{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.892827699917559,
  "eval_steps": 500,
  "global_step": 12000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08244023083264633,
      "grad_norm": 1.0573325157165527,
      "learning_rate": 4.892915980230642e-07,
      "loss": 0.05755834102630615,
      "step": 100
    },
    {
      "epoch": 0.16488046166529266,
      "grad_norm": 10.260250091552734,
      "learning_rate": 9.835255354200989e-07,
      "loss": 0.04523322582244873,
      "step": 200
    },
    {
      "epoch": 0.247320692497939,
      "grad_norm": 0.5175366997718811,
      "learning_rate": 1.4777594728171335e-06,
      "loss": 0.03658797979354858,
      "step": 300
    },
    {
      "epoch": 0.3297609233305853,
      "grad_norm": 5.0066118240356445,
      "learning_rate": 1.971993410214168e-06,
      "loss": 0.04241968631744385,
      "step": 400
    },
    {
      "epoch": 0.41220115416323166,
      "grad_norm": 16.185205459594727,
      "learning_rate": 2.466227347611203e-06,
      "loss": 0.03233745574951172,
      "step": 500
    },
    {
      "epoch": 0.494641384995878,
      "grad_norm": 0.4887259900569916,
      "learning_rate": 2.9604612850082373e-06,
      "loss": 0.04120903968811035,
      "step": 600
    },
    {
      "epoch": 0.5770816158285244,
      "grad_norm": 1.360079050064087,
      "learning_rate": 2.999528173020731e-06,
      "loss": 0.03448781490325928,
      "step": 700
    },
    {
      "epoch": 0.6595218466611706,
      "grad_norm": 1.5775821208953857,
      "learning_rate": 2.997945372145348e-06,
      "loss": 0.03620944499969483,
      "step": 800
    },
    {
      "epoch": 0.7419620774938169,
      "grad_norm": 37.682884216308594,
      "learning_rate": 2.9952492059335665e-06,
      "loss": 0.033068180084228516,
      "step": 900
    },
    {
      "epoch": 0.8244023083264633,
      "grad_norm": 0.5983888506889343,
      "learning_rate": 2.99144167834231e-06,
      "loss": 0.03487896919250488,
      "step": 1000
    },
    {
      "epoch": 0.9068425391591096,
      "grad_norm": 0.4312576651573181,
      "learning_rate": 2.986525619360788e-06,
      "loss": 0.032608640193939206,
      "step": 1100
    },
    {
      "epoch": 0.989282769991756,
      "grad_norm": 1.5949877500534058,
      "learning_rate": 2.980504682907069e-06,
      "loss": 0.03462482452392578,
      "step": 1200
    },
    {
      "epoch": 1.0717230008244023,
      "grad_norm": 0.5395241379737854,
      "learning_rate": 2.9733833441122652e-06,
      "loss": 0.029383325576782228,
      "step": 1300
    },
    {
      "epoch": 1.1541632316570487,
      "grad_norm": 7.3991804122924805,
      "learning_rate": 2.9651668959943407e-06,
      "loss": 0.03298326969146728,
      "step": 1400
    },
    {
      "epoch": 1.2366034624896949,
      "grad_norm": 3.2689311504364014,
      "learning_rate": 2.955861445524012e-06,
      "loss": 0.03119053363800049,
      "step": 1500
    },
    {
      "epoch": 1.3190436933223413,
      "grad_norm": 1.3022229671478271,
      "learning_rate": 2.9454739090856716e-06,
      "loss": 0.03160511493682861,
      "step": 1600
    },
    {
      "epoch": 1.4014839241549877,
      "grad_norm": 1.545177936553955,
      "learning_rate": 2.9340120073367064e-06,
      "loss": 0.03241936206817627,
      "step": 1700
    },
    {
      "epoch": 1.4839241549876339,
      "grad_norm": 0.3807108998298645,
      "learning_rate": 2.921484259469025e-06,
      "loss": 0.028808791637420655,
      "step": 1800
    },
    {
      "epoch": 1.5663643858202803,
      "grad_norm": 1.6713629961013794,
      "learning_rate": 2.907899976877075e-06,
      "loss": 0.026836631298065187,
      "step": 1900
    },
    {
      "epoch": 1.6488046166529267,
      "grad_norm": 0.8516013622283936,
      "learning_rate": 2.8932692562370356e-06,
      "loss": 0.02777437925338745,
      "step": 2000
    },
    {
      "epoch": 1.731244847485573,
      "grad_norm": 6.933730602264404,
      "learning_rate": 2.8776029720023492e-06,
      "loss": 0.03317852735519409,
      "step": 2100
    },
    {
      "epoch": 1.8136850783182195,
      "grad_norm": 2.6626434326171875,
      "learning_rate": 2.8609127683211535e-06,
      "loss": 0.030532124042510985,
      "step": 2200
    },
    {
      "epoch": 1.8961253091508656,
      "grad_norm": 0.9223625659942627,
      "learning_rate": 2.8432110503816364e-06,
      "loss": 0.028622543811798094,
      "step": 2300
    },
    {
      "epoch": 1.9785655399835118,
      "grad_norm": 1.147865891456604,
      "learning_rate": 2.824510975191734e-06,
      "loss": 0.0330674409866333,
      "step": 2400
    },
    {
      "epoch": 2.061005770816158,
      "grad_norm": 0.507649838924408,
      "learning_rate": 2.8048264418000297e-06,
      "loss": 0.029734506607055664,
      "step": 2500
    },
    {
      "epoch": 2.1434460016488046,
      "grad_norm": 0.648606538772583,
      "learning_rate": 2.7841720809651287e-06,
      "loss": 0.02952629327774048,
      "step": 2600
    },
    {
      "epoch": 2.225886232481451,
      "grad_norm": 6.885851860046387,
      "learning_rate": 2.762563244281172e-06,
      "loss": 0.033362927436828616,
      "step": 2700
    },
    {
      "epoch": 2.3083264633140974,
      "grad_norm": 0.7185697555541992,
      "learning_rate": 2.7400159927675868e-06,
      "loss": 0.03310190677642822,
      "step": 2800
    },
    {
      "epoch": 2.390766694146744,
      "grad_norm": 0.9038472771644592,
      "learning_rate": 2.7165470849315476e-06,
      "loss": 0.027033202648162842,
      "step": 2900
    },
    {
      "epoch": 2.4732069249793898,
      "grad_norm": 1.6981157064437866,
      "learning_rate": 2.692173964312021e-06,
      "loss": 0.03098677396774292,
      "step": 3000
    },
    {
      "epoch": 2.555647155812036,
      "grad_norm": 0.38965705037117004,
      "learning_rate": 2.666914746514651e-06,
      "loss": 0.025331289768218995,
      "step": 3100
    },
    {
      "epoch": 2.6380873866446826,
      "grad_norm": 0.9481067061424255,
      "learning_rate": 2.6407882057471234e-06,
      "loss": 0.02945547103881836,
      "step": 3200
    },
    {
      "epoch": 2.720527617477329,
      "grad_norm": 0.990297794342041,
      "learning_rate": 2.61381376086502e-06,
      "loss": 0.025877423286437988,
      "step": 3300
    },
    {
      "epoch": 2.8029678483099754,
      "grad_norm": 0.7205927968025208,
      "learning_rate": 2.586011460938527e-06,
      "loss": 0.0348543381690979,
      "step": 3400
    },
    {
      "epoch": 2.8854080791426218,
      "grad_norm": 1.2724188566207886,
      "learning_rate": 2.5574019703507284e-06,
      "loss": 0.025783424377441407,
      "step": 3500
    },
    {
      "epoch": 2.9678483099752677,
      "grad_norm": 0.3951258063316345,
      "learning_rate": 2.528006553438566e-06,
      "loss": 0.024769763946533203,
      "step": 3600
    },
    {
      "epoch": 3.050288540807914,
      "grad_norm": 0.7116732001304626,
      "learning_rate": 2.4978470586878702e-06,
      "loss": 0.0287685227394104,
      "step": 3700
    },
    {
      "epoch": 3.1327287716405605,
      "grad_norm": 0.9427194595336914,
      "learning_rate": 2.4669459024942216e-06,
      "loss": 0.03142688512802124,
      "step": 3800
    },
    {
      "epoch": 3.215169002473207,
      "grad_norm": 4.737741470336914,
      "learning_rate": 2.4353260525017004e-06,
      "loss": 0.025456478595733644,
      "step": 3900
    },
    {
      "epoch": 3.2976092333058533,
      "grad_norm": 1.237444519996643,
      "learning_rate": 2.4030110105319206e-06,
      "loss": 0.02399829149246216,
      "step": 4000
    },
    {
      "epoch": 3.3800494641384997,
      "grad_norm": 4.982211589813232,
      "learning_rate": 2.370024795116028e-06,
      "loss": 0.03101783275604248,
      "step": 4100
    },
    {
      "epoch": 3.462489694971146,
      "grad_norm": 5.987162113189697,
      "learning_rate": 2.336391923642643e-06,
      "loss": 0.023696184158325195,
      "step": 4200
    },
    {
      "epoch": 3.5449299258037925,
      "grad_norm": 0.5781798362731934,
      "learning_rate": 2.302137394135031e-06,
      "loss": 0.026220085620880126,
      "step": 4300
    },
    {
      "epoch": 3.6273701566364385,
      "grad_norm": 1.0097777843475342,
      "learning_rate": 2.267286666671027e-06,
      "loss": 0.029556829929351807,
      "step": 4400
    },
    {
      "epoch": 3.709810387469085,
      "grad_norm": 1.0615909099578857,
      "learning_rate": 2.2318656444595387e-06,
      "loss": 0.02913331747055054,
      "step": 4500
    },
    {
      "epoch": 3.7922506183017313,
      "grad_norm": 0.6333794593811035,
      "learning_rate": 2.1959006545876846e-06,
      "loss": 0.025029284954071043,
      "step": 4600
    },
    {
      "epoch": 3.8746908491343777,
      "grad_norm": 0.660271167755127,
      "learning_rate": 2.1594184284528776e-06,
      "loss": 0.031456120014190674,
      "step": 4700
    },
    {
      "epoch": 3.957131079967024,
      "grad_norm": 1.3678995370864868,
      "learning_rate": 2.1224460818944066e-06,
      "loss": 0.03159121990203857,
      "step": 4800
    },
    {
      "epoch": 4.03957131079967,
      "grad_norm": 1.6306558847427368,
      "learning_rate": 2.0850110950392694e-06,
      "loss": 0.023191912174224852,
      "step": 4900
    },
    {
      "epoch": 4.122011541632316,
      "grad_norm": 1.2425507307052612,
      "learning_rate": 2.047141291877252e-06,
      "loss": 0.030113303661346437,
      "step": 5000
    },
    {
      "epoch": 4.204451772464963,
      "grad_norm": 0.47728583216667175,
      "learning_rate": 2.00886481958042e-06,
      "loss": 0.024720721244812012,
      "step": 5100
    },
    {
      "epoch": 4.286892003297609,
      "grad_norm": 7.698798179626465,
      "learning_rate": 1.97021012758241e-06,
      "loss": 0.027791497707366945,
      "step": 5200
    },
    {
      "epoch": 4.369332234130256,
      "grad_norm": 0.9410794973373413,
      "learning_rate": 1.9312059464330545e-06,
      "loss": 0.022262310981750487,
      "step": 5300
    },
    {
      "epoch": 4.451772464962902,
      "grad_norm": 6.470306873321533,
      "learning_rate": 1.8918812664440643e-06,
      "loss": 0.023623311519622804,
      "step": 5400
    },
    {
      "epoch": 4.534212695795548,
      "grad_norm": 0.5035800933837891,
      "learning_rate": 1.8522653161416466e-06,
      "loss": 0.02535334587097168,
      "step": 5500
    },
    {
      "epoch": 4.616652926628195,
      "grad_norm": 2.6831247806549072,
      "learning_rate": 1.8123875405420576e-06,
      "loss": 0.022764217853546143,
      "step": 5600
    },
    {
      "epoch": 4.699093157460841,
      "grad_norm": 0.7162504196166992,
      "learning_rate": 1.7722775792662551e-06,
      "loss": 0.027024078369140624,
      "step": 5700
    },
    {
      "epoch": 4.781533388293488,
      "grad_norm": 0.8824426531791687,
      "learning_rate": 1.7319652445099035e-06,
      "loss": 0.02422706365585327,
      "step": 5800
    },
    {
      "epoch": 4.863973619126133,
      "grad_norm": 0.9424160122871399,
      "learning_rate": 1.6914804988851126e-06,
      "loss": 0.030813112258911132,
      "step": 5900
    },
    {
      "epoch": 4.9464138499587795,
      "grad_norm": 0.8058213591575623,
      "learning_rate": 1.6508534331503764e-06,
      "loss": 0.0320208215713501,
      "step": 6000
    },
    {
      "epoch": 5.028854080791426,
      "grad_norm": 0.6557570099830627,
      "learning_rate": 1.610114243845269e-06,
      "loss": 0.032469592094421386,
      "step": 6100
    },
    {
      "epoch": 5.111294311624072,
      "grad_norm": 0.6476128697395325,
      "learning_rate": 1.569293210846512e-06,
      "loss": 0.028678691387176512,
      "step": 6200
    },
    {
      "epoch": 5.193734542456719,
      "grad_norm": 17.67458724975586,
      "learning_rate": 1.5284206748621066e-06,
      "loss": 0.022574949264526366,
      "step": 6300
    },
    {
      "epoch": 5.276174773289365,
      "grad_norm": 0.6299949884414673,
      "learning_rate": 1.4875270148802465e-06,
      "loss": 0.028071470260620117,
      "step": 6400
    },
    {
      "epoch": 5.3586150041220115,
      "grad_norm": 0.17750702798366547,
      "learning_rate": 1.4466426255897827e-06,
      "loss": 0.02460844039916992,
      "step": 6500
    },
    {
      "epoch": 5.441055234954658,
      "grad_norm": 3.046633720397949,
      "learning_rate": 1.4057978947890166e-06,
      "loss": 0.028238294124603273,
      "step": 6600
    },
    {
      "epoch": 5.523495465787304,
      "grad_norm": 1.1183128356933594,
      "learning_rate": 1.3650231807996163e-06,
      "loss": 0.022344279289245605,
      "step": 6700
    },
    {
      "epoch": 5.605935696619951,
      "grad_norm": 0.39727112650871277,
      "learning_rate": 1.3243487899024401e-06,
      "loss": 0.024733517169952392,
      "step": 6800
    },
    {
      "epoch": 5.688375927452597,
      "grad_norm": 1.1431382894515991,
      "learning_rate": 1.2838049538120375e-06,
      "loss": 0.024790296554565428,
      "step": 6900
    },
    {
      "epoch": 5.7708161582852435,
      "grad_norm": 0.270554780960083,
      "learning_rate": 1.243421807206581e-06,
      "loss": 0.023978376388549806,
      "step": 7000
    },
    {
      "epoch": 5.85325638911789,
      "grad_norm": 2.6371097564697266,
      "learning_rate": 1.2032293653299107e-06,
      "loss": 0.024820666313171386,
      "step": 7100
    },
    {
      "epoch": 5.935696619950535,
      "grad_norm": 0.4371972680091858,
      "learning_rate": 1.1632575016823583e-06,
      "loss": 0.023902339935302733,
      "step": 7200
    },
    {
      "epoch": 6.018136850783182,
      "grad_norm": 0.3910028040409088,
      "learning_rate": 1.1235359258169183e-06,
      "loss": 0.023613801002502443,
      "step": 7300
    },
    {
      "epoch": 6.100577081615828,
      "grad_norm": 0.5897251963615417,
      "learning_rate": 1.0840941612572765e-06,
      "loss": 0.025773169994354247,
      "step": 7400
    },
    {
      "epoch": 6.183017312448475,
      "grad_norm": 7.796975135803223,
      "learning_rate": 1.0449615235541093e-06,
      "loss": 0.028378984928131103,
      "step": 7500
    },
    {
      "epoch": 6.265457543281121,
      "grad_norm": 2.8554458618164062,
      "learning_rate": 1.0061670984959582e-06,
      "loss": 0.023146660327911378,
      "step": 7600
    },
    {
      "epoch": 6.347897774113767,
      "grad_norm": 1.5360387563705444,
      "learning_rate": 9.677397204908788e-07,
      "loss": 0.025156841278076172,
      "step": 7700
    },
    {
      "epoch": 6.430338004946414,
      "grad_norm": 0.2781471312046051,
      "learning_rate": 9.297079511349307e-07,
      "loss": 0.023876771926879883,
      "step": 7800
    },
    {
      "epoch": 6.51277823577906,
      "grad_norm": 0.5193030834197998,
      "learning_rate": 8.921000579834404e-07,
      "loss": 0.021548757553100584,
      "step": 7900
    },
    {
      "epoch": 6.595218466611707,
      "grad_norm": 1.3652324676513672,
      "learning_rate": 8.549439935408109e-07,
      "loss": 0.027704770565032958,
      "step": 8000
    },
    {
      "epoch": 6.677658697444353,
      "grad_norm": 0.567807137966156,
      "learning_rate": 8.182673744844971e-07,
      "loss": 0.024193654060363768,
      "step": 8100
    },
    {
      "epoch": 6.760098928276999,
      "grad_norm": 1.0867784023284912,
      "learning_rate": 7.820974611385887e-07,
      "loss": 0.024752085208892823,
      "step": 8200
    },
    {
      "epoch": 6.842539159109646,
      "grad_norm": 12.679245948791504,
      "learning_rate": 7.464611372122565e-07,
      "loss": 0.02242401838302612,
      "step": 8300
    },
    {
      "epoch": 6.924979389942292,
      "grad_norm": 1.22047758102417,
      "learning_rate": 7.113848898181258e-07,
      "loss": 0.031413540840148926,
      "step": 8400
    },
    {
      "epoch": 7.007419620774938,
      "grad_norm": 36.422203063964844,
      "learning_rate": 6.76894789785417e-07,
      "loss": 0.0245809006690979,
      "step": 8500
    },
    {
      "epoch": 7.089859851607584,
      "grad_norm": 1.0370782613754272,
      "learning_rate": 6.430164722825002e-07,
      "loss": 0.02020338773727417,
      "step": 8600
    },
    {
      "epoch": 7.1723000824402305,
      "grad_norm": 1.1046611070632935,
      "learning_rate": 6.097751177632599e-07,
      "loss": 0.02843546390533447,
      "step": 8700
    },
    {
      "epoch": 7.254740313272877,
      "grad_norm": 1.1630239486694336,
      "learning_rate": 5.77195433251426e-07,
      "loss": 0.023567092418670655,
      "step": 8800
    },
    {
      "epoch": 7.337180544105523,
      "grad_norm": 0.6131232976913452,
      "learning_rate": 5.453016339767939e-07,
      "loss": 0.02418841600418091,
      "step": 8900
    },
    {
      "epoch": 7.41962077493817,
      "grad_norm": 1.4645527601242065,
      "learning_rate": 5.141174253769704e-07,
      "loss": 0.0257061243057251,
      "step": 9000
    },
    {
      "epoch": 7.502061005770816,
      "grad_norm": 0.9117152690887451,
      "learning_rate": 4.836659854780321e-07,
      "loss": 0.02661696672439575,
      "step": 9100
    },
    {
      "epoch": 7.5845012366034625,
      "grad_norm": 1.2171125411987305,
      "learning_rate": 4.5396994766719033e-07,
      "loss": 0.02204680919647217,
      "step": 9200
    },
    {
      "epoch": 7.666941467436109,
      "grad_norm": 0.6495709419250488,
      "learning_rate": 4.2505138387025753e-07,
      "loss": 0.029301033020019532,
      "step": 9300
    },
    {
      "epoch": 7.749381698268755,
      "grad_norm": 0.6626441478729248,
      "learning_rate": 3.969317881464367e-07,
      "loss": 0.021526577472686766,
      "step": 9400
    },
    {
      "epoch": 7.831821929101402,
      "grad_norm": 16.135684967041016,
      "learning_rate": 3.696320607126065e-07,
      "loss": 0.026122121810913085,
      "step": 9500
    },
    {
      "epoch": 7.914262159934048,
      "grad_norm": 0.8759784698486328,
      "learning_rate": 3.4317249240899686e-07,
      "loss": 0.025852499008178712,
      "step": 9600
    },
    {
      "epoch": 7.9967023907666945,
      "grad_norm": 0.800774872303009,
      "learning_rate": 3.175727496177826e-07,
      "loss": 0.02209474563598633,
      "step": 9700
    },
    {
      "epoch": 8.07914262159934,
      "grad_norm": 0.8495875000953674,
      "learning_rate": 2.928518596458161e-07,
      "loss": 0.02649038314819336,
      "step": 9800
    },
    {
      "epoch": 8.161582852431987,
      "grad_norm": 0.7733114361763,
      "learning_rate": 2.690281965823608e-07,
      "loss": 0.024643311500549315,
      "step": 9900
    },
    {
      "epoch": 8.244023083264633,
      "grad_norm": 12.20607852935791,
      "learning_rate": 2.461194676423352e-07,
      "loss": 0.026993231773376467,
      "step": 10000
    },
    {
      "epoch": 8.32646331409728,
      "grad_norm": 26.955886840820312,
      "learning_rate": 2.2414270000521946e-07,
      "loss": 0.02212390899658203,
      "step": 10100
    },
    {
      "epoch": 8.408903544929926,
      "grad_norm": 0.8895039558410645,
      "learning_rate": 2.031142281594066e-07,
      "loss": 0.02063568115234375,
      "step": 10200
    },
    {
      "epoch": 8.491343775762573,
      "grad_norm": 0.5100795030593872,
      "learning_rate": 1.8304968176140035e-07,
      "loss": 0.024049296379089355,
      "step": 10300
    },
    {
      "epoch": 8.573784006595218,
      "grad_norm": 1.8475189208984375,
      "learning_rate": 1.6396397401889679e-07,
      "loss": 0.02524357557296753,
      "step": 10400
    },
    {
      "epoch": 8.656224237427864,
      "grad_norm": 0.6764451861381531,
      "learning_rate": 1.4587129060636367e-07,
      "loss": 0.028507494926452638,
      "step": 10500
    },
    {
      "epoch": 8.738664468260511,
      "grad_norm": 1.1165720224380493,
      "learning_rate": 1.2878507912137682e-07,
      "loss": 0.02533757209777832,
      "step": 10600
    },
    {
      "epoch": 8.821104699093157,
      "grad_norm": 0.7385006546974182,
      "learning_rate": 1.1271803908953354e-07,
      "loss": 0.022719991207122803,
      "step": 10700
    },
    {
      "epoch": 8.903544929925804,
      "grad_norm": 8.316965103149414,
      "learning_rate": 9.76821125253844e-08,
      "loss": 0.021582581996917725,
      "step": 10800
    },
    {
      "epoch": 8.98598516075845,
      "grad_norm": 1.0215933322906494,
      "learning_rate": 8.368847505639149e-08,
      "loss": 0.02419511079788208,
      "step": 10900
    },
    {
      "epoch": 9.068425391591097,
      "grad_norm": 8.314555168151855,
      "learning_rate": 7.074752761651227e-08,
      "loss": 0.026871368885040284,
      "step": 11000
    },
    {
      "epoch": 9.150865622423742,
      "grad_norm": 7.914130687713623,
      "learning_rate": 5.8868888715585325e-08,
      "loss": 0.02440465450286865,
      "step": 11100
    },
    {
      "epoch": 9.23330585325639,
      "grad_norm": 17.640907287597656,
      "learning_rate": 4.806138729026111e-08,
      "loss": 0.020871245861053468,
      "step": 11200
    },
    {
      "epoch": 9.315746084089035,
      "grad_norm": 0.4218542277812958,
      "learning_rate": 3.833305614179061e-08,
      "loss": 0.024367706775665285,
      "step": 11300
    },
    {
      "epoch": 9.398186314921682,
      "grad_norm": 0.497744619846344,
      "learning_rate": 2.9691125965554454e-08,
      "loss": 0.027901573181152342,
      "step": 11400
    },
    {
      "epoch": 9.480626545754328,
      "grad_norm": 0.6788234710693359,
      "learning_rate": 2.214201997676152e-08,
      "loss": 0.021528902053833007,
      "step": 11500
    },
    {
      "epoch": 9.563066776586975,
      "grad_norm": 0.21850308775901794,
      "learning_rate": 1.5691349136322697e-08,
      "loss": 0.02456042289733887,
      "step": 11600
    },
    {
      "epoch": 9.64550700741962,
      "grad_norm": 0.7916850447654724,
      "learning_rate": 1.0343907980436218e-08,
      "loss": 0.019252289533615113,
      "step": 11700
    },
    {
      "epoch": 9.727947238252266,
      "grad_norm": 0.3894334137439728,
      "learning_rate": 6.103671056994387e-09,
      "loss": 0.020840485095977784,
      "step": 11800
    },
    {
      "epoch": 9.810387469084914,
      "grad_norm": 1.1665902137756348,
      "learning_rate": 2.9737899714539775e-09,
      "loss": 0.030273616313934326,
      "step": 11900
    },
    {
      "epoch": 9.892827699917559,
      "grad_norm": 0.6720395088195801,
      "learning_rate": 9.565910443685155e-10,
      "loss": 0.02424750566482544,
      "step": 12000
    }
  ],
  "logging_steps": 100,
  "max_steps": 12130,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7807792431338136.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}