{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9915764139590855,
  "eval_steps": 25,
  "global_step": 103,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009626955475330927,
      "grad_norm": 36.655242919921875,
      "learning_rate": 9.997674418116759e-06,
      "loss": 10.061,
      "step": 1
    },
    {
      "epoch": 0.019253910950661854,
      "grad_norm": 29.486038208007812,
      "learning_rate": 9.99069983579947e-06,
      "loss": 9.9813,
      "step": 2
    },
    {
      "epoch": 0.02888086642599278,
      "grad_norm": 16.687410354614258,
      "learning_rate": 9.979082741033047e-06,
      "loss": 9.5428,
      "step": 3
    },
    {
      "epoch": 0.03850782190132371,
      "grad_norm": 19.905546188354492,
      "learning_rate": 9.96283394041954e-06,
      "loss": 9.7047,
      "step": 4
    },
    {
      "epoch": 0.048134777376654635,
      "grad_norm": 21.7939453125,
      "learning_rate": 9.941968549125481e-06,
      "loss": 9.7184,
      "step": 5
    },
    {
      "epoch": 0.05776173285198556,
      "grad_norm": Infinity,
      "learning_rate": 9.941968549125481e-06,
      "loss": 9.7494,
      "step": 6
    },
    {
      "epoch": 0.06738868832731648,
      "grad_norm": 37.23790740966797,
      "learning_rate": 9.916505976821262e-06,
      "loss": 9.8672,
      "step": 7
    },
    {
      "epoch": 0.07701564380264742,
      "grad_norm": 57.11663055419922,
      "learning_rate": 9.886469909625624e-06,
      "loss": 9.9945,
      "step": 8
    },
    {
      "epoch": 0.08664259927797834,
      "grad_norm": 32.410648345947266,
      "learning_rate": 9.851888288072053e-06,
      "loss": 9.832,
      "step": 9
    },
    {
      "epoch": 0.09626955475330927,
      "grad_norm": 20.996421813964844,
      "learning_rate": 9.81279328111758e-06,
      "loss": 9.6547,
      "step": 10
    },
    {
      "epoch": 0.10589651022864019,
      "grad_norm": 29.850004196166992,
      "learning_rate": 9.769221256218165e-06,
      "loss": 9.634,
      "step": 11
    },
    {
      "epoch": 0.11552346570397112,
      "grad_norm": 20.321626663208008,
      "learning_rate": 9.721212745498493e-06,
      "loss": 9.5294,
      "step": 12
    },
    {
      "epoch": 0.12515042117930206,
      "grad_norm": 21.042863845825195,
      "learning_rate": 9.66881240804768e-06,
      "loss": 9.4986,
      "step": 13
    },
    {
      "epoch": 0.13477737665463296,
      "grad_norm": 39.393123626708984,
      "learning_rate": 9.612068988375898e-06,
      "loss": 9.7214,
      "step": 14
    },
    {
      "epoch": 0.1444043321299639,
      "grad_norm": 29.8813533782959,
      "learning_rate": 9.551035271070665e-06,
      "loss": 9.6157,
      "step": 15
    },
    {
      "epoch": 0.15403128760529483,
      "grad_norm": 22.601821899414062,
      "learning_rate": 9.485768031694872e-06,
      "loss": 9.5022,
      "step": 16
    },
    {
      "epoch": 0.16365824308062576,
      "grad_norm": 38.687896728515625,
      "learning_rate": 9.416327983972304e-06,
      "loss": 9.5861,
      "step": 17
    },
    {
      "epoch": 0.17328519855595667,
      "grad_norm": 40.1544303894043,
      "learning_rate": 9.342779723309746e-06,
      "loss": 9.6032,
      "step": 18
    },
    {
      "epoch": 0.1829121540312876,
      "grad_norm": 31.16316032409668,
      "learning_rate": 9.26519166670821e-06,
      "loss": 9.4739,
      "step": 19
    },
    {
      "epoch": 0.19253910950661854,
      "grad_norm": 25.174264907836914,
      "learning_rate": 9.183635989119211e-06,
      "loss": 9.3975,
      "step": 20
    },
    {
      "epoch": 0.20216606498194944,
      "grad_norm": 21.90279197692871,
      "learning_rate": 9.098188556305262e-06,
      "loss": 9.3676,
      "step": 21
    },
    {
      "epoch": 0.21179302045728038,
      "grad_norm": 27.172040939331055,
      "learning_rate": 9.008928854267054e-06,
      "loss": 9.3662,
      "step": 22
    },
    {
      "epoch": 0.2214199759326113,
      "grad_norm": 35.05919647216797,
      "learning_rate": 8.91593991530297e-06,
      "loss": 9.3918,
      "step": 23
    },
    {
      "epoch": 0.23104693140794225,
      "grad_norm": 59.50571823120117,
      "learning_rate": 8.819308240769726e-06,
      "loss": 9.4201,
      "step": 24
    },
    {
      "epoch": 0.24067388688327315,
      "grad_norm": 31.860584259033203,
      "learning_rate": 8.71912372061598e-06,
      "loss": 9.345,
      "step": 25
    },
    {
      "epoch": 0.24067388688327315,
      "eval_clap": 0.21781522035598755,
      "eval_loss": 3.680818557739258,
      "eval_runtime": 197.7141,
      "eval_samples_per_second": 0.162,
      "eval_steps_per_second": 0.162,
      "step": 25
    },
    {
      "epoch": 0.2503008423586041,
      "grad_norm": 35.62887191772461,
      "learning_rate": 8.615479549763756e-06,
      "loss": 9.2727,
      "step": 26
    },
    {
      "epoch": 0.259927797833935,
      "grad_norm": 29.90762710571289,
      "learning_rate": 8.508472141415468e-06,
      "loss": 9.2321,
      "step": 27
    },
    {
      "epoch": 0.2695547533092659,
      "grad_norm": 25.5911808013916,
      "learning_rate": 8.398201037367202e-06,
      "loss": 9.1778,
      "step": 28
    },
    {
      "epoch": 0.27918170878459686,
      "grad_norm": 22.98084259033203,
      "learning_rate": 8.284768815411693e-06,
      "loss": 9.1713,
      "step": 29
    },
    {
      "epoch": 0.2888086642599278,
      "grad_norm": 23.99754524230957,
      "learning_rate": 8.168280993917078e-06,
      "loss": 9.1769,
      "step": 30
    },
    {
      "epoch": 0.29843561973525873,
      "grad_norm": 26.287574768066406,
      "learning_rate": 8.048845933670274e-06,
      "loss": 9.0526,
      "step": 31
    },
    {
      "epoch": 0.30806257521058966,
      "grad_norm": 47.93935775756836,
      "learning_rate": 7.92657473707621e-06,
      "loss": 9.1205,
      "step": 32
    },
    {
      "epoch": 0.3176895306859206,
      "grad_norm": 30.085956573486328,
      "learning_rate": 7.801581144806752e-06,
      "loss": 8.9902,
      "step": 33
    },
    {
      "epoch": 0.32731648616125153,
      "grad_norm": 55.95182418823242,
      "learning_rate": 7.673981429995372e-06,
      "loss": 9.0223,
      "step": 34
    },
    {
      "epoch": 0.3369434416365824,
      "grad_norm": 43.94280242919922,
      "learning_rate": 7.5438942900761035e-06,
      "loss": 9.0648,
      "step": 35
    },
    {
      "epoch": 0.34657039711191334,
      "grad_norm": 44.075782775878906,
      "learning_rate": 7.411440736367281e-06,
      "loss": 9.0315,
      "step": 36
    },
    {
      "epoch": 0.3561973525872443,
      "grad_norm": 36.636837005615234,
      "learning_rate": 7.276743981502856e-06,
      "loss": 8.9343,
      "step": 37
    },
    {
      "epoch": 0.3658243080625752,
      "grad_norm": 57.34428787231445,
      "learning_rate": 7.139929324815965e-06,
      "loss": 8.9535,
      "step": 38
    },
    {
      "epoch": 0.37545126353790614,
      "grad_norm": 33.31437301635742,
      "learning_rate": 7.00112403578139e-06,
      "loss": 8.831,
      "step": 39
    },
    {
      "epoch": 0.3850782190132371,
      "grad_norm": 41.02770233154297,
      "learning_rate": 6.860457235625322e-06,
      "loss": 8.7563,
      "step": 40
    },
    {
      "epoch": 0.394705174488568,
      "grad_norm": Infinity,
      "learning_rate": 6.860457235625322e-06,
      "loss": 8.7286,
      "step": 41
    },
    {
      "epoch": 0.4043321299638989,
      "grad_norm": 36.15497970581055,
      "learning_rate": 6.7180597772125665e-06,
      "loss": 8.8619,
      "step": 42
    },
    {
      "epoch": 0.4139590854392298,
      "grad_norm": 27.45692253112793,
      "learning_rate": 6.574064123322925e-06,
      "loss": 8.7769,
      "step": 43
    },
    {
      "epoch": 0.42358604091456076,
      "grad_norm": 44.91440200805664,
      "learning_rate": 6.42860422342998e-06,
      "loss": 8.8987,
      "step": 44
    },
    {
      "epoch": 0.4332129963898917,
      "grad_norm": 49.40604782104492,
      "learning_rate": 6.281815389096903e-06,
      "loss": 8.5464,
      "step": 45
    },
    {
      "epoch": 0.4428399518652226,
      "grad_norm": 38.211082458496094,
      "learning_rate": 6.133834168105206e-06,
      "loss": 8.6558,
      "step": 46
    },
    {
      "epoch": 0.45246690734055356,
      "grad_norm": 40.19668960571289,
      "learning_rate": 5.9847982174335314e-06,
      "loss": 8.6081,
      "step": 47
    },
    {
      "epoch": 0.4620938628158845,
      "grad_norm": 31.05793571472168,
      "learning_rate": 5.834846175204612e-06,
      "loss": 8.6122,
      "step": 48
    },
    {
      "epoch": 0.4717208182912154,
      "grad_norm": 54.35275650024414,
      "learning_rate": 5.684117531719552e-06,
      "loss": 8.5534,
      "step": 49
    },
    {
      "epoch": 0.4813477737665463,
      "grad_norm": 31.807424545288086,
      "learning_rate": 5.532752499699381e-06,
      "loss": 8.5598,
      "step": 50
    },
    {
      "epoch": 0.4813477737665463,
      "eval_clap": 0.2060224413871765,
      "eval_loss": 3.6995468139648438,
      "eval_runtime": 203.4451,
      "eval_samples_per_second": 0.157,
      "eval_steps_per_second": 0.157,
      "step": 50
    },
    {
      "epoch": 0.49097472924187724,
      "grad_norm": 32.47773742675781,
      "learning_rate": 5.380891883854591e-06,
      "loss": 8.5232,
      "step": 51
    },
    {
      "epoch": 0.5006016847172082,
      "grad_norm": 32.18419647216797,
      "learning_rate": 5.228676949903974e-06,
      "loss": 8.5755,
      "step": 52
    },
    {
      "epoch": 0.5102286401925391,
      "grad_norm": 40.90557098388672,
      "learning_rate": 5.07624929316463e-06,
      "loss": 8.4902,
      "step": 53
    },
    {
      "epoch": 0.51985559566787,
      "grad_norm": 33.113006591796875,
      "learning_rate": 4.923750706835371e-06,
      "loss": 8.5366,
      "step": 54
    },
    {
      "epoch": 0.529482551143201,
      "grad_norm": 38.09598159790039,
      "learning_rate": 4.771323050096028e-06,
      "loss": 8.5472,
      "step": 55
    },
    {
      "epoch": 0.5391095066185319,
      "grad_norm": 27.295963287353516,
      "learning_rate": 4.619108116145411e-06,
      "loss": 8.5864,
      "step": 56
    },
    {
      "epoch": 0.5487364620938628,
      "grad_norm": 43.426124572753906,
      "learning_rate": 4.467247500300621e-06,
      "loss": 8.3008,
      "step": 57
    },
    {
      "epoch": 0.5583634175691937,
      "grad_norm": 26.15068817138672,
      "learning_rate": 4.31588246828045e-06,
      "loss": 8.5288,
      "step": 58
    },
    {
      "epoch": 0.5679903730445247,
      "grad_norm": 28.06884765625,
      "learning_rate": 4.165153824795391e-06,
      "loss": 8.4413,
      "step": 59
    },
    {
      "epoch": 0.5776173285198556,
      "grad_norm": 37.16442108154297,
      "learning_rate": 4.015201782566471e-06,
      "loss": 8.2101,
      "step": 60
    },
    {
      "epoch": 0.5872442839951865,
      "grad_norm": 45.41092300415039,
      "learning_rate": 3.866165831894796e-06,
      "loss": 8.1815,
      "step": 61
    },
    {
      "epoch": 0.5968712394705175,
      "grad_norm": 35.478515625,
      "learning_rate": 3.7181846109031007e-06,
      "loss": 8.379,
      "step": 62
    },
    {
      "epoch": 0.6064981949458483,
      "grad_norm": 34.70208740234375,
      "learning_rate": 3.5713957765700224e-06,
      "loss": 8.2477,
      "step": 63
    },
    {
      "epoch": 0.6161251504211793,
      "grad_norm": 32.52558135986328,
      "learning_rate": 3.425935876677077e-06,
      "loss": 8.2687,
      "step": 64
    },
    {
      "epoch": 0.6257521058965102,
      "grad_norm": 59.53068923950195,
      "learning_rate": 3.2819402227874364e-06,
      "loss": 7.8701,
      "step": 65
    },
    {
      "epoch": 0.6353790613718412,
      "grad_norm": 25.783588409423828,
      "learning_rate": 3.1395427643746802e-06,
      "loss": 8.3832,
      "step": 66
    },
    {
      "epoch": 0.6450060168471721,
      "grad_norm": 30.451751708984375,
      "learning_rate": 2.99887596421861e-06,
      "loss": 8.2528,
      "step": 67
    },
    {
      "epoch": 0.6546329723225031,
      "grad_norm": 36.75849914550781,
      "learning_rate": 2.860070675184036e-06,
      "loss": 8.1908,
      "step": 68
    },
    {
      "epoch": 0.6642599277978339,
      "grad_norm": 36.29214859008789,
      "learning_rate": 2.7232560184971437e-06,
      "loss": 8.0419,
      "step": 69
    },
    {
      "epoch": 0.6738868832731648,
      "grad_norm": 40.11077880859375,
      "learning_rate": 2.588559263632719e-06,
      "loss": 8.001,
      "step": 70
    },
    {
      "epoch": 0.6835138387484958,
      "grad_norm": 43.78921890258789,
      "learning_rate": 2.4561057099238973e-06,
      "loss": 8.1344,
      "step": 71
    },
    {
      "epoch": 0.6931407942238267,
      "grad_norm": 18.768470764160156,
      "learning_rate": 2.3260185700046295e-06,
      "loss": 8.4484,
      "step": 72
    },
    {
      "epoch": 0.7027677496991577,
      "grad_norm": 36.79136657714844,
      "learning_rate": 2.1984188551932513e-06,
      "loss": 8.078,
      "step": 73
    },
    {
      "epoch": 0.7123947051744886,
      "grad_norm": 23.20965003967285,
      "learning_rate": 2.0734252629237892e-06,
      "loss": 8.3404,
      "step": 74
    },
    {
      "epoch": 0.7220216606498195,
      "grad_norm": 23.93864631652832,
      "learning_rate": 1.9511540663297284e-06,
      "loss": 8.3691,
      "step": 75
    },
    {
      "epoch": 0.7220216606498195,
      "eval_clap": 0.21875908970832825,
      "eval_loss": 3.7276365756988525,
      "eval_runtime": 203.3924,
      "eval_samples_per_second": 0.157,
      "eval_steps_per_second": 0.157,
      "step": 75
    },
    {
      "epoch": 0.7316486161251504,
      "grad_norm": 41.18170166015625,
      "learning_rate": 1.8317190060829242e-06,
      "loss": 7.9022,
      "step": 76
    },
    {
      "epoch": 0.7412755716004813,
      "grad_norm": 25.832717895507812,
      "learning_rate": 1.7152311845883096e-06,
      "loss": 8.1734,
      "step": 77
    },
    {
      "epoch": 0.7509025270758123,
      "grad_norm": 26.72269630432129,
      "learning_rate": 1.601798962632799e-06,
      "loss": 8.1561,
      "step": 78
    },
    {
      "epoch": 0.7605294825511432,
      "grad_norm": 28.269739151000977,
      "learning_rate": 1.491527858584535e-06,
      "loss": 8.0723,
      "step": 79
    },
    {
      "epoch": 0.7701564380264742,
      "grad_norm": 37.14287185668945,
      "learning_rate": 1.3845204502362442e-06,
      "loss": 7.8806,
      "step": 80
    },
    {
      "epoch": 0.779783393501805,
      "grad_norm": 28.547544479370117,
      "learning_rate": 1.28087627938402e-06,
      "loss": 8.09,
      "step": 81
    },
    {
      "epoch": 0.789410348977136,
      "grad_norm": 24.613683700561523,
      "learning_rate": 1.1806917592302763e-06,
      "loss": 8.2687,
      "step": 82
    },
    {
      "epoch": 0.7990373044524669,
      "grad_norm": 36.22146987915039,
      "learning_rate": 1.0840600846970333e-06,
      "loss": 8.1399,
      "step": 83
    },
    {
      "epoch": 0.8086642599277978,
      "grad_norm": 38.009300231933594,
      "learning_rate": 9.91071145732948e-07,
      "loss": 7.8937,
      "step": 84
    },
    {
      "epoch": 0.8182912154031288,
      "grad_norm": 42.18280792236328,
      "learning_rate": 9.018114436947373e-07,
      "loss": 7.9889,
      "step": 85
    },
    {
      "epoch": 0.8279181708784596,
      "grad_norm": 28.27996826171875,
      "learning_rate": 8.163640108807897e-07,
      "loss": 8.094,
      "step": 86
    },
    {
      "epoch": 0.8375451263537906,
      "grad_norm": 53.69871139526367,
      "learning_rate": 7.348083332917927e-07,
      "loss": 7.7992,
      "step": 87
    },
    {
      "epoch": 0.8471720818291215,
      "grad_norm": 25.41583251953125,
      "learning_rate": 6.572202766902569e-07,
      "loss": 8.2104,
      "step": 88
    },
    {
      "epoch": 0.8567990373044525,
      "grad_norm": 54.796871185302734,
      "learning_rate": 5.836720160276971e-07,
      "loss": 7.9115,
      "step": 89
    },
    {
      "epoch": 0.8664259927797834,
      "grad_norm": 23.627187728881836,
      "learning_rate": 5.1423196830513e-07,
      "loss": 8.2171,
      "step": 90
    },
    {
      "epoch": 0.8760529482551144,
      "grad_norm": 34.87358856201172,
      "learning_rate": 4.4896472892933693e-07,
      "loss": 8.0587,
      "step": 91
    },
    {
      "epoch": 0.8856799037304453,
      "grad_norm": 42.69806671142578,
      "learning_rate": 3.8793101162410417e-07,
      "loss": 7.7615,
      "step": 92
    },
    {
      "epoch": 0.8953068592057761,
      "grad_norm": 22.716751098632812,
      "learning_rate": 3.3118759195232273e-07,
      "loss": 8.2045,
      "step": 93
    },
    {
      "epoch": 0.9049338146811071,
      "grad_norm": 47.218284606933594,
      "learning_rate": 2.787872545015069e-07,
      "loss": 7.684,
      "step": 94
    },
    {
      "epoch": 0.914560770156438,
      "grad_norm": 24.743898391723633,
      "learning_rate": 2.307787437818365e-07,
      "loss": 8.1474,
      "step": 95
    },
    {
      "epoch": 0.924187725631769,
      "grad_norm": 27.12813377380371,
      "learning_rate": 1.8720671888242058e-07,
      "loss": 8.2783,
      "step": 96
    },
    {
      "epoch": 0.9338146811070999,
      "grad_norm": 45.253604888916016,
      "learning_rate": 1.4811171192794628e-07,
      "loss": 7.945,
      "step": 97
    },
    {
      "epoch": 0.9434416365824309,
      "grad_norm": 30.242605209350586,
      "learning_rate": 1.1353009037437523e-07,
      "loss": 8.1772,
      "step": 98
    },
    {
      "epoch": 0.9530685920577617,
      "grad_norm": 37.83307647705078,
      "learning_rate": 8.34940231787379e-08,
      "loss": 7.8305,
      "step": 99
    },
    {
      "epoch": 0.9626955475330926,
      "grad_norm": 23.995698928833008,
      "learning_rate": 5.803145087451945e-08,
      "loss": 8.1954,
      "step": 100
    },
    {
      "epoch": 0.9626955475330926,
      "eval_clap": 0.2072528600692749,
      "eval_loss": 3.7368812561035156,
      "eval_runtime": 204.8586,
      "eval_samples_per_second": 0.156,
      "eval_steps_per_second": 0.156,
      "step": 100
    },
    {
      "epoch": 0.9723225030084236,
      "grad_norm": 44.95185470581055,
      "learning_rate": 3.716605958046071e-08,
      "loss": 7.7546,
      "step": 101
    },
    {
      "epoch": 0.9819494584837545,
      "grad_norm": 38.132503509521484,
      "learning_rate": 2.0917258966953735e-08,
      "loss": 7.8938,
      "step": 102
    },
    {
      "epoch": 0.9915764139590855,
      "grad_norm": 33.25323486328125,
      "learning_rate": 9.300164200530815e-09,
      "loss": 7.895,
      "step": 103
    },
    {
      "epoch": 0.9915764139590855,
      "step": 103,
      "total_flos": 171610142427840.0,
      "train_loss": 8.696112142025846,
      "train_runtime": 1142.9145,
      "train_samples_per_second": 0.727,
      "train_steps_per_second": 0.09
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 103,
  "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": 171610142427840.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}