{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.008210517673139291,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.210517673139291e-05,
      "grad_norm": 1.3583542108535767,
      "learning_rate": 1e-05,
      "loss": 1.8764,
      "step": 1
    },
    {
      "epoch": 8.210517673139291e-05,
      "eval_loss": 2.0353238582611084,
      "eval_runtime": 1410.7367,
      "eval_samples_per_second": 7.271,
      "eval_steps_per_second": 0.909,
      "step": 1
    },
    {
      "epoch": 0.00016421035346278582,
      "grad_norm": 0.9403209686279297,
      "learning_rate": 2e-05,
      "loss": 2.2456,
      "step": 2
    },
    {
      "epoch": 0.00024631553019417875,
      "grad_norm": 1.0389089584350586,
      "learning_rate": 3e-05,
      "loss": 2.1613,
      "step": 3
    },
    {
      "epoch": 0.00032842070692557163,
      "grad_norm": 1.2952375411987305,
      "learning_rate": 4e-05,
      "loss": 2.067,
      "step": 4
    },
    {
      "epoch": 0.00041052588365696457,
      "grad_norm": 1.1285730600357056,
      "learning_rate": 5e-05,
      "loss": 2.0318,
      "step": 5
    },
    {
      "epoch": 0.0004926310603883575,
      "grad_norm": 1.138143539428711,
      "learning_rate": 6e-05,
      "loss": 1.9186,
      "step": 6
    },
    {
      "epoch": 0.0005747362371197504,
      "grad_norm": 1.3923189640045166,
      "learning_rate": 7e-05,
      "loss": 2.0116,
      "step": 7
    },
    {
      "epoch": 0.0006568414138511433,
      "grad_norm": 1.3150489330291748,
      "learning_rate": 8e-05,
      "loss": 1.9182,
      "step": 8
    },
    {
      "epoch": 0.0007389465905825362,
      "grad_norm": 1.29096257686615,
      "learning_rate": 9e-05,
      "loss": 1.7837,
      "step": 9
    },
    {
      "epoch": 0.0007389465905825362,
      "eval_loss": 1.8958570957183838,
      "eval_runtime": 1414.3183,
      "eval_samples_per_second": 7.252,
      "eval_steps_per_second": 0.907,
      "step": 9
    },
    {
      "epoch": 0.0008210517673139291,
      "grad_norm": 1.190146565437317,
      "learning_rate": 0.0001,
      "loss": 1.8945,
      "step": 10
    },
    {
      "epoch": 0.0009031569440453221,
      "grad_norm": 1.033207654953003,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.5682,
      "step": 11
    },
    {
      "epoch": 0.000985262120776715,
      "grad_norm": 1.2630507946014404,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.9524,
      "step": 12
    },
    {
      "epoch": 0.0010673672975081078,
      "grad_norm": 0.8601189255714417,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.7826,
      "step": 13
    },
    {
      "epoch": 0.0011494724742395009,
      "grad_norm": 0.6138840913772583,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.9201,
      "step": 14
    },
    {
      "epoch": 0.0012315776509708937,
      "grad_norm": 0.9678861498832703,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.6454,
      "step": 15
    },
    {
      "epoch": 0.0013136828277022865,
      "grad_norm": 0.8818705677986145,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.9118,
      "step": 16
    },
    {
      "epoch": 0.0013957880044336796,
      "grad_norm": 0.8292626738548279,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.8557,
      "step": 17
    },
    {
      "epoch": 0.0014778931811650724,
      "grad_norm": 0.7435213327407837,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.7706,
      "step": 18
    },
    {
      "epoch": 0.0014778931811650724,
      "eval_loss": 1.6920524835586548,
      "eval_runtime": 1413.5511,
      "eval_samples_per_second": 7.256,
      "eval_steps_per_second": 0.908,
      "step": 18
    },
    {
      "epoch": 0.0015599983578964654,
      "grad_norm": 0.964107096195221,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.3101,
      "step": 19
    },
    {
      "epoch": 0.0016421035346278583,
      "grad_norm": 0.7826007008552551,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.6482,
      "step": 20
    },
    {
      "epoch": 0.001724208711359251,
      "grad_norm": 0.8321696519851685,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.825,
      "step": 21
    },
    {
      "epoch": 0.0018063138880906441,
      "grad_norm": 1.1344892978668213,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.091,
      "step": 22
    },
    {
      "epoch": 0.001888419064822037,
      "grad_norm": 0.885356605052948,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.5937,
      "step": 23
    },
    {
      "epoch": 0.00197052424155343,
      "grad_norm": 1.1985459327697754,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.5686,
      "step": 24
    },
    {
      "epoch": 0.002052629418284823,
      "grad_norm": 0.807948648929596,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.194,
      "step": 25
    },
    {
      "epoch": 0.0021347345950162157,
      "grad_norm": 0.6608679294586182,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.8281,
      "step": 26
    },
    {
      "epoch": 0.0022168397717476085,
      "grad_norm": 0.868128776550293,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.7768,
      "step": 27
    },
    {
      "epoch": 0.0022168397717476085,
      "eval_loss": 1.5856971740722656,
      "eval_runtime": 1412.7068,
      "eval_samples_per_second": 7.261,
      "eval_steps_per_second": 0.908,
      "step": 27
    },
    {
      "epoch": 0.0022989449484790017,
      "grad_norm": 0.7959260940551758,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.8639,
      "step": 28
    },
    {
      "epoch": 0.0023810501252103946,
      "grad_norm": 0.8122575879096985,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.7216,
      "step": 29
    },
    {
      "epoch": 0.0024631553019417874,
      "grad_norm": 0.9101079106330872,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.57,
      "step": 30
    },
    {
      "epoch": 0.0025452604786731802,
      "grad_norm": 0.9344307780265808,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.5108,
      "step": 31
    },
    {
      "epoch": 0.002627365655404573,
      "grad_norm": 0.6139394044876099,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.5798,
      "step": 32
    },
    {
      "epoch": 0.0027094708321359663,
      "grad_norm": 0.7699390053749084,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.7372,
      "step": 33
    },
    {
      "epoch": 0.002791576008867359,
      "grad_norm": 0.7680745720863342,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.7336,
      "step": 34
    },
    {
      "epoch": 0.002873681185598752,
      "grad_norm": 0.7378080487251282,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.8474,
      "step": 35
    },
    {
      "epoch": 0.002955786362330145,
      "grad_norm": 0.9059414863586426,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.4418,
      "step": 36
    },
    {
      "epoch": 0.002955786362330145,
      "eval_loss": 1.5442832708358765,
      "eval_runtime": 1413.5895,
      "eval_samples_per_second": 7.256,
      "eval_steps_per_second": 0.908,
      "step": 36
    },
    {
      "epoch": 0.0030378915390615376,
      "grad_norm": 0.8282952904701233,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.503,
      "step": 37
    },
    {
      "epoch": 0.003119996715792931,
      "grad_norm": 0.8562686443328857,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.5108,
      "step": 38
    },
    {
      "epoch": 0.0032021018925243237,
      "grad_norm": 0.8166694641113281,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.2283,
      "step": 39
    },
    {
      "epoch": 0.0032842070692557165,
      "grad_norm": 0.5978056788444519,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.4893,
      "step": 40
    },
    {
      "epoch": 0.0033663122459871094,
      "grad_norm": 1.075669765472412,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.3745,
      "step": 41
    },
    {
      "epoch": 0.003448417422718502,
      "grad_norm": 0.6868987679481506,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.4326,
      "step": 42
    },
    {
      "epoch": 0.0035305225994498955,
      "grad_norm": 0.67482990026474,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.6454,
      "step": 43
    },
    {
      "epoch": 0.0036126277761812883,
      "grad_norm": 0.5418546795845032,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.7307,
      "step": 44
    },
    {
      "epoch": 0.003694732952912681,
      "grad_norm": 0.8468795418739319,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.5811,
      "step": 45
    },
    {
      "epoch": 0.003694732952912681,
      "eval_loss": 1.5238127708435059,
      "eval_runtime": 1414.3795,
      "eval_samples_per_second": 7.252,
      "eval_steps_per_second": 0.907,
      "step": 45
    },
    {
      "epoch": 0.003776838129644074,
      "grad_norm": 0.5245246291160583,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.6244,
      "step": 46
    },
    {
      "epoch": 0.0038589433063754668,
      "grad_norm": 0.934582531452179,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.2247,
      "step": 47
    },
    {
      "epoch": 0.00394104848310686,
      "grad_norm": 0.669644296169281,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.6391,
      "step": 48
    },
    {
      "epoch": 0.004023153659838252,
      "grad_norm": 0.6915856003761292,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.3849,
      "step": 49
    },
    {
      "epoch": 0.004105258836569646,
      "grad_norm": 0.5015689730644226,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.54,
      "step": 50
    },
    {
      "epoch": 0.004187364013301039,
      "grad_norm": 0.6193185448646545,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.6695,
      "step": 51
    },
    {
      "epoch": 0.004269469190032431,
      "grad_norm": 0.5835232138633728,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.5131,
      "step": 52
    },
    {
      "epoch": 0.004351574366763825,
      "grad_norm": 0.4596083462238312,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.4117,
      "step": 53
    },
    {
      "epoch": 0.004433679543495217,
      "grad_norm": 0.9295161366462708,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.4409,
      "step": 54
    },
    {
      "epoch": 0.004433679543495217,
      "eval_loss": 1.5125960111618042,
      "eval_runtime": 1416.4883,
      "eval_samples_per_second": 7.241,
      "eval_steps_per_second": 0.906,
      "step": 54
    },
    {
      "epoch": 0.00451578472022661,
      "grad_norm": 0.5094868540763855,
      "learning_rate": 5e-05,
      "loss": 1.7088,
      "step": 55
    },
    {
      "epoch": 0.0045978898969580035,
      "grad_norm": 0.7837563157081604,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.25,
      "step": 56
    },
    {
      "epoch": 0.004679995073689396,
      "grad_norm": 0.7246440649032593,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.4149,
      "step": 57
    },
    {
      "epoch": 0.004762100250420789,
      "grad_norm": 0.7790331244468689,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.4097,
      "step": 58
    },
    {
      "epoch": 0.0048442054271521815,
      "grad_norm": 0.8052862286567688,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.6103,
      "step": 59
    },
    {
      "epoch": 0.004926310603883575,
      "grad_norm": 0.5868442058563232,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.6559,
      "step": 60
    },
    {
      "epoch": 0.005008415780614968,
      "grad_norm": 0.5471727848052979,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.3239,
      "step": 61
    },
    {
      "epoch": 0.0050905209573463605,
      "grad_norm": 0.48499777913093567,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.6929,
      "step": 62
    },
    {
      "epoch": 0.005172626134077754,
      "grad_norm": 0.7574016451835632,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.4487,
      "step": 63
    },
    {
      "epoch": 0.005172626134077754,
      "eval_loss": 1.5053952932357788,
      "eval_runtime": 1416.14,
      "eval_samples_per_second": 7.243,
      "eval_steps_per_second": 0.906,
      "step": 63
    },
    {
      "epoch": 0.005254731310809146,
      "grad_norm": 0.7113258242607117,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.6275,
      "step": 64
    },
    {
      "epoch": 0.005336836487540539,
      "grad_norm": 0.5914005637168884,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.6337,
      "step": 65
    },
    {
      "epoch": 0.005418941664271933,
      "grad_norm": 0.6201595067977905,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.6234,
      "step": 66
    },
    {
      "epoch": 0.005501046841003325,
      "grad_norm": 0.8037741184234619,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.2794,
      "step": 67
    },
    {
      "epoch": 0.005583152017734718,
      "grad_norm": 0.5970195531845093,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.7876,
      "step": 68
    },
    {
      "epoch": 0.005665257194466111,
      "grad_norm": 0.9002119302749634,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.466,
      "step": 69
    },
    {
      "epoch": 0.005747362371197504,
      "grad_norm": 0.6695420145988464,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.7067,
      "step": 70
    },
    {
      "epoch": 0.005829467547928897,
      "grad_norm": 0.9000733494758606,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.0297,
      "step": 71
    },
    {
      "epoch": 0.00591157272466029,
      "grad_norm": 0.6280279159545898,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.0359,
      "step": 72
    },
    {
      "epoch": 0.00591157272466029,
      "eval_loss": 1.5000574588775635,
      "eval_runtime": 1413.6191,
      "eval_samples_per_second": 7.256,
      "eval_steps_per_second": 0.908,
      "step": 72
    },
    {
      "epoch": 0.005993677901391683,
      "grad_norm": 0.7631202340126038,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.392,
      "step": 73
    },
    {
      "epoch": 0.006075783078123075,
      "grad_norm": 0.6028785109519958,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.5885,
      "step": 74
    },
    {
      "epoch": 0.0061578882548544685,
      "grad_norm": 1.0977727174758911,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.629,
      "step": 75
    },
    {
      "epoch": 0.006239993431585862,
      "grad_norm": 0.6360693573951721,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.6415,
      "step": 76
    },
    {
      "epoch": 0.006322098608317254,
      "grad_norm": 0.8207737803459167,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.3515,
      "step": 77
    },
    {
      "epoch": 0.006404203785048647,
      "grad_norm": 0.8579248785972595,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.4226,
      "step": 78
    },
    {
      "epoch": 0.00648630896178004,
      "grad_norm": 0.6944251656532288,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.4225,
      "step": 79
    },
    {
      "epoch": 0.006568414138511433,
      "grad_norm": 0.6882073879241943,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.5884,
      "step": 80
    },
    {
      "epoch": 0.006650519315242826,
      "grad_norm": 0.7763206362724304,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.4043,
      "step": 81
    },
    {
      "epoch": 0.006650519315242826,
      "eval_loss": 1.4972970485687256,
      "eval_runtime": 1412.9736,
      "eval_samples_per_second": 7.259,
      "eval_steps_per_second": 0.908,
      "step": 81
    },
    {
      "epoch": 0.006732624491974219,
      "grad_norm": 0.7503749132156372,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.6366,
      "step": 82
    },
    {
      "epoch": 0.006814729668705612,
      "grad_norm": 0.6911786198616028,
      "learning_rate": 8.548121372247918e-06,
      "loss": 1.5811,
      "step": 83
    },
    {
      "epoch": 0.006896834845437004,
      "grad_norm": 0.5811960101127625,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.6024,
      "step": 84
    },
    {
      "epoch": 0.006978940022168398,
      "grad_norm": 0.7332911491394043,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.5254,
      "step": 85
    },
    {
      "epoch": 0.007061045198899791,
      "grad_norm": 0.9922388195991516,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.1505,
      "step": 86
    },
    {
      "epoch": 0.007143150375631183,
      "grad_norm": 0.567830502986908,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.78,
      "step": 87
    },
    {
      "epoch": 0.0072252555523625766,
      "grad_norm": 0.7100740075111389,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.6115,
      "step": 88
    },
    {
      "epoch": 0.007307360729093969,
      "grad_norm": 0.710722029209137,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.4315,
      "step": 89
    },
    {
      "epoch": 0.007389465905825362,
      "grad_norm": 0.8105925917625427,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.5851,
      "step": 90
    },
    {
      "epoch": 0.007389465905825362,
      "eval_loss": 1.4960790872573853,
      "eval_runtime": 1413.3933,
      "eval_samples_per_second": 7.257,
      "eval_steps_per_second": 0.908,
      "step": 90
    },
    {
      "epoch": 0.0074715710825567555,
      "grad_norm": 0.6303733587265015,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.5841,
      "step": 91
    },
    {
      "epoch": 0.007553676259288148,
      "grad_norm": 0.7646224498748779,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.7062,
      "step": 92
    },
    {
      "epoch": 0.007635781436019541,
      "grad_norm": 0.9230985045433044,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.3967,
      "step": 93
    },
    {
      "epoch": 0.0077178866127509335,
      "grad_norm": 0.6842741966247559,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.5842,
      "step": 94
    },
    {
      "epoch": 0.007799991789482327,
      "grad_norm": 0.6308616995811462,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.5846,
      "step": 95
    },
    {
      "epoch": 0.00788209696621372,
      "grad_norm": 0.5984325408935547,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.5692,
      "step": 96
    },
    {
      "epoch": 0.007964202142945112,
      "grad_norm": 0.7772747874259949,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.3807,
      "step": 97
    },
    {
      "epoch": 0.008046307319676505,
      "grad_norm": 0.6606855392456055,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.4403,
      "step": 98
    },
    {
      "epoch": 0.008128412496407899,
      "grad_norm": 0.5787830948829651,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.7207,
      "step": 99
    },
    {
      "epoch": 0.008128412496407899,
      "eval_loss": 1.4957927465438843,
      "eval_runtime": 1413.4229,
      "eval_samples_per_second": 7.257,
      "eval_steps_per_second": 0.908,
      "step": 99
    },
    {
      "epoch": 0.008210517673139291,
      "grad_norm": 0.6355916857719421,
      "learning_rate": 0.0,
      "loss": 1.3047,
      "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": 9.607440322107802e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}