{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02655689815429558,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002655689815429558,
      "grad_norm": 16.932558059692383,
      "learning_rate": 1e-05,
      "loss": 26.79,
      "step": 1
    },
    {
      "epoch": 0.0002655689815429558,
      "eval_loss": 10.071907997131348,
      "eval_runtime": 559.8005,
      "eval_samples_per_second": 5.665,
      "eval_steps_per_second": 0.709,
      "step": 1
    },
    {
      "epoch": 0.0005311379630859116,
      "grad_norm": 14.588117599487305,
      "learning_rate": 2e-05,
      "loss": 15.0363,
      "step": 2
    },
    {
      "epoch": 0.0007967069446288673,
      "grad_norm": 18.925893783569336,
      "learning_rate": 3e-05,
      "loss": 16.4197,
      "step": 3
    },
    {
      "epoch": 0.0010622759261718232,
      "grad_norm": 19.222543716430664,
      "learning_rate": 4e-05,
      "loss": 23.3828,
      "step": 4
    },
    {
      "epoch": 0.001327844907714779,
      "grad_norm": 21.194564819335938,
      "learning_rate": 5e-05,
      "loss": 19.5726,
      "step": 5
    },
    {
      "epoch": 0.0015934138892577346,
      "grad_norm": 22.77863883972168,
      "learning_rate": 6e-05,
      "loss": 18.2281,
      "step": 6
    },
    {
      "epoch": 0.0018589828708006906,
      "grad_norm": 20.478927612304688,
      "learning_rate": 7e-05,
      "loss": 20.6862,
      "step": 7
    },
    {
      "epoch": 0.0021245518523436463,
      "grad_norm": 24.290197372436523,
      "learning_rate": 8e-05,
      "loss": 19.408,
      "step": 8
    },
    {
      "epoch": 0.002390120833886602,
      "grad_norm": 23.530662536621094,
      "learning_rate": 9e-05,
      "loss": 14.6411,
      "step": 9
    },
    {
      "epoch": 0.002390120833886602,
      "eval_loss": 7.5023980140686035,
      "eval_runtime": 559.8751,
      "eval_samples_per_second": 5.664,
      "eval_steps_per_second": 0.709,
      "step": 9
    },
    {
      "epoch": 0.002655689815429558,
      "grad_norm": 21.587501525878906,
      "learning_rate": 0.0001,
      "loss": 10.7612,
      "step": 10
    },
    {
      "epoch": 0.0029212587969725135,
      "grad_norm": 21.97700309753418,
      "learning_rate": 9.99695413509548e-05,
      "loss": 8.3382,
      "step": 11
    },
    {
      "epoch": 0.0031868277785154693,
      "grad_norm": 20.751781463623047,
      "learning_rate": 9.987820251299122e-05,
      "loss": 13.3529,
      "step": 12
    },
    {
      "epoch": 0.003452396760058425,
      "grad_norm": 14.957468032836914,
      "learning_rate": 9.972609476841367e-05,
      "loss": 4.1384,
      "step": 13
    },
    {
      "epoch": 0.003717965741601381,
      "grad_norm": 17.004064559936523,
      "learning_rate": 9.951340343707852e-05,
      "loss": 7.9299,
      "step": 14
    },
    {
      "epoch": 0.0039835347231443365,
      "grad_norm": 26.11749839782715,
      "learning_rate": 9.924038765061042e-05,
      "loss": 8.4737,
      "step": 15
    },
    {
      "epoch": 0.004249103704687293,
      "grad_norm": 18.64482307434082,
      "learning_rate": 9.890738003669029e-05,
      "loss": 7.5791,
      "step": 16
    },
    {
      "epoch": 0.004514672686230248,
      "grad_norm": 26.95172882080078,
      "learning_rate": 9.851478631379982e-05,
      "loss": 11.9976,
      "step": 17
    },
    {
      "epoch": 0.004780241667773204,
      "grad_norm": 18.327199935913086,
      "learning_rate": 9.806308479691595e-05,
      "loss": 6.3552,
      "step": 18
    },
    {
      "epoch": 0.004780241667773204,
      "eval_loss": 2.5800344944000244,
      "eval_runtime": 560.149,
      "eval_samples_per_second": 5.661,
      "eval_steps_per_second": 0.709,
      "step": 18
    },
    {
      "epoch": 0.00504581064931616,
      "grad_norm": 15.647052764892578,
      "learning_rate": 9.755282581475769e-05,
      "loss": 6.5816,
      "step": 19
    },
    {
      "epoch": 0.005311379630859116,
      "grad_norm": 17.486684799194336,
      "learning_rate": 9.698463103929542e-05,
      "loss": 3.9695,
      "step": 20
    },
    {
      "epoch": 0.005576948612402072,
      "grad_norm": 21.761070251464844,
      "learning_rate": 9.635919272833938e-05,
      "loss": 5.1097,
      "step": 21
    },
    {
      "epoch": 0.005842517593945027,
      "grad_norm": 14.224836349487305,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.9224,
      "step": 22
    },
    {
      "epoch": 0.006108086575487983,
      "grad_norm": 12.894025802612305,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.679,
      "step": 23
    },
    {
      "epoch": 0.0063736555570309385,
      "grad_norm": 17.416015625,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.0615,
      "step": 24
    },
    {
      "epoch": 0.006639224538573895,
      "grad_norm": 8.535757064819336,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.7809,
      "step": 25
    },
    {
      "epoch": 0.00690479352011685,
      "grad_norm": 12.756429672241211,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.8468,
      "step": 26
    },
    {
      "epoch": 0.007170362501659806,
      "grad_norm": 12.496906280517578,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.7602,
      "step": 27
    },
    {
      "epoch": 0.007170362501659806,
      "eval_loss": 0.20372115075588226,
      "eval_runtime": 559.8065,
      "eval_samples_per_second": 5.664,
      "eval_steps_per_second": 0.709,
      "step": 27
    },
    {
      "epoch": 0.007435931483202762,
      "grad_norm": 6.117914199829102,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.4319,
      "step": 28
    },
    {
      "epoch": 0.007701500464745718,
      "grad_norm": 10.269083976745605,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.3816,
      "step": 29
    },
    {
      "epoch": 0.007967069446288673,
      "grad_norm": 8.173473358154297,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.3573,
      "step": 30
    },
    {
      "epoch": 0.00823263842783163,
      "grad_norm": 7.133336544036865,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.1658,
      "step": 31
    },
    {
      "epoch": 0.008498207409374585,
      "grad_norm": 4.3148298263549805,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.1436,
      "step": 32
    },
    {
      "epoch": 0.00876377639091754,
      "grad_norm": 12.986287117004395,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.4481,
      "step": 33
    },
    {
      "epoch": 0.009029345372460496,
      "grad_norm": 8.799443244934082,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.2404,
      "step": 34
    },
    {
      "epoch": 0.009294914354003453,
      "grad_norm": 6.142348289489746,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.1254,
      "step": 35
    },
    {
      "epoch": 0.009560483335546408,
      "grad_norm": 5.877281665802002,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.1166,
      "step": 36
    },
    {
      "epoch": 0.009560483335546408,
      "eval_loss": 0.07145125418901443,
      "eval_runtime": 559.908,
      "eval_samples_per_second": 5.663,
      "eval_steps_per_second": 0.709,
      "step": 36
    },
    {
      "epoch": 0.009826052317089363,
      "grad_norm": 5.168353080749512,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0559,
      "step": 37
    },
    {
      "epoch": 0.01009162129863232,
      "grad_norm": 5.736714839935303,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.1733,
      "step": 38
    },
    {
      "epoch": 0.010357190280175276,
      "grad_norm": 1.031773328781128,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.019,
      "step": 39
    },
    {
      "epoch": 0.010622759261718231,
      "grad_norm": 0.3790012300014496,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0093,
      "step": 40
    },
    {
      "epoch": 0.010888328243261186,
      "grad_norm": 9.644392967224121,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.4539,
      "step": 41
    },
    {
      "epoch": 0.011153897224804143,
      "grad_norm": 20.26791763305664,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.1645,
      "step": 42
    },
    {
      "epoch": 0.011419466206347099,
      "grad_norm": 24.0386962890625,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.9467,
      "step": 43
    },
    {
      "epoch": 0.011685035187890054,
      "grad_norm": 9.300283432006836,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.3329,
      "step": 44
    },
    {
      "epoch": 0.01195060416943301,
      "grad_norm": 8.567636489868164,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.1665,
      "step": 45
    },
    {
      "epoch": 0.01195060416943301,
      "eval_loss": 0.07661288231611252,
      "eval_runtime": 559.8843,
      "eval_samples_per_second": 5.664,
      "eval_steps_per_second": 0.709,
      "step": 45
    },
    {
      "epoch": 0.012216173150975966,
      "grad_norm": 3.942033052444458,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0614,
      "step": 46
    },
    {
      "epoch": 0.012481742132518922,
      "grad_norm": 3.180799722671509,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.0409,
      "step": 47
    },
    {
      "epoch": 0.012747311114061877,
      "grad_norm": 10.57024097442627,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.5203,
      "step": 48
    },
    {
      "epoch": 0.013012880095604834,
      "grad_norm": 24.475112915039062,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.144,
      "step": 49
    },
    {
      "epoch": 0.01327844907714779,
      "grad_norm": 12.837873458862305,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.8704,
      "step": 50
    },
    {
      "epoch": 0.013544018058690745,
      "grad_norm": 9.662187576293945,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.9199,
      "step": 51
    },
    {
      "epoch": 0.0138095870402337,
      "grad_norm": 17.19619369506836,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.6195,
      "step": 52
    },
    {
      "epoch": 0.014075156021776657,
      "grad_norm": 7.147523880004883,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.3419,
      "step": 53
    },
    {
      "epoch": 0.014340725003319612,
      "grad_norm": 1.385001301765442,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0217,
      "step": 54
    },
    {
      "epoch": 0.014340725003319612,
      "eval_loss": 0.046595290303230286,
      "eval_runtime": 559.6995,
      "eval_samples_per_second": 5.666,
      "eval_steps_per_second": 0.709,
      "step": 54
    },
    {
      "epoch": 0.014606293984862568,
      "grad_norm": 0.8563135862350464,
      "learning_rate": 5e-05,
      "loss": 0.0221,
      "step": 55
    },
    {
      "epoch": 0.014871862966405525,
      "grad_norm": 7.8890461921691895,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.1978,
      "step": 56
    },
    {
      "epoch": 0.01513743194794848,
      "grad_norm": 7.418190002441406,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.3631,
      "step": 57
    },
    {
      "epoch": 0.015403000929491435,
      "grad_norm": 3.629096031188965,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.3229,
      "step": 58
    },
    {
      "epoch": 0.01566856991103439,
      "grad_norm": 6.946701526641846,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.4263,
      "step": 59
    },
    {
      "epoch": 0.015934138892577346,
      "grad_norm": 2.2904245853424072,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0595,
      "step": 60
    },
    {
      "epoch": 0.0161997078741203,
      "grad_norm": 5.863007068634033,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.1395,
      "step": 61
    },
    {
      "epoch": 0.01646527685566326,
      "grad_norm": 4.192048072814941,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.18,
      "step": 62
    },
    {
      "epoch": 0.016730845837206215,
      "grad_norm": 10.30323314666748,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.1841,
      "step": 63
    },
    {
      "epoch": 0.016730845837206215,
      "eval_loss": 0.03462190553545952,
      "eval_runtime": 559.7706,
      "eval_samples_per_second": 5.665,
      "eval_steps_per_second": 0.709,
      "step": 63
    },
    {
      "epoch": 0.01699641481874917,
      "grad_norm": 3.4951865673065186,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.1341,
      "step": 64
    },
    {
      "epoch": 0.017261983800292126,
      "grad_norm": 3.107192277908325,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.119,
      "step": 65
    },
    {
      "epoch": 0.01752755278183508,
      "grad_norm": 0.26891380548477173,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0107,
      "step": 66
    },
    {
      "epoch": 0.017793121763378036,
      "grad_norm": 1.4425851106643677,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.0359,
      "step": 67
    },
    {
      "epoch": 0.01805869074492099,
      "grad_norm": 0.804293155670166,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.0302,
      "step": 68
    },
    {
      "epoch": 0.01832425972646395,
      "grad_norm": 0.1133980005979538,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.0048,
      "step": 69
    },
    {
      "epoch": 0.018589828708006906,
      "grad_norm": 0.35559359192848206,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0094,
      "step": 70
    },
    {
      "epoch": 0.01885539768954986,
      "grad_norm": 0.2842927873134613,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.0073,
      "step": 71
    },
    {
      "epoch": 0.019120966671092816,
      "grad_norm": 3.8495614528656006,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.2604,
      "step": 72
    },
    {
      "epoch": 0.019120966671092816,
      "eval_loss": 0.0361790768802166,
      "eval_runtime": 559.8064,
      "eval_samples_per_second": 5.664,
      "eval_steps_per_second": 0.709,
      "step": 72
    },
    {
      "epoch": 0.01938653565263577,
      "grad_norm": 3.6799263954162598,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0665,
      "step": 73
    },
    {
      "epoch": 0.019652104634178727,
      "grad_norm": 0.21115446090698242,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.0065,
      "step": 74
    },
    {
      "epoch": 0.019917673615721682,
      "grad_norm": 0.9436402320861816,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0193,
      "step": 75
    },
    {
      "epoch": 0.02018324259726464,
      "grad_norm": 4.517977714538574,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.2632,
      "step": 76
    },
    {
      "epoch": 0.020448811578807596,
      "grad_norm": 1.7417783737182617,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.0566,
      "step": 77
    },
    {
      "epoch": 0.02071438056035055,
      "grad_norm": 0.07233806699514389,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.0025,
      "step": 78
    },
    {
      "epoch": 0.020979949541893507,
      "grad_norm": 3.043607234954834,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.0618,
      "step": 79
    },
    {
      "epoch": 0.021245518523436462,
      "grad_norm": 1.1216740608215332,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0171,
      "step": 80
    },
    {
      "epoch": 0.021511087504979418,
      "grad_norm": 0.18935361504554749,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.0035,
      "step": 81
    },
    {
      "epoch": 0.021511087504979418,
      "eval_loss": 0.030739974230527878,
      "eval_runtime": 559.8399,
      "eval_samples_per_second": 5.664,
      "eval_steps_per_second": 0.709,
      "step": 81
    },
    {
      "epoch": 0.021776656486522373,
      "grad_norm": 4.249741554260254,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.3826,
      "step": 82
    },
    {
      "epoch": 0.02204222546806533,
      "grad_norm": 1.0712897777557373,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.0169,
      "step": 83
    },
    {
      "epoch": 0.022307794449608287,
      "grad_norm": 0.07341117411851883,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.0022,
      "step": 84
    },
    {
      "epoch": 0.022573363431151242,
      "grad_norm": 0.10707651823759079,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0047,
      "step": 85
    },
    {
      "epoch": 0.022838932412694198,
      "grad_norm": 0.08516495674848557,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.0034,
      "step": 86
    },
    {
      "epoch": 0.023104501394237153,
      "grad_norm": 1.109482765197754,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.0298,
      "step": 87
    },
    {
      "epoch": 0.023370070375780108,
      "grad_norm": 4.274382591247559,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.1633,
      "step": 88
    },
    {
      "epoch": 0.023635639357323063,
      "grad_norm": 4.241298198699951,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.1244,
      "step": 89
    },
    {
      "epoch": 0.02390120833886602,
      "grad_norm": 0.4226183593273163,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0099,
      "step": 90
    },
    {
      "epoch": 0.02390120833886602,
      "eval_loss": 0.030956266447901726,
      "eval_runtime": 559.9924,
      "eval_samples_per_second": 5.663,
      "eval_steps_per_second": 0.709,
      "step": 90
    },
    {
      "epoch": 0.024166777320408978,
      "grad_norm": 0.1662449985742569,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0056,
      "step": 91
    },
    {
      "epoch": 0.024432346301951933,
      "grad_norm": 0.1186576634645462,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.0044,
      "step": 92
    },
    {
      "epoch": 0.024697915283494888,
      "grad_norm": 0.24360933899879456,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.0076,
      "step": 93
    },
    {
      "epoch": 0.024963484265037843,
      "grad_norm": 0.07054503262042999,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.0021,
      "step": 94
    },
    {
      "epoch": 0.0252290532465808,
      "grad_norm": 0.06228477507829666,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0017,
      "step": 95
    },
    {
      "epoch": 0.025494622228123754,
      "grad_norm": 6.644521713256836,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.492,
      "step": 96
    },
    {
      "epoch": 0.02576019120966671,
      "grad_norm": 3.683866262435913,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.0485,
      "step": 97
    },
    {
      "epoch": 0.026025760191209668,
      "grad_norm": 0.042617376893758774,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.002,
      "step": 98
    },
    {
      "epoch": 0.026291329172752623,
      "grad_norm": 0.17293287813663483,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.0065,
      "step": 99
    },
    {
      "epoch": 0.026291329172752623,
      "eval_loss": 0.030459770932793617,
      "eval_runtime": 559.7954,
      "eval_samples_per_second": 5.665,
      "eval_steps_per_second": 0.709,
      "step": 99
    },
    {
      "epoch": 0.02655689815429558,
      "grad_norm": 0.04684700816869736,
      "learning_rate": 0.0,
      "loss": 0.0018,
      "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": 1.293847239768146e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}