{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9994447529150472,
  "eval_steps": 100,
  "global_step": 675,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007403294466037387,
      "grad_norm": 0.6776805171272973,
      "learning_rate": 1.4705882352941177e-06,
      "loss": 1.2512,
      "step": 5
    },
    {
      "epoch": 0.014806588932074774,
      "grad_norm": 0.44944873495655524,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 1.2594,
      "step": 10
    },
    {
      "epoch": 0.02220988339811216,
      "grad_norm": 0.34624498626136563,
      "learning_rate": 4.411764705882353e-06,
      "loss": 1.2327,
      "step": 15
    },
    {
      "epoch": 0.029613177864149548,
      "grad_norm": 0.3384934751143345,
      "learning_rate": 5.882352941176471e-06,
      "loss": 1.1823,
      "step": 20
    },
    {
      "epoch": 0.037016472330186935,
      "grad_norm": 0.2415385954324663,
      "learning_rate": 7.352941176470589e-06,
      "loss": 1.1483,
      "step": 25
    },
    {
      "epoch": 0.04441976679622432,
      "grad_norm": 0.21956265650508958,
      "learning_rate": 8.823529411764707e-06,
      "loss": 1.1051,
      "step": 30
    },
    {
      "epoch": 0.05182306126226171,
      "grad_norm": 0.18350394805421755,
      "learning_rate": 1.0294117647058823e-05,
      "loss": 1.0659,
      "step": 35
    },
    {
      "epoch": 0.059226355728299096,
      "grad_norm": 0.16210146685861945,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 1.0381,
      "step": 40
    },
    {
      "epoch": 0.06662965019433648,
      "grad_norm": 0.1607004827826561,
      "learning_rate": 1.323529411764706e-05,
      "loss": 1.0217,
      "step": 45
    },
    {
      "epoch": 0.07403294466037387,
      "grad_norm": 0.16745984502215897,
      "learning_rate": 1.4705882352941179e-05,
      "loss": 1.038,
      "step": 50
    },
    {
      "epoch": 0.08143623912641125,
      "grad_norm": 0.14843663256682382,
      "learning_rate": 1.6176470588235296e-05,
      "loss": 1.0276,
      "step": 55
    },
    {
      "epoch": 0.08883953359244864,
      "grad_norm": 0.17168834832578023,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 1.0032,
      "step": 60
    },
    {
      "epoch": 0.09624282805848602,
      "grad_norm": 0.15126385928527755,
      "learning_rate": 1.911764705882353e-05,
      "loss": 0.9954,
      "step": 65
    },
    {
      "epoch": 0.10364612252452342,
      "grad_norm": 0.1688834438402727,
      "learning_rate": 1.9999464266898485e-05,
      "loss": 0.9919,
      "step": 70
    },
    {
      "epoch": 0.1110494169905608,
      "grad_norm": 0.20449596627344765,
      "learning_rate": 1.9993437928712977e-05,
      "loss": 0.9839,
      "step": 75
    },
    {
      "epoch": 0.11845271145659819,
      "grad_norm": 0.17590208096396392,
      "learning_rate": 1.998071963486563e-05,
      "loss": 0.9714,
      "step": 80
    },
    {
      "epoch": 0.12585600592263557,
      "grad_norm": 0.14935660715610657,
      "learning_rate": 1.9961317901970953e-05,
      "loss": 0.9577,
      "step": 85
    },
    {
      "epoch": 0.13325930038867295,
      "grad_norm": 0.1656804473286765,
      "learning_rate": 1.993524572210807e-05,
      "loss": 0.9607,
      "step": 90
    },
    {
      "epoch": 0.14066259485471036,
      "grad_norm": 0.20165204812335902,
      "learning_rate": 1.990252055412077e-05,
      "loss": 0.9538,
      "step": 95
    },
    {
      "epoch": 0.14806588932074774,
      "grad_norm": 0.1672105719290636,
      "learning_rate": 1.9863164311926433e-05,
      "loss": 0.9842,
      "step": 100
    },
    {
      "epoch": 0.14806588932074774,
      "eval_loss": 0.9855244755744934,
      "eval_runtime": 7.1036,
      "eval_samples_per_second": 18.019,
      "eval_steps_per_second": 2.252,
      "step": 100
    },
    {
      "epoch": 0.15546918378678512,
      "grad_norm": 0.1594521756746442,
      "learning_rate": 1.981720334984174e-05,
      "loss": 0.9583,
      "step": 105
    },
    {
      "epoch": 0.1628724782528225,
      "grad_norm": 0.17121067681141633,
      "learning_rate": 1.9764668444934853e-05,
      "loss": 0.9474,
      "step": 110
    },
    {
      "epoch": 0.17027577271885988,
      "grad_norm": 0.15907478498991337,
      "learning_rate": 1.970559477641606e-05,
      "loss": 0.9207,
      "step": 115
    },
    {
      "epoch": 0.1776790671848973,
      "grad_norm": 0.1606853101811812,
      "learning_rate": 1.9640021902080523e-05,
      "loss": 0.9532,
      "step": 120
    },
    {
      "epoch": 0.18508236165093467,
      "grad_norm": 0.14842172195462983,
      "learning_rate": 1.9567993731818988e-05,
      "loss": 0.9512,
      "step": 125
    },
    {
      "epoch": 0.19248565611697205,
      "grad_norm": 0.16039228542123013,
      "learning_rate": 1.9489558498214197e-05,
      "loss": 0.9443,
      "step": 130
    },
    {
      "epoch": 0.19988895058300943,
      "grad_norm": 0.15683712656065646,
      "learning_rate": 1.9404768724242667e-05,
      "loss": 0.9257,
      "step": 135
    },
    {
      "epoch": 0.20729224504904684,
      "grad_norm": 0.17249812910241194,
      "learning_rate": 1.931368118810346e-05,
      "loss": 0.9545,
      "step": 140
    },
    {
      "epoch": 0.21469553951508422,
      "grad_norm": 0.15206299782477828,
      "learning_rate": 1.92163568851975e-05,
      "loss": 0.938,
      "step": 145
    },
    {
      "epoch": 0.2220988339811216,
      "grad_norm": 0.16815584502250794,
      "learning_rate": 1.911286098728296e-05,
      "loss": 0.9285,
      "step": 150
    },
    {
      "epoch": 0.22950212844715898,
      "grad_norm": 0.16122796157665575,
      "learning_rate": 1.900326279883392e-05,
      "loss": 0.9624,
      "step": 155
    },
    {
      "epoch": 0.23690542291319638,
      "grad_norm": 0.15224168391003395,
      "learning_rate": 1.8887635710631716e-05,
      "loss": 0.9662,
      "step": 160
    },
    {
      "epoch": 0.24430871737923376,
      "grad_norm": 0.14815411902225328,
      "learning_rate": 1.8766057150619865e-05,
      "loss": 0.9346,
      "step": 165
    },
    {
      "epoch": 0.25171201184527114,
      "grad_norm": 0.15183932254655913,
      "learning_rate": 1.8638608532055635e-05,
      "loss": 0.9533,
      "step": 170
    },
    {
      "epoch": 0.2591153063113085,
      "grad_norm": 0.1446345977964626,
      "learning_rate": 1.8505375198992856e-05,
      "loss": 0.9395,
      "step": 175
    },
    {
      "epoch": 0.2665186007773459,
      "grad_norm": 0.14315212915090392,
      "learning_rate": 1.836644636913258e-05,
      "loss": 0.9099,
      "step": 180
    },
    {
      "epoch": 0.2739218952433833,
      "grad_norm": 0.16987297421517,
      "learning_rate": 1.8221915074079764e-05,
      "loss": 0.9342,
      "step": 185
    },
    {
      "epoch": 0.2813251897094207,
      "grad_norm": 0.17161893073243528,
      "learning_rate": 1.8071878097046064e-05,
      "loss": 0.9115,
      "step": 190
    },
    {
      "epoch": 0.2887284841754581,
      "grad_norm": 0.1544233807044902,
      "learning_rate": 1.7916435908040413e-05,
      "loss": 0.9309,
      "step": 195
    },
    {
      "epoch": 0.2961317786414955,
      "grad_norm": 0.14748037798669633,
      "learning_rate": 1.7755692596590778e-05,
      "loss": 0.9333,
      "step": 200
    },
    {
      "epoch": 0.2961317786414955,
      "eval_loss": 0.9494131803512573,
      "eval_runtime": 7.1466,
      "eval_samples_per_second": 17.911,
      "eval_steps_per_second": 2.239,
      "step": 200
    },
    {
      "epoch": 0.30353507310753286,
      "grad_norm": 0.1555651675700521,
      "learning_rate": 1.7589755802042188e-05,
      "loss": 0.9287,
      "step": 205
    },
    {
      "epoch": 0.31093836757357024,
      "grad_norm": 0.16353203572144123,
      "learning_rate": 1.7418736641477636e-05,
      "loss": 0.9099,
      "step": 210
    },
    {
      "epoch": 0.3183416620396076,
      "grad_norm": 0.15764904906951305,
      "learning_rate": 1.7242749635310222e-05,
      "loss": 0.913,
      "step": 215
    },
    {
      "epoch": 0.325744956505645,
      "grad_norm": 0.1448977765793318,
      "learning_rate": 1.7061912630596252e-05,
      "loss": 0.9173,
      "step": 220
    },
    {
      "epoch": 0.3331482509716824,
      "grad_norm": 0.15258137653598713,
      "learning_rate": 1.6876346722120747e-05,
      "loss": 0.9319,
      "step": 225
    },
    {
      "epoch": 0.34055154543771976,
      "grad_norm": 0.1563094102159032,
      "learning_rate": 1.6686176171308125e-05,
      "loss": 0.955,
      "step": 230
    },
    {
      "epoch": 0.3479548399037572,
      "grad_norm": 0.14423025166628695,
      "learning_rate": 1.6491528323012412e-05,
      "loss": 0.9132,
      "step": 235
    },
    {
      "epoch": 0.3553581343697946,
      "grad_norm": 0.14263303346026474,
      "learning_rate": 1.6292533520242663e-05,
      "loss": 0.9157,
      "step": 240
    },
    {
      "epoch": 0.36276142883583196,
      "grad_norm": 0.13731880620436607,
      "learning_rate": 1.6089325016880737e-05,
      "loss": 0.9058,
      "step": 245
    },
    {
      "epoch": 0.37016472330186934,
      "grad_norm": 0.17337841623245412,
      "learning_rate": 1.588203888844982e-05,
      "loss": 0.9261,
      "step": 250
    },
    {
      "epoch": 0.3775680177679067,
      "grad_norm": 0.1517393366410306,
      "learning_rate": 1.5670813940993504e-05,
      "loss": 0.8936,
      "step": 255
    },
    {
      "epoch": 0.3849713122339441,
      "grad_norm": 0.14624943669912388,
      "learning_rate": 1.5455791618126407e-05,
      "loss": 0.8844,
      "step": 260
    },
    {
      "epoch": 0.3923746066999815,
      "grad_norm": 0.14950642484342547,
      "learning_rate": 1.5237115906318565e-05,
      "loss": 0.9132,
      "step": 265
    },
    {
      "epoch": 0.39977790116601886,
      "grad_norm": 0.15048654068633793,
      "learning_rate": 1.5014933238477069e-05,
      "loss": 0.8891,
      "step": 270
    },
    {
      "epoch": 0.4071811956320563,
      "grad_norm": 0.1570568189193127,
      "learning_rate": 1.4789392395889468e-05,
      "loss": 0.9186,
      "step": 275
    },
    {
      "epoch": 0.41458449009809367,
      "grad_norm": 0.15381562012177635,
      "learning_rate": 1.4560644408594602e-05,
      "loss": 0.8927,
      "step": 280
    },
    {
      "epoch": 0.42198778456413105,
      "grad_norm": 0.1444417700490563,
      "learning_rate": 1.432884245424761e-05,
      "loss": 0.9081,
      "step": 285
    },
    {
      "epoch": 0.42939107903016843,
      "grad_norm": 0.15807566475131207,
      "learning_rate": 1.4094141755546816e-05,
      "loss": 0.9389,
      "step": 290
    },
    {
      "epoch": 0.4367943734962058,
      "grad_norm": 0.14968340220236578,
      "learning_rate": 1.3856699476291176e-05,
      "loss": 0.8926,
      "step": 295
    },
    {
      "epoch": 0.4441976679622432,
      "grad_norm": 0.15781464037029244,
      "learning_rate": 1.3616674616137902e-05,
      "loss": 0.9161,
      "step": 300
    },
    {
      "epoch": 0.4441976679622432,
      "eval_loss": 0.930830717086792,
      "eval_runtime": 7.1062,
      "eval_samples_per_second": 18.013,
      "eval_steps_per_second": 2.252,
      "step": 300
    },
    {
      "epoch": 0.4516009624282806,
      "grad_norm": 0.15525393114371358,
      "learning_rate": 1.3374227904130724e-05,
      "loss": 0.9071,
      "step": 305
    },
    {
      "epoch": 0.45900425689431795,
      "grad_norm": 0.1457498963275538,
      "learning_rate": 1.3129521691070108e-05,
      "loss": 0.8833,
      "step": 310
    },
    {
      "epoch": 0.46640755136035533,
      "grad_norm": 0.14987682585253773,
      "learning_rate": 1.2882719840797473e-05,
      "loss": 0.9022,
      "step": 315
    },
    {
      "epoch": 0.47381084582639277,
      "grad_norm": 0.15509542057237247,
      "learning_rate": 1.2633987620466229e-05,
      "loss": 0.8885,
      "step": 320
    },
    {
      "epoch": 0.48121414029243015,
      "grad_norm": 0.14584510044567442,
      "learning_rate": 1.2383491589873122e-05,
      "loss": 0.8899,
      "step": 325
    },
    {
      "epoch": 0.48861743475846753,
      "grad_norm": 0.14309664992352822,
      "learning_rate": 1.213139948992394e-05,
      "loss": 0.8998,
      "step": 330
    },
    {
      "epoch": 0.4960207292245049,
      "grad_norm": 0.15130038484765435,
      "learning_rate": 1.187788013030837e-05,
      "loss": 0.8988,
      "step": 335
    },
    {
      "epoch": 0.5034240236905423,
      "grad_norm": 0.1459259790309168,
      "learning_rate": 1.1623103276459086e-05,
      "loss": 0.9007,
      "step": 340
    },
    {
      "epoch": 0.5108273181565797,
      "grad_norm": 0.14777529707412382,
      "learning_rate": 1.1367239535870913e-05,
      "loss": 0.8925,
      "step": 345
    },
    {
      "epoch": 0.518230612622617,
      "grad_norm": 0.14724048128355402,
      "learning_rate": 1.1110460243856051e-05,
      "loss": 0.8785,
      "step": 350
    },
    {
      "epoch": 0.5256339070886544,
      "grad_norm": 0.14527394357147336,
      "learning_rate": 1.085293734881197e-05,
      "loss": 0.8982,
      "step": 355
    },
    {
      "epoch": 0.5330372015546918,
      "grad_norm": 0.14050877787386462,
      "learning_rate": 1.0594843297078736e-05,
      "loss": 0.9181,
      "step": 360
    },
    {
      "epoch": 0.5404404960207292,
      "grad_norm": 0.15865485844086924,
      "learning_rate": 1.0336350917462925e-05,
      "loss": 0.9062,
      "step": 365
    },
    {
      "epoch": 0.5478437904867666,
      "grad_norm": 0.13521171802296975,
      "learning_rate": 1.0077633305505402e-05,
      "loss": 0.8927,
      "step": 370
    },
    {
      "epoch": 0.555247084952804,
      "grad_norm": 0.13603561195542918,
      "learning_rate": 9.818863707570476e-06,
      "loss": 0.9154,
      "step": 375
    },
    {
      "epoch": 0.5626503794188414,
      "grad_norm": 0.13965992628983345,
      "learning_rate": 9.560215404834094e-06,
      "loss": 0.9016,
      "step": 380
    },
    {
      "epoch": 0.5700536738848788,
      "grad_norm": 0.13666000951700663,
      "learning_rate": 9.30186159724869e-06,
      "loss": 0.8612,
      "step": 385
    },
    {
      "epoch": 0.5774569683509162,
      "grad_norm": 0.13625895333241347,
      "learning_rate": 9.043975287562443e-06,
      "loss": 0.9001,
      "step": 390
    },
    {
      "epoch": 0.5848602628169536,
      "grad_norm": 0.14371829685671048,
      "learning_rate": 8.786729165470584e-06,
      "loss": 0.8738,
      "step": 395
    },
    {
      "epoch": 0.592263557282991,
      "grad_norm": 0.13916699255941037,
      "learning_rate": 8.530295491976338e-06,
      "loss": 0.8804,
      "step": 400
    },
    {
      "epoch": 0.592263557282991,
      "eval_loss": 0.9166682958602905,
      "eval_runtime": 7.0621,
      "eval_samples_per_second": 18.125,
      "eval_steps_per_second": 2.266,
      "step": 400
    },
    {
      "epoch": 0.5996668517490283,
      "grad_norm": 0.13004150614702822,
      "learning_rate": 8.274845984038916e-06,
      "loss": 0.8647,
      "step": 405
    },
    {
      "epoch": 0.6070701462150657,
      "grad_norm": 0.14629481441132058,
      "learning_rate": 8.020551699585843e-06,
      "loss": 0.9007,
      "step": 410
    },
    {
      "epoch": 0.6144734406811031,
      "grad_norm": 0.12877499400506406,
      "learning_rate": 7.76758292296659e-06,
      "loss": 0.8745,
      "step": 415
    },
    {
      "epoch": 0.6218767351471405,
      "grad_norm": 0.13752238505053258,
      "learning_rate": 7.5161090509242005e-06,
      "loss": 0.8928,
      "step": 420
    },
    {
      "epoch": 0.6292800296131779,
      "grad_norm": 0.14148995267833064,
      "learning_rate": 7.2662984791613186e-06,
      "loss": 0.8845,
      "step": 425
    },
    {
      "epoch": 0.6366833240792152,
      "grad_norm": 0.14452849454657804,
      "learning_rate": 7.01831848957653e-06,
      "loss": 0.8991,
      "step": 430
    },
    {
      "epoch": 0.6440866185452526,
      "grad_norm": 0.13297035448949285,
      "learning_rate": 6.772335138246548e-06,
      "loss": 0.8966,
      "step": 435
    },
    {
      "epoch": 0.65148991301129,
      "grad_norm": 0.13999651657873824,
      "learning_rate": 6.528513144229256e-06,
      "loss": 0.8901,
      "step": 440
    },
    {
      "epoch": 0.6588932074773274,
      "grad_norm": 0.13786802129264458,
      "learning_rate": 6.287015779262064e-06,
      "loss": 0.8988,
      "step": 445
    },
    {
      "epoch": 0.6662965019433648,
      "grad_norm": 0.13362818972180024,
      "learning_rate": 6.048004758429451e-06,
      "loss": 0.8773,
      "step": 450
    },
    {
      "epoch": 0.6736997964094021,
      "grad_norm": 0.14094460764095268,
      "learning_rate": 5.811640131872867e-06,
      "loss": 0.9022,
      "step": 455
    },
    {
      "epoch": 0.6811030908754395,
      "grad_norm": 0.13177032254471754,
      "learning_rate": 5.578080177615575e-06,
      "loss": 0.8681,
      "step": 460
    },
    {
      "epoch": 0.688506385341477,
      "grad_norm": 0.1447285259606947,
      "learning_rate": 5.347481295574141e-06,
      "loss": 0.8642,
      "step": 465
    },
    {
      "epoch": 0.6959096798075144,
      "grad_norm": 0.16212399303569955,
      "learning_rate": 5.119997902827584e-06,
      "loss": 0.8768,
      "step": 470
    },
    {
      "epoch": 0.7033129742735518,
      "grad_norm": 0.13407281956450473,
      "learning_rate": 4.8957823302142916e-06,
      "loss": 0.8861,
      "step": 475
    },
    {
      "epoch": 0.7107162687395892,
      "grad_norm": 0.12431950401558224,
      "learning_rate": 4.674984720325961e-06,
      "loss": 0.8663,
      "step": 480
    },
    {
      "epoch": 0.7181195632056265,
      "grad_norm": 0.13146748720425666,
      "learning_rate": 4.457752926966888e-06,
      "loss": 0.8618,
      "step": 485
    },
    {
      "epoch": 0.7255228576716639,
      "grad_norm": 0.12584510121252945,
      "learning_rate": 4.244232416145839e-06,
      "loss": 0.8854,
      "step": 490
    },
    {
      "epoch": 0.7329261521377013,
      "grad_norm": 0.12990134879461734,
      "learning_rate": 4.0345661686669745e-06,
      "loss": 0.8762,
      "step": 495
    },
    {
      "epoch": 0.7403294466037387,
      "grad_norm": 0.13783047027951226,
      "learning_rate": 3.828894584384867e-06,
      "loss": 0.8859,
      "step": 500
    },
    {
      "epoch": 0.7403294466037387,
      "eval_loss": 0.9078959226608276,
      "eval_runtime": 7.1187,
      "eval_samples_per_second": 17.981,
      "eval_steps_per_second": 2.248,
      "step": 500
    },
    {
      "epoch": 0.747732741069776,
      "grad_norm": 0.12586000345704224,
      "learning_rate": 3.62735538818787e-06,
      "loss": 0.8688,
      "step": 505
    },
    {
      "epoch": 0.7551360355358134,
      "grad_norm": 0.14104016395887148,
      "learning_rate": 3.4300835377726904e-06,
      "loss": 0.8703,
      "step": 510
    },
    {
      "epoch": 0.7625393300018508,
      "grad_norm": 0.13533570426883107,
      "learning_rate": 3.2372111332720045e-06,
      "loss": 0.9138,
      "step": 515
    },
    {
      "epoch": 0.7699426244678882,
      "grad_norm": 0.14074880883541166,
      "learning_rate": 3.048867328795588e-06,
      "loss": 0.8618,
      "step": 520
    },
    {
      "epoch": 0.7773459189339256,
      "grad_norm": 0.13230663319443067,
      "learning_rate": 2.865178245944218e-06,
      "loss": 0.8604,
      "step": 525
    },
    {
      "epoch": 0.784749213399963,
      "grad_norm": 0.1247899466464526,
      "learning_rate": 2.686266889354211e-06,
      "loss": 0.8859,
      "step": 530
    },
    {
      "epoch": 0.7921525078660003,
      "grad_norm": 0.13575024760681823,
      "learning_rate": 2.5122530643292274e-06,
      "loss": 0.8905,
      "step": 535
    },
    {
      "epoch": 0.7995558023320377,
      "grad_norm": 0.1357493128741245,
      "learning_rate": 2.3432532966144526e-06,
      "loss": 0.8852,
      "step": 540
    },
    {
      "epoch": 0.8069590967980751,
      "grad_norm": 0.13498792821706115,
      "learning_rate": 2.1793807543668857e-06,
      "loss": 0.8828,
      "step": 545
    },
    {
      "epoch": 0.8143623912641126,
      "grad_norm": 0.12019174745605471,
      "learning_rate": 2.0207451723739633e-06,
      "loss": 0.8742,
      "step": 550
    },
    {
      "epoch": 0.82176568573015,
      "grad_norm": 0.12150186530956911,
      "learning_rate": 1.8674527785713247e-06,
      "loss": 0.8802,
      "step": 555
    },
    {
      "epoch": 0.8291689801961873,
      "grad_norm": 0.13657600204630863,
      "learning_rate": 1.7196062229088606e-06,
      "loss": 0.8458,
      "step": 560
    },
    {
      "epoch": 0.8365722746622247,
      "grad_norm": 0.14316460964604913,
      "learning_rate": 1.577304508612717e-06,
      "loss": 0.8772,
      "step": 565
    },
    {
      "epoch": 0.8439755691282621,
      "grad_norm": 0.11702464461690702,
      "learning_rate": 1.4406429258892762e-06,
      "loss": 0.8978,
      "step": 570
    },
    {
      "epoch": 0.8513788635942995,
      "grad_norm": 0.13649799424857104,
      "learning_rate": 1.3097129881154936e-06,
      "loss": 0.8679,
      "step": 575
    },
    {
      "epoch": 0.8587821580603369,
      "grad_norm": 0.12879197044894133,
      "learning_rate": 1.1846023705583442e-06,
      "loss": 0.8611,
      "step": 580
    },
    {
      "epoch": 0.8661854525263742,
      "grad_norm": 0.12611530487166148,
      "learning_rate": 1.065394851664394e-06,
      "loss": 0.8847,
      "step": 585
    },
    {
      "epoch": 0.8735887469924116,
      "grad_norm": 0.12199166350158228,
      "learning_rate": 9.521702569588199e-07,
      "loss": 0.9041,
      "step": 590
    },
    {
      "epoch": 0.880992041458449,
      "grad_norm": 0.13250148039242704,
      "learning_rate": 8.450044055914497e-07,
      "loss": 0.8703,
      "step": 595
    },
    {
      "epoch": 0.8883953359244864,
      "grad_norm": 0.12335176677515089,
      "learning_rate": 7.439690595656013e-07,
      "loss": 0.8931,
      "step": 600
    },
    {
      "epoch": 0.8883953359244864,
      "eval_loss": 0.904110312461853,
      "eval_runtime": 7.0453,
      "eval_samples_per_second": 18.168,
      "eval_steps_per_second": 2.271,
      "step": 600
    },
    {
      "epoch": 0.8957986303905238,
      "grad_norm": 0.13803312908970108,
      "learning_rate": 6.491318756837417e-07,
      "loss": 0.8773,
      "step": 605
    },
    {
      "epoch": 0.9032019248565611,
      "grad_norm": 0.11990945958525849,
      "learning_rate": 5.605563602421149e-07,
      "loss": 0.8506,
      "step": 610
    },
    {
      "epoch": 0.9106052193225985,
      "grad_norm": 0.12252169940099521,
      "learning_rate": 4.783018265047179e-07,
      "loss": 0.9066,
      "step": 615
    },
    {
      "epoch": 0.9180085137886359,
      "grad_norm": 0.12997936768176632,
      "learning_rate": 4.024233549850509e-07,
      "loss": 0.8924,
      "step": 620
    },
    {
      "epoch": 0.9254118082546733,
      "grad_norm": 0.12018543528554308,
      "learning_rate": 3.329717565622825e-07,
      "loss": 0.8889,
      "step": 625
    },
    {
      "epoch": 0.9328151027207107,
      "grad_norm": 0.12623553627779757,
      "learning_rate": 2.6999353845651113e-07,
      "loss": 0.8718,
      "step": 630
    },
    {
      "epoch": 0.9402183971867482,
      "grad_norm": 0.12569602093691798,
      "learning_rate": 2.1353087308590314e-07,
      "loss": 0.8885,
      "step": 635
    },
    {
      "epoch": 0.9476216916527855,
      "grad_norm": 0.12693697747520694,
      "learning_rate": 1.6362156982656085e-07,
      "loss": 0.8778,
      "step": 640
    },
    {
      "epoch": 0.9550249861188229,
      "grad_norm": 0.11916388416111799,
      "learning_rate": 1.2029904969404482e-07,
      "loss": 0.8574,
      "step": 645
    },
    {
      "epoch": 0.9624282805848603,
      "grad_norm": 0.13423693830897884,
      "learning_rate": 8.359232296349163e-08,
      "loss": 0.8633,
      "step": 650
    },
    {
      "epoch": 0.9698315750508977,
      "grad_norm": 0.12941855976651295,
      "learning_rate": 5.3525969743324356e-08,
      "loss": 0.8779,
      "step": 655
    },
    {
      "epoch": 0.9772348695169351,
      "grad_norm": 0.11997265846004904,
      "learning_rate": 3.012012351554017e-08,
      "loss": 0.8493,
      "step": 660
    },
    {
      "epoch": 0.9846381639829724,
      "grad_norm": 0.13237634154671962,
      "learning_rate": 1.3390457653639221e-08,
      "loss": 0.8863,
      "step": 665
    },
    {
      "epoch": 0.9920414584490098,
      "grad_norm": 0.13967439000954648,
      "learning_rate": 3.3481749271768726e-09,
      "loss": 0.8954,
      "step": 670
    },
    {
      "epoch": 0.9994447529150472,
      "grad_norm": 0.12596999235093093,
      "learning_rate": 0.0,
      "loss": 0.861,
      "step": 675
    },
    {
      "epoch": 0.9994447529150472,
      "step": 675,
      "total_flos": 1.6624354892709888e+17,
      "train_loss": 0.9221899901496039,
      "train_runtime": 5284.4545,
      "train_samples_per_second": 4.089,
      "train_steps_per_second": 0.128
    }
  ],
  "logging_steps": 5,
  "max_steps": 675,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.6624354892709888e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}