{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.28651874218272183,
  "eval_steps": 500,
  "global_step": 26000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016529927433618567,
      "grad_norm": 2.137389659881592,
      "learning_rate": 0.0001599141895763845,
      "loss": 6.3906,
      "num_input_tokens_seen": 872064,
      "step": 150
    },
    {
      "epoch": 0.0033059854867237134,
      "grad_norm": 1.725138783454895,
      "learning_rate": 0.000159826028182259,
      "loss": 5.6466,
      "num_input_tokens_seen": 1744032,
      "step": 300
    },
    {
      "epoch": 0.00495897823008557,
      "grad_norm": 1.9830477237701416,
      "learning_rate": 0.00015973786678813348,
      "loss": 5.4449,
      "num_input_tokens_seen": 2615552,
      "step": 450
    },
    {
      "epoch": 0.006611970973447427,
      "grad_norm": 1.8168050050735474,
      "learning_rate": 0.00015964970539400798,
      "loss": 5.3521,
      "num_input_tokens_seen": 3469792,
      "step": 600
    },
    {
      "epoch": 0.008264963716809284,
      "grad_norm": 1.9247260093688965,
      "learning_rate": 0.00015956154399988245,
      "loss": 5.2863,
      "num_input_tokens_seen": 4342304,
      "step": 750
    },
    {
      "epoch": 0.00991795646017114,
      "grad_norm": 1.9191653728485107,
      "learning_rate": 0.00015947338260575695,
      "loss": 5.2405,
      "num_input_tokens_seen": 5211616,
      "step": 900
    },
    {
      "epoch": 0.011570949203532997,
      "grad_norm": 1.748758316040039,
      "learning_rate": 0.00015938522121163143,
      "loss": 5.1998,
      "num_input_tokens_seen": 6098432,
      "step": 1050
    },
    {
      "epoch": 0.013223941946894854,
      "grad_norm": 2.057206869125366,
      "learning_rate": 0.00015929705981750593,
      "loss": 5.1706,
      "num_input_tokens_seen": 6967904,
      "step": 1200
    },
    {
      "epoch": 0.014876934690256709,
      "grad_norm": 2.0983762741088867,
      "learning_rate": 0.0001592088984233804,
      "loss": 5.1521,
      "num_input_tokens_seen": 7851072,
      "step": 1350
    },
    {
      "epoch": 0.016529927433618568,
      "grad_norm": 1.9689010381698608,
      "learning_rate": 0.0001591207370292549,
      "loss": 5.1314,
      "num_input_tokens_seen": 8719744,
      "step": 1500
    },
    {
      "epoch": 0.01818292017698042,
      "grad_norm": 1.7962827682495117,
      "learning_rate": 0.00015903257563512938,
      "loss": 5.0878,
      "num_input_tokens_seen": 9566912,
      "step": 1650
    },
    {
      "epoch": 0.01983591292034228,
      "grad_norm": 1.8615788221359253,
      "learning_rate": 0.00015894441424100389,
      "loss": 5.0739,
      "num_input_tokens_seen": 10450048,
      "step": 1800
    },
    {
      "epoch": 0.021488905663704136,
      "grad_norm": 1.8449132442474365,
      "learning_rate": 0.00015885625284687836,
      "loss": 5.0658,
      "num_input_tokens_seen": 11348640,
      "step": 1950
    },
    {
      "epoch": 0.023141898407065993,
      "grad_norm": 1.8516219854354858,
      "learning_rate": 0.00015876809145275284,
      "loss": 5.0462,
      "num_input_tokens_seen": 12226144,
      "step": 2100
    },
    {
      "epoch": 0.02479489115042785,
      "grad_norm": 1.9487632513046265,
      "learning_rate": 0.00015867993005862734,
      "loss": 5.0265,
      "num_input_tokens_seen": 13119040,
      "step": 2250
    },
    {
      "epoch": 0.026447883893789707,
      "grad_norm": 1.8343034982681274,
      "learning_rate": 0.0001585917686645018,
      "loss": 5.0056,
      "num_input_tokens_seen": 13993280,
      "step": 2400
    },
    {
      "epoch": 0.028100876637151564,
      "grad_norm": 2.002856731414795,
      "learning_rate": 0.00015850360727037632,
      "loss": 4.9993,
      "num_input_tokens_seen": 14876768,
      "step": 2550
    },
    {
      "epoch": 0.029753869380513418,
      "grad_norm": 1.981166124343872,
      "learning_rate": 0.0001584154458762508,
      "loss": 4.9943,
      "num_input_tokens_seen": 15749088,
      "step": 2700
    },
    {
      "epoch": 0.03140686212387528,
      "grad_norm": 1.9732400178909302,
      "learning_rate": 0.0001583272844821253,
      "loss": 4.9762,
      "num_input_tokens_seen": 16634176,
      "step": 2850
    },
    {
      "epoch": 0.033059854867237136,
      "grad_norm": 1.8369622230529785,
      "learning_rate": 0.00015823912308799977,
      "loss": 4.9525,
      "num_input_tokens_seen": 17509824,
      "step": 3000
    },
    {
      "epoch": 0.034712847610598986,
      "grad_norm": 1.9628883600234985,
      "learning_rate": 0.00015815096169387427,
      "loss": 4.9481,
      "num_input_tokens_seen": 18398112,
      "step": 3150
    },
    {
      "epoch": 0.03636584035396084,
      "grad_norm": 1.8523181676864624,
      "learning_rate": 0.00015806280029974874,
      "loss": 4.9306,
      "num_input_tokens_seen": 19272928,
      "step": 3300
    },
    {
      "epoch": 0.0380188330973227,
      "grad_norm": 1.9627933502197266,
      "learning_rate": 0.00015797463890562325,
      "loss": 4.9217,
      "num_input_tokens_seen": 20162880,
      "step": 3450
    },
    {
      "epoch": 0.03967182584068456,
      "grad_norm": 1.8966543674468994,
      "learning_rate": 0.00015788647751149772,
      "loss": 4.919,
      "num_input_tokens_seen": 21041888,
      "step": 3600
    },
    {
      "epoch": 0.041324818584046415,
      "grad_norm": 1.9131779670715332,
      "learning_rate": 0.00015779831611737222,
      "loss": 4.9118,
      "num_input_tokens_seen": 21914272,
      "step": 3750
    },
    {
      "epoch": 0.04297781132740827,
      "grad_norm": 1.8262194395065308,
      "learning_rate": 0.0001577101547232467,
      "loss": 4.9139,
      "num_input_tokens_seen": 22802432,
      "step": 3900
    },
    {
      "epoch": 0.04463080407077013,
      "grad_norm": 1.9549835920333862,
      "learning_rate": 0.0001576219933291212,
      "loss": 4.8919,
      "num_input_tokens_seen": 23680544,
      "step": 4050
    },
    {
      "epoch": 0.046283796814131986,
      "grad_norm": 1.9537177085876465,
      "learning_rate": 0.00015753383193499568,
      "loss": 4.8895,
      "num_input_tokens_seen": 24572928,
      "step": 4200
    },
    {
      "epoch": 0.04793678955749384,
      "grad_norm": 1.9916348457336426,
      "learning_rate": 0.00015744567054087018,
      "loss": 4.8798,
      "num_input_tokens_seen": 25458752,
      "step": 4350
    },
    {
      "epoch": 0.0495897823008557,
      "grad_norm": 1.9964395761489868,
      "learning_rate": 0.00015735750914674465,
      "loss": 4.8734,
      "num_input_tokens_seen": 26339424,
      "step": 4500
    },
    {
      "epoch": 0.05124277504421756,
      "grad_norm": 1.9595707654953003,
      "learning_rate": 0.00015726934775261916,
      "loss": 4.8654,
      "num_input_tokens_seen": 27208928,
      "step": 4650
    },
    {
      "epoch": 0.052895767787579415,
      "grad_norm": 2.002746820449829,
      "learning_rate": 0.00015718118635849363,
      "loss": 4.8536,
      "num_input_tokens_seen": 28083488,
      "step": 4800
    },
    {
      "epoch": 0.05454876053094127,
      "grad_norm": 2.014301300048828,
      "learning_rate": 0.00015709302496436813,
      "loss": 4.8513,
      "num_input_tokens_seen": 28948832,
      "step": 4950
    },
    {
      "epoch": 0.05620175327430313,
      "grad_norm": 1.82748544216156,
      "learning_rate": 0.0001570048635702426,
      "loss": 4.8477,
      "num_input_tokens_seen": 29830752,
      "step": 5100
    },
    {
      "epoch": 0.05785474601766498,
      "grad_norm": 1.907245397567749,
      "learning_rate": 0.0001569167021761171,
      "loss": 4.8445,
      "num_input_tokens_seen": 30709248,
      "step": 5250
    },
    {
      "epoch": 0.059507738761026836,
      "grad_norm": 1.9649808406829834,
      "learning_rate": 0.00015682854078199158,
      "loss": 4.8313,
      "num_input_tokens_seen": 31597856,
      "step": 5400
    },
    {
      "epoch": 0.06116073150438869,
      "grad_norm": 1.9375178813934326,
      "learning_rate": 0.00015674037938786606,
      "loss": 4.8206,
      "num_input_tokens_seen": 32485120,
      "step": 5550
    },
    {
      "epoch": 0.06281372424775056,
      "grad_norm": 1.8886380195617676,
      "learning_rate": 0.00015665221799374056,
      "loss": 4.8152,
      "num_input_tokens_seen": 33354688,
      "step": 5700
    },
    {
      "epoch": 0.06446671699111241,
      "grad_norm": 1.8993780612945557,
      "learning_rate": 0.00015656405659961504,
      "loss": 4.8155,
      "num_input_tokens_seen": 34230592,
      "step": 5850
    },
    {
      "epoch": 0.06611970973447427,
      "grad_norm": 1.8930308818817139,
      "learning_rate": 0.00015647589520548954,
      "loss": 4.8173,
      "num_input_tokens_seen": 35090336,
      "step": 6000
    },
    {
      "epoch": 0.06777270247783612,
      "grad_norm": 1.951819658279419,
      "learning_rate": 0.00015638773381136401,
      "loss": 4.8118,
      "num_input_tokens_seen": 35973024,
      "step": 6150
    },
    {
      "epoch": 0.06942569522119797,
      "grad_norm": 1.9142402410507202,
      "learning_rate": 0.00015629957241723852,
      "loss": 4.8079,
      "num_input_tokens_seen": 36855936,
      "step": 6300
    },
    {
      "epoch": 0.07107868796455984,
      "grad_norm": 1.9393310546875,
      "learning_rate": 0.000156211411023113,
      "loss": 4.7883,
      "num_input_tokens_seen": 37722848,
      "step": 6450
    },
    {
      "epoch": 0.07273168070792169,
      "grad_norm": 1.8511933088302612,
      "learning_rate": 0.00015612383737161498,
      "loss": 4.8043,
      "num_input_tokens_seen": 38597600,
      "step": 6600
    },
    {
      "epoch": 0.07438467345128355,
      "grad_norm": 1.8763892650604248,
      "learning_rate": 0.00015603567597748946,
      "loss": 4.7932,
      "num_input_tokens_seen": 39493152,
      "step": 6750
    },
    {
      "epoch": 0.0760376661946454,
      "grad_norm": 1.9806557893753052,
      "learning_rate": 0.00015594751458336396,
      "loss": 4.7813,
      "num_input_tokens_seen": 40352640,
      "step": 6900
    },
    {
      "epoch": 0.07769065893800726,
      "grad_norm": 2.001722574234009,
      "learning_rate": 0.00015585935318923843,
      "loss": 4.7941,
      "num_input_tokens_seen": 41236160,
      "step": 7050
    },
    {
      "epoch": 0.07934365168136912,
      "grad_norm": 2.1065292358398438,
      "learning_rate": 0.00015577119179511294,
      "loss": 4.7819,
      "num_input_tokens_seen": 42111296,
      "step": 7200
    },
    {
      "epoch": 0.08099664442473098,
      "grad_norm": 1.8941328525543213,
      "learning_rate": 0.0001556830304009874,
      "loss": 4.7737,
      "num_input_tokens_seen": 42992864,
      "step": 7350
    },
    {
      "epoch": 0.08264963716809283,
      "grad_norm": 1.8765467405319214,
      "learning_rate": 0.00015559486900686191,
      "loss": 4.764,
      "num_input_tokens_seen": 43871808,
      "step": 7500
    },
    {
      "epoch": 0.0843026299114547,
      "grad_norm": 1.9826706647872925,
      "learning_rate": 0.0001555067076127364,
      "loss": 4.7805,
      "num_input_tokens_seen": 44742496,
      "step": 7650
    },
    {
      "epoch": 0.08595562265481654,
      "grad_norm": 1.9296499490737915,
      "learning_rate": 0.0001554185462186109,
      "loss": 4.7585,
      "num_input_tokens_seen": 45594112,
      "step": 7800
    },
    {
      "epoch": 0.08760861539817841,
      "grad_norm": 1.9379116296768188,
      "learning_rate": 0.00015533038482448537,
      "loss": 4.7682,
      "num_input_tokens_seen": 46465952,
      "step": 7950
    },
    {
      "epoch": 0.08926160814154026,
      "grad_norm": 1.8769218921661377,
      "learning_rate": 0.00015524222343035987,
      "loss": 4.7574,
      "num_input_tokens_seen": 47325664,
      "step": 8100
    },
    {
      "epoch": 0.09091460088490212,
      "grad_norm": 1.8942108154296875,
      "learning_rate": 0.00015515406203623434,
      "loss": 4.7493,
      "num_input_tokens_seen": 48202944,
      "step": 8250
    },
    {
      "epoch": 0.09256759362826397,
      "grad_norm": 1.84010648727417,
      "learning_rate": 0.00015506590064210885,
      "loss": 4.7515,
      "num_input_tokens_seen": 49074048,
      "step": 8400
    },
    {
      "epoch": 0.09422058637162582,
      "grad_norm": 1.8978796005249023,
      "learning_rate": 0.00015497773924798332,
      "loss": 4.7512,
      "num_input_tokens_seen": 49959008,
      "step": 8550
    },
    {
      "epoch": 0.09587357911498769,
      "grad_norm": 1.9536223411560059,
      "learning_rate": 0.0001548895778538578,
      "loss": 4.758,
      "num_input_tokens_seen": 50863648,
      "step": 8700
    },
    {
      "epoch": 0.09752657185834954,
      "grad_norm": 2.0626060962677,
      "learning_rate": 0.0001548014164597323,
      "loss": 4.7434,
      "num_input_tokens_seen": 51730944,
      "step": 8850
    },
    {
      "epoch": 0.0991795646017114,
      "grad_norm": 1.9423109292984009,
      "learning_rate": 0.00015471325506560677,
      "loss": 4.736,
      "num_input_tokens_seen": 52593024,
      "step": 9000
    },
    {
      "epoch": 0.10083255734507325,
      "grad_norm": 1.9180619716644287,
      "learning_rate": 0.00015462509367148127,
      "loss": 4.7187,
      "num_input_tokens_seen": 53470528,
      "step": 9150
    },
    {
      "epoch": 0.10248555008843512,
      "grad_norm": 1.8776642084121704,
      "learning_rate": 0.00015453693227735575,
      "loss": 4.7382,
      "num_input_tokens_seen": 54362720,
      "step": 9300
    },
    {
      "epoch": 0.10413854283179697,
      "grad_norm": 1.9289714097976685,
      "learning_rate": 0.00015444877088323025,
      "loss": 4.7181,
      "num_input_tokens_seen": 55238304,
      "step": 9450
    },
    {
      "epoch": 0.10579153557515883,
      "grad_norm": 1.9489550590515137,
      "learning_rate": 0.00015436060948910473,
      "loss": 4.7287,
      "num_input_tokens_seen": 56107040,
      "step": 9600
    },
    {
      "epoch": 0.10744452831852068,
      "grad_norm": 2.01839280128479,
      "learning_rate": 0.00015427244809497923,
      "loss": 4.7097,
      "num_input_tokens_seen": 56995456,
      "step": 9750
    },
    {
      "epoch": 0.10909752106188254,
      "grad_norm": 1.9155646562576294,
      "learning_rate": 0.0001541842867008537,
      "loss": 4.7153,
      "num_input_tokens_seen": 57852640,
      "step": 9900
    },
    {
      "epoch": 0.1107505138052444,
      "grad_norm": 2.008150100708008,
      "learning_rate": 0.0001540961253067282,
      "loss": 4.7139,
      "num_input_tokens_seen": 58719840,
      "step": 10050
    },
    {
      "epoch": 0.11240350654860626,
      "grad_norm": 1.9440505504608154,
      "learning_rate": 0.00015400796391260268,
      "loss": 4.7184,
      "num_input_tokens_seen": 59594784,
      "step": 10200
    },
    {
      "epoch": 0.11405649929196811,
      "grad_norm": 1.9298348426818848,
      "learning_rate": 0.00015391980251847718,
      "loss": 4.708,
      "num_input_tokens_seen": 60451712,
      "step": 10350
    },
    {
      "epoch": 0.11570949203532996,
      "grad_norm": 1.9444379806518555,
      "learning_rate": 0.00015383164112435166,
      "loss": 4.6979,
      "num_input_tokens_seen": 61335008,
      "step": 10500
    },
    {
      "epoch": 0.11736248477869182,
      "grad_norm": 2.0216357707977295,
      "learning_rate": 0.00015374406747285365,
      "loss": 4.7055,
      "num_input_tokens_seen": 62197344,
      "step": 10650
    },
    {
      "epoch": 0.11901547752205367,
      "grad_norm": 1.9788328409194946,
      "learning_rate": 0.00015365590607872815,
      "loss": 4.6948,
      "num_input_tokens_seen": 63058464,
      "step": 10800
    },
    {
      "epoch": 0.12066847026541554,
      "grad_norm": 2.0648193359375,
      "learning_rate": 0.00015356774468460263,
      "loss": 4.7058,
      "num_input_tokens_seen": 63942112,
      "step": 10950
    },
    {
      "epoch": 0.12232146300877739,
      "grad_norm": 1.9497121572494507,
      "learning_rate": 0.00015348017103310462,
      "loss": 4.6924,
      "num_input_tokens_seen": 64815232,
      "step": 11100
    },
    {
      "epoch": 0.12397445575213925,
      "grad_norm": 1.9825148582458496,
      "learning_rate": 0.0001533920096389791,
      "loss": 4.7021,
      "num_input_tokens_seen": 65689856,
      "step": 11250
    },
    {
      "epoch": 0.12562744849550112,
      "grad_norm": 1.9766299724578857,
      "learning_rate": 0.0001533038482448536,
      "loss": 4.6921,
      "num_input_tokens_seen": 66570272,
      "step": 11400
    },
    {
      "epoch": 0.12728044123886295,
      "grad_norm": 1.9706653356552124,
      "learning_rate": 0.00015321568685072807,
      "loss": 4.6847,
      "num_input_tokens_seen": 67436096,
      "step": 11550
    },
    {
      "epoch": 0.12893343398222482,
      "grad_norm": 1.9741766452789307,
      "learning_rate": 0.00015312811319923006,
      "loss": 4.6835,
      "num_input_tokens_seen": 68326816,
      "step": 11700
    },
    {
      "epoch": 0.13058642672558668,
      "grad_norm": 1.850825548171997,
      "learning_rate": 0.00015303995180510456,
      "loss": 4.6874,
      "num_input_tokens_seen": 69203328,
      "step": 11850
    },
    {
      "epoch": 0.13223941946894854,
      "grad_norm": 2.0040206909179688,
      "learning_rate": 0.00015295179041097904,
      "loss": 4.6805,
      "num_input_tokens_seen": 70049696,
      "step": 12000
    },
    {
      "epoch": 0.13389241221231038,
      "grad_norm": 1.9326891899108887,
      "learning_rate": 0.00015286362901685354,
      "loss": 4.6781,
      "num_input_tokens_seen": 70929856,
      "step": 12150
    },
    {
      "epoch": 0.13554540495567224,
      "grad_norm": 1.8233270645141602,
      "learning_rate": 0.00015277546762272802,
      "loss": 4.6732,
      "num_input_tokens_seen": 71797184,
      "step": 12300
    },
    {
      "epoch": 0.1371983976990341,
      "grad_norm": 2.026263475418091,
      "learning_rate": 0.00015268730622860252,
      "loss": 4.672,
      "num_input_tokens_seen": 72662528,
      "step": 12450
    },
    {
      "epoch": 0.13885139044239594,
      "grad_norm": 1.8338570594787598,
      "learning_rate": 0.000152599144834477,
      "loss": 4.6718,
      "num_input_tokens_seen": 73543840,
      "step": 12600
    },
    {
      "epoch": 0.1405043831857578,
      "grad_norm": 1.934313416481018,
      "learning_rate": 0.0001525109834403515,
      "loss": 4.6595,
      "num_input_tokens_seen": 74426752,
      "step": 12750
    },
    {
      "epoch": 0.14215737592911967,
      "grad_norm": 1.861647367477417,
      "learning_rate": 0.00015242282204622597,
      "loss": 4.6692,
      "num_input_tokens_seen": 75309888,
      "step": 12900
    },
    {
      "epoch": 0.14381036867248154,
      "grad_norm": 1.9282541275024414,
      "learning_rate": 0.00015233466065210047,
      "loss": 4.6604,
      "num_input_tokens_seen": 76194976,
      "step": 13050
    },
    {
      "epoch": 0.14546336141584337,
      "grad_norm": 1.975542664527893,
      "learning_rate": 0.00015224649925797495,
      "loss": 4.662,
      "num_input_tokens_seen": 77078048,
      "step": 13200
    },
    {
      "epoch": 0.14711635415920524,
      "grad_norm": 1.8979029655456543,
      "learning_rate": 0.00015215833786384945,
      "loss": 4.6554,
      "num_input_tokens_seen": 77940000,
      "step": 13350
    },
    {
      "epoch": 0.1487693469025671,
      "grad_norm": 1.875108242034912,
      "learning_rate": 0.00015207017646972392,
      "loss": 4.6599,
      "num_input_tokens_seen": 78822336,
      "step": 13500
    },
    {
      "epoch": 0.15042233964592897,
      "grad_norm": 1.9476161003112793,
      "learning_rate": 0.0001519820150755984,
      "loss": 4.6688,
      "num_input_tokens_seen": 79708256,
      "step": 13650
    },
    {
      "epoch": 0.1520753323892908,
      "grad_norm": 1.9902242422103882,
      "learning_rate": 0.0001518938536814729,
      "loss": 4.6626,
      "num_input_tokens_seen": 80595168,
      "step": 13800
    },
    {
      "epoch": 0.15372832513265267,
      "grad_norm": 1.7958108186721802,
      "learning_rate": 0.00015180569228734738,
      "loss": 4.662,
      "num_input_tokens_seen": 81484416,
      "step": 13950
    },
    {
      "epoch": 0.15538131787601453,
      "grad_norm": 1.8727210760116577,
      "learning_rate": 0.00015171753089322188,
      "loss": 4.6579,
      "num_input_tokens_seen": 82355712,
      "step": 14100
    },
    {
      "epoch": 0.1570343106193764,
      "grad_norm": 2.0186071395874023,
      "learning_rate": 0.00015162936949909635,
      "loss": 4.6494,
      "num_input_tokens_seen": 83223136,
      "step": 14250
    },
    {
      "epoch": 0.15868730336273823,
      "grad_norm": 1.8837051391601562,
      "learning_rate": 0.00015154120810497086,
      "loss": 4.6463,
      "num_input_tokens_seen": 84097152,
      "step": 14400
    },
    {
      "epoch": 0.1603402961061001,
      "grad_norm": 1.8699517250061035,
      "learning_rate": 0.00015145304671084533,
      "loss": 4.6489,
      "num_input_tokens_seen": 84976576,
      "step": 14550
    },
    {
      "epoch": 0.16199328884946196,
      "grad_norm": 1.956932783126831,
      "learning_rate": 0.00015136488531671983,
      "loss": 4.649,
      "num_input_tokens_seen": 85868224,
      "step": 14700
    },
    {
      "epoch": 0.1636462815928238,
      "grad_norm": 2.020624876022339,
      "learning_rate": 0.0001512767239225943,
      "loss": 4.6458,
      "num_input_tokens_seen": 86746944,
      "step": 14850
    },
    {
      "epoch": 0.16529927433618566,
      "grad_norm": 1.9445135593414307,
      "learning_rate": 0.0001511885625284688,
      "loss": 4.6387,
      "num_input_tokens_seen": 87626976,
      "step": 15000
    },
    {
      "epoch": 0.16695226707954752,
      "grad_norm": 1.9843000173568726,
      "learning_rate": 0.00015110040113434328,
      "loss": 4.6481,
      "num_input_tokens_seen": 88483616,
      "step": 15150
    },
    {
      "epoch": 0.1686052598229094,
      "grad_norm": 2.0259897708892822,
      "learning_rate": 0.00015101282748284528,
      "loss": 4.6317,
      "num_input_tokens_seen": 89374048,
      "step": 15300
    },
    {
      "epoch": 0.17025825256627122,
      "grad_norm": 1.8472915887832642,
      "learning_rate": 0.00015092466608871975,
      "loss": 4.6468,
      "num_input_tokens_seen": 90265376,
      "step": 15450
    },
    {
      "epoch": 0.1719112453096331,
      "grad_norm": 1.9485039710998535,
      "learning_rate": 0.00015083650469459425,
      "loss": 4.6272,
      "num_input_tokens_seen": 91161504,
      "step": 15600
    },
    {
      "epoch": 0.17356423805299495,
      "grad_norm": 2.0340664386749268,
      "learning_rate": 0.00015074834330046873,
      "loss": 4.6252,
      "num_input_tokens_seen": 92033536,
      "step": 15750
    },
    {
      "epoch": 0.17521723079635682,
      "grad_norm": 1.8034217357635498,
      "learning_rate": 0.00015066018190634323,
      "loss": 4.6347,
      "num_input_tokens_seen": 92906464,
      "step": 15900
    },
    {
      "epoch": 0.17687022353971865,
      "grad_norm": 1.9323750734329224,
      "learning_rate": 0.0001505720205122177,
      "loss": 4.624,
      "num_input_tokens_seen": 93773664,
      "step": 16050
    },
    {
      "epoch": 0.17852321628308052,
      "grad_norm": 1.9791151285171509,
      "learning_rate": 0.00015048385911809218,
      "loss": 4.6184,
      "num_input_tokens_seen": 94646528,
      "step": 16200
    },
    {
      "epoch": 0.18017620902644238,
      "grad_norm": 2.0325284004211426,
      "learning_rate": 0.00015039569772396668,
      "loss": 4.6129,
      "num_input_tokens_seen": 95522304,
      "step": 16350
    },
    {
      "epoch": 0.18182920176980424,
      "grad_norm": 1.773972511291504,
      "learning_rate": 0.00015030753632984116,
      "loss": 4.6283,
      "num_input_tokens_seen": 96397632,
      "step": 16500
    },
    {
      "epoch": 0.18348219451316608,
      "grad_norm": 1.792601466178894,
      "learning_rate": 0.00015021937493571566,
      "loss": 4.6201,
      "num_input_tokens_seen": 97283072,
      "step": 16650
    },
    {
      "epoch": 0.18513518725652794,
      "grad_norm": 1.9488441944122314,
      "learning_rate": 0.00015013121354159013,
      "loss": 4.6174,
      "num_input_tokens_seen": 98164960,
      "step": 16800
    },
    {
      "epoch": 0.1867881799998898,
      "grad_norm": 1.8708151578903198,
      "learning_rate": 0.00015004305214746464,
      "loss": 4.6156,
      "num_input_tokens_seen": 99030464,
      "step": 16950
    },
    {
      "epoch": 0.18844117274325164,
      "grad_norm": 1.9848783016204834,
      "learning_rate": 0.0001499548907533391,
      "loss": 4.6069,
      "num_input_tokens_seen": 99913184,
      "step": 17100
    },
    {
      "epoch": 0.1900941654866135,
      "grad_norm": 1.9591269493103027,
      "learning_rate": 0.00014986672935921361,
      "loss": 4.6195,
      "num_input_tokens_seen": 100797056,
      "step": 17250
    },
    {
      "epoch": 0.19174715822997537,
      "grad_norm": 1.9400300979614258,
      "learning_rate": 0.0001497785679650881,
      "loss": 4.6167,
      "num_input_tokens_seen": 101678336,
      "step": 17400
    },
    {
      "epoch": 0.19340015097333724,
      "grad_norm": 1.9163286685943604,
      "learning_rate": 0.0001496904065709626,
      "loss": 4.6135,
      "num_input_tokens_seen": 102532640,
      "step": 17550
    },
    {
      "epoch": 0.19505314371669907,
      "grad_norm": 1.86648690700531,
      "learning_rate": 0.00014960224517683707,
      "loss": 4.6063,
      "num_input_tokens_seen": 103403264,
      "step": 17700
    },
    {
      "epoch": 0.19670613646006094,
      "grad_norm": 1.9310001134872437,
      "learning_rate": 0.00014951408378271157,
      "loss": 4.6143,
      "num_input_tokens_seen": 104304224,
      "step": 17850
    },
    {
      "epoch": 0.1983591292034228,
      "grad_norm": 1.9832515716552734,
      "learning_rate": 0.00014942592238858604,
      "loss": 4.6138,
      "num_input_tokens_seen": 105184128,
      "step": 18000
    },
    {
      "epoch": 0.20001212194678467,
      "grad_norm": 1.9453548192977905,
      "learning_rate": 0.00014933776099446055,
      "loss": 4.6143,
      "num_input_tokens_seen": 106070880,
      "step": 18150
    },
    {
      "epoch": 0.2016651146901465,
      "grad_norm": 1.8135297298431396,
      "learning_rate": 0.00014924959960033502,
      "loss": 4.6197,
      "num_input_tokens_seen": 106944960,
      "step": 18300
    },
    {
      "epoch": 0.20331810743350837,
      "grad_norm": 1.892717719078064,
      "learning_rate": 0.00014916143820620952,
      "loss": 4.6039,
      "num_input_tokens_seen": 107808512,
      "step": 18450
    },
    {
      "epoch": 0.20497110017687023,
      "grad_norm": 1.9304077625274658,
      "learning_rate": 0.000149073276812084,
      "loss": 4.6103,
      "num_input_tokens_seen": 108679584,
      "step": 18600
    },
    {
      "epoch": 0.20662409292023207,
      "grad_norm": 1.874104380607605,
      "learning_rate": 0.0001489851154179585,
      "loss": 4.6092,
      "num_input_tokens_seen": 109561440,
      "step": 18750
    },
    {
      "epoch": 0.20827708566359393,
      "grad_norm": 1.9672309160232544,
      "learning_rate": 0.00014889695402383297,
      "loss": 4.6027,
      "num_input_tokens_seen": 110445760,
      "step": 18900
    },
    {
      "epoch": 0.2099300784069558,
      "grad_norm": 1.9013960361480713,
      "learning_rate": 0.00014880879262970748,
      "loss": 4.6161,
      "num_input_tokens_seen": 111310304,
      "step": 19050
    },
    {
      "epoch": 0.21158307115031766,
      "grad_norm": 1.902948021888733,
      "learning_rate": 0.00014872063123558195,
      "loss": 4.6118,
      "num_input_tokens_seen": 112181440,
      "step": 19200
    },
    {
      "epoch": 0.2132360638936795,
      "grad_norm": 1.9160059690475464,
      "learning_rate": 0.00014863246984145645,
      "loss": 4.5929,
      "num_input_tokens_seen": 113074496,
      "step": 19350
    },
    {
      "epoch": 0.21488905663704136,
      "grad_norm": 1.843983769416809,
      "learning_rate": 0.00014854489618995845,
      "loss": 4.5982,
      "num_input_tokens_seen": 113972512,
      "step": 19500
    },
    {
      "epoch": 0.21654204938040322,
      "grad_norm": 1.83791184425354,
      "learning_rate": 0.00014845673479583292,
      "loss": 4.6046,
      "num_input_tokens_seen": 114839680,
      "step": 19650
    },
    {
      "epoch": 0.2181950421237651,
      "grad_norm": 1.8458436727523804,
      "learning_rate": 0.00014836857340170742,
      "loss": 4.5987,
      "num_input_tokens_seen": 115716000,
      "step": 19800
    },
    {
      "epoch": 0.21984803486712692,
      "grad_norm": 2.0030035972595215,
      "learning_rate": 0.0001482804120075819,
      "loss": 4.5873,
      "num_input_tokens_seen": 116581408,
      "step": 19950
    },
    {
      "epoch": 0.2215010276104888,
      "grad_norm": 1.8120313882827759,
      "learning_rate": 0.00014819225061345637,
      "loss": 4.5893,
      "num_input_tokens_seen": 117446368,
      "step": 20100
    },
    {
      "epoch": 0.22315402035385065,
      "grad_norm": 1.8799773454666138,
      "learning_rate": 0.00014810408921933087,
      "loss": 4.5746,
      "num_input_tokens_seen": 118320096,
      "step": 20250
    },
    {
      "epoch": 0.22480701309721252,
      "grad_norm": 1.9042309522628784,
      "learning_rate": 0.00014801592782520535,
      "loss": 4.5851,
      "num_input_tokens_seen": 119192128,
      "step": 20400
    },
    {
      "epoch": 0.22646000584057435,
      "grad_norm": 1.8850473165512085,
      "learning_rate": 0.00014792776643107985,
      "loss": 4.5883,
      "num_input_tokens_seen": 120065888,
      "step": 20550
    },
    {
      "epoch": 0.22811299858393622,
      "grad_norm": 1.8963854312896729,
      "learning_rate": 0.00014783960503695433,
      "loss": 4.5869,
      "num_input_tokens_seen": 120921504,
      "step": 20700
    },
    {
      "epoch": 0.22976599132729808,
      "grad_norm": 1.8145036697387695,
      "learning_rate": 0.00014775144364282883,
      "loss": 4.5857,
      "num_input_tokens_seen": 121819936,
      "step": 20850
    },
    {
      "epoch": 0.23141898407065992,
      "grad_norm": 1.8780988454818726,
      "learning_rate": 0.0001476632822487033,
      "loss": 4.5793,
      "num_input_tokens_seen": 122700576,
      "step": 21000
    },
    {
      "epoch": 0.23307197681402178,
      "grad_norm": 1.8859424591064453,
      "learning_rate": 0.00014757512085457778,
      "loss": 4.5847,
      "num_input_tokens_seen": 123578848,
      "step": 21150
    },
    {
      "epoch": 0.23472496955738364,
      "grad_norm": 1.8556190729141235,
      "learning_rate": 0.00014748695946045228,
      "loss": 4.5915,
      "num_input_tokens_seen": 124451552,
      "step": 21300
    },
    {
      "epoch": 0.2363779623007455,
      "grad_norm": 1.8445396423339844,
      "learning_rate": 0.00014739879806632676,
      "loss": 4.5857,
      "num_input_tokens_seen": 125326208,
      "step": 21450
    },
    {
      "epoch": 0.23803095504410735,
      "grad_norm": 1.903262972831726,
      "learning_rate": 0.00014731063667220126,
      "loss": 4.5811,
      "num_input_tokens_seen": 126206560,
      "step": 21600
    },
    {
      "epoch": 0.2396839477874692,
      "grad_norm": 1.7595880031585693,
      "learning_rate": 0.00014722247527807573,
      "loss": 4.567,
      "num_input_tokens_seen": 127077440,
      "step": 21750
    },
    {
      "epoch": 0.24133694053083107,
      "grad_norm": 1.8828771114349365,
      "learning_rate": 0.00014713431388395024,
      "loss": 4.5792,
      "num_input_tokens_seen": 127955584,
      "step": 21900
    },
    {
      "epoch": 0.24298993327419294,
      "grad_norm": 1.8850219249725342,
      "learning_rate": 0.0001470461524898247,
      "loss": 4.5749,
      "num_input_tokens_seen": 128807200,
      "step": 22050
    },
    {
      "epoch": 0.24464292601755477,
      "grad_norm": 1.9162580966949463,
      "learning_rate": 0.00014695799109569919,
      "loss": 4.5725,
      "num_input_tokens_seen": 129672192,
      "step": 22200
    },
    {
      "epoch": 0.24629591876091664,
      "grad_norm": 1.866351842880249,
      "learning_rate": 0.0001468698297015737,
      "loss": 4.569,
      "num_input_tokens_seen": 130541696,
      "step": 22350
    },
    {
      "epoch": 0.2479489115042785,
      "grad_norm": 1.849186658859253,
      "learning_rate": 0.00014678166830744816,
      "loss": 4.5832,
      "num_input_tokens_seen": 131420992,
      "step": 22500
    },
    {
      "epoch": 0.24960190424764037,
      "grad_norm": 1.8402087688446045,
      "learning_rate": 0.00014669350691332266,
      "loss": 4.5664,
      "num_input_tokens_seen": 132312352,
      "step": 22650
    },
    {
      "epoch": 0.25125489699100223,
      "grad_norm": 1.8887277841567993,
      "learning_rate": 0.00014660534551919714,
      "loss": 4.5771,
      "num_input_tokens_seen": 133195968,
      "step": 22800
    },
    {
      "epoch": 0.25290788973436407,
      "grad_norm": 2.029491424560547,
      "learning_rate": 0.00014651718412507164,
      "loss": 4.5718,
      "num_input_tokens_seen": 134079040,
      "step": 22950
    },
    {
      "epoch": 0.2545608824777259,
      "grad_norm": 1.9162187576293945,
      "learning_rate": 0.00014642902273094612,
      "loss": 4.5746,
      "num_input_tokens_seen": 134957440,
      "step": 23100
    },
    {
      "epoch": 0.2562138752210878,
      "grad_norm": 1.8331772089004517,
      "learning_rate": 0.00014634086133682062,
      "loss": 4.5736,
      "num_input_tokens_seen": 135835328,
      "step": 23250
    },
    {
      "epoch": 0.25786686796444963,
      "grad_norm": 1.9076178073883057,
      "learning_rate": 0.0001462526999426951,
      "loss": 4.5647,
      "num_input_tokens_seen": 136701184,
      "step": 23400
    },
    {
      "epoch": 0.25951986070781147,
      "grad_norm": 1.9407544136047363,
      "learning_rate": 0.0001461645385485696,
      "loss": 4.5607,
      "num_input_tokens_seen": 137547264,
      "step": 23550
    },
    {
      "epoch": 0.26117285345117336,
      "grad_norm": 1.9287118911743164,
      "learning_rate": 0.0001460769648970716,
      "loss": 4.5642,
      "num_input_tokens_seen": 138417888,
      "step": 23700
    },
    {
      "epoch": 0.2628258461945352,
      "grad_norm": 2.0106074810028076,
      "learning_rate": 0.00014598939124557358,
      "loss": 4.5689,
      "num_input_tokens_seen": 139297088,
      "step": 23850
    },
    {
      "epoch": 0.2644788389378971,
      "grad_norm": 1.8796470165252686,
      "learning_rate": 0.00014590122985144808,
      "loss": 4.5736,
      "num_input_tokens_seen": 140165984,
      "step": 24000
    },
    {
      "epoch": 0.2661318316812589,
      "grad_norm": 1.8495882749557495,
      "learning_rate": 0.00014581306845732256,
      "loss": 4.5613,
      "num_input_tokens_seen": 141043680,
      "step": 24150
    },
    {
      "epoch": 0.26778482442462076,
      "grad_norm": 1.8603812456130981,
      "learning_rate": 0.00014572490706319706,
      "loss": 4.5707,
      "num_input_tokens_seen": 141913088,
      "step": 24300
    },
    {
      "epoch": 0.26943781716798265,
      "grad_norm": 1.8450992107391357,
      "learning_rate": 0.00014563674566907153,
      "loss": 4.5685,
      "num_input_tokens_seen": 142780992,
      "step": 24450
    },
    {
      "epoch": 0.2710908099113445,
      "grad_norm": 1.9459301233291626,
      "learning_rate": 0.000145548584274946,
      "loss": 4.5624,
      "num_input_tokens_seen": 143655008,
      "step": 24600
    },
    {
      "epoch": 0.2727438026547063,
      "grad_norm": 1.87797212600708,
      "learning_rate": 0.0001454604228808205,
      "loss": 4.5753,
      "num_input_tokens_seen": 144533760,
      "step": 24750
    },
    {
      "epoch": 0.2743967953980682,
      "grad_norm": 1.9368420839309692,
      "learning_rate": 0.00014537226148669498,
      "loss": 4.5473,
      "num_input_tokens_seen": 145405376,
      "step": 24900
    },
    {
      "epoch": 0.27604978814143005,
      "grad_norm": 1.9425833225250244,
      "learning_rate": 0.0001452841000925695,
      "loss": 4.5621,
      "num_input_tokens_seen": 146278176,
      "step": 25050
    },
    {
      "epoch": 0.2777027808847919,
      "grad_norm": 1.8315942287445068,
      "learning_rate": 0.00014519593869844396,
      "loss": 4.5441,
      "num_input_tokens_seen": 147150880,
      "step": 25200
    },
    {
      "epoch": 0.2793557736281538,
      "grad_norm": 1.865020990371704,
      "learning_rate": 0.00014510777730431846,
      "loss": 4.5681,
      "num_input_tokens_seen": 148039488,
      "step": 25350
    },
    {
      "epoch": 0.2810087663715156,
      "grad_norm": 1.9058725833892822,
      "learning_rate": 0.00014501961591019294,
      "loss": 4.55,
      "num_input_tokens_seen": 148898720,
      "step": 25500
    },
    {
      "epoch": 0.2826617591148775,
      "grad_norm": 1.9358283281326294,
      "learning_rate": 0.00014493145451606741,
      "loss": 4.5608,
      "num_input_tokens_seen": 149776576,
      "step": 25650
    },
    {
      "epoch": 0.28431475185823935,
      "grad_norm": 1.871090292930603,
      "learning_rate": 0.00014484329312194192,
      "loss": 4.539,
      "num_input_tokens_seen": 150667296,
      "step": 25800
    },
    {
      "epoch": 0.2859677446016012,
      "grad_norm": 1.885185956954956,
      "learning_rate": 0.0001447551317278164,
      "loss": 4.5421,
      "num_input_tokens_seen": 151536512,
      "step": 25950
    }
  ],
  "logging_steps": 150,
  "max_steps": 272232,
  "num_input_tokens_seen": 151830560,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2344361017958400.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}