{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05579775712209701,
  "eval_steps": 500,
  "global_step": 2035,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002741904526884374,
      "grad_norm": 533.0549778145878,
      "learning_rate": 2.910112359550562e-06,
      "loss": 2.0392507553100585,
      "step": 10
    },
    {
      "epoch": 0.0005483809053768748,
      "grad_norm": 129.62802977018143,
      "learning_rate": 3.921348314606742e-06,
      "loss": 1.1088291168212892,
      "step": 20
    },
    {
      "epoch": 0.0008225713580653121,
      "grad_norm": 37.028700378797375,
      "learning_rate": 4.932584269662922e-06,
      "loss": 0.8763736724853516,
      "step": 30
    },
    {
      "epoch": 0.0010967618107537496,
      "grad_norm": 11.415105214785655,
      "learning_rate": 5.943820224719102e-06,
      "loss": 0.8334451675415039,
      "step": 40
    },
    {
      "epoch": 0.0013709522634421868,
      "grad_norm": 168.0092220161655,
      "learning_rate": 6.955056179775282e-06,
      "loss": 0.841560173034668,
      "step": 50
    },
    {
      "epoch": 0.0016451427161306242,
      "grad_norm": 10.9544582922062,
      "learning_rate": 7.966292134831462e-06,
      "loss": 0.7757131099700928,
      "step": 60
    },
    {
      "epoch": 0.0019193331688190617,
      "grad_norm": 52.12017293008163,
      "learning_rate": 8.977528089887641e-06,
      "loss": 0.7379593849182129,
      "step": 70
    },
    {
      "epoch": 0.0021935236215074993,
      "grad_norm": 24.23368291019739,
      "learning_rate": 9.988764044943822e-06,
      "loss": 0.871122169494629,
      "step": 80
    },
    {
      "epoch": 0.0024677140741959365,
      "grad_norm": 44.606225719656116,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 0.8103988647460938,
      "step": 90
    },
    {
      "epoch": 0.0027419045268843737,
      "grad_norm": 19.394878252919106,
      "learning_rate": 1.2011235955056182e-05,
      "loss": 0.8088878631591797,
      "step": 100
    },
    {
      "epoch": 0.0030160949795728113,
      "grad_norm": 154.65284754287825,
      "learning_rate": 1.3022471910112362e-05,
      "loss": 0.7940959930419922,
      "step": 110
    },
    {
      "epoch": 0.0032902854322612485,
      "grad_norm": 58.453168158560985,
      "learning_rate": 1.403370786516854e-05,
      "loss": 0.8113164901733398,
      "step": 120
    },
    {
      "epoch": 0.003564475884949686,
      "grad_norm": 121.71906195134056,
      "learning_rate": 1.504494382022472e-05,
      "loss": 0.802008056640625,
      "step": 130
    },
    {
      "epoch": 0.0038386663376381233,
      "grad_norm": 7.063904217729592,
      "learning_rate": 1.60561797752809e-05,
      "loss": 0.7886086940765381,
      "step": 140
    },
    {
      "epoch": 0.004112856790326561,
      "grad_norm": 5.886231107848548,
      "learning_rate": 1.706741573033708e-05,
      "loss": 0.8553682327270508,
      "step": 150
    },
    {
      "epoch": 0.004387047243014999,
      "grad_norm": 17.479053516912124,
      "learning_rate": 1.8078651685393256e-05,
      "loss": 0.878786849975586,
      "step": 160
    },
    {
      "epoch": 0.004661237695703435,
      "grad_norm": 15.809884339669948,
      "learning_rate": 1.908988764044944e-05,
      "loss": 0.8892171859741211,
      "step": 170
    },
    {
      "epoch": 0.004935428148391873,
      "grad_norm": 15.552804520715554,
      "learning_rate": 2e-05,
      "loss": 0.907989501953125,
      "step": 180
    },
    {
      "epoch": 0.005209618601080311,
      "grad_norm": 8.234516558585694,
      "learning_rate": 2e-05,
      "loss": 0.8959874153137207,
      "step": 190
    },
    {
      "epoch": 0.005483809053768747,
      "grad_norm": 47.07479845477993,
      "learning_rate": 2e-05,
      "loss": 0.7972547054290772,
      "step": 200
    },
    {
      "epoch": 0.005757999506457185,
      "grad_norm": 14.678891090428264,
      "learning_rate": 2e-05,
      "loss": 0.7945639610290527,
      "step": 210
    },
    {
      "epoch": 0.006032189959145623,
      "grad_norm": 17.99623194706809,
      "learning_rate": 2e-05,
      "loss": 0.8467901229858399,
      "step": 220
    },
    {
      "epoch": 0.00630638041183406,
      "grad_norm": 51.95652459415379,
      "learning_rate": 2e-05,
      "loss": 0.7964937210083007,
      "step": 230
    },
    {
      "epoch": 0.006580570864522497,
      "grad_norm": 10.738865490640423,
      "learning_rate": 2e-05,
      "loss": 0.7535751342773438,
      "step": 240
    },
    {
      "epoch": 0.006854761317210935,
      "grad_norm": 10.795608734038868,
      "learning_rate": 2e-05,
      "loss": 0.828792953491211,
      "step": 250
    },
    {
      "epoch": 0.007128951769899372,
      "grad_norm": 14.551689425739292,
      "learning_rate": 2e-05,
      "loss": 0.8123558044433594,
      "step": 260
    },
    {
      "epoch": 0.00740314222258781,
      "grad_norm": 26.532992867443514,
      "learning_rate": 2e-05,
      "loss": 0.8517896652221679,
      "step": 270
    },
    {
      "epoch": 0.007677332675276247,
      "grad_norm": 34.07990246963607,
      "learning_rate": 2e-05,
      "loss": 0.8389625549316406,
      "step": 280
    },
    {
      "epoch": 0.007951523127964684,
      "grad_norm": 27.19116883891022,
      "learning_rate": 2e-05,
      "loss": 0.8190082550048828,
      "step": 290
    },
    {
      "epoch": 0.008225713580653122,
      "grad_norm": 16.718638113526183,
      "learning_rate": 2e-05,
      "loss": 0.8008914947509765,
      "step": 300
    },
    {
      "epoch": 0.00849990403334156,
      "grad_norm": 27.009662680205103,
      "learning_rate": 2e-05,
      "loss": 0.8091920852661133,
      "step": 310
    },
    {
      "epoch": 0.008774094486029997,
      "grad_norm": 9.031648650732553,
      "learning_rate": 2e-05,
      "loss": 0.8081918716430664,
      "step": 320
    },
    {
      "epoch": 0.009048284938718433,
      "grad_norm": 15.927828911998665,
      "learning_rate": 2e-05,
      "loss": 0.7878878593444825,
      "step": 330
    },
    {
      "epoch": 0.00932247539140687,
      "grad_norm": 6.019580282287438,
      "learning_rate": 2e-05,
      "loss": 0.8092373847961426,
      "step": 340
    },
    {
      "epoch": 0.009596665844095308,
      "grad_norm": 10.097656044283081,
      "learning_rate": 2e-05,
      "loss": 0.8236124038696289,
      "step": 350
    },
    {
      "epoch": 0.009870856296783746,
      "grad_norm": 3.898510274122292,
      "learning_rate": 2e-05,
      "loss": 0.8201662063598633,
      "step": 360
    },
    {
      "epoch": 0.010145046749472184,
      "grad_norm": 10.433240846124043,
      "learning_rate": 2e-05,
      "loss": 0.7954160213470459,
      "step": 370
    },
    {
      "epoch": 0.010419237202160621,
      "grad_norm": 3.9109175859167626,
      "learning_rate": 2e-05,
      "loss": 0.8451309204101562,
      "step": 380
    },
    {
      "epoch": 0.010693427654849059,
      "grad_norm": 19.47785359214917,
      "learning_rate": 2e-05,
      "loss": 0.8227203369140625,
      "step": 390
    },
    {
      "epoch": 0.010967618107537495,
      "grad_norm": 1.9979422322935754,
      "learning_rate": 2e-05,
      "loss": 0.7947024345397949,
      "step": 400
    },
    {
      "epoch": 0.011241808560225932,
      "grad_norm": 2.1152537387703063,
      "learning_rate": 2e-05,
      "loss": 0.7340120315551758,
      "step": 410
    },
    {
      "epoch": 0.01151599901291437,
      "grad_norm": 2.457083494187141,
      "learning_rate": 2e-05,
      "loss": 0.7300191879272461,
      "step": 420
    },
    {
      "epoch": 0.011790189465602808,
      "grad_norm": 17.457321034227927,
      "learning_rate": 2e-05,
      "loss": 0.7896897315979003,
      "step": 430
    },
    {
      "epoch": 0.012064379918291245,
      "grad_norm": 3.7757446450653047,
      "learning_rate": 2e-05,
      "loss": 0.7420886039733887,
      "step": 440
    },
    {
      "epoch": 0.012338570370979683,
      "grad_norm": 10.718659609403895,
      "learning_rate": 2e-05,
      "loss": 0.7464280605316163,
      "step": 450
    },
    {
      "epoch": 0.01261276082366812,
      "grad_norm": 13.096467752661693,
      "learning_rate": 2e-05,
      "loss": 0.7420991420745849,
      "step": 460
    },
    {
      "epoch": 0.012886951276356558,
      "grad_norm": 7.554114077938612,
      "learning_rate": 2e-05,
      "loss": 0.7896678924560547,
      "step": 470
    },
    {
      "epoch": 0.013161141729044994,
      "grad_norm": 1.9610155148576782,
      "learning_rate": 2e-05,
      "loss": 0.7641692161560059,
      "step": 480
    },
    {
      "epoch": 0.013435332181733432,
      "grad_norm": 3.743726960430974,
      "learning_rate": 2e-05,
      "loss": 0.7724472999572753,
      "step": 490
    },
    {
      "epoch": 0.01370952263442187,
      "grad_norm": 3.6205794374072897,
      "learning_rate": 2e-05,
      "loss": 0.7726649284362793,
      "step": 500
    },
    {
      "epoch": 0.013983713087110307,
      "grad_norm": 2.751894400685354,
      "learning_rate": 2e-05,
      "loss": 0.7311810970306396,
      "step": 510
    },
    {
      "epoch": 0.014257903539798744,
      "grad_norm": 15.8354606407861,
      "learning_rate": 2e-05,
      "loss": 0.7479830741882324,
      "step": 520
    },
    {
      "epoch": 0.014532093992487182,
      "grad_norm": 9.741291005928273,
      "learning_rate": 2e-05,
      "loss": 0.758505916595459,
      "step": 530
    },
    {
      "epoch": 0.01480628444517562,
      "grad_norm": 6.361558235058739,
      "learning_rate": 2e-05,
      "loss": 0.7497701644897461,
      "step": 540
    },
    {
      "epoch": 0.015080474897864056,
      "grad_norm": 12.406630096904701,
      "learning_rate": 2e-05,
      "loss": 0.7578043937683105,
      "step": 550
    },
    {
      "epoch": 0.015354665350552493,
      "grad_norm": 5.437533111150059,
      "learning_rate": 2e-05,
      "loss": 0.7494767665863037,
      "step": 560
    },
    {
      "epoch": 0.015628855803240933,
      "grad_norm": 5.385414434765143,
      "learning_rate": 2e-05,
      "loss": 0.76002197265625,
      "step": 570
    },
    {
      "epoch": 0.01590304625592937,
      "grad_norm": 2.514872003150109,
      "learning_rate": 2e-05,
      "loss": 0.753857946395874,
      "step": 580
    },
    {
      "epoch": 0.016177236708617804,
      "grad_norm": 7.350990110651167,
      "learning_rate": 2e-05,
      "loss": 0.7598513603210449,
      "step": 590
    },
    {
      "epoch": 0.016451427161306244,
      "grad_norm": 9.359850474100211,
      "learning_rate": 2e-05,
      "loss": 0.7978845596313476,
      "step": 600
    },
    {
      "epoch": 0.01672561761399468,
      "grad_norm": 2.5927971608846243,
      "learning_rate": 2e-05,
      "loss": 0.7353355407714843,
      "step": 610
    },
    {
      "epoch": 0.01699980806668312,
      "grad_norm": 13.580441280433185,
      "learning_rate": 2e-05,
      "loss": 0.7530646800994873,
      "step": 620
    },
    {
      "epoch": 0.017273998519371555,
      "grad_norm": 7.032504711444772,
      "learning_rate": 2e-05,
      "loss": 0.7999831199645996,
      "step": 630
    },
    {
      "epoch": 0.017548188972059994,
      "grad_norm": 3.7623518166414134,
      "learning_rate": 2e-05,
      "loss": 0.7583576202392578,
      "step": 640
    },
    {
      "epoch": 0.01782237942474843,
      "grad_norm": 9.996121547764488,
      "learning_rate": 2e-05,
      "loss": 0.7126437187194824,
      "step": 650
    },
    {
      "epoch": 0.018096569877436866,
      "grad_norm": 3.8005663709948423,
      "learning_rate": 2e-05,
      "loss": 0.7714213371276856,
      "step": 660
    },
    {
      "epoch": 0.018370760330125305,
      "grad_norm": 2.2803953101797445,
      "learning_rate": 2e-05,
      "loss": 0.735899829864502,
      "step": 670
    },
    {
      "epoch": 0.01864495078281374,
      "grad_norm": 2.2804717033812687,
      "learning_rate": 2e-05,
      "loss": 0.7463047981262207,
      "step": 680
    },
    {
      "epoch": 0.01891914123550218,
      "grad_norm": 2.6630744686256174,
      "learning_rate": 2e-05,
      "loss": 0.7112466812133789,
      "step": 690
    },
    {
      "epoch": 0.019193331688190617,
      "grad_norm": 8.59421748677637,
      "learning_rate": 2e-05,
      "loss": 0.8032501220703125,
      "step": 700
    },
    {
      "epoch": 0.019467522140879056,
      "grad_norm": 6.839099911030037,
      "learning_rate": 2e-05,
      "loss": 0.7257285118103027,
      "step": 710
    },
    {
      "epoch": 0.019741712593567492,
      "grad_norm": 6.527196880605798,
      "learning_rate": 2e-05,
      "loss": 0.7394065856933594,
      "step": 720
    },
    {
      "epoch": 0.020015903046255928,
      "grad_norm": 4.91546686150854,
      "learning_rate": 2e-05,
      "loss": 0.7233449459075928,
      "step": 730
    },
    {
      "epoch": 0.020290093498944367,
      "grad_norm": 9.615722695591046,
      "learning_rate": 2e-05,
      "loss": 0.714713191986084,
      "step": 740
    },
    {
      "epoch": 0.020564283951632803,
      "grad_norm": 2.6469047522209244,
      "learning_rate": 2e-05,
      "loss": 0.7250522613525391,
      "step": 750
    },
    {
      "epoch": 0.020838474404321242,
      "grad_norm": 27.513230581702402,
      "learning_rate": 2e-05,
      "loss": 0.709619665145874,
      "step": 760
    },
    {
      "epoch": 0.021112664857009678,
      "grad_norm": 2.3305572520941102,
      "learning_rate": 2e-05,
      "loss": 0.7650126457214356,
      "step": 770
    },
    {
      "epoch": 0.021386855309698118,
      "grad_norm": 1.7645473455518579,
      "learning_rate": 2e-05,
      "loss": 0.7501170635223389,
      "step": 780
    },
    {
      "epoch": 0.021661045762386553,
      "grad_norm": 2.706703322701269,
      "learning_rate": 2e-05,
      "loss": 0.7390304565429687,
      "step": 790
    },
    {
      "epoch": 0.02193523621507499,
      "grad_norm": 1.343452945442269,
      "learning_rate": 2e-05,
      "loss": 0.7560922145843506,
      "step": 800
    },
    {
      "epoch": 0.02220942666776343,
      "grad_norm": 1.8131674161495455,
      "learning_rate": 2e-05,
      "loss": 0.7617329597473145,
      "step": 810
    },
    {
      "epoch": 0.022483617120451865,
      "grad_norm": 6.6257304148619,
      "learning_rate": 2e-05,
      "loss": 0.7030315399169922,
      "step": 820
    },
    {
      "epoch": 0.022757807573140304,
      "grad_norm": 2.7477972541714237,
      "learning_rate": 2e-05,
      "loss": 0.7051456451416016,
      "step": 830
    },
    {
      "epoch": 0.02303199802582874,
      "grad_norm": 1.8551689554260649,
      "learning_rate": 2e-05,
      "loss": 0.790980863571167,
      "step": 840
    },
    {
      "epoch": 0.02330618847851718,
      "grad_norm": 4.091035715965749,
      "learning_rate": 2e-05,
      "loss": 0.7167482376098633,
      "step": 850
    },
    {
      "epoch": 0.023580378931205615,
      "grad_norm": 3.13444342764459,
      "learning_rate": 2e-05,
      "loss": 0.7428287506103516,
      "step": 860
    },
    {
      "epoch": 0.023854569383894055,
      "grad_norm": 7.428502868185567,
      "learning_rate": 2e-05,
      "loss": 0.7720952510833741,
      "step": 870
    },
    {
      "epoch": 0.02412875983658249,
      "grad_norm": 2.738880412295684,
      "learning_rate": 2e-05,
      "loss": 0.7307533264160156,
      "step": 880
    },
    {
      "epoch": 0.024402950289270926,
      "grad_norm": 5.442319700482665,
      "learning_rate": 2e-05,
      "loss": 0.7590367794036865,
      "step": 890
    },
    {
      "epoch": 0.024677140741959366,
      "grad_norm": 4.209775631505361,
      "learning_rate": 2e-05,
      "loss": 0.7398377418518066,
      "step": 900
    },
    {
      "epoch": 0.0249513311946478,
      "grad_norm": 3.317366374639838,
      "learning_rate": 2e-05,
      "loss": 0.7573592662811279,
      "step": 910
    },
    {
      "epoch": 0.02522552164733624,
      "grad_norm": 2.21708523073645,
      "learning_rate": 2e-05,
      "loss": 0.7442788124084473,
      "step": 920
    },
    {
      "epoch": 0.025499712100024677,
      "grad_norm": 5.003510596258695,
      "learning_rate": 2e-05,
      "loss": 0.7208542823791504,
      "step": 930
    },
    {
      "epoch": 0.025773902552713116,
      "grad_norm": 1.8666696979850983,
      "learning_rate": 2e-05,
      "loss": 0.7219260215759278,
      "step": 940
    },
    {
      "epoch": 0.026048093005401552,
      "grad_norm": 2.319707094464392,
      "learning_rate": 2e-05,
      "loss": 0.705035400390625,
      "step": 950
    },
    {
      "epoch": 0.026322283458089988,
      "grad_norm": 1.559433923602148,
      "learning_rate": 2e-05,
      "loss": 0.7253781795501709,
      "step": 960
    },
    {
      "epoch": 0.026596473910778427,
      "grad_norm": 3.1103622605289294,
      "learning_rate": 2e-05,
      "loss": 0.7434506416320801,
      "step": 970
    },
    {
      "epoch": 0.026870664363466863,
      "grad_norm": 4.482952591971397,
      "learning_rate": 2e-05,
      "loss": 0.7423406600952148,
      "step": 980
    },
    {
      "epoch": 0.027144854816155303,
      "grad_norm": 2.349643537640656,
      "learning_rate": 2e-05,
      "loss": 0.7380632400512696,
      "step": 990
    },
    {
      "epoch": 0.02741904526884374,
      "grad_norm": 6.624084473754211,
      "learning_rate": 2e-05,
      "loss": 0.7448741912841796,
      "step": 1000
    },
    {
      "epoch": 0.027693235721532178,
      "grad_norm": 1.959542744744174,
      "learning_rate": 2e-05,
      "loss": 0.7620717048645019,
      "step": 1010
    },
    {
      "epoch": 0.027967426174220614,
      "grad_norm": 1.9359370487542638,
      "learning_rate": 2e-05,
      "loss": 0.7283543586730957,
      "step": 1020
    },
    {
      "epoch": 0.02824161662690905,
      "grad_norm": 3.7510091510273424,
      "learning_rate": 2e-05,
      "loss": 0.7341510772705078,
      "step": 1030
    },
    {
      "epoch": 0.02851580707959749,
      "grad_norm": 1.645233108914731,
      "learning_rate": 2e-05,
      "loss": 0.7321323394775391,
      "step": 1040
    },
    {
      "epoch": 0.028789997532285925,
      "grad_norm": 5.060129114701537,
      "learning_rate": 2e-05,
      "loss": 0.7923129558563232,
      "step": 1050
    },
    {
      "epoch": 0.029064187984974364,
      "grad_norm": 6.767343077930711,
      "learning_rate": 2e-05,
      "loss": 0.7364850997924804,
      "step": 1060
    },
    {
      "epoch": 0.0293383784376628,
      "grad_norm": 7.157354259172915,
      "learning_rate": 2e-05,
      "loss": 0.7175948143005371,
      "step": 1070
    },
    {
      "epoch": 0.02961256889035124,
      "grad_norm": 10.118526445754803,
      "learning_rate": 2e-05,
      "loss": 0.6956705093383789,
      "step": 1080
    },
    {
      "epoch": 0.029886759343039675,
      "grad_norm": 3.2975128574851205,
      "learning_rate": 2e-05,
      "loss": 0.7435084342956543,
      "step": 1090
    },
    {
      "epoch": 0.03016094979572811,
      "grad_norm": 3.79438108252297,
      "learning_rate": 2e-05,
      "loss": 0.7209542274475098,
      "step": 1100
    },
    {
      "epoch": 0.03043514024841655,
      "grad_norm": 3.6413783178286896,
      "learning_rate": 2e-05,
      "loss": 0.7462982177734375,
      "step": 1110
    },
    {
      "epoch": 0.030709330701104987,
      "grad_norm": 2.4359365603997323,
      "learning_rate": 2e-05,
      "loss": 0.7772771835327148,
      "step": 1120
    },
    {
      "epoch": 0.030983521153793426,
      "grad_norm": 2.067253539210089,
      "learning_rate": 2e-05,
      "loss": 0.754563283920288,
      "step": 1130
    },
    {
      "epoch": 0.031257711606481865,
      "grad_norm": 1.3603842511083,
      "learning_rate": 2e-05,
      "loss": 0.7163387298583984,
      "step": 1140
    },
    {
      "epoch": 0.0315319020591703,
      "grad_norm": 7.634204958345298,
      "learning_rate": 2e-05,
      "loss": 0.7153648376464844,
      "step": 1150
    },
    {
      "epoch": 0.03180609251185874,
      "grad_norm": 2.224287938133906,
      "learning_rate": 2e-05,
      "loss": 0.7743209838867188,
      "step": 1160
    },
    {
      "epoch": 0.03208028296454717,
      "grad_norm": 8.328106347948369,
      "learning_rate": 2e-05,
      "loss": 0.7125131130218506,
      "step": 1170
    },
    {
      "epoch": 0.03235447341723561,
      "grad_norm": 4.9140382117559716,
      "learning_rate": 2e-05,
      "loss": 0.734964656829834,
      "step": 1180
    },
    {
      "epoch": 0.03262866386992405,
      "grad_norm": 1.6437427011396712,
      "learning_rate": 2e-05,
      "loss": 0.736287260055542,
      "step": 1190
    },
    {
      "epoch": 0.03290285432261249,
      "grad_norm": 1.7984413046378422,
      "learning_rate": 2e-05,
      "loss": 0.6888255119323731,
      "step": 1200
    },
    {
      "epoch": 0.03317704477530092,
      "grad_norm": 3.003273429621072,
      "learning_rate": 2e-05,
      "loss": 0.7354516506195068,
      "step": 1210
    },
    {
      "epoch": 0.03345123522798936,
      "grad_norm": 1.581766516298146,
      "learning_rate": 2e-05,
      "loss": 0.7175889492034913,
      "step": 1220
    },
    {
      "epoch": 0.0337254256806778,
      "grad_norm": 2.3247470513343185,
      "learning_rate": 2e-05,
      "loss": 0.714189863204956,
      "step": 1230
    },
    {
      "epoch": 0.03399961613336624,
      "grad_norm": 7.9334494235192325,
      "learning_rate": 2e-05,
      "loss": 0.7136695861816407,
      "step": 1240
    },
    {
      "epoch": 0.034273806586054674,
      "grad_norm": 49.62487496955337,
      "learning_rate": 2e-05,
      "loss": 0.7086945533752441,
      "step": 1250
    },
    {
      "epoch": 0.03454799703874311,
      "grad_norm": 2.890774584879648,
      "learning_rate": 2e-05,
      "loss": 0.7269087791442871,
      "step": 1260
    },
    {
      "epoch": 0.034822187491431546,
      "grad_norm": 4.796531005737684,
      "learning_rate": 2e-05,
      "loss": 0.7484929084777832,
      "step": 1270
    },
    {
      "epoch": 0.03509637794411999,
      "grad_norm": 1.6372708148105157,
      "learning_rate": 2e-05,
      "loss": 0.6999114036560059,
      "step": 1280
    },
    {
      "epoch": 0.035370568396808424,
      "grad_norm": 4.162341191850801,
      "learning_rate": 2e-05,
      "loss": 0.7129648208618165,
      "step": 1290
    },
    {
      "epoch": 0.03564475884949686,
      "grad_norm": 4.017056556093628,
      "learning_rate": 2e-05,
      "loss": 0.7217267036437989,
      "step": 1300
    },
    {
      "epoch": 0.035918949302185296,
      "grad_norm": 9.786655951652824,
      "learning_rate": 2e-05,
      "loss": 0.7361152648925782,
      "step": 1310
    },
    {
      "epoch": 0.03619313975487373,
      "grad_norm": 17.798888728639277,
      "learning_rate": 2e-05,
      "loss": 0.7423253059387207,
      "step": 1320
    },
    {
      "epoch": 0.036467330207562175,
      "grad_norm": 25.98230175781132,
      "learning_rate": 2e-05,
      "loss": 0.7079302787780761,
      "step": 1330
    },
    {
      "epoch": 0.03674152066025061,
      "grad_norm": 4.107909151191186,
      "learning_rate": 2e-05,
      "loss": 0.7637813568115235,
      "step": 1340
    },
    {
      "epoch": 0.03701571111293905,
      "grad_norm": 1.8177555687046802,
      "learning_rate": 2e-05,
      "loss": 0.7440331459045411,
      "step": 1350
    },
    {
      "epoch": 0.03728990156562748,
      "grad_norm": 6.631474920460703,
      "learning_rate": 2e-05,
      "loss": 0.7420357704162598,
      "step": 1360
    },
    {
      "epoch": 0.037564092018315925,
      "grad_norm": 1.182591249805126,
      "learning_rate": 2e-05,
      "loss": 0.7243555068969727,
      "step": 1370
    },
    {
      "epoch": 0.03783828247100436,
      "grad_norm": 1.5239290367740697,
      "learning_rate": 2e-05,
      "loss": 0.7780046463012695,
      "step": 1380
    },
    {
      "epoch": 0.0381124729236928,
      "grad_norm": 1.9611702789468477,
      "learning_rate": 2e-05,
      "loss": 0.7606742858886719,
      "step": 1390
    },
    {
      "epoch": 0.03838666337638123,
      "grad_norm": 3.4538398959809564,
      "learning_rate": 2e-05,
      "loss": 0.7161018371582031,
      "step": 1400
    },
    {
      "epoch": 0.03866085382906967,
      "grad_norm": 6.74405592418129,
      "learning_rate": 2e-05,
      "loss": 0.7269341945648193,
      "step": 1410
    },
    {
      "epoch": 0.03893504428175811,
      "grad_norm": 5.0613023509206,
      "learning_rate": 2e-05,
      "loss": 0.7150623321533203,
      "step": 1420
    },
    {
      "epoch": 0.03920923473444655,
      "grad_norm": 15.935601654785444,
      "learning_rate": 2e-05,
      "loss": 0.6991084098815918,
      "step": 1430
    },
    {
      "epoch": 0.039483425187134984,
      "grad_norm": 189.58206876056943,
      "learning_rate": 2e-05,
      "loss": 0.715428352355957,
      "step": 1440
    },
    {
      "epoch": 0.03975761563982342,
      "grad_norm": 13.224258279776146,
      "learning_rate": 2e-05,
      "loss": 0.7448666572570801,
      "step": 1450
    },
    {
      "epoch": 0.040031806092511855,
      "grad_norm": 15.23890210961455,
      "learning_rate": 2e-05,
      "loss": 0.7545663833618164,
      "step": 1460
    },
    {
      "epoch": 0.0403059965452003,
      "grad_norm": 2.089772579003186,
      "learning_rate": 2e-05,
      "loss": 0.7143968105316162,
      "step": 1470
    },
    {
      "epoch": 0.040580186997888734,
      "grad_norm": 672.5570249806746,
      "learning_rate": 2e-05,
      "loss": 0.6955307960510254,
      "step": 1480
    },
    {
      "epoch": 0.04085437745057717,
      "grad_norm": 2.499047720535622,
      "learning_rate": 2e-05,
      "loss": 0.7183216094970704,
      "step": 1490
    },
    {
      "epoch": 0.041128567903265606,
      "grad_norm": 1.6820671266931866,
      "learning_rate": 2e-05,
      "loss": 0.7442133903503418,
      "step": 1500
    },
    {
      "epoch": 0.04140275835595405,
      "grad_norm": 1.6322487359391142,
      "learning_rate": 2e-05,
      "loss": 0.7415005683898925,
      "step": 1510
    },
    {
      "epoch": 0.041676948808642485,
      "grad_norm": 2.0768691766562974,
      "learning_rate": 2e-05,
      "loss": 0.7350949764251709,
      "step": 1520
    },
    {
      "epoch": 0.04195113926133092,
      "grad_norm": 3.462638107939682,
      "learning_rate": 2e-05,
      "loss": 0.6958516597747803,
      "step": 1530
    },
    {
      "epoch": 0.042225329714019356,
      "grad_norm": 1.9410342316482636,
      "learning_rate": 2e-05,
      "loss": 0.7019001960754394,
      "step": 1540
    },
    {
      "epoch": 0.04249952016670779,
      "grad_norm": 2.2435234267896944,
      "learning_rate": 2e-05,
      "loss": 0.7038233757019043,
      "step": 1550
    },
    {
      "epoch": 0.042773710619396235,
      "grad_norm": 50.31729516447788,
      "learning_rate": 2e-05,
      "loss": 0.6971765041351319,
      "step": 1560
    },
    {
      "epoch": 0.04304790107208467,
      "grad_norm": 6.726153221416043,
      "learning_rate": 2e-05,
      "loss": 0.7901406764984131,
      "step": 1570
    },
    {
      "epoch": 0.04332209152477311,
      "grad_norm": 25.290061958502374,
      "learning_rate": 2e-05,
      "loss": 0.7404637813568116,
      "step": 1580
    },
    {
      "epoch": 0.04359628197746154,
      "grad_norm": 11.648387859593914,
      "learning_rate": 2e-05,
      "loss": 0.7325190544128418,
      "step": 1590
    },
    {
      "epoch": 0.04387047243014998,
      "grad_norm": 3.998377511327454,
      "learning_rate": 2e-05,
      "loss": 0.6938001155853272,
      "step": 1600
    },
    {
      "epoch": 0.04414466288283842,
      "grad_norm": 1.4609573707991412,
      "learning_rate": 2e-05,
      "loss": 0.6974159240722656,
      "step": 1610
    },
    {
      "epoch": 0.04441885333552686,
      "grad_norm": 1.2908767847499276,
      "learning_rate": 2e-05,
      "loss": 0.735476303100586,
      "step": 1620
    },
    {
      "epoch": 0.04469304378821529,
      "grad_norm": 1.5263587301999937,
      "learning_rate": 2e-05,
      "loss": 0.6849418640136719,
      "step": 1630
    },
    {
      "epoch": 0.04496723424090373,
      "grad_norm": 2.71012026891521,
      "learning_rate": 2e-05,
      "loss": 0.6952274322509766,
      "step": 1640
    },
    {
      "epoch": 0.04524142469359217,
      "grad_norm": 1.5738552850120824,
      "learning_rate": 2e-05,
      "loss": 0.7284816265106201,
      "step": 1650
    },
    {
      "epoch": 0.04551561514628061,
      "grad_norm": 1.5435257666345013,
      "learning_rate": 2e-05,
      "loss": 0.7115949153900146,
      "step": 1660
    },
    {
      "epoch": 0.045789805598969044,
      "grad_norm": 1.516425220632835,
      "learning_rate": 2e-05,
      "loss": 0.6966533660888672,
      "step": 1670
    },
    {
      "epoch": 0.04606399605165748,
      "grad_norm": 1.4858677693562772,
      "learning_rate": 2e-05,
      "loss": 0.712862491607666,
      "step": 1680
    },
    {
      "epoch": 0.046338186504345916,
      "grad_norm": 1.1928774431737874,
      "learning_rate": 2e-05,
      "loss": 0.715973949432373,
      "step": 1690
    },
    {
      "epoch": 0.04661237695703436,
      "grad_norm": 1.3801750667103458,
      "learning_rate": 2e-05,
      "loss": 0.6785056114196777,
      "step": 1700
    },
    {
      "epoch": 0.046886567409722794,
      "grad_norm": 1.1562227123885702,
      "learning_rate": 2e-05,
      "loss": 0.6806015014648438,
      "step": 1710
    },
    {
      "epoch": 0.04716075786241123,
      "grad_norm": 1.966065169897555,
      "learning_rate": 2e-05,
      "loss": 0.6789681911468506,
      "step": 1720
    },
    {
      "epoch": 0.047434948315099666,
      "grad_norm": 1.796240102087905,
      "learning_rate": 2e-05,
      "loss": 0.6643640041351319,
      "step": 1730
    },
    {
      "epoch": 0.04770913876778811,
      "grad_norm": 1.4714599948408273,
      "learning_rate": 2e-05,
      "loss": 0.672383975982666,
      "step": 1740
    },
    {
      "epoch": 0.047983329220476545,
      "grad_norm": 1.05613596470809,
      "learning_rate": 2e-05,
      "loss": 0.6921384334564209,
      "step": 1750
    },
    {
      "epoch": 0.04825751967316498,
      "grad_norm": 1.168321764739896,
      "learning_rate": 2e-05,
      "loss": 0.6853407859802246,
      "step": 1760
    },
    {
      "epoch": 0.04853171012585342,
      "grad_norm": 1.304231611987027,
      "learning_rate": 2e-05,
      "loss": 0.6831422328948975,
      "step": 1770
    },
    {
      "epoch": 0.04880590057854185,
      "grad_norm": 1.271885101891083,
      "learning_rate": 2e-05,
      "loss": 0.7312606811523438,
      "step": 1780
    },
    {
      "epoch": 0.049080091031230295,
      "grad_norm": 1.1274168419233672,
      "learning_rate": 2e-05,
      "loss": 0.7195809841156006,
      "step": 1790
    },
    {
      "epoch": 0.04935428148391873,
      "grad_norm": 2.1060356897000196,
      "learning_rate": 2e-05,
      "loss": 0.6862109184265137,
      "step": 1800
    },
    {
      "epoch": 0.04962847193660717,
      "grad_norm": 1.1668574261874323,
      "learning_rate": 2e-05,
      "loss": 0.7068725109100342,
      "step": 1810
    },
    {
      "epoch": 0.0499026623892956,
      "grad_norm": 3.1583477159166673,
      "learning_rate": 2e-05,
      "loss": 0.7150220394134521,
      "step": 1820
    },
    {
      "epoch": 0.05017685284198404,
      "grad_norm": 1.5843620172233683,
      "learning_rate": 2e-05,
      "loss": 0.66549072265625,
      "step": 1830
    },
    {
      "epoch": 0.05045104329467248,
      "grad_norm": 1.2547928536390052,
      "learning_rate": 2e-05,
      "loss": 0.7375857353210449,
      "step": 1840
    },
    {
      "epoch": 0.05072523374736092,
      "grad_norm": 4.29725259279178,
      "learning_rate": 2e-05,
      "loss": 0.6876885890960693,
      "step": 1850
    },
    {
      "epoch": 0.050999424200049354,
      "grad_norm": 1.9025925412069744,
      "learning_rate": 2e-05,
      "loss": 0.7387830734252929,
      "step": 1860
    },
    {
      "epoch": 0.05127361465273779,
      "grad_norm": 1.5406949311604028,
      "learning_rate": 2e-05,
      "loss": 0.6733179092407227,
      "step": 1870
    },
    {
      "epoch": 0.05154780510542623,
      "grad_norm": 20.215212215144863,
      "learning_rate": 2e-05,
      "loss": 0.7654403686523438,
      "step": 1880
    },
    {
      "epoch": 0.05182199555811467,
      "grad_norm": 1.5669531048405803,
      "learning_rate": 2e-05,
      "loss": 0.7350390911102295,
      "step": 1890
    },
    {
      "epoch": 0.052096186010803104,
      "grad_norm": 7.2191546562371425,
      "learning_rate": 2e-05,
      "loss": 0.7414397716522216,
      "step": 1900
    },
    {
      "epoch": 0.05237037646349154,
      "grad_norm": 1.2325274169727398,
      "learning_rate": 2e-05,
      "loss": 0.7655929088592529,
      "step": 1910
    },
    {
      "epoch": 0.052644566916179976,
      "grad_norm": 1.1944179026527708,
      "learning_rate": 2e-05,
      "loss": 0.7075240135192871,
      "step": 1920
    },
    {
      "epoch": 0.05291875736886842,
      "grad_norm": 1.302822879313398,
      "learning_rate": 2e-05,
      "loss": 0.6797014236450195,
      "step": 1930
    },
    {
      "epoch": 0.053192947821556855,
      "grad_norm": 2.0168747405099747,
      "learning_rate": 2e-05,
      "loss": 0.7000571727752686,
      "step": 1940
    },
    {
      "epoch": 0.05346713827424529,
      "grad_norm": 1.6344897385611805,
      "learning_rate": 2e-05,
      "loss": 0.7235137939453125,
      "step": 1950
    },
    {
      "epoch": 0.053741328726933726,
      "grad_norm": 3.5766753006414125,
      "learning_rate": 2e-05,
      "loss": 0.7371991634368896,
      "step": 1960
    },
    {
      "epoch": 0.05401551917962216,
      "grad_norm": 1.4953479982574733,
      "learning_rate": 2e-05,
      "loss": 0.7229987621307373,
      "step": 1970
    },
    {
      "epoch": 0.054289709632310605,
      "grad_norm": 1.6598347475638233,
      "learning_rate": 2e-05,
      "loss": 0.6758342742919922,
      "step": 1980
    },
    {
      "epoch": 0.05456390008499904,
      "grad_norm": 1.3876361065240026,
      "learning_rate": 2e-05,
      "loss": 0.6621166229248047,
      "step": 1990
    },
    {
      "epoch": 0.05483809053768748,
      "grad_norm": 1.2953540155757288,
      "learning_rate": 2e-05,
      "loss": 0.701081657409668,
      "step": 2000
    },
    {
      "epoch": 0.05511228099037591,
      "grad_norm": 1.0757376098134102,
      "learning_rate": 2e-05,
      "loss": 0.6949031829833985,
      "step": 2010
    },
    {
      "epoch": 0.055386471443064356,
      "grad_norm": 1.3515745918409625,
      "learning_rate": 2e-05,
      "loss": 0.6849285125732422,
      "step": 2020
    },
    {
      "epoch": 0.05566066189575279,
      "grad_norm": 3.4678908742290884,
      "learning_rate": 2e-05,
      "loss": 0.6919690608978272,
      "step": 2030
    }
  ],
  "logging_steps": 10,
  "max_steps": 5935,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2035,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 963613493821440.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}