grad_norm": 0.5637592673301697,
      "learning_rate": 0.00010455828920356115,
      "loss": 0.3103,
      "step": 2430
    },
    {
      "epoch": 2.3169632265717675,
      "grad_norm": 0.5744633078575134,
      "learning_rate": 0.00010392990946401313,
      "loss": 0.3271,
      "step": 2440
    },
    {
      "epoch": 2.326453143534994,
      "grad_norm": 0.7118310928344727,
      "learning_rate": 0.00010330137426761135,
      "loss": 0.3276,
      "step": 2450
    },
    {
      "epoch": 2.3359430604982205,
      "grad_norm": 0.5940092206001282,
      "learning_rate": 0.00010267270847755048,
      "loss": 0.3152,
      "step": 2460
    },
    {
      "epoch": 2.345432977461447,
      "grad_norm": 0.6454032063484192,
      "learning_rate": 0.00010204393696219117,
      "loss": 0.2916,
      "step": 2470
    },
    {
      "epoch": 2.3549228944246736,
      "grad_norm": 0.5936978459358215,
      "learning_rate": 0.00010141508459407623,
      "loss": 0.3146,
      "step": 2480
    },
    {
      "epoch": 2.3644128113879006,
      "grad_norm": 0.5801250338554382,
      "learning_rate": 0.00010078617624894684,
      "loss": 0.3129,
      "step": 2490
    },
    {
      "epoch": 2.373902728351127,
      "grad_norm": 0.6835585832595825,
      "learning_rate": 0.00010015723680475846,
      "loss": 0.3028,
      "step": 2500
    },
    {
      "epoch": 2.373902728351127,
      "eval_loss": 0.4224609136581421,
      "eval_runtime": 20.4149,
      "eval_samples_per_second": 15.528,
      "eval_steps_per_second": 7.788,
      "step": 2500
    },
    {
      "epoch": 2.3833926453143537,
      "grad_norm": 0.5739105939865112,
      "learning_rate": 9.95282911406968e-05,
      "loss": 0.2934,
      "step": 2510
    },
    {
      "epoch": 2.3928825622775802,
      "grad_norm": 0.4810318350791931,
      "learning_rate": 9.889936413619356e-05,
      "loss": 0.3147,
      "step": 2520
    },
    {
      "epoch": 2.4023724792408068,
      "grad_norm": 0.5853947997093201,
      "learning_rate": 9.827048066994225e-05,
      "loss": 0.3008,
      "step": 2530
    },
    {
      "epoch": 2.4118623962040333,
      "grad_norm": 0.5773667693138123,
      "learning_rate": 9.764166561891432e-05,
      "loss": 0.2926,
      "step": 2540
    },
    {
      "epoch": 2.42135231316726,
      "grad_norm": 0.7114972472190857,
      "learning_rate": 9.70129438573747e-05,
      "loss": 0.3169,
      "step": 2550
    },
    {
      "epoch": 2.4308422301304864,
      "grad_norm": 0.6915512681007385,
      "learning_rate": 9.63843402558981e-05,
      "loss": 0.3068,
      "step": 2560
    },
    {
      "epoch": 2.440332147093713,
      "grad_norm": 0.594857394695282,
      "learning_rate": 9.57558796803852e-05,
      "loss": 0.3196,
      "step": 2570
    },
    {
      "epoch": 2.4498220640569395,
      "grad_norm": 0.6631921529769897,
      "learning_rate": 9.512758699107879e-05,
      "loss": 0.2999,
      "step": 2580
    },
    {
      "epoch": 2.459311981020166,
      "grad_norm": 0.6086694002151489,
      "learning_rate": 9.449948704158071e-05,
      "loss": 0.3128,
      "step": 2590
    },
    {
      "epoch": 2.4688018979833926,
      "grad_norm": 0.6541831493377686,
      "learning_rate": 9.38716046778684e-05,
      "loss": 0.3279,
      "step": 2600
    },
    {
      "epoch": 2.478291814946619,
      "grad_norm": 0.5784711241722107,
      "learning_rate": 9.324396473731217e-05,
      "loss": 0.3026,
      "step": 2610
    },
    {
      "epoch": 2.4877817319098456,
      "grad_norm": 0.6732935905456543,
      "learning_rate": 9.261659204769284e-05,
      "loss": 0.3212,
      "step": 2620
    },
    {
      "epoch": 2.497271648873072,
      "grad_norm": 0.6389648914337158,
      "learning_rate": 9.198951142621929e-05,
      "loss": 0.3184,
      "step": 2630
    },
    {
      "epoch": 2.5067615658362987,
      "grad_norm": 0.5656270980834961,
      "learning_rate": 9.136274767854716e-05,
      "loss": 0.31,
      "step": 2640
    },
    {
      "epoch": 2.5162514827995253,
      "grad_norm": 0.61983323097229,
      "learning_rate": 9.07363255977973e-05,
      "loss": 0.3148,
      "step": 2650
    },
    {
      "epoch": 2.525741399762752,
      "grad_norm": 0.46594876050949097,
      "learning_rate": 9.011026996357503e-05,
      "loss": 0.303,
      "step": 2660
    },
    {
      "epoch": 2.535231316725979,
      "grad_norm": 0.6862909197807312,
      "learning_rate": 8.948460554099018e-05,
      "loss": 0.3072,
      "step": 2670
    },
    {
      "epoch": 2.5447212336892053,
      "grad_norm": 0.6350931525230408,
      "learning_rate": 8.885935707967716e-05,
      "loss": 0.2909,
      "step": 2680
    },
    {
      "epoch": 2.554211150652432,
      "grad_norm": 0.6156574487686157,
      "learning_rate": 8.823454931281616e-05,
      "loss": 0.3375,
      "step": 2690
    },
    {
      "epoch": 2.5637010676156584,
      "grad_norm": 0.5949609875679016,
      "learning_rate": 8.76102069561545e-05,
      "loss": 0.3335,
      "step": 2700
    },
    {
      "epoch": 2.573190984578885,
      "grad_norm": 0.5457854866981506,
      "learning_rate": 8.698635470702923e-05,
      "loss": 0.3119,
      "step": 2710
    },
    {
      "epoch": 2.5826809015421115,
      "grad_norm": 0.5788692235946655,
      "learning_rate": 8.636301724339004e-05,
      "loss": 0.2898,
      "step": 2720
    },
    {
      "epoch": 2.592170818505338,
      "grad_norm": 0.5722967982292175,
      "learning_rate": 8.574021922282292e-05,
      "loss": 0.3079,
      "step": 2730
    },
    {
      "epoch": 2.6016607354685646,
      "grad_norm": 0.6501619815826416,
      "learning_rate": 8.511798528157512e-05,
      "loss": 0.2971,
      "step": 2740
    },
    {
      "epoch": 2.611150652431791,
      "grad_norm": 0.6138727068901062,
      "learning_rate": 8.449634003358022e-05,
      "loss": 0.3286,
      "step": 2750
    },
    {
      "epoch": 2.6206405693950177,
      "grad_norm": 0.5789212584495544,
      "learning_rate": 8.387530806948476e-05,
      "loss": 0.3101,
      "step": 2760
    },
    {
      "epoch": 2.630130486358244,
      "grad_norm": 0.6013932228088379,
      "learning_rate": 8.325491395567541e-05,
      "loss": 0.2997,
      "step": 2770
    },
    {
      "epoch": 2.639620403321471,
      "grad_norm": 0.5596510767936707,
      "learning_rate": 8.263518223330697e-05,
      "loss": 0.2928,
      "step": 2780
    },
    {
      "epoch": 2.6491103202846977,
      "grad_norm": 0.7271096706390381,
      "learning_rate": 8.201613741733203e-05,
      "loss": 0.3144,
      "step": 2790
    },
    {
      "epoch": 2.6586002372479243,
      "grad_norm": 0.715353786945343,
      "learning_rate": 8.13978039955308e-05,
      "loss": 0.3341,
      "step": 2800
    },
    {
      "epoch": 2.668090154211151,
      "grad_norm": 0.6036480665206909,
      "learning_rate": 8.078020642754274e-05,
      "loss": 0.3176,
      "step": 2810
    },
    {
      "epoch": 2.6775800711743774,
      "grad_norm": 0.5531415939331055,
      "learning_rate": 8.016336914389874e-05,
      "loss": 0.3043,
      "step": 2820
    },
    {
      "epoch": 2.687069988137604,
      "grad_norm": 0.5626965165138245,
      "learning_rate": 7.954731654505491e-05,
      "loss": 0.316,
      "step": 2830
    },
    {
      "epoch": 2.6965599051008304,
      "grad_norm": 0.6845198273658752,
      "learning_rate": 7.89320730004274e-05,
      "loss": 0.3167,
      "step": 2840
    },
    {
      "epoch": 2.706049822064057,
      "grad_norm": 0.5867395997047424,
      "learning_rate": 7.831766284742807e-05,
      "loss": 0.3189,
      "step": 2850
    },
    {
      "epoch": 2.7155397390272835,
      "grad_norm": 0.5502896308898926,
      "learning_rate": 7.77041103905023e-05,
      "loss": 0.3085,
      "step": 2860
    },
    {
      "epoch": 2.72502965599051,
      "grad_norm": 0.6936707496643066,
      "learning_rate": 7.709143990016702e-05,
      "loss": 0.2824,
      "step": 2870
    },
    {
      "epoch": 2.7345195729537366,
      "grad_norm": 0.6040688157081604,
      "learning_rate": 7.6479675612051e-05,
      "loss": 0.3005,
      "step": 2880
    },
    {
      "epoch": 2.744009489916963,
      "grad_norm": 0.6335172057151794,
      "learning_rate": 7.586884172593609e-05,
      "loss": 0.3048,
      "step": 2890
    },
    {
      "epoch": 2.7534994068801897,
      "grad_norm": 0.5545411705970764,
      "learning_rate": 7.525896240479976e-05,
      "loss": 0.3137,
      "step": 2900
    },
    {
      "epoch": 2.7629893238434162,
      "grad_norm": 0.56629878282547,
      "learning_rate": 7.465006177385953e-05,
      "loss": 0.3164,
      "step": 2910
    },
    {
      "epoch": 2.7724792408066428,
      "grad_norm": 0.6280866861343384,
      "learning_rate": 7.404216391961847e-05,
      "loss": 0.3266,
      "step": 2920
    },
    {
      "epoch": 2.7819691577698693,
      "grad_norm": 0.6720747947692871,
      "learning_rate": 7.343529288891239e-05,
      "loss": 0.2954,
      "step": 2930
    },
    {
      "epoch": 2.791459074733096,
      "grad_norm": 0.7422773838043213,
      "learning_rate": 7.282947268795877e-05,
      "loss": 0.3037,
      "step": 2940
    },
    {
      "epoch": 2.8009489916963224,
      "grad_norm": 0.6017013192176819,
      "learning_rate": 7.222472728140695e-05,
      "loss": 0.3007,
      "step": 2950
    },
    {
      "epoch": 2.8104389086595494,
      "grad_norm": 0.5282939672470093,
      "learning_rate": 7.162108059139032e-05,
      "loss": 0.2987,
      "step": 2960
    },
    {
      "epoch": 2.819928825622776,
      "grad_norm": 0.6391469240188599,
      "learning_rate": 7.101855649657991e-05,
      "loss": 0.306,
      "step": 2970
    },
    {
      "epoch": 2.8294187425860025,
      "grad_norm": 0.7014105319976807,
      "learning_rate": 7.041717883123977e-05,
      "loss": 0.2957,
      "step": 2980
    },
    {
      "epoch": 2.838908659549229,
      "grad_norm": 0.7407575845718384,
      "learning_rate": 6.981697138428434e-05,
      "loss": 0.2931,
      "step": 2990
    },
    {
      "epoch": 2.8483985765124555,
      "grad_norm": 0.6662490367889404,
      "learning_rate": 6.921795789833723e-05,
      "loss": 0.2909,
      "step": 3000
    },
    {
      "epoch": 2.8483985765124555,
      "eval_loss": 0.3944380581378937,
      "eval_runtime": 20.3916,
      "eval_samples_per_second": 15.546,
      "eval_steps_per_second": 7.797,
      "step": 3000
    }
  ],
  "logging_steps": 10,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 2.9630137686215885e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}