{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.007975435658172828,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.975435658172828e-05,
      "grad_norm": 58.57548904418945,
      "learning_rate": 1e-05,
      "loss": 12.2331,
      "step": 1
    },
    {
      "epoch": 7.975435658172828e-05,
      "eval_loss": 12.32491397857666,
      "eval_runtime": 554.4191,
      "eval_samples_per_second": 19.045,
      "eval_steps_per_second": 2.381,
      "step": 1
    },
    {
      "epoch": 0.00015950871316345656,
      "grad_norm": 50.0570182800293,
      "learning_rate": 2e-05,
      "loss": 12.694,
      "step": 2
    },
    {
      "epoch": 0.00023926306974518484,
      "grad_norm": 54.007179260253906,
      "learning_rate": 3e-05,
      "loss": 12.2986,
      "step": 3
    },
    {
      "epoch": 0.0003190174263269131,
      "grad_norm": 49.70405960083008,
      "learning_rate": 4e-05,
      "loss": 11.9994,
      "step": 4
    },
    {
      "epoch": 0.00039877178290864137,
      "grad_norm": 44.04093933105469,
      "learning_rate": 5e-05,
      "loss": 9.5563,
      "step": 5
    },
    {
      "epoch": 0.0004785261394903697,
      "grad_norm": 39.21303939819336,
      "learning_rate": 6e-05,
      "loss": 7.4503,
      "step": 6
    },
    {
      "epoch": 0.000558280496072098,
      "grad_norm": 49.072200775146484,
      "learning_rate": 7e-05,
      "loss": 3.8217,
      "step": 7
    },
    {
      "epoch": 0.0006380348526538262,
      "grad_norm": 19.435436248779297,
      "learning_rate": 8e-05,
      "loss": 0.8504,
      "step": 8
    },
    {
      "epoch": 0.0007177892092355545,
      "grad_norm": 4.429564476013184,
      "learning_rate": 9e-05,
      "loss": 0.6351,
      "step": 9
    },
    {
      "epoch": 0.0007177892092355545,
      "eval_loss": 0.4419458508491516,
      "eval_runtime": 553.8414,
      "eval_samples_per_second": 19.065,
      "eval_steps_per_second": 2.383,
      "step": 9
    },
    {
      "epoch": 0.0007975435658172827,
      "grad_norm": 0.0200470183044672,
      "learning_rate": 0.0001,
      "loss": 0.0003,
      "step": 10
    },
    {
      "epoch": 0.0008772979223990111,
      "grad_norm": 15.89320182800293,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.8913,
      "step": 11
    },
    {
      "epoch": 0.0009570522789807393,
      "grad_norm": 64.74942016601562,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.7326,
      "step": 12
    },
    {
      "epoch": 0.0010368066355624676,
      "grad_norm": 2.8113746643066406,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.0253,
      "step": 13
    },
    {
      "epoch": 0.001116560992144196,
      "grad_norm": 0.020627321675419807,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.0002,
      "step": 14
    },
    {
      "epoch": 0.001196315348725924,
      "grad_norm": 3.4705936908721924,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.282,
      "step": 15
    },
    {
      "epoch": 0.0012760697053076525,
      "grad_norm": 8.107240676879883,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.3368,
      "step": 16
    },
    {
      "epoch": 0.0013558240618893806,
      "grad_norm": 7.4358367919921875,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.1098,
      "step": 17
    },
    {
      "epoch": 0.001435578418471109,
      "grad_norm": 3.5417537689208984,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.1003,
      "step": 18
    },
    {
      "epoch": 0.001435578418471109,
      "eval_loss": 0.06634360551834106,
      "eval_runtime": 553.4057,
      "eval_samples_per_second": 19.08,
      "eval_steps_per_second": 2.385,
      "step": 18
    },
    {
      "epoch": 0.0015153327750528373,
      "grad_norm": 1.3719432353973389,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0373,
      "step": 19
    },
    {
      "epoch": 0.0015950871316345655,
      "grad_norm": 0.40530410408973694,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0055,
      "step": 20
    },
    {
      "epoch": 0.0016748414882162938,
      "grad_norm": 4.31416130065918,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.1612,
      "step": 21
    },
    {
      "epoch": 0.0017545958447980222,
      "grad_norm": 0.035329561680555344,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.0005,
      "step": 22
    },
    {
      "epoch": 0.0018343502013797503,
      "grad_norm": 0.30401676893234253,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.0022,
      "step": 23
    },
    {
      "epoch": 0.0019141045579614787,
      "grad_norm": 0.19815795123577118,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0013,
      "step": 24
    },
    {
      "epoch": 0.001993858914543207,
      "grad_norm": 0.12030813843011856,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0008,
      "step": 25
    },
    {
      "epoch": 0.002073613271124935,
      "grad_norm": 0.025320129469037056,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.0003,
      "step": 26
    },
    {
      "epoch": 0.0021533676277066633,
      "grad_norm": 0.9278749823570251,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.0106,
      "step": 27
    },
    {
      "epoch": 0.0021533676277066633,
      "eval_loss": 0.09537636488676071,
      "eval_runtime": 553.5551,
      "eval_samples_per_second": 19.075,
      "eval_steps_per_second": 2.385,
      "step": 27
    },
    {
      "epoch": 0.002233121984288392,
      "grad_norm": 0.07682035863399506,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0008,
      "step": 28
    },
    {
      "epoch": 0.00231287634087012,
      "grad_norm": 5.222334384918213,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.1142,
      "step": 29
    },
    {
      "epoch": 0.002392630697451848,
      "grad_norm": 7.269686222076416,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.4306,
      "step": 30
    },
    {
      "epoch": 0.0024723850540335768,
      "grad_norm": 5.748641014099121,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.2281,
      "step": 31
    },
    {
      "epoch": 0.002552139410615305,
      "grad_norm": 2.5787816047668457,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.1349,
      "step": 32
    },
    {
      "epoch": 0.002631893767197033,
      "grad_norm": 3.364776611328125,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.0688,
      "step": 33
    },
    {
      "epoch": 0.002711648123778761,
      "grad_norm": 4.464049816131592,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.0255,
      "step": 34
    },
    {
      "epoch": 0.00279140248036049,
      "grad_norm": 1.2259021997451782,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0306,
      "step": 35
    },
    {
      "epoch": 0.002871156836942218,
      "grad_norm": 0.13717339932918549,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.0029,
      "step": 36
    },
    {
      "epoch": 0.002871156836942218,
      "eval_loss": 0.042516034096479416,
      "eval_runtime": 553.518,
      "eval_samples_per_second": 19.076,
      "eval_steps_per_second": 2.385,
      "step": 36
    },
    {
      "epoch": 0.002950911193523946,
      "grad_norm": 2.9602785110473633,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.1396,
      "step": 37
    },
    {
      "epoch": 0.0030306655501056746,
      "grad_norm": 0.29989227652549744,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.0094,
      "step": 38
    },
    {
      "epoch": 0.003110419906687403,
      "grad_norm": 1.6319737434387207,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.0541,
      "step": 39
    },
    {
      "epoch": 0.003190174263269131,
      "grad_norm": 1.022342324256897,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0178,
      "step": 40
    },
    {
      "epoch": 0.0032699286198508595,
      "grad_norm": 0.27077966928482056,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.0071,
      "step": 41
    },
    {
      "epoch": 0.0033496829764325877,
      "grad_norm": 2.3816652297973633,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0555,
      "step": 42
    },
    {
      "epoch": 0.003429437333014316,
      "grad_norm": 3.106501579284668,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.0806,
      "step": 43
    },
    {
      "epoch": 0.0035091916895960444,
      "grad_norm": 0.04690181091427803,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.001,
      "step": 44
    },
    {
      "epoch": 0.0035889460461777725,
      "grad_norm": 0.15731936693191528,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0036,
      "step": 45
    },
    {
      "epoch": 0.0035889460461777725,
      "eval_loss": 0.04225198179483414,
      "eval_runtime": 553.5138,
      "eval_samples_per_second": 19.076,
      "eval_steps_per_second": 2.385,
      "step": 45
    },
    {
      "epoch": 0.0036687004027595007,
      "grad_norm": 3.039454698562622,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0774,
      "step": 46
    },
    {
      "epoch": 0.003748454759341229,
      "grad_norm": 0.4984506666660309,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.0084,
      "step": 47
    },
    {
      "epoch": 0.0038282091159229574,
      "grad_norm": 0.03135956823825836,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.0005,
      "step": 48
    },
    {
      "epoch": 0.003907963472504686,
      "grad_norm": 3.206134796142578,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.0499,
      "step": 49
    },
    {
      "epoch": 0.003987717829086414,
      "grad_norm": 4.812526226043701,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.2402,
      "step": 50
    },
    {
      "epoch": 0.004067472185668142,
      "grad_norm": 0.019093716517090797,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.0003,
      "step": 51
    },
    {
      "epoch": 0.00414722654224987,
      "grad_norm": 6.016909122467041,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.1171,
      "step": 52
    },
    {
      "epoch": 0.0042269808988315985,
      "grad_norm": 3.237635850906372,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.0479,
      "step": 53
    },
    {
      "epoch": 0.004306735255413327,
      "grad_norm": 0.45389387011528015,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0071,
      "step": 54
    },
    {
      "epoch": 0.004306735255413327,
      "eval_loss": 0.039176907390356064,
      "eval_runtime": 553.614,
      "eval_samples_per_second": 19.073,
      "eval_steps_per_second": 2.384,
      "step": 54
    },
    {
      "epoch": 0.004386489611995055,
      "grad_norm": 1.7394068241119385,
      "learning_rate": 5e-05,
      "loss": 0.0313,
      "step": 55
    },
    {
      "epoch": 0.004466243968576784,
      "grad_norm": 1.723865270614624,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.0238,
      "step": 56
    },
    {
      "epoch": 0.004545998325158512,
      "grad_norm": 2.5933642387390137,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.0253,
      "step": 57
    },
    {
      "epoch": 0.00462575268174024,
      "grad_norm": 0.04176973178982735,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0006,
      "step": 58
    },
    {
      "epoch": 0.004705507038321968,
      "grad_norm": 3.8093903064727783,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.0485,
      "step": 59
    },
    {
      "epoch": 0.004785261394903696,
      "grad_norm": 4.592166900634766,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0812,
      "step": 60
    },
    {
      "epoch": 0.0048650157514854245,
      "grad_norm": 0.9173868298530579,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.0104,
      "step": 61
    },
    {
      "epoch": 0.0049447701080671536,
      "grad_norm": 1.9208635091781616,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.0213,
      "step": 62
    },
    {
      "epoch": 0.005024524464648882,
      "grad_norm": 2.4270222187042236,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.0342,
      "step": 63
    },
    {
      "epoch": 0.005024524464648882,
      "eval_loss": 0.02897912636399269,
      "eval_runtime": 553.584,
      "eval_samples_per_second": 19.074,
      "eval_steps_per_second": 2.384,
      "step": 63
    },
    {
      "epoch": 0.00510427882123061,
      "grad_norm": 0.15133006870746613,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0014,
      "step": 64
    },
    {
      "epoch": 0.005184033177812338,
      "grad_norm": 3.995213747024536,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.2232,
      "step": 65
    },
    {
      "epoch": 0.005263787534394066,
      "grad_norm": 0.10878176242113113,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0011,
      "step": 66
    },
    {
      "epoch": 0.005343541890975794,
      "grad_norm": 0.055173374712467194,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.0007,
      "step": 67
    },
    {
      "epoch": 0.005423296247557522,
      "grad_norm": 5.00130558013916,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.1167,
      "step": 68
    },
    {
      "epoch": 0.005503050604139251,
      "grad_norm": 0.32802918553352356,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.0026,
      "step": 69
    },
    {
      "epoch": 0.00558280496072098,
      "grad_norm": 0.10490323603153229,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0014,
      "step": 70
    },
    {
      "epoch": 0.005662559317302708,
      "grad_norm": 0.014080111868679523,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.0002,
      "step": 71
    },
    {
      "epoch": 0.005742313673884436,
      "grad_norm": 0.021097006276249886,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.0005,
      "step": 72
    },
    {
      "epoch": 0.005742313673884436,
      "eval_loss": 0.038278449326753616,
      "eval_runtime": 553.4245,
      "eval_samples_per_second": 19.079,
      "eval_steps_per_second": 2.385,
      "step": 72
    },
    {
      "epoch": 0.005822068030466164,
      "grad_norm": 0.014087294228374958,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0002,
      "step": 73
    },
    {
      "epoch": 0.005901822387047892,
      "grad_norm": 0.00338623090647161,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.0001,
      "step": 74
    },
    {
      "epoch": 0.005981576743629621,
      "grad_norm": 0.0011795306345447898,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.006061331100211349,
      "grad_norm": 5.963899612426758,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.0601,
      "step": 76
    },
    {
      "epoch": 0.0061410854567930774,
      "grad_norm": 0.037896182388067245,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.0006,
      "step": 77
    },
    {
      "epoch": 0.006220839813374806,
      "grad_norm": 0.24905402958393097,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.0033,
      "step": 78
    },
    {
      "epoch": 0.006300594169956534,
      "grad_norm": 0.02116982452571392,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.0003,
      "step": 79
    },
    {
      "epoch": 0.006380348526538262,
      "grad_norm": 0.001493555959314108,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.00646010288311999,
      "grad_norm": 0.04112343490123749,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.0002,
      "step": 81
    },
    {
      "epoch": 0.00646010288311999,
      "eval_loss": 0.03697933256626129,
      "eval_runtime": 553.647,
      "eval_samples_per_second": 19.072,
      "eval_steps_per_second": 2.384,
      "step": 81
    },
    {
      "epoch": 0.006539857239701719,
      "grad_norm": 0.852574348449707,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0052,
      "step": 82
    },
    {
      "epoch": 0.006619611596283447,
      "grad_norm": 5.428268909454346,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.1395,
      "step": 83
    },
    {
      "epoch": 0.006699365952865175,
      "grad_norm": 0.053005896508693695,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.0007,
      "step": 84
    },
    {
      "epoch": 0.0067791203094469035,
      "grad_norm": 1.3258788585662842,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0071,
      "step": 85
    },
    {
      "epoch": 0.006858874666028632,
      "grad_norm": 0.125382199883461,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.0009,
      "step": 86
    },
    {
      "epoch": 0.00693862902261036,
      "grad_norm": 0.025496359914541245,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.0003,
      "step": 87
    },
    {
      "epoch": 0.007018383379192089,
      "grad_norm": 7.4097113609313965,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.1218,
      "step": 88
    },
    {
      "epoch": 0.007098137735773817,
      "grad_norm": 0.0033981853630393744,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.0,
      "step": 89
    },
    {
      "epoch": 0.007177892092355545,
      "grad_norm": 0.38592103123664856,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0025,
      "step": 90
    },
    {
      "epoch": 0.007177892092355545,
      "eval_loss": 0.03521589934825897,
      "eval_runtime": 553.4928,
      "eval_samples_per_second": 19.077,
      "eval_steps_per_second": 2.385,
      "step": 90
    },
    {
      "epoch": 0.007257646448937273,
      "grad_norm": 0.0367887020111084,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0004,
      "step": 91
    },
    {
      "epoch": 0.007337400805519001,
      "grad_norm": 0.030135678127408028,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.0003,
      "step": 92
    },
    {
      "epoch": 0.0074171551621007295,
      "grad_norm": 0.30348286032676697,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.0022,
      "step": 93
    },
    {
      "epoch": 0.007496909518682458,
      "grad_norm": 0.007436178158968687,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.0001,
      "step": 94
    },
    {
      "epoch": 0.007576663875264187,
      "grad_norm": 3.1514601707458496,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.1337,
      "step": 95
    },
    {
      "epoch": 0.007656418231845915,
      "grad_norm": 4.589775085449219,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.2785,
      "step": 96
    },
    {
      "epoch": 0.007736172588427643,
      "grad_norm": 1.7154332399368286,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.0127,
      "step": 97
    },
    {
      "epoch": 0.007815926945009372,
      "grad_norm": 4.0604634284973145,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.0165,
      "step": 98
    },
    {
      "epoch": 0.0078956813015911,
      "grad_norm": 10.015667915344238,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.1357,
      "step": 99
    },
    {
      "epoch": 0.0078956813015911,
      "eval_loss": 0.03452092781662941,
      "eval_runtime": 553.3103,
      "eval_samples_per_second": 19.083,
      "eval_steps_per_second": 2.386,
      "step": 99
    },
    {
      "epoch": 0.007975435658172828,
      "grad_norm": 13.142882347106934,
      "learning_rate": 0.0,
      "loss": 0.1644,
      "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": 7.455967199782502e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}