{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08048289738430583,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008048289738430583,
      "grad_norm": 11.192166328430176,
      "learning_rate": 1e-05,
      "loss": 6.6585,
      "step": 1
    },
    {
      "epoch": 0.0008048289738430583,
      "eval_loss": 6.805187702178955,
      "eval_runtime": 104.6359,
      "eval_samples_per_second": 39.986,
      "eval_steps_per_second": 1.252,
      "step": 1
    },
    {
      "epoch": 0.0016096579476861167,
      "grad_norm": 11.650690078735352,
      "learning_rate": 2e-05,
      "loss": 7.0188,
      "step": 2
    },
    {
      "epoch": 0.002414486921529175,
      "grad_norm": 11.421113014221191,
      "learning_rate": 3e-05,
      "loss": 6.4525,
      "step": 3
    },
    {
      "epoch": 0.0032193158953722333,
      "grad_norm": 11.061086654663086,
      "learning_rate": 4e-05,
      "loss": 6.3784,
      "step": 4
    },
    {
      "epoch": 0.004024144869215292,
      "grad_norm": 9.775355339050293,
      "learning_rate": 5e-05,
      "loss": 6.2196,
      "step": 5
    },
    {
      "epoch": 0.00482897384305835,
      "grad_norm": 9.562323570251465,
      "learning_rate": 6e-05,
      "loss": 5.6062,
      "step": 6
    },
    {
      "epoch": 0.005633802816901409,
      "grad_norm": 10.165483474731445,
      "learning_rate": 7e-05,
      "loss": 5.2028,
      "step": 7
    },
    {
      "epoch": 0.006438631790744467,
      "grad_norm": 10.02241325378418,
      "learning_rate": 8e-05,
      "loss": 4.0975,
      "step": 8
    },
    {
      "epoch": 0.007243460764587525,
      "grad_norm": 8.44987964630127,
      "learning_rate": 9e-05,
      "loss": 3.0836,
      "step": 9
    },
    {
      "epoch": 0.007243460764587525,
      "eval_loss": 2.5053255558013916,
      "eval_runtime": 104.9058,
      "eval_samples_per_second": 39.883,
      "eval_steps_per_second": 1.249,
      "step": 9
    },
    {
      "epoch": 0.008048289738430584,
      "grad_norm": 6.6600728034973145,
      "learning_rate": 0.0001,
      "loss": 2.4739,
      "step": 10
    },
    {
      "epoch": 0.008853118712273641,
      "grad_norm": 5.0193281173706055,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.1564,
      "step": 11
    },
    {
      "epoch": 0.0096579476861167,
      "grad_norm": 4.505955219268799,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.8849,
      "step": 12
    },
    {
      "epoch": 0.010462776659959759,
      "grad_norm": 5.045136451721191,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.7878,
      "step": 13
    },
    {
      "epoch": 0.011267605633802818,
      "grad_norm": 4.680845260620117,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.954,
      "step": 14
    },
    {
      "epoch": 0.012072434607645875,
      "grad_norm": 2.519116163253784,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.5238,
      "step": 15
    },
    {
      "epoch": 0.012877263581488933,
      "grad_norm": 4.319192886352539,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.8018,
      "step": 16
    },
    {
      "epoch": 0.013682092555331992,
      "grad_norm": 2.92718768119812,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.6114,
      "step": 17
    },
    {
      "epoch": 0.01448692152917505,
      "grad_norm": 2.9451489448547363,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.5827,
      "step": 18
    },
    {
      "epoch": 0.01448692152917505,
      "eval_loss": 1.637782096862793,
      "eval_runtime": 104.9159,
      "eval_samples_per_second": 39.88,
      "eval_steps_per_second": 1.249,
      "step": 18
    },
    {
      "epoch": 0.015291750503018108,
      "grad_norm": 2.3936715126037598,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.5507,
      "step": 19
    },
    {
      "epoch": 0.01609657947686117,
      "grad_norm": 4.588832855224609,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.6737,
      "step": 20
    },
    {
      "epoch": 0.016901408450704224,
      "grad_norm": 4.155963897705078,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.6339,
      "step": 21
    },
    {
      "epoch": 0.017706237424547282,
      "grad_norm": 2.737631320953369,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.531,
      "step": 22
    },
    {
      "epoch": 0.01851106639839034,
      "grad_norm": 2.7039952278137207,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.6107,
      "step": 23
    },
    {
      "epoch": 0.0193158953722334,
      "grad_norm": 2.363913059234619,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.5691,
      "step": 24
    },
    {
      "epoch": 0.02012072434607646,
      "grad_norm": 1.343972086906433,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.6317,
      "step": 25
    },
    {
      "epoch": 0.020925553319919517,
      "grad_norm": 1.7515672445297241,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.5421,
      "step": 26
    },
    {
      "epoch": 0.021730382293762576,
      "grad_norm": 1.2362278699874878,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.5112,
      "step": 27
    },
    {
      "epoch": 0.021730382293762576,
      "eval_loss": 1.5076904296875,
      "eval_runtime": 104.8339,
      "eval_samples_per_second": 39.911,
      "eval_steps_per_second": 1.25,
      "step": 27
    },
    {
      "epoch": 0.022535211267605635,
      "grad_norm": 1.300615906715393,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.4843,
      "step": 28
    },
    {
      "epoch": 0.023340040241448694,
      "grad_norm": 1.56174635887146,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.442,
      "step": 29
    },
    {
      "epoch": 0.02414486921529175,
      "grad_norm": 1.2243015766143799,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.3991,
      "step": 30
    },
    {
      "epoch": 0.024949698189134808,
      "grad_norm": 3.7497904300689697,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.6153,
      "step": 31
    },
    {
      "epoch": 0.025754527162977867,
      "grad_norm": 2.2340564727783203,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.5808,
      "step": 32
    },
    {
      "epoch": 0.026559356136820925,
      "grad_norm": 1.3580228090286255,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.4753,
      "step": 33
    },
    {
      "epoch": 0.027364185110663984,
      "grad_norm": 1.3715550899505615,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.4633,
      "step": 34
    },
    {
      "epoch": 0.028169014084507043,
      "grad_norm": 1.1812132596969604,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.4643,
      "step": 35
    },
    {
      "epoch": 0.0289738430583501,
      "grad_norm": 1.5139570236206055,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.5013,
      "step": 36
    },
    {
      "epoch": 0.0289738430583501,
      "eval_loss": 1.4720921516418457,
      "eval_runtime": 104.853,
      "eval_samples_per_second": 39.903,
      "eval_steps_per_second": 1.249,
      "step": 36
    },
    {
      "epoch": 0.02977867203219316,
      "grad_norm": 1.8641102313995361,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.4444,
      "step": 37
    },
    {
      "epoch": 0.030583501006036216,
      "grad_norm": 2.7784502506256104,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.4846,
      "step": 38
    },
    {
      "epoch": 0.031388329979879274,
      "grad_norm": 1.257810115814209,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.3544,
      "step": 39
    },
    {
      "epoch": 0.03219315895372234,
      "grad_norm": 1.5466625690460205,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.4845,
      "step": 40
    },
    {
      "epoch": 0.03299798792756539,
      "grad_norm": 1.6509723663330078,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.414,
      "step": 41
    },
    {
      "epoch": 0.03380281690140845,
      "grad_norm": 2.0773937702178955,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.4217,
      "step": 42
    },
    {
      "epoch": 0.03460764587525151,
      "grad_norm": 4.887015342712402,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.5279,
      "step": 43
    },
    {
      "epoch": 0.035412474849094565,
      "grad_norm": 1.6943373680114746,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.4103,
      "step": 44
    },
    {
      "epoch": 0.03621730382293763,
      "grad_norm": 1.8067197799682617,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.2827,
      "step": 45
    },
    {
      "epoch": 0.03621730382293763,
      "eval_loss": 1.430705189704895,
      "eval_runtime": 104.8515,
      "eval_samples_per_second": 39.904,
      "eval_steps_per_second": 1.249,
      "step": 45
    },
    {
      "epoch": 0.03702213279678068,
      "grad_norm": 3.1064023971557617,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.5073,
      "step": 46
    },
    {
      "epoch": 0.037826961770623745,
      "grad_norm": 1.9709528684616089,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.3964,
      "step": 47
    },
    {
      "epoch": 0.0386317907444668,
      "grad_norm": 2.6226296424865723,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.5358,
      "step": 48
    },
    {
      "epoch": 0.03943661971830986,
      "grad_norm": 1.5384474992752075,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.3684,
      "step": 49
    },
    {
      "epoch": 0.04024144869215292,
      "grad_norm": 1.7795501947402954,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.5023,
      "step": 50
    },
    {
      "epoch": 0.04104627766599597,
      "grad_norm": 1.9440804719924927,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.3768,
      "step": 51
    },
    {
      "epoch": 0.041851106639839035,
      "grad_norm": 1.7918343544006348,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.3898,
      "step": 52
    },
    {
      "epoch": 0.04265593561368209,
      "grad_norm": 1.6904802322387695,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.2864,
      "step": 53
    },
    {
      "epoch": 0.04346076458752515,
      "grad_norm": 2.007007360458374,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.3977,
      "step": 54
    },
    {
      "epoch": 0.04346076458752515,
      "eval_loss": 1.397533655166626,
      "eval_runtime": 104.7915,
      "eval_samples_per_second": 39.927,
      "eval_steps_per_second": 1.25,
      "step": 54
    },
    {
      "epoch": 0.04426559356136821,
      "grad_norm": 1.9125590324401855,
      "learning_rate": 5e-05,
      "loss": 1.4675,
      "step": 55
    },
    {
      "epoch": 0.04507042253521127,
      "grad_norm": 1.4900492429733276,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.413,
      "step": 56
    },
    {
      "epoch": 0.045875251509054325,
      "grad_norm": 2.335010290145874,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.4394,
      "step": 57
    },
    {
      "epoch": 0.04668008048289739,
      "grad_norm": 1.7225452661514282,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.3768,
      "step": 58
    },
    {
      "epoch": 0.04748490945674044,
      "grad_norm": 1.1971241235733032,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.4439,
      "step": 59
    },
    {
      "epoch": 0.0482897384305835,
      "grad_norm": 1.7993239164352417,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.4337,
      "step": 60
    },
    {
      "epoch": 0.04909456740442656,
      "grad_norm": 1.193589448928833,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.2794,
      "step": 61
    },
    {
      "epoch": 0.049899396378269616,
      "grad_norm": 1.2995184659957886,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.2957,
      "step": 62
    },
    {
      "epoch": 0.05070422535211268,
      "grad_norm": 1.5458860397338867,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.4027,
      "step": 63
    },
    {
      "epoch": 0.05070422535211268,
      "eval_loss": 1.3566713333129883,
      "eval_runtime": 104.8245,
      "eval_samples_per_second": 39.914,
      "eval_steps_per_second": 1.25,
      "step": 63
    },
    {
      "epoch": 0.05150905432595573,
      "grad_norm": 1.243240475654602,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.3594,
      "step": 64
    },
    {
      "epoch": 0.052313883299798795,
      "grad_norm": 1.6665877103805542,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.3725,
      "step": 65
    },
    {
      "epoch": 0.05311871227364185,
      "grad_norm": 1.9751228094100952,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.3449,
      "step": 66
    },
    {
      "epoch": 0.053923541247484906,
      "grad_norm": 1.640518307685852,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.4013,
      "step": 67
    },
    {
      "epoch": 0.05472837022132797,
      "grad_norm": 1.4377756118774414,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.3361,
      "step": 68
    },
    {
      "epoch": 0.055533199195171024,
      "grad_norm": 1.8161500692367554,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.3564,
      "step": 69
    },
    {
      "epoch": 0.056338028169014086,
      "grad_norm": 1.4024537801742554,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.5085,
      "step": 70
    },
    {
      "epoch": 0.05714285714285714,
      "grad_norm": 1.6841168403625488,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.2695,
      "step": 71
    },
    {
      "epoch": 0.0579476861167002,
      "grad_norm": 2.2560067176818848,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.3388,
      "step": 72
    },
    {
      "epoch": 0.0579476861167002,
      "eval_loss": 1.3307467699050903,
      "eval_runtime": 105.0349,
      "eval_samples_per_second": 39.834,
      "eval_steps_per_second": 1.247,
      "step": 72
    },
    {
      "epoch": 0.05875251509054326,
      "grad_norm": 1.5936686992645264,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.2245,
      "step": 73
    },
    {
      "epoch": 0.05955734406438632,
      "grad_norm": 1.7071914672851562,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.326,
      "step": 74
    },
    {
      "epoch": 0.060362173038229376,
      "grad_norm": 1.3684706687927246,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.3298,
      "step": 75
    },
    {
      "epoch": 0.06116700201207243,
      "grad_norm": 1.5466399192810059,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.3475,
      "step": 76
    },
    {
      "epoch": 0.061971830985915494,
      "grad_norm": 1.5489482879638672,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.2671,
      "step": 77
    },
    {
      "epoch": 0.06277665995975855,
      "grad_norm": 1.2277204990386963,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.3749,
      "step": 78
    },
    {
      "epoch": 0.0635814889336016,
      "grad_norm": 1.2665647268295288,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.4556,
      "step": 79
    },
    {
      "epoch": 0.06438631790744467,
      "grad_norm": 1.3061295747756958,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.3503,
      "step": 80
    },
    {
      "epoch": 0.06519114688128773,
      "grad_norm": 1.5980522632598877,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.3163,
      "step": 81
    },
    {
      "epoch": 0.06519114688128773,
      "eval_loss": 1.3149529695510864,
      "eval_runtime": 104.9208,
      "eval_samples_per_second": 39.878,
      "eval_steps_per_second": 1.249,
      "step": 81
    },
    {
      "epoch": 0.06599597585513078,
      "grad_norm": 1.584516167640686,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.2814,
      "step": 82
    },
    {
      "epoch": 0.06680080482897384,
      "grad_norm": 1.2764320373535156,
      "learning_rate": 8.548121372247918e-06,
      "loss": 1.2364,
      "step": 83
    },
    {
      "epoch": 0.0676056338028169,
      "grad_norm": 1.677539348602295,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.3964,
      "step": 84
    },
    {
      "epoch": 0.06841046277665996,
      "grad_norm": 1.598472237586975,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.5972,
      "step": 85
    },
    {
      "epoch": 0.06921529175050302,
      "grad_norm": 1.4204151630401611,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.4061,
      "step": 86
    },
    {
      "epoch": 0.07002012072434607,
      "grad_norm": 1.343601942062378,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.3895,
      "step": 87
    },
    {
      "epoch": 0.07082494969818913,
      "grad_norm": 1.6658458709716797,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.2865,
      "step": 88
    },
    {
      "epoch": 0.0716297786720322,
      "grad_norm": 1.5555486679077148,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.3754,
      "step": 89
    },
    {
      "epoch": 0.07243460764587525,
      "grad_norm": 1.6924740076065063,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.2451,
      "step": 90
    },
    {
      "epoch": 0.07243460764587525,
      "eval_loss": 1.3083361387252808,
      "eval_runtime": 105.803,
      "eval_samples_per_second": 39.545,
      "eval_steps_per_second": 1.238,
      "step": 90
    },
    {
      "epoch": 0.07323943661971831,
      "grad_norm": 1.3936550617218018,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.3828,
      "step": 91
    },
    {
      "epoch": 0.07404426559356136,
      "grad_norm": 1.1824584007263184,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.3104,
      "step": 92
    },
    {
      "epoch": 0.07484909456740442,
      "grad_norm": 1.5771610736846924,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.2057,
      "step": 93
    },
    {
      "epoch": 0.07565392354124749,
      "grad_norm": 1.4560160636901855,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.3677,
      "step": 94
    },
    {
      "epoch": 0.07645875251509054,
      "grad_norm": 1.4910780191421509,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.2196,
      "step": 95
    },
    {
      "epoch": 0.0772635814889336,
      "grad_norm": 1.288588285446167,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.3186,
      "step": 96
    },
    {
      "epoch": 0.07806841046277666,
      "grad_norm": 1.227581262588501,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.3112,
      "step": 97
    },
    {
      "epoch": 0.07887323943661972,
      "grad_norm": 1.3534032106399536,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.3355,
      "step": 98
    },
    {
      "epoch": 0.07967806841046278,
      "grad_norm": 1.3254411220550537,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.2597,
      "step": 99
    },
    {
      "epoch": 0.07967806841046278,
      "eval_loss": 1.3059089183807373,
      "eval_runtime": 105.3364,
      "eval_samples_per_second": 39.72,
      "eval_steps_per_second": 1.244,
      "step": 99
    },
    {
      "epoch": 0.08048289738430583,
      "grad_norm": 2.148303985595703,
      "learning_rate": 0.0,
      "loss": 1.2935,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.770335240004567e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}