{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07996801279488205,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007996801279488205,
      "grad_norm": 6.359498977661133,
      "learning_rate": 1e-05,
      "loss": 7.5787,
      "step": 1
    },
    {
      "epoch": 0.0007996801279488205,
      "eval_loss": 7.8461995124816895,
      "eval_runtime": 65.4027,
      "eval_samples_per_second": 16.1,
      "eval_steps_per_second": 2.018,
      "step": 1
    },
    {
      "epoch": 0.001599360255897641,
      "grad_norm": 6.157934188842773,
      "learning_rate": 2e-05,
      "loss": 7.6096,
      "step": 2
    },
    {
      "epoch": 0.0023990403838464614,
      "grad_norm": 5.621501445770264,
      "learning_rate": 3e-05,
      "loss": 7.8058,
      "step": 3
    },
    {
      "epoch": 0.003198720511795282,
      "grad_norm": 6.5738677978515625,
      "learning_rate": 4e-05,
      "loss": 8.0013,
      "step": 4
    },
    {
      "epoch": 0.003998400639744102,
      "grad_norm": 6.065139293670654,
      "learning_rate": 5e-05,
      "loss": 7.1979,
      "step": 5
    },
    {
      "epoch": 0.004798080767692923,
      "grad_norm": 6.060821533203125,
      "learning_rate": 6e-05,
      "loss": 6.8884,
      "step": 6
    },
    {
      "epoch": 0.005597760895641743,
      "grad_norm": 6.489013195037842,
      "learning_rate": 7e-05,
      "loss": 7.6614,
      "step": 7
    },
    {
      "epoch": 0.006397441023590564,
      "grad_norm": 7.009871959686279,
      "learning_rate": 8e-05,
      "loss": 7.0684,
      "step": 8
    },
    {
      "epoch": 0.007197121151539384,
      "grad_norm": 5.987380504608154,
      "learning_rate": 9e-05,
      "loss": 6.6335,
      "step": 9
    },
    {
      "epoch": 0.007197121151539384,
      "eval_loss": 6.301669597625732,
      "eval_runtime": 64.8317,
      "eval_samples_per_second": 16.242,
      "eval_steps_per_second": 2.036,
      "step": 9
    },
    {
      "epoch": 0.007996801279488205,
      "grad_norm": 7.33066463470459,
      "learning_rate": 0.0001,
      "loss": 6.4759,
      "step": 10
    },
    {
      "epoch": 0.008796481407437025,
      "grad_norm": 7.483557224273682,
      "learning_rate": 9.99695413509548e-05,
      "loss": 6.0371,
      "step": 11
    },
    {
      "epoch": 0.009596161535385846,
      "grad_norm": 5.732779026031494,
      "learning_rate": 9.987820251299122e-05,
      "loss": 5.0003,
      "step": 12
    },
    {
      "epoch": 0.010395841663334666,
      "grad_norm": 6.240601062774658,
      "learning_rate": 9.972609476841367e-05,
      "loss": 4.9242,
      "step": 13
    },
    {
      "epoch": 0.011195521791283487,
      "grad_norm": 6.761163234710693,
      "learning_rate": 9.951340343707852e-05,
      "loss": 4.9644,
      "step": 14
    },
    {
      "epoch": 0.011995201919232307,
      "grad_norm": 7.382585048675537,
      "learning_rate": 9.924038765061042e-05,
      "loss": 4.677,
      "step": 15
    },
    {
      "epoch": 0.012794882047181128,
      "grad_norm": 8.166483879089355,
      "learning_rate": 9.890738003669029e-05,
      "loss": 4.6715,
      "step": 16
    },
    {
      "epoch": 0.013594562175129948,
      "grad_norm": 8.002703666687012,
      "learning_rate": 9.851478631379982e-05,
      "loss": 4.3609,
      "step": 17
    },
    {
      "epoch": 0.014394242303078768,
      "grad_norm": 6.686599254608154,
      "learning_rate": 9.806308479691595e-05,
      "loss": 4.4421,
      "step": 18
    },
    {
      "epoch": 0.014394242303078768,
      "eval_loss": 4.342203140258789,
      "eval_runtime": 64.9139,
      "eval_samples_per_second": 16.221,
      "eval_steps_per_second": 2.033,
      "step": 18
    },
    {
      "epoch": 0.015193922431027589,
      "grad_norm": 6.648100852966309,
      "learning_rate": 9.755282581475769e-05,
      "loss": 4.4866,
      "step": 19
    },
    {
      "epoch": 0.01599360255897641,
      "grad_norm": 5.807915210723877,
      "learning_rate": 9.698463103929542e-05,
      "loss": 4.2142,
      "step": 20
    },
    {
      "epoch": 0.01679328268692523,
      "grad_norm": 5.9541096687316895,
      "learning_rate": 9.635919272833938e-05,
      "loss": 4.485,
      "step": 21
    },
    {
      "epoch": 0.01759296281487405,
      "grad_norm": 6.071778297424316,
      "learning_rate": 9.567727288213005e-05,
      "loss": 4.1178,
      "step": 22
    },
    {
      "epoch": 0.018392642942822873,
      "grad_norm": 5.7872185707092285,
      "learning_rate": 9.493970231495835e-05,
      "loss": 4.4135,
      "step": 23
    },
    {
      "epoch": 0.01919232307077169,
      "grad_norm": 6.7662858963012695,
      "learning_rate": 9.414737964294636e-05,
      "loss": 4.3118,
      "step": 24
    },
    {
      "epoch": 0.019992003198720514,
      "grad_norm": 5.508387088775635,
      "learning_rate": 9.330127018922194e-05,
      "loss": 4.1724,
      "step": 25
    },
    {
      "epoch": 0.020791683326669332,
      "grad_norm": 5.747828006744385,
      "learning_rate": 9.24024048078213e-05,
      "loss": 4.3605,
      "step": 26
    },
    {
      "epoch": 0.021591363454618154,
      "grad_norm": 6.477874279022217,
      "learning_rate": 9.145187862775209e-05,
      "loss": 4.1249,
      "step": 27
    },
    {
      "epoch": 0.021591363454618154,
      "eval_loss": 4.122183322906494,
      "eval_runtime": 65.0038,
      "eval_samples_per_second": 16.199,
      "eval_steps_per_second": 2.031,
      "step": 27
    },
    {
      "epoch": 0.022391043582566973,
      "grad_norm": 5.405932426452637,
      "learning_rate": 9.045084971874738e-05,
      "loss": 4.0658,
      "step": 28
    },
    {
      "epoch": 0.023190723710515795,
      "grad_norm": 6.421638488769531,
      "learning_rate": 8.940053768033609e-05,
      "loss": 4.4341,
      "step": 29
    },
    {
      "epoch": 0.023990403838464614,
      "grad_norm": 5.2888383865356445,
      "learning_rate": 8.83022221559489e-05,
      "loss": 4.1154,
      "step": 30
    },
    {
      "epoch": 0.024790083966413436,
      "grad_norm": 5.253130912780762,
      "learning_rate": 8.715724127386972e-05,
      "loss": 3.9418,
      "step": 31
    },
    {
      "epoch": 0.025589764094362255,
      "grad_norm": 4.973030090332031,
      "learning_rate": 8.596699001693255e-05,
      "loss": 3.9959,
      "step": 32
    },
    {
      "epoch": 0.026389444222311077,
      "grad_norm": 6.877074718475342,
      "learning_rate": 8.473291852294987e-05,
      "loss": 4.397,
      "step": 33
    },
    {
      "epoch": 0.027189124350259896,
      "grad_norm": 6.104552745819092,
      "learning_rate": 8.345653031794292e-05,
      "loss": 4.1429,
      "step": 34
    },
    {
      "epoch": 0.027988804478208718,
      "grad_norm": 6.565894603729248,
      "learning_rate": 8.213938048432697e-05,
      "loss": 3.7672,
      "step": 35
    },
    {
      "epoch": 0.028788484606157537,
      "grad_norm": 6.402747631072998,
      "learning_rate": 8.07830737662829e-05,
      "loss": 3.7757,
      "step": 36
    },
    {
      "epoch": 0.028788484606157537,
      "eval_loss": 3.980862855911255,
      "eval_runtime": 64.8672,
      "eval_samples_per_second": 16.233,
      "eval_steps_per_second": 2.035,
      "step": 36
    },
    {
      "epoch": 0.02958816473410636,
      "grad_norm": 5.338390827178955,
      "learning_rate": 7.938926261462366e-05,
      "loss": 3.7549,
      "step": 37
    },
    {
      "epoch": 0.030387844862055178,
      "grad_norm": 6.575376033782959,
      "learning_rate": 7.795964517353735e-05,
      "loss": 3.8059,
      "step": 38
    },
    {
      "epoch": 0.031187524990004,
      "grad_norm": 6.826125621795654,
      "learning_rate": 7.649596321166024e-05,
      "loss": 4.0356,
      "step": 39
    },
    {
      "epoch": 0.03198720511795282,
      "grad_norm": 6.553135395050049,
      "learning_rate": 7.500000000000001e-05,
      "loss": 3.7619,
      "step": 40
    },
    {
      "epoch": 0.03278688524590164,
      "grad_norm": 7.697059631347656,
      "learning_rate": 7.347357813929454e-05,
      "loss": 3.9946,
      "step": 41
    },
    {
      "epoch": 0.03358656537385046,
      "grad_norm": 5.825917720794678,
      "learning_rate": 7.191855733945387e-05,
      "loss": 3.9097,
      "step": 42
    },
    {
      "epoch": 0.03438624550179928,
      "grad_norm": 5.886120796203613,
      "learning_rate": 7.033683215379002e-05,
      "loss": 3.6738,
      "step": 43
    },
    {
      "epoch": 0.0351859256297481,
      "grad_norm": 6.294511795043945,
      "learning_rate": 6.873032967079561e-05,
      "loss": 4.0373,
      "step": 44
    },
    {
      "epoch": 0.03598560575769692,
      "grad_norm": 6.388889789581299,
      "learning_rate": 6.710100716628344e-05,
      "loss": 3.7921,
      "step": 45
    },
    {
      "epoch": 0.03598560575769692,
      "eval_loss": 3.93093204498291,
      "eval_runtime": 64.8235,
      "eval_samples_per_second": 16.244,
      "eval_steps_per_second": 2.036,
      "step": 45
    },
    {
      "epoch": 0.036785285885645745,
      "grad_norm": 5.413031578063965,
      "learning_rate": 6.545084971874738e-05,
      "loss": 3.8995,
      "step": 46
    },
    {
      "epoch": 0.03758496601359456,
      "grad_norm": 4.84060525894165,
      "learning_rate": 6.378186779084995e-05,
      "loss": 3.9409,
      "step": 47
    },
    {
      "epoch": 0.03838464614154338,
      "grad_norm": 5.393630504608154,
      "learning_rate": 6.209609477998338e-05,
      "loss": 3.8495,
      "step": 48
    },
    {
      "epoch": 0.039184326269492205,
      "grad_norm": 5.282654762268066,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 3.7573,
      "step": 49
    },
    {
      "epoch": 0.03998400639744103,
      "grad_norm": 4.579346179962158,
      "learning_rate": 5.868240888334653e-05,
      "loss": 4.0155,
      "step": 50
    },
    {
      "epoch": 0.04078368652538984,
      "grad_norm": 5.972344875335693,
      "learning_rate": 5.695865504800327e-05,
      "loss": 3.9595,
      "step": 51
    },
    {
      "epoch": 0.041583366653338664,
      "grad_norm": 6.893924713134766,
      "learning_rate": 5.522642316338268e-05,
      "loss": 3.9452,
      "step": 52
    },
    {
      "epoch": 0.04238304678128749,
      "grad_norm": 5.096782684326172,
      "learning_rate": 5.348782368720626e-05,
      "loss": 3.5734,
      "step": 53
    },
    {
      "epoch": 0.04318272690923631,
      "grad_norm": 5.061729431152344,
      "learning_rate": 5.174497483512506e-05,
      "loss": 3.52,
      "step": 54
    },
    {
      "epoch": 0.04318272690923631,
      "eval_loss": 3.8698742389678955,
      "eval_runtime": 64.9487,
      "eval_samples_per_second": 16.213,
      "eval_steps_per_second": 2.032,
      "step": 54
    },
    {
      "epoch": 0.043982407037185124,
      "grad_norm": 5.499988079071045,
      "learning_rate": 5e-05,
      "loss": 4.0566,
      "step": 55
    },
    {
      "epoch": 0.044782087165133946,
      "grad_norm": 5.24320125579834,
      "learning_rate": 4.825502516487497e-05,
      "loss": 3.736,
      "step": 56
    },
    {
      "epoch": 0.04558176729308277,
      "grad_norm": 4.890809535980225,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 3.827,
      "step": 57
    },
    {
      "epoch": 0.04638144742103159,
      "grad_norm": 5.598406791687012,
      "learning_rate": 4.477357683661734e-05,
      "loss": 3.5459,
      "step": 58
    },
    {
      "epoch": 0.047181127548980406,
      "grad_norm": 5.470479965209961,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 3.7696,
      "step": 59
    },
    {
      "epoch": 0.04798080767692923,
      "grad_norm": 6.037547588348389,
      "learning_rate": 4.131759111665349e-05,
      "loss": 4.1592,
      "step": 60
    },
    {
      "epoch": 0.04878048780487805,
      "grad_norm": 5.132472038269043,
      "learning_rate": 3.960441545911204e-05,
      "loss": 3.7845,
      "step": 61
    },
    {
      "epoch": 0.04958016793282687,
      "grad_norm": 6.724290370941162,
      "learning_rate": 3.790390522001662e-05,
      "loss": 3.7481,
      "step": 62
    },
    {
      "epoch": 0.05037984806077569,
      "grad_norm": 4.897818565368652,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 3.8861,
      "step": 63
    },
    {
      "epoch": 0.05037984806077569,
      "eval_loss": 3.841887950897217,
      "eval_runtime": 64.8922,
      "eval_samples_per_second": 16.227,
      "eval_steps_per_second": 2.034,
      "step": 63
    },
    {
      "epoch": 0.05117952818872451,
      "grad_norm": 5.615442276000977,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 4.1557,
      "step": 64
    },
    {
      "epoch": 0.05197920831667333,
      "grad_norm": 5.482508182525635,
      "learning_rate": 3.289899283371657e-05,
      "loss": 4.2472,
      "step": 65
    },
    {
      "epoch": 0.052778888444622155,
      "grad_norm": 8.17457103729248,
      "learning_rate": 3.12696703292044e-05,
      "loss": 3.8963,
      "step": 66
    },
    {
      "epoch": 0.05357856857257097,
      "grad_norm": 6.345828533172607,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 4.0517,
      "step": 67
    },
    {
      "epoch": 0.05437824870051979,
      "grad_norm": 4.803496360778809,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 3.5726,
      "step": 68
    },
    {
      "epoch": 0.055177928828468614,
      "grad_norm": 4.9716997146606445,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 3.7366,
      "step": 69
    },
    {
      "epoch": 0.055977608956417436,
      "grad_norm": 5.260076999664307,
      "learning_rate": 2.500000000000001e-05,
      "loss": 3.8737,
      "step": 70
    },
    {
      "epoch": 0.05677728908436625,
      "grad_norm": 5.536251068115234,
      "learning_rate": 2.350403678833976e-05,
      "loss": 3.7522,
      "step": 71
    },
    {
      "epoch": 0.057576969212315074,
      "grad_norm": 4.966779708862305,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 3.9975,
      "step": 72
    },
    {
      "epoch": 0.057576969212315074,
      "eval_loss": 3.810777187347412,
      "eval_runtime": 64.8369,
      "eval_samples_per_second": 16.241,
      "eval_steps_per_second": 2.036,
      "step": 72
    },
    {
      "epoch": 0.058376649340263896,
      "grad_norm": 5.360210418701172,
      "learning_rate": 2.061073738537635e-05,
      "loss": 3.4565,
      "step": 73
    },
    {
      "epoch": 0.05917632946821272,
      "grad_norm": 5.443131446838379,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 4.1542,
      "step": 74
    },
    {
      "epoch": 0.059976009596161534,
      "grad_norm": 5.148866653442383,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 3.8738,
      "step": 75
    },
    {
      "epoch": 0.060775689724110356,
      "grad_norm": 5.219843864440918,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 3.8506,
      "step": 76
    },
    {
      "epoch": 0.06157536985205918,
      "grad_norm": 4.833649635314941,
      "learning_rate": 1.526708147705013e-05,
      "loss": 3.6357,
      "step": 77
    },
    {
      "epoch": 0.062375049980008,
      "grad_norm": 5.183854103088379,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 3.8796,
      "step": 78
    },
    {
      "epoch": 0.06317473010795682,
      "grad_norm": 4.822139263153076,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 3.8039,
      "step": 79
    },
    {
      "epoch": 0.06397441023590564,
      "grad_norm": 5.325417518615723,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 3.7121,
      "step": 80
    },
    {
      "epoch": 0.06477409036385445,
      "grad_norm": 5.68792200088501,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 3.8676,
      "step": 81
    },
    {
      "epoch": 0.06477409036385445,
      "eval_loss": 3.790825605392456,
      "eval_runtime": 64.9998,
      "eval_samples_per_second": 16.2,
      "eval_steps_per_second": 2.031,
      "step": 81
    },
    {
      "epoch": 0.06557377049180328,
      "grad_norm": 4.972930908203125,
      "learning_rate": 9.549150281252633e-06,
      "loss": 3.8641,
      "step": 82
    },
    {
      "epoch": 0.0663734506197521,
      "grad_norm": 5.177651882171631,
      "learning_rate": 8.548121372247918e-06,
      "loss": 3.9937,
      "step": 83
    },
    {
      "epoch": 0.06717313074770093,
      "grad_norm": 5.202006816864014,
      "learning_rate": 7.597595192178702e-06,
      "loss": 3.8965,
      "step": 84
    },
    {
      "epoch": 0.06797281087564974,
      "grad_norm": 5.003640174865723,
      "learning_rate": 6.698729810778065e-06,
      "loss": 3.6745,
      "step": 85
    },
    {
      "epoch": 0.06877249100359856,
      "grad_norm": 5.02064847946167,
      "learning_rate": 5.852620357053651e-06,
      "loss": 4.0451,
      "step": 86
    },
    {
      "epoch": 0.06957217113154739,
      "grad_norm": 6.714007377624512,
      "learning_rate": 5.060297685041659e-06,
      "loss": 3.5304,
      "step": 87
    },
    {
      "epoch": 0.0703718512594962,
      "grad_norm": 4.566380500793457,
      "learning_rate": 4.322727117869951e-06,
      "loss": 3.7025,
      "step": 88
    },
    {
      "epoch": 0.07117153138744502,
      "grad_norm": 4.762030601501465,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 3.5985,
      "step": 89
    },
    {
      "epoch": 0.07197121151539385,
      "grad_norm": 4.6840314865112305,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 3.619,
      "step": 90
    },
    {
      "epoch": 0.07197121151539385,
      "eval_loss": 3.782498598098755,
      "eval_runtime": 64.88,
      "eval_samples_per_second": 16.23,
      "eval_steps_per_second": 2.035,
      "step": 90
    },
    {
      "epoch": 0.07277089164334266,
      "grad_norm": 5.267907619476318,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 3.6987,
      "step": 91
    },
    {
      "epoch": 0.07357057177129149,
      "grad_norm": 4.929231643676758,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 3.5549,
      "step": 92
    },
    {
      "epoch": 0.0743702518992403,
      "grad_norm": 4.731836795806885,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 3.7003,
      "step": 93
    },
    {
      "epoch": 0.07516993202718912,
      "grad_norm": 5.483896255493164,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 3.7144,
      "step": 94
    },
    {
      "epoch": 0.07596961215513795,
      "grad_norm": 4.872249603271484,
      "learning_rate": 7.596123493895991e-07,
      "loss": 3.985,
      "step": 95
    },
    {
      "epoch": 0.07676929228308677,
      "grad_norm": 4.845506191253662,
      "learning_rate": 4.865965629214819e-07,
      "loss": 4.1145,
      "step": 96
    },
    {
      "epoch": 0.07756897241103558,
      "grad_norm": 5.09095573425293,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 4.1055,
      "step": 97
    },
    {
      "epoch": 0.07836865253898441,
      "grad_norm": 5.559736728668213,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 3.6654,
      "step": 98
    },
    {
      "epoch": 0.07916833266693322,
      "grad_norm": 5.160393714904785,
      "learning_rate": 3.04586490452119e-08,
      "loss": 3.4554,
      "step": 99
    },
    {
      "epoch": 0.07916833266693322,
      "eval_loss": 3.7806127071380615,
      "eval_runtime": 64.7968,
      "eval_samples_per_second": 16.251,
      "eval_steps_per_second": 2.037,
      "step": 99
    },
    {
      "epoch": 0.07996801279488205,
      "grad_norm": 5.4672346115112305,
      "learning_rate": 0.0,
      "loss": 3.8669,
      "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": 7.41887686213632e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}