{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1109,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009017132551848512,
      "grad_norm": 1.8547641038894653,
      "learning_rate": 9.00900900900901e-06,
      "loss": 0.9349,
      "step": 10
    },
    {
      "epoch": 0.018034265103697024,
      "grad_norm": 1.347398281097412,
      "learning_rate": 1.801801801801802e-05,
      "loss": 0.7242,
      "step": 20
    },
    {
      "epoch": 0.027051397655545536,
      "grad_norm": 1.2487881183624268,
      "learning_rate": 2.702702702702703e-05,
      "loss": 0.4507,
      "step": 30
    },
    {
      "epoch": 0.03606853020739405,
      "grad_norm": 1.1477875709533691,
      "learning_rate": 3.603603603603604e-05,
      "loss": 0.33,
      "step": 40
    },
    {
      "epoch": 0.04508566275924256,
      "grad_norm": 0.923848569393158,
      "learning_rate": 4.5045045045045046e-05,
      "loss": 0.234,
      "step": 50
    },
    {
      "epoch": 0.05410279531109107,
      "grad_norm": 0.9260658025741577,
      "learning_rate": 5.405405405405406e-05,
      "loss": 0.2077,
      "step": 60
    },
    {
      "epoch": 0.06311992786293959,
      "grad_norm": 1.255967378616333,
      "learning_rate": 6.306306306306306e-05,
      "loss": 0.1886,
      "step": 70
    },
    {
      "epoch": 0.0721370604147881,
      "grad_norm": 0.7384198904037476,
      "learning_rate": 7.207207207207208e-05,
      "loss": 0.1645,
      "step": 80
    },
    {
      "epoch": 0.0811541929666366,
      "grad_norm": 0.672892153263092,
      "learning_rate": 8.108108108108109e-05,
      "loss": 0.1591,
      "step": 90
    },
    {
      "epoch": 0.09017132551848513,
      "grad_norm": 0.8307783007621765,
      "learning_rate": 9.009009009009009e-05,
      "loss": 0.1595,
      "step": 100
    },
    {
      "epoch": 0.09918845807033363,
      "grad_norm": 0.7313665151596069,
      "learning_rate": 9.90990990990991e-05,
      "loss": 0.1406,
      "step": 110
    },
    {
      "epoch": 0.10820559062218214,
      "grad_norm": 0.985645592212677,
      "learning_rate": 9.997993520894937e-05,
      "loss": 0.1385,
      "step": 120
    },
    {
      "epoch": 0.11722272317403065,
      "grad_norm": 0.9960182905197144,
      "learning_rate": 9.99105961120544e-05,
      "loss": 0.137,
      "step": 130
    },
    {
      "epoch": 0.12623985572587917,
      "grad_norm": 0.5437267422676086,
      "learning_rate": 9.979180368331558e-05,
      "loss": 0.1269,
      "step": 140
    },
    {
      "epoch": 0.13525698827772767,
      "grad_norm": 0.5780126452445984,
      "learning_rate": 9.962367562682496e-05,
      "loss": 0.1282,
      "step": 150
    },
    {
      "epoch": 0.1442741208295762,
      "grad_norm": 0.8550663590431213,
      "learning_rate": 9.940637853030572e-05,
      "loss": 0.1267,
      "step": 160
    },
    {
      "epoch": 0.1532912533814247,
      "grad_norm": 0.5869548916816711,
      "learning_rate": 9.914012770005072e-05,
      "loss": 0.1224,
      "step": 170
    },
    {
      "epoch": 0.1623083859332732,
      "grad_norm": 0.6128000617027283,
      "learning_rate": 9.882518694758875e-05,
      "loss": 0.1059,
      "step": 180
    },
    {
      "epoch": 0.17132551848512173,
      "grad_norm": 0.852254331111908,
      "learning_rate": 9.846186832828989e-05,
      "loss": 0.0997,
      "step": 190
    },
    {
      "epoch": 0.18034265103697025,
      "grad_norm": 0.6299287676811218,
      "learning_rate": 9.805053183216923e-05,
      "loss": 0.1038,
      "step": 200
    },
    {
      "epoch": 0.18935978358881875,
      "grad_norm": 0.8325192928314209,
      "learning_rate": 9.759158502719481e-05,
      "loss": 0.1207,
      "step": 210
    },
    {
      "epoch": 0.19837691614066727,
      "grad_norm": 0.46743109822273254,
      "learning_rate": 9.708548265545375e-05,
      "loss": 0.105,
      "step": 220
    },
    {
      "epoch": 0.2073940486925158,
      "grad_norm": 0.6069552302360535,
      "learning_rate": 9.653272618257631e-05,
      "loss": 0.0968,
      "step": 230
    },
    {
      "epoch": 0.2164111812443643,
      "grad_norm": 0.6297630071640015,
      "learning_rate": 9.593386330086458e-05,
      "loss": 0.0982,
      "step": 240
    },
    {
      "epoch": 0.2254283137962128,
      "grad_norm": 0.574450671672821,
      "learning_rate": 9.528948738661784e-05,
      "loss": 0.0996,
      "step": 250
    },
    {
      "epoch": 0.2344454463480613,
      "grad_norm": 0.8703469038009644,
      "learning_rate": 9.460023691219277e-05,
      "loss": 0.0919,
      "step": 260
    },
    {
      "epoch": 0.24346257889990983,
      "grad_norm": 0.6118870377540588,
      "learning_rate": 9.386679481338033e-05,
      "loss": 0.094,
      "step": 270
    },
    {
      "epoch": 0.25247971145175835,
      "grad_norm": 0.47032231092453003,
      "learning_rate": 9.308988781272694e-05,
      "loss": 0.0918,
      "step": 280
    },
    {
      "epoch": 0.26149684400360684,
      "grad_norm": 0.5307496786117554,
      "learning_rate": 9.227028569946996e-05,
      "loss": 0.095,
      "step": 290
    },
    {
      "epoch": 0.27051397655545534,
      "grad_norm": 0.37769177556037903,
      "learning_rate": 9.140880056680088e-05,
      "loss": 0.0892,
      "step": 300
    },
    {
      "epoch": 0.2795311091073039,
      "grad_norm": 0.5687931776046753,
      "learning_rate": 9.050628600721234e-05,
      "loss": 0.0853,
      "step": 310
    },
    {
      "epoch": 0.2885482416591524,
      "grad_norm": 0.6189451217651367,
      "learning_rate": 8.956363626672595e-05,
      "loss": 0.0838,
      "step": 320
    },
    {
      "epoch": 0.2975653742110009,
      "grad_norm": 0.6863543391227722,
      "learning_rate": 8.858178535883905e-05,
      "loss": 0.0825,
      "step": 330
    },
    {
      "epoch": 0.3065825067628494,
      "grad_norm": 0.8236618041992188,
      "learning_rate": 8.756170613906833e-05,
      "loss": 0.0832,
      "step": 340
    },
    {
      "epoch": 0.3155996393146979,
      "grad_norm": 0.5764484405517578,
      "learning_rate": 8.650440934100728e-05,
      "loss": 0.0775,
      "step": 350
    },
    {
      "epoch": 0.3246167718665464,
      "grad_norm": 0.40208104252815247,
      "learning_rate": 8.541094257485265e-05,
      "loss": 0.0751,
      "step": 360
    },
    {
      "epoch": 0.33363390441839497,
      "grad_norm": 0.6935873031616211,
      "learning_rate": 8.428238928939207e-05,
      "loss": 0.0793,
      "step": 370
    },
    {
      "epoch": 0.34265103697024346,
      "grad_norm": 0.5251246094703674,
      "learning_rate": 8.311986769848141e-05,
      "loss": 0.0713,
      "step": 380
    },
    {
      "epoch": 0.35166816952209196,
      "grad_norm": 0.4371775686740875,
      "learning_rate": 8.192452967307576e-05,
      "loss": 0.0712,
      "step": 390
    },
    {
      "epoch": 0.3606853020739405,
      "grad_norm": 0.6153225302696228,
      "learning_rate": 8.069755959991142e-05,
      "loss": 0.0694,
      "step": 400
    },
    {
      "epoch": 0.369702434625789,
      "grad_norm": 0.4341914653778076,
      "learning_rate": 7.944017320797013e-05,
      "loss": 0.075,
      "step": 410
    },
    {
      "epoch": 0.3787195671776375,
      "grad_norm": 0.4805607199668884,
      "learning_rate": 7.815361636388827e-05,
      "loss": 0.0665,
      "step": 420
    },
    {
      "epoch": 0.38773669972948605,
      "grad_norm": 0.508466362953186,
      "learning_rate": 7.683916383750436e-05,
      "loss": 0.0692,
      "step": 430
    },
    {
      "epoch": 0.39675383228133454,
      "grad_norm": 0.7154425978660583,
      "learning_rate": 7.549811803876825e-05,
      "loss": 0.0693,
      "step": 440
    },
    {
      "epoch": 0.40577096483318303,
      "grad_norm": 0.3025909960269928,
      "learning_rate": 7.413180772726348e-05,
      "loss": 0.0721,
      "step": 450
    },
    {
      "epoch": 0.4147880973850316,
      "grad_norm": 0.5098099708557129,
      "learning_rate": 7.274158669562126e-05,
      "loss": 0.0691,
      "step": 460
    },
    {
      "epoch": 0.4238052299368801,
      "grad_norm": 0.31458744406700134,
      "learning_rate": 7.13288324281309e-05,
      "loss": 0.0668,
      "step": 470
    },
    {
      "epoch": 0.4328223624887286,
      "grad_norm": 0.5931514501571655,
      "learning_rate": 6.989494473587554e-05,
      "loss": 0.0656,
      "step": 480
    },
    {
      "epoch": 0.4418394950405771,
      "grad_norm": 0.3595449924468994,
      "learning_rate": 6.844134436974567e-05,
      "loss": 0.0646,
      "step": 490
    },
    {
      "epoch": 0.4508566275924256,
      "grad_norm": 0.5599433779716492,
      "learning_rate": 6.696947161270476e-05,
      "loss": 0.0687,
      "step": 500
    },
    {
      "epoch": 0.4598737601442741,
      "grad_norm": 0.4869447946548462,
      "learning_rate": 6.548078485270152e-05,
      "loss": 0.0683,
      "step": 510
    },
    {
      "epoch": 0.4688908926961226,
      "grad_norm": 0.36777040362358093,
      "learning_rate": 6.397675913764347e-05,
      "loss": 0.0658,
      "step": 520
    },
    {
      "epoch": 0.47790802524797116,
      "grad_norm": 0.5203920602798462,
      "learning_rate": 6.245888471386263e-05,
      "loss": 0.0627,
      "step": 530
    },
    {
      "epoch": 0.48692515779981965,
      "grad_norm": 0.46625274419784546,
      "learning_rate": 6.0928665549522554e-05,
      "loss": 0.0622,
      "step": 540
    },
    {
      "epoch": 0.49594229035166815,
      "grad_norm": 0.7451359629631042,
      "learning_rate": 5.9387617844429e-05,
      "loss": 0.0618,
      "step": 550
    },
    {
      "epoch": 0.5049594229035167,
      "grad_norm": 0.392704576253891,
      "learning_rate": 5.78372685277209e-05,
      "loss": 0.0589,
      "step": 560
    },
    {
      "epoch": 0.5139765554553652,
      "grad_norm": 0.44599130749702454,
      "learning_rate": 5.627915374493061e-05,
      "loss": 0.0615,
      "step": 570
    },
    {
      "epoch": 0.5229936880072137,
      "grad_norm": 0.3163304328918457,
      "learning_rate": 5.4714817335911894e-05,
      "loss": 0.0503,
      "step": 580
    },
    {
      "epoch": 0.5320108205590622,
      "grad_norm": 0.6041306257247925,
      "learning_rate": 5.314580930514431e-05,
      "loss": 0.0598,
      "step": 590
    },
    {
      "epoch": 0.5410279531109107,
      "grad_norm": 0.38383838534355164,
      "learning_rate": 5.157368428592933e-05,
      "loss": 0.0589,
      "step": 600
    },
    {
      "epoch": 0.5500450856627592,
      "grad_norm": 0.2501381039619446,
      "learning_rate": 5e-05,
      "loss": 0.049,
      "step": 610
    },
    {
      "epoch": 0.5590622182146078,
      "grad_norm": 0.3422386348247528,
      "learning_rate": 4.8426315714070684e-05,
      "loss": 0.0538,
      "step": 620
    },
    {
      "epoch": 0.5680793507664562,
      "grad_norm": 0.5101218223571777,
      "learning_rate": 4.6854190694855694e-05,
      "loss": 0.0497,
      "step": 630
    },
    {
      "epoch": 0.5770964833183048,
      "grad_norm": 0.37502148747444153,
      "learning_rate": 4.528518266408811e-05,
      "loss": 0.052,
      "step": 640
    },
    {
      "epoch": 0.5861136158701533,
      "grad_norm": 0.3856571912765503,
      "learning_rate": 4.3720846255069406e-05,
      "loss": 0.0568,
      "step": 650
    },
    {
      "epoch": 0.5951307484220018,
      "grad_norm": 0.3386954069137573,
      "learning_rate": 4.21627314722791e-05,
      "loss": 0.0493,
      "step": 660
    },
    {
      "epoch": 0.6041478809738503,
      "grad_norm": 0.28927159309387207,
      "learning_rate": 4.0612382155571026e-05,
      "loss": 0.0574,
      "step": 670
    },
    {
      "epoch": 0.6131650135256989,
      "grad_norm": 0.3935062289237976,
      "learning_rate": 3.907133445047747e-05,
      "loss": 0.0434,
      "step": 680
    },
    {
      "epoch": 0.6221821460775473,
      "grad_norm": 0.39534249901771545,
      "learning_rate": 3.75411152861374e-05,
      "loss": 0.0487,
      "step": 690
    },
    {
      "epoch": 0.6311992786293958,
      "grad_norm": 0.35437795519828796,
      "learning_rate": 3.602324086235655e-05,
      "loss": 0.0512,
      "step": 700
    },
    {
      "epoch": 0.6402164111812444,
      "grad_norm": 0.2841149866580963,
      "learning_rate": 3.451921514729848e-05,
      "loss": 0.0391,
      "step": 710
    },
    {
      "epoch": 0.6492335437330928,
      "grad_norm": 0.3514391779899597,
      "learning_rate": 3.303052838729525e-05,
      "loss": 0.0484,
      "step": 720
    },
    {
      "epoch": 0.6582506762849414,
      "grad_norm": 0.29207444190979004,
      "learning_rate": 3.155865563025433e-05,
      "loss": 0.0443,
      "step": 730
    },
    {
      "epoch": 0.6672678088367899,
      "grad_norm": 0.27113544940948486,
      "learning_rate": 3.010505526412447e-05,
      "loss": 0.0446,
      "step": 740
    },
    {
      "epoch": 0.6762849413886384,
      "grad_norm": 0.4424648880958557,
      "learning_rate": 2.867116757186911e-05,
      "loss": 0.0431,
      "step": 750
    },
    {
      "epoch": 0.6853020739404869,
      "grad_norm": 0.4714156687259674,
      "learning_rate": 2.7258413304378734e-05,
      "loss": 0.0468,
      "step": 760
    },
    {
      "epoch": 0.6943192064923355,
      "grad_norm": 0.3349123001098633,
      "learning_rate": 2.5868192272736514e-05,
      "loss": 0.0433,
      "step": 770
    },
    {
      "epoch": 0.7033363390441839,
      "grad_norm": 0.5246461629867554,
      "learning_rate": 2.450188196123177e-05,
      "loss": 0.041,
      "step": 780
    },
    {
      "epoch": 0.7123534715960325,
      "grad_norm": 0.37693607807159424,
      "learning_rate": 2.3160836162495653e-05,
      "loss": 0.0512,
      "step": 790
    },
    {
      "epoch": 0.721370604147881,
      "grad_norm": 0.33574390411376953,
      "learning_rate": 2.1846383636111743e-05,
      "loss": 0.0452,
      "step": 800
    },
    {
      "epoch": 0.7303877366997295,
      "grad_norm": 0.22386135160923004,
      "learning_rate": 2.0559826792029884e-05,
      "loss": 0.0424,
      "step": 810
    },
    {
      "epoch": 0.739404869251578,
      "grad_norm": 0.40371736884117126,
      "learning_rate": 1.9302440400088606e-05,
      "loss": 0.0357,
      "step": 820
    },
    {
      "epoch": 0.7484220018034266,
      "grad_norm": 0.4526534676551819,
      "learning_rate": 1.8075470326924243e-05,
      "loss": 0.0432,
      "step": 830
    },
    {
      "epoch": 0.757439134355275,
      "grad_norm": 0.2903415858745575,
      "learning_rate": 1.6880132301518598e-05,
      "loss": 0.0375,
      "step": 840
    },
    {
      "epoch": 0.7664562669071235,
      "grad_norm": 0.30989566445350647,
      "learning_rate": 1.5717610710607948e-05,
      "loss": 0.0377,
      "step": 850
    },
    {
      "epoch": 0.7754733994589721,
      "grad_norm": 0.3357095420360565,
      "learning_rate": 1.458905742514734e-05,
      "loss": 0.0376,
      "step": 860
    },
    {
      "epoch": 0.7844905320108205,
      "grad_norm": 0.47947272658348083,
      "learning_rate": 1.3495590658992718e-05,
      "loss": 0.037,
      "step": 870
    },
    {
      "epoch": 0.7935076645626691,
      "grad_norm": 0.3474498391151428,
      "learning_rate": 1.2438293860931677e-05,
      "loss": 0.0397,
      "step": 880
    },
    {
      "epoch": 0.8025247971145176,
      "grad_norm": 0.4065302610397339,
      "learning_rate": 1.1418214641160958e-05,
      "loss": 0.0378,
      "step": 890
    },
    {
      "epoch": 0.8115419296663661,
      "grad_norm": 0.20412218570709229,
      "learning_rate": 1.0436363733274057e-05,
      "loss": 0.0333,
      "step": 900
    },
    {
      "epoch": 0.8205590622182146,
      "grad_norm": 0.2562933564186096,
      "learning_rate": 9.493713992787672e-06,
      "loss": 0.0396,
      "step": 910
    },
    {
      "epoch": 0.8295761947700632,
      "grad_norm": 0.3250836133956909,
      "learning_rate": 8.591199433199126e-06,
      "loss": 0.0351,
      "step": 920
    },
    {
      "epoch": 0.8385933273219116,
      "grad_norm": 0.31816214323043823,
      "learning_rate": 7.72971430053005e-06,
      "loss": 0.043,
      "step": 930
    },
    {
      "epoch": 0.8476104598737602,
      "grad_norm": 0.28158149123191833,
      "learning_rate": 6.910112187273066e-06,
      "loss": 0.0324,
      "step": 940
    },
    {
      "epoch": 0.8566275924256087,
      "grad_norm": 0.34491991996765137,
      "learning_rate": 6.133205186619695e-06,
      "loss": 0.046,
      "step": 950
    },
    {
      "epoch": 0.8656447249774571,
      "grad_norm": 0.3850158154964447,
      "learning_rate": 5.399763087807236e-06,
      "loss": 0.0339,
      "step": 960
    },
    {
      "epoch": 0.8746618575293057,
      "grad_norm": 0.3283858597278595,
      "learning_rate": 4.710512613382151e-06,
      "loss": 0.0388,
      "step": 970
    },
    {
      "epoch": 0.8836789900811542,
      "grad_norm": 0.4049375653266907,
      "learning_rate": 4.0661366991354365e-06,
      "loss": 0.0346,
      "step": 980
    },
    {
      "epoch": 0.8926961226330027,
      "grad_norm": 0.43446460366249084,
      "learning_rate": 3.4672738174236884e-06,
      "loss": 0.0346,
      "step": 990
    },
    {
      "epoch": 0.9017132551848512,
      "grad_norm": 0.2909717857837677,
      "learning_rate": 2.914517344546258e-06,
      "loss": 0.0372,
      "step": 1000
    },
    {
      "epoch": 0.9107303877366997,
      "grad_norm": 0.42221134901046753,
      "learning_rate": 2.4084149728051952e-06,
      "loss": 0.0317,
      "step": 1010
    },
    {
      "epoch": 0.9197475202885482,
      "grad_norm": 0.3318589925765991,
      "learning_rate": 1.9494681678307703e-06,
      "loss": 0.0343,
      "step": 1020
    },
    {
      "epoch": 0.9287646528403968,
      "grad_norm": 0.3418586552143097,
      "learning_rate": 1.538131671710108e-06,
      "loss": 0.0364,
      "step": 1030
    },
    {
      "epoch": 0.9377817853922452,
      "grad_norm": 0.2581607699394226,
      "learning_rate": 1.1748130524112666e-06,
      "loss": 0.0347,
      "step": 1040
    },
    {
      "epoch": 0.9467989179440938,
      "grad_norm": 0.37032172083854675,
      "learning_rate": 8.59872299949288e-07,
      "loss": 0.0402,
      "step": 1050
    },
    {
      "epoch": 0.9558160504959423,
      "grad_norm": 0.2215413898229599,
      "learning_rate": 5.936214696942887e-07,
      "loss": 0.0357,
      "step": 1060
    },
    {
      "epoch": 0.9648331830477908,
      "grad_norm": 0.30502429604530334,
      "learning_rate": 3.7632437317505207e-07,
      "loss": 0.0332,
      "step": 1070
    },
    {
      "epoch": 0.9738503155996393,
      "grad_norm": 0.24881534278392792,
      "learning_rate": 2.0819631668442253e-07,
      "loss": 0.033,
      "step": 1080
    },
    {
      "epoch": 0.9828674481514879,
      "grad_norm": 0.7615265846252441,
      "learning_rate": 8.940388794559939e-08,
      "loss": 0.0378,
      "step": 1090
    },
    {
      "epoch": 0.9918845807033363,
      "grad_norm": 0.4428829848766327,
      "learning_rate": 2.0064791050633526e-08,
      "loss": 0.0334,
      "step": 1100
    },
    {
      "epoch": 1.0,
      "step": 1109,
      "total_flos": 2.052344509146071e+17,
      "train_loss": 0.08958469805575578,
      "train_runtime": 1690.0157,
      "train_samples_per_second": 5.249,
      "train_steps_per_second": 0.656
    }
  ],
  "logging_steps": 10,
  "max_steps": 1109,
  "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": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.052344509146071e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}