{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05242879105215299,
  "eval_steps": 3000,
  "global_step": 6000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00043690659210127495,
      "grad_norm": 1.8826903104782104,
      "learning_rate": 2.4500000000000003e-05,
      "loss": 9.762939453125,
      "step": 50
    },
    {
      "epoch": 0.0008738131842025499,
      "grad_norm": 0.9995923042297363,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 8.305597534179688,
      "step": 100
    },
    {
      "epoch": 0.001310719776303825,
      "grad_norm": 0.9061496257781982,
      "learning_rate": 7.45e-05,
      "loss": 7.173495483398438,
      "step": 150
    },
    {
      "epoch": 0.0017476263684050998,
      "grad_norm": 1.6024847030639648,
      "learning_rate": 9.95e-05,
      "loss": 6.624603271484375,
      "step": 200
    },
    {
      "epoch": 0.002184532960506375,
      "grad_norm": 1.2123334407806396,
      "learning_rate": 0.0001245,
      "loss": 6.243399658203125,
      "step": 250
    },
    {
      "epoch": 0.00262143955260765,
      "grad_norm": 1.0432322025299072,
      "learning_rate": 0.0001495,
      "loss": 5.9879296875,
      "step": 300
    },
    {
      "epoch": 0.0030583461447089245,
      "grad_norm": 0.9280146360397339,
      "learning_rate": 0.00017449999999999999,
      "loss": 5.776607666015625,
      "step": 350
    },
    {
      "epoch": 0.0034952527368101996,
      "grad_norm": 1.0289900302886963,
      "learning_rate": 0.00019950000000000002,
      "loss": 5.5920703125,
      "step": 400
    },
    {
      "epoch": 0.003932159328911475,
      "grad_norm": 1.0593407154083252,
      "learning_rate": 0.0002245,
      "loss": 5.437271728515625,
      "step": 450
    },
    {
      "epoch": 0.00436906592101275,
      "grad_norm": 1.0122662782669067,
      "learning_rate": 0.0002495,
      "loss": 5.287777709960937,
      "step": 500
    },
    {
      "epoch": 0.004805972513114025,
      "grad_norm": 0.7662743926048279,
      "learning_rate": 0.0002745,
      "loss": 5.155453491210937,
      "step": 550
    },
    {
      "epoch": 0.0052428791052153,
      "grad_norm": 0.7941539287567139,
      "learning_rate": 0.0002995,
      "loss": 5.030631713867187,
      "step": 600
    },
    {
      "epoch": 0.005679785697316574,
      "grad_norm": 0.6195730566978455,
      "learning_rate": 0.00032450000000000003,
      "loss": 4.909389953613282,
      "step": 650
    },
    {
      "epoch": 0.006116692289417849,
      "grad_norm": 0.6587674617767334,
      "learning_rate": 0.0003495,
      "loss": 4.786273498535156,
      "step": 700
    },
    {
      "epoch": 0.006553598881519124,
      "grad_norm": 0.7233771681785583,
      "learning_rate": 0.0003745,
      "loss": 4.6648342895507815,
      "step": 750
    },
    {
      "epoch": 0.006990505473620399,
      "grad_norm": 0.5489601492881775,
      "learning_rate": 0.0003995,
      "loss": 4.555048522949218,
      "step": 800
    },
    {
      "epoch": 0.007427412065721674,
      "grad_norm": 0.6154086589813232,
      "learning_rate": 0.0004245,
      "loss": 4.461051330566407,
      "step": 850
    },
    {
      "epoch": 0.00786431865782295,
      "grad_norm": 0.41333407163619995,
      "learning_rate": 0.00044950000000000003,
      "loss": 4.374936828613281,
      "step": 900
    },
    {
      "epoch": 0.008301225249924224,
      "grad_norm": 0.5036063194274902,
      "learning_rate": 0.0004745,
      "loss": 4.3033209228515625,
      "step": 950
    },
    {
      "epoch": 0.0087381318420255,
      "grad_norm": 0.3687891364097595,
      "learning_rate": 0.0004995,
      "loss": 4.233715209960938,
      "step": 1000
    },
    {
      "epoch": 0.009175038434126774,
      "grad_norm": 0.5433846116065979,
      "learning_rate": 0.0005245,
      "loss": 4.186253967285157,
      "step": 1050
    },
    {
      "epoch": 0.00961194502622805,
      "grad_norm": 0.439351350069046,
      "learning_rate": 0.0005495,
      "loss": 4.139383850097656,
      "step": 1100
    },
    {
      "epoch": 0.010048851618329325,
      "grad_norm": 0.36215880513191223,
      "learning_rate": 0.0005745,
      "loss": 4.08899658203125,
      "step": 1150
    },
    {
      "epoch": 0.0104857582104306,
      "grad_norm": 0.3970701992511749,
      "learning_rate": 0.0005995000000000001,
      "loss": 4.061238403320313,
      "step": 1200
    },
    {
      "epoch": 0.010922664802531873,
      "grad_norm": 0.3410918712615967,
      "learning_rate": 0.0006245000000000001,
      "loss": 4.026336669921875,
      "step": 1250
    },
    {
      "epoch": 0.011359571394633148,
      "grad_norm": 0.3047930598258972,
      "learning_rate": 0.0006495,
      "loss": 3.9928851318359375,
      "step": 1300
    },
    {
      "epoch": 0.011796477986734423,
      "grad_norm": 0.2819700241088867,
      "learning_rate": 0.0006745,
      "loss": 3.9584146118164063,
      "step": 1350
    },
    {
      "epoch": 0.012233384578835698,
      "grad_norm": 0.29095014929771423,
      "learning_rate": 0.0006995,
      "loss": 3.9291363525390626,
      "step": 1400
    },
    {
      "epoch": 0.012670291170936973,
      "grad_norm": 0.2987957298755646,
      "learning_rate": 0.0007245000000000001,
      "loss": 3.9090225219726564,
      "step": 1450
    },
    {
      "epoch": 0.013107197763038248,
      "grad_norm": 0.28419050574302673,
      "learning_rate": 0.0007495000000000001,
      "loss": 3.890744934082031,
      "step": 1500
    },
    {
      "epoch": 0.013544104355139523,
      "grad_norm": 0.3039053976535797,
      "learning_rate": 0.0007745,
      "loss": 3.861073303222656,
      "step": 1550
    },
    {
      "epoch": 0.013981010947240798,
      "grad_norm": 0.25676754117012024,
      "learning_rate": 0.0007995,
      "loss": 3.8428253173828124,
      "step": 1600
    },
    {
      "epoch": 0.014417917539342073,
      "grad_norm": 0.2573896646499634,
      "learning_rate": 0.0008245,
      "loss": 3.8260653686523436,
      "step": 1650
    },
    {
      "epoch": 0.014854824131443348,
      "grad_norm": 0.272127240896225,
      "learning_rate": 0.0008495000000000001,
      "loss": 3.8006341552734373,
      "step": 1700
    },
    {
      "epoch": 0.015291730723544623,
      "grad_norm": 0.23205944895744324,
      "learning_rate": 0.0008745000000000001,
      "loss": 3.7862649536132813,
      "step": 1750
    },
    {
      "epoch": 0.0157286373156459,
      "grad_norm": 0.22847425937652588,
      "learning_rate": 0.0008995,
      "loss": 3.771934814453125,
      "step": 1800
    },
    {
      "epoch": 0.016165543907747174,
      "grad_norm": 0.2651786208152771,
      "learning_rate": 0.0009245,
      "loss": 3.76009521484375,
      "step": 1850
    },
    {
      "epoch": 0.01660245049984845,
      "grad_norm": 0.24903950095176697,
      "learning_rate": 0.0009495,
      "loss": 3.7454238891601563,
      "step": 1900
    },
    {
      "epoch": 0.017039357091949724,
      "grad_norm": 0.24524764716625214,
      "learning_rate": 0.0009745000000000001,
      "loss": 3.735928955078125,
      "step": 1950
    },
    {
      "epoch": 0.017476263684051,
      "grad_norm": 0.22325558960437775,
      "learning_rate": 0.0009995000000000002,
      "loss": 3.7209417724609377,
      "step": 2000
    },
    {
      "epoch": 0.017913170276152274,
      "grad_norm": 0.23860357701778412,
      "learning_rate": 0.001,
      "loss": 3.7122769165039062,
      "step": 2050
    },
    {
      "epoch": 0.01835007686825355,
      "grad_norm": 0.2162218689918518,
      "learning_rate": 0.001,
      "loss": 3.690401611328125,
      "step": 2100
    },
    {
      "epoch": 0.018786983460354824,
      "grad_norm": 0.2171812504529953,
      "learning_rate": 0.001,
      "loss": 3.6825027465820312,
      "step": 2150
    },
    {
      "epoch": 0.0192238900524561,
      "grad_norm": 0.22677843272686005,
      "learning_rate": 0.001,
      "loss": 3.6679034423828125,
      "step": 2200
    },
    {
      "epoch": 0.019660796644557374,
      "grad_norm": 0.23934350907802582,
      "learning_rate": 0.001,
      "loss": 3.6494000244140623,
      "step": 2250
    },
    {
      "epoch": 0.02009770323665865,
      "grad_norm": 0.20819289982318878,
      "learning_rate": 0.001,
      "loss": 3.640907897949219,
      "step": 2300
    },
    {
      "epoch": 0.020534609828759924,
      "grad_norm": 0.22890810668468475,
      "learning_rate": 0.001,
      "loss": 3.6309326171875,
      "step": 2350
    },
    {
      "epoch": 0.0209715164208612,
      "grad_norm": 0.2085026353597641,
      "learning_rate": 0.001,
      "loss": 3.6261746215820314,
      "step": 2400
    },
    {
      "epoch": 0.021408423012962474,
      "grad_norm": 0.22136099636554718,
      "learning_rate": 0.001,
      "loss": 3.614878845214844,
      "step": 2450
    },
    {
      "epoch": 0.021845329605063746,
      "grad_norm": 0.21210630238056183,
      "learning_rate": 0.001,
      "loss": 3.599817810058594,
      "step": 2500
    },
    {
      "epoch": 0.02228223619716502,
      "grad_norm": 0.24638274312019348,
      "learning_rate": 0.001,
      "loss": 3.591536865234375,
      "step": 2550
    },
    {
      "epoch": 0.022719142789266296,
      "grad_norm": 0.20501184463500977,
      "learning_rate": 0.001,
      "loss": 3.58053955078125,
      "step": 2600
    },
    {
      "epoch": 0.02315604938136757,
      "grad_norm": 0.2101815640926361,
      "learning_rate": 0.001,
      "loss": 3.5824459838867186,
      "step": 2650
    },
    {
      "epoch": 0.023592955973468846,
      "grad_norm": 0.22906431555747986,
      "learning_rate": 0.001,
      "loss": 3.564821472167969,
      "step": 2700
    },
    {
      "epoch": 0.02402986256557012,
      "grad_norm": 0.20708167552947998,
      "learning_rate": 0.001,
      "loss": 3.5566305541992187,
      "step": 2750
    },
    {
      "epoch": 0.024466769157671396,
      "grad_norm": 0.21956811845302582,
      "learning_rate": 0.001,
      "loss": 3.5507748413085936,
      "step": 2800
    },
    {
      "epoch": 0.02490367574977267,
      "grad_norm": 0.24124488234519958,
      "learning_rate": 0.001,
      "loss": 3.5426095581054686,
      "step": 2850
    },
    {
      "epoch": 0.025340582341873946,
      "grad_norm": 0.20921742916107178,
      "learning_rate": 0.001,
      "loss": 3.531602783203125,
      "step": 2900
    },
    {
      "epoch": 0.02577748893397522,
      "grad_norm": 0.19601280987262726,
      "learning_rate": 0.001,
      "loss": 3.5225894165039064,
      "step": 2950
    },
    {
      "epoch": 0.026214395526076496,
      "grad_norm": 0.20243392884731293,
      "learning_rate": 0.001,
      "loss": 3.5183840942382814,
      "step": 3000
    },
    {
      "epoch": 0.026214395526076496,
      "eval_loss": 3.518667221069336,
      "eval_runtime": 5.8945,
      "eval_samples_per_second": 165.579,
      "eval_steps_per_second": 10.349,
      "step": 3000
    },
    {
      "epoch": 0.02665130211817777,
      "grad_norm": 0.1983480155467987,
      "learning_rate": 0.001,
      "loss": 3.5175689697265624,
      "step": 3050
    },
    {
      "epoch": 0.027088208710279046,
      "grad_norm": 0.20962044596672058,
      "learning_rate": 0.001,
      "loss": 3.501134033203125,
      "step": 3100
    },
    {
      "epoch": 0.02752511530238032,
      "grad_norm": 0.20161673426628113,
      "learning_rate": 0.001,
      "loss": 3.508039855957031,
      "step": 3150
    },
    {
      "epoch": 0.027962021894481597,
      "grad_norm": 0.21198803186416626,
      "learning_rate": 0.001,
      "loss": 3.493387451171875,
      "step": 3200
    },
    {
      "epoch": 0.02839892848658287,
      "grad_norm": 0.21940743923187256,
      "learning_rate": 0.001,
      "loss": 3.4941644287109375,
      "step": 3250
    },
    {
      "epoch": 0.028835835078684147,
      "grad_norm": 0.23343515396118164,
      "learning_rate": 0.001,
      "loss": 3.4835015869140626,
      "step": 3300
    },
    {
      "epoch": 0.02927274167078542,
      "grad_norm": 0.19761498272418976,
      "learning_rate": 0.001,
      "loss": 3.482951965332031,
      "step": 3350
    },
    {
      "epoch": 0.029709648262886697,
      "grad_norm": 0.22693106532096863,
      "learning_rate": 0.001,
      "loss": 3.475736389160156,
      "step": 3400
    },
    {
      "epoch": 0.030146554854987972,
      "grad_norm": 0.19969327747821808,
      "learning_rate": 0.001,
      "loss": 3.4689141845703126,
      "step": 3450
    },
    {
      "epoch": 0.030583461447089247,
      "grad_norm": 0.23987655341625214,
      "learning_rate": 0.001,
      "loss": 3.464185791015625,
      "step": 3500
    },
    {
      "epoch": 0.031020368039190522,
      "grad_norm": 0.20894227921962738,
      "learning_rate": 0.001,
      "loss": 3.4571575927734375,
      "step": 3550
    },
    {
      "epoch": 0.0314572746312918,
      "grad_norm": 0.22110916674137115,
      "learning_rate": 0.001,
      "loss": 3.4559121704101563,
      "step": 3600
    },
    {
      "epoch": 0.03189418122339307,
      "grad_norm": 0.21295017004013062,
      "learning_rate": 0.001,
      "loss": 3.451357421875,
      "step": 3650
    },
    {
      "epoch": 0.03233108781549435,
      "grad_norm": 0.19029361009597778,
      "learning_rate": 0.001,
      "loss": 3.4517440795898438,
      "step": 3700
    },
    {
      "epoch": 0.03276799440759562,
      "grad_norm": 0.2307061105966568,
      "learning_rate": 0.001,
      "loss": 3.4454116821289062,
      "step": 3750
    },
    {
      "epoch": 0.0332049009996969,
      "grad_norm": 0.2172439694404602,
      "learning_rate": 0.001,
      "loss": 3.4348458862304687,
      "step": 3800
    },
    {
      "epoch": 0.03364180759179817,
      "grad_norm": 0.19329442083835602,
      "learning_rate": 0.001,
      "loss": 3.437733154296875,
      "step": 3850
    },
    {
      "epoch": 0.03407871418389945,
      "grad_norm": 0.2241591513156891,
      "learning_rate": 0.001,
      "loss": 3.426455383300781,
      "step": 3900
    },
    {
      "epoch": 0.03451562077600072,
      "grad_norm": 0.2319568693637848,
      "learning_rate": 0.001,
      "loss": 3.433238830566406,
      "step": 3950
    },
    {
      "epoch": 0.034952527368102,
      "grad_norm": 0.1924877166748047,
      "learning_rate": 0.001,
      "loss": 3.4249606323242188,
      "step": 4000
    },
    {
      "epoch": 0.03538943396020327,
      "grad_norm": 0.2120707631111145,
      "learning_rate": 0.001,
      "loss": 3.421075439453125,
      "step": 4050
    },
    {
      "epoch": 0.03582634055230455,
      "grad_norm": 0.19918771088123322,
      "learning_rate": 0.001,
      "loss": 3.4203054809570315,
      "step": 4100
    },
    {
      "epoch": 0.03626324714440582,
      "grad_norm": 0.2003307044506073,
      "learning_rate": 0.001,
      "loss": 3.411707763671875,
      "step": 4150
    },
    {
      "epoch": 0.0367001537365071,
      "grad_norm": 0.2270653247833252,
      "learning_rate": 0.001,
      "loss": 3.4078097534179688,
      "step": 4200
    },
    {
      "epoch": 0.03713706032860837,
      "grad_norm": 0.21652576327323914,
      "learning_rate": 0.001,
      "loss": 3.4062127685546875,
      "step": 4250
    },
    {
      "epoch": 0.03757396692070965,
      "grad_norm": 0.23578432202339172,
      "learning_rate": 0.001,
      "loss": 3.400606689453125,
      "step": 4300
    },
    {
      "epoch": 0.03801087351281092,
      "grad_norm": 0.20475627481937408,
      "learning_rate": 0.001,
      "loss": 3.395752258300781,
      "step": 4350
    },
    {
      "epoch": 0.0384477801049122,
      "grad_norm": 0.2542702555656433,
      "learning_rate": 0.001,
      "loss": 3.396254577636719,
      "step": 4400
    },
    {
      "epoch": 0.03888468669701347,
      "grad_norm": 0.18298493325710297,
      "learning_rate": 0.001,
      "loss": 3.393648986816406,
      "step": 4450
    },
    {
      "epoch": 0.03932159328911475,
      "grad_norm": 0.22572273015975952,
      "learning_rate": 0.001,
      "loss": 3.3865216064453123,
      "step": 4500
    },
    {
      "epoch": 0.03975849988121602,
      "grad_norm": 0.19484151899814606,
      "learning_rate": 0.001,
      "loss": 3.3849478149414063,
      "step": 4550
    },
    {
      "epoch": 0.0401954064733173,
      "grad_norm": 0.19386635720729828,
      "learning_rate": 0.001,
      "loss": 3.38037109375,
      "step": 4600
    },
    {
      "epoch": 0.04063231306541857,
      "grad_norm": 0.20124493539333344,
      "learning_rate": 0.001,
      "loss": 3.382728271484375,
      "step": 4650
    },
    {
      "epoch": 0.04106921965751985,
      "grad_norm": 0.19963102042675018,
      "learning_rate": 0.001,
      "loss": 3.381324462890625,
      "step": 4700
    },
    {
      "epoch": 0.04150612624962112,
      "grad_norm": 0.20611299574375153,
      "learning_rate": 0.001,
      "loss": 3.3788223266601562,
      "step": 4750
    },
    {
      "epoch": 0.0419430328417224,
      "grad_norm": 0.19405238330364227,
      "learning_rate": 0.001,
      "loss": 3.3741259765625,
      "step": 4800
    },
    {
      "epoch": 0.04237993943382367,
      "grad_norm": 0.20914608240127563,
      "learning_rate": 0.001,
      "loss": 3.370547180175781,
      "step": 4850
    },
    {
      "epoch": 0.04281684602592495,
      "grad_norm": 0.19159191846847534,
      "learning_rate": 0.001,
      "loss": 3.3625115966796875,
      "step": 4900
    },
    {
      "epoch": 0.04325375261802622,
      "grad_norm": 0.19163894653320312,
      "learning_rate": 0.001,
      "loss": 3.360504455566406,
      "step": 4950
    },
    {
      "epoch": 0.04369065921012749,
      "grad_norm": 0.19763918220996857,
      "learning_rate": 0.001,
      "loss": 3.3601028442382814,
      "step": 5000
    },
    {
      "epoch": 0.04412756580222877,
      "grad_norm": 0.18974512815475464,
      "learning_rate": 0.001,
      "loss": 3.3579150390625,
      "step": 5050
    },
    {
      "epoch": 0.04456447239433004,
      "grad_norm": 0.21315094828605652,
      "learning_rate": 0.001,
      "loss": 3.355892333984375,
      "step": 5100
    },
    {
      "epoch": 0.04500137898643132,
      "grad_norm": 0.1904531568288803,
      "learning_rate": 0.001,
      "loss": 3.360745849609375,
      "step": 5150
    },
    {
      "epoch": 0.04543828557853259,
      "grad_norm": 0.19907866418361664,
      "learning_rate": 0.001,
      "loss": 3.357358703613281,
      "step": 5200
    },
    {
      "epoch": 0.04587519217063387,
      "grad_norm": 0.22703590989112854,
      "learning_rate": 0.001,
      "loss": 3.356294860839844,
      "step": 5250
    },
    {
      "epoch": 0.04631209876273514,
      "grad_norm": 0.1892520785331726,
      "learning_rate": 0.001,
      "loss": 3.3490374755859373,
      "step": 5300
    },
    {
      "epoch": 0.04674900535483642,
      "grad_norm": 0.18953296542167664,
      "learning_rate": 0.001,
      "loss": 3.3442022705078127,
      "step": 5350
    },
    {
      "epoch": 0.04718591194693769,
      "grad_norm": 0.1933782547712326,
      "learning_rate": 0.001,
      "loss": 3.3514590454101563,
      "step": 5400
    },
    {
      "epoch": 0.04762281853903897,
      "grad_norm": 0.22573590278625488,
      "learning_rate": 0.001,
      "loss": 3.3468975830078125,
      "step": 5450
    },
    {
      "epoch": 0.04805972513114024,
      "grad_norm": 0.2123604267835617,
      "learning_rate": 0.001,
      "loss": 3.3379788208007812,
      "step": 5500
    },
    {
      "epoch": 0.04849663172324152,
      "grad_norm": 0.18217475712299347,
      "learning_rate": 0.001,
      "loss": 3.344074401855469,
      "step": 5550
    },
    {
      "epoch": 0.04893353831534279,
      "grad_norm": 0.2128428965806961,
      "learning_rate": 0.001,
      "loss": 3.3349212646484374,
      "step": 5600
    },
    {
      "epoch": 0.04937044490744407,
      "grad_norm": 0.19785532355308533,
      "learning_rate": 0.001,
      "loss": 3.327950744628906,
      "step": 5650
    },
    {
      "epoch": 0.04980735149954534,
      "grad_norm": 0.18241338431835175,
      "learning_rate": 0.001,
      "loss": 3.334012451171875,
      "step": 5700
    },
    {
      "epoch": 0.05024425809164662,
      "grad_norm": 0.2020372748374939,
      "learning_rate": 0.001,
      "loss": 3.3329043579101563,
      "step": 5750
    },
    {
      "epoch": 0.05068116468374789,
      "grad_norm": 0.2071504294872284,
      "learning_rate": 0.001,
      "loss": 3.33412353515625,
      "step": 5800
    },
    {
      "epoch": 0.05111807127584917,
      "grad_norm": 0.20365303754806519,
      "learning_rate": 0.001,
      "loss": 3.322493591308594,
      "step": 5850
    },
    {
      "epoch": 0.05155497786795044,
      "grad_norm": 0.21742033958435059,
      "learning_rate": 0.001,
      "loss": 3.329978332519531,
      "step": 5900
    },
    {
      "epoch": 0.05199188446005172,
      "grad_norm": 0.18907567858695984,
      "learning_rate": 0.001,
      "loss": 3.328219299316406,
      "step": 5950
    },
    {
      "epoch": 0.05242879105215299,
      "grad_norm": 0.18905521929264069,
      "learning_rate": 0.001,
      "loss": 3.323075866699219,
      "step": 6000
    },
    {
      "epoch": 0.05242879105215299,
      "eval_loss": 3.3261899948120117,
      "eval_runtime": 6.1096,
      "eval_samples_per_second": 159.748,
      "eval_steps_per_second": 9.984,
      "step": 6000
    }
  ],
  "logging_steps": 50,
  "max_steps": 114440,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.12679224246272e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}