{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005402047375955487,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.402047375955487e-05,
      "grad_norm": 1.061699628829956,
      "learning_rate": 1e-05,
      "loss": 2.3561,
      "step": 1
    },
    {
      "epoch": 5.402047375955487e-05,
      "eval_loss": 2.3112149238586426,
      "eval_runtime": 3362.2667,
      "eval_samples_per_second": 4.636,
      "eval_steps_per_second": 0.58,
      "step": 1
    },
    {
      "epoch": 0.00010804094751910974,
      "grad_norm": 1.3118318319320679,
      "learning_rate": 2e-05,
      "loss": 2.3782,
      "step": 2
    },
    {
      "epoch": 0.00016206142127866461,
      "grad_norm": 1.1144564151763916,
      "learning_rate": 3e-05,
      "loss": 2.2446,
      "step": 3
    },
    {
      "epoch": 0.00021608189503821948,
      "grad_norm": 1.174940824508667,
      "learning_rate": 4e-05,
      "loss": 2.2652,
      "step": 4
    },
    {
      "epoch": 0.00027010236879777437,
      "grad_norm": 1.4532380104064941,
      "learning_rate": 5e-05,
      "loss": 2.5352,
      "step": 5
    },
    {
      "epoch": 0.00032412284255732923,
      "grad_norm": 1.2197051048278809,
      "learning_rate": 6e-05,
      "loss": 2.2264,
      "step": 6
    },
    {
      "epoch": 0.0003781433163168841,
      "grad_norm": 1.1164822578430176,
      "learning_rate": 7e-05,
      "loss": 2.142,
      "step": 7
    },
    {
      "epoch": 0.00043216379007643895,
      "grad_norm": 1.55741548538208,
      "learning_rate": 8e-05,
      "loss": 2.4181,
      "step": 8
    },
    {
      "epoch": 0.0004861842638359938,
      "grad_norm": 1.3686168193817139,
      "learning_rate": 9e-05,
      "loss": 2.3264,
      "step": 9
    },
    {
      "epoch": 0.0004861842638359938,
      "eval_loss": 1.989229440689087,
      "eval_runtime": 3370.5193,
      "eval_samples_per_second": 4.625,
      "eval_steps_per_second": 0.578,
      "step": 9
    },
    {
      "epoch": 0.0005402047375955487,
      "grad_norm": 1.062412142753601,
      "learning_rate": 0.0001,
      "loss": 1.8345,
      "step": 10
    },
    {
      "epoch": 0.0005942252113551035,
      "grad_norm": 1.1697839498519897,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.9388,
      "step": 11
    },
    {
      "epoch": 0.0006482456851146585,
      "grad_norm": 1.3678555488586426,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.0119,
      "step": 12
    },
    {
      "epoch": 0.0007022661588742134,
      "grad_norm": 1.381777048110962,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.6446,
      "step": 13
    },
    {
      "epoch": 0.0007562866326337682,
      "grad_norm": 1.0860157012939453,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.6745,
      "step": 14
    },
    {
      "epoch": 0.0008103071063933231,
      "grad_norm": 1.466055154800415,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.8303,
      "step": 15
    },
    {
      "epoch": 0.0008643275801528779,
      "grad_norm": 1.3503963947296143,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.7245,
      "step": 16
    },
    {
      "epoch": 0.0009183480539124328,
      "grad_norm": 1.4205446243286133,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.7683,
      "step": 17
    },
    {
      "epoch": 0.0009723685276719876,
      "grad_norm": 1.3751708269119263,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.7489,
      "step": 18
    },
    {
      "epoch": 0.0009723685276719876,
      "eval_loss": 1.6231409311294556,
      "eval_runtime": 3370.1387,
      "eval_samples_per_second": 4.626,
      "eval_steps_per_second": 0.578,
      "step": 18
    },
    {
      "epoch": 0.0010263890014315425,
      "grad_norm": 1.411476969718933,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.5006,
      "step": 19
    },
    {
      "epoch": 0.0010804094751910975,
      "grad_norm": 1.5040185451507568,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.743,
      "step": 20
    },
    {
      "epoch": 0.0011344299489506524,
      "grad_norm": 1.4046059846878052,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.7263,
      "step": 21
    },
    {
      "epoch": 0.001188450422710207,
      "grad_norm": 1.1052309274673462,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.5053,
      "step": 22
    },
    {
      "epoch": 0.001242470896469762,
      "grad_norm": 0.9669276475906372,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.5642,
      "step": 23
    },
    {
      "epoch": 0.001296491370229317,
      "grad_norm": 1.1981260776519775,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.572,
      "step": 24
    },
    {
      "epoch": 0.0013505118439888718,
      "grad_norm": 1.1273926496505737,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.6082,
      "step": 25
    },
    {
      "epoch": 0.0014045323177484267,
      "grad_norm": 1.089220404624939,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.4618,
      "step": 26
    },
    {
      "epoch": 0.0014585527915079814,
      "grad_norm": 0.9762293100357056,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.6464,
      "step": 27
    },
    {
      "epoch": 0.0014585527915079814,
      "eval_loss": 1.5239306688308716,
      "eval_runtime": 3370.1015,
      "eval_samples_per_second": 4.626,
      "eval_steps_per_second": 0.578,
      "step": 27
    },
    {
      "epoch": 0.0015125732652675364,
      "grad_norm": 0.9106154441833496,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.3052,
      "step": 28
    },
    {
      "epoch": 0.0015665937390270913,
      "grad_norm": 0.9534875750541687,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.5035,
      "step": 29
    },
    {
      "epoch": 0.0016206142127866462,
      "grad_norm": 0.9660364389419556,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.4769,
      "step": 30
    },
    {
      "epoch": 0.0016746346865462011,
      "grad_norm": 1.024480938911438,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.5453,
      "step": 31
    },
    {
      "epoch": 0.0017286551603057558,
      "grad_norm": 0.892098069190979,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.3765,
      "step": 32
    },
    {
      "epoch": 0.0017826756340653107,
      "grad_norm": 1.0651084184646606,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.4993,
      "step": 33
    },
    {
      "epoch": 0.0018366961078248656,
      "grad_norm": 0.9315266013145447,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.5011,
      "step": 34
    },
    {
      "epoch": 0.0018907165815844206,
      "grad_norm": 1.0802898406982422,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.6234,
      "step": 35
    },
    {
      "epoch": 0.0019447370553439753,
      "grad_norm": 1.2187426090240479,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.5154,
      "step": 36
    },
    {
      "epoch": 0.0019447370553439753,
      "eval_loss": 1.4882609844207764,
      "eval_runtime": 3370.139,
      "eval_samples_per_second": 4.626,
      "eval_steps_per_second": 0.578,
      "step": 36
    },
    {
      "epoch": 0.0019987575291035304,
      "grad_norm": 1.2731837034225464,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.4256,
      "step": 37
    },
    {
      "epoch": 0.002052778002863085,
      "grad_norm": 0.9401973485946655,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.4064,
      "step": 38
    },
    {
      "epoch": 0.00210679847662264,
      "grad_norm": 1.1949783563613892,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.4051,
      "step": 39
    },
    {
      "epoch": 0.002160818950382195,
      "grad_norm": 1.3753553628921509,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.2702,
      "step": 40
    },
    {
      "epoch": 0.0022148394241417496,
      "grad_norm": 1.9385082721710205,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.5789,
      "step": 41
    },
    {
      "epoch": 0.0022688598979013048,
      "grad_norm": 1.170527696609497,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.4807,
      "step": 42
    },
    {
      "epoch": 0.0023228803716608595,
      "grad_norm": 1.255044937133789,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.4827,
      "step": 43
    },
    {
      "epoch": 0.002376900845420414,
      "grad_norm": 1.1622134447097778,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.4609,
      "step": 44
    },
    {
      "epoch": 0.0024309213191799693,
      "grad_norm": 1.0290035009384155,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.4929,
      "step": 45
    },
    {
      "epoch": 0.0024309213191799693,
      "eval_loss": 1.4531553983688354,
      "eval_runtime": 3370.0357,
      "eval_samples_per_second": 4.626,
      "eval_steps_per_second": 0.578,
      "step": 45
    },
    {
      "epoch": 0.002484941792939524,
      "grad_norm": 0.9841757416725159,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.3785,
      "step": 46
    },
    {
      "epoch": 0.002538962266699079,
      "grad_norm": 1.1201504468917847,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.4038,
      "step": 47
    },
    {
      "epoch": 0.002592982740458634,
      "grad_norm": 1.2595245838165283,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.411,
      "step": 48
    },
    {
      "epoch": 0.0026470032142181885,
      "grad_norm": 0.9506502747535706,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.3282,
      "step": 49
    },
    {
      "epoch": 0.0027010236879777437,
      "grad_norm": 1.121146559715271,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.4374,
      "step": 50
    },
    {
      "epoch": 0.0027550441617372984,
      "grad_norm": 1.039516568183899,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.4768,
      "step": 51
    },
    {
      "epoch": 0.0028090646354968535,
      "grad_norm": 0.9859927296638489,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.4673,
      "step": 52
    },
    {
      "epoch": 0.002863085109256408,
      "grad_norm": 0.9465391635894775,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.5106,
      "step": 53
    },
    {
      "epoch": 0.002917105583015963,
      "grad_norm": 1.1751928329467773,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.3325,
      "step": 54
    },
    {
      "epoch": 0.002917105583015963,
      "eval_loss": 1.4378173351287842,
      "eval_runtime": 3370.1952,
      "eval_samples_per_second": 4.626,
      "eval_steps_per_second": 0.578,
      "step": 54
    },
    {
      "epoch": 0.002971126056775518,
      "grad_norm": 1.083316683769226,
      "learning_rate": 5e-05,
      "loss": 1.4346,
      "step": 55
    },
    {
      "epoch": 0.0030251465305350727,
      "grad_norm": 1.12709641456604,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.51,
      "step": 56
    },
    {
      "epoch": 0.003079167004294628,
      "grad_norm": 1.2147878408432007,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.6,
      "step": 57
    },
    {
      "epoch": 0.0031331874780541826,
      "grad_norm": 1.0804308652877808,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.4287,
      "step": 58
    },
    {
      "epoch": 0.0031872079518137373,
      "grad_norm": 0.9167782068252563,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.4368,
      "step": 59
    },
    {
      "epoch": 0.0032412284255732924,
      "grad_norm": 1.4328035116195679,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.222,
      "step": 60
    },
    {
      "epoch": 0.003295248899332847,
      "grad_norm": 2.311690330505371,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.6455,
      "step": 61
    },
    {
      "epoch": 0.0033492693730924022,
      "grad_norm": 0.9619605541229248,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.2385,
      "step": 62
    },
    {
      "epoch": 0.003403289846851957,
      "grad_norm": 1.0867960453033447,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.2282,
      "step": 63
    },
    {
      "epoch": 0.003403289846851957,
      "eval_loss": 1.4248102903366089,
      "eval_runtime": 3370.2237,
      "eval_samples_per_second": 4.626,
      "eval_steps_per_second": 0.578,
      "step": 63
    },
    {
      "epoch": 0.0034573103206115116,
      "grad_norm": 1.1048400402069092,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.4752,
      "step": 64
    },
    {
      "epoch": 0.0035113307943710668,
      "grad_norm": 0.9802713990211487,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.4726,
      "step": 65
    },
    {
      "epoch": 0.0035653512681306215,
      "grad_norm": 0.8620728850364685,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.2183,
      "step": 66
    },
    {
      "epoch": 0.003619371741890176,
      "grad_norm": 0.8618316054344177,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.3536,
      "step": 67
    },
    {
      "epoch": 0.0036733922156497313,
      "grad_norm": 0.8729385137557983,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.3593,
      "step": 68
    },
    {
      "epoch": 0.003727412689409286,
      "grad_norm": 0.898639976978302,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.4913,
      "step": 69
    },
    {
      "epoch": 0.003781433163168841,
      "grad_norm": 0.9885318279266357,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.4738,
      "step": 70
    },
    {
      "epoch": 0.003835453636928396,
      "grad_norm": 0.9679330587387085,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.5127,
      "step": 71
    },
    {
      "epoch": 0.0038894741106879505,
      "grad_norm": 0.8212774395942688,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.3274,
      "step": 72
    },
    {
      "epoch": 0.0038894741106879505,
      "eval_loss": 1.4179484844207764,
      "eval_runtime": 3370.1941,
      "eval_samples_per_second": 4.626,
      "eval_steps_per_second": 0.578,
      "step": 72
    },
    {
      "epoch": 0.003943494584447506,
      "grad_norm": 1.0723795890808105,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.5697,
      "step": 73
    },
    {
      "epoch": 0.003997515058207061,
      "grad_norm": 0.9993148446083069,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.3406,
      "step": 74
    },
    {
      "epoch": 0.004051535531966615,
      "grad_norm": 0.974729061126709,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.4961,
      "step": 75
    },
    {
      "epoch": 0.00410555600572617,
      "grad_norm": 1.0231529474258423,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.4926,
      "step": 76
    },
    {
      "epoch": 0.004159576479485725,
      "grad_norm": 0.9222609400749207,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.4712,
      "step": 77
    },
    {
      "epoch": 0.00421359695324528,
      "grad_norm": 1.1976020336151123,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.5043,
      "step": 78
    },
    {
      "epoch": 0.004267617427004835,
      "grad_norm": 1.4451897144317627,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.3476,
      "step": 79
    },
    {
      "epoch": 0.00432163790076439,
      "grad_norm": 1.0686806440353394,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.492,
      "step": 80
    },
    {
      "epoch": 0.004375658374523945,
      "grad_norm": 0.9768352508544922,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.413,
      "step": 81
    },
    {
      "epoch": 0.004375658374523945,
      "eval_loss": 1.4142619371414185,
      "eval_runtime": 3370.8773,
      "eval_samples_per_second": 4.625,
      "eval_steps_per_second": 0.578,
      "step": 81
    },
    {
      "epoch": 0.004429678848283499,
      "grad_norm": 0.9269257187843323,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.4816,
      "step": 82
    },
    {
      "epoch": 0.004483699322043054,
      "grad_norm": 1.01197350025177,
      "learning_rate": 8.548121372247918e-06,
      "loss": 1.4349,
      "step": 83
    },
    {
      "epoch": 0.0045377197958026095,
      "grad_norm": 0.8954335451126099,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.4416,
      "step": 84
    },
    {
      "epoch": 0.004591740269562164,
      "grad_norm": 0.8160538077354431,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.2484,
      "step": 85
    },
    {
      "epoch": 0.004645760743321719,
      "grad_norm": 0.9298813343048096,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.479,
      "step": 86
    },
    {
      "epoch": 0.004699781217081274,
      "grad_norm": 0.9313685297966003,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.3051,
      "step": 87
    },
    {
      "epoch": 0.004753801690840828,
      "grad_norm": 1.6026023626327515,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.4277,
      "step": 88
    },
    {
      "epoch": 0.0048078221646003835,
      "grad_norm": 0.8113055229187012,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.4505,
      "step": 89
    },
    {
      "epoch": 0.004861842638359939,
      "grad_norm": 0.9440635442733765,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.4504,
      "step": 90
    },
    {
      "epoch": 0.004861842638359939,
      "eval_loss": 1.4125441312789917,
      "eval_runtime": 3370.8329,
      "eval_samples_per_second": 4.625,
      "eval_steps_per_second": 0.578,
      "step": 90
    },
    {
      "epoch": 0.004915863112119493,
      "grad_norm": 0.9242429733276367,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.3518,
      "step": 91
    },
    {
      "epoch": 0.004969883585879048,
      "grad_norm": 0.8084946870803833,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.3352,
      "step": 92
    },
    {
      "epoch": 0.005023904059638603,
      "grad_norm": 0.8405563235282898,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.4091,
      "step": 93
    },
    {
      "epoch": 0.005077924533398158,
      "grad_norm": 0.9099767804145813,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.5132,
      "step": 94
    },
    {
      "epoch": 0.0051319450071577125,
      "grad_norm": 0.9288073182106018,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.3346,
      "step": 95
    },
    {
      "epoch": 0.005185965480917268,
      "grad_norm": 0.9403652548789978,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.2107,
      "step": 96
    },
    {
      "epoch": 0.005239985954676823,
      "grad_norm": 0.8419960141181946,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.2498,
      "step": 97
    },
    {
      "epoch": 0.005294006428436377,
      "grad_norm": 1.1825482845306396,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.4782,
      "step": 98
    },
    {
      "epoch": 0.005348026902195932,
      "grad_norm": 0.9216974377632141,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.3119,
      "step": 99
    },
    {
      "epoch": 0.005348026902195932,
      "eval_loss": 1.4122796058654785,
      "eval_runtime": 3371.9788,
      "eval_samples_per_second": 4.623,
      "eval_steps_per_second": 0.578,
      "step": 99
    },
    {
      "epoch": 0.005402047375955487,
      "grad_norm": 1.1032953262329102,
      "learning_rate": 0.0,
      "loss": 1.399,
      "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": 1.4652273850318848e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}