{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0021181279984749477,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.118127998474948e-05,
      "grad_norm": 0.16889730095863342,
      "learning_rate": 1e-05,
      "loss": 10.3956,
      "step": 1
    },
    {
      "epoch": 2.118127998474948e-05,
      "eval_loss": 10.398905754089355,
      "eval_runtime": 263.6586,
      "eval_samples_per_second": 150.794,
      "eval_steps_per_second": 18.85,
      "step": 1
    },
    {
      "epoch": 4.236255996949896e-05,
      "grad_norm": 0.17050734162330627,
      "learning_rate": 2e-05,
      "loss": 10.3876,
      "step": 2
    },
    {
      "epoch": 6.354383995424843e-05,
      "grad_norm": 0.1798275262117386,
      "learning_rate": 3e-05,
      "loss": 10.3979,
      "step": 3
    },
    {
      "epoch": 8.472511993899791e-05,
      "grad_norm": 0.1841912865638733,
      "learning_rate": 4e-05,
      "loss": 10.3896,
      "step": 4
    },
    {
      "epoch": 0.0001059063999237474,
      "grad_norm": 0.18602658808231354,
      "learning_rate": 5e-05,
      "loss": 10.4073,
      "step": 5
    },
    {
      "epoch": 0.00012708767990849687,
      "grad_norm": 0.1590508371591568,
      "learning_rate": 6e-05,
      "loss": 10.408,
      "step": 6
    },
    {
      "epoch": 0.00014826895989324636,
      "grad_norm": 0.18670088052749634,
      "learning_rate": 7e-05,
      "loss": 10.3834,
      "step": 7
    },
    {
      "epoch": 0.00016945023987799583,
      "grad_norm": 0.24394260346889496,
      "learning_rate": 8e-05,
      "loss": 10.3698,
      "step": 8
    },
    {
      "epoch": 0.0001906315198627453,
      "grad_norm": 0.18870773911476135,
      "learning_rate": 9e-05,
      "loss": 10.4098,
      "step": 9
    },
    {
      "epoch": 0.0001906315198627453,
      "eval_loss": 10.396601676940918,
      "eval_runtime": 264.5263,
      "eval_samples_per_second": 150.299,
      "eval_steps_per_second": 18.788,
      "step": 9
    },
    {
      "epoch": 0.0002118127998474948,
      "grad_norm": 0.18838222324848175,
      "learning_rate": 0.0001,
      "loss": 10.3923,
      "step": 10
    },
    {
      "epoch": 0.00023299407983224426,
      "grad_norm": 0.16910575330257416,
      "learning_rate": 9.99695413509548e-05,
      "loss": 10.3948,
      "step": 11
    },
    {
      "epoch": 0.00025417535981699373,
      "grad_norm": 0.19666463136672974,
      "learning_rate": 9.987820251299122e-05,
      "loss": 10.3688,
      "step": 12
    },
    {
      "epoch": 0.0002753566398017432,
      "grad_norm": 0.17982766032218933,
      "learning_rate": 9.972609476841367e-05,
      "loss": 10.3875,
      "step": 13
    },
    {
      "epoch": 0.0002965379197864927,
      "grad_norm": 0.19756174087524414,
      "learning_rate": 9.951340343707852e-05,
      "loss": 10.3725,
      "step": 14
    },
    {
      "epoch": 0.0003177191997712422,
      "grad_norm": 0.21875005960464478,
      "learning_rate": 9.924038765061042e-05,
      "loss": 10.3732,
      "step": 15
    },
    {
      "epoch": 0.00033890047975599166,
      "grad_norm": 0.22114615142345428,
      "learning_rate": 9.890738003669029e-05,
      "loss": 10.401,
      "step": 16
    },
    {
      "epoch": 0.00036008175974074113,
      "grad_norm": 0.18753595650196075,
      "learning_rate": 9.851478631379982e-05,
      "loss": 10.3818,
      "step": 17
    },
    {
      "epoch": 0.0003812630397254906,
      "grad_norm": 0.1712396889925003,
      "learning_rate": 9.806308479691595e-05,
      "loss": 10.3843,
      "step": 18
    },
    {
      "epoch": 0.0003812630397254906,
      "eval_loss": 10.390729904174805,
      "eval_runtime": 264.2162,
      "eval_samples_per_second": 150.475,
      "eval_steps_per_second": 18.81,
      "step": 18
    },
    {
      "epoch": 0.00040244431971024006,
      "grad_norm": 0.22963330149650574,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.3631,
      "step": 19
    },
    {
      "epoch": 0.0004236255996949896,
      "grad_norm": 0.18184514343738556,
      "learning_rate": 9.698463103929542e-05,
      "loss": 10.3788,
      "step": 20
    },
    {
      "epoch": 0.00044480687967973906,
      "grad_norm": 0.19332440197467804,
      "learning_rate": 9.635919272833938e-05,
      "loss": 10.3804,
      "step": 21
    },
    {
      "epoch": 0.0004659881596644885,
      "grad_norm": 0.19627565145492554,
      "learning_rate": 9.567727288213005e-05,
      "loss": 10.3853,
      "step": 22
    },
    {
      "epoch": 0.000487169439649238,
      "grad_norm": 0.19879043102264404,
      "learning_rate": 9.493970231495835e-05,
      "loss": 10.3913,
      "step": 23
    },
    {
      "epoch": 0.0005083507196339875,
      "grad_norm": 0.19176159799098969,
      "learning_rate": 9.414737964294636e-05,
      "loss": 10.3894,
      "step": 24
    },
    {
      "epoch": 0.0005295319996187369,
      "grad_norm": 0.22696080803871155,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.3604,
      "step": 25
    },
    {
      "epoch": 0.0005507132796034864,
      "grad_norm": 0.20836742222309113,
      "learning_rate": 9.24024048078213e-05,
      "loss": 10.3644,
      "step": 26
    },
    {
      "epoch": 0.0005718945595882359,
      "grad_norm": 0.2002551406621933,
      "learning_rate": 9.145187862775209e-05,
      "loss": 10.4058,
      "step": 27
    },
    {
      "epoch": 0.0005718945595882359,
      "eval_loss": 10.384385108947754,
      "eval_runtime": 264.2193,
      "eval_samples_per_second": 150.473,
      "eval_steps_per_second": 18.81,
      "step": 27
    },
    {
      "epoch": 0.0005930758395729854,
      "grad_norm": 0.2085038721561432,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.375,
      "step": 28
    },
    {
      "epoch": 0.0006142571195577349,
      "grad_norm": 0.25786292552948,
      "learning_rate": 8.940053768033609e-05,
      "loss": 10.4152,
      "step": 29
    },
    {
      "epoch": 0.0006354383995424844,
      "grad_norm": 0.2436630129814148,
      "learning_rate": 8.83022221559489e-05,
      "loss": 10.3652,
      "step": 30
    },
    {
      "epoch": 0.0006566196795272338,
      "grad_norm": 0.20807240903377533,
      "learning_rate": 8.715724127386972e-05,
      "loss": 10.3717,
      "step": 31
    },
    {
      "epoch": 0.0006778009595119833,
      "grad_norm": 0.21431414783000946,
      "learning_rate": 8.596699001693255e-05,
      "loss": 10.3851,
      "step": 32
    },
    {
      "epoch": 0.0006989822394967328,
      "grad_norm": 0.2529206871986389,
      "learning_rate": 8.473291852294987e-05,
      "loss": 10.3919,
      "step": 33
    },
    {
      "epoch": 0.0007201635194814823,
      "grad_norm": 0.20583346486091614,
      "learning_rate": 8.345653031794292e-05,
      "loss": 10.3932,
      "step": 34
    },
    {
      "epoch": 0.0007413447994662317,
      "grad_norm": 0.19697058200836182,
      "learning_rate": 8.213938048432697e-05,
      "loss": 10.3836,
      "step": 35
    },
    {
      "epoch": 0.0007625260794509812,
      "grad_norm": 0.22605247795581818,
      "learning_rate": 8.07830737662829e-05,
      "loss": 10.3709,
      "step": 36
    },
    {
      "epoch": 0.0007625260794509812,
      "eval_loss": 10.377544403076172,
      "eval_runtime": 264.2986,
      "eval_samples_per_second": 150.428,
      "eval_steps_per_second": 18.804,
      "step": 36
    },
    {
      "epoch": 0.0007837073594357307,
      "grad_norm": 0.23540405929088593,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.3821,
      "step": 37
    },
    {
      "epoch": 0.0008048886394204801,
      "grad_norm": 0.25848376750946045,
      "learning_rate": 7.795964517353735e-05,
      "loss": 10.3993,
      "step": 38
    },
    {
      "epoch": 0.0008260699194052297,
      "grad_norm": 0.2196625918149948,
      "learning_rate": 7.649596321166024e-05,
      "loss": 10.3743,
      "step": 39
    },
    {
      "epoch": 0.0008472511993899792,
      "grad_norm": 0.22024263441562653,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.3815,
      "step": 40
    },
    {
      "epoch": 0.0008684324793747286,
      "grad_norm": 0.22341415286064148,
      "learning_rate": 7.347357813929454e-05,
      "loss": 10.4108,
      "step": 41
    },
    {
      "epoch": 0.0008896137593594781,
      "grad_norm": 0.2678864300251007,
      "learning_rate": 7.191855733945387e-05,
      "loss": 10.3734,
      "step": 42
    },
    {
      "epoch": 0.0009107950393442276,
      "grad_norm": 0.24385559558868408,
      "learning_rate": 7.033683215379002e-05,
      "loss": 10.3607,
      "step": 43
    },
    {
      "epoch": 0.000931976319328977,
      "grad_norm": 0.2389352172613144,
      "learning_rate": 6.873032967079561e-05,
      "loss": 10.36,
      "step": 44
    },
    {
      "epoch": 0.0009531575993137265,
      "grad_norm": 0.24411995708942413,
      "learning_rate": 6.710100716628344e-05,
      "loss": 10.3555,
      "step": 45
    },
    {
      "epoch": 0.0009531575993137265,
      "eval_loss": 10.370607376098633,
      "eval_runtime": 264.3906,
      "eval_samples_per_second": 150.376,
      "eval_steps_per_second": 18.798,
      "step": 45
    },
    {
      "epoch": 0.000974338879298476,
      "grad_norm": 0.24778561294078827,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.3654,
      "step": 46
    },
    {
      "epoch": 0.0009955201592832255,
      "grad_norm": 0.27637922763824463,
      "learning_rate": 6.378186779084995e-05,
      "loss": 10.3488,
      "step": 47
    },
    {
      "epoch": 0.001016701439267975,
      "grad_norm": 0.28022265434265137,
      "learning_rate": 6.209609477998338e-05,
      "loss": 10.3677,
      "step": 48
    },
    {
      "epoch": 0.0010378827192527244,
      "grad_norm": 0.2709881365299225,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 10.349,
      "step": 49
    },
    {
      "epoch": 0.0010590639992374739,
      "grad_norm": 0.2436312437057495,
      "learning_rate": 5.868240888334653e-05,
      "loss": 10.3602,
      "step": 50
    },
    {
      "epoch": 0.0010802452792222233,
      "grad_norm": 0.2696683704853058,
      "learning_rate": 5.695865504800327e-05,
      "loss": 10.3797,
      "step": 51
    },
    {
      "epoch": 0.0011014265592069728,
      "grad_norm": 0.2767253518104553,
      "learning_rate": 5.522642316338268e-05,
      "loss": 10.3767,
      "step": 52
    },
    {
      "epoch": 0.0011226078391917223,
      "grad_norm": 0.28129932284355164,
      "learning_rate": 5.348782368720626e-05,
      "loss": 10.3607,
      "step": 53
    },
    {
      "epoch": 0.0011437891191764717,
      "grad_norm": 0.2902565598487854,
      "learning_rate": 5.174497483512506e-05,
      "loss": 10.3621,
      "step": 54
    },
    {
      "epoch": 0.0011437891191764717,
      "eval_loss": 10.363870620727539,
      "eval_runtime": 263.6718,
      "eval_samples_per_second": 150.786,
      "eval_steps_per_second": 18.849,
      "step": 54
    },
    {
      "epoch": 0.0011649703991612214,
      "grad_norm": 0.25226110219955444,
      "learning_rate": 5e-05,
      "loss": 10.3868,
      "step": 55
    },
    {
      "epoch": 0.0011861516791459709,
      "grad_norm": 0.3142261505126953,
      "learning_rate": 4.825502516487497e-05,
      "loss": 10.35,
      "step": 56
    },
    {
      "epoch": 0.0012073329591307204,
      "grad_norm": 0.366685152053833,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 10.3823,
      "step": 57
    },
    {
      "epoch": 0.0012285142391154698,
      "grad_norm": 0.2839343547821045,
      "learning_rate": 4.477357683661734e-05,
      "loss": 10.357,
      "step": 58
    },
    {
      "epoch": 0.0012496955191002193,
      "grad_norm": 0.2913300395011902,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 10.3403,
      "step": 59
    },
    {
      "epoch": 0.0012708767990849688,
      "grad_norm": 0.28911805152893066,
      "learning_rate": 4.131759111665349e-05,
      "loss": 10.351,
      "step": 60
    },
    {
      "epoch": 0.0012920580790697182,
      "grad_norm": 0.33699050545692444,
      "learning_rate": 3.960441545911204e-05,
      "loss": 10.3366,
      "step": 61
    },
    {
      "epoch": 0.0013132393590544677,
      "grad_norm": 0.2737447917461395,
      "learning_rate": 3.790390522001662e-05,
      "loss": 10.3459,
      "step": 62
    },
    {
      "epoch": 0.0013344206390392172,
      "grad_norm": 0.26118916273117065,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 10.3575,
      "step": 63
    },
    {
      "epoch": 0.0013344206390392172,
      "eval_loss": 10.358147621154785,
      "eval_runtime": 264.4036,
      "eval_samples_per_second": 150.369,
      "eval_steps_per_second": 18.797,
      "step": 63
    },
    {
      "epoch": 0.0013556019190239666,
      "grad_norm": 0.2942837178707123,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.3614,
      "step": 64
    },
    {
      "epoch": 0.001376783199008716,
      "grad_norm": 0.34198886156082153,
      "learning_rate": 3.289899283371657e-05,
      "loss": 10.3492,
      "step": 65
    },
    {
      "epoch": 0.0013979644789934656,
      "grad_norm": 0.30794763565063477,
      "learning_rate": 3.12696703292044e-05,
      "loss": 10.3687,
      "step": 66
    },
    {
      "epoch": 0.001419145758978215,
      "grad_norm": 0.3069867491722107,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 10.3396,
      "step": 67
    },
    {
      "epoch": 0.0014403270389629645,
      "grad_norm": 0.2907857298851013,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 10.3519,
      "step": 68
    },
    {
      "epoch": 0.001461508318947714,
      "grad_norm": 0.2831253707408905,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 10.3592,
      "step": 69
    },
    {
      "epoch": 0.0014826895989324634,
      "grad_norm": 0.2868959605693817,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.3545,
      "step": 70
    },
    {
      "epoch": 0.001503870878917213,
      "grad_norm": 0.28792205452919006,
      "learning_rate": 2.350403678833976e-05,
      "loss": 10.3609,
      "step": 71
    },
    {
      "epoch": 0.0015250521589019624,
      "grad_norm": 0.3293297588825226,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 10.3534,
      "step": 72
    },
    {
      "epoch": 0.0015250521589019624,
      "eval_loss": 10.353981018066406,
      "eval_runtime": 264.3866,
      "eval_samples_per_second": 150.378,
      "eval_steps_per_second": 18.798,
      "step": 72
    },
    {
      "epoch": 0.0015462334388867119,
      "grad_norm": 0.3583596646785736,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.3684,
      "step": 73
    },
    {
      "epoch": 0.0015674147188714613,
      "grad_norm": 0.33219587802886963,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 10.3615,
      "step": 74
    },
    {
      "epoch": 0.0015885959988562108,
      "grad_norm": 0.3535849153995514,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 10.3904,
      "step": 75
    },
    {
      "epoch": 0.0016097772788409603,
      "grad_norm": 0.33791688084602356,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 10.3546,
      "step": 76
    },
    {
      "epoch": 0.00163095855882571,
      "grad_norm": 0.32664117217063904,
      "learning_rate": 1.526708147705013e-05,
      "loss": 10.3715,
      "step": 77
    },
    {
      "epoch": 0.0016521398388104594,
      "grad_norm": 0.3056585192680359,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 10.3574,
      "step": 78
    },
    {
      "epoch": 0.0016733211187952089,
      "grad_norm": 0.31749436259269714,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 10.369,
      "step": 79
    },
    {
      "epoch": 0.0016945023987799583,
      "grad_norm": 0.3024196922779083,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 10.3541,
      "step": 80
    },
    {
      "epoch": 0.0017156836787647078,
      "grad_norm": 0.31615588068962097,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 10.3619,
      "step": 81
    },
    {
      "epoch": 0.0017156836787647078,
      "eval_loss": 10.351547241210938,
      "eval_runtime": 263.9177,
      "eval_samples_per_second": 150.645,
      "eval_steps_per_second": 18.832,
      "step": 81
    },
    {
      "epoch": 0.0017368649587494573,
      "grad_norm": 0.302412748336792,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.3478,
      "step": 82
    },
    {
      "epoch": 0.0017580462387342068,
      "grad_norm": 0.34448879957199097,
      "learning_rate": 8.548121372247918e-06,
      "loss": 10.333,
      "step": 83
    },
    {
      "epoch": 0.0017792275187189562,
      "grad_norm": 0.2946290075778961,
      "learning_rate": 7.597595192178702e-06,
      "loss": 10.3425,
      "step": 84
    },
    {
      "epoch": 0.0018004087987037057,
      "grad_norm": 0.3481883406639099,
      "learning_rate": 6.698729810778065e-06,
      "loss": 10.33,
      "step": 85
    },
    {
      "epoch": 0.0018215900786884552,
      "grad_norm": 0.3070729970932007,
      "learning_rate": 5.852620357053651e-06,
      "loss": 10.3511,
      "step": 86
    },
    {
      "epoch": 0.0018427713586732046,
      "grad_norm": 0.3426555395126343,
      "learning_rate": 5.060297685041659e-06,
      "loss": 10.3715,
      "step": 87
    },
    {
      "epoch": 0.001863952638657954,
      "grad_norm": 0.3272855579853058,
      "learning_rate": 4.322727117869951e-06,
      "loss": 10.3723,
      "step": 88
    },
    {
      "epoch": 0.0018851339186427036,
      "grad_norm": 0.3252405524253845,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 10.3478,
      "step": 89
    },
    {
      "epoch": 0.001906315198627453,
      "grad_norm": 0.3317711651325226,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 10.3445,
      "step": 90
    },
    {
      "epoch": 0.001906315198627453,
      "eval_loss": 10.350534439086914,
      "eval_runtime": 264.5384,
      "eval_samples_per_second": 150.292,
      "eval_steps_per_second": 18.787,
      "step": 90
    },
    {
      "epoch": 0.0019274964786122025,
      "grad_norm": 0.3351341187953949,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 10.3455,
      "step": 91
    },
    {
      "epoch": 0.001948677758596952,
      "grad_norm": 0.31914907693862915,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 10.3619,
      "step": 92
    },
    {
      "epoch": 0.0019698590385817017,
      "grad_norm": 0.31719982624053955,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 10.3511,
      "step": 93
    },
    {
      "epoch": 0.001991040318566451,
      "grad_norm": 0.3255273699760437,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 10.3649,
      "step": 94
    },
    {
      "epoch": 0.0020122215985512006,
      "grad_norm": 0.3029558062553406,
      "learning_rate": 7.596123493895991e-07,
      "loss": 10.3522,
      "step": 95
    },
    {
      "epoch": 0.00203340287853595,
      "grad_norm": 0.3137965500354767,
      "learning_rate": 4.865965629214819e-07,
      "loss": 10.33,
      "step": 96
    },
    {
      "epoch": 0.0020545841585206995,
      "grad_norm": 0.3334927558898926,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 10.3613,
      "step": 97
    },
    {
      "epoch": 0.0020757654385054488,
      "grad_norm": 0.31634390354156494,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 10.3522,
      "step": 98
    },
    {
      "epoch": 0.0020969467184901985,
      "grad_norm": 0.28614795207977295,
      "learning_rate": 3.04586490452119e-08,
      "loss": 10.3672,
      "step": 99
    },
    {
      "epoch": 0.0020969467184901985,
      "eval_loss": 10.350330352783203,
      "eval_runtime": 264.4391,
      "eval_samples_per_second": 150.348,
      "eval_steps_per_second": 18.795,
      "step": 99
    },
    {
      "epoch": 0.0021181279984749477,
      "grad_norm": 0.31697142124176025,
      "learning_rate": 0.0,
      "loss": 10.3324,
      "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": 5230244659200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}